From 0ccd3ed4638f5ae10771cc74147fcfb8a92a7e2d Mon Sep 17 00:00:00 2001 From: Turtle Date: Wed, 29 Jul 2026 13:34:45 +0800 Subject: [PATCH 01/22] feat(feedback): add a /feedback command recorded through the command plane MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Register a global `/feedback` command so a user can record a remark about the session without spending a model turn. `/feedback ` acknowledges; empty or whitespace-only input returns a usage error. The plugin appends no session event of its own. `dsh-commands` already writes a `command/run` / `command/done` pair for every dispatched command, carrying the verbatim text and the settled outcome, and both records are log-only and non-surface. The feedback is therefore durably in the session log and invisible to the model without this package touching the log format. Text is never parsed, so `/feedback /plan felt slow` records that literal content. Nothing consumes the records; capture is deliberately inert. New group `packages/feedback/` — no existing group owns feedback capture. Its row raises the packages/README.md word ceiling by 10, which had no headroom; one redundant sentence there was removed to offset most of the cost. --- .../2026-07-28-feedback-command.i18n.yaml | 6 + .../feature/2026-07-28-feedback-command.md | 61 ++++++ .../feature/2026-07-28-feedback-command.zh.md | 61 ++++++ docs/config-catalog.md | 3 +- docs/module-graph.md | 9 +- packages/README.i18n.yaml | 4 +- packages/README.md | 3 +- packages/README.zh.md | 3 +- packages/examples/tui-demo/package.json | 2 + packages/examples/tui-demo/src/index.ts | 4 +- .../examples/tui-demo/tests/tui-agent.spec.ts | 27 +-- packages/examples/tui-demo/tsconfig.json | 3 + packages/feedback/README.i18n.yaml | 6 + packages/feedback/README.md | 11 ++ packages/feedback/README.zh.md | 11 ++ .../command-feedback/README.i18n.yaml | 6 + packages/feedback/command-feedback/README.md | 60 ++++++ .../feedback/command-feedback/README.zh.md | 60 ++++++ .../feedback/command-feedback/package.json | 44 +++++ .../feedback/command-feedback/src/index.ts | 40 ++++ .../command-feedback/src/invariant.ts | 30 +++ .../tests/command-feedback.spec.ts | 176 ++++++++++++++++++ .../tests/loader-composition.spec.ts | 105 +++++++++++ .../feedback/command-feedback/tsconfig.json | 24 +++ pnpm-lock.yaml | 30 +++ scripts/doc-budgets.manifest.json | 2 +- tsconfig.base.json | 2 + tsconfig.host.json | 1 + 28 files changed, 774 insertions(+), 20 deletions(-) create mode 100644 .agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-07-28-feedback-command.md create mode 100644 .agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md create mode 100644 packages/feedback/README.i18n.yaml create mode 100644 packages/feedback/README.md create mode 100644 packages/feedback/README.zh.md create mode 100644 packages/feedback/command-feedback/README.i18n.yaml create mode 100644 packages/feedback/command-feedback/README.md create mode 100644 packages/feedback/command-feedback/README.zh.md create mode 100644 packages/feedback/command-feedback/package.json create mode 100644 packages/feedback/command-feedback/src/index.ts create mode 100644 packages/feedback/command-feedback/src/invariant.ts create mode 100644 packages/feedback/command-feedback/tests/command-feedback.spec.ts create mode 100644 packages/feedback/command-feedback/tests/loader-composition.spec.ts create mode 100644 packages/feedback/command-feedback/tsconfig.json diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml new file mode 100644 index 0000000000..ba56da8945 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-28-feedback-command.md +2026-07-28-feedback-command.md: ae32d3908d568c4a511e8d9e2b8cf50569fb80bf +2026-07-28-feedback-command.zh.md: f69dbf6a50161e7f5048b76be46bc4063f9e757a diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.md b/.agents/notes/implemented/feature/2026-07-28-feedback-command.md new file mode 100644 index 0000000000..ae32d3908d --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.md @@ -0,0 +1,61 @@ +# Agent Note: `/feedback` command + +Status: implemented + +English | [中文](2026-07-28-feedback-command.zh.md) + +## Problem + +A user who notices something wrong mid-session has nowhere to put that observation. Telling the model wastes a turn, changes the conversation the user was having, and buries the remark in derived history where no later reader can find it. Writing it outside the session loses the context that makes it meaningful — which session, at which point, against which work. + +The capture surface has to be usable at the moment of annoyance, which rules out anything requiring the user to leave the TUI, and it must not perturb the run in progress: no model tokens, no turn of work, no change to the request the user is waiting on. + +## Decision + +`@deepseek-ai/dsh-command-feedback` in `packages/feedback/command-feedback/` registers one global `feedback` command over `ctx.commands`. `/feedback ` acknowledges; bare or whitespace-only input returns a direct usage error. The handler is synchronous, injects only `commands`, and has no configuration. + +The plugin appends **no session event of its own**. `dsh-commands` already writes a `command/run` / `command/done` pair for every dispatched command, carrying the command name, the verbatim unparsed suffix, the invocation source, and the settled outcome. Those records are log-only and non-surface, so the feedback lands in the session log and stays invisible to the model without this package contributing anything to the log format. The appends start persistence's ordinary eager drain; nothing forces a flush, so the acknowledgement reports that the entry is recorded in the log rather than already on disk. + +Capture is deliberately inert: nothing in this repository reads those records back. + +### Why no dedicated `session/feedback` event + +An earlier iteration declared one. It was removed because it duplicated a record the registry already writes: both would carry the same text, appended microseconds apart, and a consumer would have to decide which is authoritative. Selecting `command/run` records by command name is enough to find feedback, and it keeps this package free of the session event format entirely — no `SessionEventMap` merge, no invariant relation, no persistence catalog entry. + +The cost is that the recorded text is the raw suffix including its leading separator whitespace, and that feedback is distinguished from other commands only by name. Both are read-time concerns for a consumer that does not yet exist; neither justifies a second durable record now. + +### Why the model never sees it + +Feedback is about the session, not input to it. Injecting it as a user message would change the next model request, contradicting the requirement that recording not perturb the run, and would make the remark part of the conversation it comments on. `command/run` and `command/done` are absent from `SurfaceEventType`, so they cannot acquire a `surfaceOp` or enter derived history even by mistake. + +### Verbatim text + +Nothing is parsed. `/feedback /plan felt slow` records that literal text; the leading `/plan` is content, not a nested command. The handler trims only to decide whether any text was supplied. Control-word grammar of the kind `/goal` uses would make the corresponding literal feedback impossible to express, which is the opposite of what a capture surface is for. + +### A new group + +`packages/feedback/` is a new group because no existing one owns this. `goal/` is objective state, `session-title/` is titles, `core/` is the product spine. The group holds one package; a consumer would join it rather than forcing this one to grow. + +## Alternatives considered + +**Declare a dedicated `session/feedback` log-only event.** Implemented first, then removed. It gave feedback a first-class queryable type with pre-trimmed text, but duplicated the registry's record, added a `SessionEventMap` member and persistence-catalog entry to the frozen log format, and created two records of one act with no rule for which wins. + +**Inject feedback as a user message via `agent.inject()`.** Needs no new event type and reuses the path `/goal` mutations take. Rejected: it makes the feedback model-visible, so it enters the next request, changes the run being commented on, and consumes tokens — contradicting all three parts of the no-perturbation requirement. + +**Make `/feedback` a true no-op that records nothing.** The most literal reading of "does not do anything". Rejected because it makes the command pointless: the stated requirement was that the remark reach the session log. + +**Register the command inside an existing package** such as `packages/ui/commands`. Avoids a new group and its README pair. Rejected: `ctx.commands` is the registry, not a home for arbitrary command implementations, and the requester asked for a standalone package. + +**Parse structure out of the text** (category prefixes, severity markers). Rejected as speculative: no consumer exists to use the structure, and any control-word grammar makes the corresponding literal feedback unrecordable. Verbatim text is the widest surface a future consumer can narrow; a parsed one cannot be widened after the fact. + +**Add a model-facing tool instead of a slash command.** Rejected: feedback is a direct human observation. Routing it through the model spends a turn, lets the model paraphrase the user's words, and makes the record contingent on the model choosing to call the tool. + +## Consequences + +The TUI mounts the command unconditionally — no configuration, no dependency on the goal stack. The headless CLI, ACP, and JSON-RPC apps do not consume `ctx.commands`, so `/feedback` is unavailable there. + +This package is now small enough that its whole contract is the command definition plus one validation branch. It owns no session event, so it needs no invariant relation and cannot affect replay, forking, or crash recovery. + +Deferred: no consumer; no structured fields; no amend or withdraw, since the log is append-only and this package adds no tombstone; the recorded text is untrimmed, so a consumer trims at read time; and no explicit durability barrier, so an entry recorded immediately before a crash can be lost with any other unflushed tail. + +No snapshot accompanies this change. AGENTS.md asks for a keyless snapshot through a runnable example for product-user-visible behavior; this was skipped at the requester's explicit direction. The package tests plus a real Loader composition test over a `cordis.yml` are the whole of the evidence, alongside interactive verification in the assembled TUI. diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md b/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md new file mode 100644 index 0000000000..f69dbf6a50 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md @@ -0,0 +1,61 @@ +# Agent Note: `/feedback` 命令 + +Status: implemented + +[English](2026-07-28-feedback-command.md) | 中文 + +## 问题 + +用户在会话中途发现问题时，没有地方记下这个观察。告诉模型会浪费一个轮次、改变用户原本进行的对话，并把这条评论埋进派生历史，使后续读者无法找到它。写到会话之外则会丢失让它有意义的上下文：属于哪个会话、处于哪个时点、针对哪项工作。 + +采集接口必须能在用户产生不满的那一刻使用，因此任何需要用户离开 TUI 的方案都不可行；它还不能扰动正在进行的运行：不消耗模型 token、不产生工作轮次、不改变用户正在等待的请求。 + +## 决策 + +位于 `packages/feedback/command-feedback/` 的 `@deepseek-ai/dsh-command-feedback` 通过 `ctx.commands` 注册一个全局 `feedback` 命令。`/feedback ` 给出确认；空输入或仅含空白的输入返回直接用法错误。处理器是同步的，只注入 `commands`，且没有任何配置。 + +该插件**不追加属于自己的会话事件**。`dsh-commands` 已经为每个已分发命令写入一对 `command/run` / `command/done`，携带命令名、原样未解析的后缀、调用来源以及结算结果。这些记录仅写入日志且非 surface，因此反馈会进入会话日志并对模型保持不可见，而本包无需向日志格式贡献任何内容。这些追加会启动持久化的常规即时排空；没有任何环节强制 flush，因此确认文本报告的是条目已记录在日志中，而非已经落盘。 + +采集刻意不产生后续动作：本仓库中没有任何代码读回这些记录。 + +### 为何不设专用的 `session/feedback` 事件 + +早先的实现声明过该事件，后来将其移除，因为它重复了注册表已经写入的记录：两者会携带相同文本、相隔极短时间先后追加，而消费方还得判断以哪一条为准。依据命令名筛选 `command/run` 记录已足以找到反馈，同时让本包完全不涉及会话事件格式——没有 `SessionEventMap` 合并、没有不变式关系、没有持久化目录条目。 + +代价是被记录的文本为原始后缀，包含其前导分隔空白；且反馈仅凭命令名与其他命令相区分。两者都属于尚不存在的消费方在读取时需要处理的问题，目前都不足以支撑再增加一条持久记录。 + +### 为何模型永不看到它 + +反馈是关于会话的，而不是会话的输入。将其作为 user 消息注入会改变下一次模型请求，与「记录不得扰动运行」的要求相冲突，也会让该评论成为它所评论的那段对话的一部分。`command/run` 与 `command/done` 不属于 `SurfaceEventType`，因此即便出错也无法获得 `surfaceOp` 或进入派生历史。 + +### 原样文本 + +不做任何解析。`/feedback /plan felt slow` 记录的就是该字面文本；开头的 `/plan` 是内容，而非嵌套命令。处理器仅为判断是否提供了文本而修剪。若采用 `/goal` 那样的控制词语法，对应的字面反馈将无法表达，这与采集接口的目的正好相反。 + +### 一个新的分组 + +`packages/feedback/` 是新分组，因为现有分组都不拥有此职责：`goal/` 负责目标状态，`session-title/` 负责标题，`core/` 是产品主干。该分组目前只有一个包；未来的消费方应加入该分组，而不是迫使这个包不断膨胀。 + +## 考虑过的替代方案 + +**声明专用的 `session/feedback` 仅日志事件。** 先实现后移除。它让反馈拥有一等的可查询类型和预先修剪的文本，但重复了注册表的记录，向已冻结的日志格式新增了一个 `SessionEventMap` 成员与持久化目录条目，并使同一行为产生两条记录而没有取舍规则。 + +**通过 `agent.inject()` 将反馈作为 user 消息注入。** 无需新增事件类型，并复用 `/goal` 变更所走的路径。已否决：它会让反馈对模型可见，从而进入下一次请求、改变正被评论的那次运行并消耗 token——与「不得扰动」要求的三个方面全部冲突。 + +**让 `/feedback` 成为真正的空操作，什么都不记录。** 这是对「什么都不做」最字面的理解。已否决：这会使命令失去意义——明确的要求是让这条评论进入会话日志。 + +**在现有包中注册该命令**，例如 `packages/ui/commands`。可省去新分组及其双语 README。已否决：`ctx.commands` 是注册表，而不是任意命令实现的归属地；且请求者明确要求独立的包。 + +**从文本中解析结构**（类别前缀、严重程度标记）。已否决，属于投机设计：目前没有消费方使用该结构，而任何控制词语法都会让对应的字面反馈无法记录。原样文本是未来消费方可以收窄的最宽接口；而已被解析的接口无法事后放宽。 + +**改为提供面向模型的工具。** 已否决：反馈是人类的直接观察。经由模型会消耗一个轮次、让模型改写用户的原话，并使记录取决于模型是否选择调用该工具。 + +## 后果 + +TUI 无条件挂载该命令：没有配置，也不依赖 goal 栈。无头 CLI、ACP 和 JSON-RPC 应用不消费 `ctx.commands`，因此 `/feedback` 在那里不可用。 + +本包现已小到其全部契约就是命令定义加一个校验分支。它不拥有任何会话事件，因此无需不变式关系，也不可能影响回放、fork 或崩溃恢复。 + +延期事项：没有消费方；没有结构化字段；不支持修改或撤回，因为日志仅追加且本包不新增 tombstone；被记录的文本未修剪，需由消费方在读取时处理；且没有显式持久化屏障，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。 + +本次变更不附带 snapshot。AGENTS.md 要求面向产品用户的可见行为变更通过可运行示例附带无密钥 snapshot；此项按请求者的明确指示跳过。包测试连同一个基于真实 `cordis.yml` 的 Loader 组合测试即为全部证据，此外还有在组装后 TUI 中的交互验证。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 68343a6a19..2c2d68e934 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1994,7 +1994,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`JsonlCompression`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) · [`SessionReferenceConfig`](#deepseek-aidsh-session-reference) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`uiTui`](../packages/ui/tui/src/index.ts) -Source: [`packages/examples/tui-demo/src/index.ts:39`](../packages/examples/tui-demo/src/index.ts) +Source: [`packages/examples/tui-demo/src/index.ts:40`](../packages/examples/tui-demo/src/index.ts) ## `@deepseek-ai/dsh-user-approval` @@ -2219,6 +2219,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co - `@deepseek-ai/dsh-client-ui-theme` ([`packages/client/ui-theme/src/index.ts`](../packages/client/ui-theme/src/index.ts)) - `@deepseek-ai/dsh-client-ui-trajectory` ([`packages/client/ui-trajectory/src/index.ts`](../packages/client/ui-trajectory/src/index.ts)) - `@deepseek-ai/dsh-client-ui-workspace` ([`packages/client/ui-workspace/src/index.ts`](../packages/client/ui-workspace/src/index.ts)) +- `@deepseek-ai/dsh-command-feedback` — requires `commands` ([`packages/feedback/command-feedback/src/index.ts`](../packages/feedback/command-feedback/src/index.ts)) - `@deepseek-ai/dsh-command-goal` — requires `commands` · `goals` ([`packages/goal/command-goal/src/index.ts`](../packages/goal/command-goal/src/index.ts)) - `@deepseek-ai/dsh-commands` ([`packages/ui/commands/src/index.ts`](../packages/ui/commands/src/index.ts)) - `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts)) diff --git a/docs/module-graph.md b/docs/module-graph.md index 703f4c8abf..cc680d7c96 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -181,6 +181,9 @@ flowchart TD pkg_jsonrpc_demo["jsonrpc-demo"] pkg_tui_demo["tui-demo"] end + subgraph group_feedback["packages/feedback"] + pkg_command_feedback["command-feedback"] + end subgraph group_guard["packages/guard"] pkg_repeat_tool_guard["repeat-tool-guard"] end @@ -604,6 +607,8 @@ flowchart TD pkg_client_ui_goal --> pkg_client_ui_slots pkg_client_ui_goal --> pkg_goal pkg_client_ui_goal --> pkg_invariants + pkg_command_feedback --> pkg_commands + pkg_command_feedback --> pkg_invariants pkg_pty_local --> pkg_agent pkg_pty_local --> pkg_invariants pkg_pty_local --> pkg_pty @@ -928,6 +933,7 @@ flowchart TD pkg_tui_demo --> pkg_agent pkg_tui_demo --> pkg_agent_loop pkg_tui_demo --> pkg_agent_spine_demo + pkg_tui_demo --> pkg_command_feedback pkg_tui_demo --> pkg_command_goal pkg_tui_demo --> pkg_commands pkg_tui_demo --> pkg_invariants @@ -1069,6 +1075,7 @@ flowchart TD | [`acp`](../packages/acp/acp) | `acp` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | | [`client-ui-goal`](../packages/client/ui-goal) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants) | +| [`command-feedback`](../packages/feedback/command-feedback) | `feedback` | [`commands`](../packages/ui/commands), [`invariants`](../packages/support/invariants) | | [`pty-local`](../packages/pty/pty-local) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subprocess`](../packages/subprocess/subprocess) | | [`tasks-local`](../packages/tasks/tasks-local) | `tasks` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tasks`](../packages/tasks/tasks), [`timeout`](../packages/util/timeout) | | [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel) | `telemetry` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-telemetry`](../packages/telemetry/session-telemetry) | @@ -1116,6 +1123,6 @@ flowchart TD | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`sdk-protocol`](../packages/sdk/sdk-protocol), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/acp/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`invariants`](../packages/support/invariants), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-query`](../packages/session-query/session-query), [`session-query-sqlite`](../packages/session-query/session-query-sqlite), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | | [`cli-demo`](../packages/examples/cli-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | -| [`tui-demo`](../packages/examples/tui-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`command-goal`](../packages/goal/command-goal), [`commands`](../packages/ui/commands), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-query`](../packages/session-query/session-query), [`session-query-sqlite`](../packages/session-query/session-query-sqlite), [`session-reference`](../packages/context/session-reference), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) | +| [`tui-demo`](../packages/examples/tui-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`command-feedback`](../packages/feedback/command-feedback), [`command-goal`](../packages/goal/command-goal), [`commands`](../packages/ui/commands), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-query`](../packages/session-query/session-query), [`session-query-sqlite`](../packages/session-query/session-query-sqlite), [`session-reference`](../packages/context/session-reference), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-interaction`](../packages/ui/user-interaction), [`workspace-context`](../packages/context/workspace-context) | | [`sdk-client`](../packages/sdk/sdk-client) | `sdk` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sdk-protocol`](../packages/sdk/sdk-protocol), [`session`](../packages/core/session) | | [`subagent-dsh-sdk`](../packages/subagent/subagent-dsh-sdk) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sdk-client`](../packages/sdk/sdk-client), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subprocess`](../packages/subprocess/subprocess) | diff --git a/packages/README.i18n.yaml b/packages/README.i18n.yaml index ba5ab61b06..0510fee0b7 100644 --- a/packages/README.i18n.yaml +++ b/packages/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/README.md -README.md: 7a86e0f034264d4059e75775016d8d5d84600d8d -README.zh.md: bfcba626bea2a70f5c2aa508bb2a5b8c09bb61dc +README.md: b283af83596b738deeb6fc482fb4ff18bedf8df8 +README.zh.md: 91bc90ff05b849aaeec1ce1010a0e5a45b5a402a diff --git a/packages/README.md b/packages/README.md index 7a86e0f034..b283af8359 100644 --- a/packages/README.md +++ b/packages/README.md @@ -12,6 +12,7 @@ Packages live at `packages///`; groups are containers, while names r |---|---|---| | [`core/`](core/README.md) | Product API spine: sessions, prompts, tools, agent services, and the concrete loop | Product — stable surface | | [`goal/`](goal/README.md) | Persisted same-session goal state and lifecycle | Product — stable surface | +| [`feedback/`](feedback/README.md) | Recorded human feedback | Product — stable surface | | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface | | [`subprocess/`](subprocess/README.md) | Subprocess capability family: spawn seam + local process-tree implementation | Product — stable surface | | [`bash/`](bash/README.md) | Bash capability family: executor seam, local impl, model-facing tool | Product — stable surface | @@ -50,7 +51,7 @@ Packages live at `packages///`; groups are containers, while names r | [`support/`](support/README.md) | Support infrastructure (testkits, invariants, replay, Loader smokes) | Support — lower compatibility expectations | | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (`Branded`, Harness home/path helpers, timeout, retention) | Support — small, stable, harness-dep-free | -Groups distinguish product API from support infrastructure. New packages join an existing group; a new group updates its README and this table. +New packages join an existing group; a new group updates its README and this table. ## Dependencies diff --git a/packages/README.zh.md b/packages/README.zh.md index bfcba626be..91bc90ff05 100644 --- a/packages/README.zh.md +++ b/packages/README.zh.md @@ -12,6 +12,7 @@ |---|---|---| | [`core/`](core/README.md) | 产品 API 主干：会话、提示词、工具、agent（智能体）服务与具体循环 | 产品：稳定表面 | | [`goal/`](goal/README.md) | 持久化的同会话 goal 状态与生命周期 | 产品：稳定表面 | +| [`feedback/`](feedback/README.md) | 记录人类对会话的反馈 | 产品：稳定表面 | | [`llm/`](llm/README.md) | LLM（大语言模型）能力系列：抽象服务 + 提供方适配器 | 产品：稳定表面 | | [`subprocess/`](subprocess/README.md) | 进程管理能力系列：spawn seam + 本地进程树实现 | 产品：稳定表面 | | [`bash/`](bash/README.md) | Bash 能力系列：执行器 seam、本地实现、面向模型的工具 | 产品：稳定表面 | @@ -50,7 +51,7 @@ | [`support/`](support/README.md) | 支持基础设施（testkit、不变式、回放、Loader 冒烟测试） | 支持：兼容性预期较低 | | [`util/`](util/README.md) | 组间共享的低层零依赖工具（`Branded`、Harness home／路径辅助函数、超时、保留策略） | 支持：小型、稳定、无 harness 依赖 | -组用于区分产品 API 与支持基础设施。新包加入现有组；新组则更新其 README 和此表。 +新包加入现有组；新组则更新其 README 和此表。 ## 依赖 diff --git a/packages/examples/tui-demo/package.json b/packages/examples/tui-demo/package.json index 50145e6c29..9c48f98511 100644 --- a/packages/examples/tui-demo/package.json +++ b/packages/examples/tui-demo/package.json @@ -32,6 +32,7 @@ "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-commands": "^0.0.1", "@deepseek-ai/dsh-command-goal": "^0.0.1", + "@deepseek-ai/dsh-command-feedback": "^0.0.1", "@deepseek-ai/dsh-agent-spine-demo": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", @@ -55,6 +56,7 @@ "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-commands": "workspace:^", "@deepseek-ai/dsh-command-goal": "workspace:^", + "@deepseek-ai/dsh-command-feedback": "workspace:^", "@deepseek-ai/dsh-agent-spine-demo": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", diff --git a/packages/examples/tui-demo/src/index.ts b/packages/examples/tui-demo/src/index.ts index c60ba94b3c..9d2f6a3bdf 100644 --- a/packages/examples/tui-demo/src/index.ts +++ b/packages/examples/tui-demo/src/index.ts @@ -1,6 +1,6 @@ /** * Full-screen terminal app: the default agent spine ({@link @deepseek-ai/dsh-agent-spine-demo}) - * plus persisted goals, human commands, JSONL persistence, keyboard-backed + * plus persisted goals, human commands including `/feedback`, JSONL persistence, keyboard-backed * user interaction, and one pre-created agent whose exact session identity the * TUI drives. Swappable adapters, executors, optional tools, and HMR stay in the leaf. This Loader plugin * intentionally exposes named exports only; a default export would hide its @@ -16,6 +16,7 @@ import { SessionId } from '@deepseek-ai/dsh-session' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' import CommandService from '@deepseek-ai/dsh-commands' import * as commandGoal from '@deepseek-ai/dsh-command-goal' +import * as commandFeedback from '@deepseek-ai/dsh-command-feedback' import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo' import * as workspaceContext from '@deepseek-ai/dsh-workspace-context' import SessionPersistenceJsonl, { @@ -122,6 +123,7 @@ export function composeTuiApp(ctx: Context, config: Config): void { const goals = config.goals ?? {} const persistenceRoot = config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT ctx.plugin(CommandService) + ctx.plugin(commandFeedback) if (goals !== false) ctx.plugin(commandGoal) ctx.plugin(SessionPersistenceJsonl, { root: persistenceRoot, diff --git a/packages/examples/tui-demo/tests/tui-agent.spec.ts b/packages/examples/tui-demo/tests/tui-agent.spec.ts index f647b3d9c6..aa483e7b1b 100644 --- a/packages/examples/tui-demo/tests/tui-agent.spec.ts +++ b/packages/examples/tui-demo/tests/tui-agent.spec.ts @@ -49,6 +49,7 @@ describe('dsh-tui-demo app', () => { expect(calls.map(call => call.name)).toEqual([ 'CommandService', + 'command-feedback', 'command-goal', 'SessionPersistenceJsonl', 'session-checkpoint-policy', @@ -61,14 +62,14 @@ describe('dsh-tui-demo app', () => { 'tool-ask-user', ]) expect(calls[0]?.config).toBeUndefined() - expect(calls[2]?.config).toEqual({ root: '/tmp/tui-sessions', compression: 'none' }) - expect(calls[4]?.config).toEqual({ path: join('/tmp/tui-sessions', 'session-query.db') }) - expect(calls[5]?.config).toEqual({ + expect(calls[3]?.config).toEqual({ root: '/tmp/tui-sessions', compression: 'none' }) + expect(calls[5]?.config).toEqual({ path: join('/tmp/tui-sessions', 'session-query.db') }) + expect(calls[6]?.config).toEqual({ maxReferences: 2, candidateLimit: 7, maxReferenceBytes: 1234, }) - const tuiConfig = calls[8]?.config as { sessionId: string } + const tuiConfig = calls[9]?.config as { sessionId: string } expect(tuiConfig).toMatchObject({ welcome: 'TUI ready', resumeCommand: 'dsh --resume {session}', @@ -76,7 +77,7 @@ describe('dsh-tui-demo app', () => { maxToolOutputLines: 3, }) expect(tuiConfig.sessionId).toMatch(/^main-session-[0-9a-f-]{36}$/) - const spineConfig = calls[9]?.config as { + const spineConfig = calls[10]?.config as { readonly agents: Array> readonly goals: Record readonly maxParallelToolCalls: number @@ -109,11 +110,11 @@ describe('dsh-tui-demo app', () => { workspaceContext: false, }) - expect(calls[2]?.config).toEqual({ root: './.sessions' }) - expect(calls[5]?.config).toEqual({}) + expect(calls[3]?.config).toEqual({ root: './.sessions' }) + expect(calls[6]?.config).toEqual({}) // No configured welcome forwards none: the TUI banner sweeps in without a subtitle. - expect(calls[8]?.config).toEqual({ sessionId: 'persisted-session' }) - expect((calls[9]?.config as { agents: Array> }).agents[0]).toMatchObject({ + expect(calls[9]?.config).toEqual({ sessionId: 'persisted-session' }) + expect((calls[10]?.config as { agents: Array> }).agents[0]).toMatchObject({ id: 'main', resumeSessionId: 'persisted-session', }) @@ -129,12 +130,14 @@ describe('dsh-tui-demo app', () => { workspaceContext: false, }) - const tuiConfig = calls[7]?.config as { sessionId: string } + const tuiConfig = calls[8]?.config as { sessionId: string } expect(tuiConfig.sessionId).toMatch(/^main-session-[0-9a-f-]{36}$/) - expect((calls[8]?.config as { agents: Array> }).agents[0]) + expect((calls[9]?.config as { agents: Array> }).agents[0]) .toMatchObject({ sessionId: tuiConfig.sessionId }) expect(calls.map(call => call.name)).not.toContain('command-goal') - expect(calls[8]?.config).toMatchObject({ goals: false }) + // `/feedback` is unconditional: disabling goals must not remove it. + expect(calls.map(call => call.name)).toContain('command-feedback') + expect(calls[9]?.config).toMatchObject({ goals: false }) }) it('has the namespace-plugin export shape so the Loader keeps its schema', () => { diff --git a/packages/examples/tui-demo/tsconfig.json b/packages/examples/tui-demo/tsconfig.json index d26d5b7da6..bfd6d5554c 100644 --- a/packages/examples/tui-demo/tsconfig.json +++ b/packages/examples/tui-demo/tsconfig.json @@ -35,6 +35,9 @@ { "path": "../../goal/command-goal" }, + { + "path": "../../feedback/command-feedback" + }, { "path": "../agent-spine-demo" }, diff --git a/packages/feedback/README.i18n.yaml b/packages/feedback/README.i18n.yaml new file mode 100644 index 0000000000..eca3b1c420 --- /dev/null +++ b/packages/feedback/README.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write packages/feedback/README.md +README.md: ab7bc6f3e3a3be0c280855ff80e92c7d7a7e665e +README.zh.md: 9c050ac42aa468895c04124a76a3bce58756df0e diff --git a/packages/feedback/README.md b/packages/feedback/README.md new file mode 100644 index 0000000000..ab7bc6f3e3 --- /dev/null +++ b/packages/feedback/README.md @@ -0,0 +1,11 @@ +# feedback/ — recorded human feedback + +English | [中文](README.zh.md) + +The feedback family lets a human record a remark about the session without acting on it. Feedback is durable session-log content, separate from the model conversation and from any policy that might later read it. + +| Package | Role | ctx key | +|---|---|---| +| `command-feedback/` | Human-facing `/feedback` command recorded through the command plane | — | + +A recorded remark is log-only: it never enters the model surface or derived history, and no shipped plugin consumes it. A future consumer reads the command records from the session log rather than changing how they are captured. diff --git a/packages/feedback/README.zh.md b/packages/feedback/README.zh.md new file mode 100644 index 0000000000..9c050ac42a --- /dev/null +++ b/packages/feedback/README.zh.md @@ -0,0 +1,11 @@ +# feedback/：记录的人类反馈 + +[English](README.md) | 中文 + +feedback 家族让人类记录对会话的评价，但不据此采取任何动作。反馈属于持久的会话日志内容，与模型对话以及后续可能读取它的任何策略相互独立。 + +| 包 | 职责 | ctx 键 | +|---|---|---| +| `command-feedback/` | 面向用户的 `/feedback` 命令，通过命令平面完成记录 | 无 | + +被记录的评价仅写入日志：它绝不会进入模型 surface 或派生历史，随附插件也不会消费它。未来的消费方从会话日志中读取命令记录，而不是改变它们的采集方式。 diff --git a/packages/feedback/command-feedback/README.i18n.yaml b/packages/feedback/command-feedback/README.i18n.yaml new file mode 100644 index 0000000000..37f10ac485 --- /dev/null +++ b/packages/feedback/command-feedback/README.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write packages/feedback/command-feedback/README.md +README.md: 90992b7295536a9099766910f616e640d4b4bcfe +README.zh.md: a7c4f03997cea182ed24dcfc7f309dc3bd872d5e diff --git a/packages/feedback/command-feedback/README.md b/packages/feedback/command-feedback/README.md new file mode 100644 index 0000000000..90992b7295 --- /dev/null +++ b/packages/feedback/command-feedback/README.md @@ -0,0 +1,60 @@ +# @deepseek-ai/dsh-command-feedback + +English | [中文](README.zh.md) + +Human-facing `/feedback` capture. The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers it; the shipped TUI executes it without a model turn. + +## Command contract + +| Input | Result | +|---|---| +| `/feedback ` | Acknowledge with `Feedback recorded.` The registry's `command/run` record carries the verbatim text. | +| `/feedback` | Return a direct usage error. Whitespace-only input is treated as empty. | + +Feedback text is never parsed: no truncation, case folding, or control words. Text that looks like another command, such as `/feedback /plan felt slow`, is feedback content. Repeated commands each produce their own record; nothing is replaced or merged. + +## What this plugin does and does not do + +The command records a remark and does nothing else. It appends no session event of its own, starts no model work, and no plugin in this repository reads its records. + +The record is the command registry's own `command/run` / `command/done` pairing, which [`dsh-commands`](../../ui/commands/README.md) appends for every dispatched command. Those appends start persistence's ordinary eager drain; neither the registry nor this command forces a `session/flush`, so the acknowledgement means the entry is in the log, not that it has already reached disk. `command/run` carries the command name, the verbatim unparsed suffix, and the invocation source; the paired `command/done` carries the outcome. Both are log-only and are absent from the ordered surface, from `deriveMessages()`, and from every model request. A rejected empty input still leaves that pairing, settled as `kind: 'error'`, so no entry can be mistaken for accepted feedback. + +A dedicated `session/feedback` event was considered and rejected: it would duplicate a record the registry already writes, and a consumer can select feedback by the command name it already stores. + +## Composition + +The producer injects only `commands`. A custom app mounts the registry plus this plugin: + +```yaml +- id: commands + name: '@deepseek-ai/dsh-commands' +- id: command-feedback + name: '@deepseek-ai/dsh-command-feedback' +``` + +The TUI app mounts this command unconditionally; it has no configuration and no dependency on the persisted-goal stack. The headless CLI, ACP automation, and JSON-RPC adapters do not consume `ctx.commands`, so they do not expose it. + +## Model Experience + +### Human `/feedback` capture + +#### What the model sees + +Nothing. The slash input, the recorded text, and the acknowledgement are all absent from model requests. The registry's `command/run` and `command/done` records are log-only and carry no `surfaceOp`, so they never reach the ordered surface, `deriveMessages()`, or a system prompt. Recording feedback during a turn does not change that turn's remaining requests. + +#### Token effect + +Zero direct token effect. Neither an accepted entry nor a usage error adds model tokens, in the recording turn or any later one. + +#### KV Cache effect + +Independent of the model request path. Recording appends to the session log only, leaving an already-reusable request prefix untouched. Nothing this package contributes can invalidate cache reuse. + +## Known Limitations and Deferred Work + +- **Nothing consumes the recorded feedback** — capture is deliberately inert. There is no retrieval, aggregation, export, or reporting surface, and no model-facing tool reads it; a consumer is a separate package that selects `command/run` records by command name. +- **No structured fields** — an entry is one free-text string with no category, severity, or referenced-event link, so feedback cannot be filtered by subject without re-reading its text. +- **No amend or withdraw** — the session log is append-only and this package adds no tombstone, so a mistaken entry stays recorded and can only be superseded by a later one. +- **Untrimmed text in the record** — the handler trims only to validate; `command/run` stores the raw suffix, including its leading separator whitespace, so a consumer trims at read time. +- **No explicit durability barrier** — the acknowledgement follows the append, not a flush, so an entry recorded immediately before a crash can be lost with any other unflushed tail. Feedback is not worth forcing a synchronous disk write for; a consumer that needs one awaits `ctx.sessions.flush(session)`. +- **TUI only in the shipped apps** — the headless CLI, ACP automation, and JSON-RPC adapters do not mount `ctx.commands`, so `/feedback` is unavailable there. diff --git a/packages/feedback/command-feedback/README.zh.md b/packages/feedback/command-feedback/README.zh.md new file mode 100644 index 0000000000..a7c4f03997 --- /dev/null +++ b/packages/feedback/command-feedback/README.zh.md @@ -0,0 +1,60 @@ +# @deepseek-ai/dsh-command-feedback + +[English](README.md) | 中文 + +面向用户的 `/feedback` 采集。该插件通过 [`ctx.commands`](../../ui/commands/README.md) 注册一个全局命令，因此每个已组合的命令适配器都能发现它；随附 TUI 无需模型轮次即可执行。 + +## 命令契约 + +| 输入 | 结果 | +|---|---| +| `/feedback ` | 以 `Feedback recorded.` 确认。注册表的 `command/run` 记录携带原样文本。 | +| `/feedback` | 返回一个直接用法错误。仅含空白的输入视为空输入。 | + +反馈文本从不被解析：没有截断、大小写折叠或控制词。看起来像另一个命令的文本（例如 `/feedback /plan felt slow`）就是反馈内容。重复执行命令会各自产生自己的记录，不会替换或合并。 + +## 本插件做什么、不做什么 + +该命令记录一条评价，不做别的事。它不追加属于自己的会话事件，不启动任何模型工作，本仓库中也没有任何插件读取它的记录。 + +记录来自命令注册表自身的 `command/run` / `command/done` 配对，由 [`dsh-commands`](../../ui/commands/README.md) 为每个已分发命令追加。这些追加会启动持久化的常规即时排空；注册表与本命令都不会强制 `session/flush`，因此确认文本表示条目已进入日志，而不表示它已经落盘。`command/run` 携带命令名、原样未解析的后缀以及调用来源；配对的 `command/done` 携带结果。两者都仅写入日志，不出现在有序 surface、`deriveMessages()` 以及任何模型请求中。被拒绝的空输入仍会留下该配对，并以 `kind: 'error'` 结算，因此任何条目都不会被误认为已接受的反馈。 + +曾考虑并否决了专用的 `session/feedback` 事件：它会重复注册表已经写入的记录，而消费方可以依据注册表已存储的命令名筛选反馈。 + +## 组合 + +生产方只注入 `commands`。自定义应用挂载注册表以及本插件： + +```yaml +- id: commands + name: '@deepseek-ai/dsh-commands' +- id: command-feedback + name: '@deepseek-ai/dsh-command-feedback' +``` + +TUI 应用无条件挂载此命令；它没有配置，也不依赖持久 goal 栈。无头 CLI、ACP 自动化和 JSON-RPC 适配器不消费 `ctx.commands`，因此不会暴露它。 + +## 模型体验 + +### 用户 `/feedback` 采集 + +#### 模型看到的内容 + +无。斜杠输入、被记录的文本以及确认文本都不出现在模型请求中。注册表的 `command/run` 与 `command/done` 记录仅写入日志且不携带 `surfaceOp`，因此它们绝不会进入有序 surface、`deriveMessages()` 或系统提示词。在某个轮次中记录反馈不会改变该轮次剩余的请求。 + +#### Token 影响 + +无直接 token 影响。无论是已接受的条目还是用法错误，都不会在记录所在轮次或此后任何轮次增加模型 token。 + +#### KV Cache 影响 + +与模型请求路径无关。记录只追加到会话日志，不触碰已经可复用的请求前缀。本包贡献的任何内容都不会使缓存复用失效。 + +## 已知限制与暂缓工作 + +- **没有任何消费方读取被记录的反馈**：采集刻意不产生任何后续动作。这里没有检索、聚合、导出或报告 surface，也没有面向模型的工具读取它；消费方是另一个依据命令名筛选 `command/run` 记录的独立包。 +- **没有结构化字段**：一条条目就是一个自由文本字符串，没有类别、严重程度或关联事件链接，因此无法在不重读文本的情况下按主题过滤反馈。 +- **不支持修改或撤回**：会话日志是仅追加的，本包也不新增 tombstone，因此错误的条目会一直保留在记录中，只能由后续条目取代。 +- **记录中的文本未修剪**：处理器只为校验而修剪；`command/run` 存储原始后缀，包含其前导分隔空白，因此消费方需在读取时修剪。 +- **没有显式持久化屏障**：确认文本紧随追加而非 flush，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。为反馈强制同步写盘并不值得；需要该保证的消费方可自行等待 `ctx.sessions.flush(session)`。 +- **随附应用中只有 TUI 使用此命令**：无头 CLI、ACP 自动化和 JSON-RPC 适配器不挂载 `ctx.commands`，因此 `/feedback` 在那里不可用。 diff --git a/packages/feedback/command-feedback/package.json b/packages/feedback/command-feedback/package.json new file mode 100644 index 0000000000..6ad91d0e0d --- /dev/null +++ b/packages/feedback/command-feedback/package.json @@ -0,0 +1,44 @@ +{ + "name": "@deepseek-ai/dsh-command-feedback", + "description": "Human-facing slash command that records session feedback as a log-only event", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./invariant": { + "types": "./lib/types/invariant.d.ts", + "default": "./lib/invariant.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/invariant.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-commands": "^0.0.1", + "@deepseek-ai/dsh-invariants": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "devDependencies": { + "@cordisjs/plugin-include": "workspace:^", + "@cordisjs/plugin-loader": "workspace:^", + "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-commands": "workspace:^", + "@deepseek-ai/dsh-invariants": "workspace:^", + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/feedback/command-feedback/src/index.ts b/packages/feedback/command-feedback/src/index.ts new file mode 100644 index 0000000000..7bf7cd0853 --- /dev/null +++ b/packages/feedback/command-feedback/src/index.ts @@ -0,0 +1,40 @@ +/** + * Human-facing `/feedback` command. It records a remark about the session and + * does nothing else: the command registry's own `command/run` and + * `command/done` events are the whole record, so this plugin only validates the + * input and acknowledges it. Those appends are eager but unflushed, so the + * acknowledgement reports the entry is logged, not that it reached disk. + * @module @deepseek-ai/dsh-command-feedback + */ + +import type { Context } from 'cordis' +import type { CommandInvocation, CommandResult } from '@deepseek-ai/dsh-commands' + +export const name = 'command-feedback' +export const inject = ['commands'] + +const USAGE = 'Usage: /feedback ' + +/** + * Validate and acknowledge one feedback entry. `command/run` already carries + * the verbatim text, so no further append is needed; returning an error instead + * settles that record as `kind: 'error'` and leaves no accepted feedback. + * @param invocation - receiving agent, raw command input, and UI cancellation. + * @returns an acknowledgement, or a usage error when no feedback text was supplied. + */ +function executeFeedbackCommand(invocation: CommandInvocation): CommandResult { + if (invocation.rawInput.trim().length === 0) { + return { kind: 'error', text: `Feedback text is required. ${USAGE}` } + } + return { kind: 'success', text: 'Feedback recorded.' } +} + +/** Register the global `/feedback` command for every composed command adapter. */ +export function apply(ctx: Context): void { + ctx.commands.register({ + name: 'feedback', + description: 'record feedback about this session', + input: { hint: '' }, + handler: executeFeedbackCommand, + }) +} diff --git a/packages/feedback/command-feedback/src/invariant.ts b/packages/feedback/command-feedback/src/invariant.ts new file mode 100644 index 0000000000..72a3ead213 --- /dev/null +++ b/packages/feedback/command-feedback/src/invariant.ts @@ -0,0 +1,30 @@ +/** + * Package-owned invariant companion for `@deepseek-ai/dsh-command-feedback`. + * @module @deepseek-ai/dsh-command-feedback/invariant + */ + +/* jscpd:ignore-start */ +import type { Context } from 'cordis' +import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants' + +const PACKAGE_NAME = '@deepseek-ai/dsh-command-feedback' + +/** Cordis companion plugin name. */ +export const name = 'command-feedback-invariant' +/** Service required before the companion can reserve package ownership. */ +export const inject = ['invariants'] + +/** + * No runtime invariant: this command declares no session event and owns no state projection. The + * `command/run`/`command/done` pairing that records feedback belongs to `dsh-commands`. + */ +const install: InvariantInstaller = () => {} + +/** + * Register this package's invariant companion. + * @param ctx - Cordis context carrying the invariant service. + * @returns the installed registration's disposer after setup succeeds. + */ +export const apply = (ctx: Context): Promise<() => void> => + Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install)) +/* jscpd:ignore-end */ diff --git a/packages/feedback/command-feedback/tests/command-feedback.spec.ts b/packages/feedback/command-feedback/tests/command-feedback.spec.ts new file mode 100644 index 0000000000..362bb8ce30 --- /dev/null +++ b/packages/feedback/command-feedback/tests/command-feedback.spec.ts @@ -0,0 +1,176 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import Loader from '@cordisjs/plugin-loader' +import AgentRegistry from '@deepseek-ai/dsh-agent' +import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' +import CommandService from '@deepseek-ai/dsh-commands' +import SessionStore, { foldSurface, Session, SessionId } from '@deepseek-ai/dsh-session' +import * as commandFeedback from '@deepseek-ai/dsh-command-feedback' + +interface Harness { + readonly ctx: Context + readonly agent: Agent + readonly session: Session + readonly plugin: Awaited> +} + +/** Build a live idle agent over a store-owned session, as an app's spine does. */ +function stubAgent(ctx: Context, id: string): { agent: Agent; session: Session } { + const session = ctx.sessions.create(SessionId(id)) + let status: AgentStatus = 'idle' + const agent: Agent = { + id: session.id, + options: {}, + session, + ctx: new Context(), + get status() { return status }, + get acceptsNextStep() { return status === 'running' }, + send: () => {}, + followup: () => {}, + steer: () => {}, + inject: () => {}, + cancel() { status = 'idle' }, + whenIdle() { return Promise.resolve() }, + } + return { agent, session } +} + +/** Mount the real command registry and this producer. */ +async function harness(): Promise { + const ctx = new Context() + await ctx.plugin(CommandService) + await ctx.plugin(AgentRegistry) + await ctx.plugin(SessionStore) + const plugin = await ctx.plugin(commandFeedback) + const { agent, session } = stubAgent(ctx, `command-feedback-${Math.random()}`) + ctx.agents.register(agent) + return { ctx, agent, session, plugin } +} + +/** Execute `/feedback` through the same registry boundary as a UI adapter. */ +async function run(test: Harness, suffix = ''): Promise<{ kind: string; text?: string }> { + const settled = await test.ctx.commands.execute( + test.agent, + `/feedback${suffix}`, + new AbortController().signal, + ) + if (settled === undefined) throw new Error('feedback command was not registered') + return settled.result +} + +/** The registry's durable record of each accepted command, in log order. */ +function commandRecords(session: Session): { name: string; args: string; kind: string }[] { + const runs = session.events.filter(event => event.type === 'command/run') + return runs.map((event) => { + const done = session.events.find(item => + item.type === 'command/done' && item.data.commandId === event.data.commandId) + if (done?.type !== 'command/done') throw new Error('every command/run must be paired') + return { name: event.data.name, args: event.data.args, kind: done.data.kind } + }) +} + +describe('@deepseek-ai/dsh-command-feedback registration', () => { + it('registers one global command with Loader-safe exports and disposes it', async () => { + const test = await harness() + expect(commandFeedback.name).toBe('command-feedback') + expect(commandFeedback.inject).toEqual(['commands']) + expect('default' in commandFeedback).toBe(false) + const loader = Object.create(Loader.prototype) as Loader + expect(loader.unwrapExports(commandFeedback)).toBe(commandFeedback) + + expect(test.ctx.commands.list(test.agent)).toContainEqual({ + name: 'feedback', + description: 'record feedback about this session', + input: { hint: '' }, + }) + expect(test.ctx.commands.find(test.agent, 'feedback')).toBeDefined() + + await test.plugin.dispose() + expect(test.ctx.commands.find(test.agent, 'feedback')).toBeUndefined() + }) +}) + +describe('/feedback human command', () => { + it('acknowledges feedback and leaves the registry record as its durable trace', async () => { + const test = await harness() + await expect(run(test, ' the diff view is unreadable')).resolves.toEqual({ + kind: 'success', + text: 'Feedback recorded.', + }) + expect(commandRecords(test.session)).toEqual([ + { name: 'feedback', args: ' the diff view is unreadable', kind: 'success' }, + ]) + }) + + it('adds no event of its own beyond the registry pairing', async () => { + const test = await harness() + await run(test, ' nothing else happens') + // The whole point of the command: record and do nothing. Only the + // registry's own pairing appears, and no turn of model work starts. + expect(test.session.events.map(event => event.type)).toEqual(['command/run', 'command/done']) + }) + + it('records verbatim text, including input that looks like another command', async () => { + const test = await harness() + await run(test, ' /plan felt SLOW\n\ttwice today ') + expect(commandRecords(test.session)).toEqual([ + { name: 'feedback', args: ' /plan felt SLOW\n\ttwice today ', kind: 'success' }, + ]) + }) + + it('records each entry separately without replacing earlier ones', async () => { + const test = await harness() + await run(test, ' first') + await run(test, ' second') + expect(commandRecords(test.session).map(record => record.args)).toEqual([' first', ' second']) + }) + + it('records concurrent submissions in dispatch order', async () => { + const test = await harness() + const signal = new AbortController().signal + // The shipped TUI dispatches commands fire-and-forget. + const settled = await Promise.all([ + test.ctx.commands.execute(test.agent, '/feedback first', signal), + test.ctx.commands.execute(test.agent, '/feedback second', signal), + ]) + expect(settled.map(item => item?.result)).toEqual([ + { kind: 'success', text: 'Feedback recorded.' }, + { kind: 'success', text: 'Feedback recorded.' }, + ]) + expect(commandRecords(test.session).map(record => record.args)).toEqual([' first', ' second']) + }) + + it('keeps every recorded event off the model surface and out of derived history', async () => { + const test = await harness() + await run(test, ' invisible to the model') + for (const event of test.session.events) { + expect('surfaceOp' in event).toBe(false) + expect(test.session.deriveEventMessage(event)).toBeNull() + } + expect(foldSurface(test.session.events).nodes).toEqual([]) + expect(test.session.surface.nodes).toEqual([]) + expect(test.session.deriveMessages()).toEqual([]) + }) + + it('rejects empty and whitespace-only input as a failed command record', async () => { + const test = await harness() + const expected = { + kind: 'error', + text: 'Feedback text is required. Usage: /feedback ', + } + await expect(run(test)).resolves.toEqual(expected) + await expect(run(test, ' \n\t ')).resolves.toEqual(expected) + // Rejected input still leaves the registry's own pairing, settled as an + // error, so no entry is mistaken for accepted feedback. + expect(commandRecords(test.session).map(record => record.kind)).toEqual(['error', 'error']) + }) + + it('records nothing when dispatch rejects an already-cancelled request', async () => { + const test = await harness() + const controller = new AbortController() + controller.abort(new Error('user cancelled the command')) + await expect(test.ctx.commands.execute(test.agent, '/feedback too late', controller.signal)) + .rejects.toThrow('user cancelled the command') + expect(test.session.events).toEqual([]) + }) +}) diff --git a/packages/feedback/command-feedback/tests/loader-composition.spec.ts b/packages/feedback/command-feedback/tests/loader-composition.spec.ts new file mode 100644 index 0000000000..9aa206f9ad --- /dev/null +++ b/packages/feedback/command-feedback/tests/loader-composition.spec.ts @@ -0,0 +1,105 @@ +import { mkdtemp, rm, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { pathToFileURL } from 'node:url' +import { afterEach, describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import Loader from '@cordisjs/plugin-loader' +import Include from '@cordisjs/plugin-include' +import AgentRegistry from '@deepseek-ai/dsh-agent' +import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' +import CommandService from '@deepseek-ai/dsh-commands' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' +import * as CommandFeedback from '@deepseek-ai/dsh-command-feedback' + +let root: string | undefined +let context: Context | undefined + +afterEach(async () => { + await context?.fiber.dispose() + context = undefined + if (root !== undefined) await rm(root, { recursive: true, force: true }) + root = undefined +}) + +/** Register one idle agent over a store-owned session, as an app's spine does. */ +function agent(ctx: Context): Agent { + const scope = ctx.plugin(() => {}) + const id = SessionId('feedback-loader-agent') + const session = ctx.sessions.create(id) + let status: AgentStatus = 'idle' + const value: Agent = { + id, + options: {}, + session, + ctx: scope.ctx, + get status() { return status }, + get acceptsNextStep() { return status === 'running' }, + send: () => {}, + followup: () => {}, + steer: () => {}, + inject: () => {}, + cancel() { status = 'idle' }, + whenIdle: () => Promise.resolve(), + } + ctx.agents.register(value) + return value +} + +describe('/feedback real Loader composition through cordis.yml', () => { + it('boots cordis.yml and records feedback without model-visible output', async () => { + root = await mkdtemp(join(tmpdir(), 'dsh-command-feedback-loader-')) + const configPath = join(root, 'cordis.yml') + await writeFile(configPath, [ + "- name: '@deepseek-ai/dsh-agent'", + "- name: '@deepseek-ai/dsh-session'", + "- name: '@deepseek-ai/dsh-commands'", + "- name: '@deepseek-ai/dsh-command-feedback'", + '', + ].join('\n')) + + context = new Context() + context.baseUrl = pathToFileURL(root).href + '/' + await context.plugin(Loader) + context.loader.builtins.include = Include + const modules = new Map([ + ['@deepseek-ai/dsh-agent', AgentRegistry], + ['@deepseek-ai/dsh-session', SessionStore], + ['@deepseek-ai/dsh-commands', CommandService], + ['@deepseek-ai/dsh-command-feedback', CommandFeedback], + ]) + context.loader.internal = { + version: 'v2', + async import(specifier: string) { + if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`) + return modules.get(specifier) + }, + } as unknown as NonNullable + await context.loader.create({ name: 'cordis:include', config: { path: pathToFileURL(configPath).href } }) + await context.loader.await() + + const owner = agent(context) + const signal = new AbortController().signal + + // Discoverable through the composed registry, as a UI adapter finds it. + expect(context.commands.list(owner).map(command => command.name)).toContain('feedback') + + const accepted = await context.commands.execute(owner, '/feedback the diff view is unreadable', signal) + expect(accepted?.result).toEqual({ kind: 'success', text: 'Feedback recorded.' }) + const rejected = await context.commands.execute(owner, '/feedback', signal) + expect(rejected?.result).toEqual({ + kind: 'error', + text: 'Feedback text is required. Usage: /feedback ', + }) + + // The command records itself through the registry and does nothing else. + expect(owner.session.events.map(event => event.type)) + .toEqual(['command/run', 'command/done', 'command/run', 'command/done']) + const run = owner.session.events.find(event => event.type === 'command/run') + expect(run?.type === 'command/run' && run.data.args).toBe(' the diff view is unreadable') + + // Nothing reached the model. + expect(owner.session.deriveMessages()).toEqual([]) + expect(owner.session.surface.nodes).toEqual([]) + }) +}) diff --git a/packages/feedback/command-feedback/tsconfig.json b/packages/feedback/command-feedback/tsconfig.json new file mode 100644 index 0000000000..6a27b54d3a --- /dev/null +++ b/packages/feedback/command-feedback/tsconfig.json @@ -0,0 +1,24 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../ui/commands" + }, + { + "path": "../../support/invariants" + } + ] +} diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 18cb1ec0d1..38e1c9eef5 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -2303,6 +2303,9 @@ importers: '@deepseek-ai/dsh-agent-spine-demo': specifier: workspace:^ version: link:../agent-spine-demo + '@deepseek-ai/dsh-command-feedback': + specifier: workspace:^ + version: link:../../feedback/command-feedback '@deepseek-ai/dsh-command-goal': specifier: workspace:^ version: link:../../goal/command-goal @@ -2358,6 +2361,33 @@ importers: specifier: ^3.17.0 version: 3.18.0 + packages/feedback/command-feedback: + devDependencies: + '@cordisjs/plugin-include': + specifier: workspace:^ + version: link:../../../vendor/include + '@cordisjs/plugin-loader': + specifier: workspace:^ + version: link:../../../vendor/loader + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-commands': + specifier: workspace:^ + version: link:../../ui/commands + '@deepseek-ai/dsh-invariants': + specifier: workspace:^ + version: link:../../support/invariants + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) + packages/fs/fs: devDependencies: '@deepseek-ai/dsh-brand': diff --git a/scripts/doc-budgets.manifest.json b/scripts/doc-budgets.manifest.json index 42198d4eea..7a67ce8bac 100644 --- a/scripts/doc-budgets.manifest.json +++ b/scripts/doc-budgets.manifest.json @@ -7,5 +7,5 @@ "docs/testing.md": 1100, "examples/AGENTS.md": 310, "packages/AGENTS.md": 675, - "packages/README.md": 870 + "packages/README.md": 880 } diff --git a/tsconfig.base.json b/tsconfig.base.json index 00c19c4b8c..b87f867107 100644 --- a/tsconfig.base.json +++ b/tsconfig.base.json @@ -72,6 +72,7 @@ "./packages/compact/*/src/invariant.ts", "./packages/context/*/src/invariant.ts", "./packages/goal/*/src/invariant.ts", + "./packages/feedback/*/src/invariant.ts", "./packages/guard/*/src/invariant.ts", "./packages/plan/*/src/invariant.ts", "./packages/subagent/*/src/invariant.ts", @@ -161,6 +162,7 @@ "./packages/compact/*/src", "./packages/context/*/src", "./packages/goal/*/src", + "./packages/feedback/*/src", "./packages/guard/*/src", "./packages/plan/*/src", "./packages/subagent/*/src", diff --git a/tsconfig.host.json b/tsconfig.host.json index e2112b7f6a..5c1a7488c0 100644 --- a/tsconfig.host.json +++ b/tsconfig.host.json @@ -83,6 +83,7 @@ { "path": "./packages/goal/tool-goal" }, { "path": "./packages/goal/goal-session" }, { "path": "./packages/goal/command-goal" }, + { "path": "./packages/feedback/command-feedback" }, { "path": "./packages/context/time-context" }, { "path": "./packages/context/session-reference" }, { "path": "./packages/ui/user-interaction" }, From eb6fa864813f6513a037e79b4dbacf9d4477338d Mon Sep 17 00:00:00 2001 From: Turtle Date: Wed, 29 Jul 2026 21:33:53 +0800 Subject: [PATCH 02/22] fix(feedback): keep payload in feedback event --- .../2026-07-28-feedback-command.i18n.yaml | 4 +- .../feature/2026-07-28-feedback-command.md | 20 +++--- .../feature/2026-07-28-feedback-command.zh.md | 20 +++--- ...ssion-projection-and-command-log.i18n.yaml | 4 +- ...7-27-session-projection-and-command-log.md | 4 +- ...7-session-projection-and-command-log.zh.md | 4 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/commands.i18n.yaml | 6 +- docs/core-data-structures/commands.md | 6 ++ docs/core-data-structures/commands.zh.md | 6 ++ docs/event-producer-consumer.md | 2 +- docs/persistence-catalog.md | 23 +++++-- .../client/connection/src/client/fixture.ts | 12 ++-- .../src/client/sessions/conversation.ts | 5 +- .../src/client/sessions/fold-adapter.ts | 4 +- packages/client/runtime/tests/event-script.ts | 2 + .../client/runtime/tests/fold-adapter.spec.ts | 8 +++ .../src/client/chat/GenericCommandCard.tsx | 4 +- .../cordis/tool-cordis/src/api-catalog.ts | 2 +- packages/feedback/README.i18n.yaml | 4 +- packages/feedback/README.md | 4 +- packages/feedback/README.zh.md | 4 +- .../command-feedback/README.i18n.yaml | 4 +- packages/feedback/command-feedback/README.md | 17 +++-- .../feedback/command-feedback/README.zh.md | 17 +++-- .../feedback/command-feedback/package.json | 3 +- .../feedback/command-feedback/src/index.ts | 39 +++++++++--- .../command-feedback/src/invariant.ts | 4 +- .../tests/command-feedback.spec.ts | 62 +++++++++++-------- .../tests/loader-composition.spec.ts | 9 ++- .../feedback/command-feedback/tsconfig.json | 3 + packages/plan/plan-mode/README.i18n.yaml | 4 +- packages/plan/plan-mode/README.md | 2 +- packages/plan/plan-mode/README.zh.md | 2 +- packages/plan/plan-mode/src/index.ts | 1 + .../plan/plan-mode/tests/projection.spec.ts | 11 +++- packages/ui/commands/README.i18n.yaml | 4 +- packages/ui/commands/README.md | 4 +- packages/ui/commands/README.zh.md | 4 +- packages/ui/commands/src/index.ts | 17 ++++- packages/ui/commands/tests/commands.spec.ts | 19 ++++++ 42 files changed, 248 insertions(+), 130 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml index ba56da8945..7a429953d8 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-28-feedback-command.md -2026-07-28-feedback-command.md: ae32d3908d568c4a511e8d9e2b8cf50569fb80bf -2026-07-28-feedback-command.zh.md: f69dbf6a50161e7f5048b76be46bc4063f9e757a +2026-07-28-feedback-command.md: 1c093d0e37eb72dc66e3c5569bd642557dde56a1 +2026-07-28-feedback-command.zh.md: 300946a71ac7485a4bc787dd70ae5357147627f3 diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.md b/.agents/notes/implemented/feature/2026-07-28-feedback-command.md index ae32d3908d..1c093d0e37 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.md +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.md @@ -14,15 +14,15 @@ The capture surface has to be usable at the moment of annoyance, which rules out `@deepseek-ai/dsh-command-feedback` in `packages/feedback/command-feedback/` registers one global `feedback` command over `ctx.commands`. `/feedback ` acknowledges; bare or whitespace-only input returns a direct usage error. The handler is synchronous, injects only `commands`, and has no configuration. -The plugin appends **no session event of its own**. `dsh-commands` already writes a `command/run` / `command/done` pair for every dispatched command, carrying the command name, the verbatim unparsed suffix, the invocation source, and the settled outcome. Those records are log-only and non-surface, so the feedback lands in the session log and stays invisible to the model without this package contributing anything to the log format. The appends start persistence's ordinary eager drain; nothing forces a flush, so the acknowledgement reports that the entry is recorded in the log rather than already on disk. +The package declares the log-only `feedback/record { text }` session event and exports `recordFeedback(session, text)` as its command-independent producer. The producer discards surrounding whitespace, rejects an empty result, and appends exactly one event. `/feedback` delegates to it, so another UI, hook, or host integration can record the same domain fact without constructing a slash command. -Capture is deliberately inert: nothing in this repository reads those records back. +`dsh-commands` still writes its `command/run` / `command/done` lifecycle pair around `/feedback`, but this command sets `recordInput: false`. Its `command/run` therefore carries the command identity and source without `args`; the feedback text exists only in `feedback/record`, while `command/done` carries the acknowledgement outcome. All three records are log-only and non-surface. Their appends start persistence's ordinary eager drain; nothing forces a flush, so acknowledgement reports that the feedback is in the log rather than already on disk. -### Why no dedicated `session/feedback` event +Capture is deliberately inert: nothing in this repository reads `feedback/record`. -An earlier iteration declared one. It was removed because it duplicated a record the registry already writes: both would carry the same text, appended microseconds apart, and a consumer would have to decide which is authoritative. Selecting `command/run` records by command name is enough to find feedback, and it keeps this package free of the session event format entirely — no `SessionEventMap` merge, no invariant relation, no persistence catalog entry. +### Why feedback owns an event -The cost is that the recorded text is the raw suffix including its leading separator whitespace, and that feedback is distinguished from other commands only by name. Both are read-time concerns for a consumer that does not yet exist; neither justifies a second durable record now. +Feedback is a domain fact, while `/feedback` is one trigger. Keeping the only payload in `feedback/record` lets later triggers use the same event and lets consumers select feedback without depending on command names or parsing command lifecycle records. Omitting `command/run.args` for this definition avoids two authoritative-looking copies of one human remark. ### Why the model never sees it @@ -30,7 +30,7 @@ Feedback is about the session, not input to it. Injecting it as a user message w ### Verbatim text -Nothing is parsed. `/feedback /plan felt slow` records that literal text; the leading `/plan` is content, not a nested command. The handler trims only to decide whether any text was supplied. Control-word grammar of the kind `/goal` uses would make the corresponding literal feedback impossible to express, which is the opposite of what a capture surface is for. +Surrounding whitespace is discarded, but nothing else is parsed. `/feedback /plan felt slow` records `/plan felt slow`; the leading `/plan` is content, not a nested command. Control-word grammar of the kind `/goal` uses would make the corresponding literal feedback impossible to express, which is the opposite of what a capture surface is for. ### A new group @@ -38,7 +38,9 @@ Nothing is parsed. `/feedback /plan felt slow` records that literal text; the le ## Alternatives considered -**Declare a dedicated `session/feedback` log-only event.** Implemented first, then removed. It gave feedback a first-class queryable type with pre-trimmed text, but duplicated the registry's record, added a `SessionEventMap` member and persistence-catalog entry to the frozen log format, and created two records of one act with no rule for which wins. +**Use `command/run` as the feedback record.** Rejected because feedback would then be coupled to one trigger and consumers would have to identify a domain fact by command name. A non-command producer could not create the same record without pretending to execute a command. + +**Store the text in both `feedback/record` and `command/run.args`.** Rejected because one act would have two payload copies with no useful distinction. `recordInput: false` preserves the generic lifecycle while leaving the domain event authoritative. **Inject feedback as a user message via `agent.inject()`.** Needs no new event type and reuses the path `/goal` mutations take. Rejected: it makes the feedback model-visible, so it enters the next request, changes the run being commented on, and consumes tokens — contradicting all three parts of the no-perturbation requirement. @@ -54,8 +56,8 @@ Nothing is parsed. `/feedback /plan felt slow` records that literal text; the le The TUI mounts the command unconditionally — no configuration, no dependency on the goal stack. The headless CLI, ACP, and JSON-RPC apps do not consume `ctx.commands`, so `/feedback` is unavailable there. -This package is now small enough that its whole contract is the command definition plus one validation branch. It owns no session event, so it needs no invariant relation and cannot affect replay, forking, or crash recovery. +The package owns one independent append-only event with no cross-event or mutable-data relation for an invariant companion to check. The event follows the session log's existing replay, fork, persistence, and crash-tail behavior. -Deferred: no consumer; no structured fields; no amend or withdraw, since the log is append-only and this package adds no tombstone; the recorded text is untrimmed, so a consumer trims at read time; and no explicit durability barrier, so an entry recorded immediately before a crash can be lost with any other unflushed tail. +Deferred: no consumer; no structured fields; no amend or withdraw, since the log is append-only and this package adds no tombstone; and no explicit durability barrier, so an entry recorded immediately before a crash can be lost with any other unflushed tail. No snapshot accompanies this change. AGENTS.md asks for a keyless snapshot through a runnable example for product-user-visible behavior; this was skipped at the requester's explicit direction. The package tests plus a real Loader composition test over a `cordis.yml` are the whole of the evidence, alongside interactive verification in the assembled TUI. diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md b/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md index f69dbf6a50..300946a71a 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md @@ -14,15 +14,15 @@ Status: implemented 位于 `packages/feedback/command-feedback/` 的 `@deepseek-ai/dsh-command-feedback` 通过 `ctx.commands` 注册一个全局 `feedback` 命令。`/feedback ` 给出确认；空输入或仅含空白的输入返回直接用法错误。处理器是同步的，只注入 `commands`，且没有任何配置。 -该插件**不追加属于自己的会话事件**。`dsh-commands` 已经为每个已分发命令写入一对 `command/run` / `command/done`，携带命令名、原样未解析的后缀、调用来源以及结算结果。这些记录仅写入日志且非 surface，因此反馈会进入会话日志并对模型保持不可见，而本包无需向日志格式贡献任何内容。这些追加会启动持久化的常规即时排空；没有任何环节强制 flush，因此确认文本报告的是条目已记录在日志中，而非已经落盘。 +本包（package）声明仅写入日志的 `feedback/record { text }` 会话事件，并导出 `recordFeedback(session, text)`，作为不依赖命令的生产方。该生产方丢弃前后空白，拒绝空结果，并且恰好追加一个事件。`/feedback` 委托给它，因此其他 UI、钩子或 host 集成无需构造斜杠命令也能记录同一个领域事实。 -采集刻意不产生后续动作：本仓库中没有任何代码读回这些记录。 +`dsh-commands` 仍会围绕 `/feedback` 写入 `command/run` / `command/done` 生命周期配对，但该命令设置了 `recordInput: false`。因此，它的 `command/run` 携带命令标识与来源，但不携带 `args`；反馈文本只存在于 `feedback/record` 中，而 `command/done` 携带确认结果。三个记录都仅写入日志且非 surface。它们的追加会启动持久化的常规即时排空；没有任何环节强制 flush，因此确认文本报告的是反馈已进入日志，而非已经落盘。 -### 为何不设专用的 `session/feedback` 事件 +采集刻意不产生后续动作：本仓库中没有任何代码读取 `feedback/record`。 -早先的实现声明过该事件，后来将其移除，因为它重复了注册表已经写入的记录：两者会携带相同文本、相隔极短时间先后追加，而消费方还得判断以哪一条为准。依据命令名筛选 `command/run` 记录已足以找到反馈，同时让本包完全不涉及会话事件格式——没有 `SessionEventMap` 合并、没有不变式关系、没有持久化目录条目。 +### 为何反馈拥有自己的事件 -代价是被记录的文本为原始后缀，包含其前导分隔空白；且反馈仅凭命令名与其他命令相区分。两者都属于尚不存在的消费方在读取时需要处理的问题，目前都不足以支撑再增加一条持久记录。 +反馈是领域事实，而 `/feedback` 是一种触发方式。只把载荷保存在 `feedback/record` 中，既让后续触发方式可以使用同一个事件，也让消费方无需依赖命令名或解析命令生命周期记录即可筛选反馈。在该定义中省略 `command/run.args`，可避免同一条人类评价出现两个看起来都具有权威性的副本。 ### 为何模型永不看到它 @@ -30,7 +30,7 @@ Status: implemented ### 原样文本 -不做任何解析。`/feedback /plan felt slow` 记录的就是该字面文本；开头的 `/plan` 是内容，而非嵌套命令。处理器仅为判断是否提供了文本而修剪。若采用 `/goal` 那样的控制词语法，对应的字面反馈将无法表达，这与采集接口的目的正好相反。 +前后空白会被丢弃，但除此之外不做解析。`/feedback /plan felt slow` 记录 `/plan felt slow`；开头的 `/plan` 是内容，而非嵌套命令。若采用 `/goal` 那样的控制词语法，对应的字面反馈将无法表达，这与采集接口的目的正好相反。 ### 一个新的分组 @@ -38,7 +38,9 @@ Status: implemented ## 考虑过的替代方案 -**声明专用的 `session/feedback` 仅日志事件。** 先实现后移除。它让反馈拥有一等的可查询类型和预先修剪的文本，但重复了注册表的记录，向已冻结的日志格式新增了一个 `SessionEventMap` 成员与持久化目录条目，并使同一行为产生两条记录而没有取舍规则。 +**使用 `command/run` 作为反馈记录。** 已否决，因为这会将反馈与一种触发方式耦合，消费方还必须通过命令名识别领域事实。非命令生产方若不伪装成执行命令，就无法创建相同记录。 + +**同时在 `feedback/record` 与 `command/run.args` 中存储文本。** 已否决，因为同一行为会产生两个没有实质区别的载荷副本。`recordInput: false` 保留通用生命周期，同时让领域事件保持权威性。 **通过 `agent.inject()` 将反馈作为 user 消息注入。** 无需新增事件类型，并复用 `/goal` 变更所走的路径。已否决：它会让反馈对模型可见，从而进入下一次请求、改变正被评论的那次运行并消耗 token——与「不得扰动」要求的三个方面全部冲突。 @@ -54,8 +56,8 @@ Status: implemented TUI 无条件挂载该命令：没有配置，也不依赖 goal 栈。无头 CLI、ACP 和 JSON-RPC 应用不消费 `ctx.commands`，因此 `/feedback` 在那里不可用。 -本包现已小到其全部契约就是命令定义加一个校验分支。它不拥有任何会话事件，因此无需不变式关系，也不可能影响回放、fork 或崩溃恢复。 +本包拥有一个独立的仅追加事件，不存在跨事件关系或可变数据关系可供不变式伴生插件检查。该事件遵循会话日志现有的回放、fork、持久化和崩溃尾部行为。 -延期事项：没有消费方；没有结构化字段；不支持修改或撤回，因为日志仅追加且本包不新增 tombstone；被记录的文本未修剪，需由消费方在读取时处理；且没有显式持久化屏障，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。 +延期事项：没有消费方；没有结构化字段；不支持修改或撤回，因为日志仅追加且本包不新增 tombstone；且没有显式持久化屏障，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。 本次变更不附带 snapshot。AGENTS.md 要求面向产品用户的可见行为变更通过可运行示例附带无密钥 snapshot；此项按请求者的明确指示跳过。包测试连同一个基于真实 `cordis.yml` 的 Loader 组合测试即为全部证据，此外还有在组装后 TUI 中的交互验证。 diff --git a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml index 8f720e33b5..49c96e63a3 100644 --- a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml +++ b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md -2026-07-27-session-projection-and-command-log.md: 6a073c956c27bbfc65cff2d4f44ca12023df0cd5 -2026-07-27-session-projection-and-command-log.zh.md: 500f07968db049e4a174ff3b7a075bfe095283db +2026-07-27-session-projection-and-command-log.md: 6ffdae7df9e908356c972f077d66b831f3b6a1ff +2026-07-27-session-projection-and-command-log.zh.md: d2a40fb72245df413c7790932a41ddea3be7902d diff --git a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md index 6a073c956c..6ffdae7df9 100644 --- a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md +++ b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.md @@ -115,11 +115,11 @@ The one existing violation of "no hooks through inject" — `DetailsInjected.use Two log-only (non-surface, model-invisible) events, mirroring the `tool/call`/`tool/result` pairing: ```ts ignore-check -'command/run': { commandId: string; name: string; args: string; source: CommandSource } +'command/run': { commandId: string; name: string; args?: string; source: CommandSource } 'command/done': { commandId: string; kind: 'success' | 'error'; text?: string } ``` -The host command executor (`packages/ui/commands`) appends `command/run` before invoking the handler and `command/done` at settlement — direct standalone appends on the receiving agent's session, in the same shape as every other plugin-owned log-only event after the [synthetic-turn removal](../../implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md): no turn wraps them (turns describe model-loop executions only), persistence drains them at ordinary checkpoints, and the commands package's own invariant companion enforces the run/done pairing. The payload is structured — `name` and `args` are the parser's own split (`parseCommand`'s name and rawInput), so a consumer (a projection unit folding its own command records, a rich command card) never re-parses a line. `text` is the handler's verbatim outcome — factual data of the same nature as `tool/result.content`, not presentation (how it is laid out remains client-computed at render time, satisfying the "presentation never enters the log" red line). Domains that want the model to know the outcome keep doing what they do today (plan's narration, goal's inject) — that is a domain decision, unchanged. +The host command executor (`packages/ui/commands`) appends `command/run` before invoking the handler and `command/done` at settlement — direct standalone appends on the receiving agent's session, in the same shape as every other plugin-owned log-only event after the [synthetic-turn removal](../../implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md): no turn wraps them (turns describe model-loop executions only), persistence drains them at ordinary checkpoints, and the commands package's own invariant companion enforces the run/done pairing. The payload is structured — `name` and, by default, `args` are the parser's own split (`parseCommand`'s name and rawInput), so a consumer (a projection unit folding its own command records, a rich command card) never re-parses a line. A definition sets `recordInput: false` when its authoritative domain event owns the payload; `command/run` then omits `args` rather than duplicating it. `text` is the handler's verbatim outcome — factual data of the same nature as `tool/result.content`, not presentation (how it is laid out remains client-computed at render time, satisfying the "presentation never enters the log" red line). Domains that want the model to know the outcome keep doing what they do today (plan's narration, goal's inject) — that is a domain decision, unchanged. Because committed events broadcast on the mux stream, refresh persistence, multi-tab sync, and fork/resume recovery all come for free. The `command.execute` RPC degrades to admission — `{ matched, commandId? }`: whether the line resolved, and the minted pairing id when it did, so the issuing client can correlate its request with the flow node the lifecycle events produce. The one-shot notice channel (`runDetached` → `noticeFor`) is retired. diff --git a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md index 500f07968d..d2a40fb722 100644 --- a/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md +++ b/.agents/notes/proposed/architecture/2026-07-27-session-projection-and-command-log.zh.md @@ -115,11 +115,11 @@ type UseProjection = { 两个仅日志（非 surface、模型不可见）事件，镜像 `tool/call`/`tool/result` 的配对： ```ts ignore-check -'command/run': { commandId: string; name: string; args: string; source: CommandSource } +'command/run': { commandId: string; name: string; args?: string; source: CommandSource } 'command/done': { commandId: string; kind: 'success' | 'error'; text?: string } ``` -host 侧命令执行器（`packages/ui/commands`）在调用处理器前追加 `command/run`，在结算时追加 `command/done`——在接收 agent 的会话上直接独立追加，与[合成轮次移除](../../implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md)之后所有插件自有 log-only 事件同一形状：没有轮次包裹它们（轮次只描述模型循环执行），持久化在常规检查点排空它们，run/done 配对由 commands 包自己的 invariant 伴生插件把守。载荷是结构化的——`name` 与 `args` 就是解析器自己的切分（`parseCommand` 的 name 与 rawInput），因此消费方（折叠自己命令记录的投影单元、富命令卡片）永远无需重新解析行文本。`text` 是处理器的原样结果——与 `tool/result.content` 同一性质的事实数据，不是呈现（版式如何编排仍由客户端在渲染时计算，满足「呈现永不入日志」这条红线）。想让模型知道结果的领域继续做它们今天在做的事（plan 的旁白、goal 的注入）——那是领域自己的决定，保持不变。 +host 侧命令执行器（`packages/ui/commands`）在调用处理器前追加 `command/run`，在结算时追加 `command/done`——在接收 agent 的会话上直接独立追加，与[合成轮次移除](../../implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md)之后所有插件自有 log-only 事件同一形状：没有轮次包裹它们（轮次只描述模型循环执行），持久化在常规检查点排空它们，run/done 配对由 commands 包自己的 invariant 伴生插件把守。载荷是结构化的——`name` 以及默认携带的 `args` 来自解析器自己的切分（`parseCommand` 的 name 与 rawInput），因此消费方（折叠自己命令记录的投影单元、富命令卡片）永远无需重新解析行文本。当载荷由权威领域事件持有时，命令定义会设置 `recordInput: false`；此时 `command/run` 省略 `args`，而不是重复该载荷。`text` 是处理器的原样结果——与 `tool/result.content` 同一性质的事实数据，不是呈现（版式如何编排仍由客户端在渲染时计算，满足「呈现永不入日志」这条红线）。想让模型知道结果的领域继续做它们今天在做的事（plan 的旁白、goal 的注入）——那是领域自己的决定，保持不变。 由于已提交事件会在 mux 流上广播，刷新后仍在、多标签页同步、fork/恢复后可还原这三件事随之全部自动获得。`command.execute` RPC 退化为准入判定——`{ matched, commandId? }`：该行是否匹配命中，以及命中时新铸的配对 id，发起命令的客户端据此把自己的请求与生命周期事件产出的 flow 节点关联起来。一次性通知通道（`runDetached` → `noticeFor`）就此下线。 diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 967241fbf6..54291934fd 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -420,7 +420,7 @@ A command was registered or unregistered. This is an unfiltered registry notific 'commands/change'(): void ``` -Source: [`packages/ui/commands/src/index.ts:154`](../../packages/ui/commands/src/index.ts) +Source: [`packages/ui/commands/src/index.ts:161`](../../packages/ui/commands/src/index.ts) ## `domain/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e0dd17fa02..ffd80cc6e5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -442,7 +442,7 @@ async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise CommandResult | Promise } diff --git a/docs/core-data-structures/commands.zh.md b/docs/core-data-structures/commands.zh.md index 1a51305df3..f90e7c93c4 100644 --- a/docs/core-data-structures/commands.zh.md +++ b/docs/core-data-structures/commands.zh.md @@ -31,6 +31,12 @@ interface CommandDefinition { readonly description: string /** Optional free-form input hint advertised to capable clients. */ readonly input?: CommandInputDescriptor + /** + * Whether `command/run` records `rawInput`. Defaults to true. A command + * whose domain event owns the payload sets this false to avoid duplicating + * that payload in the session log. + */ + readonly recordInput?: boolean /** Execute against the receiving agent without sending the command to the model. */ readonly handler: (invocation: CommandInvocation) => CommandResult | Promise } diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 9d66b52bfb..a169747843 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -24,7 +24,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/step` | `serial` | [`packages/core/agent/src/types.ts:326`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`plan-mode`](../packages/plan/plan-mode), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`time-context`](../packages/context/time-context), [`tool-skill`](../packages/skill/tool-skill), [`user-approval`](../packages/ui/user-approval), [`workspace-context`](../packages/context/workspace-context) | | `agent/turn-stopping` | `serial` | [`packages/core/agent/src/types.ts:373`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:30`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/acp/acp) | -| `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:154`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | `apiproxy`, [`tui`](../packages/ui/tui) | +| `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:161`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | `apiproxy`, [`tui`](../packages/ui/tui) | | `domain/changed` | `emit` | [`packages/storage/storage-domain/src/events.ts:46`](../packages/storage/storage-domain/src/events.ts) | [`storage-domain`](../packages/storage/storage-domain) (`emit`) | `apiproxy`, [`storage-domain`](../packages/storage/storage-domain), [`workspace`](../packages/workspace/workspace) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:62`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:71`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 7c027afd68..7c4dd1010b 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -185,7 +185,7 @@ Source: [`packages/core/session/src/types.ts:219`](../packages/core/session/src/ 'command/done': { commandId: CommandId; kind: 'success' | 'error'; text?: string } ``` -Source: [`packages/ui/commands/src/index.ts:138`](../packages/ui/commands/src/index.ts) +Source: [`packages/ui/commands/src/index.ts:145`](../packages/ui/commands/src/index.ts) #### `command/run` — log-only @@ -197,12 +197,13 @@ Source: [`packages/ui/commands/src/index.ts:138`](../packages/ui/commands/src/in * and `args` are `parseCommand`'s own split (name and verbatim rawInput, * separator whitespace included), so a consumer (a projection unit * folding its own command records, a rich command card) never re-parses - * a line. + * a line. `args` is absent when the definition sets `recordInput: false` + * because an authoritative domain event owns the input payload. */ -'command/run': { commandId: CommandId; name: string; args: string; source: CommandSource } +'command/run': { commandId: CommandId; name: string; args?: string; source: CommandSource } ``` -Source: [`packages/ui/commands/src/index.ts:132`](../packages/ui/commands/src/index.ts) +Source: [`packages/ui/commands/src/index.ts:139`](../packages/ui/commands/src/index.ts) ### `compact/*` @@ -256,6 +257,20 @@ Types: [ContentBlock](core-data-structures/core.md) Source: [`packages/compact/compact/src/types.ts:22`](../packages/compact/compact/src/types.ts) +### `feedback/*` + +#### `feedback/record` — log-only + +```ts persistence-catalog +/** + * One recorded human remark about this session. Log-only and independent + * of its trigger; it never enters the model surface or derived history. + */ +'feedback/record': { text: string } +``` + +Source: [`packages/feedback/command-feedback/src/index.ts:24`](../packages/feedback/command-feedback/src/index.ts) + ### `hook/*` #### `hook/invoked` — log-only diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index be9ba79347..5d5e34bf31 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -304,9 +304,9 @@ function viewFor(event: SessionEvent, log: readonly SessionEvent[]): ToolEventVi /** * Fixture parallel of the plan unit's double-event fold: `command/run` - * records named `plan` set the wanted target (`off` → false, else true); - * `plan/mode` commits and clears it. `wanted` is exposed for the prompt - * boundary (the fixture's agent/step parallel). + * records named `plan` with recorded input set the wanted target (`off` → + * false, else true); `plan/mode` commits and clears it. `wanted` is exposed + * for the prompt boundary (the fixture's agent/step parallel). */ function foldPlan(log: readonly SessionEvent[]): { active: boolean; pending: boolean; wanted: boolean | null } { let active = false @@ -315,7 +315,8 @@ function foldPlan(log: readonly SessionEvent[]): { active: boolean; pending: boo const item = event as unknown as { type: string; data?: Record } if (item.type === 'command/run' && item.data?.['name'] === 'plan') { const args = item.data['args'] - wanted = (typeof args === 'string' ? args : '').trim() !== 'off' + if (typeof args !== 'string') continue + wanted = args.trim() !== 'off' } else if (item.type === 'plan/mode') { active = item.data?.['active'] === true wanted = null @@ -374,8 +375,9 @@ function projectionFramesOf(id: SessionId, log: readonly SessionEvent[], event: }] } // The plan unit advances on its two folded event kinds. + const commandData = event as unknown as { data: { name?: string; args?: unknown } } if (type === 'plan/mode' || (type === 'command/run' - && (event as unknown as { data: { name?: string } }).data.name === 'plan')) { + && commandData.data.name === 'plan' && typeof commandData.data.args === 'string')) { return [{ type: 'session/projection', sessionId: id, diff --git a/packages/client/runtime/src/client/sessions/conversation.ts b/packages/client/runtime/src/client/sessions/conversation.ts index f5f0717236..474f7cc8b3 100644 --- a/packages/client/runtime/src/client/sessions/conversation.ts +++ b/packages/client/runtime/src/client/sessions/conversation.ts @@ -140,7 +140,10 @@ export interface CommandNode { commandId: CommandId /** Command name (run payload's structured field); null when the run fell outside the window. */ name: string | null - /** Verbatim rawInput after the name, separator whitespace included (run payload); null when the run fell outside the window. */ + /** + * Verbatim rawInput after the name, including separator whitespace; null + * when omitted by the command or when the run fell outside the window. + */ args: string | null /** Settlement outcome (done payload); null while the command is still executing. */ outcome: { kind: 'success' | 'error'; text?: string } | null diff --git a/packages/client/runtime/src/client/sessions/fold-adapter.ts b/packages/client/runtime/src/client/sessions/fold-adapter.ts index 039c36056b..c884d2ec8e 100644 --- a/packages/client/runtime/src/client/sessions/fold-adapter.ts +++ b/packages/client/runtime/src/client/sessions/fold-adapter.ts @@ -234,10 +234,10 @@ export class FoldAdapter { // enter the client program, so this wire consumer narrows structurally // (the same posture as tool/code-dispatch in session.ts). if ((event.type as string) === 'command/run') { - const data = event.data as unknown as { commandId: CommandId; name: string; args: string } + const data = event.data as unknown as { commandId: CommandId; name: string; args?: string } this.commandIdx.set(data.commandId, { kind: 'command', seq: event.seq, time: event.time, - commandId: data.commandId, name: data.name, args: data.args, outcome: null, + commandId: data.commandId, name: data.name, args: data.args ?? null, outcome: null, }) return } diff --git a/packages/client/runtime/tests/event-script.ts b/packages/client/runtime/tests/event-script.ts index 53f80e0e69..7da9bf0184 100644 --- a/packages/client/runtime/tests/event-script.ts +++ b/packages/client/runtime/tests/event-script.ts @@ -67,6 +67,8 @@ export const ev = { at(seq, { type: 'turn/end', data: { turn, reason: { kind: reason } } }), commandRun: (seq: number, commandId: string, name: string, args = ''): SessionEvent => at(seq, { type: 'command/run', data: { commandId, name, args, source: { kind: 'user' } } }), + commandRunWithoutInput: (seq: number, commandId: string, name: string): SessionEvent => + at(seq, { type: 'command/run', data: { commandId, name, source: { kind: 'user' } } }), commandDone: (seq: number, commandId: string, kind: 'success' | 'error' = 'success', text?: string): SessionEvent => at(seq, { type: 'command/done', data: { commandId, kind, ...text === undefined ? {} : { text } } }), } diff --git a/packages/client/runtime/tests/fold-adapter.spec.ts b/packages/client/runtime/tests/fold-adapter.spec.ts index b40bdb4111..0b14fda5c3 100644 --- a/packages/client/runtime/tests/fold-adapter.spec.ts +++ b/packages/client/runtime/tests/fold-adapter.spec.ts @@ -195,6 +195,14 @@ describe('FoldAdapter', () => { }) }) + it('represents command input omitted by the host as null', () => { + const adapter = new FoldAdapter() + adapter.reset([ev.commandRunWithoutInput(0, 'cmd-private', 'feedback')], 0) + expect(adapter.nodes().nodes[0]).toMatchObject({ + kind: 'command', name: 'feedback', args: null, outcome: null, + }) + }) + it('soft-falls a done-only window into a node built from the done (cross-window cut)', () => { const adapter = new FoldAdapter() adapter.reset([ev.commandDone(80, 'cmd-3', 'error', '失败了')], 80) diff --git a/packages/client/ui-conversation/src/client/chat/GenericCommandCard.tsx b/packages/client/ui-conversation/src/client/chat/GenericCommandCard.tsx index 1dfea5488b..1d6db2581d 100644 --- a/packages/client/ui-conversation/src/client/chat/GenericCommandCard.tsx +++ b/packages/client/ui-conversation/src/client/chat/GenericCommandCard.tsx @@ -21,8 +21,8 @@ export function GenericCommandCard({ node }: CommandRowOwnerProps) { ? '执行中…' : text ?? (node.outcome.kind === 'error' ? '命令失败' : '已完成') // Display line rebuilt from the structured payload (args carries its own - // separator whitespace verbatim); a cross-window node whose run page fell - // out of the window has neither. + // separator whitespace verbatim); omitted input and a cross-window node + // whose run page fell out both render without it. const title = node.name === null ? '命令' : `/${node.name}${node.args ?? ''}` return ( CommandResult | Promise;\n}', + declaration: 'export interface CommandDefinition {\n readonly name: string;\n readonly description: string;\n readonly input?: CommandInputDescriptor;\n readonly recordInput?: boolean;\n readonly handler: (invocation: CommandInvocation) => CommandResult | Promise;\n}', }, { name: 'CommandDescriptor', diff --git a/packages/feedback/README.i18n.yaml b/packages/feedback/README.i18n.yaml index eca3b1c420..31ed2d25e8 100644 --- a/packages/feedback/README.i18n.yaml +++ b/packages/feedback/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/feedback/README.md -README.md: ab7bc6f3e3a3be0c280855ff80e92c7d7a7e665e -README.zh.md: 9c050ac42aa468895c04124a76a3bce58756df0e +README.md: 7962a16ee9bc7d8a969a466591d761829cd55d7f +README.zh.md: aad8f4d797ff16a5ef9be4c968fb28d708bad13e diff --git a/packages/feedback/README.md b/packages/feedback/README.md index ab7bc6f3e3..7962a16ee9 100644 --- a/packages/feedback/README.md +++ b/packages/feedback/README.md @@ -6,6 +6,6 @@ The feedback family lets a human record a remark about the session without actin | Package | Role | ctx key | |---|---|---| -| `command-feedback/` | Human-facing `/feedback` command recorded through the command plane | — | +| `command-feedback/` | Trigger-independent `feedback/record` event plus the human-facing `/feedback` producer | — | -A recorded remark is log-only: it never enters the model surface or derived history, and no shipped plugin consumes it. A future consumer reads the command records from the session log rather than changing how they are captured. +A recorded remark is log-only: it never enters the model surface or derived history, and no shipped plugin consumes it. A future consumer reads `feedback/record` events from the session log rather than changing how they are captured. diff --git a/packages/feedback/README.zh.md b/packages/feedback/README.zh.md index 9c050ac42a..aad8f4d797 100644 --- a/packages/feedback/README.zh.md +++ b/packages/feedback/README.zh.md @@ -6,6 +6,6 @@ feedback 家族让人类记录对会话的评价，但不据此采取任何动 | 包 | 职责 | ctx 键 | |---|---|---| -| `command-feedback/` | 面向用户的 `/feedback` 命令，通过命令平面完成记录 | 无 | +| `command-feedback/` | 与触发方式无关的 `feedback/record` 事件，以及面向用户的 `/feedback` 生产方 | 无 | -被记录的评价仅写入日志：它绝不会进入模型 surface 或派生历史，随附插件也不会消费它。未来的消费方从会话日志中读取命令记录，而不是改变它们的采集方式。 +被记录的评价仅写入日志：它绝不会进入模型 surface 或派生历史，随附插件也不会消费它。未来的消费方从会话日志中读取 `feedback/record` 事件，而不是改变它们的采集方式。 diff --git a/packages/feedback/command-feedback/README.i18n.yaml b/packages/feedback/command-feedback/README.i18n.yaml index 37f10ac485..47c169ec3f 100644 --- a/packages/feedback/command-feedback/README.i18n.yaml +++ b/packages/feedback/command-feedback/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/feedback/command-feedback/README.md -README.md: 90992b7295536a9099766910f616e640d4b4bcfe -README.zh.md: a7c4f03997cea182ed24dcfc7f309dc3bd872d5e +README.md: c9650d6a2c595550545b3dbf07f62e6aa65f39b9 +README.zh.md: ba24276ba1bd71a4eb68c7fdb48a3760bdbec8fc diff --git a/packages/feedback/command-feedback/README.md b/packages/feedback/command-feedback/README.md index 90992b7295..c9650d6a2c 100644 --- a/packages/feedback/command-feedback/README.md +++ b/packages/feedback/command-feedback/README.md @@ -2,24 +2,24 @@ English | [中文](README.zh.md) -Human-facing `/feedback` capture. The plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers it; the shipped TUI executes it without a model turn. +Trigger-independent session feedback plus human-facing `/feedback` capture. The package exports `recordFeedback(session, text)`, which appends one log-only `feedback/record` event. Its plugin registers one global command through [`ctx.commands`](../../ui/commands/README.md), so every composed command adapter discovers it; the shipped TUI executes it without a model turn. ## Command contract | Input | Result | |---|---| -| `/feedback ` | Acknowledge with `Feedback recorded.` The registry's `command/run` record carries the verbatim text. | +| `/feedback ` | Append `feedback/record` and acknowledge with `Feedback recorded.` | | `/feedback` | Return a direct usage error. Whitespace-only input is treated as empty. | -Feedback text is never parsed: no truncation, case folding, or control words. Text that looks like another command, such as `/feedback /plan felt slow`, is feedback content. Repeated commands each produce their own record; nothing is replaced or merged. +Surrounding whitespace is discarded, but feedback is otherwise unparsed: no truncation, case folding, or control words. Text that looks like another command, such as `/feedback /plan felt slow`, is feedback content. Repeated commands each produce their own event; nothing is replaced or merged. ## What this plugin does and does not do -The command records a remark and does nothing else. It appends no session event of its own, starts no model work, and no plugin in this repository reads its records. +`recordFeedback(session, text)` is the command-independent write path. It rejects empty normalized text and appends `feedback/record { text }`; a different UI, hook, or host integration can call it without constructing a slash command. The `/feedback` handler uses that producer, starts no model work, and no plugin in this repository reads the event. -The record is the command registry's own `command/run` / `command/done` pairing, which [`dsh-commands`](../../ui/commands/README.md) appends for every dispatched command. Those appends start persistence's ordinary eager drain; neither the registry nor this command forces a `session/flush`, so the acknowledgement means the entry is in the log, not that it has already reached disk. `command/run` carries the command name, the verbatim unparsed suffix, and the invocation source; the paired `command/done` carries the outcome. Both are log-only and are absent from the ordered surface, from `deriveMessages()`, and from every model request. A rejected empty input still leaves that pairing, settled as `kind: 'error'`, so no entry can be mistaken for accepted feedback. +The feedback text appears in exactly one durable payload: `feedback/record`. [`dsh-commands`](../../ui/commands/README.md) still appends its generic `command/run` / `command/done` pairing, but this definition sets `recordInput: false`, so `command/run` omits `args`; the paired `command/done` carries only the outcome. All three events are log-only and absent from the ordered surface, `deriveMessages()`, and model requests. These appends start persistence's ordinary eager drain, but neither producer forces `session/flush`, so acknowledgement means the feedback is in the log, not that it has reached disk. Rejected empty input leaves only the command pairing settled as `kind: 'error'`, with no `feedback/record`. -A dedicated `session/feedback` event was considered and rejected: it would duplicate a record the registry already writes, and a consumer can select feedback by the command name it already stores. +The event is authoritative rather than the command record because feedback may arrive through a trigger other than `/feedback`. Keeping the payload out of `command/run` avoids two records carrying the same text. ## Composition @@ -40,7 +40,7 @@ The TUI app mounts this command unconditionally; it has no configuration and no #### What the model sees -Nothing. The slash input, the recorded text, and the acknowledgement are all absent from model requests. The registry's `command/run` and `command/done` records are log-only and carry no `surfaceOp`, so they never reach the ordered surface, `deriveMessages()`, or a system prompt. Recording feedback during a turn does not change that turn's remaining requests. +Nothing. The slash input, `feedback/record`, and the acknowledgement are absent from model requests. The feedback event and registry lifecycle records are log-only and carry no `surfaceOp`, so they never reach the ordered surface, `deriveMessages()`, or a system prompt. Recording feedback during a turn does not change that turn's remaining requests. #### Token effect @@ -52,9 +52,8 @@ Independent of the model request path. Recording appends to the session log only ## Known Limitations and Deferred Work -- **Nothing consumes the recorded feedback** — capture is deliberately inert. There is no retrieval, aggregation, export, or reporting surface, and no model-facing tool reads it; a consumer is a separate package that selects `command/run` records by command name. +- **Nothing consumes the recorded feedback** — capture is deliberately inert. There is no retrieval, aggregation, export, or reporting surface, and no model-facing tool reads `feedback/record`; a consumer is a separate package. - **No structured fields** — an entry is one free-text string with no category, severity, or referenced-event link, so feedback cannot be filtered by subject without re-reading its text. - **No amend or withdraw** — the session log is append-only and this package adds no tombstone, so a mistaken entry stays recorded and can only be superseded by a later one. -- **Untrimmed text in the record** — the handler trims only to validate; `command/run` stores the raw suffix, including its leading separator whitespace, so a consumer trims at read time. - **No explicit durability barrier** — the acknowledgement follows the append, not a flush, so an entry recorded immediately before a crash can be lost with any other unflushed tail. Feedback is not worth forcing a synchronous disk write for; a consumer that needs one awaits `ctx.sessions.flush(session)`. - **TUI only in the shipped apps** — the headless CLI, ACP automation, and JSON-RPC adapters do not mount `ctx.commands`, so `/feedback` is unavailable there. diff --git a/packages/feedback/command-feedback/README.zh.md b/packages/feedback/command-feedback/README.zh.md index a7c4f03997..ba24276ba1 100644 --- a/packages/feedback/command-feedback/README.zh.md +++ b/packages/feedback/command-feedback/README.zh.md @@ -2,24 +2,24 @@ [English](README.md) | 中文 -面向用户的 `/feedback` 采集。该插件通过 [`ctx.commands`](../../ui/commands/README.md) 注册一个全局命令，因此每个已组合的命令适配器都能发现它；随附 TUI 无需模型轮次即可执行。 +与触发方式无关的会话反馈，以及面向用户的 `/feedback` 采集。本包（package）导出 `recordFeedback(session, text)`，后者追加一个仅写入日志的 `feedback/record` 事件。该插件通过 [`ctx.commands`](../../ui/commands/README.md) 注册一个全局命令，因此每个已组合的命令适配器都能发现它；随附 TUI 无需模型轮次即可执行。 ## 命令契约 | 输入 | 结果 | |---|---| -| `/feedback ` | 以 `Feedback recorded.` 确认。注册表的 `command/run` 记录携带原样文本。 | +| `/feedback ` | 追加 `feedback/record`，并以 `Feedback recorded.` 确认。 | | `/feedback` | 返回一个直接用法错误。仅含空白的输入视为空输入。 | -反馈文本从不被解析：没有截断、大小写折叠或控制词。看起来像另一个命令的文本（例如 `/feedback /plan felt slow`）就是反馈内容。重复执行命令会各自产生自己的记录，不会替换或合并。 +前后空白会被丢弃，但除此之外，反馈内容不会被解析：没有截断、大小写折叠或控制词。看起来像另一个命令的文本（例如 `/feedback /plan felt slow`）就是反馈内容。重复执行命令时，每次都会产生一个事件；不会发生替换或合并。 ## 本插件做什么、不做什么 -该命令记录一条评价，不做别的事。它不追加属于自己的会话事件，不启动任何模型工作，本仓库中也没有任何插件读取它的记录。 +`recordFeedback(session, text)` 是不依赖命令的写入路径。它拒绝规范化后为空的文本，并追加 `feedback/record { text }`；其他 UI、钩子或 host 集成无需构造斜杠命令即可调用它。`/feedback` 处理器通过该生产方写入，不启动任何模型工作；本仓库中也没有任何插件读取该事件。 -记录来自命令注册表自身的 `command/run` / `command/done` 配对，由 [`dsh-commands`](../../ui/commands/README.md) 为每个已分发命令追加。这些追加会启动持久化的常规即时排空；注册表与本命令都不会强制 `session/flush`，因此确认文本表示条目已进入日志，而不表示它已经落盘。`command/run` 携带命令名、原样未解析的后缀以及调用来源；配对的 `command/done` 携带结果。两者都仅写入日志，不出现在有序 surface、`deriveMessages()` 以及任何模型请求中。被拒绝的空输入仍会留下该配对，并以 `kind: 'error'` 结算，因此任何条目都不会被误认为已接受的反馈。 +反馈文本只出现在一个持久载荷中：`feedback/record`。[`dsh-commands`](../../ui/commands/README.md) 仍会追加通用的 `command/run` / `command/done` 配对，但此定义设置了 `recordInput: false`，因此 `command/run` 会省略 `args`；配对的 `command/done` 只携带结果。三个事件都仅写入日志，不出现在有序 surface、`deriveMessages()` 以及模型请求中。这些追加会启动持久化的常规即时排空，但两个生产方都不会强制 `session/flush`，因此确认文本表示反馈已进入日志，而不表示它已经落盘。被拒绝的空输入只会留下以 `kind: 'error'` 结算的命令配对，不会产生 `feedback/record`。 -曾考虑并否决了专用的 `session/feedback` 事件：它会重复注册表已经写入的记录，而消费方可以依据注册表已存储的命令名筛选反馈。 +权威记录是该事件，而不是命令记录，因为反馈可能来自 `/feedback` 之外的触发方式。让载荷不进入 `command/run`，可避免两条记录携带相同文本。 ## 组合 @@ -40,7 +40,7 @@ TUI 应用无条件挂载此命令；它没有配置，也不依赖持久 goal #### 模型看到的内容 -无。斜杠输入、被记录的文本以及确认文本都不出现在模型请求中。注册表的 `command/run` 与 `command/done` 记录仅写入日志且不携带 `surfaceOp`，因此它们绝不会进入有序 surface、`deriveMessages()` 或系统提示词。在某个轮次中记录反馈不会改变该轮次剩余的请求。 +无。斜杠输入、`feedback/record` 以及确认文本都不出现在模型请求中。反馈事件和注册表生命周期记录仅写入日志且不携带 `surfaceOp`，因此它们绝不会进入有序 surface、`deriveMessages()` 或系统提示词。在某个轮次中记录反馈不会改变该轮次剩余的请求。 #### Token 影响 @@ -52,9 +52,8 @@ TUI 应用无条件挂载此命令；它没有配置，也不依赖持久 goal ## 已知限制与暂缓工作 -- **没有任何消费方读取被记录的反馈**：采集刻意不产生任何后续动作。这里没有检索、聚合、导出或报告 surface，也没有面向模型的工具读取它；消费方是另一个依据命令名筛选 `command/run` 记录的独立包。 +- **没有任何消费方读取被记录的反馈**：采集刻意不产生任何后续动作。这里没有检索、聚合、导出或报告 surface，也没有面向模型的工具读取 `feedback/record`；消费方是另一个独立包。 - **没有结构化字段**：一条条目就是一个自由文本字符串，没有类别、严重程度或关联事件链接，因此无法在不重读文本的情况下按主题过滤反馈。 - **不支持修改或撤回**：会话日志是仅追加的，本包也不新增 tombstone，因此错误的条目会一直保留在记录中，只能由后续条目取代。 -- **记录中的文本未修剪**：处理器只为校验而修剪；`command/run` 存储原始后缀，包含其前导分隔空白，因此消费方需在读取时修剪。 - **没有显式持久化屏障**：确认文本紧随追加而非 flush，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。为反馈强制同步写盘并不值得；需要该保证的消费方可自行等待 `ctx.sessions.flush(session)`。 - **随附应用中只有 TUI 使用此命令**：无头 CLI、ACP 自动化和 JSON-RPC 适配器不挂载 `ctx.commands`，因此 `/feedback` 在那里不可用。 diff --git a/packages/feedback/command-feedback/package.json b/packages/feedback/command-feedback/package.json index 6ad91d0e0d..25bc8446c3 100644 --- a/packages/feedback/command-feedback/package.json +++ b/packages/feedback/command-feedback/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-command-feedback", - "description": "Human-facing slash command that records session feedback as a log-only event", + "description": "Log-only session feedback producer and human-facing slash command", "version": "0.0.1", "private": true, "type": "module", @@ -29,6 +29,7 @@ "peerDependencies": { "@deepseek-ai/dsh-commands": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "cordis": "^4.0.0-rc.7" }, "devDependencies": { diff --git a/packages/feedback/command-feedback/src/index.ts b/packages/feedback/command-feedback/src/index.ts index 7bf7cd0853..ae78b3cd4f 100644 --- a/packages/feedback/command-feedback/src/index.ts +++ b/packages/feedback/command-feedback/src/index.ts @@ -1,24 +1,45 @@ /** - * Human-facing `/feedback` command. It records a remark about the session and - * does nothing else: the command registry's own `command/run` and - * `command/done` events are the whole record, so this plugin only validates the - * input and acknowledges it. Those appends are eager but unflushed, so the - * acknowledgement reports the entry is logged, not that it reached disk. + * Session feedback event plus the human-facing `/feedback` producer. Recording + * appends one authoritative log-only event and does not start model work. The + * append is eager but unflushed, so acknowledgement reports that the entry is + * logged, not that it reached disk. * @module @deepseek-ai/dsh-command-feedback */ import type { Context } from 'cordis' import type { CommandInvocation, CommandResult } from '@deepseek-ai/dsh-commands' +import type { Session } from '@deepseek-ai/dsh-session' export const name = 'command-feedback' export const inject = ['commands'] const USAGE = 'Usage: /feedback ' +declare module '@deepseek-ai/dsh-session' { + interface SessionEventMap { + /** + * One recorded human remark about this session. Log-only and independent + * of its trigger; it never enters the model surface or derived history. + */ + 'feedback/record': { text: string } + } +} + /** - * Validate and acknowledge one feedback entry. `command/run` already carries - * the verbatim text, so no further append is needed; returning an error instead - * settles that record as `kind: 'error'` and leaves no accepted feedback. + * Record feedback independently of any UI trigger. + * @param session - session the feedback describes. + * @param text - human-authored feedback; surrounding whitespace is discarded. + * @throws {TypeError} when the normalized text is empty. + */ +export function recordFeedback(session: Session, text: string): void { + const normalized = text.trim() + if (normalized.length === 0) throw new TypeError('feedback text must not be empty') + session.append('feedback/record', { text: normalized }) +} + +/** + * Validate, record, and acknowledge one feedback entry. Returning an error + * leaves no `feedback/record` event. * @param invocation - receiving agent, raw command input, and UI cancellation. * @returns an acknowledgement, or a usage error when no feedback text was supplied. */ @@ -26,6 +47,7 @@ function executeFeedbackCommand(invocation: CommandInvocation): CommandResult { if (invocation.rawInput.trim().length === 0) { return { kind: 'error', text: `Feedback text is required. ${USAGE}` } } + recordFeedback(invocation.agent.session, invocation.rawInput) return { kind: 'success', text: 'Feedback recorded.' } } @@ -35,6 +57,7 @@ export function apply(ctx: Context): void { name: 'feedback', description: 'record feedback about this session', input: { hint: '' }, + recordInput: false, handler: executeFeedbackCommand, }) } diff --git a/packages/feedback/command-feedback/src/invariant.ts b/packages/feedback/command-feedback/src/invariant.ts index 72a3ead213..9c825a6e87 100644 --- a/packages/feedback/command-feedback/src/invariant.ts +++ b/packages/feedback/command-feedback/src/invariant.ts @@ -15,8 +15,8 @@ export const name = 'command-feedback-invariant' export const inject = ['invariants'] /** - * No runtime invariant: this command declares no session event and owns no state projection. The - * `command/run`/`command/done` pairing that records feedback belongs to `dsh-commands`. + * No runtime invariant: each `feedback/record` is an independent append-only + * fact with no cross-event or mutable-data relationship. */ const install: InvariantInstaller = () => {} diff --git a/packages/feedback/command-feedback/tests/command-feedback.spec.ts b/packages/feedback/command-feedback/tests/command-feedback.spec.ts index 362bb8ce30..853e967176 100644 --- a/packages/feedback/command-feedback/tests/command-feedback.spec.ts +++ b/packages/feedback/command-feedback/tests/command-feedback.spec.ts @@ -58,15 +58,11 @@ async function run(test: Harness, suffix = ''): Promise<{ kind: string; text?: s return settled.result } -/** The registry's durable record of each accepted command, in log order. */ -function commandRecords(session: Session): { name: string; args: string; kind: string }[] { - const runs = session.events.filter(event => event.type === 'command/run') - return runs.map((event) => { - const done = session.events.find(item => - item.type === 'command/done' && item.data.commandId === event.data.commandId) - if (done?.type !== 'command/done') throw new Error('every command/run must be paired') - return { name: event.data.name, args: event.data.args, kind: done.data.kind } - }) +/** Authoritative feedback payloads in log order. */ +function feedbackTexts(session: Session): string[] { + return session.events + .filter(event => event.type === 'feedback/record') + .map(event => event.data.text) } describe('@deepseek-ai/dsh-command-feedback registration', () => { @@ -83,7 +79,7 @@ describe('@deepseek-ai/dsh-command-feedback registration', () => { description: 'record feedback about this session', input: { hint: '' }, }) - expect(test.ctx.commands.find(test.agent, 'feedback')).toBeDefined() + expect(test.ctx.commands.find(test.agent, 'feedback')).toMatchObject({ recordInput: false }) await test.plugin.dispose() expect(test.ctx.commands.find(test.agent, 'feedback')).toBeUndefined() @@ -91,38 +87,47 @@ describe('@deepseek-ai/dsh-command-feedback registration', () => { }) describe('/feedback human command', () => { - it('acknowledges feedback and leaves the registry record as its durable trace', async () => { + it('acknowledges feedback and records its payload exactly once in the domain event', async () => { const test = await harness() await expect(run(test, ' the diff view is unreadable')).resolves.toEqual({ kind: 'success', text: 'Feedback recorded.', }) - expect(commandRecords(test.session)).toEqual([ - { name: 'feedback', args: ' the diff view is unreadable', kind: 'success' }, - ]) + expect(feedbackTexts(test.session)).toEqual(['the diff view is unreadable']) + const commandRun = test.session.events.find(event => event.type === 'command/run') + expect(commandRun?.type === 'command/run' && Object.hasOwn(commandRun.data, 'args')).toBe(false) + expect(JSON.stringify(test.session.events).match(/the diff view is unreadable/gu)).toHaveLength(1) }) - it('adds no event of its own beyond the registry pairing', async () => { + it('exports a command-independent feedback producer', async () => { + const test = await harness() + commandFeedback.recordFeedback(test.session, ' recorded outside a command ') + expect(test.session.events.map(event => event.type)).toEqual(['feedback/record']) + expect(feedbackTexts(test.session)).toEqual(['recorded outside a command']) + expect(() => { commandFeedback.recordFeedback(test.session, ' \n\t ') }) + .toThrow('feedback text must not be empty') + expect(feedbackTexts(test.session)).toEqual(['recorded outside a command']) + }) + + it('keeps command bookkeeping around the authoritative feedback event', async () => { const test = await harness() await run(test, ' nothing else happens') - // The whole point of the command: record and do nothing. Only the - // registry's own pairing appears, and no turn of model work starts. - expect(test.session.events.map(event => event.type)).toEqual(['command/run', 'command/done']) + expect(test.session.events.map(event => event.type)).toEqual([ + 'command/run', 'feedback/record', 'command/done', + ]) }) - it('records verbatim text, including input that looks like another command', async () => { + it('normalizes surrounding whitespace without parsing command-like content', async () => { const test = await harness() await run(test, ' /plan felt SLOW\n\ttwice today ') - expect(commandRecords(test.session)).toEqual([ - { name: 'feedback', args: ' /plan felt SLOW\n\ttwice today ', kind: 'success' }, - ]) + expect(feedbackTexts(test.session)).toEqual(['/plan felt SLOW\n\ttwice today']) }) it('records each entry separately without replacing earlier ones', async () => { const test = await harness() await run(test, ' first') await run(test, ' second') - expect(commandRecords(test.session).map(record => record.args)).toEqual([' first', ' second']) + expect(feedbackTexts(test.session)).toEqual(['first', 'second']) }) it('records concurrent submissions in dispatch order', async () => { @@ -137,7 +142,7 @@ describe('/feedback human command', () => { { kind: 'success', text: 'Feedback recorded.' }, { kind: 'success', text: 'Feedback recorded.' }, ]) - expect(commandRecords(test.session).map(record => record.args)).toEqual([' first', ' second']) + expect(feedbackTexts(test.session)).toEqual(['first', 'second']) }) it('keeps every recorded event off the model surface and out of derived history', async () => { @@ -160,9 +165,12 @@ describe('/feedback human command', () => { } await expect(run(test)).resolves.toEqual(expected) await expect(run(test, ' \n\t ')).resolves.toEqual(expected) - // Rejected input still leaves the registry's own pairing, settled as an - // error, so no entry is mistaken for accepted feedback. - expect(commandRecords(test.session).map(record => record.kind)).toEqual(['error', 'error']) + expect(feedbackTexts(test.session)).toEqual([]) + const done = test.session.events.filter(event => event.type === 'command/done') + expect(done.map(event => event.data.kind)).toEqual(['error', 'error']) + for (const event of test.session.events) { + if (event.type === 'command/run') expect(Object.hasOwn(event.data, 'args')).toBe(false) + } }) it('records nothing when dispatch rejects an already-cancelled request', async () => { diff --git a/packages/feedback/command-feedback/tests/loader-composition.spec.ts b/packages/feedback/command-feedback/tests/loader-composition.spec.ts index 9aa206f9ad..dbb175d304 100644 --- a/packages/feedback/command-feedback/tests/loader-composition.spec.ts +++ b/packages/feedback/command-feedback/tests/loader-composition.spec.ts @@ -92,11 +92,14 @@ describe('/feedback real Loader composition through cordis.yml', () => { text: 'Feedback text is required. Usage: /feedback ', }) - // The command records itself through the registry and does nothing else. + // The domain event owns the payload; generic command bookkeeping omits it. expect(owner.session.events.map(event => event.type)) - .toEqual(['command/run', 'command/done', 'command/run', 'command/done']) + .toEqual(['command/run', 'feedback/record', 'command/done', 'command/run', 'command/done']) const run = owner.session.events.find(event => event.type === 'command/run') - expect(run?.type === 'command/run' && run.data.args).toBe(' the diff view is unreadable') + expect(run?.type === 'command/run' && Object.hasOwn(run.data, 'args')).toBe(false) + const feedback = owner.session.events.find(event => event.type === 'feedback/record') + expect(feedback?.type === 'feedback/record' && feedback.data.text).toBe('the diff view is unreadable') + expect(JSON.stringify(owner.session.events).match(/the diff view is unreadable/gu)).toHaveLength(1) // Nothing reached the model. expect(owner.session.deriveMessages()).toEqual([]) diff --git a/packages/feedback/command-feedback/tsconfig.json b/packages/feedback/command-feedback/tsconfig.json index 6a27b54d3a..0a99f13f01 100644 --- a/packages/feedback/command-feedback/tsconfig.json +++ b/packages/feedback/command-feedback/tsconfig.json @@ -17,6 +17,9 @@ { "path": "../../ui/commands" }, + { + "path": "../../core/session" + }, { "path": "../../support/invariants" } diff --git a/packages/plan/plan-mode/README.i18n.yaml b/packages/plan/plan-mode/README.i18n.yaml index c5a13bee7e..791f77b637 100644 --- a/packages/plan/plan-mode/README.i18n.yaml +++ b/packages/plan/plan-mode/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/plan/plan-mode/README.md -README.md: d3c2c14fe616e1c9b4e33b716570b084db6474cf -README.zh.md: 6d6878c4b0300a716ad16be60fd86bc79f1514ba +README.md: e3a98115d2d9f14fa0bb46e4d867f6b79cbf269d +README.zh.md: f8481cff12992e83af39498908c5ca2624a4f974 diff --git a/packages/plan/plan-mode/README.md b/packages/plan/plan-mode/README.md index d3c2c14fe6..e3a98115d2 100644 --- a/packages/plan/plan-mode/README.md +++ b/packages/plan/plan-mode/README.md @@ -20,7 +20,7 @@ The TUI consumes the plugin-owned `/plan` command; other front doors may drive t ## Session projection -When the composition mounts `ctx.sessionProjections` ([`@deepseek-ai/dsh-session-projection`](../../session-projection/session-projection/README.md)), this package registers the `plan` projection unit under an injected child. The unit folds two event kinds: a `command/run` record named `plan` sets the wanted target (`off` → inactive, anything else → active), and `plan/mode` commits the logged state and clears it; every other event returns the same state reference. `view` derives `{ active, pending }`, where `pending` is true only while an outstanding selection differs from the logged state — a pure replay quantity, so host restarts, other tabs, and cold reads all recover it from the log alone (the `/plan` handler calls `set()` before any failing path, keeping the logged request and the run plane from forking). The key merges into `SessionProjectionMap` from `src/types.ts` (served to host consumers via `./types` and client aggregates via `./client`); the framework drives the unit and carriers serve the value on the history tail page and the `session/projection` push frame. Compositions without the registry are unaffected. +When the composition mounts `ctx.sessionProjections` ([`@deepseek-ai/dsh-session-projection`](../../session-projection/session-projection/README.md)), this package registers the `plan` projection unit under an injected child. The unit folds two event kinds: a `command/run` record named `plan` with recorded `args` sets the wanted target (`off` → inactive, anything else → active), and `plan/mode` commits the logged state and clears it; every other event returns the same state reference. `view` derives `{ active, pending }`, where `pending` is true only while an outstanding selection differs from the logged state — a pure replay quantity, so host restarts, other tabs, and cold reads all recover it from the log alone (the `/plan` handler calls `set()` before any failing path, keeping the logged request and the run plane from forking). The key merges into `SessionProjectionMap` from `src/types.ts` (served to host consumers via `./types` and client aggregates via `./client`); the framework drives the unit and carriers serve the value on the history tail page and the `session/projection` push frame. Compositions without the registry are unaffected. ## Configuration diff --git a/packages/plan/plan-mode/README.zh.md b/packages/plan/plan-mode/README.zh.md index 6d6878c4b0..f8481cff12 100644 --- a/packages/plan/plan-mode/README.zh.md +++ b/packages/plan/plan-mode/README.zh.md @@ -20,7 +20,7 @@ TUI 消费插件拥有的 `/plan` 命令；其他入口可以直接驱动同一 ## 会话投影 -当组合挂载 `ctx.sessionProjections`（[`@deepseek-ai/dsh-session-projection`](../../session-projection/session-projection/README.md)）时，本包在注入子插件下注册 `plan` 投影单元。该单元折叠两种事件：名为 `plan` 的 `command/run` 记录设置目标值（`off` → 未激活，其余 → 激活），`plan/mode` 提交已记录状态并将其清除；其他任何事件返回同一状态引用。`view` 推导 `{ active, pending }`，其中 `pending` 仅在未兑现的选择不同于已记录状态时为 true——它是纯回放量，host 重启、其他标签页与冷读都只凭日志即可恢复（`/plan` 处理器在任何可能失败的路径之前调用 `set()`，使已入日志的请求与运行面不可能分叉）。key 从 `src/types.ts` merge 进 `SessionProjectionMap`（host 消费方经 `./types`、client 聚合经 `./client`）；框架驱动单元，载体在历史尾页与 `session/projection` 推送帧上提供该值。未挂注册表的组合不受影响。 +当组合挂载 `ctx.sessionProjections`（[`@deepseek-ai/dsh-session-projection`](../../session-projection/session-projection/README.md)）时，本包在注入子插件下注册 `plan` 投影单元。该单元折叠两种事件：名为 `plan` 且带有已记录 `args` 的 `command/run` 记录设置目标值（`off` → 未激活，其余 → 激活），`plan/mode` 提交已记录状态并将其清除；其他任何事件返回同一状态引用。`view` 推导 `{ active, pending }`，其中 `pending` 仅在未兑现的选择不同于已记录状态时为 true——它是纯回放量，host 重启、其他标签页与冷读都只凭日志即可恢复（`/plan` 处理器在任何可能失败的路径之前调用 `set()`，使已入日志的请求与运行面不可能分叉）。key 从 `src/types.ts` merge 进 `SessionProjectionMap`（host 消费方经 `./types`、client 聚合经 `./client`）；框架驱动单元，载体在历史尾页与 `session/projection` 推送帧上提供该值。未挂注册表的组合不受影响。 ## 配置 diff --git a/packages/plan/plan-mode/src/index.ts b/packages/plan/plan-mode/src/index.ts index dc6b788825..9d584dc776 100644 --- a/packages/plan/plan-mode/src/index.ts +++ b/packages/plan/plan-mode/src/index.ts @@ -234,6 +234,7 @@ export class PlanModeService extends Service { init: () => ({ active: false, wanted: null }), apply: (state, event) => { if (event.type === 'command/run' && event.data.name === 'plan') { + if (event.data.args === undefined) return state const wanted = event.data.args.trim() !== 'off' return wanted === state.wanted ? state : { active: state.active, wanted } } diff --git a/packages/plan/plan-mode/tests/projection.spec.ts b/packages/plan/plan-mode/tests/projection.spec.ts index 7c69417e58..cb662bc227 100644 --- a/packages/plan/plan-mode/tests/projection.spec.ts +++ b/packages/plan/plan-mode/tests/projection.spec.ts @@ -1,9 +1,9 @@ /** * The `plan` projection unit (session-projection RFC's complete example): a * double-event fold over the session log. `command/run` records named `plan` - * set the wanted target (`off` → false, anything else → true); `plan/mode` - * commits and clears it; `view` derives `{ active, pending }` where pending - * is true only while an outstanding selection differs from the logged state. + * with recorded input set the wanted target (`off` → false, anything else + * → true); `plan/mode` commits and clears it. `view` reports pending only + * while an outstanding selection differs from the logged state. * Pending is thereby a pure replay quantity — a cold fold answers it without * the service's in-memory intent. Composition without plan-mode has no `plan` * key; unloading the fiber removes it (HMR safety). @@ -88,6 +88,11 @@ describe('plan projection unit', () => { commandId: CommandId('other-1'), name: 'compact', args: '', source: { kind: 'user' }, }) expect(bench.values().plan).toEqual({ active: true, pending: false }) + // A command lifecycle with omitted input carries no plan selection. + bench.session.append('command/run', { + commandId: CommandId('plan-no-input'), name: 'plan', source: { kind: 'user' }, + }) + expect(bench.values().plan).toEqual({ active: true, pending: false }) runPlanCommand(bench.session, ' off', 1) expect(bench.values().plan).toEqual({ active: true, pending: true }) commitPlanMode(bench.session, false, 1) diff --git a/packages/ui/commands/README.i18n.yaml b/packages/ui/commands/README.i18n.yaml index 5c37ccbb16..339c11a248 100644 --- a/packages/ui/commands/README.i18n.yaml +++ b/packages/ui/commands/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/ui/commands/README.md -README.md: 4ad72cf9e232c8d41e525f42eecde5637032a391 -README.zh.md: bace8f6346ac737a838d802dfc5c6ffe52c56edd +README.md: 77397aadf8dd070d962d1a4f95dea2e4700a6c15 +README.zh.md: 8f02325271548b652b069433bcdb9c1c99de547e diff --git a/packages/ui/commands/README.md b/packages/ui/commands/README.md index 4ad72cf9e2..77397aadf8 100644 --- a/packages/ui/commands/README.md +++ b/packages/ui/commands/README.md @@ -6,9 +6,9 @@ Plugin-owned human-command registry consumed by interactive UI adapters. The [pl ## Service contract -`ctx.commands.register(definition)` registers one lowercase command name, description, optional unstructured-input hint, and abortable handler. A registered command is available to every composed command adapter; a plugin that is incompatible with a deployment does not register there. A plain-context registration is global. A command-producing plugin mounted beneath `agent.ctx` declares its own `commands` injection and creates an exact agent-scoped definition; it shadows a global definition with the same name. This child-injection shape preserves the agent scope without making the core agent loop depend on a UI service. Duplicate names within one layer fail during registration. Every disposer is the exact Cordis effect disposer, and registration or removal notifies every `commands/change` observer so live adapters can refresh discovery; observer failures are logged and cannot veto the registry mutation or starve later observers. +`ctx.commands.register(definition)` registers one lowercase command name, description, optional unstructured-input hint, optional `recordInput` policy, and abortable handler. `recordInput` defaults to true; a command whose authoritative domain event owns the payload sets it to false so `command/run` omits `args` instead of duplicating the input. A registered command is available to every composed command adapter; a plugin that is incompatible with a deployment does not register there. A plain-context registration is global. A command-producing plugin mounted beneath `agent.ctx` declares its own `commands` injection and creates an exact agent-scoped definition; it shadows a global definition with the same name. This child-injection shape preserves the agent scope without making the core agent loop depend on a UI service. Duplicate names within one layer fail during registration. Every disposer is the exact Cordis effect disposer, and registration or removal notifies every `commands/change` observer so live adapters can refresh discovery; observer failures are logged and cannot veto the registry mutation or starve later observers. -`list(agent)` returns immutable, name-sorted descriptors after scoped shadowing. `find(agent, name)` returns the corresponding definition. `execute(agent, line, signal)` uses `parseCommand()` and runs only a known command, returning the settled `CommandExecution` (the normalized result plus the lifecycle pairing `commandId`) or `undefined` for invalid syntax or unknown names. A resolved command's lifecycle is logged on the receiving agent's session as the log-only pair `command/run` (before the handler, with a minted `commandId`, the parser's structured `name`/`args` split, and the issuing `CommandSource`) and `command/done` (at settlement, with the outcome kind and verbatim text; a thrown or aborted handler settles as `kind: 'error'`). Admission misses log nothing. Both are direct standalone appends on the receiving agent's session: no turn wraps them, and persistence drains them through ordinary checkpoints and teardown. +`list(agent)` returns immutable, name-sorted descriptors after scoped shadowing. `find(agent, name)` returns the corresponding definition. `execute(agent, line, signal)` uses `parseCommand()` and runs only a known command, returning the settled `CommandExecution` (the normalized result plus the lifecycle pairing `commandId`) or `undefined` for invalid syntax or unknown names. A resolved command's lifecycle is logged on the receiving agent's session as the log-only pair `command/run` (before the handler, with a minted `commandId`, the parser's structured name, the issuing `CommandSource`, and `args` unless `recordInput` is false) and `command/done` (at settlement, with the outcome kind and verbatim text; a thrown or aborted handler settles as `kind: 'error'`). Admission misses log nothing. Both are direct standalone appends on the receiving agent's session: no turn wraps them, and persistence drains them through ordinary checkpoints and teardown. `parseCommand()` recognizes a slash at byte zero, a lowercase name containing letters, digits, `_`, or `-`, and either end-of-input or whitespace. It returns every byte after the name as `rawInput`, including separator whitespace; consumers own their command-specific grammar and may normalize only what that grammar permits. diff --git a/packages/ui/commands/README.zh.md b/packages/ui/commands/README.zh.md index bace8f6346..8f02325271 100644 --- a/packages/ui/commands/README.zh.md +++ b/packages/ui/commands/README.zh.md @@ -6,9 +6,9 @@ ## 服务契约 -`ctx.commands.register(definition)` 注册一个小写命令名称、描述、可选的非结构化输入提示，以及可中止的处理器。每个已注册命令都可供所有已组合的命令适配器使用；与某项部署不兼容的插件不会在此注册。普通上下文中的注册全局生效。在 `agent.ctx` 下挂载的命令生产插件会声明自身的 `commands` 注入，并创建精确限定到该 agent 的定义；该定义会遮蔽同名的全局定义。这种子级注入形态保留了 agent 作用域，同时不会让核心 agent loop 依赖 UI 服务。同一层中的名称重复会在注册时失败。每个 disposer 都是 Cordis effect 返回的确切 disposer；注册或移除命令时，系统会通知每个 `commands/change` 观察者，使实时适配器能够刷新发现结果。观察者失败会写入日志，既不能否决注册表变更，也不能阻止后续观察者运行。 +`ctx.commands.register(definition)` 注册一个小写命令名称、描述、可选的非结构化输入提示、可选的 `recordInput` 策略，以及可中止的处理器。`recordInput` 默认为 true；若载荷由命令的权威领域事件持有，该命令会将 `recordInput` 设为 false，让 `command/run` 省略 `args`，避免重复记录输入。每个已注册命令都可供所有已组合的命令适配器使用；与某项部署不兼容的插件不会在此注册。普通上下文中的注册全局生效。在 `agent.ctx` 下挂载的命令生产插件会声明自身的 `commands` 注入，并创建精确限定到该 agent 的定义；该定义会遮蔽同名的全局定义。这种子级注入形态保留了 agent 作用域，同时不会让核心 agent loop 依赖 UI 服务。同一层中的名称重复会在注册时失败。每个 disposer 都是 Cordis effect 返回的确切 disposer；注册或移除命令时，系统会通知每个 `commands/change` 观察者，使实时适配器能够刷新发现结果。观察者失败会写入日志，既不能否决注册表变更，也不能阻止后续观察者运行。 -`list(agent)` 在应用作用域遮蔽后，返回按名称排序的不可变描述符。`find(agent, name)` 返回相应定义。`execute(agent, line, signal)` 使用 `parseCommand()`，且只运行已知命令，返回已结算的 `CommandExecution`（规范化结果加生命周期配对 `commandId`）；语法无效或名称未知时返回 `undefined`。已解析命令的生命周期会以 log-only 事件对的形式记录在接收 agent 的会话日志中：`command/run`（进入处理器前记录，携带铸造的 `commandId`、解析器的结构化 `name`/`args` 切分和发起方 `CommandSource`）与 `command/done`（结算时记录，携带结局种类与原样文本；处理器抛出或被中止时以 `kind: 'error'` 结算）。未通过准入的输入不记录任何事件。两者都是直接独立追加：没有轮次包裹它们，持久化在常规检查点与 teardown 时排空它们。 +`list(agent)` 在应用作用域遮蔽后，返回按名称排序的不可变描述符。`find(agent, name)` 返回相应定义。`execute(agent, line, signal)` 使用 `parseCommand()`，且只运行已知命令，返回已结算的 `CommandExecution`（规范化结果加生命周期配对 `commandId`）；语法无效或名称未知时返回 `undefined`。已解析命令的生命周期会以 log-only 事件对的形式记录在接收 agent 的会话日志中：`command/run`（进入处理器前记录，携带铸造的 `commandId`、解析器得到的结构化名称、发起方 `CommandSource`，以及 `args`（`recordInput` 为 false 时省略））与 `command/done`（结算时记录，携带结局种类与原样文本；处理器抛出或被中止时以 `kind: 'error'` 结算）。未通过准入的输入不记录任何事件。两者都是直接独立追加：没有轮次包裹它们，持久化在常规检查点与 teardown 时排空它们。 `parseCommand()` 识别位于字节零位置的斜杠、由小写字母、数字、`_` 或 `-` 构成的名称，以及名称后紧接输入末尾或空白的形式。它将名称后的每个字节作为 `rawInput` 返回，其中包括分隔空白；消费方拥有各命令专用的语法，只能执行该语法允许的规范化。 diff --git a/packages/ui/commands/src/index.ts b/packages/ui/commands/src/index.ts index b1a5121243..b6dea581eb 100644 --- a/packages/ui/commands/src/index.ts +++ b/packages/ui/commands/src/index.ts @@ -71,6 +71,12 @@ export interface CommandDefinition { readonly description: string /** Optional free-form input hint advertised to capable clients. */ readonly input?: CommandInputDescriptor + /** + * Whether `command/run` records `rawInput`. Defaults to true. A command + * whose domain event owns the payload sets this false to avoid duplicating + * that payload in the session log. + */ + readonly recordInput?: boolean /** Execute against the receiving agent without sending the command to the model. */ readonly handler: (invocation: CommandInvocation) => CommandResult | Promise } @@ -127,9 +133,10 @@ declare module '@deepseek-ai/dsh-session' { * and `args` are `parseCommand`'s own split (name and verbatim rawInput, * separator whitespace included), so a consumer (a projection unit * folding its own command records, a rich command card) never re-parses - * a line. + * a line. `args` is absent when the definition sets `recordInput: false` + * because an authoritative domain event owns the input payload. */ - 'command/run': { commandId: CommandId; name: string; args: string; source: CommandSource } + 'command/run': { commandId: CommandId; name: string; args?: string; source: CommandSource } /** * The paired command settled. `kind`/`text` carry the handler's verbatim * outcome (a thrown/aborted handler settles as `kind: 'error'` with the @@ -239,6 +246,7 @@ function normalizeDefinition(definition: CommandDefinition): RegisteredCommand { name: definition.name, description: definition.description, ...input === undefined ? {} : { input }, + ...definition.recordInput === undefined ? {} : { recordInput: definition.recordInput }, handler: definition.handler, }) const descriptor = Object.freeze({ @@ -357,7 +365,10 @@ export class CommandService extends Service { if (signal.aborted) throw abortError(signal) const commandId = this.mintCommandId() this.appendLifecycle(agent.session, 'command/run', { - commandId, name: parsed.name, args: parsed.rawInput, source: { kind: 'user' }, + commandId, + name: parsed.name, + ...command.definition.recordInput === false ? {} : { args: parsed.rawInput }, + source: { kind: 'user' }, }) const invocation = Object.freeze({ agent, rawInput: parsed.rawInput, signal }) let result: CommandResult diff --git a/packages/ui/commands/tests/commands.spec.ts b/packages/ui/commands/tests/commands.spec.ts index f22e974d58..b85971f5d7 100644 --- a/packages/ui/commands/tests/commands.spec.ts +++ b/packages/ui/commands/tests/commands.spec.ts @@ -320,6 +320,25 @@ describe('CommandService', () => { ]) }) + it('omits raw input from command/run when an authoritative domain event owns it', async () => { + const ctx = await mount() + const { agent } = await mintAgentScope(ctx, 'a') + const seen = vi.fn(() => ({ kind: 'success' as const })) + ctx.commands.register({ + name: 'private', + description: 'Record privately', + recordInput: false, + handler: seen, + }) + + await ctx.commands.execute(agent, '/private keep this once', new AbortController().signal) + + expect(seen).toHaveBeenCalledWith(expect.objectContaining({ rawInput: ' keep this once' })) + const run = agent.session.events.find(event => event.type === 'command/run') + expect(run?.type).toBe('command/run') + expect(run?.type === 'command/run' && Object.hasOwn(run.data, 'args')).toBe(false) + }) + it('mints distinct monotonic commandIds across executions', async () => { const ctx = await mount() const { agent } = await mintAgentScope(ctx, 'a') From b8d51704f343d730fda933148e0c3a0f3176bb1f Mon Sep 17 00:00:00 2001 From: Turtle Date: Wed, 29 Jul 2026 21:43:31 +0800 Subject: [PATCH 03/22] docs: refresh feedback module graph --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 511e132360..61477ae104 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -618,6 +618,7 @@ flowchart TD pkg_client_ui_goal --> pkg_invariants pkg_command_feedback --> pkg_commands pkg_command_feedback --> pkg_invariants + pkg_command_feedback --> pkg_session pkg_pty_local --> pkg_agent pkg_pty_local --> pkg_invariants pkg_pty_local --> pkg_pty @@ -1092,7 +1093,7 @@ flowchart TD | [`acp`](../packages/acp/acp) | `acp` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`commands`](../packages/ui/commands), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`session-projection`](../packages/session-projection/session-projection), [`user-approval`](../packages/ui/user-approval) | | [`client-ui-goal`](../packages/client/ui-goal) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants) | -| [`command-feedback`](../packages/feedback/command-feedback) | `feedback` | [`commands`](../packages/ui/commands), [`invariants`](../packages/support/invariants) | +| [`command-feedback`](../packages/feedback/command-feedback) | `feedback` | [`commands`](../packages/ui/commands), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session) | | [`pty-local`](../packages/pty/pty-local) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subprocess`](../packages/subprocess/subprocess) | | [`tasks-local`](../packages/tasks/tasks-local) | `tasks` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tasks`](../packages/tasks/tasks), [`timeout`](../packages/util/timeout) | | [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel) | `telemetry` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-telemetry`](../packages/telemetry/session-telemetry) | From c836fcd416ddf0bc0c384fa24d6abbebdeb12c8d Mon Sep 17 00:00:00 2001 From: Turtle Date: Wed, 5 Aug 2026 12:43:35 +0800 Subject: [PATCH 04/22] feat(telemetry): add feedback-gated OTEL modes --- ...3-session-telemetry-otel-revival.i18n.yaml | 4 +- ...26-07-23-session-telemetry-otel-revival.md | 4 +- ...07-23-session-telemetry-otel-revival.zh.md | 4 +- .../2026-07-28-feedback-command.i18n.yaml | 4 +- .../feature/2026-07-28-feedback-command.md | 8 +- .../feature/2026-07-28-feedback-command.zh.md | 8 +- ...feedback-gated-session-telemetry.i18n.yaml | 6 + ...-08-05-feedback-gated-session-telemetry.md | 35 ++++ ...-05-feedback-gated-session-telemetry.zh.md | 35 ++++ docs/config-catalog.md | 16 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 4 +- .../tests/fixtures/telemetry-otel-driver.ts | 10 ++ .../tests/fixtures/telemetry-otel.cordis.yml | 9 + examples/package.json | 2 + packages/feedback/README.i18n.yaml | 4 +- packages/feedback/README.md | 2 +- packages/feedback/README.zh.md | 2 +- .../command-feedback/README.i18n.yaml | 4 +- packages/feedback/command-feedback/README.md | 4 +- .../feedback/command-feedback/README.zh.md | 4 +- packages/telemetry/README.i18n.yaml | 4 +- packages/telemetry/README.md | 6 +- packages/telemetry/README.zh.md | 6 +- .../session-telemetry-otel/README.i18n.yaml | 4 +- .../session-telemetry-otel/README.md | 16 +- .../session-telemetry-otel/README.zh.md | 16 +- .../session-telemetry-otel/package.json | 2 + .../session-telemetry-otel/src/index.ts | 94 +++++++---- .../session-telemetry-otel/src/invariant.ts | 7 +- .../tests/loader-composition.e2e.ts | 93 ++++++++--- .../session-telemetry-otel/tests/otel.spec.ts | 90 +++++++++- .../session-telemetry-otel/tsconfig.json | 3 + .../session-telemetry/README.i18n.yaml | 4 +- .../telemetry/session-telemetry/README.md | 11 +- .../telemetry/session-telemetry/README.zh.md | 11 +- .../session-telemetry/src/coordinator.ts | 158 ++++++++++++------ .../telemetry/session-telemetry/src/index.ts | 17 +- .../session-telemetry/tests/telemetry.spec.ts | 93 ++++++++++- pnpm-lock.yaml | 9 + 41 files changed, 635 insertions(+), 182 deletions(-) create mode 100644 .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md create mode 100644 .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml index cd9e4f7e9f..3f487762d6 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md -2026-07-23-session-telemetry-otel-revival.md: a58598d8a956d47cb0cf6aa3e659f38314bc4b17 -2026-07-23-session-telemetry-otel-revival.zh.md: cc09717e349d5ae2ab5157bf46de30b1823c775f +2026-07-23-session-telemetry-otel-revival.md: dcbff9757cbb730b66f456535fbd7ae471b6ffd1 +2026-07-23-session-telemetry-otel-revival.zh.md: c3a098041795fa92bb4e0dd421ca09be94907cb8 diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md index a58598d8a9..dcbff9757c 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md @@ -14,7 +14,7 @@ Every deployment that wants harness sessions in an observability stack must hand - **`@deepseek-ai/dsh-session-telemetry`** — the seam. `TelemetryBackend` (`emit`/`flush?`/`shutdown`), the service-registered `Telemetry` form, and `TelemetryCoordinator` owning capture: adoption with cursor read-back, the per-append firehose (project → `structuredClone` → redact → `emit`, zero I/O), the fixed first-chunk-per-(turn, step) projection, the `agent/error` relay, and dispose-time `shutdown` records. - **The `telemetry/record` waterfall** — the delta over the branch version and the seam's redaction extension point. Every record passes it before reaching any backend; the seam ships NO rules of its own — the innermost `next()` is a pass-through, deployments mount their rules as listeners (stacking by transforming `next()`'s return value), and a throwing rule withholds the record fail-closed. Redaction applies to the exported copy only; the canonical log is never rewritten. -- **`@deepseek-ai/dsh-session-telemetry-otel`** — the reference backend: OTel JS SDK log pipeline (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter), configured verbatim through `exporter`/`processor` passthroughs. `exporter.url` is required and validated at load; unmounted or unconfigured, nothing leaves the process. +- **`@deepseek-ai/dsh-session-telemetry-otel`** — the reference backend: OTel JS SDK log pipeline (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter), configured verbatim through `exporter`/`processor` passthroughs. Its default `FULL` mode requires `exporter.url`; the later [feedback-gated telemetry decision](2026-08-05-feedback-gated-session-telemetry.md) adds `FEEDBACK_ONLY` and `DISABLED` delivery modes without moving the redaction or backend boundary. The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry, queueing, and loss policy are the reporting SDK's, configured through passthroughs — delivery is best-effort (at-most-once across a crash), which the READMEs state plainly. @@ -34,4 +34,4 @@ The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry ## Consequences -A deployment adds one `cordis.yml` entry with an OTLP endpoint and gets its session stream in any OTel-compatible stack; removing the entry is the opt-out, with no residual state. A rule-free deployment exports records exactly as captured — including any credentials embedded in file contents or command output — so a deployment crossing a trust boundary must mount `telemetry/record` listeners, and both READMEs state this plainly. Where rules are mounted, exported bodies can differ from canonical log bytes, so receivers must not treat telemetry as a byte-exact replica; the log remains the source of truth. Crash durability is explicitly out of scope until the outbox decision above is revisited. +A deployment adds one `cordis.yml` entry with an OTLP endpoint and gets its session stream in any OTel-compatible stack. `FULL` preserves that behavior by default, `FEEDBACK_ONLY` withholds records until feedback releases a prefix, and `DISABLED` constructs no reporting pipeline; removing the entry remains a silent opt-out, while the disabled mode keeps the local feedback warning. A rule-free deployment exports records exactly as captured — including any credentials embedded in file contents or command output — so a deployment crossing a trust boundary must mount `telemetry/record` listeners, and both READMEs state this plainly. Where rules are mounted, exported bodies can differ from canonical log bytes, so receivers must not treat telemetry as a byte-exact replica; the log remains the source of truth. Crash durability is explicitly out of scope until the outbox decision above is revisited. diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md index cc09717e34..c3a0980417 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md @@ -14,7 +14,7 @@ Status: implemented - **`@deepseek-ai/dsh-session-telemetry`** —— seam 本体。`TelemetryBackend`（`emit`/`flush?`/`shutdown`）、服务注册形态的 `Telemetry`、以及拥有捕获侧的 `TelemetryCoordinator`：带游标回读的收养、逐 append 的 firehose（投影 → `structuredClone` → 脱敏 → `emit`，零 I/O）、固定的每 (turn, step) 首 chunk 投影、`agent/error` 转发、以及 dispose 时的 `shutdown` 记录。 - **`telemetry/record` waterfall** —— 相对分支版本的增量，也是该 seam 的脱敏扩展点。每条记录抵达任何 backend 前必经此处；seam 自身不带任何规则——最内层 `next()` 原样透传，部署方以监听器挂载自己的规则（通过变换 `next()` 的返回值堆叠），抛异常的规则将该记录 fail-closed 扣下。脱敏只作用于导出副本；canonical log 永不改写。 -- **`@deepseek-ai/dsh-session-telemetry-otel`** —— 参考 backend：OTel JS SDK 日志管线（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter），经 `exporter`/`processor` passthrough 原样配置。`exporter.url` 必填且加载时校验；未挂载或未配置时，任何数据都不会离开进程。 +- **`@deepseek-ai/dsh-session-telemetry-otel`** —— 参考 backend：OTel JS SDK 日志管线（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter），经 `exporter`/`processor` passthrough 原样配置。其默认 `FULL` 模式要求 `exporter.url`；后续的[反馈门控遥测决策](2026-08-05-feedback-gated-session-telemetry.md)增加了 `FEEDBACK_ONLY` 与 `DISABLED` 投递模式，但未移动脱敏或后端边界。 边界公理保持不变：harness 的职责止于 `emit()`。批处理、重试、排队与丢失策略属于 reporting SDK，经 passthrough 配置——投递是尽力而为（崩溃时至多一次），README 对此如实陈述。 @@ -34,4 +34,4 @@ Status: implemented ## Consequences -部署方在 `cordis.yml` 加一个带 OTLP endpoint 的条目即可把会话流接入任何 OTel 兼容体系；删除条目即退出，无残留状态。未挂载规则的部署导出的记录与捕获时完全一致——包括文件内容与命令输出中内嵌的任何凭据——因此跨信任边界的部署必须挂载 `telemetry/record` 监听器，两个 README 对此如实陈述。挂载规则后，导出的 body 可能与 canonical log 字节不同，接收端不得把遥测当作字节精确副本；日志仍是唯一事实源。崩溃持久性在上述 outbox 决定重启前明确不在范围内。 +部署方在 `cordis.yml` 加一个带 OTLP endpoint 的条目即可把会话流接入任何 OTel 兼容体系。`FULL` 默认保留该行为，`FEEDBACK_ONLY` 在反馈释放前暂存记录前缀，`DISABLED` 则不构造上报流水线；删除条目仍是静默退出方式，而禁用模式会保留本地反馈警告。未挂载规则的部署导出的记录与捕获时完全一致，包括文件内容与命令输出中内嵌的任何凭据。因此，跨信任边界的部署必须挂载 `telemetry/record` 监听器，两个 README 对此如实陈述。挂载规则后，导出的 body 可能与 canonical log 字节不同，接收端不得把遥测当作字节精确副本；日志仍是真源。崩溃持久性在上述 outbox 决定重启前明确不在范围内。 diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml index 7a429953d8..be039deb2c 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-28-feedback-command.md -2026-07-28-feedback-command.md: 1c093d0e37eb72dc66e3c5569bd642557dde56a1 -2026-07-28-feedback-command.zh.md: 300946a71ac7485a4bc787dd70ae5357147627f3 +2026-07-28-feedback-command.md: 963153ceb4332b74693ff5c1d248c616ff4e8de9 +2026-07-28-feedback-command.zh.md: 4dd02dcfb8d0606436c22e269db8c0d6cf163cee diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.md b/.agents/notes/implemented/feature/2026-07-28-feedback-command.md index 1c093d0e37..963153ceb4 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.md +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.md @@ -18,7 +18,7 @@ The package declares the log-only `feedback/record { text }` session event and e `dsh-commands` still writes its `command/run` / `command/done` lifecycle pair around `/feedback`, but this command sets `recordInput: false`. Its `command/run` therefore carries the command identity and source without `args`; the feedback text exists only in `feedback/record`, while `command/done` carries the acknowledgement outcome. All three records are log-only and non-surface. Their appends start persistence's ordinary eager drain; nothing forces a flush, so acknowledgement reports that the feedback is in the log rather than already on disk. -Capture is deliberately inert: nothing in this repository reads `feedback/record`. +Capture remains inert for the running agent and model. The optional OTel telemetry package later adds one infrastructure consumer: it observes `feedback/record` as a release trigger in `FEEDBACK_ONLY` mode and as the local-only warning trigger in `DISABLED` mode, without changing the feedback event or command path. See [Feedback-gated session telemetry](2026-08-05-feedback-gated-session-telemetry.md). ### Why feedback owns an event @@ -34,7 +34,7 @@ Surrounding whitespace is discarded, but nothing else is parsed. `/feedback /pla ### A new group -`packages/feedback/` is a new group because no existing one owns this. `goal/` is objective state, `session-title/` is titles, `core/` is the product spine. The group holds one package; a consumer would join it rather than forcing this one to grow. +`packages/feedback/` is a new group because no existing one owns this. `goal/` is objective state, `session-title/` is titles, `core/` is the product spine. The group holds one producer package; cross-cutting consumers stay in their owning groups rather than forcing this one to grow. ## Alternatives considered @@ -48,7 +48,7 @@ Surrounding whitespace is discarded, but nothing else is parsed. `/feedback /pla **Register the command inside an existing package** such as `packages/ui/commands`. Avoids a new group and its README pair. Rejected: `ctx.commands` is the registry, not a home for arbitrary command implementations, and the requester asked for a standalone package. -**Parse structure out of the text** (category prefixes, severity markers). Rejected as speculative: no consumer exists to use the structure, and any control-word grammar makes the corresponding literal feedback unrecordable. Verbatim text is the widest surface a future consumer can narrow; a parsed one cannot be widened after the fact. +**Parse structure out of the text** (category prefixes, severity markers). Rejected as speculative: no consumer needs that structure, and any control-word grammar makes the corresponding literal feedback unrecordable. Verbatim text is the widest surface a future consumer can narrow; a parsed one cannot be widened after the fact. **Add a model-facing tool instead of a slash command.** Rejected: feedback is a direct human observation. Routing it through the model spends a turn, lets the model paraphrase the user's words, and makes the record contingent on the model choosing to call the tool. @@ -58,6 +58,6 @@ The TUI mounts the command unconditionally — no configuration, no dependency o The package owns one independent append-only event with no cross-event or mutable-data relation for an invariant companion to check. The event follows the session log's existing replay, fork, persistence, and crash-tail behavior. -Deferred: no consumer; no structured fields; no amend or withdraw, since the log is append-only and this package adds no tombstone; and no explicit durability barrier, so an entry recorded immediately before a crash can be lost with any other unflushed tail. +Deferred: no product or model consumer; no structured fields; no amend or withdraw, since the log is append-only and this package adds no tombstone; and no explicit durability barrier, so an entry recorded immediately before a crash can be lost with any other unflushed tail. The optional telemetry consumer treats the event only as an export-policy trigger. No snapshot accompanies this change. AGENTS.md asks for a keyless snapshot through a runnable example for product-user-visible behavior; this was skipped at the requester's explicit direction. The package tests plus a real Loader composition test over a `cordis.yml` are the whole of the evidence, alongside interactive verification in the assembled TUI. diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md b/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md index 300946a71a..4dd02dcfb8 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md @@ -18,7 +18,7 @@ Status: implemented `dsh-commands` 仍会围绕 `/feedback` 写入 `command/run` / `command/done` 生命周期配对，但该命令设置了 `recordInput: false`。因此，它的 `command/run` 携带命令标识与来源，但不携带 `args`；反馈文本只存在于 `feedback/record` 中，而 `command/done` 携带确认结果。三个记录都仅写入日志且非 surface。它们的追加会启动持久化的常规即时排空；没有任何环节强制 flush，因此确认文本报告的是反馈已进入日志，而非已经落盘。 -采集刻意不产生后续动作：本仓库中没有任何代码读取 `feedback/record`。 +采集对正在运行的 agent 与模型仍不产生后续动作。可选的 OTel 遥测包后续增加了一个基础设施消费方：它在 `FEEDBACK_ONLY` 模式下将 `feedback/record` 作为释放触发器，在 `DISABLED` 模式下将其作为本地警告触发器，且不改变反馈事件或命令路径。见[反馈门控的会话遥测](2026-08-05-feedback-gated-session-telemetry.md)。 ### 为何反馈拥有自己的事件 @@ -34,7 +34,7 @@ Status: implemented ### 一个新的分组 -`packages/feedback/` 是新分组，因为现有分组都不拥有此职责：`goal/` 负责目标状态，`session-title/` 负责标题，`core/` 是产品主干。该分组目前只有一个包；未来的消费方应加入该分组，而不是迫使这个包不断膨胀。 +`packages/feedback/` 是新分组，因为现有分组都不拥有此职责：`goal/` 负责目标状态，`session-title/` 负责标题，`core/` 是产品主干。该分组只包含一个生产方包；跨领域的消费方留在各自所属的分组，而不是迫使这个包不断膨胀。 ## 考虑过的替代方案 @@ -48,7 +48,7 @@ Status: implemented **在现有包中注册该命令**，例如 `packages/ui/commands`。可省去新分组及其双语 README。已否决：`ctx.commands` 是注册表，而不是任意命令实现的归属地；且请求者明确要求独立的包。 -**从文本中解析结构**（类别前缀、严重程度标记）。已否决，属于投机设计：目前没有消费方使用该结构，而任何控制词语法都会让对应的字面反馈无法记录。原样文本是未来消费方可以收窄的最宽接口；而已被解析的接口无法事后放宽。 +**从文本中解析结构**（类别前缀、严重程度标记）。已否决，属于投机设计：没有消费方需要该结构，而任何控制词语法都会让对应的字面反馈无法记录。原样文本是未来消费方可以收窄的最宽接口；而已被解析的接口无法事后放宽。 **改为提供面向模型的工具。** 已否决：反馈是人类的直接观察。经由模型会消耗一个轮次、让模型改写用户的原话，并使记录取决于模型是否选择调用该工具。 @@ -58,6 +58,6 @@ TUI 无条件挂载该命令：没有配置，也不依赖 goal 栈。无头 CLI 本包拥有一个独立的仅追加事件，不存在跨事件关系或可变数据关系可供不变式伴生插件检查。该事件遵循会话日志现有的回放、fork、持久化和崩溃尾部行为。 -延期事项：没有消费方；没有结构化字段；不支持修改或撤回，因为日志仅追加且本包不新增 tombstone；且没有显式持久化屏障，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。 +延期事项：没有产品或模型消费方；没有结构化字段；不支持修改或撤回，因为日志仅追加且本包不新增 tombstone；且没有显式持久化屏障，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。可选的遥测消费方只将该事件作为导出策略触发器。 本次变更不附带 snapshot。AGENTS.md 要求面向产品用户的可见行为变更通过可运行示例附带无密钥 snapshot；此项按请求者的明确指示跳过。包测试连同一个基于真实 `cordis.yml` 的 Loader 组合测试即为全部证据，此外还有在组装后 TUI 中的交互验证。 diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml new file mode 100644 index 0000000000..d12ad78728 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md +2026-08-05-feedback-gated-session-telemetry.md: 21a9028c603f3faaec39b2ddb8ef14644d6c84d4 +2026-08-05-feedback-gated-session-telemetry.zh.md: ea94c743b962a93a5fc64bdc2e4ed103aadecc99 diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md new file mode 100644 index 0000000000..21a9028c60 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md @@ -0,0 +1,35 @@ +# Agent Note: Feedback-gated session telemetry + +Status: implemented + +English | [中文](2026-08-05-feedback-gated-session-telemetry.zh.md) + +## Problem + +Session telemetry originally has one mounted behavior: every accepted record enters the reporting backend immediately. Deployments need two stricter policies without replacing the plugin: hold a session's telemetry unless its user records feedback, or disable reporting while still explaining what happens to feedback. The policy must preserve the existing full-export default and the telemetry seam's redaction-before-backend boundary. + +## Decision + +`@deepseek-ai/dsh-session-telemetry-otel` exposes three uppercase `mode` values: + +- `FULL` is the default and preserves immediate delivery to the configured OTel pipeline. +- `FEEDBACK_ONLY` captures redacted copies in memory and releases the pending session prefix when `feedback/record` is appended. The released prefix includes the feedback event itself. Records appended after that event form another withheld prefix until another feedback event releases them. +- `DISABLED` constructs no exporter, processor, or logger provider. A `feedback/record` listener prints that nothing is shared and the feedback remains local. + +The generic telemetry coordinator owns the delivery distinction as `immediate` or `held`. Both paths project, clone, and run `telemetry/record` listeners at capture time. Immediate delivery sends the accepted record to the backend and advances the session's handoff cursor. Held delivery retains the accepted record per session without moving that cursor. `release(session)` submits the retained records in order, contains each backend failure independently, advances the cursor only for submitted records, and removes the released prefix. + +The OTel feedback listener is registered after the coordinator's session listener. Cordis therefore gives the coordinator the feedback append first, then the OTel listener releases a prefix that already contains that event. `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`; `DISABLED` does not validate or use exporter configuration. + +## Alternatives considered + +**Open a session permanently after its first feedback.** Rejected because later work would be shared without another feedback act and the plugin would need additional open-session state. Releasing one pending prefix per feedback has the smaller state machine and the narrower sharing boundary. + +**Buffer after `TelemetryCoordinator.emit()` in the OTel backend.** Rejected because the coordinator would advance its handoff cursor before a record became eligible for upload. A plugin rebuild would then lose the only retained copy and incorrectly treat the prefix as handed off. + +**Replay the canonical session log when feedback arrives.** Rejected because replay would repeat projection and redaction, exclude telemetry operation records that are not session events, and require more lifecycle state to distinguish previously released prefixes. + +**Use an unmounted plugin as the disabled state.** That remains the silent opt-out, but it cannot warn when feedback is recorded. The explicit disabled mode lets a deployment keep one configuration shape and communicate that the local feedback did not leave the process. + +## Consequences + +`FULL` remains source- and wire-compatible with the original default. `FEEDBACK_ONLY` retains deep-copied, already-redacted records in process memory until feedback or session collection; a crash before release uploads nothing from that prefix. A clean shutdown after the last feedback is part of the new withheld suffix, so feedback-only streams do not carry a reliable shutdown or crash signal. Each later feedback releases the suffix accumulated since the previous one. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log. diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md new file mode 100644 index 0000000000..ea94c743b9 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md @@ -0,0 +1,35 @@ +# Agent Note：反馈门控的会话遥测 + +Status: implemented + +[English](2026-08-05-feedback-gated-session-telemetry.md) | 中文 + +## 问题 + +会话遥测原本只有一种已挂载行为：每条已接受记录都立即进入上报后端。部署方需要两种更严格的策略，且不替换插件：只有用户记录反馈时才释放该会话的遥测，或禁用上报并仍向用户说明反馈的去向。该策略必须保留现有的全量导出默认值，以及遥测 seam 在记录抵达后端之前脱敏的边界。 + +## 决策 + +`@deepseek-ai/dsh-session-telemetry-otel` 公开三个大写的 `mode` 值： + +- `FULL` 是默认值，保留向已配置 OTel 流水线的即时投递。 +- `FEEDBACK_ONLY` 在内存中捕获已脱敏副本，并在追加 `feedback/record` 时释放待处理的会话前缀。已释放前缀包含反馈事件本身。在该事件之后追加的记录会形成另一个暂存前缀，直到下一个反馈事件将其释放。 +- `DISABLED` 不构造导出器、处理器或日志提供方。`feedback/record` 监听器会输出警告，说明什么都不会共享，且反馈仍留在本地。 + +通用遥测协调器以 `immediate` 或 `held` 的形式拥有这两种投递方式。两条路径都会在捕获时进行投影、深拷贝，并运行 `telemetry/record` 监听器。即时投递把已接受记录发送到后端，并推进会话的 handoff 游标。暂存投递按会话保留已接受记录，且不移动该游标。`release(session)` 按顺序提交保留的记录，独立隔离每个后端失败，仅为已提交的记录推进游标，并移除已释放前缀。 + +OTel 反馈监听器在协调器的会话监听器之后注册。因此，Cordis 先将反馈追加交给协调器，再由 OTel 监听器释放已包含该事件的前缀。`exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填；`DISABLED` 不校验也不使用导出器配置。 + +## 考虑过的替代方案 + +**会话在首次反馈后永久开放。** 已否决，因为后续工作会在用户未再次提交反馈的情况下被共享，而且插件需要额外的会话开放状态。每次反馈只释放一个待处理前缀，状态机更小，共享边界也更窄。 + +**在 OTel 后端的 `TelemetryCoordinator.emit()` 之后缓冲。** 已否决，因为协调器会在记录具备上传资格前推进 handoff 游标。插件重建后，唯一保留的副本会丢失，而协调器会错误地将该前缀视为已交接。 + +**反馈到达时回放权威会话日志。** 已否决，因为回放会重复执行投影与脱敏，排除不属于会话事件的遥测运维记录，且需要更多生命周期状态才能区分已释放前缀。 + +**以不挂载插件表示禁用状态。** 这仍然是静默退出方式，但无法在记录反馈时输出警告。显式禁用模式让部署方可以保持同一种配置形态，并说明本地反馈未离开进程。 + +## 后果 + +`FULL` 与原有默认值保持源码及协议兼容。`FEEDBACK_ONLY` 会在进程内存中保留已深拷贝且已脱敏的记录，直到收到反馈或会话被回收；释放前发生崩溃时，该前缀不上传任何内容。上次反馈之后的干净关闭属于新的暂存后缀，因此仅反馈的流不携带可靠的关闭或崩溃信号。每个后续反馈都会释放从上一个反馈开始累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index f552e6ab63..0c4fb632c1 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1159,12 +1159,13 @@ Requires: `sessions` ```ts config-catalog /** - * Plugin configuration: two verbatim SDK option shapes plus nothing else. - * `exporter.url` is the one field this package validates itself — required, - * no default, must parse as an `http(s)` URL — because a missing endpoint - * must fail at plugin load, not at first export. + * Plugin configuration: one sharing policy plus two verbatim SDK option + * shapes. `exporter.url` is required for modes that upload and unused for + * `DISABLED`. */ export interface Config { + /** Sharing policy; defaults to immediate `FULL` delivery. */ + mode?: TelemetryMode /** * Passed verbatim to the SDK's OTLP/HTTP log exporter — the complete * `OTLPExporterNodeConfigBase` shape (`headers`, `timeoutMillis`, @@ -1172,7 +1173,7 @@ export interface Config { * is the one field this package requires and validates itself. */ exporter?: OTLPExporterNodeConfigBase & { - /** Full logs endpoint (e.g. `https://collector.example.com/v1/logs`). Required; validated at plugin load. */ + /** Full logs endpoint (e.g. `https://collector.example.com/v1/logs`). Required outside `DISABLED`; validated at load. */ url?: string } /** @@ -1181,11 +1182,14 @@ export interface Config { */ processor?: Omit } + +/** Session-sharing policy selected by {@link Config.mode}. */ +export type TelemetryMode = typeof TELEMETRY_MODES[number] ``` Depends on: `BatchLogRecordProcessorOptions` (`@opentelemetry/sdk-logs`) · `OTLPExporterNodeConfigBase` (`@opentelemetry/otlp-exporter-base`) -Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:40`](../packages/telemetry/session-telemetry-otel/src/index.ts) +Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:54`](../packages/telemetry/session-telemetry-otel/src/index.ts) ## `@deepseek-ai/dsh-session-title` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 54291934fd..d159fa0a53 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -853,7 +853,7 @@ Transform one outbound record before it reaches the backend. This waterfall is t 'telemetry/record'(record: TelemetryRecord, next: () => TelemetryRecord): TelemetryRecord ``` -Source: [`packages/telemetry/session-telemetry/src/index.ts:41`](../../packages/telemetry/session-telemetry/src/index.ts) +Source: [`packages/telemetry/session-telemetry/src/index.ts:42`](../../packages/telemetry/session-telemetry/src/index.ts) ## `tools/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 395d0850e1..e051463877 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -1996,7 +1996,7 @@ flush?(): void abstract shutdown(): Promise ``` -Source: [`packages/telemetry/session-telemetry/src/index.ts:135`](../../packages/telemetry/session-telemetry/src/index.ts) +Source: [`packages/telemetry/session-telemetry/src/index.ts:140`](../../packages/telemetry/session-telemetry/src/index.ts) ## `ctx.tokenMeter` — `TokenMeterService` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index fabd16bbdd..4ccc19f305 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -33,7 +33,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:58`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`llm-replay`](../packages/support/llm-replay), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-title`](../packages/session-title/session-title) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:71`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | `apiproxy`, [`compact`](../packages/compact/compact), [`goal`](../packages/goal/goal), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`llm-retry`](../packages/llm/llm-retry), [`plan-mode`](../packages/plan/plan-mode), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-telemetry`](../packages/telemetry/session-telemetry), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:81`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), `apiproxy`, [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection-cache`](../packages/session-projection/session-projection-cache), [`session-telemetry`](../packages/telemetry/session-telemetry), [`session-title`](../packages/session-title/session-title) | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:93`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/acp/acp), `apiproxy`, [`cli-demo`](../packages/examples/cli-demo), [`compact`](../packages/compact/compact), [`compact-basic`](../packages/compact/compact-basic), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection`](../packages/session-projection/session-projection), [`session-projection-cache`](../packages/session-projection/session-projection-cache), [`session-telemetry`](../packages/telemetry/session-telemetry), [`session-title`](../packages/session-title/session-title), [`token-meter`](../packages/llm/token-meter), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-approval`](../packages/ui/user-approval), [`workspace-context`](../packages/context/workspace-context) | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:93`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/acp/acp), `apiproxy`, [`cli-demo`](../packages/examples/cli-demo), [`compact`](../packages/compact/compact), [`compact-basic`](../packages/compact/compact-basic), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection`](../packages/session-projection/session-projection), [`session-projection-cache`](../packages/session-projection/session-projection-cache), [`session-telemetry`](../packages/telemetry/session-telemetry), [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel), [`session-title`](../packages/session-title/session-title), [`token-meter`](../packages/llm/token-meter), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-approval`](../packages/ui/user-approval), [`workspace-context`](../packages/context/workspace-context) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:103`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence), [`session-telemetry`](../packages/telemetry/session-telemetry) | | `slash/input-begin-command` | `bail` | [`packages/client/ui-slash/src/types.ts:230`](../packages/client/ui-slash/src/types.ts) | - | `ui-conversation` | | `slash/input-consume-token` | `bail` | [`packages/client/ui-slash/src/types.ts:244`](../packages/client/ui-slash/src/types.ts) | - | `ui-conversation` | @@ -45,7 +45,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:131`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`subagent`](../packages/subagent/subagent) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:29`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:35`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | -| `telemetry/record` | `waterfall` | [`packages/telemetry/session-telemetry/src/index.ts:41`](../packages/telemetry/session-telemetry/src/index.ts) | [`session-telemetry`](../packages/telemetry/session-telemetry) (`waterfall`) | - | +| `telemetry/record` | `waterfall` | [`packages/telemetry/session-telemetry/src/index.ts:42`](../packages/telemetry/session-telemetry/src/index.ts) | [`session-telemetry`](../packages/telemetry/session-telemetry) (`waterfall`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:156`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | | `tools/code-dispatch-log` | `waterfall` | [`packages/core/tools/src/index.ts:138`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`spill-policy`](../packages/spill/spill-policy) | | `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:113`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`timeout-policy`](../packages/timeout/timeout-policy) | diff --git a/examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts b/examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts index 02be1a9011..72305f0724 100644 --- a/examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts +++ b/examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts @@ -11,6 +11,7 @@ import { createServer } from 'node:http' import { once } from 'node:events' import { boot, resolveConfigPath } from '@deepseek-ai/dsh-app-boot' import { runOneShot } from '@deepseek-ai/dsh-cli-demo/src/cli.ts' +import { recordFeedback } from '@deepseek-ai/dsh-command-feedback' const configPath = process.argv[2] if (configPath === undefined) throw new Error('telemetry-otel driver requires a config path') @@ -35,6 +36,15 @@ try { // The fixture credential rides the model-visible user message; the exported // copy must scrub it while the canonical log keeps the original bytes. await runOneShot(ctx, { task: 'prove telemetry with key sk-e2efixture1234567890' }) + const mode = process.env.DSH_TELEMETRY_E2E_MODE ?? 'FULL' + if (mode !== 'FULL') { + const [agent] = ctx.get('agents')?.roots() ?? [] + if (agent === undefined) throw new Error('telemetry-otel driver requires one root agent') + recordFeedback(agent.session, 'fixture feedback') + if (mode === 'FEEDBACK_ONLY') { + await runOneShot(ctx, { task: 'post-feedback private suffix' }) + } + } } finally { await ctx.fiber.dispose() } diff --git a/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml b/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml index 34e23b828e..1433173768 100644 --- a/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml +++ b/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml @@ -2,6 +2,14 @@ # path, exporting to the mock OTLP collector the driver starts (url via env). # The redact-rule entry models a deployment mounting its own scrub rule on the # telemetry/record waterfall — the seam itself ships no rules. +- id: logger-console + name: '@cordisjs/plugin-logger-console' + config: + colors: false + levels: + default: 3 + showTime: '' + - id: cli-mock-llm name: './cli-mock-llm.ts' @@ -14,6 +22,7 @@ - id: telemetry-otel name: '@deepseek-ai/dsh-session-telemetry-otel' config: + mode: !!js process.env.DSH_TELEMETRY_E2E_MODE || 'FULL' exporter: url: !!js process.env.DSH_TELEMETRY_E2E_URL diff --git a/examples/package.json b/examples/package.json index 51fc48b8fa..0298685693 100644 --- a/examples/package.json +++ b/examples/package.json @@ -7,6 +7,7 @@ "dependencies": { "@cordisjs/plugin-hmr": "workspace:*", "@cordisjs/plugin-include": "workspace:*", + "@cordisjs/plugin-logger-console": "workspace:*", "@deepseek-ai/dsh-acp-demo": "workspace:*", "@deepseek-ai/dsh-agent-spine-demo": "workspace:*", "@deepseek-ai/dsh-app-boot": "workspace:*", @@ -14,6 +15,7 @@ "@deepseek-ai/dsh-bash-sandbox": "workspace:*", "@deepseek-ai/dsh-cli-demo": "workspace:*", "@deepseek-ai/dsh-code-runtime-worker": "workspace:*", + "@deepseek-ai/dsh-command-feedback": "workspace:*", "@deepseek-ai/dsh-compact-basic": "workspace:*", "@deepseek-ai/dsh-compact-tool-result-prune": "workspace:*", "@deepseek-ai/dsh-fs-local": "workspace:*", diff --git a/packages/feedback/README.i18n.yaml b/packages/feedback/README.i18n.yaml index 31ed2d25e8..4ad5a93fb5 100644 --- a/packages/feedback/README.i18n.yaml +++ b/packages/feedback/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/feedback/README.md -README.md: 7962a16ee9bc7d8a969a466591d761829cd55d7f -README.zh.md: aad8f4d797ff16a5ef9be4c968fb28d708bad13e +README.md: d2a4a5a27e1c661d2f62b328578fd890a0c622ee +README.zh.md: 2fa42e3bb5f05dfc425356f302f44e497b100f24 diff --git a/packages/feedback/README.md b/packages/feedback/README.md index 7962a16ee9..d2a4a5a27e 100644 --- a/packages/feedback/README.md +++ b/packages/feedback/README.md @@ -8,4 +8,4 @@ The feedback family lets a human record a remark about the session without actin |---|---|---| | `command-feedback/` | Trigger-independent `feedback/record` event plus the human-facing `/feedback` producer | — | -A recorded remark is log-only: it never enters the model surface or derived history, and no shipped plugin consumes it. A future consumer reads `feedback/record` events from the session log rather than changing how they are captured. +A recorded remark is log-only: it never enters the model surface or derived history. When mounted, [`dsh-session-telemetry-otel`](../telemetry/session-telemetry-otel/) observes `feedback/record` to release a pending telemetry prefix or warn that disabled telemetry leaves the feedback local; capture itself remains independent of that policy. diff --git a/packages/feedback/README.zh.md b/packages/feedback/README.zh.md index aad8f4d797..2fa42e3bb5 100644 --- a/packages/feedback/README.zh.md +++ b/packages/feedback/README.zh.md @@ -8,4 +8,4 @@ feedback 家族让人类记录对会话的评价，但不据此采取任何动 |---|---|---| | `command-feedback/` | 与触发方式无关的 `feedback/record` 事件，以及面向用户的 `/feedback` 生产方 | 无 | -被记录的评价仅写入日志：它绝不会进入模型 surface 或派生历史，随附插件也不会消费它。未来的消费方从会话日志中读取 `feedback/record` 事件，而不是改变它们的采集方式。 +被记录的评价仅写入日志：它绝不会进入模型 surface 或派生历史。挂载后，[`dsh-session-telemetry-otel`](../telemetry/session-telemetry-otel/) 会观察 `feedback/record`，以释放待处理的遥测前缀，或在遥测已禁用时警告反馈将留在本地；采集本身与该策略相互独立。 diff --git a/packages/feedback/command-feedback/README.i18n.yaml b/packages/feedback/command-feedback/README.i18n.yaml index 47c169ec3f..ea439ce2fe 100644 --- a/packages/feedback/command-feedback/README.i18n.yaml +++ b/packages/feedback/command-feedback/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/feedback/command-feedback/README.md -README.md: c9650d6a2c595550545b3dbf07f62e6aa65f39b9 -README.zh.md: ba24276ba1bd71a4eb68c7fdb48a3760bdbec8fc +README.md: e3b0e58f1746c7bcd1c74ac0990a872a1f24d7d7 +README.zh.md: 40ec871caff6f90b0b1c685e833c874e32a48d16 diff --git a/packages/feedback/command-feedback/README.md b/packages/feedback/command-feedback/README.md index c9650d6a2c..e3b0e58f17 100644 --- a/packages/feedback/command-feedback/README.md +++ b/packages/feedback/command-feedback/README.md @@ -15,7 +15,7 @@ Surrounding whitespace is discarded, but feedback is otherwise unparsed: no trun ## What this plugin does and does not do -`recordFeedback(session, text)` is the command-independent write path. It rejects empty normalized text and appends `feedback/record { text }`; a different UI, hook, or host integration can call it without constructing a slash command. The `/feedback` handler uses that producer, starts no model work, and no plugin in this repository reads the event. +`recordFeedback(session, text)` is the command-independent write path. It rejects empty normalized text and appends `feedback/record { text }`; a different UI, hook, or host integration can call it without constructing a slash command. The `/feedback` handler uses that producer and starts no model work. The optional [`dsh-session-telemetry-otel`](../../telemetry/session-telemetry-otel/) consumer observes the event without changing its capture contract. The feedback text appears in exactly one durable payload: `feedback/record`. [`dsh-commands`](../../ui/commands/README.md) still appends its generic `command/run` / `command/done` pairing, but this definition sets `recordInput: false`, so `command/run` omits `args`; the paired `command/done` carries only the outcome. All three events are log-only and absent from the ordered surface, `deriveMessages()`, and model requests. These appends start persistence's ordinary eager drain, but neither producer forces `session/flush`, so acknowledgement means the feedback is in the log, not that it has reached disk. Rejected empty input leaves only the command pairing settled as `kind: 'error'`, with no `feedback/record`. @@ -52,7 +52,7 @@ Independent of the model request path. Recording appends to the session log only ## Known Limitations and Deferred Work -- **Nothing consumes the recorded feedback** — capture is deliberately inert. There is no retrieval, aggregation, export, or reporting surface, and no model-facing tool reads `feedback/record`; a consumer is a separate package. +- **No feedback retrieval or management surface** — the optional OTel plugin uses the event only as a sharing trigger. There is no retrieval, aggregation, categorization, or model-facing tool for `feedback/record`. - **No structured fields** — an entry is one free-text string with no category, severity, or referenced-event link, so feedback cannot be filtered by subject without re-reading its text. - **No amend or withdraw** — the session log is append-only and this package adds no tombstone, so a mistaken entry stays recorded and can only be superseded by a later one. - **No explicit durability barrier** — the acknowledgement follows the append, not a flush, so an entry recorded immediately before a crash can be lost with any other unflushed tail. Feedback is not worth forcing a synchronous disk write for; a consumer that needs one awaits `ctx.sessions.flush(session)`. diff --git a/packages/feedback/command-feedback/README.zh.md b/packages/feedback/command-feedback/README.zh.md index ba24276ba1..40ec871caf 100644 --- a/packages/feedback/command-feedback/README.zh.md +++ b/packages/feedback/command-feedback/README.zh.md @@ -15,7 +15,7 @@ ## 本插件做什么、不做什么 -`recordFeedback(session, text)` 是不依赖命令的写入路径。它拒绝规范化后为空的文本，并追加 `feedback/record { text }`；其他 UI、钩子或 host 集成无需构造斜杠命令即可调用它。`/feedback` 处理器通过该生产方写入，不启动任何模型工作；本仓库中也没有任何插件读取该事件。 +`recordFeedback(session, text)` 是不依赖命令的写入路径。它拒绝规范化后为空的文本，并追加 `feedback/record { text }`；其他 UI、钩子或 host 集成无需构造斜杠命令即可调用它。`/feedback` 处理器通过该生产方写入，且不启动任何模型工作。可选的 [`dsh-session-telemetry-otel`](../../telemetry/session-telemetry-otel/) 消费方会观察该事件，但不改变它的采集契约。 反馈文本只出现在一个持久载荷中：`feedback/record`。[`dsh-commands`](../../ui/commands/README.md) 仍会追加通用的 `command/run` / `command/done` 配对，但此定义设置了 `recordInput: false`，因此 `command/run` 会省略 `args`；配对的 `command/done` 只携带结果。三个事件都仅写入日志，不出现在有序 surface、`deriveMessages()` 以及模型请求中。这些追加会启动持久化的常规即时排空，但两个生产方都不会强制 `session/flush`，因此确认文本表示反馈已进入日志，而不表示它已经落盘。被拒绝的空输入只会留下以 `kind: 'error'` 结算的命令配对，不会产生 `feedback/record`。 @@ -52,7 +52,7 @@ TUI 应用无条件挂载此命令；它没有配置，也不依赖持久 goal ## 已知限制与暂缓工作 -- **没有任何消费方读取被记录的反馈**：采集刻意不产生任何后续动作。这里没有检索、聚合、导出或报告 surface，也没有面向模型的工具读取 `feedback/record`；消费方是另一个独立包。 +- **没有反馈检索或管理 surface**：可选的 OTel 插件仅将该事件用作共享触发器。本包不为 `feedback/record` 提供检索、聚合、分类或面向模型的工具。 - **没有结构化字段**：一条条目就是一个自由文本字符串，没有类别、严重程度或关联事件链接，因此无法在不重读文本的情况下按主题过滤反馈。 - **不支持修改或撤回**：会话日志是仅追加的，本包也不新增 tombstone，因此错误的条目会一直保留在记录中，只能由后续条目取代。 - **没有显式持久化屏障**：确认文本紧随追加而非 flush，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。为反馈强制同步写盘并不值得；需要该保证的消费方可自行等待 `ctx.sessions.flush(session)`。 diff --git a/packages/telemetry/README.i18n.yaml b/packages/telemetry/README.i18n.yaml index 41f1bd956f..cd3be8d155 100644 --- a/packages/telemetry/README.i18n.yaml +++ b/packages/telemetry/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/telemetry/README.md -README.md: 944cb3f9bac6169feddf8b49bc481cfbe7c6fa9d -README.zh.md: 795b20abb47e1bf791730cc7f3ebb0522549a271 +README.md: 0adf140a19bd6ab19c4d4139d4ebdae941c0d1b0 +README.zh.md: 57988732e36d105ebcc48adcdab9344a6cccb525 diff --git a/packages/telemetry/README.md b/packages/telemetry/README.md index 944cb3f9ba..0adf140a19 100644 --- a/packages/telemetry/README.md +++ b/packages/telemetry/README.md @@ -2,9 +2,9 @@ English | [中文](README.zh.md) -Outbound session reporting: the telemetry seam plus its OpenTelemetry backend. The design — the boundary axiom (the harness's aspect ends at `emit()`; delivery is the reporting SDK's), the `telemetry/record` waterfall (deployment-mounted redaction rules; the seam ships none), the fixed chunk projection, the handoff cursor, and the operational-record channel — is pinned in [the revival Agent Note](../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md). +Outbound session reporting: the telemetry seam plus its OpenTelemetry backend. The boundary axiom, redaction waterfall, fixed chunk projection, handoff cursor, and operational-record channel are pinned in [the revival Agent Note](../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md); immediate, feedback-gated, and disabled delivery are owned by [the mode decision](../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md). | Package | Role | |---|---| -| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | The seam: capture points, projection, redaction, handoff cursor, ops signals, and the minimal backend contract (`emit`/`flush?`/`shutdown`). | -| [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | The backend a deployment loads: the OTel JS SDK's log pipeline (`LoggerProvider` + `BatchLogRecordProcessor` + OTLP/HTTP exporter), configured verbatim through passthroughs. | +| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | The seam: capture points, projection, redaction, immediate or held handoff, cursor, ops signals, and the minimal backend contract (`emit`/`flush?`/`shutdown`). | +| [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | The backend a deployment loads: `FULL`, `FEEDBACK_ONLY`, or `DISABLED` policy around the OTel JS SDK log pipeline. | diff --git a/packages/telemetry/README.zh.md b/packages/telemetry/README.zh.md index 795b20abb4..57988732e3 100644 --- a/packages/telemetry/README.zh.md +++ b/packages/telemetry/README.zh.md @@ -2,9 +2,9 @@ [English](README.md) | 中文 -面向外部的会话上报：遥测（telemetry）seam 及其 OpenTelemetry 后端。整套设计固定在[复活 Agent Note（agent 决策记录）](../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)中：边界公理（harness 的职责止于 `emit()`，投递由上报 SDK 负责）、`telemetry/record` waterfall（瀑布式事件；脱敏规则由部署方挂载，seam 自身不带任何规则）、固定分片投影、handoff 游标，以及运维记录通道。 +面向外部的会话上报：遥测（telemetry）seam 及其 OpenTelemetry 后端。边界公理、脱敏 waterfall（瀑布式事件）、固定分片投影、handoff 游标及运维记录通道的决定见[复活 Agent Note（agent 决策记录）](../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)；即时、反馈门控及禁用投递由[模式决策](../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md)统一规定。 | 包（package） | 职责 | |---|---| -| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | seam 本体：捕获点、投影、脱敏、handoff 游标、运维信号，以及最小后端契约（`emit`/`flush?`/`shutdown`）。 | -| [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | 部署方要加载的后端：OTel JS SDK 的日志流水线（`LoggerProvider` + `BatchLogRecordProcessor` + OTLP/HTTP 导出器），经透传（passthrough）原样配置。 | +| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | seam 本体：捕获点、投影、脱敏、即时或暂存交接、游标、运维信号，以及最小后端契约（`emit`/`flush?`/`shutdown`）。 | +| [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | 部署方要加载的后端：围绕 OTel JS SDK 日志流水线实施 `FULL`、`FEEDBACK_ONLY` 或 `DISABLED` 策略。 | diff --git a/packages/telemetry/session-telemetry-otel/README.i18n.yaml b/packages/telemetry/session-telemetry-otel/README.i18n.yaml index b1a2052a3f..6557557b8c 100644 --- a/packages/telemetry/session-telemetry-otel/README.i18n.yaml +++ b/packages/telemetry/session-telemetry-otel/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/telemetry/session-telemetry-otel/README.md -README.md: 9b208e291e77bee50d9d4fd14808268dca75f2db -README.zh.md: 76de1bf1ad58a0239907f3b63c672177874c7966 +README.md: fab2461477b2174bded42ed6f05ae55c7c5f697c +README.zh.md: ab0191188836e03434adbce527d31b62ead848a3 diff --git a/packages/telemetry/session-telemetry-otel/README.md b/packages/telemetry/session-telemetry-otel/README.md index 9b208e291e..fab2461477 100644 --- a/packages/telemetry/session-telemetry-otel/README.md +++ b/packages/telemetry/session-telemetry-otel/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — the only entry a deployment loads. It composes the OTel JS SDK as-is (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP log exporter) and maps each record the seam hands over onto `logger.emit()`, under two instrumentation scopes: ledger records on `@deepseek-ai/dsh-session-telemetry-otel`, operational records on `@deepseek-ai/dsh-session-telemetry-otel/ops`. Resource identity (`service.name`/`service.version`) comes from `dsh-llm`'s `APP_IDENTITY`, the same source the attribution headers use. +The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — the only entry a deployment loads. Its `mode` decides whether the seam hands records over immediately, releases them only at recorded feedback, or keeps telemetry local. Uploading modes compose the OTel JS SDK as-is (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP log exporter) and map each handed-over record onto `logger.emit()`, under two instrumentation scopes: ledger records on `@deepseek-ai/dsh-session-telemetry-otel`, operational records on `@deepseek-ai/dsh-session-telemetry-otel/ops`. Resource identity (`service.name`/`service.version`) comes from `dsh-llm`'s `APP_IDENTITY`, the same source the attribution headers use. ## Config @@ -10,6 +10,7 @@ The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — th - id: telemetry-otel name: '@deepseek-ai/dsh-session-telemetry-otel' config: + mode: FULL # FULL (default), FEEDBACK_ONLY, or DISABLED exporter: # passed verbatim to the SDK's OTLP/HTTP log exporter url: https://collector.example.com/v1/logs headers: @@ -17,15 +18,21 @@ The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — th processor: {} # optional; passed verbatim to BatchLogRecordProcessor ``` -`exporter.url` is the one field this package validates itself — required, no default, must parse as `http(s)` — so a missing endpoint fails at plugin load (as does a non-positive-integer `processor.maxExportBatchSize`, which the SDK accepts but then hangs on at shutdown). Everything else is the SDK's option shape, owned and documented by the SDK, and both blocks pass through whole: every `OTLPExporterNodeConfigBase` field (`headers`, `timeoutMillis`, `compression`, `keepAlive`, …) reaches the exporter, and batching, export cadence (`scheduledDelayMillis`), retry, queue bounds, and loss policy under sustained failure are the SDK's documented behavior, tuned through the `processor` passthrough. The backend deliberately implements no `flush()`: the batch processor is the only flusher in the process, which is what makes `shutdown()`'s drain complete. Removing this block from `cordis.yml` is the opt-out: no residual state, no `enabled` flag. +| `mode` | Behavior | +|---|---| +| `FULL` | Default. Each projected record, including lifecycle ops records, is handed to the OTel SDK immediately. | +| `FEEDBACK_ONLY` | Each `feedback/record` releases the redacted, projected session prefix through that event. Later records wait for another feedback event and remain local if none arrives. | +| `DISABLED` | No coordinator, provider, processor, or exporter is constructed. No telemetry record leaves the process. A `feedback/record` logs `session telemetry is DISABLED; nothing will be shared and this feedback remains local`; the event remains in the local session log. | + +`exporter.url` is required in `FULL` and `FEEDBACK_ONLY`, has no default, and must parse as `http(s)`; it is optional and unused in `DISABLED`. Uploading modes also reject a non-positive-integer `processor.maxExportBatchSize`, which the SDK accepts but then hangs on at shutdown. Everything else is the SDK's option shape, owned and documented by the SDK, and both blocks pass through whole: every `OTLPExporterNodeConfigBase` field (`headers`, `timeoutMillis`, `compression`, `keepAlive`, …) reaches the exporter, and batching, export cadence (`scheduledDelayMillis`), retry, queue bounds, and loss policy under sustained failure are the SDK's documented behavior, tuned through the `processor` passthrough. The backend deliberately implements no `flush()`: the batch processor is the only flusher in the process, which is what makes `shutdown()`'s drain complete. ## What leaves the machine -Records carry the complete `event.data` as the seam's `telemetry/record` waterfall returns it — user and assistant message content, tool arguments and results (command output, file contents), the full system prompt and tool schemas (`request/header`), todo text, compaction summaries, hook `stderrSummary`, and the session `cwd` (a local path). The seam ships no redaction rules: with no `telemetry/record` listener mounted, that is the raw captured copy, so a deployment exporting beyond a trusted boundary mounts its own rules (see [the seam README](../session-telemetry/README.md#the-redact-waterfall)). Provider credentials never appear regardless: adapter API keys are constructor parameters, not session events, so they are structurally absent from the log and therefore from telemetry. +In uploading modes, records carry the complete `event.data` as the seam's `telemetry/record` waterfall returns it — user and assistant message content, tool arguments and results (command output, file contents), the full system prompt and tool schemas (`request/header`), todo text, compaction summaries, hook `stderrSummary`, feedback text, and the session `cwd` (a local path). The seam ships no redaction rules: with no `telemetry/record` listener mounted, that is the raw captured copy, so a deployment exporting beyond a trusted boundary mounts its own rules (see [the seam README](../session-telemetry/README.md#the-redact-waterfall)). Provider credentials never appear regardless: adapter API keys are constructor parameters, not session events, so they are structurally absent from the log and therefore from telemetry. `DISABLED` does not construct the SDK pipeline or hand any capture to a backend. ## Field mapping -Seam record → SDK log record: `time` → `timestamp`/`observedTimestamp`; `severity` → `severityNumber`/`severityText` (INFO 9 / WARN 13 / ERROR 17); `body` → the structured log body; `attributes` verbatim. Receivers dedupe on `(session.id, event.seq)`, alert on severity, and detect crashes by `shutdown`-record absence (a session with activity, no `shutdown` ops record, gone stale ended uncleanly). The marker means telemetry stopped observing the session cleanly — emitted at the session's own disposal, or at application teardown for sessions still running then; a marker followed by more of that session's events is a telemetry reload, not a session restart. Streams are not self-contained across lineage: a resumed session continues its own id's stream from where the previous process left off, and a forked session's stream starts at its inherited boundary — its prefix lives in the parent's stream, stitched via `session.parent_id` + `session.seed_length`. One consequence of continuing rather than replaying: a turn left open mid-stream and never closed marks the previous process dying inside it. The local log is repaired with synthetic closers at resume, but those repairs are never exported — the wire stream stays faithful to what the crashed process actually shipped, and a later clean `shutdown` marker attests only to the resumed process's own exit. +Seam record → SDK log record: `time` → `timestamp`/`observedTimestamp`; `severity` → `severityNumber`/`severityText` (INFO 9 / WARN 13 / ERROR 17); `body` → the structured log body; `attributes` verbatim. Receivers dedupe on `(session.id, event.seq)` and alert on severity. In `FULL`, they may also detect crashes by `shutdown`-record absence: the marker is emitted at the session's own disposal or application teardown, and a marker followed by more events is a telemetry reload. In `FEEDBACK_ONLY`, a released prefix normally has no later `shutdown` marker, so its absence is not a crash signal. Streams are not self-contained across lineage: a resumed session continues its own id's stream from where the previous process left off, and a forked session's stream starts at its inherited boundary — its prefix lives in the parent's stream, stitched via `session.parent_id` + `session.seed_length`. A resumed local log may contain synthetic closers that were never exported; the wire stream stays faithful to records actually handed to the SDK. ## Model Experience @@ -39,3 +46,4 @@ None; this package neither assembles nor sends a provider request. - **Upstream experimental tree** — `@opentelemetry/sdk-logs` is still published from the upstream experimental tree; SDK API churn lands here and only here — the seam contract does not move. - **No live-collector coverage** — every test exports to a local mock collector; the keyless Loader-composition e2e (`tests/loader-composition.e2e.ts`) covers the wire shape on every run, and behavior against a real OTLP deployment (auth, TLS, throttling) is the SDK exporter's documented territory. +- **Feedback-only memory** — each session retains deep-copied, redacted projected records in memory until feedback releases them or the session becomes unreachable. There is no durable pre-feedback spool; a crash before feedback uploads nothing. diff --git a/packages/telemetry/session-telemetry-otel/README.zh.md b/packages/telemetry/session-telemetry-otel/README.zh.md index 76de1bf1ad..ab01911888 100644 --- a/packages/telemetry/session-telemetry-otel/README.zh.md +++ b/packages/telemetry/session-telemetry-otel/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -[遥测（telemetry）seam](../session-telemetry/) 的 OpenTelemetry 后端，也是部署方唯一要加载的条目。它原样组合 OTel JS SDK（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP 日志导出器），把 seam 交接过来的每条记录映射到 `logger.emit()`，并使用两个插桩作用域（instrumentation scope）：ledger 记录挂在 `@deepseek-ai/dsh-session-telemetry-otel` 下，运维记录挂在 `@deepseek-ai/dsh-session-telemetry-otel/ops` 下。资源身份（`service.name`/`service.version`）来自 `dsh-llm` 的 `APP_IDENTITY`，与归因标头同源。 +[遥测（telemetry）seam](../session-telemetry/) 的 OpenTelemetry 后端，也是部署方唯一要加载的条目。其 `mode` 决定 seam 是立即交接记录、仅在记录反馈时释放记录，还是将遥测留在本地。上传模式会原样组合 OTel JS SDK（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP 日志导出器），把每条已交接记录映射到 `logger.emit()`，并使用两个插桩作用域（instrumentation scope）：ledger 记录挂在 `@deepseek-ai/dsh-session-telemetry-otel` 下，运维记录挂在 `@deepseek-ai/dsh-session-telemetry-otel/ops` 下。资源身份（`service.name`/`service.version`）来自 `dsh-llm` 的 `APP_IDENTITY`，与归因标头同源。 ## 配置 @@ -10,6 +10,7 @@ - id: telemetry-otel name: '@deepseek-ai/dsh-session-telemetry-otel' config: + mode: FULL # FULL (default), FEEDBACK_ONLY, or DISABLED exporter: # passed verbatim to the SDK's OTLP/HTTP log exporter url: https://collector.example.com/v1/logs headers: @@ -17,15 +18,21 @@ processor: {} # optional; passed verbatim to BatchLogRecordProcessor ``` -`exporter.url` 是本包（package）唯一自行校验的字段：必填、无默认值、必须能解析为 `http(s)`，因此缺失端点会在插件加载时失败（`processor.maxExportBatchSize` 不是正整数时同样如此：SDK 会接受该值，随后却在关闭时因它挂起）。其余全部是 SDK 自己的选项形态，由 SDK 拥有并在 SDK 文档中说明，两个配置块都整体透传（passthrough）：`OTLPExporterNodeConfigBase` 的每个字段（`headers`、`timeoutMillis`、`compression`、`keepAlive` 等）都会到达导出器；批处理、导出节奏（`scheduledDelayMillis`）、重试、队列上限，以及持续失败下的丢失策略，都是 SDK 的文档化行为，经 `processor` 透传调优。该后端刻意不实现 `flush()`：批处理器是进程内唯一执行 flush 的组件，`shutdown()` 的排空正因如此才是完整的。从 `cordis.yml` 中删除该配置块即为退出方式：无残留状态，也没有 `enabled` 开关。 +| `mode` | 行为 | +|---|---| +| `FULL` | 默认值。每条已投影记录都立即交给 OTel SDK，包括生命周期运维记录。 | +| `FEEDBACK_ONLY` | 每个 `feedback/record` 都会释放截至该事件的已脱敏、已投影会话前缀。后续记录等待下一个反馈事件；如果没有后续反馈，则留在本地。 | +| `DISABLED` | 不构造协调器、提供方、处理器或导出器。没有遥测记录会离开进程。`feedback/record` 会记录 `session telemetry is DISABLED; nothing will be shared and this feedback remains local`；该事件留在本地会话日志中。 | + +`exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填，无默认值，且必须能解析为 `http(s)`；在 `DISABLED` 中可省略且不使用。上传模式也会拒绝不是正整数的 `processor.maxExportBatchSize`，SDK 虽会接受该值，但随后会在关闭时挂起。其余全部是 SDK 自己的选项形态，由 SDK 拥有并在 SDK 文档中说明，两个配置块都整体透传（passthrough）：`OTLPExporterNodeConfigBase` 的每个字段（`headers`、`timeoutMillis`、`compression`、`keepAlive` 等）都会到达导出器；批处理、导出节奏（`scheduledDelayMillis`）、重试、队列上限，以及持续失败下的丢失策略，都是 SDK 的文档化行为，经 `processor` 透传调优。该后端刻意不实现 `flush()`：批处理器是进程内唯一执行 flush 的组件，`shutdown()` 的排空正因如此才是完整的。 ## 哪些数据会离开本机 -记录携带完整的 `event.data`，内容以 seam 的 `telemetry/record` waterfall（瀑布式事件）返回的结果为准：用户与 assistant 消息内容、工具参数与工具结果（命令输出、文件内容）、完整的系统提示词与工具 schema（`request/header`）、todo 文本、压缩（compaction）摘要、钩子的 `stderrSummary`，以及会话 `cwd`（一个本地路径）。seam 不带任何脱敏规则：未挂载 `telemetry/record` 监听器时，导出的就是捕获原样的副本，因此向可信边界之外导出的部署方要挂载自己的规则（见 [seam README](../session-telemetry/README.md#the-redact-waterfall)）。无论如何，提供方凭据都不会出现：适配器的 API key 是构造函数参数而非会话事件，因此它们在结构上就不存在于日志中，也就不存在于遥测中。 +在上传模式中，记录携带完整的 `event.data`，内容以 seam 的 `telemetry/record` waterfall（瀑布式事件）返回的结果为准：用户与 assistant 消息内容、工具参数与工具结果（命令输出、文件内容）、完整的系统提示词与工具 schema（`request/header`）、todo 文本、压缩（compaction）摘要、钩子的 `stderrSummary`、反馈文本，以及会话 `cwd`（一个本地路径）。seam 不带任何脱敏规则：未挂载 `telemetry/record` 监听器时，导出的就是捕获原样的副本，因此向可信边界之外导出的部署方要挂载自己的规则（见 [seam README](../session-telemetry/README.md#the-redact-waterfall)）。无论如何，提供方凭据都不会出现：适配器的 API key 是构造函数参数而非会话事件，因此它们在结构上就不存在于日志中，也就不存在于遥测中。`DISABLED` 不会构造 SDK 流水线，也不会将任何捕获内容交给后端。 ## 字段映射 -seam 记录 → SDK 日志记录：`time` → `timestamp`/`observedTimestamp`；`severity` → `severityNumber`/`severityText`（INFO 9 / WARN 13 / ERROR 17）；`body` → 结构化日志 body；`attributes` 原样照搬。接收端基于 `(session.id, event.seq)` 去重、按严重级别告警，并通过 `shutdown` 记录的缺失检测崩溃（一个曾有活动、没有 `shutdown` 运维记录、且已然陈旧的会话，就是未干净结束的会话）。该标记的含义是遥测干净地停止了对该会话的观察：它在会话自身 dispose（资源释放）时发出，对于届时仍在运行的会话，则在应用关闭时发出；标记之后又出现该会话的更多事件，说明发生的是遥测重载，而不是会话重启。跨谱系（lineage）的流并不自足：恢复的会话在其自身 id 的流上从上一个进程停止之处继续；fork 出的会话，其流从继承边界开始，前缀位于父会话的流中，由接收端基于 `session.parent_id` + `session.seed_length` 拼接。继续而非回放的一个后果：流中一个开启后再未关闭的轮次，标志着上一个进程死在了该轮次之内。恢复时本地日志会以合成的关闭事件修复，但这些修复绝不导出：导出的流忠实于崩溃进程实际发出的内容，其后干净的 `shutdown` 标记也只证明恢复后进程自身的退出。 +seam 记录 → SDK 日志记录：`time` → `timestamp`/`observedTimestamp`；`severity` → `severityNumber`/`severityText`（INFO 9 / WARN 13 / ERROR 17）；`body` → 结构化日志 body；`attributes` 原样照搬。接收端基于 `(session.id, event.seq)` 去重，并按严重级别告警。在 `FULL` 中，接收端还可通过缺少 `shutdown` 记录检测崩溃：该标记在会话自身 dispose（资源释放）或应用关闭时发出；标记之后出现更多事件，说明遥测发生了重载。在 `FEEDBACK_ONLY` 中，已释放的前缀通常不包含随后的 `shutdown` 标记，因此缺少该标记不是崩溃信号。跨谱系（lineage）的流并不自足：恢复的会话在其自身 id 的流上从上一个进程停止之处继续；fork 出的会话的流从继承边界开始，其前缀位于父会话的流中，由接收端基于 `session.parent_id` + `session.seed_length` 拼接。恢复后的本地日志可能包含从未导出的合成关闭事件；协议流忠实于实际交给 SDK 的记录。 ## 模型体验 @@ -39,3 +46,4 @@ seam 记录 → SDK 日志记录：`time` → `timestamp`/`observedTimestamp`； - **上游实验性源码树**：`@opentelemetry/sdk-logs` 仍从上游实验性（experimental）源码树发布；SDK API 的变动只会落在本包，也仅落在本包；seam 契约不动。 - **无真实 collector 覆盖**：所有测试都导出到本地 mock collector；无密钥的 Loader 组合 e2e（`tests/loader-composition.e2e.ts`）在每次运行中都覆盖协议格式（wire format）形态，而面对真实 OTLP 部署的行为（认证、TLS、限流）属于 SDK 导出器文档的职责范围。 +- **仅反馈模式的内存占用**：每个会话都会在内存中保留已深拷贝、已脱敏的投影记录，直到反馈将其释放或会话变得不可达。反馈前不存在持久化 spool；如果在反馈前崩溃，则什么都不上传。 diff --git a/packages/telemetry/session-telemetry-otel/package.json b/packages/telemetry/session-telemetry-otel/package.json index 7be8c04ce4..4037cfe28a 100644 --- a/packages/telemetry/session-telemetry-otel/package.json +++ b/packages/telemetry/session-telemetry-otel/package.json @@ -36,6 +36,7 @@ "schemastery": "^3.18.0" }, "peerDependencies": { + "@deepseek-ai/dsh-command-feedback": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -44,6 +45,7 @@ }, "devDependencies": { "@cordisjs/plugin-loader": "workspace:^", + "@deepseek-ai/dsh-command-feedback": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/telemetry/session-telemetry-otel/src/index.ts b/packages/telemetry/session-telemetry-otel/src/index.ts index 85dd75f275..cb0ee71fc7 100644 --- a/packages/telemetry/session-telemetry-otel/src/index.ts +++ b/packages/telemetry/session-telemetry-otel/src/index.ts @@ -6,8 +6,8 @@ * record handed over by the seam onto `logger.emit()`. Per the seam's * boundary axiom, everything downstream of that call (batching, retry, * queueing, loss policy) is the SDK's documented behavior, configured - * verbatim through the `exporter`/`processor` passthroughs; this package - * adds no knobs of its own on top of them. + * verbatim through the `exporter`/`processor` passthroughs. This package owns + * only whether capture is immediate, feedback-released, or disabled. * * @module @deepseek-ai/dsh-session-telemetry-otel */ @@ -15,7 +15,14 @@ import { createRequire } from 'node:module' import z from 'schemastery' import type { Context } from 'cordis' -import { Telemetry, TelemetryCoordinator, type TelemetryRecord, type TelemetrySeverity } from '@deepseek-ai/dsh-session-telemetry' +import type {} from '@deepseek-ai/dsh-command-feedback' +import { + Telemetry, + TelemetryCoordinator, + type TelemetryDelivery, + type TelemetryRecord, + type TelemetrySeverity, +} from '@deepseek-ai/dsh-session-telemetry' import { APP_IDENTITY } from '@deepseek-ai/dsh-llm' import { BatchLogRecordProcessor, @@ -31,13 +38,22 @@ import { resourceFromAttributes } from '@opentelemetry/resources' // version (same pattern as dsh-llm's attribution identity). const { version } = createRequire(import.meta.url)('../package.json') as { version: string } +/** Supported session-sharing policies for the OTel backend. */ +export const TELEMETRY_MODES = ['FULL', 'FEEDBACK_ONLY', 'DISABLED'] as const + +/** Session-sharing policy selected by {@link Config.mode}. */ +export type TelemetryMode = typeof TELEMETRY_MODES[number] + +const DISABLED_FEEDBACK_WARNING = 'session telemetry is DISABLED; nothing will be shared and this feedback remains local' + /** - * Plugin configuration: two verbatim SDK option shapes plus nothing else. - * `exporter.url` is the one field this package validates itself — required, - * no default, must parse as an `http(s)` URL — because a missing endpoint - * must fail at plugin load, not at first export. + * Plugin configuration: one sharing policy plus two verbatim SDK option + * shapes. `exporter.url` is required for modes that upload and unused for + * `DISABLED`. */ export interface Config { + /** Sharing policy; defaults to immediate `FULL` delivery. */ + mode?: TelemetryMode /** * Passed verbatim to the SDK's OTLP/HTTP log exporter — the complete * `OTLPExporterNodeConfigBase` shape (`headers`, `timeoutMillis`, @@ -45,7 +61,7 @@ export interface Config { * is the one field this package requires and validates itself. */ exporter?: OTLPExporterNodeConfigBase & { - /** Full logs endpoint (e.g. `https://collector.example.com/v1/logs`). Required; validated at plugin load. */ + /** Full logs endpoint (e.g. `https://collector.example.com/v1/logs`). Required outside `DISABLED`; validated at load. */ url?: string } /** @@ -57,13 +73,14 @@ export interface Config { /** * Schemastery validator for {@link Config}; cordis runs it before the plugin - * starts. Shape-level only — the load-bearing `exporter.url` check lives in - * the constructor so its error message names the field. Both slots are opaque - * passthroughs: the SDK owns their shapes and validates its own options; - * re-declaring them field-by-field here would violate the boundary axiom - * (and silently drop every field not re-declared). + * starts. Shape-level only — the mode-dependent `exporter.url` check lives in + * the constructor so its error message names the field. Both SDK slots are + * opaque passthroughs: the SDK owns their shapes and validates its own + * options; re-declaring them field-by-field here would violate the boundary + * axiom (and silently drop every field not re-declared). */ export const Config: z = z.object({ + mode: z.union(TELEMETRY_MODES).default('FULL'), exporter: z.any(), processor: z.any(), }) @@ -76,22 +93,32 @@ const SEVERITY: Record { + if (event.type === 'feedback/record') ctx.logger.warn(DISABLED_FEEDBACK_WARNING) + }) + return + } + const url = config.exporter?.url if (url === undefined || url.length === 0) { throw new Error('session-telemetry-otel: exporter.url is required (the full OTLP logs endpoint)') @@ -134,16 +161,26 @@ export class TelemetryOtel extends Telemetry { }) this.ledger = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel', version) this.ops = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel/ops', version) - new TelemetryCoordinator(ctx, this) + const delivery: TelemetryDelivery = mode === 'FULL' ? 'immediate' : 'held' + const coordinator = new TelemetryCoordinator(ctx, this, delivery) + if (mode === 'FEEDBACK_ONLY') { + // The coordinator listener is registered first, so a feedback event + // enters the held prefix before this listener releases that exact prefix. + ctx.on('session/event', (session, event) => { + if (event.type === 'feedback/record') coordinator.release(session) + }) + } } /** * Map one seam record onto the SDK logger for its channel — a synchronous - * enqueue into the batch processor's queue. + * enqueue into the batch processor's queue. Direct calls are no-ops in + * `DISABLED`, where no coordinator or SDK pipeline exists. * @param record - the logical record handed over by the coordinator. */ emit(record: TelemetryRecord): void { const logger = record.channel === 'ops' ? this.ops : this.ledger + if (logger === undefined) return logger.emit({ timestamp: record.time, observedTimestamp: record.time, @@ -167,14 +204,15 @@ export class TelemetryOtel extends Telemetry { /** * Delegate disposal to the SDK's shutdown contract: drain the queue and * quiesce. With no concurrent `forceFlush()` in the process (see above), - * shutdown's internal drain is complete — everything emitted before this - * call, including the coordinator's dispose-time `shutdown` markers, is - * exported before the exporter closes. Awaited (and error-contained) by - * the coordinator's disposer. + * shutdown's internal drain is complete — everything handed to the SDK + * before this call is exported before the exporter closes. In `FULL`, that + * includes dispose-time `shutdown` markers; held suffixes never reach the + * SDK. Awaited (and error-contained) by the coordinator's disposer. A + * disabled backend resolves immediately. * @returns resolves when the SDK pipeline has quiesced. */ shutdown(): Promise { - return this.provider.shutdown() + return this.provider === undefined ? Promise.resolve() : this.provider.shutdown() } } diff --git a/packages/telemetry/session-telemetry-otel/src/invariant.ts b/packages/telemetry/session-telemetry-otel/src/invariant.ts index 075e5cc193..030b7ce670 100644 --- a/packages/telemetry/session-telemetry-otel/src/invariant.ts +++ b/packages/telemetry/session-telemetry-otel/src/invariant.ts @@ -15,10 +15,9 @@ export const name = 'session-telemetry-otel-invariant' export const inject = ['invariants'] /** - * No runtime invariant: the backend forwards seam records into the OTel SDK's - * in-process pipeline and appends nothing to any session; its only observable - * effects (batching, export) happen inside the SDK past the seam's boundary - * axiom, out of reach of an independent companion. + * No runtime invariant: mode selection changes capture handoff, SDK setup, and + * local diagnostics without mutating session or service state an independent + * companion can compare. Export remains inside the SDK past the seam boundary. */ const install: InvariantInstaller = () => {} diff --git a/packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts b/packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts index 8f16662614..e07e05fed9 100644 --- a/packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts +++ b/packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts @@ -40,6 +40,11 @@ interface OtlpCapture { }[] } +interface FixtureOutput { + captures: OtlpCapture[] + logContent: string +} + async function jsonlFiles(dir: string): Promise { const entries = await readdir(dir, { withFileTypes: true }) const paths = await Promise.all(entries.map(async (entry) => { @@ -50,10 +55,29 @@ async function jsonlFiles(dir: string): Promise { return paths.flat() } +async function readFixtureOutput(cwd: string): Promise { + const captures = JSON.parse(await readFile(join(cwd, 'otlp-captures.json'), 'utf8')) as OtlpCapture[] + const logs = await jsonlFiles(join(cwd, '.sessions')) + expect(logs).toHaveLength(1) + return { captures, logContent: await readFile(logs[0] as string, 'utf8') } +} + +function allRecords(captures: OtlpCapture[]) { + return captures.flatMap(capture => capture.resourceLogs.flatMap(resource => + resource.scopeLogs.flatMap(scoped => scoped.logRecords.map(record => ({ scope: scoped.scope.name, record }))))) +} + +function eventTypes(captures: OtlpCapture[]): string[] { + return allRecords(captures).flatMap(({ record }) => + record.attributes?.flatMap(attribute => + attribute.key === 'event.type' && typeof attribute.value['stringValue'] === 'string' + ? [attribute.value['stringValue']] + : []) ?? []) +} + describe('session-telemetry-otel through a real headless cordis.yml', () => { it('exports redacted ledger records to the collector while the canonical log keeps the secret', async () => { - let captures: OtlpCapture[] = [] - let logContent = '' + let output!: FixtureOutput const { stderr } = await runLoaderSmoke({ label: 'session-telemetry-otel loader smoke', tempDirPrefix: 'telemetry-otel-e2e-', @@ -61,39 +85,70 @@ describe('session-telemetry-otel through a real headless cordis.yml', () => { libBinScript: driver, configPath, tsconfigPath: repoTsconfig, - inspect: async (cwd) => { - captures = JSON.parse(await readFile(join(cwd, 'otlp-captures.json'), 'utf8')) as OtlpCapture[] - const logs = await jsonlFiles(join(cwd, '.sessions')) - expect(logs).toHaveLength(1) - logContent = await readFile(logs[0] as string, 'utf8') - }, + inspect: async (cwd) => { output = await readFixtureOutput(cwd) }, }) expect(stderr).not.toContain('UNHANDLED') - const records = captures.flatMap(capture => capture.resourceLogs.flatMap(resource => - resource.scopeLogs.flatMap(scoped => scoped.logRecords.map(record => ({ scope: scoped.scope.name, record }))))) + const records = allRecords(output.captures) expect(records.length).toBeGreaterThan(0) - const eventTypes = records.flatMap(({ record }) => - record.attributes?.flatMap(attribute => - attribute.key === 'event.type' && typeof attribute.value['stringValue'] === 'string' - ? [attribute.value['stringValue']] - : []) ?? []) + const types = eventTypes(output.captures) for (const expected of ['turn/start', 'user/message', 'tool/call', 'tool/result', 'assistant/message', 'turn/end']) { - expect(eventTypes, expected).toContain(expected) + expect(types, expected).toContain(expected) } expect(records.some(({ scope }) => scope.endsWith('/ops'))).toBe(true) // The deployment-mounted rule on the wire: the fixture credential never // leaves the process, its surrounding prose does, and the placeholder // marks the spot — the seam itself ships no rules. - const wire = JSON.stringify(captures) + const wire = JSON.stringify(output.captures) expect(wire).not.toContain(FIXTURE_SECRET) expect(wire).toContain(FIXTURE_PLACEHOLDER) expect(wire).toContain('prove telemetry with key') // The canonical session log is never rewritten. - expect(logContent).toContain(FIXTURE_SECRET) - expect(logContent).not.toContain(FIXTURE_PLACEHOLDER) + expect(output.logContent).toContain(FIXTURE_SECRET) + expect(output.logContent).not.toContain(FIXTURE_PLACEHOLDER) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + + it('exports only prefixes ending in feedback under feedback-only mode', async () => { + let output!: FixtureOutput + const { stderr } = await runLoaderSmoke({ + label: 'session-telemetry-otel feedback-only loader smoke', + tempDirPrefix: 'telemetry-otel-feedback-e2e-', + binScript: driver, + libBinScript: driver, + configPath, + tsconfigPath: repoTsconfig, + env: { DSH_TELEMETRY_E2E_MODE: 'FEEDBACK_ONLY' }, + inspect: async (cwd) => { output = await readFixtureOutput(cwd) }, + }) + expect(stderr).not.toContain('UNHANDLED') + + const wire = JSON.stringify(output.captures) + expect(eventTypes(output.captures)).toContain('feedback/record') + expect(wire).toContain('fixture feedback') + expect(wire).toContain('prove telemetry with key') + expect(wire).not.toContain('post-feedback private suffix') + expect(output.logContent).toContain('post-feedback private suffix') + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + + it('keeps disabled feedback local and prints the stable warning', async () => { + let output!: FixtureOutput + const { stdout } = await runLoaderSmoke({ + label: 'session-telemetry-otel disabled loader smoke', + tempDirPrefix: 'telemetry-otel-disabled-e2e-', + binScript: driver, + libBinScript: driver, + configPath, + tsconfigPath: repoTsconfig, + env: { DSH_TELEMETRY_E2E_MODE: 'DISABLED' }, + inspect: async (cwd) => { output = await readFixtureOutput(cwd) }, + }) + + expect(output.captures).toEqual([]) + expect(output.logContent).toContain('fixture feedback') + expect(stdout.match(/session telemetry is DISABLED; nothing will be shared and this feedback remains local/)?.[0]) + .toMatchInlineSnapshot('"session telemetry is DISABLED; nothing will be shared and this feedback remains local"') }, LOADER_SMOKE_TEST_TIMEOUT_MS) }) diff --git a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts index cccb90ed43..18c466f7aa 100644 --- a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts +++ b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts @@ -5,12 +5,13 @@ * for the default-exported Service class. */ -import { afterEach, describe, expect, it } from 'vitest' +import { afterEach, describe, expect, it, vi } from 'vitest' import { createServer, type Server } from 'node:http' import { once } from 'node:events' import { gunzipSync } from 'node:zlib' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' +import { recordFeedback } from '@deepseek-ai/dsh-command-feedback' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import TelemetryOtel, { Config } from '../src/index.ts' @@ -30,6 +31,7 @@ interface OtlpLogsRequest { severityNumber: number severityText: string attributes?: { key: string; value: Record }[] + body?: unknown }[] }[] }[] @@ -88,6 +90,14 @@ function allRecords(captures: Capture[]) { s.logRecords.map(record => ({ scope: s.scope.name, record }))))) } +function eventTypes(captures: Capture[]): string[] { + return allRecords(captures).flatMap(({ record }) => + record.attributes?.flatMap(attribute => + attribute.key === 'event.type' && typeof attribute.value['stringValue'] === 'string' + ? [attribute.value['stringValue']] + : []) ?? []) +} + describe('TelemetryOtel wire', () => { it('ships session records and the ops shutdown marker through the real SDK pipeline', async () => { const { url, captures } = await mockCollector() @@ -195,6 +205,82 @@ describe('TelemetryOtel wire', () => { r.record.attributes?.some(a => a.key === 'event.type' && a.value.stringValue === 'turn/start')) expect(start?.record.severityNumber).toBe(13) }) + + it('holds each session suffix until the next feedback event', async () => { + const { url, captures } = await mockCollector() + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(TelemetryOtel, { + mode: 'FEEDBACK_ONLY', + exporter: { url }, + }) + const session = ctx.sessions.create(SessionId('feedback-only'), { meta: {} }) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + recordFeedback(session, 'first report') + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + recordFeedback(session, 'second report') + session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) + await fiber.dispose() + + const types = allRecords(captures).flatMap(({ record }) => + record.attributes?.flatMap(attribute => + attribute.key === 'event.type' ? [attribute.value.stringValue] : []) ?? []) + expect(types).toEqual(['turn/start', 'feedback/record', 'turn/end', 'feedback/record']) + expect(JSON.stringify(captures)).toContain('first report') + expect(JSON.stringify(captures)).toContain('second report') + expect(allRecords(captures).some(({ scope }) => scope.endsWith('/ops'))).toBe(false) + }) + + it('sends no request when feedback-only mode ends without feedback', async () => { + const { url, captures } = await mockCollector() + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(TelemetryOtel, { + mode: 'FEEDBACK_ONLY', + exporter: { url }, + }) + const session = ctx.sessions.create(SessionId('no-feedback'), { meta: {} }) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await fiber.dispose() + expect(captures).toEqual([]) + }) + + it('boots disabled without exporter config and warns when feedback stays local', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) + const fiber = await ctx.plugin(TelemetryOtel, { mode: 'DISABLED' }) + const session = ctx.sessions.create(SessionId('disabled'), { meta: {} }) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + recordFeedback(session, 'local report') + + expect(warn).toHaveBeenCalledWith( + 'session telemetry is DISABLED; nothing will be shared and this feedback remains local', + ) + ctx.telemetry.emit({ + channel: 'ledger', + time: 0, + severity: 'info', + attributes: {}, + body: null, + }) + await ctx.telemetry.shutdown() + await fiber.dispose() + recordFeedback(session, 'after disposal') + expect(warn).toHaveBeenCalledTimes(1) + }) + + it('defaults direct construction to full delivery', async () => { + const { url, captures } = await mockCollector() + const ctx = new Context() + await ctx.plugin(SessionStore) + new TelemetryOtel(ctx, { exporter: { url } }) + const session = ctx.sessions.create(SessionId('direct-default'), { meta: {} }) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await ctx.fiber.dispose() + + expect(eventTypes(captures)).toContain('turn/start') + }) }) describe('TelemetryOtel config fails loud', () => { @@ -203,6 +289,8 @@ describe('TelemetryOtel config fails loud', () => { [{ exporter: { url: '' } }, /exporter\.url is required/], [{ exporter: { url: 'not a url' } }, /not a valid URL/], [{ exporter: { url: 'ftp://collector' } }, /must be http\(s\)/], + [{ mode: 'FEEDBACK_ONLY' }, /exporter\.url is required/], + [{ mode: 'INVALID' }, /INVALID/], // The SDK accepts a non-positive batch size but its shutdown drain then // splices empty batches forever — dispose would hang, so reject at load. [{ exporter: { url: 'http://c/v1/logs' }, processor: { maxExportBatchSize: 0 } }, /maxExportBatchSize/], diff --git a/packages/telemetry/session-telemetry-otel/tsconfig.json b/packages/telemetry/session-telemetry-otel/tsconfig.json index 9512133cf7..4ba93f9eb1 100644 --- a/packages/telemetry/session-telemetry-otel/tsconfig.json +++ b/packages/telemetry/session-telemetry-otel/tsconfig.json @@ -20,6 +20,9 @@ { "path": "../../core/session" }, + { + "path": "../../feedback/command-feedback" + }, { "path": "../../llm/llm" }, diff --git a/packages/telemetry/session-telemetry/README.i18n.yaml b/packages/telemetry/session-telemetry/README.i18n.yaml index 18f6751424..da3a62e2fd 100644 --- a/packages/telemetry/session-telemetry/README.i18n.yaml +++ b/packages/telemetry/session-telemetry/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/telemetry/session-telemetry/README.md -README.md: 272c9abe78849be3d2bba2c54cd7e25bcbe2d4c2 -README.zh.md: e6f077c1d12d00e746147908560d05381fde11c3 +README.md: d38433a728c699c7fb3cc0512bb6a2d977dd4cc6 +README.zh.md: 3a86b01321fc7dfd33d39530ee7fa38a6ee1f2dc diff --git a/packages/telemetry/session-telemetry/README.md b/packages/telemetry/session-telemetry/README.md index 272c9abe78..d38433a728 100644 --- a/packages/telemetry/session-telemetry/README.md +++ b/packages/telemetry/session-telemetry/README.md @@ -2,23 +2,23 @@ English | [中文](README.zh.md) -The telemetry seam: the CAPTURE side of session-event reporting, behind a backend contract any reporting SDK satisfies with zero bending. The boundary axiom that shapes everything here: **this package's aspect ends at `emit()`** — batching, retry, queueing, and loss policy belong to the backend's SDK and are neither specified nor wrapped. Rationale and rejected alternatives: [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md). +The telemetry seam: the capture side of session-event reporting, behind a backend contract any reporting SDK satisfies with zero bending. Capture can hand each redacted record over immediately or hold a per-session prefix for an explicit release. The boundary axiom that shapes everything here: **this package's aspect ends at `emit()`** — batching, retry, queueing, and loss policy belong to the backend's SDK and are neither specified nor wrapped. Rationale and rejected alternatives: [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md) and [feedback-gated delivery](../../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md). ## The backend contract -`TelemetryBackend` is three members: `emit(record)` (MUST be a non-blocking enqueue — it runs synchronously on the `session/event` hot path), optional `flush()` (a turn-boundary hint, fire-and-forget; most backends leave it unimplemented and let their SDK's batching cadence govern export timing — an implementer owns the interaction between concurrent flushes and `shutdown()`'s drain), and `shutdown()` (the lifecycle forward: drain-and-quiesce, awaited at dispose). `Telemetry` is its service-registered form under the `telemetry` context key — one implementation per context, duplicate load throws. A backend composes `TelemetryCoordinator` in its constructor. +`TelemetryBackend` is three members: `emit(record)` (MUST be a non-blocking enqueue — it runs synchronously on the `session/event` hot path, either at capture or held-prefix release), optional `flush()` (a turn-boundary hint, fire-and-forget; most backends leave it unimplemented and let their SDK's batching cadence govern export timing — an implementer owns the interaction between concurrent flushes and `shutdown()`'s drain), and `shutdown()` (the lifecycle forward: drain-and-quiesce, awaited at dispose). `Telemetry` is its service-registered form under the `telemetry` context key — one implementation per context, duplicate load throws. A backend composes `TelemetryCoordinator` with `immediate` delivery or `held` delivery and calls `release(session)` at its owning trigger. ## Capture points -The coordinator registers, all through the composing fiber's effects: `session/created` (adopt: record the header, read the log back through the projection from the construction boundary — constructor seeds from fork/resume never re-emit on the firehose and never re-export), `session/event` (project, deep-copy, redact, hand off; zero I/O), `session/flush` (forward the optional `flush()` hint and return void — the loop's awaited parallel must never wait on telemetry), `session/disposed` (emit the session's `shutdown` operational record at its own termination edge — where receivers key crash detection — then retire it, so a long-lived backend neither retains closed sessions nor re-marks them at unload), `agent/error` (the one live-bus relay; the session event vocabulary intentionally has no operational-error record), a dispose effect (mark each session still alive at teardown, then await the backend's `shutdown()`; failures warn instead of throwing), and an adoption sweep of `ctx.sessions.list()` (a hot reload does not replay `session/created`). +The coordinator registers, all through the composing fiber's effects: `session/created` (adopt: record the header, read the log back through the projection from the construction boundary — constructor seeds from fork/resume never re-emit on the firehose and never re-export), `session/event` (project, deep-copy, redact, then hand off or hold; zero I/O), `session/flush` (forward the optional `flush()` hint and return void — the loop's awaited parallel must never wait on telemetry), `session/disposed` (capture the session's `shutdown` operational record at its termination edge, then retire it), `agent/error` (the one live-bus relay; the session event vocabulary intentionally has no operational-error record), a dispose effect (capture shutdown for each still-live session, then await the backend's `shutdown()`; failures warn instead of throwing), and an adoption sweep of `ctx.sessions.list()` (a hot reload does not replay `session/created`). Immediate delivery hands lifecycle records over; held delivery leaves any suffix after the last release local, including its later shutdown marker. ## The redact waterfall -Every record passes the `telemetry/record` waterfall between projection and `emit()` — the seam's scrubbing extension point. The seam ships NO rules of its own: the innermost `next()` passes the record through unchanged, so with no listener mounted records reach the backend exactly as captured, and exported data is precisely as clean as the rules a deployment mounts. Listeners stack by transforming `next()`'s return value; returning without `next()` replaces everything beneath, and a throwing listener withholds that one record fail-closed inside the coordinator's containment. Redaction applies to the exported copy only; the canonical session log is never rewritten. +Every record passes the `telemetry/record` waterfall immediately after projection — the seam's scrubbing extension point. The seam ships NO rules of its own: the innermost `next()` passes the record through unchanged, so with no listener mounted records reach the backend exactly as captured, and exported data is precisely as clean as the rules a deployment mounts. Listeners stack by transforming `next()`'s return value; returning without `next()` replaces everything beneath, and a throwing listener withholds that one record fail-closed inside the coordinator's containment. Held delivery stores only the waterfall result, so later policy removal cannot expose the original capture. Redaction applies to the outbound copy only; the canonical session log is never rewritten. ## The handoff cursor -A module-scope `WeakMap` marks the highest seq HANDED OFF (not delivered) per session, advanced at emit time. It survives reloads that do not re-evaluate this module — config re-applies and backend source reloads, which is where iteration happens; that asymmetry is why the cursor lives in the seam. On re-adoption the coordinator re-hands only events past the cursor (events at or below it still rebuild the chunk-projection state); a missing cursor safely degrades to a re-hand from the session's construction boundary (`Session.firstLiveSeq` — seq 0 for a session born in this process), absorbed by receiver-side dedupe on `(session.id, event.seq)`. Constructor seeds never re-export: a resumed session's history shipped from the previous process under the same id, and a fork's inherited prefix lives in the parent's stream (receivers stitch on `session.parent_id` + `session.seed_length`). The accepted cost, consistent with at-most-once delivery: a resume does not backfill records a previous process failed to deliver — a deployment with a backfill requirement needs the deferred outbox, not replay. This is a deliberate, narrow exception to the registrations-are-effects discipline: entries die with their sessions, the value is a monotonic watermark, and losing it is never an error. +A module-scope `WeakMap` marks the highest seq HANDED OFF (not delivered) per session. Immediate delivery advances it at capture; held delivery advances it only when `release(session)` hands that record to the backend. An unreleased prefix therefore survives a coordinator reload through deterministic re-adoption instead of disappearing with its in-memory copy. On re-adoption the coordinator re-hands only events past the cursor (events at or below it still rebuild the chunk-projection state); a missing cursor safely degrades to a re-hand from the session's construction boundary (`Session.firstLiveSeq` — seq 0 for a session born in this process), absorbed by receiver-side dedupe on `(session.id, event.seq)`. Constructor seeds never re-export: a resumed session's history shipped from the previous process under the same id, and a fork's inherited prefix lives in the parent's stream (receivers stitch on `session.parent_id` + `session.seed_length`). The accepted cost, consistent with at-most-once delivery: a resume does not backfill records a previous process failed to deliver — a deployment with a backfill requirement needs the deferred outbox, not replay. This is a deliberate, narrow exception to the registrations-are-effects discipline: entries die with their sessions, the value is a monotonic watermark, and losing it is never an error. ## The fixed chunk projection @@ -40,3 +40,4 @@ None; this package neither assembles nor sends a provider request. - **Best-effort delivery** — the cursor marks handed-off, not delivered; a session torn down inside a reload window cannot be re-adopted; whatever sits in a backend queue at crash time is lost. A durable outbox (spool, per-sink cursors, at-least-once) is deferred until a deployment states a crash-loss requirement — see [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md). - **No built-in redaction rules** — with no `telemetry/record` listener mounted, records leave the process exactly as captured, including any credentials embedded in file contents or command output; a deployment exporting to a shared collector owns its rule set. +- **Held prefixes duplicate memory** — held delivery retains one deep-copied, redacted record per projected event until release or session collection. It adds no durable outbox and intentionally trades memory for a simple no-upload-before-trigger boundary. diff --git a/packages/telemetry/session-telemetry/README.zh.md b/packages/telemetry/session-telemetry/README.zh.md index e6f077c1d1..3a86b01321 100644 --- a/packages/telemetry/session-telemetry/README.zh.md +++ b/packages/telemetry/session-telemetry/README.zh.md @@ -2,23 +2,23 @@ [English](README.md) | 中文 -遥测（telemetry）seam：会话事件上报的捕获侧，隔在一个后端契约之后，任何上报 SDK 都无需变形即可满足该契约。塑造本包（package）一切设计的边界公理：**本包的职责止于 `emit()`**。批处理、重试、排队与丢失策略都属于后端自身的 SDK，本包既不为其立规，也不做包装。设计依据与被否决的替代方案见[复活 Agent Note（agent 决策记录）](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)。 +遥测（telemetry）seam：会话事件上报的捕获侧，隔在一个后端契约之后，任何上报 SDK 都无需变形即可满足该契约。捕获侧可立即交接每条已脱敏记录，也可按会话暂存一个前缀，等待显式释放。塑造本包（package）一切设计的边界公理：**本包的职责止于 `emit()`**。批处理、重试、排队与丢失策略都属于后端自身的 SDK，本包既不为其立规，也不做包装。设计依据与被否决的替代方案见[复活 Agent Note（agent 决策记录）](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)与[反馈门控投递](../../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md)。 ## 后端契约 -`TelemetryBackend` 只有三个成员：`emit(record)`（必须是非阻塞入队；它在 `session/event` 热路径上同步执行）、可选的 `flush()`（轮次边界提示，触发后不等待结果；多数后端不实现它，而由其 SDK 的批处理节奏决定导出时机；并发 flush 与 `shutdown()` 的排空之间的交互由实现方自行负责）、以及 `shutdown()`（生命周期转发点：排空并完全停稳，在 dispose（资源释放）时被等待）。`Telemetry` 是它注册在 `telemetry` 上下文键下的服务形态：每个上下文只允许一个实现，重复加载会抛出异常。后端在其构造函数中组合 `TelemetryCoordinator`。 +`TelemetryBackend` 只有三个成员：`emit(record)`（必须是非阻塞入队；它会在捕获或暂存前缀释放时，于 `session/event` 热路径上同步执行）、可选的 `flush()`（轮次边界提示，触发后不等待结果；多数后端不实现它，而由其 SDK 的批处理节奏决定导出时机；并发 flush 与 `shutdown()` 的排空之间的交互由实现方自行负责）、以及 `shutdown()`（生命周期转发点：排空并完全停稳，在 dispose（资源释放）时被等待）。`Telemetry` 是它注册在 `telemetry` 上下文键下的服务形态：每个上下文只允许一个实现，重复加载会抛出异常。后端以 `immediate` 或 `held` 投递模式组合 `TelemetryCoordinator`，并在自身所属的触发器中调用 `release(session)`。 ## 捕获点 -协调器的全部注册都经由组合方 fiber 的 effect 完成：`session/created`（收养：记录 header，并经投影从构造边界起回读日志；来自 fork 或恢复的构造函数种子绝不会在 firehose 上再次发出，也绝不会再次导出）、`session/event`（投影、深拷贝、脱敏、交接；零 I/O）、`session/flush`（转发可选的 `flush()` 提示并返回 void；循环所等待的并行任务绝不能等待遥测）、`session/disposed`（在会话自身的终止边缘发出该会话的 `shutdown` 运维记录，接收端正是在这个边缘锚定崩溃检测；随后将该会话退役，因此长生命周期的后端既不会保留已关闭的会话，也不会在卸载时再次标记它们）、`agent/error`（唯一的实时总线转发；会话事件词汇有意不包含运维错误记录）、一个 dispose effect（拆卸时先标记每个仍存活的会话，再等待后端的 `shutdown()`；失败只发出警告而不抛出），以及对 `ctx.sessions.list()` 的收养扫描（热重载不会重放 `session/created`）。 +协调器的全部注册都经由组合方 fiber 的 effect 完成：`session/created`（收养：记录 header，并经投影从构造边界起回读日志；来自 fork 或恢复的构造函数种子绝不会在 firehose 上再次发出，也绝不会再次导出）、`session/event`（投影、深拷贝、脱敏，再交接或暂存；零 I/O）、`session/flush`（转发可选的 `flush()` 提示并返回 void；循环所等待的并行任务绝不能等待遥测）、`session/disposed`（在会话自身的终止边缘捕获该会话的 `shutdown` 运维记录，然后将其退役）、`agent/error`（唯一的实时总线转发；会话事件词汇有意不包含运维错误记录）、一个 dispose effect（捕获每个仍存活会话的 shutdown，再等待后端的 `shutdown()`；失败只发出警告而不抛出），以及对 `ctx.sessions.list()` 的收养扫描（热重载不会重放 `session/created`）。即时投递会交接生命周期记录；暂存投递会将上次释放后的任何后缀留在本地，包括随后的 shutdown 标记。 ## 脱敏 waterfall（瀑布式事件） -每条记录在投影与 `emit()` 之间都要经过 `telemetry/record` waterfall，这是该 seam 的脱敏扩展点。seam 自身不带任何规则：最内层的 `next()` 原样透传记录，因此未挂载监听器时，记录以捕获时的原样到达后端；导出数据能干净到什么程度，恰恰取决于部署方挂载了什么规则。监听器通过变换 `next()` 的返回值来堆叠；不调用 `next()` 就返回，即替换其下方的全部逻辑；抛出异常的监听器会在协调器的隔离范围内以 fail-closed 方式拦下这一条记录。脱敏只作用于导出副本；权威会话日志永不改写。 +每条记录在投影后立即经过 `telemetry/record` waterfall，这是该 seam 的脱敏扩展点。seam 自身不带任何规则：最内层的 `next()` 原样透传记录，因此未挂载监听器时，记录以捕获时的原样到达后端；导出数据能干净到什么程度，恰恰取决于部署方挂载了什么规则。监听器通过变换 `next()` 的返回值来堆叠；不调用 `next()` 就返回，即替换其下方的全部逻辑；抛出异常的监听器会在协调器的隔离范围内以 fail-closed 方式拦下这一条记录。暂存投递只保留 waterfall 的结果，因此后续移除策略也无法暴露捕获时的原始内容。脱敏只作用于外发副本；权威会话日志永不改写。 ## handoff 游标 -一个模块作用域的 `WeakMap` 记录每个会话已交接（而非已投递）的最高 seq，在 emit 时推进。游标在不重新求值本模块的重载（配置重新应用、后端源码重载）中存活，而迭代恰恰发生在这类重载中；这种不对称正是游标放在 seam 一侧的原因。重新收养时，协调器只重新交接游标之后的事件（游标及其之前的事件仍用于重建分片投影状态）；游标缺失时安全退化为从会话构造边界起的重新交接（`Session.firstLiveSeq`，对在本进程中诞生的会话即 seq 0），由接收端基于 `(session.id, event.seq)` 的去重吸收。构造函数种子绝不会再次导出：恢复会话的历史已由上一个进程以同一 id 发出，fork 继承的前缀则位于父会话的流中（接收端基于 `session.parent_id` + `session.seed_length` 拼接）。由此接受的代价与至多一次（at-most-once）投递一致：恢复不会回填上一个进程未能投递的记录；有回填要求的部署需要的是已推迟的 outbox，而不是回放。这是对「注册即 effect」纪律的一次有意且范围极窄的例外：条目随其会话消亡，值是单调水位线，丢失它绝不是错误。 +一个模块作用域的 `WeakMap` 记录每个会话已交接（而非已投递）的最高 seq。即时投递在捕获时推进游标；暂存投递只有在 `release(session)` 将记录交给后端时才推进游标。因此，重建协调器后会通过确定性重新收养恢复未释放的前缀，而不会随其内存副本一同消失。重新收养时，协调器只重新交接游标之后的事件（游标及其之前的事件仍用于重建分片投影状态）；游标缺失时安全退化为从会话构造边界起的重新交接（`Session.firstLiveSeq`，对在本进程中诞生的会话即 seq 0），由接收端基于 `(session.id, event.seq)` 的去重吸收。构造函数种子绝不会再次导出：恢复会话的历史已由上一个进程以同一 id 发出，fork 继承的前缀则位于父会话的流中（接收端基于 `session.parent_id` + `session.seed_length` 拼接）。由此接受的代价与至多一次（at-most-once）投递一致：恢复不会回填上一个进程未能投递的记录；有回填要求的部署需要的是已推迟的 outbox，而不是回放。这是对「注册即 effect」纪律的一次有意且范围极窄的例外：条目随其会话消亡，值是单调水位线，丢失它绝不是错误。 ## 固定分片投影 @@ -40,3 +40,4 @@ - **尽力而为的投递**：游标标记的是已交接而非已投递；在重载窗口内被拆除的会话无法重新收养；崩溃时留在后端队列中的内容会丢失。持久化 outbox（spool、每 sink 游标、at-least-once）推迟到有部署方提出明确的崩溃丢失要求时再实现；见[复活 Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)。 - **不内置脱敏规则**：未挂载 `telemetry/record` 监听器时，记录以捕获时的原样离开进程，包括文件内容或命令输出中内嵌的任何凭据；向共享 collector 导出的部署方自行负责其规则集。 +- **暂存前缀会重复占用内存**：暂存投递会为每个已投影事件保留一份深拷贝且已脱敏的记录，直到释放或回收会话。它不增加持久化 outbox，而是有意以内存换取简单的「触发前不上传」边界。 diff --git a/packages/telemetry/session-telemetry/src/coordinator.ts b/packages/telemetry/session-telemetry/src/coordinator.ts index 0bebbcc561..710e9b81f9 100644 --- a/packages/telemetry/session-telemetry/src/coordinator.ts +++ b/packages/telemetry/session-telemetry/src/coordinator.ts @@ -3,10 +3,11 @@ * firehose plus the one live-bus relay (`agent/error`), applies the fixed * chunk projection, builds logical records, runs each through the * `telemetry/record` waterfall (deployment-mounted redaction rules; - * pass-through when none), and hands the result to the backend — synchronously, with every - * handler self-contained so a failing backend can never starve other - * subscribers (cordis `emit` is stop-on-throw) or touch the agent loop. - * Composed by a backend in its constructor. + * pass-through when none), then hands the result to the backend immediately + * or holds it for explicit release. Every synchronous handler is + * self-contained so a failing backend can never starve other subscribers + * (cordis `emit` is stop-on-throw) or touch the agent loop. Composed by a + * backend in its constructor. * * @module @deepseek-ai/dsh-session-telemetry/coordinator */ @@ -16,6 +17,16 @@ import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import type { Agent } from '@deepseek-ai/dsh-agent' import type { TelemetryBackend, TelemetryRecord, TelemetrySeverity } from './index.ts' +/** Whether capture hands records over immediately or holds them for an explicit release. */ +export type TelemetryDelivery = 'immediate' | 'held' + +/** One redacted record waiting at the capture boundary. */ +interface PendingRecord { + readonly record: TelemetryRecord + /** Ledger cursor advanced only after the backend accepts this record. */ + readonly seq?: number +} + /** * The handoff cursor: per session, the highest `seq` handed to a backend. * Deliberately MODULE-scope ambient state — a narrow, documented exception @@ -35,14 +46,13 @@ const handoffCursor = new WeakMap() * Registers the persistence-coordinator listener set plus the `agent/error` * relay, all through `ctx.effect()`/`ctx.on()` on the composing fiber, and * sweeps already-live sessions (a hot reload does not replay - * `session/created`). A `session/disposed` emits the session's `shutdown` - * operational record — the marker rides the session's own termination edge, - * where receivers key crash detection — and retires it from the adopted set, - * so a long-lived backend neither retains closed sessions (and their frozen - * event logs) nor re-marks them at unload. Disposal marks the sessions still - * alive at teardown (their own edge would fire unobserved) and then awaits - * the backend's `shutdown()`; a failure there warns instead of throwing — - * best-effort reporting must not fail application teardown. + * `session/created`). A `session/disposed` captures the session's `shutdown` + * operational record at its own termination edge and retires it from the + * adopted set. Immediate delivery hands that marker over; held delivery keeps + * it local without another explicit release. Disposal captures the same + * marker for sessions still alive, then awaits the backend's `shutdown()`; a + * failure there warns instead of throwing — best-effort reporting must not + * fail application teardown. */ export class TelemetryCoordinator { /** @@ -53,28 +63,30 @@ export class TelemetryCoordinator { private readonly adopted = new Set() /** Per session, the `turn:step` keys whose first chunk already shipped; rebuilt from the log on re-adoption. */ private readonly chunkSeen = new WeakMap>() + /** Redacted records retained until {@link release}; weak keys do not extend session lifetime. */ + private readonly held = new WeakMap() /** * @param ctx - the composing backend's context; listeners bind to its fiber. * @param backend - the backend receiving records; owned elsewhere, never disposed here beyond `shutdown()` forwarding. + * @param delivery - immediate handoff, or held delivery released explicitly per session. */ constructor( private readonly ctx: Context, private readonly backend: TelemetryBackend, + private readonly delivery: TelemetryDelivery = 'immediate', ) { ctx.on('session/created', (session) => { this.adopt(session) }) - // The session's own termination edge: emit the shutdown marker HERE — - // receivers classify a session with activity and no marker as crashed, - // so a normally closed session in a long-running host must get its - // marker at disposal, not never. Then retire: the projection/cursor - // WeakMaps die with the Session object; only the strong adopted set - // needs the explicit release. + // Capture the shutdown marker at the session's own termination edge. + // Immediate delivery preserves crash classification; held delivery does + // not let a later lifecycle edge extend a user-released prefix. Then + // retire the only strong reference owned by this coordinator. ctx.on('session/disposed', (session) => { this.contain(() => { if (!this.adopted.delete(session)) return - this.handOff(shutdownRecord(session)) + this.submit(session, { record: this.redact(shutdownRecord(session)) }) }) }) ctx.on('session/event', (session, event) => { @@ -95,13 +107,12 @@ export class TelemetryCoordinator { }) }) ctx.effect(() => async () => { - // Sessions still adopted here are alive through a whole-application - // teardown (their own disposal edge will fire after telemetry is gone, - // unobserved) — mark them now so the receiver sees a clean stop of - // observation rather than a crash-shaped silence. + // Sessions still adopted here are alive through whole-application + // teardown, so capture the marker before the backend quiesces. Held + // delivery intentionally leaves it local without another release. for (const session of this.adopted) { this.contain(() => { - this.handOff(shutdownRecord(session)) + this.submit(session, { record: this.redact(shutdownRecord(session)) }) }) } try { @@ -115,6 +126,23 @@ export class TelemetryCoordinator { } } + /** + * Hand the records currently held for one session to the backend in capture order. + * Records captured after this call form a new held prefix. Backend failures remain + * contained per record and do not starve later records in the same release. + * @param session - session whose pending capture prefix may leave the process. + */ + release(session: Session): void { + const pending = this.held.get(session) + if (pending === undefined) return + this.held.delete(session) + for (const record of pending) { + this.contain(() => { + this.deliver(session, record) + }) + } + } + /** * Adopt a session: replay its log THROUGH the projection from the handoff * cursor, then rely on the firehose for everything after. When no cursor @@ -153,7 +181,7 @@ export class TelemetryCoordinator { } } - /** Project one event and hand it to the backend, advancing the cursor on handoff. */ + /** Project and redact one event, then submit it under the delivery policy. */ private capture(session: Session, event: SessionEvent): void { if (event.type === 'assistant/chunk') { const key = `${event.data.turn}:${event.data.step}` @@ -165,27 +193,47 @@ export class TelemetryCoordinator { if (seen.has(key)) return seen.add(key) } - this.handOff({ - channel: 'ledger', - time: event.time, - severity: severityOf(event), - attributes: identityOf(session, event), - // The live event object is mutable and the backend serializes later; - // append-time validation guarantees this clone cannot throw. - body: structuredClone(event.data), + this.submit(session, { + record: this.redact({ + channel: 'ledger', + time: event.time, + severity: severityOf(event), + attributes: identityOf(session, event), + // The live event object is mutable and the backend serializes later; + // append-time validation guarantees this clone cannot throw. + body: structuredClone(event.data), + }), + seq: event.seq, }) - handoffCursor.set(session, event.seq) } /** - * Run the `telemetry/record` waterfall over one record and hand the result - * to the backend. The innermost `next` passes the record through unchanged - * — the seam ships no rules; exported data is as clean as the listeners a - * deployment mounts. Callers run inside {@link contain}, so a throwing - * rule withholds the record instead of reaching the loop (fail-closed). + * Run the `telemetry/record` waterfall at capture time. The innermost `next` + * passes the record through unchanged — the seam ships no rules; exported + * data is as clean as the listeners a deployment mounts. Callers run inside + * {@link contain}, so a throwing rule withholds the record instead of + * reaching the loop (fail-closed). Held delivery stores only this result, so + * a later policy reload cannot expose the pre-redaction capture. */ - private handOff(record: TelemetryRecord): void { - this.backend.emit(this.ctx.waterfall('telemetry/record', record, () => record)) + private redact(record: TelemetryRecord): TelemetryRecord { + return this.ctx.waterfall('telemetry/record', record, () => record) + } + + /** Hold one redacted record or deliver it immediately under the configured policy. */ + private submit(session: Session, pending: PendingRecord): void { + if (this.delivery === 'held') { + let records = this.held.get(session) + if (records === undefined) this.held.set(session, records = []) + records.push(pending) + return + } + this.deliver(session, pending) + } + + /** Hand one redacted record to the backend, then advance its ledger cursor. */ + private deliver(session: Session, pending: PendingRecord): void { + this.backend.emit(pending.record) + if (pending.seq !== undefined) handoffCursor.set(session, pending.seq) } /** Forward the turn-end boundary to the backend's optional flush hint. */ @@ -196,19 +244,21 @@ export class TelemetryCoordinator { /** Relay one `agent/error` bus emission as an `agent-error` operational record. */ private relayAgentError(agent: Agent, turn: number, step: number, error: unknown): void { const detail = errorDetail(error) - this.handOff({ - channel: 'ops', - time: Date.now(), - severity: 'error', - attributes: { - 'telemetry.op': 'agent-error', - 'session.id': String(agent.session.id), - 'agent.id': agent.id, - 'error.name': detail.name, - turn, - step, - }, - body: detail, + this.submit(agent.session, { + record: this.redact({ + channel: 'ops', + time: Date.now(), + severity: 'error', + attributes: { + 'telemetry.op': 'agent-error', + 'session.id': String(agent.session.id), + 'agent.id': agent.id, + 'error.name': detail.name, + turn, + step, + }, + body: detail, + }), }) } diff --git a/packages/telemetry/session-telemetry/src/index.ts b/packages/telemetry/session-telemetry/src/index.ts index e7340eedd5..914ef96a95 100644 --- a/packages/telemetry/session-telemetry/src/index.ts +++ b/packages/telemetry/session-telemetry/src/index.ts @@ -3,8 +3,9 @@ * * The seam owns the CAPTURE side of session-event reporting — which records * exist (the chunk projection), what they carry (the logical record), when - * they are handed over (adoption, the per-append firehose, lifecycle - * forwarding), and the HMR handoff cursor. Everything downstream of + * they are captured (adoption, the per-append firehose, lifecycle + * forwarding), immediate versus explicitly released handoff, and the HMR + * cursor. Everything downstream of * {@link Telemetry.emit} — batching, retry, queueing, loss policy — is the * reporting SDK's territory and is deliberately not modelled here. The * design and its trade-offs are pinned in @@ -94,9 +95,10 @@ export interface TelemetryBackend { /** * Hand one record to the backend's pipeline. MUST be a non-blocking * enqueue — the coordinator calls this synchronously from the - * `session/event` hot path, so anything slower than a queue push would tax - * the agent loop. Errors thrown here are contained by the coordinator and - * logged; they never reach the loop. + * `session/event` hot path, either at capture or while releasing a held + * prefix, so anything slower than a queue push would tax the agent loop. + * Errors thrown here are contained by the coordinator and logged; they + * never reach the loop. * @param record - the logical record to report; owned by the backend after the call. */ emit(record: TelemetryRecord): void @@ -121,6 +123,9 @@ export interface TelemetryBackend { * coordinator emits its dispose-time `shutdown` markers immediately before * calling this). Awaited by the coordinator's dispose; a rejection is * logged as a warning and never fails application teardown. + * The coordinator captures dispose-time shutdown markers immediately + * before this call; immediate delivery enqueues them, while held delivery + * leaves an unreleased suffix local. * @returns resolves when the backend's pipeline has quiesced. */ shutdown(): Promise @@ -153,4 +158,4 @@ export abstract class Telemetry extends Service implements TelemetryBackend { abstract shutdown(): Promise } -export { TelemetryCoordinator } from './coordinator.ts' +export { TelemetryCoordinator, type TelemetryDelivery } from './coordinator.ts' diff --git a/packages/telemetry/session-telemetry/tests/telemetry.spec.ts b/packages/telemetry/session-telemetry/tests/telemetry.spec.ts index a449a4053d..d913e6a742 100644 --- a/packages/telemetry/session-telemetry/tests/telemetry.spec.ts +++ b/packages/telemetry/session-telemetry/tests/telemetry.spec.ts @@ -10,7 +10,12 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import SessionStore, { SessionId, type Session, type SessionEvent } from '@deepseek-ai/dsh-session' import type { Agent } from '@deepseek-ai/dsh-agent' -import { TelemetryCoordinator, type TelemetryBackend, type TelemetryRecord } from '../src/index.ts' +import { + TelemetryCoordinator, + type TelemetryBackend, + type TelemetryDelivery, + type TelemetryRecord, +} from '../src/index.ts' declare module '@deepseek-ai/dsh-session' { interface SessionEventMap { @@ -54,15 +59,21 @@ class FakeBackend implements TelemetryBackend { } } -async function setup(backend: FakeBackend = new FakeBackend()) { +async function setup( + backend: FakeBackend = new FakeBackend(), + delivery: TelemetryDelivery = 'immediate', +) { const ctx = new Context() await ctx.plugin(SessionStore) + let coordinator!: TelemetryCoordinator const fiber = await ctx.plugin({ name: 'fake-telemetry', inject: ['sessions'], - apply: (inner: Context) => void new TelemetryCoordinator(inner, backend), + apply: (inner: Context) => { + coordinator = new TelemetryCoordinator(inner, backend, delivery) + }, }) - return { ctx, backend, fiber } + return { ctx, backend, coordinator, fiber } } function liveSession(ctx: Context, id = `s-${Math.random().toString(36).slice(2)}`): Session { @@ -167,6 +178,80 @@ describe('TelemetryCoordinator capture', () => { }) }) +describe('TelemetryCoordinator held delivery', () => { + it('releases one pending prefix at a time without handing later records over early', async () => { + const { ctx, backend, coordinator } = await setup(new FakeBackend(), 'held') + const session = liveSession(ctx, 'held-prefix') + appendTurn(session) + expect(backend.records).toEqual([]) + + coordinator.release(session) + expect(backend.ledger().map(record => record.attributes['event.type'])).toEqual([ + 'turn/start', + 'user/message', + ]) + + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + expect(backend.ledger()).toHaveLength(2) + coordinator.release(session) + coordinator.release(session) + expect(backend.ledger().map(record => record.attributes['event.type'])).toEqual([ + 'turn/start', + 'user/message', + 'turn/end', + ]) + }) + + it('stores the capture-time redacted copy rather than re-running policy at release', async () => { + const { ctx, backend, coordinator } = await setup(new FakeBackend(), 'held') + const disposeRule = ctx.on('telemetry/record', (_record, next) => ({ + ...next(), + body: { scrubbed: true }, + })) + const session = liveSession(ctx, 'held-redacted') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + disposeRule() + + coordinator.release(session) + expect(backend.ledger()[0]!.body).toEqual({ scrubbed: true }) + }) + + it('contains each backend failure independently while releasing a batch', async () => { + const backend = new FakeBackend() + backend.rejectSeq = 1 + const { ctx, coordinator } = await setup(backend, 'held') + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) + const session = liveSession(ctx, 'held-failure') + appendTurn(session) + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + + coordinator.release(session) + expect(backend.ledger().map(record => record.attributes['event.seq'])).toEqual([0, 2]) + expect(warn).toHaveBeenCalled() + }) + + it('rebuilds an unreleased prefix after coordinator reload', async () => { + const first = new FakeBackend() + const { ctx, fiber } = await setup(first, 'held') + const session = liveSession(ctx, 'held-reload') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await fiber.dispose() + expect(first.records).toEqual([]) + + const second = new FakeBackend() + let coordinator!: TelemetryCoordinator + await ctx.plugin({ + name: 'fake-telemetry-after-held-reload', + inject: ['sessions'], + apply: (inner: Context) => { + coordinator = new TelemetryCoordinator(inner, second, 'held') + }, + }) + coordinator.release(session) + expect(second.ledger().map(record => record.attributes['event.seq'])).toEqual([0]) + }) +}) + describe('TelemetryCoordinator adoption', () => { it('exports an unpublished suffix without re-exporting constructor history', async () => { const backend = new FakeBackend() diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 2ecfd0e869..882d42c8d8 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -445,6 +445,9 @@ importers: '@cordisjs/plugin-include': specifier: workspace:* version: link:../vendor/include + '@cordisjs/plugin-logger-console': + specifier: workspace:* + version: link:../vendor/logger-console '@deepseek-ai/dsh-acp-demo': specifier: workspace:* version: link:../packages/examples/acp-demo @@ -466,6 +469,9 @@ importers: '@deepseek-ai/dsh-code-runtime-worker': specifier: workspace:* version: link:../packages/code-runtime/code-runtime-worker + '@deepseek-ai/dsh-command-feedback': + specifier: workspace:* + version: link:../packages/feedback/command-feedback '@deepseek-ai/dsh-compact-basic': specifier: workspace:* version: link:../packages/compact/compact-basic @@ -4810,6 +4816,9 @@ importers: '@cordisjs/plugin-loader': specifier: workspace:^ version: link:../../../vendor/loader + '@deepseek-ai/dsh-command-feedback': + specifier: workspace:^ + version: link:../../feedback/command-feedback '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants From 9d9b547d55dc6a2db4449193bcc505e2b5282712 Mon Sep 17 00:00:00 2001 From: Turtle Date: Wed, 5 Aug 2026 12:47:53 +0800 Subject: [PATCH 05/22] docs: refresh telemetry module graph --- docs/module-graph.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 61477ae104..bddaf47f98 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -630,10 +630,6 @@ flowchart TD pkg_tasks_local --> pkg_invariants pkg_tasks_local --> pkg_tasks pkg_tasks_local --> pkg_timeout - pkg_session_telemetry_otel --> pkg_invariants - pkg_session_telemetry_otel --> pkg_llm - pkg_session_telemetry_otel --> pkg_session - pkg_session_telemetry_otel --> pkg_session_telemetry pkg_agent_loop --> pkg_agent pkg_agent_loop --> pkg_invariants pkg_agent_loop --> pkg_llm @@ -813,6 +809,11 @@ flowchart TD pkg_tool_tasks --> pkg_system_prompt pkg_tool_tasks --> pkg_tasks pkg_tool_tasks --> pkg_tools + pkg_session_telemetry_otel --> pkg_command_feedback + pkg_session_telemetry_otel --> pkg_invariants + pkg_session_telemetry_otel --> pkg_llm + pkg_session_telemetry_otel --> pkg_session + pkg_session_telemetry_otel --> pkg_session_telemetry pkg_tool_workflow --> pkg_agent pkg_tool_workflow --> pkg_invariants pkg_tool_workflow --> pkg_llm @@ -1096,7 +1097,6 @@ flowchart TD | [`command-feedback`](../packages/feedback/command-feedback) | `feedback` | [`commands`](../packages/ui/commands), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session) | | [`pty-local`](../packages/pty/pty-local) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subprocess`](../packages/subprocess/subprocess) | | [`tasks-local`](../packages/tasks/tasks-local) | `tasks` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tasks`](../packages/tasks/tasks), [`timeout`](../packages/util/timeout) | -| [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel) | `telemetry` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-telemetry`](../packages/telemetry/session-telemetry) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-goal`](../packages/goal/tool-goal) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | @@ -1126,6 +1126,7 @@ flowchart TD | [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`tools`](../packages/core/tools) | | [`tool-pty`](../packages/pty/tool-pty) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`pty`](../packages/pty/pty), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | +| [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel) | `telemetry` | [`command-feedback`](../packages/feedback/command-feedback), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-telemetry`](../packages/telemetry/session-telemetry) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subprocess`](../packages/subprocess/subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | From bb920b32e004926157b3d4e842d9d419b2b1f5ad Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 6 Aug 2026 13:59:05 +0800 Subject: [PATCH 06/22] feat(web): add dedicated skill tool row --- .../2026-08-06-web-skill-tool-row.i18n.yaml | 6 + .../feature/2026-08-06-web-skill-tool-row.md | 29 +++ .../2026-08-06-web-skill-tool-row.zh.md | 29 +++ apps/web/tests/skill-tool-row.e2e.ts | 80 +++++++ .../snapshots/skill-tool-row/ui.expected.md | 48 ++++ apps/web/tsconfig.json | 1 + .../client/ui-primitives/src/icons/index.tsx | 14 ++ .../client/ui-primitives/tests/icons.spec.tsx | 4 +- packages/client/ui-skill/README.i18n.yaml | 4 +- packages/client/ui-skill/README.md | 4 + packages/client/ui-skill/README.zh.md | 4 + packages/client/ui-skill/package.json | 20 +- .../ui-skill/src/client/SkillRow.module.css | 212 ++++++++++++++++++ .../client/ui-skill/src/client/SkillRow.tsx | 174 ++++++++++++++ packages/client/ui-skill/src/client/index.ts | 26 ++- .../client/ui-skill/src/client/locales.ts | 23 ++ .../ui-skill/tests/browser-plugin.spec.ts | 69 +++++- .../client/ui-skill/tests/skill-row.spec.tsx | 152 +++++++++++++ packages/client/ui-skill/tsconfig.json | 9 + pnpm-lock.yaml | 24 ++ tsconfig.host.json | 1 + 21 files changed, 921 insertions(+), 12 deletions(-) create mode 100644 .agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md create mode 100644 .agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md create mode 100644 apps/web/tests/skill-tool-row.e2e.ts create mode 100644 apps/web/tests/snapshots/skill-tool-row/ui.expected.md create mode 100644 packages/client/ui-skill/src/client/SkillRow.module.css create mode 100644 packages/client/ui-skill/src/client/SkillRow.tsx create mode 100644 packages/client/ui-skill/src/client/locales.ts create mode 100644 packages/client/ui-skill/tests/skill-row.spec.tsx diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml new file mode 100644 index 0000000000..8186444a8d --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md +2026-08-06-web-skill-tool-row.md: b1d76c411d7ccc839616ddcce9fee18716489bf5 +2026-08-06-web-skill-tool-row.zh.md: c16a9b84d75c641b0fdd8778ff56c331c2c81546 diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md new file mode 100644 index 0000000000..b1d76c411d --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md @@ -0,0 +1,29 @@ +# Agent Note: Web skill tool row + +Status: implemented + +English | [中文](2026-08-06-web-skill-tool-row.zh.md) + +## Problem + +The Web transcript renders `skill` calls through the generic fallback row, so a loaded instruction set looks like an unknown tool call even though Skill is a first-class product concept. The generic row also exposes the JSON argument envelope beside the result, adding noise around the one identity users need: the loaded skill name. + +## Decision + +`ui-skill` registers a component under the existing `conversation.chat.toolview` keyed slot with key `skill`. The component owns its row chrome from the public `ToolRowProps` contract, matching the independent registrant posture used by the Bash sample instead of importing conversation-private components. + +The collapsed row uses a 16-pixel document-and-sparkle glyph and the Bash row's neutral hierarchy: tertiary glyph, secondary `Skill` title, caption separator, and tertiary skill name. Running, failed, and interrupted calls retain the transcript's shimmer, error dot and first-line summary, and warning dot semantics. A settled call expands through the whole summary row into a 260-pixel bounded `Instructions` card containing the exact durable result text; the existing trajectory `Inspect` handoff remains available below the card. + +The row derives every visible value from the logged call/result slice. It reads the skill name from the recorded `name` argument and the instructions from durable result content, and never joins the current skill catalog for descriptions or provider metadata. The existing ACP `skill-load` recording is seeded through the real Web persistence and composition path for a keyless interaction and accessibility snapshot. + +## Alternatives considered + +- Keep the generic tool row and add only a `skill` color selector in `ui-conversation`. This leaves the redundant input envelope and generic expanded body in place, and makes the conversation package own a domain-specific visual rule. +- Add a new `skill` value to the host tool render-intent union. The keyed client slot already identifies this tool without changing the wire contract, so a new cross-boundary presentation value adds protocol and snapshot surface without enabling another consumer. +- Export the conversation package's private `ToolRow` component for reuse. Client packages intentionally expose contracts rather than cross-package components; exporting it would couple independent feature packages to conversation implementation details. + +## Consequences + +`ui-skill` now depends on the public conversation toolview contract, locale and primitive packages, and React in addition to its reference-source dependencies. It owns a small copy of the disclosure-row chrome, so future global interaction changes must update this registrant alongside the Bash sample and conversation rows. + +Cold replay stays deterministic when the installed skill catalog changes, and the transcript remains compact until instructions are explicitly expanded. The dedicated card intentionally shows the tool's complete framed output rather than extracting only ``, preserving exactly what reached the model and avoiding a second parser for the skill result format. diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md new file mode 100644 index 0000000000..c16a9b84d7 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md @@ -0,0 +1,29 @@ +# Agent Note: Web skill 工具行 + +Status: implemented + +[English](2026-08-06-web-skill-tool-row.md) | 中文 + +## 问题 + +Web transcript（文本记录）通过通用后备行渲染 `skill` 调用，使已加载的指令集看起来像一次未知工具调用，尽管 Skill（技能）已是产品中的一等概念。通用行还会在结果旁暴露 JSON 参数的外层结构，围绕用户真正需要的唯一标识增加了噪声：已加载的 skill 名称。 + +## 决策 + +`ui-skill` 在现有的 `conversation.chat.toolview` 键控 slot 下注册 key 为 `skill` 的组件。该组件基于公开的 `ToolRowProps` 契约自行实现行 chrome，沿用 Bash 示例的独立注册方姿态，而不导入 conversation 私有组件。 + +收起的行使用 16 像素的文档与闪光组合图标，并沿用 Bash 行的中性色层级：图标采用三级色，`Skill` 标题采用二级色，分隔符采用 caption 色，skill 名称采用三级色。运行、失败和中断调用分别沿用 transcript 的扫光、错误状态点加首行摘要，以及警告状态点语义。已结算调用可以通过整个摘要行展开一个高度上限为 260 像素的 `Instructions` 卡片，其中原样呈现持久化结果文本；用于跳转至 trajectory 的现有 `Inspect` 入口仍保留在卡片下方。 + +该行的所有可见值均派生自已记录的调用／结果片段。skill 名称来自已记录的 `name` 参数，指令来自持久化的结果内容；该行绝不关联当前 skill 目录来读取描述或提供方元数据。现有的 ACP（Agent Client Protocol）`skill-load` 记录经由真实的 Web 持久化与组合路径写入，用于无需密钥的交互和无障碍快照。 + +## 考虑过的替代方案 + +- 保留通用工具行，只添加一个 `skill` 颜色选择器，并将其放在 `ui-conversation` 中。该方案仍会保留多余的输入外层结构和通用展开体，也会让 conversation 包拥有特定领域的视觉规则。 +- 在宿主工具渲染意图联合类型中添加新的 `skill` 值。键控客户端 slot 无需更改协议契约即可识别该工具，因此新的跨边界呈现值只会增加协议与快照表层，却没有为其他消费方提供新能力。 +- 导出 conversation 包的私有 `ToolRow` 组件供复用。客户端包刻意对外暴露契约而非跨包组件；导出该组件会使独立功能包耦合到 conversation 的实现细节。 + +## 后果 + +除了引用 source 的依赖外，`ui-skill` 现在还依赖公开的 conversation toolview 契约、locale 包、原语包和 React。它自行保留了一小份折叠展开行 chrome，因此未来的全局交互变更必须与 Bash 示例和 conversation 行同步更新这个注册方。 + +即使已安装的 skill 目录发生变化，冷回放仍具有确定性；在用户显式展开指令前，transcript 保持紧凑。专用卡片有意显示工具完整封装的输出，而不是只提取 ``，从而原样保留模型实际收到的内容，也避免为 skill 结果格式再引入一个解析器。 diff --git a/apps/web/tests/skill-tool-row.e2e.ts b/apps/web/tests/skill-tool-row.e2e.ts new file mode 100644 index 0000000000..af6c941bcd --- /dev/null +++ b/apps/web/tests/skill-tool-row.e2e.ts @@ -0,0 +1,80 @@ +// Web e2e scenario: the real skill-load recording, seeded cold through the +// persistence seam, renders through ui-skill's keyed toolview without a model +// call. The disclosure proves replay-stable naming and exact durable output. +import { readFile } from 'node:fs/promises' +import { fileURLToPath } from 'node:url' +import type { Browser, Page } from 'playwright' +import { chromium } from 'playwright' +import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest' +import { + assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts, + launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold, +} from './scaffold.ts' +import { newEnglishPage, saveFailureShot } from './support.ts' + +const FIXTURE = fileURLToPath(new URL('../../../examples/acp-agent/tests/snapshots/skill-load/session.jsonl', import.meta.url)) +const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/skill-tool-row', import.meta.url)) +const UI_EXPECTED = fileURLToPath(new URL('./snapshots/skill-tool-row/ui.expected.md', import.meta.url)) +const MODE = webSnapshotMode() +const SEED_ID = 'skill-tool-row-web-e2e' +const PROMPT = 'Load the snapshot-skill skill with the skill tool, then reply DONE.' + +describe.skipIf(MODE === 'record')('web e2e: dedicated Skill tool row', () => { + let scaffold: WebScaffold + let browser: Browser + let page: Page + let tripwire: ReturnType + + beforeAll(async () => { + const fixture = await readFile(FIXTURE, 'utf8') + expect(fixtureUserPrompts(fixture)).toEqual([PROMPT]) + scaffold = await launchWebScaffold({}) + await seedSession(scaffold, fixture, SEED_ID) + browser = await chromium.launch() + page = await newEnglishPage(browser) + tripwire = watchConsole(page) + await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) + await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) + + const groupRow = page.locator('[role="treeitem"]').first() + await groupRow.waitFor({ timeout: 15_000 }) + await groupRow.click() + const sessionRow = page.locator('[role="treeitem"]').nth(1) + await sessionRow.waitFor({ timeout: 10_000 }) + await sessionRow.click() + await page.locator('[data-tool="skill"]').waitFor({ timeout: 15_000 }) + }, 120_000) + + afterAll(async () => { + await browser?.close() + await scaffold?.close() + }) + + it('expands the loaded skill to its exact recorded instructions', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-skill-tool-row')) + const call = page.locator('[data-tool="skill"]') + const row = call.getByRole('button', { name: 'Skill snapshot-skill' }) + await expect.poll(() => row.getAttribute('aria-expanded')).toBe('false') + expect(await call.getByText('snapshot-skill', { exact: true }).count()).toBe(1) + + await row.click() + await expect.poll(() => row.getAttribute('aria-expanded')).toBe('true') + await call.getByText('Instructions', { exact: true }).waitFor() + const output = call.locator('pre') + await output.waitFor() + expect(await output.textContent()).toContain('') + expect(await output.textContent()).toContain('Follow these snapshot-only instructions.') + expect(await output.evaluate(element => getComputedStyle(element.parentElement!).maxHeight)).toBe('260px') + + const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)) + .replace(/\b\d{1,2}\/\d{1,2}(?= \{\{clock\}\})/g, '{{date}}') + .split(SEED_ID).join('{{seededId}}') + await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE) + expect(tripwire.pageErrors).toEqual([]) + expect(tripwire.warnings).toEqual([]) + }, 60_000) + + it('keeps its snapshot inventory closed', async () => { + await assertFixtureInventory(SNAPSHOT_DIR, ['ui.expected.md']) + }) +}) diff --git a/apps/web/tests/snapshots/skill-tool-row/ui.expected.md b/apps/web/tests/snapshots/skill-tool-row/ui.expected.md new file mode 100644 index 0000000000..7a51aae904 --- /dev/null +++ b/apps/web/tests/snapshots/skill-tool-row/ui.expected.md @@ -0,0 +1,48 @@ +- banner: + - navigation "Session hierarchy": + - button "Load the snapshot-skill skill with" [disabled] + - tablist: + - tab "Chat" [selected] + - tab "Trajectory" +- text: Load the snapshot-skill skill with the skill tool, then reply DONE. {{date}} {{clock}} +- button "Copy": + - img +- button "Branch into a new conversation" [disabled]: + - img +- text: Available only on the last message of a completed turn +- button "Context injection @deepseek-ai/dsh-system-prompt": + - img + - img + - text: Context injection @deepseek-ai/dsh-system-prompt +- button "Context injection skill-catalog": + - img + - img + - text: Context injection skill-catalog +- button "Think Load the requested skill.": + - img + - img + - text: Think Load the requested skill. +- button "Skill snapshot-skill" [expanded]: + - img + - text: Skill snapshot-skill +- region "Instructions": "Instructions Base directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill Resolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed. Follow these snapshot-only instructions. Resolve referenced resources relative to this skill directory. " +- button "Inspect" +- button "Think The skill is loaded.": + - img + - img + - text: Think The skill is loaded. +- paragraph: DONE +- button "Copy": + - img +- button "Branch into a new conversation": + - img +- text: {{date}} {{clock}} Ran for {{duration}} TTFT {{duration}} {{throughput}} tok/s +- textbox "Message the agent" +- button "Commands": + - img +- 'button "Access mode, current: Workspace Write"': Workspace Write +- button "Select model": + - text: Select model + - img +- button "Send message" [disabled] +- text: 1 turns · 2 steps LLM {{duration}} · Tool call {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 0% Input 280 tok · Output 30 tok diff --git a/apps/web/tsconfig.json b/apps/web/tsconfig.json index dd5fe879e7..9e395e49ad 100644 --- a/apps/web/tsconfig.json +++ b/apps/web/tsconfig.json @@ -62,6 +62,7 @@ "tests/startup-auto-selection.e2e.ts", "tests/subagent-conversation.e2e.ts", "tests/bash-abort-row.e2e.ts", + "tests/skill-tool-row.e2e.ts", "tests/chat-scroll-fixture.ts", "tests/chat-scroll-contract.e2e.ts", "tests/chat-long-interactions.e2e.ts", diff --git a/packages/client/ui-primitives/src/icons/index.tsx b/packages/client/ui-primitives/src/icons/index.tsx index 71e647a3e9..b0b76e164b 100644 --- a/packages/client/ui-primitives/src/icons/index.tsx +++ b/packages/client/ui-primitives/src/icons/index.tsx @@ -750,6 +750,20 @@ export const IconSparkle16 = ({ size = 16, className }: IconProps) => ( ) +/** skill_outline_16 (skill tool-row glyph; document instructions + sparkle) */ +export const IconSkillOutline16 = ({ size = 16, className }: IconProps) => ( + + + + +) + /** ic_ds_question_outline_14 (figma extract): ring + question glyph. */ export const IconQuestionOutline14 = ({ size = 14, className }: IconProps) => ( diff --git a/packages/client/ui-primitives/tests/icons.spec.tsx b/packages/client/ui-primitives/tests/icons.spec.tsx index 9877b7df1f..92f0d3cc37 100644 --- a/packages/client/ui-primitives/tests/icons.spec.tsx +++ b/packages/client/ui-primitives/tests/icons.spec.tsx @@ -16,8 +16,8 @@ const icons = Object.fromEntries( const iconNames = Object.keys(icons) describe('ic_ds_ icon set', () => { - it('exports the full P-I set (46 deepsuite + 17 figma extracts + the hand-authored sparkle)', () => { - expect(iconNames.length).toBe(64) + it('exports the full P-I set (46 deepsuite + 17 figma extracts + two hand-authored product glyphs)', () => { + expect(iconNames.length).toBe(65) }) it.each(iconNames)('%s renders an svg with currentColor fills and no hardcoded palette', (name) => { diff --git a/packages/client/ui-skill/README.i18n.yaml b/packages/client/ui-skill/README.i18n.yaml index 059a5d8986..d23f68ee85 100644 --- a/packages/client/ui-skill/README.i18n.yaml +++ b/packages/client/ui-skill/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-skill/README.md -README.md: fc83ae47dc83e72d60f382892aa678989902d217 -README.zh.md: e103db812d2a21f7f211bc843ec0cd31d1dc2c1e +README.md: 2280c9302dbc46cff723752f88c47940f98417d5 +README.zh.md: 0e9344ff63139f77461b02b48e18b0e94e54c223 diff --git a/packages/client/ui-skill/README.md b/packages/client/ui-skill/README.md index fc83ae47dc..2280c9302d 100644 --- a/packages/client/ui-skill/README.md +++ b/packages/client/ui-skill/README.md @@ -8,6 +8,10 @@ A failed `skill.list` throws from `candidates`, which the slash shell logs and f The `/client` export surface is the plugin body (`apply`/`inject`) only; the source object is internal to the registration effect. +## Skill tool row + +The browser plugin also registers a keyed `skill` toolview in `conversation.chat.toolview`. A collapsed row renders the 16-pixel skill document-and-sparkle glyph, `Skill` title, separator, and requested skill name with the same neutral hierarchy as the Bash row; running calls carry the transcript shimmer, failures replace the name with the first error line, and interrupted calls use the warning state. A settled row expands as one whole-row disclosure into a bounded `Instructions` card containing the exact durable tool output, with the standard trajectory `Inspect` affordance when available. The row derives its name, lifecycle, and body only from the logged call/result slice, never from the current catalog, so cold replay remains stable even when installed skills or their descriptions change. + ## Model Experience ### Skill reference text in the user prompt diff --git a/packages/client/ui-skill/README.zh.md b/packages/client/ui-skill/README.zh.md index e103db812d..0e9344ff63 100644 --- a/packages/client/ui-skill/README.zh.md +++ b/packages/client/ui-skill/README.zh.md @@ -8,6 +8,10 @@ skill（技能）引用 source 的浏览器端：把 `/` 触发的 `skill` sourc `/client` 导出表层只有插件主体（`apply`／`inject`）；source 对象是注册 effect 的内部实现。 +## skill 工具行 + +浏览器插件还会把一个 key 为 `skill` 的 toolview 注册进 `conversation.chat.toolview`。收起的行以与 Bash 行相同的中性色层级显示 16 像素的 skill 文档与闪光组合图标、`Skill` 标题、分隔符和请求加载的 skill 名称；运行中的调用带有 transcript（文本记录）的扫光效果，失败时用错误首行替换名称，中断调用则使用警告状态。已结算的行以整行作为展开入口，展开后显示一个尺寸受限的 `Instructions` 卡片，其中原样呈现持久化的工具输出；可用时还会提供标准执行轨迹的 `Inspect` 入口。该行的名称、生命周期和正文只派生自已记录的调用／结果片段，绝不读取当前 skill 目录，因此即使已安装的 skill 或其描述发生变化，冷回放仍保持稳定。 + ## 模型体验 ### 用户提示词中的 skill 引用文本 diff --git a/packages/client/ui-skill/package.json b/packages/client/ui-skill/package.json index 20d61cdb53..c9d2dd4ed8 100644 --- a/packages/client/ui-skill/package.json +++ b/packages/client/ui-skill/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-client-ui-skill", - "description": "Skill reference source: '/' menu candidates from skill.list, inserts name references", + "description": "Web skill references and the dedicated skill tool row", "version": "0.0.1", "private": true, "type": "module", @@ -25,6 +25,8 @@ "dshClient": { "inject": [ "@deepseek-ai/dsh-client-runtime", + "@deepseek-ai/dsh-client-locale", + "@deepseek-ai/dsh-client-ui-conversation", "@deepseek-ai/dsh-client-ui-slash" ], "platform": "web" @@ -36,19 +38,31 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-client-connection": "^0.0.1", + "@deepseek-ai/dsh-client-locale": "^0.0.1", "@deepseek-ai/dsh-client-runtime": "^0.0.1", + "@deepseek-ai/dsh-client-ui-conversation": "^0.0.1", + "@deepseek-ai/dsh-client-ui-primitives": "^0.0.1", "@deepseek-ai/dsh-client-ui-slash": "^0.0.1", "@deepseek-ai/dsh-client-ui-slots": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", - "cordis": "^4.0.0-rc.7" + "cordis": "^4.0.0-rc.7", + "react": "^18.2.0" }, "devDependencies": { "@deepseek-ai/dsh-client-connection": "workspace:^", + "@deepseek-ai/dsh-client-locale": "workspace:^", "@deepseek-ai/dsh-client-runtime": "workspace:^", + "@deepseek-ai/dsh-client-test-runtime": "workspace:^", + "@deepseek-ai/dsh-client-ui-conversation": "workspace:^", + "@deepseek-ai/dsh-client-ui-primitives": "workspace:^", "@deepseek-ai/dsh-client-ui-slash": "workspace:^", "@deepseek-ai/dsh-client-ui-slots": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", - "cordis": "^4.0.0-rc.7" + "@testing-library/react": "^16.1.0", + "@types/react": "~18.3.1", + "cordis": "^4.0.0-rc.7", + "react": "^18.2.0", + "react-dom": "^18.2.0" }, "files": [ "lib/index.js", diff --git a/packages/client/ui-skill/src/client/SkillRow.module.css b/packages/client/ui-skill/src/client/SkillRow.module.css new file mode 100644 index 0000000000..05c3388aa9 --- /dev/null +++ b/packages/client/ui-skill/src/client/SkillRow.module.css @@ -0,0 +1,212 @@ +/* Skill toolview: Bash-matched summary row plus a bounded instructions disclosure. */ + +.card { + display: flex; + flex-direction: column; +} + +.row { + position: relative; + overflow: hidden; + display: flex; + align-items: center; + height: 24px; + min-width: 0; +} + +.row[data-expandable] { + cursor: pointer; +} + +.card[data-state='running'] .row::after { + content: ''; + position: absolute; + inset: 0 auto 0 0; + width: 300px; + background: linear-gradient( + 90deg, + transparent 0%, + color-mix(in srgb, var(--dsw-alias-bg-base) 60%, transparent) 55%, + transparent 100% + ); + animation: dsh-skill-row-sweep 2.6s ease-out infinite; + pointer-events: none; +} + +@keyframes dsh-skill-row-sweep { + 0% { left: -300px; } + 90%, 100% { left: 100%; } +} + +.leading { + position: relative; + flex: none; + width: 16px; + height: 16px; + display: inline-flex; + align-items: center; + justify-content: center; + margin-right: 6px; + color: var(--dsw-alias-label-tertiary); +} + +.chevron { + color: var(--dsw-alias-label-secondary); +} + +.iconIdle { + display: inline-flex; + opacity: 1; + transition: opacity 100ms ease; +} + +.chevronHover { + position: absolute; + inset: 0; + margin: auto; + opacity: 0; + transition: opacity 100ms ease; +} + +.row:hover .iconIdle { + opacity: 0; +} + +.row:hover .chevronHover { + opacity: 1; +} + +.title { + flex: none; + font-size: 14px; + line-height: 24px; + color: var(--dsw-alias-label-secondary); +} + +.separator { + flex: none; + width: 2px; + height: 2px; + border-radius: 1px; + margin: 0 8px; + background: var(--dsw-alias-label-caption); +} + +.summary { + flex: 1 1 auto; + min-width: 0; + overflow: hidden; + text-overflow: ellipsis; + white-space: nowrap; + font-size: 14px; + line-height: 24px; + color: var(--dsw-alias-label-tertiary); +} + +.errorSummary { + color: var(--dsw-alias-state-error-primary); +} + +.bodyWrap { + display: flex; + flex-direction: column; +} + +.instructionsCard { + display: flex; + flex-direction: column; + max-height: 260px; + margin: 4px 0 4px 4px; + overflow: hidden; + border: 1px solid var(--dsw-alias-border-l1); + border-radius: 12px; + background: var(--dsw-alias-markdown-code-block); +} + +.instructionsHeader { + flex: none; + padding: 8px 12px; + border-bottom: 1px solid var(--dsw-alias-border-l2); + background: var(--dsw-alias-markdown-code-block-banner); + font-size: 11px; + font-weight: 500; + line-height: 16px; + color: var(--dsw-alias-label-caption); + text-transform: uppercase; + letter-spacing: 0.04em; +} + +.instructions { + min-height: 0; + margin: 0; + padding: 10px 12px 12px; + overflow: auto; + white-space: pre-wrap; + overflow-wrap: anywhere; + font: var(--dsw-font-markdown-code-block-small); + color: var(--dsw-alias-label-secondary); +} + +.instructions[data-error] { + color: var(--dsw-alias-state-error-primary); +} + +.instructions::-webkit-scrollbar-thumb { + border: 2px solid transparent; + background-clip: padding-box; + border-radius: 6px; +} + +.instructions::-webkit-scrollbar-track { + margin: 6px 0; +} + +.inspectButton { + display: inline-flex; + align-self: flex-start; + align-items: center; + gap: 4px; + margin: 4px 0 2px 4px; + padding: 2px 8px; + border: 1px solid var(--dsw-alias-border-l2); + border-radius: 999px; + background: var(--dsw-alias-bg-base); + color: var(--dsw-alias-label-secondary); + font-size: 11px; + line-height: 16px; + cursor: pointer; + opacity: 0; + transition: opacity 100ms ease; +} + +.card:hover .inspectButton, +.inspectButton:focus-visible { + opacity: 1; +} + +.inspectButton:hover { + background: var(--dsw-alias-interactive-bg-hover-solid); + color: var(--dsw-alias-label-primary); +} + +.visuallyHidden { + position: absolute; + width: 1px; + height: 1px; + overflow: hidden; + clip: rect(0 0 0 0); + white-space: nowrap; +} + +@media (prefers-reduced-motion: reduce) { + .card[data-state='running'] .row::after { + animation: none; + display: none; + } + + .iconIdle, + .chevronHover, + .inspectButton { + transition: none; + } +} diff --git a/packages/client/ui-skill/src/client/SkillRow.tsx b/packages/client/ui-skill/src/client/SkillRow.tsx new file mode 100644 index 0000000000..c847678e4a --- /dev/null +++ b/packages/client/ui-skill/src/client/SkillRow.tsx @@ -0,0 +1,174 @@ +// Skill toolview registrant: a domain-owned row over the keyed toolview hole. +// The compact accent row keeps loaded instructions scannable in the transcript; +// the exact durable tool output remains available in a bounded disclosure card. + +import { useState, type KeyboardEvent, type ReactNode } from 'react' +import { + IconChevronDownOutline14, IconSkillOutline16, StateDot, +} from '@deepseek-ai/dsh-client-ui-primitives' +import type { ToolRowProps } from '@deepseek-ai/dsh-client-ui-conversation/client' +import type { PropsLocale } from '@deepseek-ai/dsh-client-ui-slots' +import css from './SkillRow.module.css' + +/** Skill row lifecycle derived solely from the durable call slice. */ +type SkillRowState = 'running' | 'ok' | 'error' | 'stopped' + +/** Full row props: the toolview runtime share plus this package's locale seat. */ +type SkillRowProps = ToolRowProps & PropsLocale<'skill'> + +/** Compact, replay-stable view model for the dedicated row. */ +interface SkillRowModel { + readonly name: string + readonly output: string | null + readonly errorSummary: string | null + readonly state: SkillRowState +} + +/** First physical line for the collapsed error summary and malformed-args fallback. */ +function firstLine(text: string): string { + const newline = text.indexOf('\n') + return newline === -1 ? text : text.slice(0, newline) +} + +/** Skill names are the only call argument the compact row presents. */ +function skillName(argsRaw: string, callId: string): string { + try { + const parsed = JSON.parse(argsRaw) as unknown + if (typeof parsed === 'object' && parsed !== null) { + const name = (parsed as Record).name + if (typeof name === 'string' && name !== '') return firstLine(name) + } + } catch { + // Streaming can expose a truncated JSON prefix; its first line is still + // more useful than replacing the call with an unrelated catalog lookup. + } + return argsRaw === '' ? callId : firstLine(argsRaw) +} + +/** Flatten the durable result exactly like the generic row's text fallback. */ +function resultText(block: ToolRowProps['block']): string | null { + if (!('kind' in block)) return null + const parts: string[] = [] + for (const item of block.content) { + parts.push(item.type === 'text' ? item.text : JSON.stringify(item, null, 2)) + } + if (parts.length === 0 && block.error !== undefined) { + parts.push(`${block.error.name}: ${block.error.code}`) + } + return parts.join('\n') || null +} + +/** Derive display state without consulting the live skill catalog. */ +function skillRowModel(block: ToolRowProps['block']): SkillRowModel { + const settled = 'kind' in block + const argsRaw = (settled ? block.call?.argsRaw : block.argsRaw) ?? '' + const state: SkillRowState = !settled + ? 'running' + : block.error?.code === 'interrupted' + ? 'stopped' + : block.isError ? 'error' : 'ok' + const output = resultText(block) + return { + name: skillName(argsRaw, block.callId), + output, + errorSummary: state === 'error' && output !== null ? firstLine(output) : null, + state, + } +} + +/** State substitution for the collapsed leading slot. */ +function leadingFor(state: SkillRowState): ReactNode { + switch (state) { + case 'error': return + case 'stopped': return + default: return + } +} + +/** Visually hidden state copy for the colour-only lifecycle cues. */ +function stateStatus(state: SkillRowState, t: SkillRowProps['t']): string | null { + switch (state) { + case 'running': return t('row.running') + case 'error': return t('row.failed') + case 'stopped': return t('row.stopped') + default: return null + } +} + +/** Inspect affordance glyph shared with the transcript's other tool rows. */ +function IconInspect() { + return ( + + + + ) +} + +/** + * Render one `skill` tool call as an accent summary and instructions disclosure. + * @param props - keyed toolview payload plus the skill locale seat. + * @returns the dedicated skill row. + */ +export function SkillRow({ block, inspect, t }: SkillRowProps) { + const model = skillRowModel(block) + const [expanded, setExpanded] = useState(false) + const expandable = model.output !== null + const open = expanded && expandable + const status = stateStatus(model.state, t) + const summary = model.errorSummary ?? model.name + const ariaLabel = status === null ? `Skill ${summary}` : `${status} Skill ${summary}` + const toggleExpand = (): void => { + setExpanded(value => !value) + } + const toggleFromKeyboard = (event: KeyboardEvent): void => { + if (!expandable || (event.key !== 'Enter' && event.key !== ' ')) return + event.preventDefault() + toggleExpand() + } + const leading = open + ? + : expandable + ? ( + <> + {leadingFor(model.state)} + + + ) + : leadingFor(model.state) + return ( +
+
+ {leading} + {status !== null ? {status} : null} + Skill + + + {summary} + +
+ {open ? ( +
+
+
{t('row.instructions')}
+ 
{model.output}
+
+ {inspect !== undefined ? ( + + ) : null} +
+ ) : null} +
+ ) +} diff --git a/packages/client/ui-skill/src/client/index.ts b/packages/client/ui-skill/src/client/index.ts index c23f15b770..9631125801 100644 --- a/packages/client/ui-skill/src/client/index.ts +++ b/packages/client/ui-skill/src/client/index.ts @@ -19,10 +19,24 @@ * not kill the prewarm other consumers will hit, so it carries its own * abort (fired only on invalidation/teardown) while a candidates caller * with an aborted signal just returns early. + * + * This browser half also owns the `skill` keyed toolview: a replay-stable + * accent row derived only from each logged call/result slice. */ import type { ConnectionHandle, SessionId, SkillEntry } from '@deepseek-ai/dsh-client-connection/client' import type { ClientContext, ISessions } from '@deepseek-ai/dsh-client-runtime/client' import type { SlashServiceContract, SlashSource } from '@deepseek-ai/dsh-client-ui-slash/client' +// Type-only: pulls the locale plugin's Context merge (ctx.locale). +import type {} from '@deepseek-ai/dsh-client-locale/client' +import { SkillRow } from './SkillRow.tsx' +import { en, NS, zh, type SkillKey } from './locales.ts' + +declare module '@deepseek-ai/dsh-client-ui-slots' { + interface LocaleNamespaceMap { + /** The dedicated skill tool row's copy. */ + skill: SkillKey + } +} /** One session's catalog fetch: the shared promise plus its own abort handle. */ interface CatalogFetch { @@ -32,14 +46,20 @@ interface CatalogFetch { settled?: readonly SkillEntry[] } -/** Required services: slash registry, routed sessions, and the wire face. */ -export const inject = ['slash', 'connection', 'sessions'] +/** Required services: reference source faces plus the tool-row and locale registries. */ +export const inject = ['slash', 'connection', 'sessions', 'slots', 'locale'] /** - * Client plugin body: register the '/' skill source over the root wire face. + * Client plugin body: register the '/' source, dictionaries, and keyed tool row. * @param ctx - client root context. */ export function apply(ctx: ClientContext): void { + ctx.effect(() => ctx.locale.register(NS, { zh, en }), 'ui-skill: dictionaries') + ctx.slots.inject('conversation.chat.toolview', () => ctx.slots.register( + { name: 'conversation.chat.toolview', key: 'skill', locale: NS }, + SkillRow, + )) + const skills = (ctx.get('connection') as ConnectionHandle).api.skills const sessions = ctx.get('sessions') as ISessions // Session-keyed catalog cache; single-flight per key. Plugin-closure state: diff --git a/packages/client/ui-skill/src/client/locales.ts b/packages/client/ui-skill/src/client/locales.ts new file mode 100644 index 0000000000..53746397bc --- /dev/null +++ b/packages/client/ui-skill/src/client/locales.ts @@ -0,0 +1,23 @@ +/** `skill` namespace dictionaries for the dedicated tool row. */ + +/** Dictionary namespace owned by this plugin. */ +export const NS = 'skill' + +/** Simplified Chinese dictionary (the key-set source of truth). */ +export const zh = { + 'row.running': '正在加载 skill', + 'row.failed': 'skill 加载失败', + 'row.stopped': 'skill 加载已中止', + 'row.instructions': '说明', +} satisfies Record + +/** The skill namespace key union. */ +export type SkillKey = keyof typeof zh + +/** English dictionary, checked complete against the zh key set. */ +export const en = { + 'row.running': 'Loading skill', + 'row.failed': 'Skill load failed', + 'row.stopped': 'Skill load stopped', + 'row.instructions': 'Instructions', +} satisfies Record diff --git a/packages/client/ui-skill/tests/browser-plugin.spec.ts b/packages/client/ui-skill/tests/browser-plugin.spec.ts index 72a7d6f7a6..3febb36efb 100644 --- a/packages/client/ui-skill/tests/browser-plugin.spec.ts +++ b/packages/client/ui-skill/tests/browser-plugin.spec.ts @@ -1,5 +1,6 @@ /** - * ui-skill browser half: source registration (duplicate-name proof) + + * ui-skill browser half: source and keyed toolview registration + + * locale dictionaries + source duplicate-name proof + * fiber-teardown removal (HMR safety) against the real SlashService, then * the source behavior contract driven directly on the captured source with * real ClientSessionContext projections — sessionId addressing, the @@ -16,6 +17,7 @@ import type { SessionId } from '@deepseek-ai/dsh-client-runtime/client' import { SlashService } from '@deepseek-ai/dsh-client-ui-slash/client' import type { ClientSessionContext, SlashSource } from '@deepseek-ai/dsh-client-ui-slash/client' import { apply, inject } from '../src/client/index.ts' +import { SkillRow as SkillToolRow } from '../src/client/SkillRow.tsx' type SkillRow = { name: string; description: string; whenToUse?: string } type ListResult = @@ -23,6 +25,38 @@ type ListResult = | { ok: false; error: { code: string; message: string; details: object } } type ListFn = (payload: object, signal?: AbortSignal) => Promise<{ result: ListResult }> +interface PresentationRegistration { + name: string + key?: string + locale?: string +} + +interface PresentationCapture { + registration?: PresentationRegistration + component?: unknown + dictionaries: Array<{ namespace: string; dictionaries: unknown }> +} + +/** Provide the presentation registries and capture the plugin's registrations. */ +function providePresentation(ctx: Context): PresentationCapture { + const capture: PresentationCapture = { dictionaries: [] } + ctx.provide('locale', { + register(namespace: string, dictionaries: unknown) { + capture.dictionaries.push({ namespace, dictionaries }) + return () => {} + }, + }) + ctx.provide('slots', { + inject(_name: string, factory: () => unknown) { factory() }, + register(registration: PresentationRegistration, component: unknown) { + capture.registration = registration + capture.component = component + return () => {} + }, + }) + return capture +} + /** Boot the plugin over fake slash/connection faces; returns the captured source and its ctx. */ async function bench(list: ListFn, addressed?: SessionId) { const ctx = new Context() @@ -34,6 +68,7 @@ async function bench(list: ListFn, addressed?: SessionId) { ? { parentSessionId: sid('parent'), childSessionId: id, mode: 'continuable' as const } : undefined, }) + providePresentation(ctx) await ctx.plugin({ inject: [...inject], apply }).await() return { ctx, source: captured! } } @@ -65,7 +100,36 @@ const req = (query: string, signal?: AbortSignal) => describe('apply', () => { it('declares the services it binds', () => { - expect(inject).toEqual(['slash', 'connection', 'sessions']) + expect(inject).toEqual(['slash', 'connection', 'sessions', 'slots', 'locale']) + }) + + it('registers the dedicated skill row and its locale dictionaries', async () => { + const ctx = new Context() + ctx.provide('slash', { registerSource: () => () => {} }) + ctx.provide('connection', { api: { skills: { list: listOk(CATALOG) } } }) + ctx.provide('sessions', { subagentAddress: () => undefined }) + const presentation = providePresentation(ctx) + await ctx.plugin({ inject: [...inject], apply }).await() + expect(presentation.registration).toEqual({ + name: 'conversation.chat.toolview', key: 'skill', locale: 'skill', + }) + expect(presentation.component).toBe(SkillToolRow) + expect(presentation.dictionaries).toEqual([{ + namespace: 'skill', dictionaries: { + zh: { + 'row.running': '正在加载 skill', + 'row.failed': 'skill 加载失败', + 'row.stopped': 'skill 加载已中止', + 'row.instructions': '说明', + }, + en: { + 'row.running': 'Loading skill', + 'row.failed': 'Skill load failed', + 'row.stopped': 'Skill load stopped', + 'row.instructions': 'Instructions', + }, + }, + }]) }) it('registers the "/" skill source; disposal frees the name (HMR safety)', async () => { @@ -74,6 +138,7 @@ describe('apply', () => { ctx.provide('sessions', {}) await ctx.plugin(SlashService).await() ctx.provide('connection', { api: { skills: { list: listOk(CATALOG) } } }) + providePresentation(ctx) const fiber = ctx.plugin({ inject: [...inject], apply }) await fiber.await() const slash = ctx.get('slash') as SlashService diff --git a/packages/client/ui-skill/tests/skill-row.spec.tsx b/packages/client/ui-skill/tests/skill-row.spec.tsx new file mode 100644 index 0000000000..2dacf0a036 --- /dev/null +++ b/packages/client/ui-skill/tests/skill-row.spec.tsx @@ -0,0 +1,152 @@ +// @vitest-environment jsdom +// Dedicated skill tool row: replay-stable naming, lifecycle states, disclosure, +// keyboard operation, exact output, and the trajectory Inspect handoff. + +import { cleanup, fireEvent, render, screen } from '@testing-library/react' +import { afterEach, describe, expect, it, vi } from 'vitest' +import type { RunningToolCall, ToolResultNode } from '@deepseek-ai/dsh-client-runtime/client' +import { makeTranslate } from '@deepseek-ai/dsh-client-test-runtime' +import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts' +import { SkillRow } from '../src/client/SkillRow.tsx' +import { zh } from '../src/client/locales.ts' + +type SkillRowProps = Parameters[0] + +const t: SkillRowProps['t'] = makeTranslate(zh, commonZh) + +afterEach(cleanup) + +function settled(over: Partial = {}): ToolResultNode { + return { + kind: 'tool-result', + seq: 3, + time: 3_000, + callId: 'call-skill', + call: { name: 'skill', argsRaw: '{"name":"dsh-manage-issues"}' }, + callTime: 2_000, + content: [{ type: 'text', text: 'Follow the issue workflow.\nKeep project fields in sync.' }], + isError: false, + callView: null, + resultView: null, + ...over, + } +} + +function running(argsRaw = '{"name":"dsh-manage-issues"}'): RunningToolCall { + return { + callId: 'call-skill', name: 'skill', argsRaw, turn: 1, step: 1, time: 2_000, callView: null, + } +} + +function props(block: SkillRowProps['block'], inspect?: () => void): SkillRowProps { + return { + callId: block.callId, + toolName: 'skill', + block, + openFile: vi.fn(), + inspect, + t, + } as unknown as SkillRowProps +} + +describe('SkillRow', () => { + it('renders a compact Bash-shaped summary and discloses the exact instructions', () => { + const inspect = vi.fn() + const view = render() + const row = screen.getByRole('button', { name: 'Skill dsh-manage-issues' }) + expect(row.getAttribute('aria-expanded')).toBe('false') + expect(view.container.querySelector('[data-tool="skill"]')?.getAttribute('data-state')).toBe('ok') + expect(view.container.querySelector('[data-tool="skill"] svg')?.getAttribute('width')).toBe('16') + expect(screen.queryByLabelText('说明')).toBeNull() + + fireEvent.click(row) + expect(row.getAttribute('aria-expanded')).toBe('true') + const card = screen.getByLabelText('说明') + expect(card.textContent).toBe('说明Follow the issue workflow.\nKeep project fields in sync.') + expect(view.container.textContent).not.toContain('{"name":"dsh-manage-issues"}') + fireEvent.click(screen.getByRole('button', { name: 'Inspect' })) + expect(inspect).toHaveBeenCalledTimes(1) + + fireEvent.click(row) + expect(row.getAttribute('aria-expanded')).toBe('false') + }) + + it('supports Enter and Space while ignoring unrelated keys', () => { + render() + const row = screen.getByRole('button') + fireEvent.keyDown(row, { key: 'Escape' }) + expect(row.getAttribute('aria-expanded')).toBe('false') + fireEvent.keyDown(row, { key: 'Enter' }) + expect(row.getAttribute('aria-expanded')).toBe('true') + fireEvent.keyDown(row, { key: ' ' }) + expect(row.getAttribute('aria-expanded')).toBe('false') + }) + + it('keeps a running call compact and announces its state', () => { + const view = render() + const row = view.container.querySelector('[data-tool="skill"] > div')! + expect(row.getAttribute('role')).toBeNull() + expect(view.container.textContent).toContain('正在加载 skill') + expect(view.container.textContent).toContain('dsh-manage-issues') + expect(view.container.querySelector('svg [fill="currentColor"]')).not.toBeNull() + }) + + it('uses the first failure line in the summary and exposes the full error', () => { + const view = render() + const row = screen.getByRole('button', { name: 'skill 加载失败 Skill SkillError: missing resource' }) + expect(view.container.querySelector('[data-tool="skill"]')?.getAttribute('data-state')).toBe('error') + expect(row.textContent).not.toContain('Check SKILL.md.') + fireEvent.click(row) + const output = view.container.querySelector('pre')! + expect(output.textContent).toBe('SkillError: missing resource\nCheck SKILL.md.') + expect(output.getAttribute('data-error')).toBe('true') + }) + + it('renders stopped, structured, and structured-error durable outcomes', () => { + const stoppedView = render() + expect(stoppedView.container.textContent).toContain('skill 加载已中止') + expect(stoppedView.container.querySelector('[data-state="warning"]')).not.toBeNull() + cleanup() + + const structuredView = render() + fireEvent.click(screen.getByRole('button')) + expect(structuredView.container.textContent).toContain('"type": "reasoning"') + cleanup() + + render() + const errorRow = screen.getByRole('button', { name: 'skill 加载失败 Skill SkillError: missing' }) + fireEvent.click(errorRow) + expect(screen.getAllByText('SkillError: missing')).toHaveLength(2) + }) + + it('falls back to durable args or call id when the skill name is unavailable', () => { + const invalid = render() + expect(invalid.container.textContent).toContain('{"name":') + cleanup() + + const scalar = render() + expect(scalar.container.textContent).toContain('"raw-name"') + cleanup() + + const emptyName = render() + expect(emptyName.container.textContent).toContain('{"name":""}') + cleanup() + + const blank = render() + expect(blank.container.textContent).toContain('call-skill') + expect(blank.container.querySelector('[role="button"]')).toBeNull() + expect(blank.container.textContent).not.toContain('正在加载 skill') + }) +}) diff --git a/packages/client/ui-skill/tsconfig.json b/packages/client/ui-skill/tsconfig.json index 318a44906a..f83486aa36 100644 --- a/packages/client/ui-skill/tsconfig.json +++ b/packages/client/ui-skill/tsconfig.json @@ -14,9 +14,18 @@ { "path": "../connection" }, + { + "path": "../locale" + }, { "path": "../runtime" }, + { + "path": "../ui-conversation" + }, + { + "path": "../ui-primitives" + }, { "path": "../ui-slash" }, diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 34c8d60cf9..09d0384667 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1942,9 +1942,21 @@ importers: '@deepseek-ai/dsh-client-connection': specifier: workspace:^ version: link:../connection + '@deepseek-ai/dsh-client-locale': + specifier: workspace:^ + version: link:../locale '@deepseek-ai/dsh-client-runtime': specifier: workspace:^ version: link:../runtime + '@deepseek-ai/dsh-client-test-runtime': + specifier: workspace:^ + version: link:../test-runtime + '@deepseek-ai/dsh-client-ui-conversation': + specifier: workspace:^ + version: link:../ui-conversation + '@deepseek-ai/dsh-client-ui-primitives': + specifier: workspace:^ + version: link:../ui-primitives '@deepseek-ai/dsh-client-ui-slash': specifier: workspace:^ version: link:../ui-slash @@ -1954,9 +1966,21 @@ importers: '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants + '@testing-library/react': + specifier: ^16.1.0 + version: 16.3.2(@testing-library/dom@10.4.1)(@types/react-dom@18.3.7(@types/react@18.3.31))(@types/react@18.3.31)(react-dom@18.3.1(react@18.3.1))(react@18.3.1) + '@types/react': + specifier: ~18.3.1 + version: 18.3.31 cordis: specifier: ^4.0.0-rc.7 version: link:../../../vendor/cordis + react: + specifier: ^18.2.0 + version: 18.3.1 + react-dom: + specifier: ^18.2.0 + version: 18.3.1(react@18.3.1) packages/client/ui-slash: dependencies: diff --git a/tsconfig.host.json b/tsconfig.host.json index 4fcf71b680..1a0f4698f7 100644 --- a/tsconfig.host.json +++ b/tsconfig.host.json @@ -49,6 +49,7 @@ "apps/web/tests/startup-auto-selection.e2e.ts", "apps/web/tests/subagent-conversation.e2e.ts", "apps/web/tests/bash-abort-row.e2e.ts", + "apps/web/tests/skill-tool-row.e2e.ts", "apps/web/tests/chat-scroll-fixture.ts", "apps/web/tests/chat-scroll-contract.e2e.ts", "apps/web/tests/chat-long-interactions.e2e.ts", From 1ed5dc81d249a7d391fc9c03da3898fad0706517 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 6 Aug 2026 14:22:54 +0800 Subject: [PATCH 07/22] docs: refresh module graph --- docs/module-graph.md | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 0e2e7e0c37..369441ff51 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -452,11 +452,6 @@ flowchart TD pkg_client_ui_layout --> pkg_client_ui_slots pkg_client_ui_layout --> pkg_client_ui_theme pkg_client_ui_layout --> pkg_invariants - pkg_client_ui_skill --> pkg_client_connection - pkg_client_ui_skill --> pkg_client_runtime - pkg_client_ui_skill --> pkg_client_ui_slash - pkg_client_ui_skill --> pkg_client_ui_slots - pkg_client_ui_skill --> pkg_invariants pkg_code_runtime_worker --> pkg_code_runtime pkg_code_runtime_worker --> pkg_invariants pkg_code_runtime_worker --> pkg_session @@ -834,6 +829,14 @@ flowchart TD pkg_client_ui_goal --> pkg_client_ui_slots pkg_client_ui_goal --> pkg_goal pkg_client_ui_goal --> pkg_invariants + pkg_client_ui_skill --> pkg_client_connection + pkg_client_ui_skill --> pkg_client_locale + pkg_client_ui_skill --> pkg_client_runtime + pkg_client_ui_skill --> pkg_client_ui_conversation + pkg_client_ui_skill --> pkg_client_ui_primitives + pkg_client_ui_skill --> pkg_client_ui_slash + pkg_client_ui_skill --> pkg_client_ui_slots + pkg_client_ui_skill --> pkg_invariants pkg_session_reference --> pkg_agent pkg_session_reference --> pkg_compact pkg_session_reference --> pkg_invariants @@ -1149,7 +1152,6 @@ flowchart TD | [`llm-replay`](../packages/support/llm-replay) | `support` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`app-boot`](../packages/ui/app-boot) | `ui` | [`invariants`](../packages/support/invariants), [`paths`](../packages/util/paths), [`system-prompt`](../packages/core/system-prompt) | | [`client-ui-layout`](../packages/client/ui-layout) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-slots`](../packages/client/ui-slots), [`client-ui-theme`](../packages/client/ui-theme), [`invariants`](../packages/support/invariants) | -| [`client-ui-skill`](../packages/client/ui-skill) | `client` | [`client-connection`](../packages/client/connection), [`client-runtime`](../packages/client/runtime), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) | | [`host-directory-picker-browse`](../packages/host/directory-picker-browse) | `host` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/support/invariants) | | [`host-directory-picker-native`](../packages/host/directory-picker-native) | `host` | [`client-runtime`](../packages/client/runtime), [`client-ui-slots`](../packages/client/ui-slots), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/support/invariants) | @@ -1224,6 +1226,7 @@ flowchart TD | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`client-ui-command`](../packages/client/ui-command) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`client-ui-goal`](../packages/client/ui-goal) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants) | +| [`client-ui-skill`](../packages/client/ui-skill) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`session-reference`](../packages/context/session-reference) | `context` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`session-query`](../packages/session-query/session-query) | | [`workspace-context`](../packages/context/workspace-context) | `context` | [`agent`](../packages/core/agent), [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tools`](../packages/core/tools) | From ee0e33e10f5be46a5854935459ae029c3c9496a1 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 6 Aug 2026 14:31:19 +0800 Subject: [PATCH 08/22] test(web): refresh markdown snapshots --- apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md | 2 +- .../tests/snapshots/markdown-inline-code-links/ui.expected.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md b/apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md index 68a4df5603..187ab25e8c 100644 --- a/apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md +++ b/apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md @@ -40,7 +40,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} - textbox "Message the agent" - button "Commands": - img diff --git a/apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md b/apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md index 059849223c..19efa06238 100644 --- a/apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md +++ b/apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md @@ -31,7 +31,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}}Ran for {{duration}} +- text: {{clock}} Ran for {{duration}} - textbox "Message the agent" - button "Commands": - img From e0e84d265a24b397663507bf8e9d97c1777a033d Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 6 Aug 2026 14:40:08 +0800 Subject: [PATCH 09/22] refactor(web): deduplicate skill disclosure leading --- .../client/ui-skill/src/client/SkillRow.tsx | 24 +++++++++++-------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/packages/client/ui-skill/src/client/SkillRow.tsx b/packages/client/ui-skill/src/client/SkillRow.tsx index c847678e4a..be1084ec39 100644 --- a/packages/client/ui-skill/src/client/SkillRow.tsx +++ b/packages/client/ui-skill/src/client/SkillRow.tsx @@ -85,6 +85,19 @@ function leadingFor(state: SkillRowState): ReactNode { } } +/** Leading disclosure slot: state icon at rest, chevron on hover or while open. */ +function disclosureLeading(state: SkillRowState, open: boolean, expandable: boolean): ReactNode { + if (open) return + const icon = leadingFor(state) + if (!expandable) return icon + return ( + <> + {icon} + + + ) +} + /** Visually hidden state copy for the colour-only lifecycle cues. */ function stateStatus(state: SkillRowState, t: SkillRowProps['t']): string | null { switch (state) { @@ -125,16 +138,7 @@ export function SkillRow({ block, inspect, t }: SkillRowProps) { event.preventDefault() toggleExpand() } - const leading = open - ? - : expandable - ? ( - <> - {leadingFor(model.state)} - - - ) - : leadingFor(model.state) + const leading = disclosureLeading(model.state, open, expandable) return (
Date: Thu, 6 Aug 2026 14:50:21 +0800 Subject: [PATCH 10/22] revert: leave markdown snapshots unchanged --- apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md | 2 +- .../tests/snapshots/markdown-inline-code-links/ui.expected.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md b/apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md index 187ab25e8c..68a4df5603 100644 --- a/apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md +++ b/apps/web/tests/snapshots/markdown-cjk-strong/ui.expected.md @@ -40,7 +40,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}} Ran for {{duration}} +- text: {{clock}}Ran for {{duration}} - textbox "Message the agent" - button "Commands": - img diff --git a/apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md b/apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md index 19efa06238..059849223c 100644 --- a/apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md +++ b/apps/web/tests/snapshots/markdown-inline-code-links/ui.expected.md @@ -31,7 +31,7 @@ - img - button "Branch into a new conversation": - img -- text: {{clock}} Ran for {{duration}} +- text: {{clock}}Ran for {{duration}} - textbox "Message the agent" - button "Commands": - img From 4e8067e8d52deec3d0320a9f5d4135034d74a976 Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 6 Aug 2026 14:57:30 +0800 Subject: [PATCH 11/22] refactor(telemetry): replay feedback sessions without buffering --- ...3-session-telemetry-otel-revival.i18n.yaml | 4 +- ...26-07-23-session-telemetry-otel-revival.md | 6 +- ...07-23-session-telemetry-otel-revival.zh.md | 6 +- ...feedback-gated-session-telemetry.i18n.yaml | 4 +- ...-08-05-feedback-gated-session-telemetry.md | 12 +- ...-05-feedback-gated-session-telemetry.zh.md | 12 +- ...6-buffer-free-feedback-telemetry.i18n.yaml | 6 + ...26-08-06-buffer-free-feedback-telemetry.md | 29 +++ ...08-06-buffer-free-feedback-telemetry.zh.md | 29 +++ docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 9 +- docs/event-producer-consumer.md | 2 +- .../cordis/tool-cordis/src/api-catalog.ts | 2 +- .../session-telemetry-otel/README.i18n.yaml | 4 +- .../session-telemetry-otel/README.md | 8 +- .../session-telemetry-otel/README.zh.md | 8 +- .../session-telemetry-otel/src/index.ts | 19 +- .../session-telemetry-otel/tests/otel.spec.ts | 2 +- .../session-telemetry/README.i18n.yaml | 4 +- .../telemetry/session-telemetry/README.md | 12 +- .../telemetry/session-telemetry/README.zh.md | 12 +- .../session-telemetry/src/coordinator.ts | 180 ++++++++---------- .../telemetry/session-telemetry/src/index.ts | 20 +- .../session-telemetry/tests/telemetry.spec.ts | 78 +++++--- 24 files changed, 270 insertions(+), 200 deletions(-) create mode 100644 .agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.i18n.yaml create mode 100644 .agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.md create mode 100644 .agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.zh.md diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml index 3f487762d6..ecb7ca1588 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md -2026-07-23-session-telemetry-otel-revival.md: dcbff9757cbb730b66f456535fbd7ae471b6ffd1 -2026-07-23-session-telemetry-otel-revival.zh.md: c3a098041795fa92bb4e0dd421ca09be94907cb8 +2026-07-23-session-telemetry-otel-revival.md: f83128e8bf62e0718e59912c16c4e449855aaa1a +2026-07-23-session-telemetry-otel-revival.zh.md: 6f955cc9e1b44ed4a558515c4904b46a9cec585f diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md index dcbff9757c..f83128e8bf 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md @@ -12,9 +12,9 @@ Every deployment that wants harness sessions in an observability stack must hand `packages/telemetry/` revives the two reviewed packages under the SDK stance — the harness provides the capability, the deployment configures where records go and owns what leaves in them: -- **`@deepseek-ai/dsh-session-telemetry`** — the seam. `TelemetryBackend` (`emit`/`flush?`/`shutdown`), the service-registered `Telemetry` form, and `TelemetryCoordinator` owning capture: adoption with cursor read-back, the per-append firehose (project → `structuredClone` → redact → `emit`, zero I/O), the fixed first-chunk-per-(turn, step) projection, the `agent/error` relay, and dispose-time `shutdown` records. +- **`@deepseek-ai/dsh-session-telemetry`** — the seam. `TelemetryBackend` (`emit`/`flush?`/`shutdown`), the service-registered `Telemetry` form, and `TelemetryCoordinator` owning capture: live adoption with cursor read-back and the per-append firehose (project → `structuredClone` → redact → `emit`, zero I/O), buffer-free on-demand replay from the canonical log, the fixed first-chunk-per-(turn, step) projection, the live `agent/error` relay, and live dispose-time `shutdown` records. - **The `telemetry/record` waterfall** — the delta over the branch version and the seam's redaction extension point. Every record passes it before reaching any backend; the seam ships NO rules of its own — the innermost `next()` is a pass-through, deployments mount their rules as listeners (stacking by transforming `next()`'s return value), and a throwing rule withholds the record fail-closed. Redaction applies to the exported copy only; the canonical log is never rewritten. -- **`@deepseek-ai/dsh-session-telemetry-otel`** — the reference backend: OTel JS SDK log pipeline (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter), configured verbatim through `exporter`/`processor` passthroughs. Its default `FULL` mode requires `exporter.url`; the later [feedback-gated telemetry decision](2026-08-05-feedback-gated-session-telemetry.md) adds `FEEDBACK_ONLY` and `DISABLED` delivery modes without moving the redaction or backend boundary. +- **`@deepseek-ai/dsh-session-telemetry-otel`** — the reference backend: OTel JS SDK log pipeline (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter), configured verbatim through `exporter`/`processor` passthroughs. Its default `FULL` mode requires `exporter.url`; the later [feedback-gated telemetry decision](2026-08-05-feedback-gated-session-telemetry.md) adds `FEEDBACK_ONLY` and `DISABLED` delivery modes without moving the redaction or backend boundary, while [buffer-free feedback replay](../simplification/2026-08-06-buffer-free-feedback-telemetry.md) avoids a second in-memory copy of the session prefix. The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry, queueing, and loss policy are the reporting SDK's, configured through passthroughs — delivery is best-effort (at-most-once across a crash), which the READMEs state plainly. @@ -34,4 +34,4 @@ The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry ## Consequences -A deployment adds one `cordis.yml` entry with an OTLP endpoint and gets its session stream in any OTel-compatible stack. `FULL` preserves that behavior by default, `FEEDBACK_ONLY` withholds records until feedback releases a prefix, and `DISABLED` constructs no reporting pipeline; removing the entry remains a silent opt-out, while the disabled mode keeps the local feedback warning. A rule-free deployment exports records exactly as captured — including any credentials embedded in file contents or command output — so a deployment crossing a trust boundary must mount `telemetry/record` listeners, and both READMEs state this plainly. Where rules are mounted, exported bodies can differ from canonical log bytes, so receivers must not treat telemetry as a byte-exact replica; the log remains the source of truth. Crash durability is explicitly out of scope until the outbox decision above is revisited. +A deployment adds one `cordis.yml` entry with an OTLP endpoint and gets its session stream in any OTel-compatible stack. `FULL` preserves that behavior by default, `FEEDBACK_ONLY` replays a canonical-log prefix when feedback is recorded, and `DISABLED` constructs no reporting pipeline; removing the entry remains a silent opt-out, while the disabled mode keeps the local feedback warning. A rule-free deployment exports records exactly as captured — including any credentials embedded in file contents or command output — so a deployment crossing a trust boundary must mount `telemetry/record` listeners, and both READMEs state this plainly. Where rules are mounted, exported bodies can differ from canonical log bytes, so receivers must not treat telemetry as a byte-exact replica; the log remains the source of truth. Crash durability is explicitly out of scope until the outbox decision above is revisited. diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md index c3a0980417..6f955cc9e1 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md @@ -12,9 +12,9 @@ Status: implemented `packages/telemetry/` 以 SDK 立场复活这两个经过评审的包——harness 提供能力，部署方配置上报去向并对导出内容负责： -- **`@deepseek-ai/dsh-session-telemetry`** —— seam 本体。`TelemetryBackend`（`emit`/`flush?`/`shutdown`）、服务注册形态的 `Telemetry`、以及拥有捕获侧的 `TelemetryCoordinator`：带游标回读的收养、逐 append 的 firehose（投影 → `structuredClone` → 脱敏 → `emit`，零 I/O）、固定的每 (turn, step) 首 chunk 投影、`agent/error` 转发、以及 dispose 时的 `shutdown` 记录。 +- **`@deepseek-ai/dsh-session-telemetry`** —— seam 本体。`TelemetryBackend`（`emit`/`flush?`/`shutdown`）、服务注册形态的 `Telemetry`、以及拥有捕获侧的 `TelemetryCoordinator`：带游标回读的实时收养与逐 append 的 firehose（投影 → `structuredClone` → 脱敏 → `emit`，零 I/O）、从权威日志进行的无缓冲按需回放、固定的每 (turn, step) 首 chunk 投影、实时 `agent/error` 转发，以及实时 dispose 时的 `shutdown` 记录。 - **`telemetry/record` waterfall** —— 相对分支版本的增量，也是该 seam 的脱敏扩展点。每条记录抵达任何 backend 前必经此处；seam 自身不带任何规则——最内层 `next()` 原样透传，部署方以监听器挂载自己的规则（通过变换 `next()` 的返回值堆叠），抛异常的规则将该记录 fail-closed 扣下。脱敏只作用于导出副本；canonical log 永不改写。 -- **`@deepseek-ai/dsh-session-telemetry-otel`** —— 参考 backend：OTel JS SDK 日志管线（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter），经 `exporter`/`processor` passthrough 原样配置。其默认 `FULL` 模式要求 `exporter.url`；后续的[反馈门控遥测决策](2026-08-05-feedback-gated-session-telemetry.md)增加了 `FEEDBACK_ONLY` 与 `DISABLED` 投递模式，但未移动脱敏或后端边界。 +- **`@deepseek-ai/dsh-session-telemetry-otel`** —— 参考 backend：OTel JS SDK 日志管线（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter），经 `exporter`/`processor` passthrough 原样配置。其默认 `FULL` 模式要求 `exporter.url`；后续的[反馈门控遥测决策](2026-08-05-feedback-gated-session-telemetry.md)增加了 `FEEDBACK_ONLY` 与 `DISABLED` 投递模式，但未移动脱敏或后端边界，而[无缓冲反馈回放](../simplification/2026-08-06-buffer-free-feedback-telemetry.md)避免在内存中创建会话前缀的第二份副本。 边界公理保持不变：harness 的职责止于 `emit()`。批处理、重试、排队与丢失策略属于 reporting SDK，经 passthrough 配置——投递是尽力而为（崩溃时至多一次），README 对此如实陈述。 @@ -34,4 +34,4 @@ Status: implemented ## Consequences -部署方在 `cordis.yml` 加一个带 OTLP endpoint 的条目即可把会话流接入任何 OTel 兼容体系。`FULL` 默认保留该行为，`FEEDBACK_ONLY` 在反馈释放前暂存记录前缀，`DISABLED` 则不构造上报流水线；删除条目仍是静默退出方式，而禁用模式会保留本地反馈警告。未挂载规则的部署导出的记录与捕获时完全一致，包括文件内容与命令输出中内嵌的任何凭据。因此，跨信任边界的部署必须挂载 `telemetry/record` 监听器，两个 README 对此如实陈述。挂载规则后，导出的 body 可能与 canonical log 字节不同，接收端不得把遥测当作字节精确副本；日志仍是真源。崩溃持久性在上述 outbox 决定重启前明确不在范围内。 +部署方在 `cordis.yml` 加一个带 OTLP endpoint 的条目即可把会话流接入任何 OTel 兼容体系。`FULL` 默认保留该行为，`FEEDBACK_ONLY` 在记录反馈时回放权威日志前缀，`DISABLED` 则不构造上报流水线；删除条目仍是静默退出方式，而禁用模式会保留本地反馈警告。未挂载规则的部署导出的记录与捕获时完全一致，包括文件内容与命令输出中内嵌的任何凭据。因此，跨信任边界的部署必须挂载 `telemetry/record` 监听器，两个 README 对此如实陈述。挂载规则后，导出的 body 可能与 canonical log 字节不同，接收端不得把遥测当作字节精确副本；日志仍是真源。崩溃持久性在上述 outbox 决定重启前明确不在范围内。 diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml index d12ad78728..7909316acd 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md -2026-08-05-feedback-gated-session-telemetry.md: 21a9028c603f3faaec39b2ddb8ef14644d6c84d4 -2026-08-05-feedback-gated-session-telemetry.zh.md: ea94c743b962a93a5fc64bdc2e4ed103aadecc99 +2026-08-05-feedback-gated-session-telemetry.md: 25cc17f75629f72d7351eb0537d72b700c84411f +2026-08-05-feedback-gated-session-telemetry.zh.md: b0e84e60e27fa20f66113c11db62026583a27a19 diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md index 21a9028c60..25cc17f756 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md @@ -13,23 +13,21 @@ Session telemetry originally has one mounted behavior: every accepted record ent `@deepseek-ai/dsh-session-telemetry-otel` exposes three uppercase `mode` values: - `FULL` is the default and preserves immediate delivery to the configured OTel pipeline. -- `FEEDBACK_ONLY` captures redacted copies in memory and releases the pending session prefix when `feedback/record` is appended. The released prefix includes the feedback event itself. Records appended after that event form another withheld prefix until another feedback event releases them. +- `FEEDBACK_ONLY` reads the canonical session log when `feedback/record` is appended and hands over the unreleased prefix through that exact event. Records appended after that boundary remain local until another feedback event. - `DISABLED` constructs no exporter, processor, or logger provider. A `feedback/record` listener prints that nothing is shared and the feedback remains local. -The generic telemetry coordinator owns the delivery distinction as `immediate` or `held`. Both paths project, clone, and run `telemetry/record` listeners at capture time. Immediate delivery sends the accepted record to the backend and advances the session's handoff cursor. Held delivery retains the accepted record per session without moving that cursor. `release(session)` submits the retained records in order, contains each backend failure independently, advances the cursor only for submitted records, and removes the released prefix. +The generic telemetry coordinator owns `live` and `on-demand` capture. Live capture projects, clones, redacts, and hands each event to the backend on the session firehose. On-demand capture registers no continuous capture listeners; `captureSession(session, throughSeq)` reads the canonical log from the handoff cursor through an inclusive boundary, then projects, clones, redacts, and hands over that prefix. The cursor advances only for handed-over records. The [buffer-free replay decision](../simplification/2026-08-06-buffer-free-feedback-telemetry.md) owns why the on-demand path uses the canonical log instead of copied records. -The OTel feedback listener is registered after the coordinator's session listener. Cordis therefore gives the coordinator the feedback append first, then the OTel listener releases a prefix that already contains that event. `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`; `DISABLED` does not validate or use exporter configuration. +The OTel feedback listener passes the feedback event's sequence to `captureSession()`. `Session.append` commits the event before publishing `session/event`, so replay includes that feedback but cannot extend past its boundary. `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`; `DISABLED` does not validate or use exporter configuration. ## Alternatives considered **Open a session permanently after its first feedback.** Rejected because later work would be shared without another feedback act and the plugin would need additional open-session state. Releasing one pending prefix per feedback has the smaller state machine and the narrower sharing boundary. -**Buffer after `TelemetryCoordinator.emit()` in the OTel backend.** Rejected because the coordinator would advance its handoff cursor before a record became eligible for upload. A plugin rebuild would then lose the only retained copy and incorrectly treat the prefix as handed off. - -**Replay the canonical session log when feedback arrives.** Rejected because replay would repeat projection and redaction, exclude telemetry operation records that are not session events, and require more lifecycle state to distinguish previously released prefixes. +**Retain capture-time redacted records until feedback.** Rejected because it duplicates an unbounded session prefix even though the canonical log already owns the events. It preserves capture-time redaction policy and operational records, but those properties do not justify the memory cost for a mode defined as uploading the session log after feedback. **Use an unmounted plugin as the disabled state.** That remains the silent opt-out, but it cannot warn when feedback is recorded. The explicit disabled mode lets a deployment keep one configuration shape and communicate that the local feedback did not leave the process. ## Consequences -`FULL` remains source- and wire-compatible with the original default. `FEEDBACK_ONLY` retains deep-copied, already-redacted records in process memory until feedback or session collection; a crash before release uploads nothing from that prefix. A clean shutdown after the last feedback is part of the new withheld suffix, so feedback-only streams do not carry a reliable shutdown or crash signal. Each later feedback releases the suffix accumulated since the previous one. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log. +`FULL` remains source- and wire-compatible with the original default. `FEEDBACK_ONLY` adds no telemetry-owned per-event buffer before feedback; a crash before feedback uploads nothing from that prefix. Replay applies the redaction policy mounted when feedback is recorded and excludes operational records that do not exist in the canonical log. Feedback-only streams therefore carry neither `agent-error` nor `shutdown` records, and shutdown absence is not a crash signal. Each later feedback captures the suffix accumulated since the previous boundary. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log. diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md index ea94c743b9..b0e84e60e2 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md @@ -13,23 +13,21 @@ Status: implemented `@deepseek-ai/dsh-session-telemetry-otel` 公开三个大写的 `mode` 值： - `FULL` 是默认值，保留向已配置 OTel 流水线的即时投递。 -- `FEEDBACK_ONLY` 在内存中捕获已脱敏副本，并在追加 `feedback/record` 时释放待处理的会话前缀。已释放前缀包含反馈事件本身。在该事件之后追加的记录会形成另一个暂存前缀，直到下一个反馈事件将其释放。 +- `FEEDBACK_ONLY` 在追加 `feedback/record` 时读取权威会话日志，并交接截至该事件的未释放前缀。该边界后追加的记录会留在本地，直到另一个反馈事件。 - `DISABLED` 不构造导出器、处理器或日志提供方。`feedback/record` 监听器会输出警告，说明什么都不会共享，且反馈仍留在本地。 -通用遥测协调器以 `immediate` 或 `held` 的形式拥有这两种投递方式。两条路径都会在捕获时进行投影、深拷贝，并运行 `telemetry/record` 监听器。即时投递把已接受记录发送到后端，并推进会话的 handoff 游标。暂存投递按会话保留已接受记录，且不移动该游标。`release(session)` 按顺序提交保留的记录，独立隔离每个后端失败，仅为已提交的记录推进游标，并移除已释放前缀。 +通用遥测协调器拥有 `live` 与 `on-demand` 捕获。实时捕获在会话 firehose 上投影、深拷贝、脱敏每个事件，并将其交给后端。按需捕获不注册持续捕获监听器；`captureSession(session, throughSeq)` 从 handoff 游标起读取权威日志，直至含边界的指定序列号，然后投影、深拷贝、脱敏并交接该前缀。游标只为已交接记录推进。[无缓冲回放决策](../simplification/2026-08-06-buffer-free-feedback-telemetry.md)说明了按需路径为何使用权威日志而非记录副本。 -OTel 反馈监听器在协调器的会话监听器之后注册。因此，Cordis 先将反馈追加交给协调器，再由 OTel 监听器释放已包含该事件的前缀。`exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填；`DISABLED` 不校验也不使用导出器配置。 +OTel 反馈监听器把反馈事件的序列号传给 `captureSession()`。`Session.append` 在发布 `session/event` 前已提交该事件，因此回放会包含该反馈，但不会超过其边界。`exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填；`DISABLED` 不校验也不使用导出器配置。 ## 考虑过的替代方案 **会话在首次反馈后永久开放。** 已否决，因为后续工作会在用户未再次提交反馈的情况下被共享，而且插件需要额外的会话开放状态。每次反馈只释放一个待处理前缀，状态机更小，共享边界也更窄。 -**在 OTel 后端的 `TelemetryCoordinator.emit()` 之后缓冲。** 已否决，因为协调器会在记录具备上传资格前推进 handoff 游标。插件重建后，唯一保留的副本会丢失，而协调器会错误地将该前缀视为已交接。 - -**反馈到达时回放权威会话日志。** 已否决，因为回放会重复执行投影与脱敏，排除不属于会话事件的遥测运维记录，且需要更多生命周期状态才能区分已释放前缀。 +**反馈前保留捕获时已脱敏记录。** 已否决，因为权威日志已拥有这些事件，该方案仍会复制无上限的会话前缀。它能保留捕获时的脱敏策略与运维记录，但对于一个定义为「反馈后上传会话日志」的模式，这些性质不足以证明该内存成本合理。 **以不挂载插件表示禁用状态。** 这仍然是静默退出方式，但无法在记录反馈时输出警告。显式禁用模式让部署方可以保持同一种配置形态，并说明本地反馈未离开进程。 ## 后果 -`FULL` 与原有默认值保持源码及协议兼容。`FEEDBACK_ONLY` 会在进程内存中保留已深拷贝且已脱敏的记录，直到收到反馈或会话被回收；释放前发生崩溃时，该前缀不上传任何内容。上次反馈之后的干净关闭属于新的暂存后缀，因此仅反馈的流不携带可靠的关闭或崩溃信号。每个后续反馈都会释放从上一个反馈开始累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。 +`FULL` 与原有默认值保持源码及协议兼容。`FEEDBACK_ONLY` 在反馈前不增加遥测自有的逐事件缓冲；反馈前发生崩溃时，该前缀不上传任何内容。回放使用记录反馈时挂载的脱敏策略，并排除权威日志中不存在的运维记录。因此，仅反馈的流既不携带 `agent-error` 记录，也不携带 `shutdown` 记录，而缺少 shutdown 不是崩溃信号。每个后续反馈都会捕获从上一个边界起累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。 diff --git a/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.i18n.yaml new file mode 100644 index 0000000000..9f6288ac04 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.md +2026-08-06-buffer-free-feedback-telemetry.md: 008bebdcb59f7ef4fe49f8e731aad77861368d5c +2026-08-06-buffer-free-feedback-telemetry.zh.md: 7052e075921f4470864f5ea1c4aed5cf6201becf diff --git a/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.md b/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.md new file mode 100644 index 0000000000..008bebdcb5 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.md @@ -0,0 +1,29 @@ +# Agent Note: Buffer-free feedback telemetry + +Status: implemented + +English | [中文](2026-08-06-buffer-free-feedback-telemetry.zh.md) + +## Problem + +Feedback-only telemetry must upload the session-log prefix only after recorded feedback. Retaining a deep-copied, redacted record for every projected event until that trigger duplicates the canonical session log and grows without a bound for a long-lived session that never records feedback. + +## Decision + +The telemetry coordinator provides `live` and `on-demand` capture. On-demand capture registers no session, flush, or operational-event listeners and retains no projected records. `captureSession(session, throughSeq?)` reads the canonical session log after the handoff cursor through an optional inclusive sequence boundary, applies the fixed projection, deep-copies each accepted event, runs the current `telemetry/record` waterfall, and hands the result to the backend. + +`FEEDBACK_ONLY` invokes that method with the `feedback/record` event's sequence. The append is already committed when `session/event` listeners run, so the replay contains the feedback event and cannot include a later suffix. The existing handoff cursor distinguishes later replays without another pending-record index. + +Because on-demand capture reads only the canonical log, it emits no `agent-error` or `shutdown` operational records. Redaction is evaluated at feedback time rather than append time. The [feedback mode decision](../feature/2026-08-05-feedback-gated-session-telemetry.md) owns the public sharing behavior; this note owns its buffer-free realization. + +## Alternatives considered + +**Retain capture-time redacted records.** This preserves the exact redaction policy and operational records observed when each event occurs, but duplicates the unbounded session prefix. The mode promises feedback-triggered session-log upload, not capture-time policy snapshots or pre-feedback operational telemetry. + +**Retain session event references or sequence numbers.** Rejected because the canonical log already supplies both order and identity. A second index saves payload copies but adds lifecycle state without enabling any required behavior. + +**Write a durable pre-feedback spool.** Deferred until a deployment requires crash recovery before feedback. It adds storage, cleanup, and confidentiality policy to a mode whose intended behavior is to upload nothing when the process exits before feedback. + +## Consequences + +A no-feedback session consumes no telemetry-owned memory proportional to its event count; the canonical session log remains the only pre-feedback copy. Feedback handling performs projection, cloning, and redaction synchronously before the backend's non-blocking enqueue, so its cost scales with the unreleased prefix. A redaction-policy change before feedback affects that replay, and a crash before feedback uploads nothing. Later feedback processes only events beyond the handoff cursor. diff --git a/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.zh.md b/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.zh.md new file mode 100644 index 0000000000..7052e07592 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 无缓冲反馈遥测 + +Status: implemented + +[English](2026-08-06-buffer-free-feedback-telemetry.md) | 中文 + +## 问题 + +仅反馈遥测必须只在记录反馈后上传会话日志前缀。若在触发前为每个已投影事件保留一份已深拷贝、已脱敏的记录，就会复制权威会话日志；对于长期运行但从不记录反馈的会话，这份副本会无限增长。 + +## 决策 + +遥测协调器提供 `live` 与 `on-demand` 捕获。按需捕获不注册会话、flush 或运维事件监听器，也不保留投影记录。`captureSession(session, throughSeq?)` 从 handoff 游标之后读取权威会话日志，直至可选的序列号边界（含边界），应用固定投影、深拷贝每个已接受事件、运行当前的 `telemetry/record` waterfall（瀑布式事件），并将结果交给后端。 + +`FEEDBACK_ONLY` 以 `feedback/record` 事件的序列号调用该方法。`session/event` 监听器运行时，追加已经提交，因此回放包含该反馈事件，且无法包含后续后缀。现有 handoff 游标可区分后续回放，无需另一个待处理记录索引。 + +按需捕获只读取权威日志，因此不会发出 `agent-error` 或 `shutdown` 运维记录。脱敏在反馈时而非追加时求值。[反馈模式决策](../feature/2026-08-05-feedback-gated-session-telemetry.md)规定公开的共享行为；本记录规定其无缓冲实现。 + +## 考虑过的替代方案 + +**保留捕获时的已脱敏记录。** 该方案会保留每个事件发生时观察到的确切脱敏策略与运维记录，但也会复制无上限的会话前缀。该模式承诺在反馈触发后上传会话日志，而非保留捕获时策略快照或反馈前运维遥测。 + +**保留会话事件引用或序列号。** 已否决，因为权威日志已同时提供顺序与身份。第二个索引可以省去载荷副本，但会增加生命周期状态，且无法实现任何必需行为。 + +**写入持久化的反馈前 spool。** 推迟到有部署要求反馈前的崩溃恢复时再实现。该方案会为一个预期在进程于反馈前退出时不上传任何内容的模式增加存储、清理与保密策略。 + +## 后果 + +没有反馈的会话不会消耗随事件数量增长的遥测自有内存；权威会话日志仍是反馈前的唯一副本。反馈处理会在后端非阻塞入队前同步执行投影、深拷贝与脱敏，因此其开销随未释放前缀增长。反馈前的脱敏策略变更会影响该次回放，而反馈前发生崩溃时什么都不上传。后续反馈只处理 handoff 游标之后的事件。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 0c4fb632c1..a4ddedab35 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1189,7 +1189,7 @@ export type TelemetryMode = typeof TELEMETRY_MODES[number] Depends on: `BatchLogRecordProcessorOptions` (`@opentelemetry/sdk-logs`) · `OTLPExporterNodeConfigBase` (`@opentelemetry/otlp-exporter-base`) -Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:54`](../packages/telemetry/session-telemetry-otel/src/index.ts) +Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:55`](../packages/telemetry/session-telemetry-otel/src/index.ts) ## `@deepseek-ai/dsh-session-title` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index d159fa0a53..a416a17d46 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -830,7 +830,7 @@ Source: [`packages/core/system-prompt/src/index.ts:35`](../../packages/core/syst ### `telemetry/record` — waterfall -Transform one outbound record before it reaches the backend. This waterfall is the seam's redaction extension point. It ships NO rules of its own: the innermost `next()` passes the record through unchanged, and with no listener mounted records reach the backend as captured, so exported data is exactly as clean as the rules a deployment mounts. Listeners stack by transforming `next()`'s return value; returning without `next()` replaces everything beneath. Dispatched synchronously on the capture hot path inside the coordinator's containment: a throwing listener withholds that one record (fail-closed) and never reaches the agent loop. Redaction applies to the exported copy only; the canonical session log is never rewritten. +Transform one outbound record before it reaches the backend. This waterfall is the seam's redaction extension point. It ships NO rules of its own: the innermost `next()` passes the record through unchanged, and with no listener mounted records reach the backend as captured, so exported data is exactly as clean as the rules a deployment mounts. Listeners stack by transforming `next()`'s return value; returning without `next()` replaces everything beneath. Dispatched synchronously on the capture hot path inside the coordinator's containment: a throwing listener withholds that one record (fail-closed) and never reaches the agent loop. Live capture dispatches at append time; on-demand capture dispatches while reading the canonical log. Redaction applies to the exported copy only; the canonical session log is never rewritten. ```ts cordis-catalog /** @@ -844,8 +844,9 @@ Transform one outbound record before it reaches the backend. This waterfall is t * `next()` replaces everything beneath. Dispatched synchronously on the * capture hot path inside the coordinator's containment: a throwing * listener withholds that one record (fail-closed) and never reaches the - * agent loop. Redaction applies to the exported copy only; the canonical - * session log is never rewritten. + * agent loop. Live capture dispatches at append time; on-demand capture + * dispatches while reading the canonical log. Redaction applies to the + * exported copy only; the canonical session log is never rewritten. * @param record - the candidate record, already the coordinator's own deep * copy; listeners return a (possibly new) record and must not mutate it. * @mode waterfall @@ -853,7 +854,7 @@ Transform one outbound record before it reaches the backend. This waterfall is t 'telemetry/record'(record: TelemetryRecord, next: () => TelemetryRecord): TelemetryRecord ``` -Source: [`packages/telemetry/session-telemetry/src/index.ts:42`](../../packages/telemetry/session-telemetry/src/index.ts) +Source: [`packages/telemetry/session-telemetry/src/index.ts:43`](../../packages/telemetry/session-telemetry/src/index.ts) ## `tools/*` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 4ccc19f305..82000e7f9a 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -45,7 +45,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:131`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`subagent`](../packages/subagent/subagent) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:29`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:35`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | -| `telemetry/record` | `waterfall` | [`packages/telemetry/session-telemetry/src/index.ts:42`](../packages/telemetry/session-telemetry/src/index.ts) | [`session-telemetry`](../packages/telemetry/session-telemetry) (`waterfall`) | - | +| `telemetry/record` | `waterfall` | [`packages/telemetry/session-telemetry/src/index.ts:43`](../packages/telemetry/session-telemetry/src/index.ts) | [`session-telemetry`](../packages/telemetry/session-telemetry) (`waterfall`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:156`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | | `tools/code-dispatch-log` | `waterfall` | [`packages/core/tools/src/index.ts:138`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`spill-policy`](../packages/spill/spill-policy) | | `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:113`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`timeout-policy`](../packages/timeout/timeout-policy) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index d4061261db..2298c9b4c6 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -1340,7 +1340,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ name: 'telemetry/record', mode: 'waterfall', signature: '\'telemetry/record\'(record: TelemetryRecord, next: () => TelemetryRecord): TelemetryRecord', - jsDoc: '/**\n * Transform one outbound record before it reaches the backend. This\n * waterfall is the seam\'s redaction extension point. It ships NO rules\n * of its own: the\n * innermost `next()` passes the record through unchanged, and with no\n * listener mounted records reach the backend as captured, so exported\n * data is exactly as clean as the rules a deployment mounts. Listeners\n * stack by transforming `next()`\'s return value; returning without\n * `next()` replaces everything beneath. Dispatched synchronously on the\n * capture hot path inside the coordinator\'s containment: a throwing\n * listener withholds that one record (fail-closed) and never reaches the\n * agent loop. Redaction applies to the exported copy only; the canonical\n * session log is never rewritten.\n * @param record - the candidate record, already the coordinator\'s own deep\n * copy; listeners return a (possibly new) record and must not mutate it.\n * @mode waterfall\n */', + jsDoc: '/**\n * Transform one outbound record before it reaches the backend. This\n * waterfall is the seam\'s redaction extension point. It ships NO rules\n * of its own: the\n * innermost `next()` passes the record through unchanged, and with no\n * listener mounted records reach the backend as captured, so exported\n * data is exactly as clean as the rules a deployment mounts. Listeners\n * stack by transforming `next()`\'s return value; returning without\n * `next()` replaces everything beneath. Dispatched synchronously on the\n * capture hot path inside the coordinator\'s containment: a throwing\n * listener withholds that one record (fail-closed) and never reaches the\n * agent loop. Live capture dispatches at append time; on-demand capture\n * dispatches while reading the canonical log. Redaction applies to the\n * exported copy only; the canonical session log is never rewritten.\n * @param record - the candidate record, already the coordinator\'s own deep\n * copy; listeners return a (possibly new) record and must not mutate it.\n * @mode waterfall\n */', summary: 'Transform one outbound record before it reaches the backend.', }, { diff --git a/packages/telemetry/session-telemetry-otel/README.i18n.yaml b/packages/telemetry/session-telemetry-otel/README.i18n.yaml index 6557557b8c..84e2447fd8 100644 --- a/packages/telemetry/session-telemetry-otel/README.i18n.yaml +++ b/packages/telemetry/session-telemetry-otel/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/telemetry/session-telemetry-otel/README.md -README.md: fab2461477b2174bded42ed6f05ae55c7c5f697c -README.zh.md: ab0191188836e03434adbce527d31b62ead848a3 +README.md: 7fc5572614a5bdba312ba97b52606032ef8f5394 +README.zh.md: 3160b67c8225fb87d5e7be2e43453ef40496fba9 diff --git a/packages/telemetry/session-telemetry-otel/README.md b/packages/telemetry/session-telemetry-otel/README.md index fab2461477..7fc5572614 100644 --- a/packages/telemetry/session-telemetry-otel/README.md +++ b/packages/telemetry/session-telemetry-otel/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — the only entry a deployment loads. Its `mode` decides whether the seam hands records over immediately, releases them only at recorded feedback, or keeps telemetry local. Uploading modes compose the OTel JS SDK as-is (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP log exporter) and map each handed-over record onto `logger.emit()`, under two instrumentation scopes: ledger records on `@deepseek-ai/dsh-session-telemetry-otel`, operational records on `@deepseek-ai/dsh-session-telemetry-otel/ops`. Resource identity (`service.name`/`service.version`) comes from `dsh-llm`'s `APP_IDENTITY`, the same source the attribution headers use. +The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — the only entry a deployment loads. Its `mode` decides whether the seam follows session events live, replays the canonical log only at recorded feedback, or keeps telemetry local. Uploading modes compose the OTel JS SDK as-is (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP log exporter) and map each handed-over record onto `logger.emit()`, under two instrumentation scopes: ledger records on `@deepseek-ai/dsh-session-telemetry-otel`, operational records on `@deepseek-ai/dsh-session-telemetry-otel/ops`. Resource identity (`service.name`/`service.version`) comes from `dsh-llm`'s `APP_IDENTITY`, the same source the attribution headers use. ## Config @@ -21,14 +21,14 @@ The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — th | `mode` | Behavior | |---|---| | `FULL` | Default. Each projected record, including lifecycle ops records, is handed to the OTel SDK immediately. | -| `FEEDBACK_ONLY` | Each `feedback/record` releases the redacted, projected session prefix through that event. Later records wait for another feedback event and remain local if none arrives. | +| `FEEDBACK_ONLY` | Each `feedback/record` replays, projects, and redacts the canonical session-log suffix through that event. Later records wait for another feedback event and remain local if none arrives. | | `DISABLED` | No coordinator, provider, processor, or exporter is constructed. No telemetry record leaves the process. A `feedback/record` logs `session telemetry is DISABLED; nothing will be shared and this feedback remains local`; the event remains in the local session log. | `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`, has no default, and must parse as `http(s)`; it is optional and unused in `DISABLED`. Uploading modes also reject a non-positive-integer `processor.maxExportBatchSize`, which the SDK accepts but then hangs on at shutdown. Everything else is the SDK's option shape, owned and documented by the SDK, and both blocks pass through whole: every `OTLPExporterNodeConfigBase` field (`headers`, `timeoutMillis`, `compression`, `keepAlive`, …) reaches the exporter, and batching, export cadence (`scheduledDelayMillis`), retry, queue bounds, and loss policy under sustained failure are the SDK's documented behavior, tuned through the `processor` passthrough. The backend deliberately implements no `flush()`: the batch processor is the only flusher in the process, which is what makes `shutdown()`'s drain complete. ## What leaves the machine -In uploading modes, records carry the complete `event.data` as the seam's `telemetry/record` waterfall returns it — user and assistant message content, tool arguments and results (command output, file contents), the full system prompt and tool schemas (`request/header`), todo text, compaction summaries, hook `stderrSummary`, feedback text, and the session `cwd` (a local path). The seam ships no redaction rules: with no `telemetry/record` listener mounted, that is the raw captured copy, so a deployment exporting beyond a trusted boundary mounts its own rules (see [the seam README](../session-telemetry/README.md#the-redact-waterfall)). Provider credentials never appear regardless: adapter API keys are constructor parameters, not session events, so they are structurally absent from the log and therefore from telemetry. `DISABLED` does not construct the SDK pipeline or hand any capture to a backend. +In uploading modes, records carry the complete `event.data` as the seam's `telemetry/record` waterfall returns it — user and assistant message content, tool arguments and results (command output, file contents), the full system prompt and tool schemas (`request/header`), todo text, compaction summaries, hook `stderrSummary`, feedback text, and the session `cwd` (a local path). The seam ships no redaction rules: with no `telemetry/record` listener mounted, that is the raw captured copy, so a deployment exporting beyond a trusted boundary mounts its own rules (see [the seam README](../session-telemetry/README.md#the-redact-waterfall)). `FULL` runs redaction at append time; `FEEDBACK_ONLY` retains no telemetry copy and runs the currently mounted rules when feedback triggers canonical-log replay. Provider credentials never appear regardless: adapter API keys are constructor parameters, not session events, so they are structurally absent from the log and therefore from telemetry. `DISABLED` does not construct the SDK pipeline or hand any capture to a backend. ## Field mapping @@ -46,4 +46,4 @@ None; this package neither assembles nor sends a provider request. - **Upstream experimental tree** — `@opentelemetry/sdk-logs` is still published from the upstream experimental tree; SDK API churn lands here and only here — the seam contract does not move. - **No live-collector coverage** — every test exports to a local mock collector; the keyless Loader-composition e2e (`tests/loader-composition.e2e.ts`) covers the wire shape on every run, and behavior against a real OTLP deployment (auth, TLS, throttling) is the SDK exporter's documented territory. -- **Feedback-only memory** — each session retains deep-copied, redacted projected records in memory until feedback releases them or the session becomes unreachable. There is no durable pre-feedback spool; a crash before feedback uploads nothing. +- **Feedback-time snapshot** — `FEEDBACK_ONLY` retains no telemetry-owned copy before feedback. It reads and redacts the current canonical log when feedback is recorded; a crash before feedback uploads nothing, and policy changes before feedback affect what that replay exports. diff --git a/packages/telemetry/session-telemetry-otel/README.zh.md b/packages/telemetry/session-telemetry-otel/README.zh.md index ab01911888..3160b67c82 100644 --- a/packages/telemetry/session-telemetry-otel/README.zh.md +++ b/packages/telemetry/session-telemetry-otel/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -[遥测（telemetry）seam](../session-telemetry/) 的 OpenTelemetry 后端，也是部署方唯一要加载的条目。其 `mode` 决定 seam 是立即交接记录、仅在记录反馈时释放记录，还是将遥测留在本地。上传模式会原样组合 OTel JS SDK（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP 日志导出器），把每条已交接记录映射到 `logger.emit()`，并使用两个插桩作用域（instrumentation scope）：ledger 记录挂在 `@deepseek-ai/dsh-session-telemetry-otel` 下，运维记录挂在 `@deepseek-ai/dsh-session-telemetry-otel/ops` 下。资源身份（`service.name`/`service.version`）来自 `dsh-llm` 的 `APP_IDENTITY`，与归因标头同源。 +[遥测（telemetry）seam](../session-telemetry/) 的 OpenTelemetry 后端，也是部署方唯一要加载的条目。其 `mode` 决定 seam 是实时跟随会话事件、仅在记录反馈时回放权威日志，还是将遥测留在本地。上传模式会原样组合 OTel JS SDK（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP 日志导出器），把每条已交接记录映射到 `logger.emit()`，并使用两个插桩作用域（instrumentation scope）：ledger 记录挂在 `@deepseek-ai/dsh-session-telemetry-otel` 下，运维记录挂在 `@deepseek-ai/dsh-session-telemetry-otel/ops` 下。资源身份（`service.name`/`service.version`）来自 `dsh-llm` 的 `APP_IDENTITY`，与归因标头同源。 ## 配置 @@ -21,14 +21,14 @@ | `mode` | 行为 | |---|---| | `FULL` | 默认值。每条已投影记录都立即交给 OTel SDK，包括生命周期运维记录。 | -| `FEEDBACK_ONLY` | 每个 `feedback/record` 都会释放截至该事件的已脱敏、已投影会话前缀。后续记录等待下一个反馈事件；如果没有后续反馈，则留在本地。 | +| `FEEDBACK_ONLY` | 每个 `feedback/record` 都会回放权威会话日志中截至该事件的后缀，并进行投影与脱敏。后续记录等待下一个反馈事件；如果没有后续反馈，则留在本地。 | | `DISABLED` | 不构造协调器、提供方、处理器或导出器。没有遥测记录会离开进程。`feedback/record` 会记录 `session telemetry is DISABLED; nothing will be shared and this feedback remains local`；该事件留在本地会话日志中。 | `exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填，无默认值，且必须能解析为 `http(s)`；在 `DISABLED` 中可省略且不使用。上传模式也会拒绝不是正整数的 `processor.maxExportBatchSize`，SDK 虽会接受该值，但随后会在关闭时挂起。其余全部是 SDK 自己的选项形态，由 SDK 拥有并在 SDK 文档中说明，两个配置块都整体透传（passthrough）：`OTLPExporterNodeConfigBase` 的每个字段（`headers`、`timeoutMillis`、`compression`、`keepAlive` 等）都会到达导出器；批处理、导出节奏（`scheduledDelayMillis`）、重试、队列上限，以及持续失败下的丢失策略，都是 SDK 的文档化行为，经 `processor` 透传调优。该后端刻意不实现 `flush()`：批处理器是进程内唯一执行 flush 的组件，`shutdown()` 的排空正因如此才是完整的。 ## 哪些数据会离开本机 -在上传模式中，记录携带完整的 `event.data`，内容以 seam 的 `telemetry/record` waterfall（瀑布式事件）返回的结果为准：用户与 assistant 消息内容、工具参数与工具结果（命令输出、文件内容）、完整的系统提示词与工具 schema（`request/header`）、todo 文本、压缩（compaction）摘要、钩子的 `stderrSummary`、反馈文本，以及会话 `cwd`（一个本地路径）。seam 不带任何脱敏规则：未挂载 `telemetry/record` 监听器时，导出的就是捕获原样的副本，因此向可信边界之外导出的部署方要挂载自己的规则（见 [seam README](../session-telemetry/README.md#the-redact-waterfall)）。无论如何，提供方凭据都不会出现：适配器的 API key 是构造函数参数而非会话事件，因此它们在结构上就不存在于日志中，也就不存在于遥测中。`DISABLED` 不会构造 SDK 流水线，也不会将任何捕获内容交给后端。 +在上传模式中，记录携带完整的 `event.data`，内容以 seam 的 `telemetry/record` waterfall（瀑布式事件）返回的结果为准：用户与 assistant 消息内容、工具参数与工具结果（命令输出、文件内容）、完整的系统提示词与工具 schema（`request/header`）、todo 文本、压缩（compaction）摘要、钩子的 `stderrSummary`、反馈文本，以及会话 `cwd`（一个本地路径）。seam 不带任何脱敏规则：未挂载 `telemetry/record` 监听器时，导出的就是捕获原样的副本，因此向可信边界之外导出的部署方要挂载自己的规则（见 [seam README](../session-telemetry/README.md#the-redact-waterfall)）。`FULL` 在追加时运行脱敏；`FEEDBACK_ONLY` 不保留遥测副本，而是在反馈触发权威日志回放时运行当时挂载的规则。无论如何，提供方凭据都不会出现：适配器的 API key 是构造函数参数而非会话事件，因此它们在结构上就不存在于日志中，也就不存在于遥测中。`DISABLED` 不会构造 SDK 流水线，也不会将任何捕获内容交给后端。 ## 字段映射 @@ -46,4 +46,4 @@ seam 记录 → SDK 日志记录：`time` → `timestamp`/`observedTimestamp`； - **上游实验性源码树**：`@opentelemetry/sdk-logs` 仍从上游实验性（experimental）源码树发布；SDK API 的变动只会落在本包，也仅落在本包；seam 契约不动。 - **无真实 collector 覆盖**：所有测试都导出到本地 mock collector；无密钥的 Loader 组合 e2e（`tests/loader-composition.e2e.ts`）在每次运行中都覆盖协议格式（wire format）形态，而面对真实 OTLP 部署的行为（认证、TLS、限流）属于 SDK 导出器文档的职责范围。 -- **仅反馈模式的内存占用**：每个会话都会在内存中保留已深拷贝、已脱敏的投影记录，直到反馈将其释放或会话变得不可达。反馈前不存在持久化 spool；如果在反馈前崩溃，则什么都不上传。 +- **反馈时快照**：`FEEDBACK_ONLY` 在反馈前不保留遥测自有副本。记录反馈时，它读取并脱敏当前的权威日志；反馈前发生崩溃时什么都不上传，而反馈前的策略变更会影响该次回放的导出内容。 diff --git a/packages/telemetry/session-telemetry-otel/src/index.ts b/packages/telemetry/session-telemetry-otel/src/index.ts index cb0ee71fc7..908f0f90fb 100644 --- a/packages/telemetry/session-telemetry-otel/src/index.ts +++ b/packages/telemetry/session-telemetry-otel/src/index.ts @@ -7,7 +7,8 @@ * boundary axiom, everything downstream of that call (batching, retry, * queueing, loss policy) is the SDK's documented behavior, configured * verbatim through the `exporter`/`processor` passthroughs. This package owns - * only whether capture is immediate, feedback-released, or disabled. + * only whether capture is live, feedback-triggered from the canonical log, or + * disabled. * * @module @deepseek-ai/dsh-session-telemetry-otel */ @@ -19,7 +20,7 @@ import type {} from '@deepseek-ai/dsh-command-feedback' import { Telemetry, TelemetryCoordinator, - type TelemetryDelivery, + type TelemetryCapture, type TelemetryRecord, type TelemetrySeverity, } from '@deepseek-ai/dsh-session-telemetry' @@ -161,13 +162,13 @@ export class TelemetryOtel extends Telemetry { }) this.ledger = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel', version) this.ops = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel/ops', version) - const delivery: TelemetryDelivery = mode === 'FULL' ? 'immediate' : 'held' - const coordinator = new TelemetryCoordinator(ctx, this, delivery) + const capture: TelemetryCapture = mode === 'FULL' ? 'live' : 'on-demand' + const coordinator = new TelemetryCoordinator(ctx, this, capture) if (mode === 'FEEDBACK_ONLY') { - // The coordinator listener is registered first, so a feedback event - // enters the held prefix before this listener releases that exact prefix. + // Session.append commits before publishing `session/event`, so the + // canonical log already includes this feedback record when replay begins. ctx.on('session/event', (session, event) => { - if (event.type === 'feedback/record') coordinator.release(session) + if (event.type === 'feedback/record') coordinator.captureSession(session, event.seq) }) } } @@ -206,8 +207,8 @@ export class TelemetryOtel extends Telemetry { * quiesce. With no concurrent `forceFlush()` in the process (see above), * shutdown's internal drain is complete — everything handed to the SDK * before this call is exported before the exporter closes. In `FULL`, that - * includes dispose-time `shutdown` markers; held suffixes never reach the - * SDK. Awaited (and error-contained) by the coordinator's disposer. A + * includes dispose-time `shutdown` markers; `FEEDBACK_ONLY` creates no ops + * records. Awaited (and error-contained) by the coordinator's disposer. A * disabled backend resolves immediately. * @returns resolves when the SDK pipeline has quiesced. */ diff --git a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts index 18c466f7aa..9b7e4119b7 100644 --- a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts +++ b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts @@ -206,7 +206,7 @@ describe('TelemetryOtel wire', () => { expect(start?.record.severityNumber).toBe(13) }) - it('holds each session suffix until the next feedback event', async () => { + it('replays each session suffix only at the next feedback event', async () => { const { url, captures } = await mockCollector() const ctx = new Context() await ctx.plugin(SessionStore) diff --git a/packages/telemetry/session-telemetry/README.i18n.yaml b/packages/telemetry/session-telemetry/README.i18n.yaml index da3a62e2fd..ee9c7288b1 100644 --- a/packages/telemetry/session-telemetry/README.i18n.yaml +++ b/packages/telemetry/session-telemetry/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/telemetry/session-telemetry/README.md -README.md: d38433a728c699c7fb3cc0512bb6a2d977dd4cc6 -README.zh.md: 3a86b01321fc7dfd33d39530ee7fa38a6ee1f2dc +README.md: 67d95bcc62bbf6783f8dcd11f0236d8c926b557b +README.zh.md: 1ee0e0eb14bb06c8ac669cd417f2ee2ce46ca430 diff --git a/packages/telemetry/session-telemetry/README.md b/packages/telemetry/session-telemetry/README.md index d38433a728..67d95bcc62 100644 --- a/packages/telemetry/session-telemetry/README.md +++ b/packages/telemetry/session-telemetry/README.md @@ -2,23 +2,23 @@ English | [中文](README.zh.md) -The telemetry seam: the capture side of session-event reporting, behind a backend contract any reporting SDK satisfies with zero bending. Capture can hand each redacted record over immediately or hold a per-session prefix for an explicit release. The boundary axiom that shapes everything here: **this package's aspect ends at `emit()`** — batching, retry, queueing, and loss policy belong to the backend's SDK and are neither specified nor wrapped. Rationale and rejected alternatives: [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md) and [feedback-gated delivery](../../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md). +The telemetry seam: the capture side of session-event reporting, behind a backend contract any reporting SDK satisfies with zero bending. Capture can follow live session events or replay a canonical session-log prefix on demand. The boundary axiom that shapes everything here: **this package's aspect ends at `emit()`** — batching, retry, queueing, and loss policy belong to the backend's SDK and are neither specified nor wrapped. Rationale and rejected alternatives: [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md), [feedback-gated delivery](../../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md), and [buffer-free feedback replay](../../../.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.md). ## The backend contract -`TelemetryBackend` is three members: `emit(record)` (MUST be a non-blocking enqueue — it runs synchronously on the `session/event` hot path, either at capture or held-prefix release), optional `flush()` (a turn-boundary hint, fire-and-forget; most backends leave it unimplemented and let their SDK's batching cadence govern export timing — an implementer owns the interaction between concurrent flushes and `shutdown()`'s drain), and `shutdown()` (the lifecycle forward: drain-and-quiesce, awaited at dispose). `Telemetry` is its service-registered form under the `telemetry` context key — one implementation per context, duplicate load throws. A backend composes `TelemetryCoordinator` with `immediate` delivery or `held` delivery and calls `release(session)` at its owning trigger. +`TelemetryBackend` is three members: `emit(record)` (MUST be a non-blocking enqueue — it runs synchronously on the `session/event` hot path or during an explicit canonical-log replay), optional `flush()` (a turn-boundary hint, fire-and-forget; most backends leave it unimplemented and let their SDK's batching cadence govern export timing — an implementer owns the interaction between concurrent flushes and `shutdown()`'s drain), and `shutdown()` (the lifecycle forward: drain-and-quiesce, awaited at dispose). `Telemetry` is its service-registered form under the `telemetry` context key — one implementation per context, duplicate load throws. A backend composes `TelemetryCoordinator` with `live` capture or `on-demand` capture and calls `captureSession(session, throughSeq?)` at its owning trigger. ## Capture points -The coordinator registers, all through the composing fiber's effects: `session/created` (adopt: record the header, read the log back through the projection from the construction boundary — constructor seeds from fork/resume never re-emit on the firehose and never re-export), `session/event` (project, deep-copy, redact, then hand off or hold; zero I/O), `session/flush` (forward the optional `flush()` hint and return void — the loop's awaited parallel must never wait on telemetry), `session/disposed` (capture the session's `shutdown` operational record at its termination edge, then retire it), `agent/error` (the one live-bus relay; the session event vocabulary intentionally has no operational-error record), a dispose effect (capture shutdown for each still-live session, then await the backend's `shutdown()`; failures warn instead of throwing), and an adoption sweep of `ctx.sessions.list()` (a hot reload does not replay `session/created`). Immediate delivery hands lifecycle records over; held delivery leaves any suffix after the last release local, including its later shutdown marker. +In `live` mode the coordinator registers, all through the composing fiber's effects: `session/created` (adopt: record the header, read the log back through the projection from the construction boundary — constructor seeds from fork/resume never re-emit on the firehose and never re-export), `session/event` (project, deep-copy, redact, then hand off; zero I/O), `session/flush` (forward the optional `flush()` hint and return void — the loop's awaited parallel must never wait on telemetry), `session/disposed` (capture the session's `shutdown` operational record at its termination edge, then retire it), `agent/error` (the one live-bus relay; the session event vocabulary intentionally has no operational-error record), a dispose effect (capture shutdown for each still-live session, then await the backend's `shutdown()`; failures warn instead of throwing), and an adoption sweep of `ctx.sessions.list()` (a hot reload does not replay `session/created`). In `on-demand` mode it registers only the dispose effect: `captureSession()` reads the canonical log through an optional inclusive sequence boundary, while flush hints and operational events remain local. ## The redact waterfall -Every record passes the `telemetry/record` waterfall immediately after projection — the seam's scrubbing extension point. The seam ships NO rules of its own: the innermost `next()` passes the record through unchanged, so with no listener mounted records reach the backend exactly as captured, and exported data is precisely as clean as the rules a deployment mounts. Listeners stack by transforming `next()`'s return value; returning without `next()` replaces everything beneath, and a throwing listener withholds that one record fail-closed inside the coordinator's containment. Held delivery stores only the waterfall result, so later policy removal cannot expose the original capture. Redaction applies to the outbound copy only; the canonical session log is never rewritten. +Every record passes the `telemetry/record` waterfall immediately after projection — the seam's scrubbing extension point. The seam ships NO rules of its own: the innermost `next()` passes the record through unchanged, so with no listener mounted records reach the backend exactly as captured, and exported data is precisely as clean as the rules a deployment mounts. Listeners stack by transforming `next()`'s return value; returning without `next()` replaces everything beneath, and a throwing listener withholds that one record fail-closed inside the coordinator's containment. Live capture runs the waterfall at append time; on-demand capture runs it while replaying the canonical log, using the rules mounted at that time. Redaction applies to the outbound copy only; the canonical session log is never rewritten. ## The handoff cursor -A module-scope `WeakMap` marks the highest seq HANDED OFF (not delivered) per session. Immediate delivery advances it at capture; held delivery advances it only when `release(session)` hands that record to the backend. An unreleased prefix therefore survives a coordinator reload through deterministic re-adoption instead of disappearing with its in-memory copy. On re-adoption the coordinator re-hands only events past the cursor (events at or below it still rebuild the chunk-projection state); a missing cursor safely degrades to a re-hand from the session's construction boundary (`Session.firstLiveSeq` — seq 0 for a session born in this process), absorbed by receiver-side dedupe on `(session.id, event.seq)`. Constructor seeds never re-export: a resumed session's history shipped from the previous process under the same id, and a fork's inherited prefix lives in the parent's stream (receivers stitch on `session.parent_id` + `session.seed_length`). The accepted cost, consistent with at-most-once delivery: a resume does not backfill records a previous process failed to deliver — a deployment with a backfill requirement needs the deferred outbox, not replay. This is a deliberate, narrow exception to the registrations-are-effects discipline: entries die with their sessions, the value is a monotonic watermark, and losing it is never an error. +A module-scope `WeakMap` marks the highest seq HANDED OFF (not delivered) per session. Live capture advances it at append time; on-demand capture advances it only while `captureSession()` hands a requested prefix to the backend. An uncaptured prefix remains solely in the canonical log, so a coordinator reload adds no telemetry-owned recovery state. On replay the coordinator re-hands only events past the cursor (events at or below it still rebuild the chunk-projection state); a missing cursor safely degrades to a re-hand from the session's construction boundary (`Session.firstLiveSeq` — seq 0 for a session born in this process), absorbed by receiver-side dedupe on `(session.id, event.seq)`. Constructor seeds never re-export: a resumed session's history shipped from the previous process under the same id, and a fork's inherited prefix lives in the parent's stream (receivers stitch on `session.parent_id` + `session.seed_length`). The accepted cost, consistent with at-most-once delivery: a resume does not backfill records a previous process failed to deliver — a deployment with a backfill requirement needs the deferred outbox, not replay. This is a deliberate, narrow exception to the registrations-are-effects discipline: entries die with their sessions, the value is a monotonic watermark, and losing it is never an error. ## The fixed chunk projection @@ -40,4 +40,4 @@ None; this package neither assembles nor sends a provider request. - **Best-effort delivery** — the cursor marks handed-off, not delivered; a session torn down inside a reload window cannot be re-adopted; whatever sits in a backend queue at crash time is lost. A durable outbox (spool, per-sink cursors, at-least-once) is deferred until a deployment states a crash-loss requirement — see [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md). - **No built-in redaction rules** — with no `telemetry/record` listener mounted, records leave the process exactly as captured, including any credentials embedded in file contents or command output; a deployment exporting to a shared collector owns its rule set. -- **Held prefixes duplicate memory** — held delivery retains one deep-copied, redacted record per projected event until release or session collection. It adds no durable outbox and intentionally trades memory for a simple no-upload-before-trigger boundary. +- **On-demand redaction uses current state** — uncaptured events exist only in the canonical session log. A later `captureSession()` deep-copies and redacts their current values with the policy mounted at that time; there is no capture-time telemetry snapshot or durable pre-capture spool. diff --git a/packages/telemetry/session-telemetry/README.zh.md b/packages/telemetry/session-telemetry/README.zh.md index 3a86b01321..1ee0e0eb14 100644 --- a/packages/telemetry/session-telemetry/README.zh.md +++ b/packages/telemetry/session-telemetry/README.zh.md @@ -2,23 +2,23 @@ [English](README.md) | 中文 -遥测（telemetry）seam：会话事件上报的捕获侧，隔在一个后端契约之后，任何上报 SDK 都无需变形即可满足该契约。捕获侧可立即交接每条已脱敏记录，也可按会话暂存一个前缀，等待显式释放。塑造本包（package）一切设计的边界公理：**本包的职责止于 `emit()`**。批处理、重试、排队与丢失策略都属于后端自身的 SDK，本包既不为其立规，也不做包装。设计依据与被否决的替代方案见[复活 Agent Note（agent 决策记录）](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)与[反馈门控投递](../../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md)。 +遥测（telemetry）seam：会话事件上报的捕获侧，隔在一个后端契约之后，任何上报 SDK 都无需变形即可满足该契约。捕获侧可跟随实时会话事件，也可按需回放权威会话日志前缀。塑造本包（package）一切设计的边界公理：**本包的职责止于 `emit()`**。批处理、重试、排队与丢失策略都属于后端自身的 SDK，本包既不为其立规，也不做包装。设计依据与被否决的替代方案见[复活 Agent Note（agent 决策记录）](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)、[反馈门控投递](../../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md)与[无缓冲反馈回放](../../../.agents/notes/implemented/simplification/2026-08-06-buffer-free-feedback-telemetry.md)。 ## 后端契约 -`TelemetryBackend` 只有三个成员：`emit(record)`（必须是非阻塞入队；它会在捕获或暂存前缀释放时，于 `session/event` 热路径上同步执行）、可选的 `flush()`（轮次边界提示，触发后不等待结果；多数后端不实现它，而由其 SDK 的批处理节奏决定导出时机；并发 flush 与 `shutdown()` 的排空之间的交互由实现方自行负责）、以及 `shutdown()`（生命周期转发点：排空并完全停稳，在 dispose（资源释放）时被等待）。`Telemetry` 是它注册在 `telemetry` 上下文键下的服务形态：每个上下文只允许一个实现，重复加载会抛出异常。后端以 `immediate` 或 `held` 投递模式组合 `TelemetryCoordinator`，并在自身所属的触发器中调用 `release(session)`。 +`TelemetryBackend` 只有三个成员：`emit(record)`（必须是非阻塞入队；它在 `session/event` 热路径或显式权威日志回放期间同步执行）、可选的 `flush()`（轮次边界提示，触发后不等待结果；多数后端不实现它，而由其 SDK 的批处理节奏决定导出时机；并发 flush 与 `shutdown()` 的排空之间的交互由实现方自行负责）、以及 `shutdown()`（生命周期转发点：排空并完全停稳，在 dispose（资源释放）时被等待）。`Telemetry` 是它注册在 `telemetry` 上下文键下的服务形态：每个上下文只允许一个实现，重复加载会抛出异常。后端以 `live` 或 `on-demand` 模式组合 `TelemetryCoordinator`，并在自身所属的触发器中调用 `captureSession(session, throughSeq?)`。 ## 捕获点 -协调器的全部注册都经由组合方 fiber 的 effect 完成：`session/created`（收养：记录 header，并经投影从构造边界起回读日志；来自 fork 或恢复的构造函数种子绝不会在 firehose 上再次发出，也绝不会再次导出）、`session/event`（投影、深拷贝、脱敏，再交接或暂存；零 I/O）、`session/flush`（转发可选的 `flush()` 提示并返回 void；循环所等待的并行任务绝不能等待遥测）、`session/disposed`（在会话自身的终止边缘捕获该会话的 `shutdown` 运维记录，然后将其退役）、`agent/error`（唯一的实时总线转发；会话事件词汇有意不包含运维错误记录）、一个 dispose effect（捕获每个仍存活会话的 shutdown，再等待后端的 `shutdown()`；失败只发出警告而不抛出），以及对 `ctx.sessions.list()` 的收养扫描（热重载不会重放 `session/created`）。即时投递会交接生命周期记录；暂存投递会将上次释放后的任何后缀留在本地，包括随后的 shutdown 标记。 +在 `live` 模式中，协调器的全部注册都经由组合方 fiber 的 effect 完成：`session/created`（收养：记录 header，并经投影从构造边界起回读日志；来自 fork 或恢复的构造函数种子绝不会在 firehose 上再次发出，也绝不会再次导出）、`session/event`（投影、深拷贝、脱敏，再交接；零 I/O）、`session/flush`（转发可选的 `flush()` 提示并返回 void；循环所等待的并行任务绝不能等待遥测）、`session/disposed`（在会话自身的终止边缘捕获该会话的 `shutdown` 运维记录，然后将其退役）、`agent/error`（唯一的实时总线转发；会话事件词汇有意不包含运维错误记录）、一个 dispose effect（捕获每个仍存活会话的 shutdown，再等待后端的 `shutdown()`；失败只发出警告而不抛出），以及对 `ctx.sessions.list()` 的收养扫描（热重载不会重放 `session/created`）。在 `on-demand` 模式中，协调器只注册 dispose effect：`captureSession()` 读取权威日志，直至可选的序列号边界（含边界）；flush 提示与运维事件留在本地。 ## 脱敏 waterfall（瀑布式事件） -每条记录在投影后立即经过 `telemetry/record` waterfall，这是该 seam 的脱敏扩展点。seam 自身不带任何规则：最内层的 `next()` 原样透传记录，因此未挂载监听器时，记录以捕获时的原样到达后端；导出数据能干净到什么程度，恰恰取决于部署方挂载了什么规则。监听器通过变换 `next()` 的返回值来堆叠；不调用 `next()` 就返回，即替换其下方的全部逻辑；抛出异常的监听器会在协调器的隔离范围内以 fail-closed 方式拦下这一条记录。暂存投递只保留 waterfall 的结果，因此后续移除策略也无法暴露捕获时的原始内容。脱敏只作用于外发副本；权威会话日志永不改写。 +每条记录在投影后立即经过 `telemetry/record` waterfall，这是该 seam 的脱敏扩展点。seam 自身不带任何规则：最内层的 `next()` 原样透传记录，因此未挂载监听器时，记录以捕获时的原样到达后端；导出数据能干净到什么程度，恰恰取决于部署方挂载了什么规则。监听器通过变换 `next()` 的返回值来堆叠；不调用 `next()` 就返回，即替换其下方的全部逻辑；抛出异常的监听器会在协调器的隔离范围内以 fail-closed 方式拦下这一条记录。实时捕获在追加时运行 waterfall；按需捕获则在回放权威日志时使用当时挂载的规则运行 waterfall。脱敏只作用于外发副本；权威会话日志永不改写。 ## handoff 游标 -一个模块作用域的 `WeakMap` 记录每个会话已交接（而非已投递）的最高 seq。即时投递在捕获时推进游标；暂存投递只有在 `release(session)` 将记录交给后端时才推进游标。因此，重建协调器后会通过确定性重新收养恢复未释放的前缀，而不会随其内存副本一同消失。重新收养时，协调器只重新交接游标之后的事件（游标及其之前的事件仍用于重建分片投影状态）；游标缺失时安全退化为从会话构造边界起的重新交接（`Session.firstLiveSeq`，对在本进程中诞生的会话即 seq 0），由接收端基于 `(session.id, event.seq)` 的去重吸收。构造函数种子绝不会再次导出：恢复会话的历史已由上一个进程以同一 id 发出，fork 继承的前缀则位于父会话的流中（接收端基于 `session.parent_id` + `session.seed_length` 拼接）。由此接受的代价与至多一次（at-most-once）投递一致：恢复不会回填上一个进程未能投递的记录；有回填要求的部署需要的是已推迟的 outbox，而不是回放。这是对「注册即 effect」纪律的一次有意且范围极窄的例外：条目随其会话消亡，值是单调水位线，丢失它绝不是错误。 +一个模块作用域的 `WeakMap` 记录每个会话已交接（而非已投递）的最高 seq。实时捕获在追加时推进游标；按需捕获只有在 `captureSession()` 将请求的前缀交给后端时才推进游标。未捕获的前缀只留在权威日志中，因此协调器重载不会增加遥测自有的恢复状态。回放时，协调器只重新交接游标之后的事件（游标及其之前的事件仍用于重建分片投影状态）；游标缺失时安全退化为从会话构造边界起的重新交接（`Session.firstLiveSeq`，对在本进程中诞生的会话即 seq 0），由接收端基于 `(session.id, event.seq)` 的去重吸收。构造函数种子绝不会再次导出：恢复会话的历史已由上一个进程以同一 id 发出，fork 继承的前缀则位于父会话的流中（接收端基于 `session.parent_id` + `session.seed_length` 拼接）。由此接受的代价与至多一次（at-most-once）投递一致：恢复不会回填上一个进程未能投递的记录；有回填要求的部署需要的是已推迟的 outbox，而不是回放。这是对「注册即 effect」纪律的一次有意且范围极窄的例外：条目随其会话消亡，值是单调水位线，丢失它绝不是错误。 ## 固定分片投影 @@ -40,4 +40,4 @@ - **尽力而为的投递**：游标标记的是已交接而非已投递；在重载窗口内被拆除的会话无法重新收养；崩溃时留在后端队列中的内容会丢失。持久化 outbox（spool、每 sink 游标、at-least-once）推迟到有部署方提出明确的崩溃丢失要求时再实现；见[复活 Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)。 - **不内置脱敏规则**：未挂载 `telemetry/record` 监听器时，记录以捕获时的原样离开进程，包括文件内容或命令输出中内嵌的任何凭据；向共享 collector 导出的部署方自行负责其规则集。 -- **暂存前缀会重复占用内存**：暂存投递会为每个已投影事件保留一份深拷贝且已脱敏的记录，直到释放或回收会话。它不增加持久化 outbox，而是有意以内存换取简单的「触发前不上传」边界。 +- **按需脱敏使用当前状态**：未捕获的事件只存在于权威会话日志中。后续的 `captureSession()` 会使用当时挂载的策略，深拷贝并脱敏其当前值；不存在捕获时的遥测快照或持久化的捕获前 spool。 diff --git a/packages/telemetry/session-telemetry/src/coordinator.ts b/packages/telemetry/session-telemetry/src/coordinator.ts index 710e9b81f9..9e32ae0693 100644 --- a/packages/telemetry/session-telemetry/src/coordinator.ts +++ b/packages/telemetry/session-telemetry/src/coordinator.ts @@ -1,13 +1,15 @@ /** - * Capture coordinator: the seam's upstream half. Subscribes to the session - * firehose plus the one live-bus relay (`agent/error`), applies the fixed - * chunk projection, builds logical records, runs each through the + * Capture coordinator: the seam's upstream half. Live capture subscribes to + * the session firehose plus the one live-bus relay (`agent/error`). Both + * capture paths apply the fixed chunk projection, build logical records, and + * run each through the * `telemetry/record` waterfall (deployment-mounted redaction rules; - * pass-through when none), then hands the result to the backend immediately - * or holds it for explicit release. Every synchronous handler is - * self-contained so a failing backend can never starve other subscribers - * (cordis `emit` is stop-on-throw) or touch the agent loop. Composed by a - * backend in its constructor. + * pass-through when none), then hands the result to the backend. Live capture + * follows the session firehose; on-demand capture replays the canonical log + * only when requested. Every synchronous handler is self-contained so a + * failing backend can never starve other subscribers (cordis `emit` is + * stop-on-throw) or touch the agent loop. Composed by a backend in its + * constructor. * * @module @deepseek-ai/dsh-session-telemetry/coordinator */ @@ -17,11 +19,11 @@ import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import type { Agent } from '@deepseek-ai/dsh-agent' import type { TelemetryBackend, TelemetryRecord, TelemetrySeverity } from './index.ts' -/** Whether capture hands records over immediately or holds them for an explicit release. */ -export type TelemetryDelivery = 'immediate' | 'held' +/** Whether capture follows live events or reads the canonical log only when requested. */ +export type TelemetryCapture = 'live' | 'on-demand' -/** One redacted record waiting at the capture boundary. */ -interface PendingRecord { +/** One projected record ready for backend handoff. */ +interface ProjectedRecord { readonly record: TelemetryRecord /** Ledger cursor advanced only after the backend accepts this record. */ readonly seq?: number @@ -43,16 +45,17 @@ const handoffCursor = new WeakMap() /** * Install the telemetry capture side onto a context for one backend. * - * Registers the persistence-coordinator listener set plus the `agent/error` - * relay, all through `ctx.effect()`/`ctx.on()` on the composing fiber, and - * sweeps already-live sessions (a hot reload does not replay + * Live capture registers the persistence-coordinator listener set plus the + * `agent/error` relay, all through `ctx.effect()`/`ctx.on()` on the composing + * fiber, and sweeps already-live sessions (a hot reload does not replay * `session/created`). A `session/disposed` captures the session's `shutdown` * operational record at its own termination edge and retires it from the - * adopted set. Immediate delivery hands that marker over; held delivery keeps - * it local without another explicit release. Disposal captures the same - * marker for sessions still alive, then awaits the backend's `shutdown()`; a - * failure there warns instead of throwing — best-effort reporting must not - * fail application teardown. + * adopted set. On-demand capture registers none of those continuous listeners; + * {@link captureSession} reads the canonical log explicitly and never creates + * operational records. Disposal captures shutdown markers for live-adopted + * sessions, then awaits the backend's `shutdown()`; a failure there warns + * instead of throwing — best-effort reporting must not fail application + * teardown. */ export class TelemetryCoordinator { /** @@ -63,56 +66,55 @@ export class TelemetryCoordinator { private readonly adopted = new Set() /** Per session, the `turn:step` keys whose first chunk already shipped; rebuilt from the log on re-adoption. */ private readonly chunkSeen = new WeakMap>() - /** Redacted records retained until {@link release}; weak keys do not extend session lifetime. */ - private readonly held = new WeakMap() - /** * @param ctx - the composing backend's context; listeners bind to its fiber. * @param backend - the backend receiving records; owned elsewhere, never disposed here beyond `shutdown()` forwarding. - * @param delivery - immediate handoff, or held delivery released explicitly per session. + * @param capture - follow live events, or wait for explicit canonical-log capture. */ constructor( private readonly ctx: Context, private readonly backend: TelemetryBackend, - private readonly delivery: TelemetryDelivery = 'immediate', + capture: TelemetryCapture = 'live', ) { - ctx.on('session/created', (session) => { - this.adopt(session) - }) - // Capture the shutdown marker at the session's own termination edge. - // Immediate delivery preserves crash classification; held delivery does - // not let a later lifecycle edge extend a user-released prefix. Then - // retire the only strong reference owned by this coordinator. - ctx.on('session/disposed', (session) => { - this.contain(() => { - if (!this.adopted.delete(session)) return - this.submit(session, { record: this.redact(shutdownRecord(session)) }) + if (capture === 'live') { + ctx.on('session/created', (session) => { + this.adopt(session) }) - }) - ctx.on('session/event', (session, event) => { - this.contain(() => { - this.capture(session, event) + // Capture the shutdown marker at the session's own termination edge, + // then retire the only strong reference owned by this coordinator. + ctx.on('session/disposed', (session) => { + this.contain(() => { + if (!this.adopted.delete(session)) return + this.deliver(session, { record: this.redact(shutdownRecord(session)) }) + }) }) - }) - // Parallel listeners are awaited by the loop at turn end; returning void - // (not the SDK's flush promise) is the turn-latency contract. - ctx.on('session/flush', (session) => { - this.contain(() => { - this.hintFlush(session) + ctx.on('session/event', (session, event) => { + this.contain(() => { + this.captureEvent(session, event) + }) }) - }) - ctx.on('agent/error', (agent, turn, step, error) => { - this.contain(() => { - this.relayAgentError(agent, turn, step, error) + // Parallel listeners are awaited by the loop at turn end; returning void + // (not the SDK's flush promise) is the turn-latency contract. + ctx.on('session/flush', (session) => { + this.contain(() => { + this.hintFlush(session) + }) }) - }) + ctx.on('agent/error', (agent, turn, step, error) => { + this.contain(() => { + this.relayAgentError(agent, turn, step, error) + }) + }) + for (const session of ctx.sessions.list()) { + this.adopt(session) + } + } ctx.effect(() => async () => { // Sessions still adopted here are alive through whole-application - // teardown, so capture the marker before the backend quiesces. Held - // delivery intentionally leaves it local without another release. + // teardown, so capture the marker before the backend quiesces. for (const session of this.adopted) { this.contain(() => { - this.submit(session, { record: this.redact(shutdownRecord(session)) }) + this.deliver(session, { record: this.redact(shutdownRecord(session)) }) }) } try { @@ -121,24 +123,27 @@ export class TelemetryCoordinator { this.ctx.logger.warn(`telemetry: backend shutdown failed: ${String(error)}`) } }, 'telemetry capture') - for (const session of ctx.sessions.list()) { - this.adopt(session) - } } /** - * Hand the records currently held for one session to the backend in capture order. - * Records captured after this call form a new held prefix. Backend failures remain - * contained per record and do not starve later records in the same release. - * @param session - session whose pending capture prefix may leave the process. + * Project and hand over the canonical session-log suffix after the handoff + * cursor, optionally stopping at an inclusive sequence boundary. Redaction + * runs during this call, so an on-demand caller retains no copied records + * before requesting capture and uses the policy mounted at that time. + * Backend and policy failures remain contained per event and do not starve + * later events in the same replay. + * @param session - session whose current canonical-log prefix may be handed over. + * @param throughSeq - optional last sequence included in this capture. */ - release(session: Session): void { - const pending = this.held.get(session) - if (pending === undefined) return - this.held.delete(session) - for (const record of pending) { + captureSession(session: Session, throughSeq?: number): void { + const cursor = handoffCursor.get(session) ?? session.firstLiveSeq - 1 + // Containment is PER EVENT: one rejected record is withheld fail-closed + // while the rest of the historical replay proceeds. + for (const event of session.events) { + if (throughSeq !== undefined && event.seq > throughSeq) break this.contain(() => { - this.deliver(session, record) + if (event.seq <= cursor) this.track(session, event) + else this.captureEvent(session, event) }) } } @@ -161,17 +166,7 @@ export class TelemetryCoordinator { private adopt(session: Session): void { if (this.adopted.has(session)) return this.adopted.add(session) - const cursor = handoffCursor.get(session) ?? session.firstLiveSeq - 1 - // Containment is PER EVENT, matching the firehose: one rejected record - // is withheld fail-closed while the rest of the historical replay - // proceeds — wrapping the whole loop would let a single failure silently - // skip the remainder of the log on an already-adopted session. - for (const event of session.events) { - this.contain(() => { - if (event.seq <= cursor) this.track(session, event) - else this.capture(session, event) - }) - } + this.captureSession(session) } /** Feed the chunk projection without handing off — the ≤cursor half of re-adoption. */ @@ -181,8 +176,8 @@ export class TelemetryCoordinator { } } - /** Project and redact one event, then submit it under the delivery policy. */ - private capture(session: Session, event: SessionEvent): void { + /** Project, redact, and hand one event to the backend. */ + private captureEvent(session: Session, event: SessionEvent): void { if (event.type === 'assistant/chunk') { const key = `${event.data.turn}:${event.data.step}` const seen = this.seen(session) @@ -193,14 +188,14 @@ export class TelemetryCoordinator { if (seen.has(key)) return seen.add(key) } - this.submit(session, { + this.deliver(session, { record: this.redact({ channel: 'ledger', time: event.time, severity: severityOf(event), attributes: identityOf(session, event), - // The live event object is mutable and the backend serializes later; - // append-time validation guarantees this clone cannot throw. + // The canonical event object is mutable and the backend serializes + // later; append-time validation guarantees this clone cannot throw. body: structuredClone(event.data), }), seq: event.seq, @@ -212,26 +207,15 @@ export class TelemetryCoordinator { * passes the record through unchanged — the seam ships no rules; exported * data is as clean as the listeners a deployment mounts. Callers run inside * {@link contain}, so a throwing rule withholds the record instead of - * reaching the loop (fail-closed). Held delivery stores only this result, so - * a later policy reload cannot expose the pre-redaction capture. + * reaching the loop (fail-closed). On-demand capture invokes this waterfall + * while reading the canonical session log, not when the event was appended. */ private redact(record: TelemetryRecord): TelemetryRecord { return this.ctx.waterfall('telemetry/record', record, () => record) } - /** Hold one redacted record or deliver it immediately under the configured policy. */ - private submit(session: Session, pending: PendingRecord): void { - if (this.delivery === 'held') { - let records = this.held.get(session) - if (records === undefined) this.held.set(session, records = []) - records.push(pending) - return - } - this.deliver(session, pending) - } - /** Hand one redacted record to the backend, then advance its ledger cursor. */ - private deliver(session: Session, pending: PendingRecord): void { + private deliver(session: Session, pending: ProjectedRecord): void { this.backend.emit(pending.record) if (pending.seq !== undefined) handoffCursor.set(session, pending.seq) } @@ -244,7 +228,7 @@ export class TelemetryCoordinator { /** Relay one `agent/error` bus emission as an `agent-error` operational record. */ private relayAgentError(agent: Agent, turn: number, step: number, error: unknown): void { const detail = errorDetail(error) - this.submit(agent.session, { + this.deliver(agent.session, { record: this.redact({ channel: 'ops', time: Date.now(), diff --git a/packages/telemetry/session-telemetry/src/index.ts b/packages/telemetry/session-telemetry/src/index.ts index 914ef96a95..0198df3140 100644 --- a/packages/telemetry/session-telemetry/src/index.ts +++ b/packages/telemetry/session-telemetry/src/index.ts @@ -4,9 +4,9 @@ * The seam owns the CAPTURE side of session-event reporting — which records * exist (the chunk projection), what they carry (the logical record), when * they are captured (adoption, the per-append firehose, lifecycle - * forwarding), immediate versus explicitly released handoff, and the HMR + * forwarding), live versus on-demand canonical-log capture, and the HMR * cursor. Everything downstream of - * {@link Telemetry.emit} — batching, retry, queueing, loss policy — is the + * {@link Telemetry.emit} — batching, retry, queueing, and loss policy — is the * reporting SDK's territory and is deliberately not modelled here. The * design and its trade-offs are pinned in * .agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md. @@ -33,8 +33,9 @@ declare module 'cordis' { * `next()` replaces everything beneath. Dispatched synchronously on the * capture hot path inside the coordinator's containment: a throwing * listener withholds that one record (fail-closed) and never reaches the - * agent loop. Redaction applies to the exported copy only; the canonical - * session log is never rewritten. + * agent loop. Live capture dispatches at append time; on-demand capture + * dispatches while reading the canonical log. Redaction applies to the + * exported copy only; the canonical session log is never rewritten. * @param record - the candidate record, already the coordinator's own deep * copy; listeners return a (possibly new) record and must not mutate it. * @mode waterfall @@ -95,8 +96,8 @@ export interface TelemetryBackend { /** * Hand one record to the backend's pipeline. MUST be a non-blocking * enqueue — the coordinator calls this synchronously from the - * `session/event` hot path, either at capture or while releasing a held - * prefix, so anything slower than a queue push would tax the agent loop. + * `session/event` hot path or an explicit canonical-log capture, so anything + * slower than a queue push would tax the agent loop or feedback handling. * Errors thrown here are contained by the coordinator and logged; they * never reach the loop. * @param record - the logical record to report; owned by the backend after the call. @@ -123,9 +124,8 @@ export interface TelemetryBackend { * coordinator emits its dispose-time `shutdown` markers immediately before * calling this). Awaited by the coordinator's dispose; a rejection is * logged as a warning and never fails application teardown. - * The coordinator captures dispose-time shutdown markers immediately - * before this call; immediate delivery enqueues them, while held delivery - * leaves an unreleased suffix local. + * The coordinator captures dispose-time shutdown markers immediately before + * this call for live capture; on-demand capture creates no ops records. * @returns resolves when the backend's pipeline has quiesced. */ shutdown(): Promise @@ -158,4 +158,4 @@ export abstract class Telemetry extends Service implements TelemetryBackend { abstract shutdown(): Promise } -export { TelemetryCoordinator, type TelemetryDelivery } from './coordinator.ts' +export { TelemetryCoordinator, type TelemetryCapture } from './coordinator.ts' diff --git a/packages/telemetry/session-telemetry/tests/telemetry.spec.ts b/packages/telemetry/session-telemetry/tests/telemetry.spec.ts index d913e6a742..f368e80979 100644 --- a/packages/telemetry/session-telemetry/tests/telemetry.spec.ts +++ b/packages/telemetry/session-telemetry/tests/telemetry.spec.ts @@ -13,7 +13,7 @@ import type { Agent } from '@deepseek-ai/dsh-agent' import { TelemetryCoordinator, type TelemetryBackend, - type TelemetryDelivery, + type TelemetryCapture, type TelemetryRecord, } from '../src/index.ts' @@ -61,7 +61,7 @@ class FakeBackend implements TelemetryBackend { async function setup( backend: FakeBackend = new FakeBackend(), - delivery: TelemetryDelivery = 'immediate', + capture: TelemetryCapture = 'live', ) { const ctx = new Context() await ctx.plugin(SessionStore) @@ -70,7 +70,7 @@ async function setup( name: 'fake-telemetry', inject: ['sessions'], apply: (inner: Context) => { - coordinator = new TelemetryCoordinator(inner, backend, delivery) + coordinator = new TelemetryCoordinator(inner, backend, capture) }, }) return { ctx, backend, coordinator, fiber } @@ -178,23 +178,24 @@ describe('TelemetryCoordinator capture', () => { }) }) -describe('TelemetryCoordinator held delivery', () => { - it('releases one pending prefix at a time without handing later records over early', async () => { - const { ctx, backend, coordinator } = await setup(new FakeBackend(), 'held') - const session = liveSession(ctx, 'held-prefix') +describe('TelemetryCoordinator on-demand capture', () => { + it('captures one canonical-log prefix at a time without following later events', async () => { + const { ctx, backend, coordinator } = await setup(new FakeBackend(), 'on-demand') + const session = liveSession(ctx, 'on-demand-prefix') appendTurn(session) + const firstBoundary = session.events[1]!.seq + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) expect(backend.records).toEqual([]) - coordinator.release(session) + coordinator.captureSession(session, firstBoundary) expect(backend.ledger().map(record => record.attributes['event.type'])).toEqual([ 'turn/start', 'user/message', ]) - session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) expect(backend.ledger()).toHaveLength(2) - coordinator.release(session) - coordinator.release(session) + coordinator.captureSession(session) + coordinator.captureSession(session) expect(backend.ledger().map(record => record.attributes['event.type'])).toEqual([ 'turn/start', 'user/message', @@ -202,38 +203,42 @@ describe('TelemetryCoordinator held delivery', () => { ]) }) - it('stores the capture-time redacted copy rather than re-running policy at release', async () => { - const { ctx, backend, coordinator } = await setup(new FakeBackend(), 'held') + it('runs the currently mounted redaction policy during canonical-log capture', async () => { + const { ctx, backend, coordinator } = await setup(new FakeBackend(), 'on-demand') + const session = liveSession(ctx, 'on-demand-redacted') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) const disposeRule = ctx.on('telemetry/record', (_record, next) => ({ ...next(), body: { scrubbed: true }, })) - const session = liveSession(ctx, 'held-redacted') - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + + coordinator.captureSession(session) + expect(backend.ledger()[0]!.body).toEqual({ scrubbed: true }) disposeRule() - coordinator.release(session) - expect(backend.ledger()[0]!.body).toEqual({ scrubbed: true }) + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + coordinator.captureSession(session) + expect(backend.ledger()[1]!.body).toEqual({ turn: 1, reason: { kind: 'completed' } }) }) - it('contains each backend failure independently while releasing a batch', async () => { + it('contains each backend failure independently while replaying a prefix', async () => { const backend = new FakeBackend() backend.rejectSeq = 1 - const { ctx, coordinator } = await setup(backend, 'held') + const { ctx, coordinator } = await setup(backend, 'on-demand') const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) - const session = liveSession(ctx, 'held-failure') + const session = liveSession(ctx, 'on-demand-failure') appendTurn(session) session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - coordinator.release(session) + coordinator.captureSession(session) expect(backend.ledger().map(record => record.attributes['event.seq'])).toEqual([0, 2]) expect(warn).toHaveBeenCalled() }) - it('rebuilds an unreleased prefix after coordinator reload', async () => { + it('captures a pending prefix after coordinator reload without retained records', async () => { const first = new FakeBackend() - const { ctx, fiber } = await setup(first, 'held') - const session = liveSession(ctx, 'held-reload') + const { ctx, fiber } = await setup(first, 'on-demand') + const session = liveSession(ctx, 'on-demand-reload') session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) await fiber.dispose() expect(first.records).toEqual([]) @@ -241,15 +246,34 @@ describe('TelemetryCoordinator held delivery', () => { const second = new FakeBackend() let coordinator!: TelemetryCoordinator await ctx.plugin({ - name: 'fake-telemetry-after-held-reload', + name: 'fake-telemetry-after-on-demand-reload', inject: ['sessions'], apply: (inner: Context) => { - coordinator = new TelemetryCoordinator(inner, second, 'held') + coordinator = new TelemetryCoordinator(inner, second, 'on-demand') }, }) - coordinator.release(session) + coordinator.captureSession(session) expect(second.ledger().map(record => record.attributes['event.seq'])).toEqual([0]) }) + + it('registers no continuous capture, flush, or ops listeners', async () => { + const { ctx, backend, coordinator, fiber } = await setup(new FakeBackend(), 'on-demand') + const redact = vi.fn((_record: TelemetryRecord, next: () => TelemetryRecord) => next()) + ctx.on('telemetry/record', redact) + const session = liveSession(ctx, 'on-demand-ledger-only') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await ctx.parallel('session/flush', session) + const agent = { id: 'agent-1', session } as Agent + ctx.emit('agent/error', agent, 1, 1, new Error('local only')) + expect(backend.flush).not.toHaveBeenCalled() + expect(backend.records).toEqual([]) + expect(redact).not.toHaveBeenCalled() + + coordinator.captureSession(session) + expect(redact).toHaveBeenCalledTimes(1) + await fiber.dispose() + expect(backend.records.map(record => record.channel)).toEqual(['ledger']) + }) }) describe('TelemetryCoordinator adoption', () => { From c6f8055388feda7b5298e5d03fb9b9f46fa778cf Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 6 Aug 2026 15:03:52 +0800 Subject: [PATCH 12/22] docs(telemetry): update capture vocabulary --- packages/telemetry/README.i18n.yaml | 4 ++-- packages/telemetry/README.md | 2 +- packages/telemetry/README.zh.md | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/packages/telemetry/README.i18n.yaml b/packages/telemetry/README.i18n.yaml index cd3be8d155..fba4bd4339 100644 --- a/packages/telemetry/README.i18n.yaml +++ b/packages/telemetry/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/telemetry/README.md -README.md: 0adf140a19bd6ab19c4d4139d4ebdae941c0d1b0 -README.zh.md: 57988732e36d105ebcc48adcdab9344a6cccb525 +README.md: ddac6c6cdc5a7326190283fbe232b6985deb4927 +README.zh.md: 6863ca56d4f63fccb60eb3c92acd1e70b25e27dd diff --git a/packages/telemetry/README.md b/packages/telemetry/README.md index 0adf140a19..ddac6c6cdc 100644 --- a/packages/telemetry/README.md +++ b/packages/telemetry/README.md @@ -6,5 +6,5 @@ Outbound session reporting: the telemetry seam plus its OpenTelemetry backend. T | Package | Role | |---|---| -| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | The seam: capture points, projection, redaction, immediate or held handoff, cursor, ops signals, and the minimal backend contract (`emit`/`flush?`/`shutdown`). | +| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | The seam: capture points, projection, redaction, live or on-demand capture, cursor, ops signals, and the minimal backend contract (`emit`/`flush?`/`shutdown`). | | [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | The backend a deployment loads: `FULL`, `FEEDBACK_ONLY`, or `DISABLED` policy around the OTel JS SDK log pipeline. | diff --git a/packages/telemetry/README.zh.md b/packages/telemetry/README.zh.md index 57988732e3..6863ca56d4 100644 --- a/packages/telemetry/README.zh.md +++ b/packages/telemetry/README.zh.md @@ -6,5 +6,5 @@ | 包（package） | 职责 | |---|---| -| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | seam 本体：捕获点、投影、脱敏、即时或暂存交接、游标、运维信号，以及最小后端契约（`emit`/`flush?`/`shutdown`）。 | +| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | seam 本体：捕获点、投影、脱敏、实时或按需捕获、游标、运维信号，以及最小后端契约（`emit`/`flush?`/`shutdown`）。 | | [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | 部署方要加载的后端：围绕 OTel JS SDK 日志流水线实施 `FULL`、`FEEDBACK_ONLY` 或 `DISABLED` 策略。 | From b10368a8d53d8cafb1ee991c4b1b9519b8271403 Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 6 Aug 2026 15:34:36 +0800 Subject: [PATCH 13/22] refactor(telemetry): strongly type sharing mode --- ...feedback-gated-session-telemetry.i18n.yaml | 4 +-- ...-08-05-feedback-gated-session-telemetry.md | 2 +- ...-05-feedback-gated-session-telemetry.zh.md | 2 +- docs/config-catalog.md | 8 ++++-- .../tests/gen-config-catalog.spec.ts | 23 ++++++++++++++++ .../session-telemetry-otel/README.i18n.yaml | 4 +-- .../session-telemetry-otel/README.md | 2 ++ .../session-telemetry-otel/README.zh.md | 2 ++ .../session-telemetry-otel/src/index.ts | 26 ++++++++++++------- .../session-telemetry-otel/tests/otel.spec.ts | 18 ++++++++----- scripts/gen-config-catalog.ts | 9 ++++--- 11 files changed, 73 insertions(+), 27 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml index 7909316acd..331b2e97c6 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md -2026-08-05-feedback-gated-session-telemetry.md: 25cc17f75629f72d7351eb0537d72b700c84411f -2026-08-05-feedback-gated-session-telemetry.zh.md: b0e84e60e27fa20f66113c11db62026583a27a19 +2026-08-05-feedback-gated-session-telemetry.md: 00a8f23fa6bf69f10277ad0d9f2513a0df73de16 +2026-08-05-feedback-gated-session-telemetry.zh.md: 888ce48abe7a5ce2212c152730f8203f5747ef41 diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md index 25cc17f756..00a8f23fa6 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md @@ -10,7 +10,7 @@ Session telemetry originally has one mounted behavior: every accepted record ent ## Decision -`@deepseek-ai/dsh-session-telemetry-otel` exposes three uppercase `mode` values: +`@deepseek-ai/dsh-session-telemetry-otel` exposes the string-valued `TelemetryMode` enum to TypeScript callers and accepts the same three uppercase `mode` values in serialized configuration: - `FULL` is the default and preserves immediate delivery to the configured OTel pipeline. - `FEEDBACK_ONLY` reads the canonical session log when `feedback/record` is appended and hands over the unreleased prefix through that exact event. Records appended after that boundary remain local until another feedback event. diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md index b0e84e60e2..888ce48abe 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md @@ -10,7 +10,7 @@ Status: implemented ## 决策 -`@deepseek-ai/dsh-session-telemetry-otel` 公开三个大写的 `mode` 值： +`@deepseek-ai/dsh-session-telemetry-otel` 向 TypeScript 调用方公开以字符串为值的 `TelemetryMode` 枚举，并在序列化配置中接受相同的三个大写 `mode` 值： - `FULL` 是默认值，保留向已配置 OTel 流水线的即时投递。 - `FEEDBACK_ONLY` 在追加 `feedback/record` 时读取权威会话日志，并交接截至该事件的未释放前缀。该边界后追加的记录会留在本地，直到另一个反馈事件。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a4ddedab35..a2f82d2bec 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1184,12 +1184,16 @@ export interface Config { } /** Session-sharing policy selected by {@link Config.mode}. */ -export type TelemetryMode = typeof TELEMETRY_MODES[number] +export enum TelemetryMode { + FULL = 'FULL', + FEEDBACK_ONLY = 'FEEDBACK_ONLY', + DISABLED = 'DISABLED', +} ``` Depends on: `BatchLogRecordProcessorOptions` (`@opentelemetry/sdk-logs`) · `OTLPExporterNodeConfigBase` (`@opentelemetry/otlp-exporter-base`) -Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:55`](../packages/telemetry/session-telemetry-otel/src/index.ts) +Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:63`](../packages/telemetry/session-telemetry-otel/src/index.ts) ## `@deepseek-ai/dsh-session-title` diff --git a/packages/examples/agent-spine-demo/tests/gen-config-catalog.spec.ts b/packages/examples/agent-spine-demo/tests/gen-config-catalog.spec.ts index 65a6f6b9ff..ae4966fd12 100644 --- a/packages/examples/agent-spine-demo/tests/gen-config-catalog.spec.ts +++ b/packages/examples/agent-spine-demo/tests/gen-config-catalog.spec.ts @@ -160,6 +160,29 @@ export function apply(ctx: Context, config: Config): void {} expect(entries[0]?.refs).toEqual([{ alias: 'Remote', imported: 'Remote', specifier: '@fix/dep' }]) }) + it('pastes an enum referenced by the config type', () => { + const entries = collectConfigCatalog(make({ + 'src/index.ts': `import type { Context } from 'cordis' +/** Fixture mode. */ +export enum Mode { + A = 'a', + B = 'b', +} +/** Fixture config. */ +export interface Config { + /** The mode. */ + mode?: Mode +} +/** Load. */ +export function apply(ctx: Context, config: Config): void {} +`, + })) + expect(entries[0]?.pastes?.map(p => p.text)).toEqual([ + '/** Fixture config. */\nexport interface Config {\n /** The mode. */\n mode?: Mode\n}', + "/** Fixture mode. */\nexport enum Mode {\n A = 'a',\n B = 'b',\n}", + ]) + }) + it('hard-errors on a referenced type name that resolves nowhere', () => { expect(() => collectConfigCatalog(make({ 'src/index.ts': `import type { Context } from 'cordis' diff --git a/packages/telemetry/session-telemetry-otel/README.i18n.yaml b/packages/telemetry/session-telemetry-otel/README.i18n.yaml index 84e2447fd8..5a6bd9bc9d 100644 --- a/packages/telemetry/session-telemetry-otel/README.i18n.yaml +++ b/packages/telemetry/session-telemetry-otel/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/telemetry/session-telemetry-otel/README.md -README.md: 7fc5572614a5bdba312ba97b52606032ef8f5394 -README.zh.md: 3160b67c8225fb87d5e7be2e43453ef40496fba9 +README.md: 01d803236329afbe65e2d92960928441aaff301c +README.zh.md: 8adf4a3c11b95dc302f8afd0dc79e99433e50f22 diff --git a/packages/telemetry/session-telemetry-otel/README.md b/packages/telemetry/session-telemetry-otel/README.md index 7fc5572614..01d8032363 100644 --- a/packages/telemetry/session-telemetry-otel/README.md +++ b/packages/telemetry/session-telemetry-otel/README.md @@ -24,6 +24,8 @@ The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — th | `FEEDBACK_ONLY` | Each `feedback/record` replays, projects, and redacts the canonical session-log suffix through that event. Later records wait for another feedback event and remain local if none arrives. | | `DISABLED` | No coordinator, provider, processor, or exporter is constructed. No telemetry record leaves the process. A `feedback/record` logs `session telemetry is DISABLED; nothing will be shared and this feedback remains local`; the event remains in the local session log. | +Programmatic TypeScript configuration uses the exported `TelemetryMode` enum (`TelemetryMode.FULL`, `TelemetryMode.FEEDBACK_ONLY`, or `TelemetryMode.DISABLED`); raw string literals are not assignable. Serialized Cordis configuration continues to use the string values shown above. + `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`, has no default, and must parse as `http(s)`; it is optional and unused in `DISABLED`. Uploading modes also reject a non-positive-integer `processor.maxExportBatchSize`, which the SDK accepts but then hangs on at shutdown. Everything else is the SDK's option shape, owned and documented by the SDK, and both blocks pass through whole: every `OTLPExporterNodeConfigBase` field (`headers`, `timeoutMillis`, `compression`, `keepAlive`, …) reaches the exporter, and batching, export cadence (`scheduledDelayMillis`), retry, queue bounds, and loss policy under sustained failure are the SDK's documented behavior, tuned through the `processor` passthrough. The backend deliberately implements no `flush()`: the batch processor is the only flusher in the process, which is what makes `shutdown()`'s drain complete. ## What leaves the machine diff --git a/packages/telemetry/session-telemetry-otel/README.zh.md b/packages/telemetry/session-telemetry-otel/README.zh.md index 3160b67c82..8adf4a3c11 100644 --- a/packages/telemetry/session-telemetry-otel/README.zh.md +++ b/packages/telemetry/session-telemetry-otel/README.zh.md @@ -24,6 +24,8 @@ | `FEEDBACK_ONLY` | 每个 `feedback/record` 都会回放权威会话日志中截至该事件的后缀，并进行投影与脱敏。后续记录等待下一个反馈事件；如果没有后续反馈，则留在本地。 | | `DISABLED` | 不构造协调器、提供方、处理器或导出器。没有遥测记录会离开进程。`feedback/record` 会记录 `session telemetry is DISABLED; nothing will be shared and this feedback remains local`；该事件留在本地会话日志中。 | +程序化 TypeScript 配置使用导出的 `TelemetryMode` 枚举（`TelemetryMode.FULL`、`TelemetryMode.FEEDBACK_ONLY` 或 `TelemetryMode.DISABLED`）；原始字符串字面量不可赋值。序列化后的 Cordis 配置继续使用上表所示的字符串值。 + `exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填，无默认值，且必须能解析为 `http(s)`；在 `DISABLED` 中可省略且不使用。上传模式也会拒绝不是正整数的 `processor.maxExportBatchSize`，SDK 虽会接受该值，但随后会在关闭时挂起。其余全部是 SDK 自己的选项形态，由 SDK 拥有并在 SDK 文档中说明，两个配置块都整体透传（passthrough）：`OTLPExporterNodeConfigBase` 的每个字段（`headers`、`timeoutMillis`、`compression`、`keepAlive` 等）都会到达导出器；批处理、导出节奏（`scheduledDelayMillis`）、重试、队列上限，以及持续失败下的丢失策略，都是 SDK 的文档化行为，经 `processor` 透传调优。该后端刻意不实现 `flush()`：批处理器是进程内唯一执行 flush 的组件，`shutdown()` 的排空正因如此才是完整的。 ## 哪些数据会离开本机 diff --git a/packages/telemetry/session-telemetry-otel/src/index.ts b/packages/telemetry/session-telemetry-otel/src/index.ts index 908f0f90fb..95991cb932 100644 --- a/packages/telemetry/session-telemetry-otel/src/index.ts +++ b/packages/telemetry/session-telemetry-otel/src/index.ts @@ -39,11 +39,19 @@ import { resourceFromAttributes } from '@opentelemetry/resources' // version (same pattern as dsh-llm's attribution identity). const { version } = createRequire(import.meta.url)('../package.json') as { version: string } -/** Supported session-sharing policies for the OTel backend. */ -export const TELEMETRY_MODES = ['FULL', 'FEEDBACK_ONLY', 'DISABLED'] as const - /** Session-sharing policy selected by {@link Config.mode}. */ -export type TelemetryMode = typeof TELEMETRY_MODES[number] +export enum TelemetryMode { + FULL = 'FULL', + FEEDBACK_ONLY = 'FEEDBACK_ONLY', + DISABLED = 'DISABLED', +} + +/** Supported session-sharing policies for runtime configuration validation. */ +export const TELEMETRY_MODES = [ + TelemetryMode.FULL, + TelemetryMode.FEEDBACK_ONLY, + TelemetryMode.DISABLED, +] as const const DISABLED_FEEDBACK_WARNING = 'session telemetry is DISABLED; nothing will be shared and this feedback remains local' @@ -81,7 +89,7 @@ export interface Config { * axiom (and silently drop every field not re-declared). */ export const Config: z = z.object({ - mode: z.union(TELEMETRY_MODES).default('FULL'), + mode: z.union(TELEMETRY_MODES).default(TelemetryMode.FULL), exporter: z.any(), processor: z.any(), }) @@ -109,8 +117,8 @@ export class TelemetryOtel extends Telemetry { constructor(ctx: Context, config: Config) { super(ctx) - const mode = config.mode ?? 'FULL' - if (mode === 'DISABLED') { + const mode = config.mode ?? TelemetryMode.FULL + if (mode === TelemetryMode.DISABLED) { this.provider = undefined this.ledger = undefined this.ops = undefined @@ -162,9 +170,9 @@ export class TelemetryOtel extends Telemetry { }) this.ledger = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel', version) this.ops = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel/ops', version) - const capture: TelemetryCapture = mode === 'FULL' ? 'live' : 'on-demand' + const capture: TelemetryCapture = mode === TelemetryMode.FULL ? 'live' : 'on-demand' const coordinator = new TelemetryCoordinator(ctx, this, capture) - if (mode === 'FEEDBACK_ONLY') { + if (mode === TelemetryMode.FEEDBACK_ONLY) { // Session.append commits before publishing `session/event`, so the // canonical log already includes this feedback record when replay begins. ctx.on('session/event', (session, event) => { diff --git a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts index 9b7e4119b7..26118e4672 100644 --- a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts +++ b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts @@ -5,7 +5,7 @@ * for the default-exported Service class. */ -import { afterEach, describe, expect, it, vi } from 'vitest' +import { afterEach, describe, expect, expectTypeOf, it, vi } from 'vitest' import { createServer, type Server } from 'node:http' import { once } from 'node:events' import { gunzipSync } from 'node:zlib' @@ -13,7 +13,7 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { recordFeedback } from '@deepseek-ai/dsh-command-feedback' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' -import TelemetryOtel, { Config } from '../src/index.ts' +import TelemetryOtel, { Config, TelemetryMode } from '../src/index.ts' interface Capture { headers: import('node:http').IncomingHttpHeaders @@ -211,7 +211,7 @@ describe('TelemetryOtel wire', () => { const ctx = new Context() await ctx.plugin(SessionStore) const fiber = await ctx.plugin(TelemetryOtel, { - mode: 'FEEDBACK_ONLY', + mode: TelemetryMode.FEEDBACK_ONLY, exporter: { url }, }) const session = ctx.sessions.create(SessionId('feedback-only'), { meta: {} }) @@ -236,7 +236,7 @@ describe('TelemetryOtel wire', () => { const ctx = new Context() await ctx.plugin(SessionStore) const fiber = await ctx.plugin(TelemetryOtel, { - mode: 'FEEDBACK_ONLY', + mode: TelemetryMode.FEEDBACK_ONLY, exporter: { url }, }) const session = ctx.sessions.create(SessionId('no-feedback'), { meta: {} }) @@ -249,7 +249,7 @@ describe('TelemetryOtel wire', () => { const ctx = new Context() await ctx.plugin(SessionStore) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) - const fiber = await ctx.plugin(TelemetryOtel, { mode: 'DISABLED' }) + const fiber = await ctx.plugin(TelemetryOtel, { mode: TelemetryMode.DISABLED }) const session = ctx.sessions.create(SessionId('disabled'), { meta: {} }) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) recordFeedback(session, 'local report') @@ -284,12 +284,18 @@ describe('TelemetryOtel wire', () => { }) describe('TelemetryOtel config fails loud', () => { + it('exposes modes through the nominal enum', () => { + expectTypeOf().toEqualTypeOf() + expectTypeOf<'FULL'>().not.toExtend() + expectTypeOf().toExtend() + }) + it.each([ [{}, /exporter\.url is required/], [{ exporter: { url: '' } }, /exporter\.url is required/], [{ exporter: { url: 'not a url' } }, /not a valid URL/], [{ exporter: { url: 'ftp://collector' } }, /must be http\(s\)/], - [{ mode: 'FEEDBACK_ONLY' }, /exporter\.url is required/], + [{ mode: TelemetryMode.FEEDBACK_ONLY }, /exporter\.url is required/], [{ mode: 'INVALID' }, /INVALID/], // The SDK accepts a non-positive batch size but its shutdown drain then // splices empty batches forever — dispose would hang, so reject at load. diff --git a/scripts/gen-config-catalog.ts b/scripts/gen-config-catalog.ts index b4c20d596a..920688df6d 100644 --- a/scripts/gen-config-catalog.ts +++ b/scripts/gen-config-catalog.ts @@ -126,12 +126,13 @@ function loadFile(abs: string, rel: string, cache: Map): FileCt } /** A type declaration a paste can contain. */ -type TypeDecl = ts.InterfaceDeclaration | ts.TypeAliasDeclaration +type TypeDecl = ts.InterfaceDeclaration | ts.TypeAliasDeclaration | ts.EnumDeclaration -/** Find an interface/type-alias declaration by name in a file, or null. */ +/** Find a pasteable type declaration by name in a file, or null. */ function findTypeDecl(ctx: FileCtx, name: string): TypeDecl | null { for (const stmt of ctx.sf.statements) { - if ((ts.isInterfaceDeclaration(stmt) || ts.isTypeAliasDeclaration(stmt)) && stmt.name.text === name) return stmt + if ((ts.isInterfaceDeclaration(stmt) || ts.isTypeAliasDeclaration(stmt) || ts.isEnumDeclaration(stmt)) + && stmt.name.text === name) return stmt } return null } @@ -207,7 +208,7 @@ function checkMemberDocs(ctx: FileCtx, decl: TypeDecl, violations: string[]): vo else ts.forEachChild(type, (n) => { walkNested(n, path) }) } if (ts.isInterfaceDeclaration(decl)) walkMembers(decl.members, decl.name.text) - else walkNested(decl.type, decl.name.text) + else if (ts.isTypeAliasDeclaration(decl)) walkNested(decl.type, decl.name.text) } /** Cross-file resolution context for the schema-path check. */ From 9db4372af80230b9c4be533d068bb07005eddd6b Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 6 Aug 2026 16:15:58 +0800 Subject: [PATCH 14/22] fix: align feedback package publication files --- packages/feedback/command-feedback/package.json | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/packages/feedback/command-feedback/package.json b/packages/feedback/command-feedback/package.json index 25bc8446c3..535c438a63 100644 --- a/packages/feedback/command-feedback/package.json +++ b/packages/feedback/command-feedback/package.json @@ -21,9 +21,7 @@ "files": [ "lib/index.js", "lib/invariant.js", - "lib/types/**/*.d.ts", - "lib/types/**/*.d.ts.map", - "src" + "lib/types/**/*.d.ts" ], "license": "BSD-3-Clause", "peerDependencies": { From ccb0842cfcc23ca11a89c136761e355eb0c94741 Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 6 Aug 2026 16:27:27 +0800 Subject: [PATCH 15/22] fix(telemetry): fail closed outside full mode --- ...feedback-gated-session-telemetry.i18n.yaml | 4 +- ...-08-05-feedback-gated-session-telemetry.md | 6 +- ...-05-feedback-gated-session-telemetry.zh.md | 6 +- docs/config-catalog.md | 2 +- .../session-telemetry-otel/README.i18n.yaml | 4 +- .../session-telemetry-otel/README.md | 2 + .../session-telemetry-otel/README.zh.md | 2 + .../session-telemetry-otel/src/index.ts | 91 +++++++++++++------ .../session-telemetry-otel/tests/otel.spec.ts | 64 ++++++++++++- 9 files changed, 139 insertions(+), 42 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml index 331b2e97c6..4255886987 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md -2026-08-05-feedback-gated-session-telemetry.md: 00a8f23fa6bf69f10277ad0d9f2513a0df73de16 -2026-08-05-feedback-gated-session-telemetry.zh.md: 888ce48abe7a5ce2212c152730f8203f5747ef41 +2026-08-05-feedback-gated-session-telemetry.md: 7d923a7e4cf61e8d1119187564b87e4cbb2065b7 +2026-08-05-feedback-gated-session-telemetry.zh.md: 2862162c0c36e5194846c7e1c7bbc24230ce90aa diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md index 00a8f23fa6..7d923a7e4c 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md @@ -18,7 +18,7 @@ Session telemetry originally has one mounted behavior: every accepted record ent The generic telemetry coordinator owns `live` and `on-demand` capture. Live capture projects, clones, redacts, and hands each event to the backend on the session firehose. On-demand capture registers no continuous capture listeners; `captureSession(session, throughSeq)` reads the canonical log from the handoff cursor through an inclusive boundary, then projects, clones, redacts, and hands over that prefix. The cursor advances only for handed-over records. The [buffer-free replay decision](../simplification/2026-08-06-buffer-free-feedback-telemetry.md) owns why the on-demand path uses the canonical log instead of copied records. -The OTel feedback listener passes the feedback event's sequence to `captureSession()`. `Session.append` commits the event before publishing `session/event`, so replay includes that feedback but cannot extend past its boundary. `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`; `DISABLED` does not validate or use exporter configuration. +Mode resolution is a closed, fail-before-setup check: an unknown direct-construction value fails before transport configuration is read. Only `FULL` exposes the public service's `emit()` path to the SDK pipeline. `FEEDBACK_ONLY` gives its on-demand coordinator a private backend capability; its listener passes an event to `captureSession()` only when the exact `feedback/record` object is already stored at `session.events[event.seq]`. `Session.append` commits that object before publishing `session/event`, so replay includes the feedback but cannot extend past its boundary. `DISABLED` creates neither the capability nor the SDK pipeline and does not inspect exporter configuration. ## Alternatives considered @@ -26,8 +26,10 @@ The OTel feedback listener passes the feedback event's sequence to `captureSessi **Retain capture-time redacted records until feedback.** Rejected because it duplicates an unbounded session prefix even though the canonical log already owns the events. It preserves capture-time redaction policy and operational records, but those properties do not justify the memory cost for a mode defined as uploading the session log after feedback. +**Temporarily allow public `emit()` calls during feedback replay.** Rejected because a redaction listener or another reentrant caller could enqueue an unrelated record while the flag was open. A private backend capability makes authorization structural and keeps the public service closed throughout replay. + **Use an unmounted plugin as the disabled state.** That remains the silent opt-out, but it cannot warn when feedback is recorded. The explicit disabled mode lets a deployment keep one configuration shape and communicate that the local feedback did not leave the process. ## Consequences -`FULL` remains source- and wire-compatible with the original default. `FEEDBACK_ONLY` adds no telemetry-owned per-event buffer before feedback; a crash before feedback uploads nothing from that prefix. Replay applies the redaction policy mounted when feedback is recorded and excludes operational records that do not exist in the canonical log. Feedback-only streams therefore carry neither `agent-error` nor `shutdown` records, and shutdown absence is not a crash signal. Each later feedback captures the suffix accumulated since the previous boundary. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log. +`FULL` remains source- and wire-compatible with the original default. `FEEDBACK_ONLY` adds no telemetry-owned per-event buffer before feedback; direct service calls and non-canonical feedback events upload nothing, and a crash before feedback uploads nothing from that prefix. Replay applies the redaction policy mounted when feedback is recorded and excludes operational records that do not exist in the canonical log. Feedback-only streams therefore carry neither `agent-error` nor `shutdown` records, and shutdown absence is not a crash signal. Each later feedback captures the suffix accumulated since the previous boundary. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log. diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md index 888ce48abe..2862162c0c 100644 --- a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md @@ -18,7 +18,7 @@ Status: implemented 通用遥测协调器拥有 `live` 与 `on-demand` 捕获。实时捕获在会话 firehose 上投影、深拷贝、脱敏每个事件，并将其交给后端。按需捕获不注册持续捕获监听器；`captureSession(session, throughSeq)` 从 handoff 游标起读取权威日志，直至含边界的指定序列号，然后投影、深拷贝、脱敏并交接该前缀。游标只为已交接记录推进。[无缓冲回放决策](../simplification/2026-08-06-buffer-free-feedback-telemetry.md)说明了按需路径为何使用权威日志而非记录副本。 -OTel 反馈监听器把反馈事件的序列号传给 `captureSession()`。`Session.append` 在发布 `session/event` 前已提交该事件，因此回放会包含该反馈，但不会超过其边界。`exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填；`DISABLED` 不校验也不使用导出器配置。 +模式解析采用封闭式检查，并在设置前失败：通过直接构造传入未知值时，会在读取传输配置前失败。只有 `FULL` 向 SDK 流水线开放公共服务的 `emit()` 路径。`FEEDBACK_ONLY` 向其按需协调器提供私有后端能力；其监听器向 `captureSession()` 传递事件的唯一条件，是该事件与那个 `feedback/record` 对象身份完全相同，且该对象已存储于 `session.events[event.seq]`。`Session.append` 在发布 `session/event` 前已提交该对象，因此回放包含该反馈，但不会越过其边界。`DISABLED` 既不创建该能力，也不创建 SDK 流水线，并且不检查导出器配置。 ## 考虑过的替代方案 @@ -26,8 +26,10 @@ OTel 反馈监听器把反馈事件的序列号传给 `captureSession()`。`Sess **反馈前保留捕获时已脱敏记录。** 已否决，因为权威日志已拥有这些事件，该方案仍会复制无上限的会话前缀。它能保留捕获时的脱敏策略与运维记录，但对于一个定义为「反馈后上传会话日志」的模式，这些性质不足以证明该内存成本合理。 +**在反馈回放期间临时允许公开 `emit()` 调用。** 已否决，因为在标志开启期间，脱敏监听器或另一个可重入调用方可能将无关记录入队。私有后端能力使授权成为结构性保证，并确保公共服务在整个回放过程中保持关闭。 + **以不挂载插件表示禁用状态。** 这仍然是静默退出方式，但无法在记录反馈时输出警告。显式禁用模式让部署方可以保持同一种配置形态，并说明本地反馈未离开进程。 ## 后果 -`FULL` 与原有默认值保持源码及协议兼容。`FEEDBACK_ONLY` 在反馈前不增加遥测自有的逐事件缓冲；反馈前发生崩溃时，该前缀不上传任何内容。回放使用记录反馈时挂载的脱敏策略，并排除权威日志中不存在的运维记录。因此，仅反馈的流既不携带 `agent-error` 记录，也不携带 `shutdown` 记录，而缺少 shutdown 不是崩溃信号。每个后续反馈都会捕获从上一个边界起累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。 +`FULL` 与原有默认值保持源码及协议兼容。`FEEDBACK_ONLY` 在反馈前不增加遥测自有的逐事件缓冲；直接服务调用与非权威反馈事件均不上传任何内容，且反馈前发生崩溃时，该前缀也不上传任何内容。回放使用记录反馈时挂载的脱敏策略，并排除权威日志中不存在的运维记录。因此，仅反馈的流既不携带 `agent-error` 记录，也不携带 `shutdown` 记录，而缺少 shutdown 不是崩溃信号。每个后续反馈都会捕获从上一个边界起累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a2f82d2bec..c386ee4e6b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1193,7 +1193,7 @@ export enum TelemetryMode { Depends on: `BatchLogRecordProcessorOptions` (`@opentelemetry/sdk-logs`) · `OTLPExporterNodeConfigBase` (`@opentelemetry/otlp-exporter-base`) -Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:63`](../packages/telemetry/session-telemetry-otel/src/index.ts) +Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:83`](../packages/telemetry/session-telemetry-otel/src/index.ts) ## `@deepseek-ai/dsh-session-title` diff --git a/packages/telemetry/session-telemetry-otel/README.i18n.yaml b/packages/telemetry/session-telemetry-otel/README.i18n.yaml index 5a6bd9bc9d..ec7fddf6b4 100644 --- a/packages/telemetry/session-telemetry-otel/README.i18n.yaml +++ b/packages/telemetry/session-telemetry-otel/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/telemetry/session-telemetry-otel/README.md -README.md: 01d803236329afbe65e2d92960928441aaff301c -README.zh.md: 8adf4a3c11b95dc302f8afd0dc79e99433e50f22 +README.md: af177dc86bc30a7b17e34e3c8c3592326b9026f2 +README.zh.md: 9a3ad628bb7d480a1c4cd8346669ad8ebbd6258f diff --git a/packages/telemetry/session-telemetry-otel/README.md b/packages/telemetry/session-telemetry-otel/README.md index 01d8032363..af177dc86b 100644 --- a/packages/telemetry/session-telemetry-otel/README.md +++ b/packages/telemetry/session-telemetry-otel/README.md @@ -26,6 +26,8 @@ The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — th Programmatic TypeScript configuration uses the exported `TelemetryMode` enum (`TelemetryMode.FULL`, `TelemetryMode.FEEDBACK_ONLY`, or `TelemetryMode.DISABLED`); raw string literals are not assignable. Serialized Cordis configuration continues to use the string values shown above. +Upload authorization is positive and fail-closed. An unknown direct-construction mode fails before transport configuration is read. Only `FULL` accepts direct `ctx.telemetry.emit()` calls. `FEEDBACK_ONLY` gives its on-demand coordinator a private backend capability and treats only the exact `feedback/record` object already stored at `session.events[event.seq]` as consent; an independently emitted bus value is ignored. `DISABLED` never constructs the SDK pipeline, even when exporter options are present. + `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`, has no default, and must parse as `http(s)`; it is optional and unused in `DISABLED`. Uploading modes also reject a non-positive-integer `processor.maxExportBatchSize`, which the SDK accepts but then hangs on at shutdown. Everything else is the SDK's option shape, owned and documented by the SDK, and both blocks pass through whole: every `OTLPExporterNodeConfigBase` field (`headers`, `timeoutMillis`, `compression`, `keepAlive`, …) reaches the exporter, and batching, export cadence (`scheduledDelayMillis`), retry, queue bounds, and loss policy under sustained failure are the SDK's documented behavior, tuned through the `processor` passthrough. The backend deliberately implements no `flush()`: the batch processor is the only flusher in the process, which is what makes `shutdown()`'s drain complete. ## What leaves the machine diff --git a/packages/telemetry/session-telemetry-otel/README.zh.md b/packages/telemetry/session-telemetry-otel/README.zh.md index 8adf4a3c11..9a3ad628bb 100644 --- a/packages/telemetry/session-telemetry-otel/README.zh.md +++ b/packages/telemetry/session-telemetry-otel/README.zh.md @@ -26,6 +26,8 @@ 程序化 TypeScript 配置使用导出的 `TelemetryMode` 枚举（`TelemetryMode.FULL`、`TelemetryMode.FEEDBACK_ONLY` 或 `TelemetryMode.DISABLED`）；原始字符串字面量不可赋值。序列化后的 Cordis 配置继续使用上表所示的字符串值。 +上传授权采用显式许可，且为 fail-closed。通过直接构造传入未知模式时，会在读取传输配置前失败。只有 `FULL` 接受对 `ctx.telemetry.emit()` 的直接调用。`FEEDBACK_ONLY` 向其按需协调器提供私有后端能力，并且仅在 `feedback/record` 对象已经存储于 `session.events[event.seq]` 且对象身份完全相同时，才将其视为同意；独立发出的总线值会被忽略。即使存在导出器选项，`DISABLED` 也绝不会构造 SDK 流水线。 + `exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填，无默认值，且必须能解析为 `http(s)`；在 `DISABLED` 中可省略且不使用。上传模式也会拒绝不是正整数的 `processor.maxExportBatchSize`，SDK 虽会接受该值，但随后会在关闭时挂起。其余全部是 SDK 自己的选项形态，由 SDK 拥有并在 SDK 文档中说明，两个配置块都整体透传（passthrough）：`OTLPExporterNodeConfigBase` 的每个字段（`headers`、`timeoutMillis`、`compression`、`keepAlive` 等）都会到达导出器；批处理、导出节奏（`scheduledDelayMillis`）、重试、队列上限，以及持续失败下的丢失策略，都是 SDK 的文档化行为，经 `processor` 透传调优。该后端刻意不实现 `flush()`：批处理器是进程内唯一执行 flush 的组件，`shutdown()` 的排空正因如此才是完整的。 ## 哪些数据会离开本机 diff --git a/packages/telemetry/session-telemetry-otel/src/index.ts b/packages/telemetry/session-telemetry-otel/src/index.ts index 95991cb932..f380d97549 100644 --- a/packages/telemetry/session-telemetry-otel/src/index.ts +++ b/packages/telemetry/session-telemetry-otel/src/index.ts @@ -20,7 +20,7 @@ import type {} from '@deepseek-ai/dsh-command-feedback' import { Telemetry, TelemetryCoordinator, - type TelemetryCapture, + type TelemetryBackend, type TelemetryRecord, type TelemetrySeverity, } from '@deepseek-ai/dsh-session-telemetry' @@ -54,6 +54,26 @@ export const TELEMETRY_MODES = [ ] as const const DISABLED_FEEDBACK_WARNING = 'session telemetry is DISABLED; nothing will be shared and this feedback remains local' +const NON_CANONICAL_FEEDBACK_WARNING = 'session telemetry ignored a feedback event absent from the canonical session log' +const DROP_RECORD: TelemetryBackend['emit'] = () => {} + +/** Resolve the default and reject unknown runtime values before transport setup. */ +function resolveMode(mode: TelemetryMode | undefined): TelemetryMode { + const resolved = mode ?? TelemetryMode.FULL + switch (resolved) { + case TelemetryMode.FULL: + case TelemetryMode.FEEDBACK_ONLY: + case TelemetryMode.DISABLED: + return resolved + default: + return assertNever(resolved) + } +} + +/** Fail closed when direct construction bypasses the runtime config schema. */ +function assertNever(value: never): never { + throw new Error(`session-telemetry-otel: unsupported mode ${JSON.stringify(value)}`) +} /** * Plugin configuration: one sharing policy plus two verbatim SDK option @@ -111,17 +131,15 @@ export class TelemetryOtel extends Telemetry { static inject = ['sessions'] static Config = Config + private readonly directEmit: TelemetryBackend['emit'] private readonly provider: LoggerProvider | undefined - private readonly ledger: Logger | undefined - private readonly ops: Logger | undefined constructor(ctx: Context, config: Config) { + const mode = resolveMode(config.mode) super(ctx) - const mode = config.mode ?? TelemetryMode.FULL if (mode === TelemetryMode.DISABLED) { + this.directEmit = DROP_RECORD this.provider = undefined - this.ledger = undefined - this.ops = undefined ctx.on('session/event', (_session, event) => { if (event.type === 'feedback/record') ctx.logger.warn(DISABLED_FEEDBACK_WARNING) }) @@ -168,37 +186,50 @@ export class TelemetryOtel extends Telemetry { }), ], }) - this.ledger = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel', version) - this.ops = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel/ops', version) - const capture: TelemetryCapture = mode === TelemetryMode.FULL ? 'live' : 'on-demand' - const coordinator = new TelemetryCoordinator(ctx, this, capture) - if (mode === TelemetryMode.FEEDBACK_ONLY) { - // Session.append commits before publishing `session/event`, so the - // canonical log already includes this feedback record when replay begins. - ctx.on('session/event', (session, event) => { - if (event.type === 'feedback/record') coordinator.captureSession(session, event.seq) + const ledger = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel', version) + const ops = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel/ops', version) + const enqueue: TelemetryBackend['emit'] = (record) => { + const logger: Logger = record.channel === 'ops' ? ops : ledger + logger.emit({ + timestamp: record.time, + observedTimestamp: record.time, + ...SEVERITY[record.severity], + // JSON-serializable by the seam's contract (validated at Session.append), + // which is exactly the AnyValue subset. + body: record.body as AnyValue, + attributes: record.attributes, }) } + const backend: TelemetryBackend = { + emit: enqueue, + shutdown: () => this.shutdown(), + } + if (mode === TelemetryMode.FULL) { + this.directEmit = enqueue + new TelemetryCoordinator(ctx, backend, 'live') + return + } + this.directEmit = DROP_RECORD + const coordinator = new TelemetryCoordinator(ctx, backend, 'on-demand') + ctx.on('session/event', (session, event) => { + if (event.type !== 'feedback/record') return + // Consent is the committed record, not an independently emitted bus value. + if (session.events[event.seq] !== event) { + ctx.logger.warn(NON_CANONICAL_FEEDBACK_WARNING) + return + } + coordinator.captureSession(session, event.seq) + }) } /** - * Map one seam record onto the SDK logger for its channel — a synchronous - * enqueue into the batch processor's queue. Direct calls are no-ops in - * `DISABLED`, where no coordinator or SDK pipeline exists. - * @param record - the logical record handed over by the coordinator. + * Hand a direct service record to the SDK only in `FULL`. Direct calls are + * no-ops in `FEEDBACK_ONLY` and `DISABLED`; feedback replay uses a private + * backend capability created only for the canonical feedback listener. + * @param record - the logical record offered directly to the service. */ emit(record: TelemetryRecord): void { - const logger = record.channel === 'ops' ? this.ops : this.ledger - if (logger === undefined) return - logger.emit({ - timestamp: record.time, - observedTimestamp: record.time, - ...SEVERITY[record.severity], - // JSON-serializable by the seam's contract (validated at Session.append), - // which is exactly the AnyValue subset. - body: record.body as AnyValue, - attributes: record.attributes, - }) + this.directEmit(record) } // The seam's optional flush() hint is deliberately NOT implemented. The diff --git a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts index 26118e4672..f7b3a007c9 100644 --- a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts +++ b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts @@ -105,6 +105,13 @@ describe('TelemetryOtel wire', () => { const session = ctx.sessions.create(SessionId('wire'), { meta: { cwd: '/tmp/w' } }) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('turn/end', { turn: 1, reason: { kind: 'error', step: 1, message: 'boom' } }) + ctx.telemetry.emit({ + channel: 'ledger', + time: Date.now(), + severity: 'info', + attributes: { 'session.id': 'wire', 'event.type': 'manual', 'event.seq': 99 }, + body: { direct: true }, + }) await fiber.dispose() expect(captures.length).toBeGreaterThan(0) @@ -128,6 +135,7 @@ describe('TelemetryOtel wire', () => { const end = ledger.find(r => r.record.attributes?.some(a => a.key === 'event.type' && a.value.stringValue === 'turn/end')) expect(end?.record.severityNumber).toBe(17) expect(end?.record.severityText).toBe('ERROR') + expect(eventTypes(captures)).toContain('manual') expect(ops).toHaveLength(1) expect(ops[0]!.record.attributes).toContainEqual({ key: 'telemetry.op', value: { stringValue: 'shutdown' } }) @@ -214,6 +222,16 @@ describe('TelemetryOtel wire', () => { mode: TelemetryMode.FEEDBACK_ONLY, exporter: { url }, }) + ctx.on('telemetry/record', (_record, next) => { + ctx.telemetry.emit({ + channel: 'ledger', + time: Date.now(), + severity: 'info', + attributes: { 'session.id': 'feedback-only', 'event.type': 'direct-bypass', 'event.seq': 99 }, + body: { mustStayLocal: true }, + }) + return next() + }) const session = ctx.sessions.create(SessionId('feedback-only'), { meta: {} }) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) recordFeedback(session, 'first report') @@ -231,25 +249,48 @@ describe('TelemetryOtel wire', () => { expect(allRecords(captures).some(({ scope }) => scope.endsWith('/ops'))).toBe(false) }) - it('sends no request when feedback-only mode ends without feedback', async () => { + it('ignores direct emits and non-canonical feedback in feedback-only mode', async () => { const { url, captures } = await mockCollector() const ctx = new Context() await ctx.plugin(SessionStore) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) const fiber = await ctx.plugin(TelemetryOtel, { mode: TelemetryMode.FEEDBACK_ONLY, exporter: { url }, }) const session = ctx.sessions.create(SessionId('no-feedback'), { meta: {} }) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + ctx.telemetry.emit({ + channel: 'ledger', + time: Date.now(), + severity: 'info', + attributes: { 'session.id': 'no-feedback', 'event.type': 'direct', 'event.seq': 99 }, + body: { mustStayLocal: true }, + }) + ctx.emit('session/event', session, { + type: 'feedback/record', + seq: session.events.length, + time: Date.now(), + data: { text: 'not committed' }, + }) await fiber.dispose() + + expect(warn).toHaveBeenCalledWith( + 'session telemetry ignored a feedback event absent from the canonical session log', + ) expect(captures).toEqual([]) }) - it('boots disabled without exporter config and warns when feedback stays local', async () => { + it('constructs no disabled transport even when exporter options are present', async () => { + const { url, captures } = await mockCollector() const ctx = new Context() await ctx.plugin(SessionStore) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) - const fiber = await ctx.plugin(TelemetryOtel, { mode: TelemetryMode.DISABLED }) + const fiber = await ctx.plugin(TelemetryOtel, { + mode: TelemetryMode.DISABLED, + exporter: { url }, + processor: { maxExportBatchSize: 0 }, + }) const session = ctx.sessions.create(SessionId('disabled'), { meta: {} }) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) recordFeedback(session, 'local report') @@ -268,6 +309,7 @@ describe('TelemetryOtel wire', () => { await fiber.dispose() recordFeedback(session, 'after disposal') expect(warn).toHaveBeenCalledTimes(1) + expect(captures).toEqual([]) }) it('defaults direct construction to full delivery', async () => { @@ -306,6 +348,22 @@ describe('TelemetryOtel config fails loud', () => { await ctx.plugin(SessionStore) await expect(ctx.plugin(TelemetryOtel, config as Config)).rejects.toThrow(message) }) + + it('rejects an unknown direct mode before reading transport config', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + let exporterRead = false + const config = { + mode: 'INVALID', + get exporter() { + exporterRead = true + throw new Error('transport config was read') + }, + } as unknown as Config + + expect(() => new TelemetryOtel(ctx, config)).toThrow(/unsupported mode "INVALID"/) + expect(exporterRead).toBe(false) + }) }) describe('dsh-session-telemetry-otel real-load-path guard', () => { From 4f595311f793bf2759243aefd31901bfc9c72aac Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 6 Aug 2026 16:32:46 +0800 Subject: [PATCH 16/22] test: include feedback in Web command catalog snapshot --- .../tests/snapshots/lifecycle-chrome/command-menu.expected.md | 1 + 1 file changed, 1 insertion(+) diff --git a/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md index 1da9b9a45e..7b18ab188b 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md @@ -1,6 +1,7 @@ - listbox "Trigger suggestions": - text: Commands - option "compact Compact older conversation history" [selected] + - option "feedback record feedback about this session" - option "goal set or view the goal for a long-running task" - option "permission Switch the permission preset (sandbox mode + approval policy)" - option "plan Enter or leave plan mode" From a667d2cd64fcc213e97d7c12c2aaf6f3e8c6c0b0 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 6 Aug 2026 17:21:13 +0800 Subject: [PATCH 17/22] fix(web): address skill row review feedback --- .../2026-08-06-web-skill-tool-row.i18n.yaml | 4 +- .../feature/2026-08-06-web-skill-tool-row.md | 6 +-- .../2026-08-06-web-skill-tool-row.zh.md | 6 +-- packages/client/connection/src/client/api.ts | 2 +- .../client/connection/src/client/fixture.ts | 43 +++++++++------ .../client/connection/src/client/index.ts | 2 +- packages/client/runtime/README.i18n.yaml | 4 +- packages/client/runtime/README.md | 2 +- packages/client/runtime/README.zh.md | 2 +- .../client/session-history/history-fold.ts | 16 ++++-- .../src/client/sessions/conversation.ts | 6 +-- .../runtime/src/client/sessions/session.ts | 12 +++-- .../src/client/sessions/transcript-adapter.ts | 26 +++++++-- packages/client/runtime/tests/fake-api.ts | 4 +- .../client/runtime/tests/history-fold.spec.ts | 14 +++++ packages/client/runtime/tests/session.spec.ts | 17 ++++++ .../runtime/tests/transcript-adapter.spec.ts | 16 ++++++ .../src/client/chat/ToolRow.tsx | 13 +---- .../client/contract/terminal-card-model.ts | 11 ++-- .../src/client/toolviews/bash-sample.tsx | 6 +-- .../ui-conversation/tests/chat-view.spec.tsx | 4 +- .../client/ui-primitives/src/icons/index.tsx | 7 +++ .../client/ui-primitives/tests/icons.spec.tsx | 4 +- packages/client/ui-skill/README.i18n.yaml | 4 +- packages/client/ui-skill/README.md | 2 +- packages/client/ui-skill/README.zh.md | 2 +- .../client/ui-skill/src/client/SkillRow.tsx | 31 +++++------ packages/client/ui-skill/src/invariant.ts | 7 +-- .../ui-skill/tests/browser-plugin.spec.ts | 44 ++++++++------- .../client/ui-skill/tests/skill-row.spec.tsx | 6 +-- packages/host/apiproxy/README.i18n.yaml | 4 +- packages/host/apiproxy/README.md | 2 +- packages/host/apiproxy/README.zh.md | 2 +- packages/host/apiproxy/src/api-proxy.ts | 54 +++++++++++++++---- packages/host/apiproxy/src/api/index.ts | 2 +- .../host/apiproxy/src/api/sessions.schema.ts | 12 ++++- packages/host/apiproxy/src/api/sessions.ts | 18 +++++-- .../apiproxy/tests/api-proxy-view.spec.ts | 41 ++++++++++++++ .../host/apiproxy/tests/rpc-schemas.spec.ts | 10 +++- 39 files changed, 326 insertions(+), 142 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml index 8186444a8d..237338a7e6 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md -2026-08-06-web-skill-tool-row.md: b1d76c411d7ccc839616ddcce9fee18716489bf5 -2026-08-06-web-skill-tool-row.zh.md: c16a9b84d75c641b0fdd8778ff56c331c2c81546 +2026-08-06-web-skill-tool-row.md: bebcf658de33d133ffea8eb190fb4e8e63bf82ff +2026-08-06-web-skill-tool-row.zh.md: 9377829aab1cb6b347cb837dafe7e7e4afb63868 diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md index b1d76c411d..bebcf658de 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md @@ -14,16 +14,16 @@ The Web transcript renders `skill` calls through the generic fallback row, so a The collapsed row uses a 16-pixel document-and-sparkle glyph and the Bash row's neutral hierarchy: tertiary glyph, secondary `Skill` title, caption separator, and tertiary skill name. Running, failed, and interrupted calls retain the transcript's shimmer, error dot and first-line summary, and warning dot semantics. A settled call expands through the whole summary row into a 260-pixel bounded `Instructions` card containing the exact durable result text; the existing trajectory `Inspect` handoff remains available below the card. -The row derives every visible value from the logged call/result slice. It reads the skill name from the recorded `name` argument and the instructions from durable result content, and never joins the current skill catalog for descriptions or provider metadata. The existing ACP `skill-load` recording is seeded through the real Web persistence and composition path for a keyless interaction and accessibility snapshot. +The row derives every visible value from the logged call/result slice. It reads the skill name from the recorded `name` argument and the instructions from durable result content, and never joins the current skill catalog for descriptions or provider metadata. Because a history page can contain a `tool/result` after its `tool/call` fell outside the window, the generic `HistoryEntry` envelope now carries the paired call's name, exact arguments JSON, and event time on result entries. The Host derives this transient annotation and the result render intent from the complete log; the runtime prefers an in-window call and otherwise materializes the same `ToolResultNode.call` and `callTime` from the annotation. An orphan result still has `call: null`, and a call-side render intent remains unavailable when its event is outside the page. The existing ACP `skill-load` recording is seeded through the real Web persistence and composition path for a keyless interaction and accessibility snapshot. ## Alternatives considered - Keep the generic tool row and add only a `skill` color selector in `ui-conversation`. This leaves the redundant input envelope and generic expanded body in place, and makes the conversation package own a domain-specific visual rule. -- Add a new `skill` value to the host tool render-intent union. The keyed client slot already identifies this tool without changing the wire contract, so a new cross-boundary presentation value adds protocol and snapshot surface without enabling another consumer. +- Add a new `skill` value to the host tool render-intent union. The keyed client slot already identifies this tool; the cross-page fix belongs to the generic history pairing envelope used by every tool rather than a skill-specific presentation value. - Export the conversation package's private `ToolRow` component for reuse. Client packages intentionally expose contracts rather than cross-package components; exporting it would couple independent feature packages to conversation implementation details. ## Consequences `ui-skill` now depends on the public conversation toolview contract, locale and primitive packages, and React in addition to its reference-source dependencies. It owns a small copy of the disclosure-row chrome, so future global interaction changes must update this registrant alongside the Bash sample and conversation rows. -Cold replay stays deterministic when the installed skill catalog changes, and the transcript remains compact until instructions are explicitly expanded. The dedicated card intentionally shows the tool's complete framed output rather than extracting only ``, preserving exactly what reached the model and avoiding a second parser for the skill result format. +Cold replay stays deterministic across pagination and when the installed skill catalog changes, and the transcript remains compact until instructions are explicitly expanded. The generic pairing annotation also prevents other keyed tool rows and result presenters from changing identity at a page boundary without persisting duplicate data. The dedicated card intentionally shows the tool's complete framed output rather than extracting only ``, preserving exactly what reached the model and avoiding a second parser for the skill result format. diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md index c16a9b84d7..9377829aab 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md @@ -14,16 +14,16 @@ Web transcript（文本记录）通过通用后备行渲染 `skill` 调用，使 收起的行使用 16 像素的文档与闪光组合图标，并沿用 Bash 行的中性色层级：图标采用三级色，`Skill` 标题采用二级色，分隔符采用 caption 色，skill 名称采用三级色。运行、失败和中断调用分别沿用 transcript 的扫光、错误状态点加首行摘要，以及警告状态点语义。已结算调用可以通过整个摘要行展开一个高度上限为 260 像素的 `Instructions` 卡片，其中原样呈现持久化结果文本；用于跳转至 trajectory 的现有 `Inspect` 入口仍保留在卡片下方。 -该行的所有可见值均派生自已记录的调用／结果片段。skill 名称来自已记录的 `name` 参数，指令来自持久化的结果内容；该行绝不关联当前 skill 目录来读取描述或提供方元数据。现有的 ACP（Agent Client Protocol）`skill-load` 记录经由真实的 Web 持久化与组合路径写入，用于无需密钥的交互和无障碍快照。 +该行的所有可见值均派生自已记录的调用／结果片段。skill 名称来自已记录的 `name` 参数，指令来自持久化的结果内容；该行绝不关联当前 skill 目录来读取描述或提供方元数据。由于 history 页可能包含 `tool/result`，而与之配对的 `tool/call` 已落在窗口外，通用 `HistoryEntry` envelope 现在会在结果条目上携带配对调用的名称、精确的 arguments JSON 和事件时间。Host 从完整日志派生这份瞬时注解和结果渲染意图；runtime 优先使用窗口内调用，否则从该注解物化出相同的 `ToolResultNode.call` 和 `callTime`。无配对结果仍为 `call: null`；调用事件位于页面外时，调用侧渲染意图仍不可用。现有的 ACP（Agent Client Protocol）`skill-load` 记录经由真实的 Web 持久化与组合路径写入，用于无需密钥的交互和无障碍快照。 ## 考虑过的替代方案 - 保留通用工具行，只添加一个 `skill` 颜色选择器，并将其放在 `ui-conversation` 中。该方案仍会保留多余的输入外层结构和通用展开体，也会让 conversation 包拥有特定领域的视觉规则。 -- 在宿主工具渲染意图联合类型中添加新的 `skill` 值。键控客户端 slot 无需更改协议契约即可识别该工具，因此新的跨边界呈现值只会增加协议与快照表层，却没有为其他消费方提供新能力。 +- 在宿主工具渲染意图联合类型中添加新的 `skill` 值。键控客户端 slot 已经能够识别该工具；跨页修复属于所有工具共用的通用 history 配对 envelope，而不是 skill 专用的呈现值。 - 导出 conversation 包的私有 `ToolRow` 组件供复用。客户端包刻意对外暴露契约而非跨包组件；导出该组件会使独立功能包耦合到 conversation 的实现细节。 ## 后果 除了引用 source 的依赖外，`ui-skill` 现在还依赖公开的 conversation toolview 契约、locale 包、原语包和 React。它自行保留了一小份折叠展开行 chrome，因此未来的全局交互变更必须与 Bash 示例和 conversation 行同步更新这个注册方。 -即使已安装的 skill 目录发生变化，冷回放仍具有确定性；在用户显式展开指令前，transcript 保持紧凑。专用卡片有意显示工具完整封装的输出，而不是只提取 ``，从而原样保留模型实际收到的内容，也避免为 skill 结果格式再引入一个解析器。 +无论跨越分页，还是已安装的 skill 目录发生变化，冷回放都保持确定性；在用户显式展开指令前，transcript 保持紧凑。通用配对注解还可防止其他键控工具行和结果 presenter 在分页边界改变身份，同时无需持久化重复数据。专用卡片有意显示工具完整封装的输出，而不是只提取 ``，从而原样保留模型实际收到的内容，也避免为 skill 结果格式再引入一个解析器。 diff --git a/packages/client/connection/src/client/api.ts b/packages/client/connection/src/client/api.ts index 6f29b2dda0..de15a9c67f 100644 --- a/packages/client/connection/src/client/api.ts +++ b/packages/client/connection/src/client/api.ts @@ -7,7 +7,7 @@ export type { ApiProxy, SessionsApi, SessionSearchItem, SessionSummary, HostApi, EventsApi, MuxFrame, HostFrame, - ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, ToolEventView, + ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, HistoryToolCall, ToolEventView, DirectoryEntry, DirectoryListing, WorkspaceApi, WorkspaceId, WorkspaceView, CommandsApi, CommandDescriptor, SkillsApi, SkillEntry, diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index 20af221f2d..5a7367acd0 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -29,7 +29,7 @@ import type { import type { CommandId } from '@deepseek-ai/dsh-commands/brand' import { deriveEventMessage, foldSurface } from '@deepseek-ai/dsh-session/surface' import type { - ApiProxy, ClientRequest, ClientResponse, HistoryEntry, HostFrame, MuxFrame, RpcReceipt, + ApiProxy, ClientRequest, ClientResponse, HistoryEntry, HistoryToolCall, HostFrame, MuxFrame, RpcReceipt, ModelProviderGroup, ModelTarget, RpcRequest, RpcResponse, RpcResult, ServerRequest, ServerResponse, SessionSummary, ToolCallView, ToolEventView, ToolResultView, WorkspaceId, WorkspaceView, } from './api.ts' @@ -661,25 +661,33 @@ function presentResult(name: string, argsRaw: string, resultText: string): ToolR } } -/** Host-side viewFor mirror: tool/call presents from its own args; tool/result back-scans the log for the paired call. */ +/** Full-log tool/result pair used by the fixture history envelope and presenter mirror. */ +function pairedHistoryCall(event: SessionEvent, log: readonly SessionEvent[]): HistoryToolCall | undefined { + if (event.type !== 'tool/result') return undefined + const callId = String(event.data.message.source.callId) + for (let i = log.length - 1; i >= 0; i--) { + const candidate = log[i] + /* v8 ignore next -- dense-array guard: i stays within [0, log.length), + so the undefined arm needs a sparse log no code path builds. */ + if (candidate !== undefined && candidate.type === 'tool/call' && String(candidate.data.callId) === callId) { + return { name: candidate.data.name, arguments: candidate.data.arguments, time: candidate.time } + } + } + return undefined +} + +/** Host-side viewFor mirror: tool/call presents from its own args; tool/result uses its full-log pair. */ function viewFor(event: SessionEvent, log: readonly SessionEvent[]): ToolEventView | undefined { if (event.type === 'tool/call') { const view = presentCall(event.data.name, event.data.arguments) return view === undefined ? undefined : { for: 'call', view } } if (event.type === 'tool/result') { - const callId = String(event.data.message.source.callId) - for (let i = log.length - 1; i >= 0; i--) { - const candidate = log[i] - /* v8 ignore next -- dense-array guard: i stays within [0, log.length), - so the undefined arm needs a sparse log no code path builds. */ - if (candidate !== undefined && candidate.type === 'tool/call' && String(candidate.data.callId) === callId) { - const resultText = event.data.message.content[0].content.map(b => (b.type === 'text' ? b.text : '')).join('') - const view = presentResult(candidate.data.name, candidate.data.arguments, resultText) - return view === undefined ? undefined : { for: 'result', view } - } - } - return undefined // cross-page unpaired: documented default + const call = pairedHistoryCall(event, log) + if (call === undefined) return undefined + const resultText = event.data.message.content[0].content.map(b => (b.type === 'text' ? b.text : '')).join('') + const view = presentResult(call.name, call.arguments, resultText) + return view === undefined ? undefined : { for: 'result', view } } return undefined } @@ -1044,7 +1052,12 @@ function pageOf( } const events = log.slice(start, end).map((event): HistoryEntry => { const view = viewFor(event, log) - return view === undefined ? { event } : { event, view } + const call = pairedHistoryCall(event, log) + return { + event, + ...view === undefined ? {} : { view }, + ...call === undefined ? {} : { call }, + } }) return { events, hasMore: start > 0 } } diff --git a/packages/client/connection/src/client/index.ts b/packages/client/connection/src/client/index.ts index 67b47b06c6..83e9722a49 100644 --- a/packages/client/connection/src/client/index.ts +++ b/packages/client/connection/src/client/index.ts @@ -13,7 +13,7 @@ import { isLoopbackHostname } from '../loopback-hostname.ts' // ---- Contract re-exports (browser-safe apiproxy channels + core types) ---- export type { ApiProxy, SessionsApi, SessionSearchItem, SessionSummary, HostApi, EventsApi, MuxFrame, HostFrame, - ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, ToolEventView, + ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, HistoryToolCall, ToolEventView, DirectoryEntry, DirectoryListing, ToolCallView, ToolResultView, WorkspaceApi, WorkspaceId, WorkspaceView, CommandsApi, CommandDescriptor, SkillsApi, SkillEntry, diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index 23c867e4c0..ef94a8834c 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/runtime/README.md -README.md: 8ac29a4258bbd7456b20c61e547d48c570e84d27 -README.zh.md: 0e065e43ecc571e68d3976d2100eb43959cb2e3d +README.md: 3d981392ce0314f41fe84bc1adb2b9484a6a5989 +README.zh.md: c05bdb6ebb33c0ffa47e2b54fb1b3d9d25f2fa6d diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index 8ac29a4258..3d981392ce 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -34,7 +34,7 @@ SlotsService gives the renderer separate bare observables for `useSessions` and ## The human transcript -`ConversationSnapshot.nodes` is the human transcript, not the model surface. `TranscriptAdapter` projects the raw window in log order — every append-origin surface event (`isAppendSurfaceEvent`) at its own log position, plus one `CompactionSummaryNode` marker per landed compaction checkpoint — and never consults surface order. `SteeringHistory` replays the durable `agent/inbox/spliced` records in that window: a user-origin message claimed from `next-step` becomes a `SteeringMessageNode` when its matching `user/message` lands, a `next-turn` claim stays a user node, and non-user next-step input stays context. `ConversationSnapshot.turnEnds` maps each completed turn in that window to its `turn/end` seq, retaining turn completion independently from the transcript so presentation can require a real boundary before enabling an action. A landed compaction therefore keeps the conversation it shadowed on the model side: the marker reports where the model stopped seeing that history instead of erasing it. Model-only replacement copies stay out: a pruned `tool/result` and a regenerated `assistant/message` rewrite one node for the model and mark no boundary. A checkpoint is a `user/message` carrying the compaction seam's plugin source that **replaced** a surface range; an appending plugin-sourced `user/message` is injected context, not a compaction. Each context node also carries a `provenance` view: `contextProvenance()` reads the durable source alone to decide whether the row is an `inject` or a cross-session `recall`, and to name its producer from the instruction paths, referenced session titles, or plugin id that source already records. The client holds no table of plugin ids, so a renamed or newly mounted producer stays identifiable without a client release and a resumed or foreign log projects exactly like a live one; a source with no readable kind degrades to an unnamed injection. Beside it, `contextForm()` reads the producer-declared `ContextForm` — the second, independent axis: `kind` says who produced the context, `form` says what shape of information it is, so several producers may share one form. A form this UI version does not present projects as null and renders opaque. The adapter's plugin literal is pinned to the seam's own declaration by a type-only import of the cordis-free [`dsh-compact/checkpoint`](../../compact/compact/README.md) leaf, so renaming it there fails `tsc` here; a **value** import of the package would fail the client purity gate, and the package **root** is unreachable even as a type (it reaches `dsh-session`'s root, whose `Context` merge collides the host `sessions` with this program's). +`ConversationSnapshot.nodes` is the human transcript, not the model surface. `TranscriptAdapter` projects the raw window in log order — every append-origin surface event (`isAppendSurfaceEvent`) at its own log position, plus one `CompactionSummaryNode` marker per landed compaction checkpoint — and never consults surface order. A paged `tool/result` first pairs against an in-window `tool/call`, then against the Host-carried complete-log call annotation; `ToolResultNode.call` is null only for a truly orphaned durable result, so a page boundary cannot change keyed toolview dispatch, argument-derived labels, or duration. The call-side render intent remains null when its event is outside the window, while the result intent is already computed by the Host from the complete pair. `SteeringHistory` replays the durable `agent/inbox/spliced` records in that window: a user-origin message claimed from `next-step` becomes a `SteeringMessageNode` when its matching `user/message` lands, a `next-turn` claim stays a user node, and non-user next-step input stays context. `ConversationSnapshot.turnEnds` maps each completed turn in that window to its `turn/end` seq, retaining turn completion independently from the transcript so presentation can require a real boundary before enabling an action. A landed compaction therefore keeps the conversation it shadowed on the model side: the marker reports where the model stopped seeing that history instead of erasing it. Model-only replacement copies stay out: a pruned `tool/result` and a regenerated `assistant/message` rewrite one node for the model and mark no boundary. A checkpoint is a `user/message` carrying the compaction seam's plugin source that **replaced** a surface range; an appending plugin-sourced `user/message` is injected context, not a compaction. Each context node also carries a `provenance` view: `contextProvenance()` reads the durable source alone to decide whether the row is an `inject` or a cross-session `recall`, and to name its producer from the instruction paths, referenced session titles, or plugin id that source already records. The client holds no table of plugin ids, so a renamed or newly mounted producer stays identifiable without a client release and a resumed or foreign log projects exactly like a live one; a source with no readable kind degrades to an unnamed injection. Beside it, `contextForm()` reads the producer-declared `ContextForm` — the second, independent axis: `kind` says who produced the context, `form` says what shape of information it is, so several producers may share one form. A form this UI version does not present projects as null and renders opaque. The adapter's plugin literal is pinned to the seam's own declaration by a type-only import of the cordis-free [`dsh-compact/checkpoint`](../../compact/compact/README.md) leaf, so renaming it there fails `tsc` here; a **value** import of the package would fail the client purity gate, and the package **root** is unreachable even as a type (it reaches `dsh-session`'s root, whose `Context` merge collides the host `sessions` with this program's). Because the projection is log-ordered, the node array is seq-monotonic by construction: log-only `command/run` / `command/done` nodes splice in by seq, `Session` merges interrupted frozen nodes by their fractional seqs, and a window whose checkpoint cites a shadowed range outside it renders the marker with nothing logged. The marker's summary text comes from the checkpoint's `compact/summary` provenance; a window cut that left the provenance outside makes the row non-expandable rather than empty, and a later page that supplies it resolves the text. Performance contract: one append materializes at most one node and copies the projection only when it adds that node; an event that changes no node keeps the previous array reference (a chunk storm costs nothing), and unchanged nodes keep their object identity. diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index 0e065e43ec..c05bdb6ebb 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -34,7 +34,7 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 ## 面向人的 transcript（文本记录） -`ConversationSnapshot.nodes` 是面向人的 transcript，不是模型 surface。`TranscriptAdapter` 按日志顺序投影原始窗口。每个 append 来源的 surface 事件（`isAppendSurfaceEvent`）落在它自己的日志位置上，每次落地的压缩（compaction）检查点还会贡献一个 `CompactionSummaryNode` 标记；适配器从不查询 surface 顺序。`SteeringHistory` 会重放该窗口中的持久 `agent/inbox/spliced` 记录：用户来源的消息从 `next-step` 被领取，并以相同身份落成 `user/message` 时，会投影为 `SteeringMessageNode`；从 `next-turn` 领取的消息仍是用户节点，非用户来源的 next-step 输入仍是上下文。`ConversationSnapshot.turnEnds` 把该窗口中的每个已完成轮次映射到其 `turn/end` seq；它独立于 transcript 保留轮次完成状态，使呈现层能够在启用操作前要求存在真实边界。于是一次落地的压缩会保留它在模型侧遮蔽掉的对话：标记报告模型从哪里开始看不见那段历史，而不是把它抹掉。仅模型可见的 replacement 副本不进入记录：被裁剪的 `tool/result` 和重新生成的 `assistant/message` 只为模型重写一个节点，不标记任何边界。检查点是携带压缩 seam 插件来源、且**替换**了一段 surface 范围的 `user/message`；一条 append 的插件来源 `user/message` 是注入上下文，不是压缩。每个上下文节点还携带一份 `provenance` 视图：`contextProvenance()` 只读取持久来源，据此判定该行是 `inject`（注入）还是跨会话的 `recall`（召回），并用该来源已经记录的指令文件路径、被引用会话标题或插件 id 命名其生产者。客户端不保存任何插件 id 表，因此重命名或新挂载的生产者无需客户端发版即可保持可辨识，恢复的会话日志与外部日志的投影结果和实时会话完全一致；没有可读 kind 的来源则降级为无名注入。与之并列的 `contextForm()` 读取生产方声明的 `ContextForm`，这是相互独立的第二根轴：`kind` 说明上下文由谁产生，`form` 说明它是何种形态的信息，因此多个生产方可以共用一种形态。本 UI 版本不呈现的形态投影为 null，按 opaque 渲染。适配器的插件字面量通过对无 cordis 的 [`dsh-compact/checkpoint`](../../compact/compact/README.md) 叶子做仅类型导入，钉在压缩 seam 自己的声明上：在那里改名会让此处 `tsc` 失败；而对该包（package）做**值**导入会被客户端纯度门禁拒绝，包的**根**即便作为类型也无法到达（它会到达 `dsh-session` 的根，其 `Context` 合并会让 host 的 `sessions` 与本程序的冲突）。 +`ConversationSnapshot.nodes` 是面向人的 transcript，不是模型 surface。`TranscriptAdapter` 按日志顺序投影原始窗口。每个 append 来源的 surface 事件（`isAppendSurfaceEvent`）落在它自己的日志位置上，每次落地的压缩（compaction）检查点还会贡献一个 `CompactionSummaryNode` 标记；适配器从不查询 surface 顺序。分页得到的 `tool/result` 会先与窗口内的 `tool/call` 配对，再与 Host 携带的完整日志调用注解配对；只有持久结果确实没有配对调用时，`ToolResultNode.call` 才为 null，因此分页边界无法改变键控 toolview 分派、由参数派生的标签或耗时。调用事件位于窗口外时，调用侧渲染意图仍为 null，而结果侧渲染意图已经由 Host 基于完整配对计算完成。`SteeringHistory` 会重放该窗口中的持久 `agent/inbox/spliced` 记录：用户来源的消息从 `next-step` 被领取，并以相同身份落成 `user/message` 时，会投影为 `SteeringMessageNode`；从 `next-turn` 领取的消息仍是用户节点，非用户来源的 next-step 输入仍是上下文。`ConversationSnapshot.turnEnds` 把该窗口中的每个已完成轮次映射到其 `turn/end` seq；它独立于 transcript 保留轮次完成状态，使呈现层能够在启用操作前要求存在真实边界。于是一次落地的压缩会保留它在模型侧遮蔽掉的对话：标记报告模型从哪里开始看不见那段历史，而不是把它抹掉。仅模型可见的 replacement 副本不进入记录：被裁剪的 `tool/result` 和重新生成的 `assistant/message` 只为模型重写一个节点，不标记任何边界。检查点是携带压缩 seam 插件来源、且**替换**了一段 surface 范围的 `user/message`；一条 append 的插件来源 `user/message` 是注入上下文，不是压缩。每个上下文节点还携带一份 `provenance` 视图：`contextProvenance()` 只读取持久来源，据此判定该行是 `inject`（注入）还是跨会话的 `recall`（召回），并用该来源已经记录的指令文件路径、被引用会话标题或插件 id 命名其生产者。客户端不保存任何插件 id 表，因此重命名或新挂载的生产者无需客户端发版即可保持可辨识，恢复的会话日志与外部日志的投影结果和实时会话完全一致；没有可读 kind 的来源则降级为无名注入。与之并列的 `contextForm()` 读取生产方声明的 `ContextForm`，这是相互独立的第二根轴：`kind` 说明上下文由谁产生，`form` 说明它是何种形态的信息，因此多个生产方可以共用一种形态。本 UI 版本不呈现的形态投影为 null，按 opaque 渲染。适配器的插件字面量通过对无 cordis 的 [`dsh-compact/checkpoint`](../../compact/compact/README.md) 叶子做仅类型导入，钉在压缩 seam 自己的声明上：在那里改名会让此处 `tsc` 失败；而对该包（package）做**值**导入会被客户端纯度门禁拒绝，包的**根**即便作为类型也无法到达（它会到达 `dsh-session` 的根，其 `Context` 合并会让 host 的 `sessions` 与本程序的冲突）。 由于投影按日志顺序，节点数组天然按 seq 单调：仅日志的 `command/run` / `command/done` 节点按 seq 插入，`Session` 按分数 seq 归并被打断的冻结节点，而检查点所引范围落在窗口之外的窗口会渲染出标记且不打印任何日志。标记的摘要文本来自检查点的 `compact/summary` 溯源；窗口切分把溯源留在窗口外时该行不可展开而非空白，后续补上溯源的分页会解析出文本。性能契约：一次追加最多物化一个节点，并且仅在加入该节点时复制投影；不改变任何节点的事件保持上一次的数组引用（分片风暴零成本），未变化的节点保持其对象标识。 diff --git a/packages/client/runtime/src/client/session-history/history-fold.ts b/packages/client/runtime/src/client/session-history/history-fold.ts index d792fd2b76..83a09d3163 100644 --- a/packages/client/runtime/src/client/session-history/history-fold.ts +++ b/packages/client/runtime/src/client/session-history/history-fold.ts @@ -362,7 +362,8 @@ export function projectConversationHistory( let contextGeneration = 0 for (const [index, event] of events.entries()) { - const view = entries[index]?.view + const entry = entries[index] + const view = entry?.view if (event.type === 'tool/call') { callIndex.set(String(event.data.callId), { name: event.data.name, @@ -370,8 +371,17 @@ export function projectConversationHistory( time: event.time, callView: view?.for === 'call' ? view.view : null, }) - } else if (event.type === 'tool/result' && view?.for === 'result') { - resultViews.set(event.seq, view.view) + } else if (event.type === 'tool/result') { + const callId = String(event.data.message.source.callId) + if (!callIndex.has(callId) && entry?.call !== undefined) { + callIndex.set(callId, { + name: entry.call.name, + argsRaw: entry.call.arguments, + time: entry.call.time, + callView: null, + }) + } + if (view?.for === 'result') resultViews.set(event.seq, view.view) } if (isSurfaceEvent(event) && event.surfaceOp !== 'append') { contextGeneration++ diff --git a/packages/client/runtime/src/client/sessions/conversation.ts b/packages/client/runtime/src/client/sessions/conversation.ts index d24b963d6b..14bd0dc9ed 100644 --- a/packages/client/runtime/src/client/sessions/conversation.ts +++ b/packages/client/runtime/src/client/sessions/conversation.ts @@ -155,16 +155,16 @@ export interface TurnErrorNode { code?: string } -/** A tool result paired (when in-window) with its call head. */ +/** A tool result paired with its durable call head when the Host can resolve it. */ export interface ToolResultNode { kind: 'tool-result' seq: number /** Unix epoch ms from the tool/result session event. */ time: number callId: string - /** Call head backfilled from the in-window tool/call; null when window truncation left the call outside (card head shows callId). */ + /** Call head from the window or history envelope; null only when the durable log has no pair (card head shows callId). */ call: { name: string; argsRaw: string } | null - /** Unix epoch ms of the paired tool/call when the call is still in-window; used for call-row duration. */ + /** Unix epoch ms of the paired tool/call; null when the durable log has no pair. */ callTime: number | null content: readonly ContentBlock[] isError: boolean diff --git a/packages/client/runtime/src/client/sessions/session.ts b/packages/client/runtime/src/client/sessions/session.ts index 776f4494fd..e663af8bf6 100644 --- a/packages/client/runtime/src/client/sessions/session.ts +++ b/packages/client/runtime/src/client/sessions/session.ts @@ -5,7 +5,7 @@ import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' import type { LlmRetryEventData } from '@deepseek-ai/dsh-llm-retry/types' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import type { - HistoryEntry, IApiClient, MessageId, MuxFrame, QueueAction, RpcError, + HistoryEntry, HistoryToolCall, IApiClient, MessageId, MuxFrame, QueueAction, RpcError, RpcId, RpcResponse, RpcResult, SessionId, SubagentAddress, ToolEventView, } from '@deepseek-ai/dsh-client-connection/client' // Value import from the inline-safe wire layer (not the connection plugin): @@ -85,6 +85,8 @@ export class Session implements SessionFace { /** Wire views aligned with `events` by index (envelope-level annotations; undefined = no view). * Kept parallel rather than merged so `events` stays the raw log slice (model-visible ⟺ logged). */ private views: (ToolEventView | undefined)[] = [] + /** Host-carried call metadata aligned with result entries when the call event is outside the page. */ + private historyCalls: (HistoryToolCall | undefined)[] = [] private baseSeq = 0 private hasMore = false private openState: OpenState = 'cold' @@ -381,10 +383,11 @@ export class Session implements SessionFace { } this.events = [...older.map(e => e.event), ...this.events] this.views = [...older.map(e => e.view), ...this.views] + this.historyCalls = [...older.map(e => e.call), ...this.historyCalls] /* v8 ignore next -- the ?? arm needs older[0] undefined, but the empty-page branch above already returned. */ this.baseSeq = older[0]?.event.seq ?? this.baseSeq this.hasMore = result.value.hasMore - this.transcript.reset(this.events, this.views) // prepend forces a rebuild (the window grew at the head) + this.transcript.reset(this.events, this.views, this.historyCalls) // prepend forces a rebuild (the window grew at the head) this.rebuildDerivedFromWindow() } catch (error) { console.error('[web-runtime] loadOlder failed:', error) @@ -411,6 +414,7 @@ export class Session implements SessionFace { this.openError = null this.events = [] this.views = [] + this.historyCalls = [] this.baseSeq = 0 // Superseded, not settled: the baseline replay re-sends still-pending requested frames verbatim // (same rpcId), re-minting fresh waits; a stale reference's respond() still reaches the host. @@ -644,9 +648,10 @@ export class Session implements SessionFace { private installWindow(entries: HistoryEntry[], hasMore: boolean, projections?: ProjectionsBaseline): void { this.events = entries.map(e => e.event) this.views = entries.map(e => e.view) + this.historyCalls = entries.map(e => e.call) this.baseSeq = this.events[0]?.seq ?? 0 this.hasMore = hasMore - this.transcript.reset(this.events, this.views) + this.transcript.reset(this.events, this.views, this.historyCalls) this.rebuildDerivedFromWindow() if (projections !== undefined) this.projections.seed(projections) const buffered = this.liveBuffer @@ -661,6 +666,7 @@ export class Session implements SessionFace { if (tailSeq !== null && event.seq <= tailSeq) return // replay overlap, drop this.events.push(event) this.views.push(view) + this.historyCalls.push(undefined) this.transcript.append(event, view) this.handoffPendingSteering(event) this.applyEventSideEffects(event, view) diff --git a/packages/client/runtime/src/client/sessions/transcript-adapter.ts b/packages/client/runtime/src/client/sessions/transcript-adapter.ts index 306571b2bf..b1d952b804 100644 --- a/packages/client/runtime/src/client/sessions/transcript-adapter.ts +++ b/packages/client/runtime/src/client/sessions/transcript-adapter.ts @@ -19,7 +19,9 @@ import type { CommandId } from '@deepseek-ai/dsh-commands/brand' // `sessions: ISessions` (TS2717, the one-program-per-side rule in // docs/development.md). import type { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact/checkpoint' -import type { ToolCallView, ToolEventView, ToolResultView } from '@deepseek-ai/dsh-client-connection/client' +import type { + HistoryToolCall, ToolCallView, ToolEventView, ToolResultView, +} from '@deepseek-ai/dsh-client-connection/client' import type { CommandNode, CompactionSummaryNode, ConversationNode } from './conversation.ts' import { toAssistantBlocks } from './conversation.ts' import { contextForm, contextProvenance } from './context-provenance.ts' @@ -213,8 +215,13 @@ export class TranscriptAdapter { * and re-project the transcript. * @param events - the new window contents (seq-ascending). * @param views - per-event wire views aligned with `events` by index (undefined slots for view-less events). + * @param calls - host-carried result pairs aligned with `events` by index. */ - reset(events: readonly SessionEvent[], views?: readonly (ToolEventView | undefined)[]): void { + reset( + events: readonly SessionEvent[], + views?: readonly (ToolEventView | undefined)[], + calls?: readonly (HistoryToolCall | undefined)[], + ): void { this.rev++ this.eventIndex = new Map() this.callIdx = new Map() @@ -228,7 +235,7 @@ export class TranscriptAdapter { /* v8 ignore next -- dense-array guard: i stays within events.length, so the undefined arm needs a sparse array no caller builds. */ if (event === undefined) continue this.eventIndex.set(event.seq, event) - this.indexCall(event, views?.[i]) + this.indexCall(event, views?.[i], calls?.[i]) this.indexCommand(event) if (this.steeringHistory.apply(event)) steeringSeqs.add(event.seq) indexAssistantStepTiming(this.stepTimings, event) @@ -338,9 +345,20 @@ export class TranscriptAdapter { return true } - private indexCall(event: SessionEvent, view?: ToolEventView): void { + private indexCall(event: SessionEvent, view?: ToolEventView, pairedCall?: HistoryToolCall): void { if (event.type === 'tool/result') { if (view?.for === 'result') this.resultViews.set(event.seq, view.view) + const callId = String(event.data.message.source.callId) + if (!this.callIdx.has(callId) && pairedCall !== undefined) { + this.callIdx.set(callId, { + name: pairedCall.name, + argsRaw: pairedCall.arguments, + turn: event.data.turn, + step: event.data.step, + time: pairedCall.time, + callView: null, + }) + } return } if (event.type !== 'tool/call') return diff --git a/packages/client/runtime/tests/fake-api.ts b/packages/client/runtime/tests/fake-api.ts index e50574d102..b13e27f3c4 100644 --- a/packages/client/runtime/tests/fake-api.ts +++ b/packages/client/runtime/tests/fake-api.ts @@ -3,7 +3,7 @@ // deferred-controlled timing). Streams are hand pumps: pushMux/pushHost. import type { CommandId } from '@deepseek-ai/dsh-commands/brand' import type { - ClientResponse, CommandDescriptor, HostFrame, IApiClient, ModelTarget, MuxFrame, + ClientResponse, CommandDescriptor, HistoryEntry, HostFrame, IApiClient, ModelTarget, MuxFrame, RpcError, RpcReceipt, RpcRequest, RpcResponse, SessionId, SessionModels, SessionSearchItem, SkillEntry, WorkspaceId, WorkspaceView, } from '@deepseek-ai/dsh-client-connection/client' @@ -68,7 +68,7 @@ export class FakeApiClient implements IApiClient { onRename: (payload: unknown) => Promise> = () => Promise.resolve(ok({ title: 'fk-renamed', seq: 0 })) onFork: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-fork' as SessionId })) onHistory: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number }) - => Promise> = + => Promise> = () => Promise.resolve(ok({ events: [], hasMore: false })) onModels: (payload: unknown) => Promise> = () => Promise.resolve(ok({ diff --git a/packages/client/runtime/tests/history-fold.spec.ts b/packages/client/runtime/tests/history-fold.spec.ts index 083bdc3566..f9b40bdb7c 100644 --- a/packages/client/runtime/tests/history-fold.spec.ts +++ b/packages/client/runtime/tests/history-fold.spec.ts @@ -53,6 +53,20 @@ describe('projectConversationHistory', () => { }]) }) + it('projects a paged tool result from its host-carried call pair', () => { + const result = ev.toolResult(50, 3, 'outside-call', '已加载 skill') + const projection = projectConversationHistory([{ + event: result, + call: { name: 'skill', arguments: '{"name":"dsh-code-review"}', time: 40 }, + }]) + expect(projection.eventNodes).toMatchObject([{ + kind: 'tool-result', + call: { name: 'skill', argsRaw: '{"name":"dsh-code-review"}' }, + callTime: 40, + callView: null, + }]) + }) + it('projects a high-sequence history window without synthesizing its unloaded prefix', () => { const baseSeq = 400_000 const events = [ diff --git a/packages/client/runtime/tests/session.spec.ts b/packages/client/runtime/tests/session.spec.ts index c288c044ee..02753fe09e 100644 --- a/packages/client/runtime/tests/session.spec.ts +++ b/packages/client/runtime/tests/session.spec.ts @@ -53,6 +53,23 @@ describe('open', () => { expect(snapshot.turnEnds.get(3)).toBe(15) }) + it('installs host-carried call metadata for a result-only tail page', async () => { + const { api, session } = makeSession() + api.onHistory = () => Promise.resolve(ok({ + events: [{ + event: ev.toolResult(50, 3, 'outside-call', '已加载 skill'), + call: { name: 'skill', arguments: '{"name":"dsh-code-review"}', time: 40 }, + }], + hasMore: true, + })) + await session.open() + expect(session.getSnapshot().nodes).toMatchObject([{ + kind: 'tool-result', + call: { name: 'skill', argsRaw: '{"name":"dsh-code-review"}' }, + callTime: 40, + }]) + }) + it('is idempotent: concurrent opens share one history call, reopening when open is a no-op', async () => { const { api, session } = makeSession() await Promise.all([session.open(), session.open()]) diff --git a/packages/client/runtime/tests/transcript-adapter.spec.ts b/packages/client/runtime/tests/transcript-adapter.spec.ts index 031acf1780..99b4cdf261 100644 --- a/packages/client/runtime/tests/transcript-adapter.spec.ts +++ b/packages/client/runtime/tests/transcript-adapter.spec.ts @@ -365,6 +365,22 @@ describe('TranscriptAdapter', () => { expect(adapter.nodes()[0]).toMatchObject({ kind: 'tool-result', callId: 'outside-call', call: null }) }) + it('materializes a paged tool-result from its host-carried call pair', () => { + const adapter = new TranscriptAdapter() + adapter.reset( + [ev.toolResult(50, 3, 'outside-call', '已加载 skill')], + [undefined], + [{ name: 'skill', arguments: '{"name":"dsh-code-review"}', time: 40 }], + ) + expect(adapter.nodes()[0]).toMatchObject({ + kind: 'tool-result', + callId: 'outside-call', + call: { name: 'skill', argsRaw: '{"name":"dsh-code-review"}' }, + callTime: 40, + callView: null, + }) + }) + it('materializes a tool-result error field when present', () => { const adapter = new TranscriptAdapter() adapter.reset([ diff --git a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx index 71cf69cc5f..ac48604fc9 100644 --- a/packages/client/ui-conversation/src/client/chat/ToolRow.tsx +++ b/packages/client/ui-conversation/src/client/chat/ToolRow.tsx @@ -23,7 +23,7 @@ import { useEffect, useRef, useState, type KeyboardEvent, type MouseEvent, type ReactNode } from 'react' import clsx from 'clsx' import { - CodeBlock, DiffBlock, ReadBlock, SearchBlock, StateDot, TerminalBlock, WebBlock, + CodeBlock, DiffBlock, IconInspectOutline12, ReadBlock, SearchBlock, StateDot, TerminalBlock, WebBlock, } from '@deepseek-ai/dsh-client-ui-primitives' import type { WebBlockProps } from '@deepseek-ai/dsh-client-ui-primitives' import type { TranslateNS } from '@deepseek-ai/dsh-client-ui-slots' @@ -99,15 +99,6 @@ export interface ToolRowProps { inspect?: (() => void) | undefined } -/** The Inspect pill's code glyph (user-supplied 16×16), fill follows text color. */ -function IconInspect() { - return ( - - - - ) -} - /** Leading-slot state substitution: the tool icon yields to the terminal state * semantic (error = red, interrupted = amber halo). Running keeps the icon — * the row sweep (CSS on data-state) carries the in-flight signal. */ @@ -319,7 +310,7 @@ export function ToolRow({ className={css.inspectButton} onClick={inspect} > - + Inspect )} diff --git a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts index 8a0c887990..b1c4cbe757 100644 --- a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts +++ b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts @@ -168,11 +168,12 @@ function collapse(body: string, rooted: boolean, separator = '/'): string { * returns a generic fenced card for an execution error or a background * start, whose text and error styling the generic path preserves. * - * Window truncation can drop the call head from a settled result (see - * `ToolResultNode.call`/`callView` in dsh-client-runtime), leaving a terminal - * result with no call side. That still renders: the command falls back to the - * result view's replacement title, then to an empty command (the prompt line - * draws bare), and the prompt shows no cwd. + * Window truncation can drop the call event and its call-side view from a + * settled result (see `ToolResultNode.callView` in dsh-client-runtime), leaving + * a terminal result with no presentation call side even though the history + * envelope preserves its name and arguments. That still renders: the command + * falls back to the result view's replacement title, then to an empty command + * (the prompt line draws bare), and the prompt shows no cwd. * @param block - RunningToolCall or ToolResultNode off the snapshot caches. * @param sessionCwd - the session workspace root, which resolves an omitted or * relative view cwd (see {@link resolveTerminalCwd}); absent leaves both unresolved. diff --git a/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx b/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx index 54e021639f..adf4ac4355 100644 --- a/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx +++ b/packages/client/ui-conversation/src/client/toolviews/bash-sample.tsx @@ -17,7 +17,7 @@ import { useState, type KeyboardEvent } from 'react' import type { Context } from 'cordis' import clsx from 'clsx' import { - IconApiOutline14, IconChevronDownOutline14, StateDot, TerminalBlock, + IconApiOutline14, IconChevronDownOutline14, IconInspectOutline12, StateDot, TerminalBlock, } from '@deepseek-ai/dsh-client-ui-primitives' import type { PropsLocale } from '@deepseek-ai/dsh-client-ui-slots' import type { ToolRowProps } from '../contract/slots.ts' @@ -153,9 +153,7 @@ export function BashRow({ toolName, block, sessionId, useSessions, inspect, t }: )} {inspect !== undefined && ( )} diff --git a/packages/client/ui-conversation/tests/chat-view.spec.tsx b/packages/client/ui-conversation/tests/chat-view.spec.tsx index b7ca8dd149..e83c82130d 100644 --- a/packages/client/ui-conversation/tests/chat-view.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-view.spec.tsx @@ -282,12 +282,12 @@ describe('chat-flow derivation', () => { }) describe('ChatView', () => { - it('a windowless tool result (call head truncated) renders with an empty tool name', () => { + it('an orphan tool result renders through the generic fallback', () => { const h = makeHarness({ nodes: [{ ...toolResult(3, 'w1'), call: null }], }) const view = render() - // classifyTool('') → others; the summary slot falls back to the callId. + // No durable call exists for this id, so the summary falls back to callId. expect(view.container.querySelector('[data-variant="others"]')).not.toBeNull() expect(view.getByText('w1')).toBeTruthy() }) diff --git a/packages/client/ui-primitives/src/icons/index.tsx b/packages/client/ui-primitives/src/icons/index.tsx index b0b76e164b..5b99a0e71c 100644 --- a/packages/client/ui-primitives/src/icons/index.tsx +++ b/packages/client/ui-primitives/src/icons/index.tsx @@ -750,6 +750,13 @@ export const IconSparkle16 = ({ size = 16, className }: IconProps) => ( ) +/** inspect_outline_12 (shared tool-row trajectory affordance glyph) */ +export const IconInspectOutline12 = ({ size = 12, className }: IconProps) => ( + + + +) + /** skill_outline_16 (skill tool-row glyph; document instructions + sparkle) */ export const IconSkillOutline16 = ({ size = 16, className }: IconProps) => ( diff --git a/packages/client/ui-primitives/tests/icons.spec.tsx b/packages/client/ui-primitives/tests/icons.spec.tsx index 92f0d3cc37..678eb9754e 100644 --- a/packages/client/ui-primitives/tests/icons.spec.tsx +++ b/packages/client/ui-primitives/tests/icons.spec.tsx @@ -16,8 +16,8 @@ const icons = Object.fromEntries( const iconNames = Object.keys(icons) describe('ic_ds_ icon set', () => { - it('exports the full P-I set (46 deepsuite + 17 figma extracts + two hand-authored product glyphs)', () => { - expect(iconNames.length).toBe(65) + it('exports the full P-I set (46 deepsuite + 17 figma extracts + three product glyphs outside those sets)', () => { + expect(iconNames.length).toBe(66) }) it.each(iconNames)('%s renders an svg with currentColor fills and no hardcoded palette', (name) => { diff --git a/packages/client/ui-skill/README.i18n.yaml b/packages/client/ui-skill/README.i18n.yaml index d23f68ee85..5c50d22b89 100644 --- a/packages/client/ui-skill/README.i18n.yaml +++ b/packages/client/ui-skill/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-skill/README.md -README.md: 2280c9302dbc46cff723752f88c47940f98417d5 -README.zh.md: 0e9344ff63139f77461b02b48e18b0e94e54c223 +README.md: ba9f1faae0f70a0f7bed4641e02703cc26bcb692 +README.zh.md: f8210a885d201cbdc89d7a34704a819e80463d2c diff --git a/packages/client/ui-skill/README.md b/packages/client/ui-skill/README.md index 2280c9302d..ba9f1faae0 100644 --- a/packages/client/ui-skill/README.md +++ b/packages/client/ui-skill/README.md @@ -10,7 +10,7 @@ The `/client` export surface is the plugin body (`apply`/`inject`) only; the sou ## Skill tool row -The browser plugin also registers a keyed `skill` toolview in `conversation.chat.toolview`. A collapsed row renders the 16-pixel skill document-and-sparkle glyph, `Skill` title, separator, and requested skill name with the same neutral hierarchy as the Bash row; running calls carry the transcript shimmer, failures replace the name with the first error line, and interrupted calls use the warning state. A settled row expands as one whole-row disclosure into a bounded `Instructions` card containing the exact durable tool output, with the standard trajectory `Inspect` affordance when available. The row derives its name, lifecycle, and body only from the logged call/result slice, never from the current catalog, so cold replay remains stable even when installed skills or their descriptions change. +The browser plugin also registers a keyed `skill` toolview in `conversation.chat.toolview`. A collapsed row renders the 16-pixel skill document-and-sparkle glyph, `Skill` title, separator, and requested skill name with the same neutral hierarchy as the Bash row; running calls carry the transcript shimmer, failures replace the name with the first error line, and interrupted calls use the warning state. A settled row expands as one whole-row disclosure into a bounded `Instructions` card containing the exact durable tool output, with the standard trajectory `Inspect` affordance when available. The row derives its name, lifecycle, and body only from the logged call/result slice, using the history envelope's host-carried durable pair when pagination left the call event outside the window; it never reads the current catalog, so cold replay remains stable across page cuts and when installed skills or their descriptions change. ## Model Experience diff --git a/packages/client/ui-skill/README.zh.md b/packages/client/ui-skill/README.zh.md index 0e9344ff63..f8210a885d 100644 --- a/packages/client/ui-skill/README.zh.md +++ b/packages/client/ui-skill/README.zh.md @@ -10,7 +10,7 @@ skill（技能）引用 source 的浏览器端：把 `/` 触发的 `skill` sourc ## skill 工具行 -浏览器插件还会把一个 key 为 `skill` 的 toolview 注册进 `conversation.chat.toolview`。收起的行以与 Bash 行相同的中性色层级显示 16 像素的 skill 文档与闪光组合图标、`Skill` 标题、分隔符和请求加载的 skill 名称；运行中的调用带有 transcript（文本记录）的扫光效果，失败时用错误首行替换名称，中断调用则使用警告状态。已结算的行以整行作为展开入口，展开后显示一个尺寸受限的 `Instructions` 卡片，其中原样呈现持久化的工具输出；可用时还会提供标准执行轨迹的 `Inspect` 入口。该行的名称、生命周期和正文只派生自已记录的调用／结果片段，绝不读取当前 skill 目录，因此即使已安装的 skill 或其描述发生变化，冷回放仍保持稳定。 +浏览器插件还会把一个 key 为 `skill` 的 toolview 注册进 `conversation.chat.toolview`。收起的行以与 Bash 行相同的中性色层级显示 16 像素的 skill 文档与闪光组合图标、`Skill` 标题、分隔符和请求加载的 skill 名称；运行中的调用带有 transcript（文本记录）的扫光效果，失败时用错误首行替换名称，中断调用则使用警告状态。已结算的行以整行作为展开入口，展开后显示一个尺寸受限的 `Instructions` 卡片，其中原样呈现持久化的工具输出；可用时还会提供标准执行轨迹的 `Inspect` 入口。该行的名称、生命周期和正文只派生自已记录的调用／结果片段；分页将调用事件留在窗口外时，则使用 history envelope 中由 Host 携带的持久配对。该行绝不读取当前 skill 目录，因此冷回放在跨分页时，以及已安装的 skill 或其描述发生变化时均保持稳定。 ## 模型体验 diff --git a/packages/client/ui-skill/src/client/SkillRow.tsx b/packages/client/ui-skill/src/client/SkillRow.tsx index be1084ec39..076da55d52 100644 --- a/packages/client/ui-skill/src/client/SkillRow.tsx +++ b/packages/client/ui-skill/src/client/SkillRow.tsx @@ -4,7 +4,7 @@ import { useState, type KeyboardEvent, type ReactNode } from 'react' import { - IconChevronDownOutline14, IconSkillOutline16, StateDot, + IconChevronDownOutline14, IconInspectOutline12, IconSkillOutline16, StateDot, } from '@deepseek-ai/dsh-client-ui-primitives' import type { ToolRowProps } from '@deepseek-ai/dsh-client-ui-conversation/client' import type { PropsLocale } from '@deepseek-ai/dsh-client-ui-slots' @@ -45,7 +45,8 @@ function skillName(argsRaw: string, callId: string): string { return argsRaw === '' ? callId : firstLine(argsRaw) } -/** Flatten the durable result exactly like the generic row's text fallback. */ +/** Flatten durable result blocks under the generic tool-row text contract. + * Keep aligned with ui-conversation's contract/tool-call-model.ts `resultText`. */ function resultText(block: ToolRowProps['block']): string | null { if (!('kind' in block)) return null const parts: string[] = [] @@ -108,15 +109,6 @@ function stateStatus(state: SkillRowState, t: SkillRowProps['t']): string | null } } -/** Inspect affordance glyph shared with the transcript's other tool rows. */ -function IconInspect() { - return ( - - - - ) -} - /** * Render one `skill` tool call as an accent summary and instructions disclosure. * @param props - keyed toolview payload plus the skill locale seat. @@ -129,7 +121,6 @@ export function SkillRow({ block, inspect, t }: SkillRowProps) { const open = expanded && expandable const status = stateStatus(model.state, t) const summary = model.errorSummary ?? model.name - const ariaLabel = status === null ? `Skill ${summary}` : `${status} Skill ${summary}` const toggleExpand = (): void => { setExpanded(value => !value) } @@ -138,18 +129,20 @@ export function SkillRow({ block, inspect, t }: SkillRowProps) { event.preventDefault() toggleExpand() } + const disclosureProps = expandable ? { + role: 'button' as const, + tabIndex: 0, + 'aria-expanded': open, + onClick: toggleExpand, + onKeyDown: toggleFromKeyboard, + } : {} const leading = disclosureLeading(model.state, open, expandable) return (
{leading} {status !== null ? {status} : null} @@ -167,7 +160,7 @@ export function SkillRow({ block, inspect, t }: SkillRowProps) { {inspect !== undefined ? ( ) : null} diff --git a/packages/client/ui-skill/src/invariant.ts b/packages/client/ui-skill/src/invariant.ts index 241482a306..9246466cd1 100644 --- a/packages/client/ui-skill/src/invariant.ts +++ b/packages/client/ui-skill/src/invariant.ts @@ -15,9 +15,10 @@ export const name = 'client-ui-skill-invariant' export const inject = ['invariants'] /** - * No runtime invariant: a single slash-source registration whose disposal is - * proven by the HMR-safety spec — it emits no cordis events and owns no - * cross-plugin mutable state. + * No runtime invariant: the slash source, locale dictionaries, and keyed + * toolview are registry-owned registrations whose disposal is proven by the + * HMR-safety spec. They emit no cordis events and own no cross-plugin mutable + * state. */ const install: InvariantInstaller = () => {} diff --git a/packages/client/ui-skill/tests/browser-plugin.spec.ts b/packages/client/ui-skill/tests/browser-plugin.spec.ts index 3febb36efb..9b047a3713 100644 --- a/packages/client/ui-skill/tests/browser-plugin.spec.ts +++ b/packages/client/ui-skill/tests/browser-plugin.spec.ts @@ -14,6 +14,7 @@ import { Context } from 'cordis' import { describe, expect, it, vi } from 'vitest' import type { SessionId } from '@deepseek-ai/dsh-client-runtime/client' +import { SlotsService } from '@deepseek-ai/dsh-client-runtime/client' import { SlashService } from '@deepseek-ai/dsh-client-ui-slash/client' import type { ClientSessionContext, SlashSource } from '@deepseek-ai/dsh-client-ui-slash/client' import { apply, inject } from '../src/client/index.ts' @@ -25,33 +26,28 @@ type ListResult = | { ok: false; error: { code: string; message: string; details: object } } type ListFn = (payload: object, signal?: AbortSignal) => Promise<{ result: ListResult }> -interface PresentationRegistration { - name: string - key?: string - locale?: string -} - interface PresentationCapture { - registration?: PresentationRegistration - component?: unknown + slots: SlotsService dictionaries: Array<{ namespace: string; dictionaries: unknown }> + localeDisposed: boolean } /** Provide the presentation registries and capture the plugin's registrations. */ function providePresentation(ctx: Context): PresentationCapture { - const capture: PresentationCapture = { dictionaries: [] } + const slots = new SlotsService(ctx) + slots.register({ + name: 'root', + children: { 'conversation.chat.toolview': { kind: 'keyed', scope: 'session' } }, + } as never, () => null) + const capture: PresentationCapture = { + slots, + dictionaries: [], + localeDisposed: false, + } ctx.provide('locale', { register(namespace: string, dictionaries: unknown) { capture.dictionaries.push({ namespace, dictionaries }) - return () => {} - }, - }) - ctx.provide('slots', { - inject(_name: string, factory: () => unknown) { factory() }, - register(registration: PresentationRegistration, component: unknown) { - capture.registration = registration - capture.component = component - return () => {} + return () => { capture.localeDisposed = true } }, }) return capture @@ -110,10 +106,10 @@ describe('apply', () => { ctx.provide('sessions', { subagentAddress: () => undefined }) const presentation = providePresentation(ctx) await ctx.plugin({ inject: [...inject], apply }).await() - expect(presentation.registration).toEqual({ - name: 'conversation.chat.toolview', key: 'skill', locale: 'skill', - }) - expect(presentation.component).toBe(SkillToolRow) + const entry = presentation.slots.entries('conversation.chat.toolview')[0] + expect(entry?.options).toMatchObject({ key: 'skill' }) + expect(entry?.locale).toBe('skill') + expect(entry?.component).toBe(SkillToolRow) expect(presentation.dictionaries).toEqual([{ namespace: 'skill', dictionaries: { zh: { @@ -138,7 +134,7 @@ describe('apply', () => { ctx.provide('sessions', {}) await ctx.plugin(SlashService).await() ctx.provide('connection', { api: { skills: { list: listOk(CATALOG) } } }) - providePresentation(ctx) + const presentation = providePresentation(ctx) const fiber = ctx.plugin({ inject: [...inject], apply }) await fiber.await() const slash = ctx.get('slash') as SlashService @@ -153,6 +149,8 @@ describe('apply', () => { // …and fiber teardown releases it. await fiber.dispose() expect(() => slash.registerSource(rival)).not.toThrow() + expect(presentation.slots.entries('conversation.chat.toolview')).toHaveLength(0) + expect(presentation.localeDisposed).toBe(true) }) }) diff --git a/packages/client/ui-skill/tests/skill-row.spec.tsx b/packages/client/ui-skill/tests/skill-row.spec.tsx index 2dacf0a036..4143b4a7a2 100644 --- a/packages/client/ui-skill/tests/skill-row.spec.tsx +++ b/packages/client/ui-skill/tests/skill-row.spec.tsx @@ -53,7 +53,7 @@ describe('SkillRow', () => { it('renders a compact Bash-shaped summary and discloses the exact instructions', () => { const inspect = vi.fn() const view = render() - const row = screen.getByRole('button', { name: 'Skill dsh-manage-issues' }) + const row = screen.getByRole('button', { name: 'Skilldsh-manage-issues' }) expect(row.getAttribute('aria-expanded')).toBe('false') expect(view.container.querySelector('[data-tool="skill"]')?.getAttribute('data-state')).toBe('ok') expect(view.container.querySelector('[data-tool="skill"] svg')?.getAttribute('width')).toBe('16') @@ -97,7 +97,7 @@ describe('SkillRow', () => { isError: true, error: { name: 'SkillError', code: 'missing' }, }))} />) - const row = screen.getByRole('button', { name: 'skill 加载失败 Skill SkillError: missing resource' }) + const row = screen.getByRole('button', { name: 'skill 加载失败SkillSkillError: missing resource' }) expect(view.container.querySelector('[data-tool="skill"]')?.getAttribute('data-state')).toBe('error') expect(row.textContent).not.toContain('Check SKILL.md.') fireEvent.click(row) @@ -126,7 +126,7 @@ describe('SkillRow', () => { isError: true, error: { name: 'SkillError', code: 'missing' }, }))} />) - const errorRow = screen.getByRole('button', { name: 'skill 加载失败 Skill SkillError: missing' }) + const errorRow = screen.getByRole('button', { name: 'skill 加载失败SkillSkillError: missing' }) fireEvent.click(errorRow) expect(screen.getAllByText('SkillError: missing')).toHaveLength(2) }) diff --git a/packages/host/apiproxy/README.i18n.yaml b/packages/host/apiproxy/README.i18n.yaml index 8ee0d81334..22342f8a24 100644 --- a/packages/host/apiproxy/README.i18n.yaml +++ b/packages/host/apiproxy/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/host/apiproxy/README.md -README.md: 00b9ea075af7eb55041d48ceb3a1363e9de90397 -README.zh.md: e62e3fa99c2908afeca85b7182701f6fcdf19de9 +README.md: 7f5d7b50cf86e251b73e2e67e38939827bd7eb13 +README.zh.md: 71b40929e065981c08a2d2b4fb1e941cbef687ff diff --git a/packages/host/apiproxy/README.md b/packages/host/apiproxy/README.md index 00b9ea075a..7f5d7b50cf 100644 --- a/packages/host/apiproxy/README.md +++ b/packages/host/apiproxy/README.md @@ -12,7 +12,7 @@ The layering/protocol decisions are recorded in the [GUI layering and RPC protoc Question responses are validated against their pending request before the first answer claims it. A multi-select item may carry both requested option labels in `selected` and non-empty `custom` text; a single-select item must use one or the other. Duplicate labels, unknown labels, mismatched ids, incomplete batches, and empty custom text are rejected as `bad-response`. -`session.history` reads an attached Session in memory or inspects a cold log through persistence without resuming or publishing an Agent, then pages on append-origin message boundaries. `maxMessages` counts `user/message` and `assistant/message` events that entered the surface by appending, so a model-only replacement copy consumes no quota. Each page stays one contiguous raw event range, which keeps a compaction's log-only provenance on the same page as the replacement that cites it. +`session.history` reads an attached Session in memory or inspects a cold log through persistence without resuming or publishing an Agent, then pages on append-origin message boundaries. `maxMessages` counts `user/message` and `assistant/message` events that entered the surface by appending, so a model-only replacement copy consumes no quota. Each page stays one contiguous raw event range, which keeps a compaction's log-only provenance on the same page as the replacement that cites it. A `tool/result` entry additionally carries its paired call's name, exact arguments JSON, and event time as a transient history annotation derived from the complete log, so a page cut cannot erase keyed toolview dispatch, argument-derived summaries, or duration. Result render intents use that same complete-log pair; an orphan result or malformed arguments still soft-fall to the generic presentation path. `session.history`'s tail page (`beforeSeq` absent) additionally carries an optional `projections` block — the watermark snapshot of every unit registered on `ctx.sessionProjections` (`@deepseek-ai/dsh-session-projection`), with `asOfSeq` = the last event seq the values reflect (`-1` on an empty log). The gateway also subscribes to the registry's change feed and mints a `session/projection` mux frame per changed unit (`{sessionId, key, value, seq}` — live push state, never logged; clients hold one generic per-session value store under higher-seq-wins). The carrier holds zero domain knowledge (each value passed its unit's own schema inside the registry; the wire schemas keep `values`/`value` wide); loadOlder pages never carry the block, and a composition without the registry serves histories without either surface. diff --git a/packages/host/apiproxy/README.zh.md b/packages/host/apiproxy/README.zh.md index e62e3fa99c..71b40929e0 100644 --- a/packages/host/apiproxy/README.zh.md +++ b/packages/host/apiproxy/README.zh.md @@ -12,7 +12,7 @@ 首个回答认领待处理请求之前，系统会对照该请求校验问题响应。多选题的回答项可以同时携带 `selected` 中的请求选项标签与非空 `custom` 文本；单选题的回答项必须二选一。标签重复、标签未知、id 不匹配、批次不完整以及自定义文本为空都会以 `bad-response` 拒绝。 -`session.history` 按追加来源的消息边界分页：`maxMessages` 统计以追加方式进入 surface 的 `user/message` 和 `assistant/message` 事件，因此仅供模型使用的替换副本不占用配额。每一页仍是一段连续的原始事件区间，从而让压缩（compaction）的仅日志溯源信息与引用它的替换留在同一页。 +`session.history` 按追加来源的消息边界分页：`maxMessages` 统计以追加方式进入 surface 的 `user/message` 和 `assistant/message` 事件，因此仅供模型使用的替换副本不占用配额。每一页仍是一段连续的原始事件区间，从而让压缩（compaction）的仅日志溯源信息与引用它的替换留在同一页。`tool/result` 条目还会携带其配对调用的名称、精确的 arguments JSON 和事件时间，作为从完整日志派生的瞬时 history 注解，因此分页切分无法抹掉键控 toolview 分派、由参数派生的摘要或耗时。结果渲染意图使用完整日志中的同一配对；无配对结果或参数损坏时，仍会软降级到通用呈现路径。 `session.history` 的尾页（不带 `beforeSeq`）额外携带一个可选的 `projections` 块——`ctx.sessionProjections`（`@deepseek-ai/dsh-session-projection`）上每个已注册单元的水位线快照，`asOfSeq` = 这些值共同反映到的最后一个事件 seq（空日志为 `-1`）。网关还订阅注册表的变更流，为每个状态发生变化的单元生成一个 `session/projection` mux 帧（`{sessionId, key, value, seq}`——实时推送状态，绝不入日志；客户端按 seq 高者胜维护一个按会话的通用值仓）。载体不持有任何领域知识（每个值在注册表内部已过其单元自己的 schema；协议 schema 对 `values`/`value` 保持宽松）；loadOlder 页永不携带该块，未装注册表的组合则两个面都不提供。 diff --git a/packages/host/apiproxy/src/api-proxy.ts b/packages/host/apiproxy/src/api-proxy.ts index 928ecc7b55..5b9511de93 100644 --- a/packages/host/apiproxy/src/api-proxy.ts +++ b/packages/host/apiproxy/src/api-proxy.ts @@ -26,7 +26,7 @@ import { // Type-only: brings the `ctx.tools` Context merge into this program (viewFor reads presenters). import type {} from '@deepseek-ai/dsh-tools' import type { - ApiProxy, CredentialView, GoalRef, HistoryEntry, HostFrame, ModelCatalogFailure, ModelProviderGroup, + ApiProxy, CredentialView, GoalRef, HistoryEntry, HistoryToolCall, HostFrame, ModelCatalogFailure, ModelProviderGroup, ModelReasoning, MuxFrame, QuestionResponsePayload, SessionProjectionsBlock, SessionSearchItem, QueuedInboxItem, SessionSummary, SettingsNamespaceView, SubagentAddress, ToolEventView, WorkspaceId, WorkspaceView, @@ -408,9 +408,9 @@ function matchesQuestions(payload: QuestionResponsePayload, pending: PendingQues * Compute the render intent for a tool/call or tool/result event through the * presenters registered at this moment; every other event type gets none. A * result's presenter needs its call's parsed args — `argsFor` supplies them - * (live: the per-session call table; history: an in-page backscan), returning - * undefined when the pairing is unavailable (e.g. the call fell off the page), - * which soft-falls to no view. Presenter or JSON.parse throws also soft-fall: + * (live: the per-session call table; history: the full-log pairing index), + * returning undefined when the pairing is unavailable, which soft-falls to no + * view. Presenter or JSON.parse throws also soft-fall: * the client's documented default (generic JSON card) covers every miss. */ function viewFor(ctx: Context, event: SessionEvent, argsFor: (callId: string) => unknown): ToolEventView | undefined { @@ -442,10 +442,8 @@ function viewFor(ctx: Context, event: SessionEvent, argsFor: (callId: string) => } /** - * Resolve a tool/result's call pairing by scanning a window of events backwards - * for the matching tool/call. Used by the history path (the page is the - * window — a cross-page pairing soft-falls to no view) and by live-path table - * misses after a reconnect-eviction. + * Resolve a tool/result's call pairing by scanning a live session backwards + * for the matching tool/call after the open-call table missed. */ function backscanArgs(events: readonly SessionEvent[], callId: string): { name: string; args: unknown } | undefined { for (let i = events.length - 1; i >= 0; i--) { @@ -463,6 +461,34 @@ function backscanArgs(events: readonly SessionEvent[], callId: string): { name: return undefined } +/** Index durable call metadata once so every history result keeps its pair across page cuts. */ +function historyCallIndex(events: readonly SessionEvent[]): ReadonlyMap { + const calls = new Map() + for (const event of events) { + if (event.type !== 'tool/call') continue + calls.set(String(event.data.callId), { + name: event.data.name, + arguments: event.data.arguments, + time: event.time, + }) + } + return calls +} + +/** Parse one indexed history pair for a result presenter, soft-falling malformed arguments. */ +function historyArgs( + calls: ReadonlyMap, + callId: string, +): { name: string; args: unknown } | undefined { + const call = calls.get(callId) + if (call === undefined) return undefined + try { + return { name: call.name, args: JSON.parse(call.arguments) } + } catch { + return undefined + } +} + /** Render one detached history page through the same presenter path as ordinary history. */ function historyPage( ctx: Context, @@ -471,10 +497,18 @@ function historyPage( maxMessages: number | undefined, ): { events: HistoryEntry[]; hasMore: boolean } { const page = paginate(events, beforeSeq, maxMessages ?? DEFAULT_MAX_MESSAGES) + const calls = historyCallIndex(events) return { events: page.events.map((event) => { - const view = viewFor(ctx, event, callId => backscanArgs(page.events, callId)) - return { event, ...view === undefined ? {} : { view } } + const view = viewFor(ctx, event, callId => historyArgs(calls, callId)) + const call = event.type === 'tool/result' + ? calls.get(String(event.data.message.source.callId)) + : undefined + return { + event, + ...view === undefined ? {} : { view }, + ...call === undefined ? {} : { call }, + } }), hasMore: page.hasMore, } diff --git a/packages/host/apiproxy/src/api/index.ts b/packages/host/apiproxy/src/api/index.ts index 4f10d92853..697e5bdeae 100644 --- a/packages/host/apiproxy/src/api/index.ts +++ b/packages/host/apiproxy/src/api/index.ts @@ -36,7 +36,7 @@ export interface ApiProxy { // ---- Domain interfaces and payload entities ---- export type { - HistoryEntry, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, + HistoryEntry, HistoryToolCall, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, ModelReasoningEffort, ModelTarget, QueueAction, SessionModels, SessionProjectionsBlock, SessionSearchItem, SessionsApi, SessionSummary, } from './sessions.ts' diff --git a/packages/host/apiproxy/src/api/sessions.schema.ts b/packages/host/apiproxy/src/api/sessions.schema.ts index 9f9c4329e6..f47289e77b 100644 --- a/packages/host/apiproxy/src/api/sessions.schema.ts +++ b/packages/host/apiproxy/src/api/sessions.schema.ts @@ -11,7 +11,7 @@ import type { MessageId } from '@deepseek-ai/dsh-llm/brand' import type { RequestPayload, ResponseValue } from './rpc-map.ts' import type { Wire } from './rpc.schema.ts' import type { - HistoryEntry, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, + HistoryEntry, HistoryToolCall, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, ModelReasoningEffort, ModelTarget, SessionProjectionsBlock, SessionSearchItem, SessionSummary, } from './sessions.ts' import type { ToolEventView } from './events.ts' @@ -193,10 +193,18 @@ export const toolEventViewSchema = z.discriminatedUnion('for', [ z.object({ for: z.literal('result'), view: z.looseObject({ card: z.string() }) }), ]) as unknown as z.ZodType -/** One session.history item: the session event plus its optional host-computed tool view. */ +/** Paired tool/call metadata carried with a paged tool/result. */ +export const historyToolCallSchema: z.ZodType> = z.object({ + name: z.string(), + arguments: z.string(), + time: z.number(), +}) + +/** One session.history item: raw event plus optional host-computed tool annotations. */ export const historyEntrySchema: z.ZodType> = z.object({ event: sessionEventSchema, view: toolEventViewSchema.optional(), + call: historyToolCallSchema.optional(), }) as unknown as z.ZodType> /** diff --git a/packages/host/apiproxy/src/api/sessions.ts b/packages/host/apiproxy/src/api/sessions.ts index 18315eef19..2a6da96db9 100644 --- a/packages/host/apiproxy/src/api/sessions.ts +++ b/packages/host/apiproxy/src/api/sessions.ts @@ -26,14 +26,26 @@ declare module '@deepseek-ai/dsh-llm' { } } +/** Paired tool/call metadata carried beside a paged result whose call may be outside the page. */ +export interface HistoryToolCall { + /** Registered tool name used for keyed presentation dispatch. */ + name: string + /** Exact durable arguments JSON from the paired tool/call. */ + arguments: string + /** Unix epoch ms of the paired tool/call event. */ + time: number +} + /** - * One history page entry: the raw event plus the optional host-computed render - * intent (same semantics as the mux frame's `view` slot — a pagination-time - * derivation, never persisted). + * One history page entry: the raw event plus optional host-computed render + * intent and result pairing. Both annotations are pagination-time derivations, + * never persisted; `call` preserves a tool/result's identity when its call + * event lies outside this page. */ export interface HistoryEntry { event: SessionEvent view?: ToolEventView + call?: HistoryToolCall } /** diff --git a/packages/host/apiproxy/tests/api-proxy-view.spec.ts b/packages/host/apiproxy/tests/api-proxy-view.spec.ts index 43083545db..3b19a26b5e 100644 --- a/packages/host/apiproxy/tests/api-proxy-view.spec.ts +++ b/packages/host/apiproxy/tests/api-proxy-view.spec.ts @@ -231,9 +231,50 @@ describe('mux live view computation', () => { ])) expect(byKey.get('tool/call:h-term')?.view).toEqual({ for: 'call', view: { card: 'terminal', title: 'ls' } }) expect(byKey.get('tool/result:h-term')?.view).toEqual({ for: 'result', view: { card: 'terminal', output: 'done' } }) + expect(byKey.get('tool/result:h-term')?.call).toEqual({ + name: 'term', arguments: '{"cmd":"ls"}', time: byKey.get('tool/call:h-term')?.event.time, + }) expect('view' in (byKey.get('tool/result:h-orphan') ?? {})).toBe(false) + expect('call' in (byKey.get('tool/result:h-orphan') ?? {})).toBe(false) expect('view' in (byKey.get('tool/result:h-bad') ?? {})).toBe(false) + expect(byKey.get('tool/result:h-bad')?.call?.arguments).toBe('{broken') expect('view' in (byKey.get('tool/result:h-plain') ?? {})).toBe(false) + expect(byKey.get('tool/result:h-plain')?.call?.name).toBe('plain') + }) + + it('carries a result pair and computes its view when the call is outside the history page', async () => { + const { ctx } = await harness() + const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' }) + const session = ctx.sessions.create() + ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent) + session.append('turn/start', { turn: 1 }) + const call = session.append('tool/call', { + turn: 1, step: 1, callId: CallId('cross-page'), name: 'term', arguments: '{"cmd":"tail"}', + }) + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + session.append('turn/start', { turn: 2 }) + appendUserText(session, 'newer message cuts the page') + const result = session.append('tool/result', { + turn: 1, step: 1, + message: createToolResultMessage({ + callId: CallId('cross-page'), + content: [{ type: 'text', text: 'late result' }], + isError: false, + }), + }, { surfaceOp: 'append' }) + + const response = await api.sessions.history({ + rpcId: RpcId('t-hist-cross-page'), + payload: { sessionId: session.id, maxMessages: 1 }, + }) + if (!response.result.ok) throw new Error('unreachable') + const entries = response.result.value.events + expect(entries.some(entry => entry.event.seq === call.seq)).toBe(false) + const entry = entries.find(candidate => candidate.event.seq === result.seq) + expect(entry).toMatchObject({ + call: { name: 'term', arguments: '{"cmd":"tail"}', time: call.time }, + view: { for: 'result', view: { card: 'terminal', output: 'done' } }, + }) }) it('counts only append-origin messages toward maxMessages and keeps compaction provenance whole', async () => { diff --git a/packages/host/apiproxy/tests/rpc-schemas.spec.ts b/packages/host/apiproxy/tests/rpc-schemas.spec.ts index b65861c1ae..3a76dd9b07 100644 --- a/packages/host/apiproxy/tests/rpc-schemas.spec.ts +++ b/packages/host/apiproxy/tests/rpc-schemas.spec.ts @@ -190,10 +190,16 @@ describe('sessions domain schemas', () => { expect(sessionHistoryRequestSchema.parse({ sessionId: 's1', beforeSeq: 3, maxMessages: 5 }).beforeSeq).toBe(3) expect(() => sessionHistoryRequestSchema.parse({ sessionId: 's1', maxMessages: 0 })).toThrow() expect(sessionHistoryValueSchema.parse({ - events: [], + events: [{ + event: { type: 'tool/result', seq: 3, time: 30, data: {} }, + call: { name: 'skill', arguments: '{"name":"review"}', time: 20 }, + }], hasMore: false, modelTarget: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, - }).hasMore).toBe(false) + })).toMatchObject({ + events: [{ call: { name: 'skill', arguments: '{"name":"review"}', time: 20 } }], + hasMore: false, + }) expect(sessionModelsRequestSchema.parse({ sessionId: 's1' }).sessionId).toBe('s1') expect(sessionModelsValueSchema.parse({ current: { provider: 'deepseek-official', model: 'deepseek-v4-flash', reasoningEffort: 'max' }, From ab94a2f7d6463ba640af5866c4b28908d5dde3b0 Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 6 Aug 2026 17:39:43 +0800 Subject: [PATCH 18/22] refactor(telemetry): centralize the default mode --- docs/config-catalog.md | 2 +- .../telemetry/session-telemetry-otel/src/index.ts | 12 ++++-------- .../session-telemetry-otel/tests/otel.spec.ts | 4 +++- 3 files changed, 8 insertions(+), 10 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index c386ee4e6b..46766c2640 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1193,7 +1193,7 @@ export enum TelemetryMode { Depends on: `BatchLogRecordProcessorOptions` (`@opentelemetry/sdk-logs`) · `OTLPExporterNodeConfigBase` (`@opentelemetry/otlp-exporter-base`) -Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:83`](../packages/telemetry/session-telemetry-otel/src/index.ts) +Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:79`](../packages/telemetry/session-telemetry-otel/src/index.ts) ## `@deepseek-ai/dsh-session-title` diff --git a/packages/telemetry/session-telemetry-otel/src/index.ts b/packages/telemetry/session-telemetry-otel/src/index.ts index f380d97549..36429448c6 100644 --- a/packages/telemetry/session-telemetry-otel/src/index.ts +++ b/packages/telemetry/session-telemetry-otel/src/index.ts @@ -46,12 +46,8 @@ export enum TelemetryMode { DISABLED = 'DISABLED', } -/** Supported session-sharing policies for runtime configuration validation. */ -export const TELEMETRY_MODES = [ - TelemetryMode.FULL, - TelemetryMode.FEEDBACK_ONLY, - TelemetryMode.DISABLED, -] as const +/** Default session-sharing policy for schema and direct construction. */ +export const DEFAULT_TELEMETRY_MODE = TelemetryMode.FULL const DISABLED_FEEDBACK_WARNING = 'session telemetry is DISABLED; nothing will be shared and this feedback remains local' const NON_CANONICAL_FEEDBACK_WARNING = 'session telemetry ignored a feedback event absent from the canonical session log' @@ -59,7 +55,7 @@ const DROP_RECORD: TelemetryBackend['emit'] = () => {} /** Resolve the default and reject unknown runtime values before transport setup. */ function resolveMode(mode: TelemetryMode | undefined): TelemetryMode { - const resolved = mode ?? TelemetryMode.FULL + const resolved = mode ?? DEFAULT_TELEMETRY_MODE switch (resolved) { case TelemetryMode.FULL: case TelemetryMode.FEEDBACK_ONLY: @@ -109,7 +105,7 @@ export interface Config { * axiom (and silently drop every field not re-declared). */ export const Config: z = z.object({ - mode: z.union(TELEMETRY_MODES).default(TelemetryMode.FULL), + mode: z.union(Object.values(TelemetryMode)).default(DEFAULT_TELEMETRY_MODE), exporter: z.any(), processor: z.any(), }) diff --git a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts index f7b3a007c9..f95af8db16 100644 --- a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts +++ b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts @@ -13,7 +13,7 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { recordFeedback } from '@deepseek-ai/dsh-command-feedback' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' -import TelemetryOtel, { Config, TelemetryMode } from '../src/index.ts' +import TelemetryOtel, { Config, DEFAULT_TELEMETRY_MODE, TelemetryMode } from '../src/index.ts' interface Capture { headers: import('node:http').IncomingHttpHeaders @@ -330,6 +330,8 @@ describe('TelemetryOtel config fails loud', () => { expectTypeOf().toEqualTypeOf() expectTypeOf<'FULL'>().not.toExtend() expectTypeOf().toExtend() + expect(DEFAULT_TELEMETRY_MODE).toBe(TelemetryMode.FULL) + expect(Config({}).mode).toBe(DEFAULT_TELEMETRY_MODE) }) it.each([ From 09d1b0d27ff43687970d7b70049dae7843ce8ae4 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 7 Aug 2026 12:50:23 +0800 Subject: [PATCH 19/22] test(web): align skill snapshot with turn actions --- apps/web/tests/snapshots/skill-tool-row/ui.expected.md | 3 --- 1 file changed, 3 deletions(-) diff --git a/apps/web/tests/snapshots/skill-tool-row/ui.expected.md b/apps/web/tests/snapshots/skill-tool-row/ui.expected.md index 7a51aae904..fc1f23d484 100644 --- a/apps/web/tests/snapshots/skill-tool-row/ui.expected.md +++ b/apps/web/tests/snapshots/skill-tool-row/ui.expected.md @@ -7,9 +7,6 @@ - text: Load the snapshot-skill skill with the skill tool, then reply DONE. {{date}} {{clock}} - button "Copy": - img -- button "Branch into a new conversation" [disabled]: - - img -- text: Available only on the last message of a completed turn - button "Context injection @deepseek-ai/dsh-system-prompt": - img - img From 768e2e866fa7681107aff90e055e023c44116957 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 7 Aug 2026 13:56:42 +0800 Subject: [PATCH 20/22] fix(web): keep skill row pairing client-local --- .../2026-08-06-web-skill-tool-row.i18n.yaml | 4 +- .../feature/2026-08-06-web-skill-tool-row.md | 6 +-- .../2026-08-06-web-skill-tool-row.zh.md | 6 +-- packages/client/connection/src/client/api.ts | 2 +- .../client/connection/src/client/fixture.ts | 43 ++++++--------- .../client/connection/src/client/index.ts | 2 +- packages/client/runtime/README.i18n.yaml | 4 +- packages/client/runtime/README.md | 2 +- packages/client/runtime/README.zh.md | 2 +- .../client/session-history/history-fold.ts | 16 ++---- .../src/client/sessions/conversation.ts | 6 +-- .../runtime/src/client/sessions/session.ts | 12 ++--- .../src/client/sessions/transcript-adapter.ts | 26 ++------- packages/client/runtime/tests/fake-api.ts | 4 +- .../client/runtime/tests/history-fold.spec.ts | 14 ----- packages/client/runtime/tests/session.spec.ts | 17 ------ .../runtime/tests/transcript-adapter.spec.ts | 16 ------ .../client/contract/terminal-card-model.ts | 11 ++-- .../ui-conversation/tests/chat-view.spec.tsx | 4 +- packages/client/ui-skill/README.i18n.yaml | 4 +- packages/client/ui-skill/README.md | 3 +- packages/client/ui-skill/README.zh.md | 3 +- packages/host/apiproxy/README.i18n.yaml | 4 +- packages/host/apiproxy/README.md | 2 +- packages/host/apiproxy/README.zh.md | 2 +- packages/host/apiproxy/src/api-proxy.ts | 54 ++++--------------- packages/host/apiproxy/src/api/index.ts | 2 +- .../host/apiproxy/src/api/sessions.schema.ts | 12 +---- packages/host/apiproxy/src/api/sessions.ts | 18 ++----- .../apiproxy/tests/api-proxy-view.spec.ts | 41 -------------- .../host/apiproxy/tests/rpc-schemas.spec.ts | 10 +--- 31 files changed, 79 insertions(+), 273 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml index 237338a7e6..a9ee64e640 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md -2026-08-06-web-skill-tool-row.md: bebcf658de33d133ffea8eb190fb4e8e63bf82ff -2026-08-06-web-skill-tool-row.zh.md: 9377829aab1cb6b347cb837dafe7e7e4afb63868 +2026-08-06-web-skill-tool-row.md: 6583062f38b0e9cff059fa4477313ff6a5bdd2aa +2026-08-06-web-skill-tool-row.zh.md: 3d5c4b712896c2cf41df3ec913c597f7f791486c diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md index bebcf658de..6583062f38 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.md @@ -14,16 +14,16 @@ The Web transcript renders `skill` calls through the generic fallback row, so a The collapsed row uses a 16-pixel document-and-sparkle glyph and the Bash row's neutral hierarchy: tertiary glyph, secondary `Skill` title, caption separator, and tertiary skill name. Running, failed, and interrupted calls retain the transcript's shimmer, error dot and first-line summary, and warning dot semantics. A settled call expands through the whole summary row into a 260-pixel bounded `Instructions` card containing the exact durable result text; the existing trajectory `Inspect` handoff remains available below the card. -The row derives every visible value from the logged call/result slice. It reads the skill name from the recorded `name` argument and the instructions from durable result content, and never joins the current skill catalog for descriptions or provider metadata. Because a history page can contain a `tool/result` after its `tool/call` fell outside the window, the generic `HistoryEntry` envelope now carries the paired call's name, exact arguments JSON, and event time on result entries. The Host derives this transient annotation and the result render intent from the complete log; the runtime prefers an in-window call and otherwise materializes the same `ToolResultNode.call` and `callTime` from the annotation. An orphan result still has `call: null`, and a call-side render intent remains unavailable when its event is outside the page. The existing ACP `skill-load` recording is seeded through the real Web persistence and composition path for a keyless interaction and accessibility snapshot. +The row derives every visible value from a paired call/result slice in the current runtime window. It reads the skill name from the recorded `name` argument and the instructions from durable result content, and never joins the current skill catalog for descriptions or provider metadata. If pagination leaves the call outside the window, the result has no tool identity and remains on the generic fallback rather than extending the history wire contract. The existing ACP `skill-load` recording is seeded through the real Web persistence and composition path for a keyless interaction and accessibility snapshot. ## Alternatives considered - Keep the generic tool row and add only a `skill` color selector in `ui-conversation`. This leaves the redundant input envelope and generic expanded body in place, and makes the conversation package own a domain-specific visual rule. -- Add a new `skill` value to the host tool render-intent union. The keyed client slot already identifies this tool; the cross-page fix belongs to the generic history pairing envelope used by every tool rather than a skill-specific presentation value. +- Add a new `skill` value to the host tool render-intent union. The keyed client slot already identifies this tool when its call is in the runtime window, so a new cross-boundary presentation value adds protocol and snapshot surface without enabling another consumer. - Export the conversation package's private `ToolRow` component for reuse. Client packages intentionally expose contracts rather than cross-package components; exporting it would couple independent feature packages to conversation implementation details. ## Consequences `ui-skill` now depends on the public conversation toolview contract, locale and primitive packages, and React in addition to its reference-source dependencies. It owns a small copy of the disclosure-row chrome, so future global interaction changes must update this registrant alongside the Bash sample and conversation rows. -Cold replay stays deterministic across pagination and when the installed skill catalog changes, and the transcript remains compact until instructions are explicitly expanded. The generic pairing annotation also prevents other keyed tool rows and result presenters from changing identity at a page boundary without persisting duplicate data. The dedicated card intentionally shows the tool's complete framed output rather than extracting only ``, preserving exactly what reached the model and avoiding a second parser for the skill result format. +Cold replay stays deterministic when the installed skill catalog changes, and the transcript remains compact until instructions are explicitly expanded. A result-only history page intentionally uses the generic fallback; keeping this edge case generic preserves the existing history protocol and confines the feature to client presentation. The dedicated card intentionally shows the tool's complete framed output rather than extracting only ``, preserving exactly what reached the model and avoiding a second parser for the skill result format. diff --git a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md index 9377829aab..3d5c4b7128 100644 --- a/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md +++ b/.agents/notes/implemented/feature/2026-08-06-web-skill-tool-row.zh.md @@ -14,16 +14,16 @@ Web transcript（文本记录）通过通用后备行渲染 `skill` 调用，使 收起的行使用 16 像素的文档与闪光组合图标，并沿用 Bash 行的中性色层级：图标采用三级色，`Skill` 标题采用二级色，分隔符采用 caption 色，skill 名称采用三级色。运行、失败和中断调用分别沿用 transcript 的扫光、错误状态点加首行摘要，以及警告状态点语义。已结算调用可以通过整个摘要行展开一个高度上限为 260 像素的 `Instructions` 卡片，其中原样呈现持久化结果文本；用于跳转至 trajectory 的现有 `Inspect` 入口仍保留在卡片下方。 -该行的所有可见值均派生自已记录的调用／结果片段。skill 名称来自已记录的 `name` 参数，指令来自持久化的结果内容；该行绝不关联当前 skill 目录来读取描述或提供方元数据。由于 history 页可能包含 `tool/result`，而与之配对的 `tool/call` 已落在窗口外，通用 `HistoryEntry` envelope 现在会在结果条目上携带配对调用的名称、精确的 arguments JSON 和事件时间。Host 从完整日志派生这份瞬时注解和结果渲染意图；runtime 优先使用窗口内调用，否则从该注解物化出相同的 `ToolResultNode.call` 和 `callTime`。无配对结果仍为 `call: null`；调用事件位于页面外时，调用侧渲染意图仍不可用。现有的 ACP（Agent Client Protocol）`skill-load` 记录经由真实的 Web 持久化与组合路径写入，用于无需密钥的交互和无障碍快照。 +该行的所有可见值均派生自当前 runtime 窗口中已配对的调用／结果片段。skill 名称来自已记录的 `name` 参数，指令来自持久化的结果内容；该行绝不关联当前 skill 目录来读取描述或提供方元数据。如果分页将调用留在窗口外，结果便没有工具身份，并继续使用通用后备路径，而不是扩展 history 协议契约。现有的 ACP（Agent Client Protocol）`skill-load` 记录经由真实的 Web 持久化与组合路径写入，用于无需密钥的交互和无障碍快照。 ## 考虑过的替代方案 - 保留通用工具行，只添加一个 `skill` 颜色选择器，并将其放在 `ui-conversation` 中。该方案仍会保留多余的输入外层结构和通用展开体，也会让 conversation 包拥有特定领域的视觉规则。 -- 在宿主工具渲染意图联合类型中添加新的 `skill` 值。键控客户端 slot 已经能够识别该工具；跨页修复属于所有工具共用的通用 history 配对 envelope，而不是 skill 专用的呈现值。 +- 在宿主工具渲染意图联合类型中添加新的 `skill` 值。键控客户端 slot 在调用位于 runtime 窗口内时已经能够识别该工具，因此新的跨边界呈现值只会增加协议和快照表层，却不会支持其他消费方。 - 导出 conversation 包的私有 `ToolRow` 组件供复用。客户端包刻意对外暴露契约而非跨包组件；导出该组件会使独立功能包耦合到 conversation 的实现细节。 ## 后果 除了引用 source 的依赖外，`ui-skill` 现在还依赖公开的 conversation toolview 契约、locale 包、原语包和 React。它自行保留了一小份折叠展开行 chrome，因此未来的全局交互变更必须与 Bash 示例和 conversation 行同步更新这个注册方。 -无论跨越分页，还是已安装的 skill 目录发生变化，冷回放都保持确定性；在用户显式展开指令前，transcript 保持紧凑。通用配对注解还可防止其他键控工具行和结果 presenter 在分页边界改变身份，同时无需持久化重复数据。专用卡片有意显示工具完整封装的输出，而不是只提取 ``，从而原样保留模型实际收到的内容，也避免为 skill 结果格式再引入一个解析器。 +即使已安装的 skill 目录发生变化，冷回放仍保持确定性；在用户显式展开指令前，transcript 保持紧凑。仅含结果的 history 页有意使用通用后备路径；让这个边缘情况保持通用呈现，可以保留现有 history 协议，并将该功能限定在客户端呈现层。专用卡片有意显示工具完整封装的输出，而不是只提取 ``，从而原样保留模型实际收到的内容，也避免为 skill 结果格式再引入一个解析器。 diff --git a/packages/client/connection/src/client/api.ts b/packages/client/connection/src/client/api.ts index de15a9c67f..6f29b2dda0 100644 --- a/packages/client/connection/src/client/api.ts +++ b/packages/client/connection/src/client/api.ts @@ -7,7 +7,7 @@ export type { ApiProxy, SessionsApi, SessionSearchItem, SessionSummary, HostApi, EventsApi, MuxFrame, HostFrame, - ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, HistoryToolCall, ToolEventView, + ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, ToolEventView, DirectoryEntry, DirectoryListing, WorkspaceApi, WorkspaceId, WorkspaceView, CommandsApi, CommandDescriptor, SkillsApi, SkillEntry, diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index bacbacdd23..dc2f8c5967 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -29,7 +29,7 @@ import type { import type { CommandId } from '@deepseek-ai/dsh-commands/brand' import { deriveEventMessage, foldSurface } from '@deepseek-ai/dsh-session/surface' import type { - ApiProxy, ClientRequest, ClientResponse, HistoryEntry, HistoryToolCall, HostFrame, MuxFrame, RpcReceipt, + ApiProxy, ClientRequest, ClientResponse, HistoryEntry, HostFrame, MuxFrame, RpcReceipt, ModelProviderGroup, ModelTarget, RpcRequest, RpcResponse, RpcResult, ServerRequest, ServerResponse, SessionSummary, ToolCallView, ToolEventView, ToolResultView, WorkspaceId, WorkspaceView, } from './api.ts' @@ -664,33 +664,25 @@ function presentResult(name: string, argsRaw: string, resultText: string): ToolR } } -/** Full-log tool/result pair used by the fixture history envelope and presenter mirror. */ -function pairedHistoryCall(event: SessionEvent, log: readonly SessionEvent[]): HistoryToolCall | undefined { - if (event.type !== 'tool/result') return undefined - const callId = String(event.data.message.source.callId) - for (let i = log.length - 1; i >= 0; i--) { - const candidate = log[i] - /* v8 ignore next -- dense-array guard: i stays within [0, log.length), - so the undefined arm needs a sparse log no code path builds. */ - if (candidate !== undefined && candidate.type === 'tool/call' && String(candidate.data.callId) === callId) { - return { name: candidate.data.name, arguments: candidate.data.arguments, time: candidate.time } - } - } - return undefined -} - -/** Host-side viewFor mirror: tool/call presents from its own args; tool/result uses its full-log pair. */ +/** Host-side viewFor mirror: tool/call presents from its own args; tool/result back-scans the log for the paired call. */ function viewFor(event: SessionEvent, log: readonly SessionEvent[]): ToolEventView | undefined { if (event.type === 'tool/call') { const view = presentCall(event.data.name, event.data.arguments) return view === undefined ? undefined : { for: 'call', view } } if (event.type === 'tool/result') { - const call = pairedHistoryCall(event, log) - if (call === undefined) return undefined - const resultText = event.data.message.content[0].content.map(b => (b.type === 'text' ? b.text : '')).join('') - const view = presentResult(call.name, call.arguments, resultText) - return view === undefined ? undefined : { for: 'result', view } + const callId = String(event.data.message.source.callId) + for (let i = log.length - 1; i >= 0; i--) { + const candidate = log[i] + /* v8 ignore next -- dense-array guard: i stays within [0, log.length), + so the undefined arm needs a sparse log no code path builds. */ + if (candidate !== undefined && candidate.type === 'tool/call' && String(candidate.data.callId) === callId) { + const resultText = event.data.message.content[0].content.map(b => (b.type === 'text' ? b.text : '')).join('') + const view = presentResult(candidate.data.name, candidate.data.arguments, resultText) + return view === undefined ? undefined : { for: 'result', view } + } + } + return undefined // cross-page unpaired: documented default } return undefined } @@ -1055,12 +1047,7 @@ function pageOf( } const events = log.slice(start, end).map((event): HistoryEntry => { const view = viewFor(event, log) - const call = pairedHistoryCall(event, log) - return { - event, - ...view === undefined ? {} : { view }, - ...call === undefined ? {} : { call }, - } + return view === undefined ? { event } : { event, view } }) return { events, hasMore: start > 0 } } diff --git a/packages/client/connection/src/client/index.ts b/packages/client/connection/src/client/index.ts index 83e9722a49..67b47b06c6 100644 --- a/packages/client/connection/src/client/index.ts +++ b/packages/client/connection/src/client/index.ts @@ -13,7 +13,7 @@ import { isLoopbackHostname } from '../loopback-hostname.ts' // ---- Contract re-exports (browser-safe apiproxy channels + core types) ---- export type { ApiProxy, SessionsApi, SessionSearchItem, SessionSummary, HostApi, EventsApi, MuxFrame, HostFrame, - ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, HistoryToolCall, ToolEventView, + ApprovalResponsePayload, QuestionResponsePayload, HistoryEntry, ToolEventView, DirectoryEntry, DirectoryListing, ToolCallView, ToolResultView, WorkspaceApi, WorkspaceId, WorkspaceView, CommandsApi, CommandDescriptor, SkillsApi, SkillEntry, diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index ef94a8834c..23c867e4c0 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/runtime/README.md -README.md: 3d981392ce0314f41fe84bc1adb2b9484a6a5989 -README.zh.md: c05bdb6ebb33c0ffa47e2b54fb1b3d9d25f2fa6d +README.md: 8ac29a4258bbd7456b20c61e547d48c570e84d27 +README.zh.md: 0e065e43ecc571e68d3976d2100eb43959cb2e3d diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index 3d981392ce..8ac29a4258 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -34,7 +34,7 @@ SlotsService gives the renderer separate bare observables for `useSessions` and ## The human transcript -`ConversationSnapshot.nodes` is the human transcript, not the model surface. `TranscriptAdapter` projects the raw window in log order — every append-origin surface event (`isAppendSurfaceEvent`) at its own log position, plus one `CompactionSummaryNode` marker per landed compaction checkpoint — and never consults surface order. A paged `tool/result` first pairs against an in-window `tool/call`, then against the Host-carried complete-log call annotation; `ToolResultNode.call` is null only for a truly orphaned durable result, so a page boundary cannot change keyed toolview dispatch, argument-derived labels, or duration. The call-side render intent remains null when its event is outside the window, while the result intent is already computed by the Host from the complete pair. `SteeringHistory` replays the durable `agent/inbox/spliced` records in that window: a user-origin message claimed from `next-step` becomes a `SteeringMessageNode` when its matching `user/message` lands, a `next-turn` claim stays a user node, and non-user next-step input stays context. `ConversationSnapshot.turnEnds` maps each completed turn in that window to its `turn/end` seq, retaining turn completion independently from the transcript so presentation can require a real boundary before enabling an action. A landed compaction therefore keeps the conversation it shadowed on the model side: the marker reports where the model stopped seeing that history instead of erasing it. Model-only replacement copies stay out: a pruned `tool/result` and a regenerated `assistant/message` rewrite one node for the model and mark no boundary. A checkpoint is a `user/message` carrying the compaction seam's plugin source that **replaced** a surface range; an appending plugin-sourced `user/message` is injected context, not a compaction. Each context node also carries a `provenance` view: `contextProvenance()` reads the durable source alone to decide whether the row is an `inject` or a cross-session `recall`, and to name its producer from the instruction paths, referenced session titles, or plugin id that source already records. The client holds no table of plugin ids, so a renamed or newly mounted producer stays identifiable without a client release and a resumed or foreign log projects exactly like a live one; a source with no readable kind degrades to an unnamed injection. Beside it, `contextForm()` reads the producer-declared `ContextForm` — the second, independent axis: `kind` says who produced the context, `form` says what shape of information it is, so several producers may share one form. A form this UI version does not present projects as null and renders opaque. The adapter's plugin literal is pinned to the seam's own declaration by a type-only import of the cordis-free [`dsh-compact/checkpoint`](../../compact/compact/README.md) leaf, so renaming it there fails `tsc` here; a **value** import of the package would fail the client purity gate, and the package **root** is unreachable even as a type (it reaches `dsh-session`'s root, whose `Context` merge collides the host `sessions` with this program's). +`ConversationSnapshot.nodes` is the human transcript, not the model surface. `TranscriptAdapter` projects the raw window in log order — every append-origin surface event (`isAppendSurfaceEvent`) at its own log position, plus one `CompactionSummaryNode` marker per landed compaction checkpoint — and never consults surface order. `SteeringHistory` replays the durable `agent/inbox/spliced` records in that window: a user-origin message claimed from `next-step` becomes a `SteeringMessageNode` when its matching `user/message` lands, a `next-turn` claim stays a user node, and non-user next-step input stays context. `ConversationSnapshot.turnEnds` maps each completed turn in that window to its `turn/end` seq, retaining turn completion independently from the transcript so presentation can require a real boundary before enabling an action. A landed compaction therefore keeps the conversation it shadowed on the model side: the marker reports where the model stopped seeing that history instead of erasing it. Model-only replacement copies stay out: a pruned `tool/result` and a regenerated `assistant/message` rewrite one node for the model and mark no boundary. A checkpoint is a `user/message` carrying the compaction seam's plugin source that **replaced** a surface range; an appending plugin-sourced `user/message` is injected context, not a compaction. Each context node also carries a `provenance` view: `contextProvenance()` reads the durable source alone to decide whether the row is an `inject` or a cross-session `recall`, and to name its producer from the instruction paths, referenced session titles, or plugin id that source already records. The client holds no table of plugin ids, so a renamed or newly mounted producer stays identifiable without a client release and a resumed or foreign log projects exactly like a live one; a source with no readable kind degrades to an unnamed injection. Beside it, `contextForm()` reads the producer-declared `ContextForm` — the second, independent axis: `kind` says who produced the context, `form` says what shape of information it is, so several producers may share one form. A form this UI version does not present projects as null and renders opaque. The adapter's plugin literal is pinned to the seam's own declaration by a type-only import of the cordis-free [`dsh-compact/checkpoint`](../../compact/compact/README.md) leaf, so renaming it there fails `tsc` here; a **value** import of the package would fail the client purity gate, and the package **root** is unreachable even as a type (it reaches `dsh-session`'s root, whose `Context` merge collides the host `sessions` with this program's). Because the projection is log-ordered, the node array is seq-monotonic by construction: log-only `command/run` / `command/done` nodes splice in by seq, `Session` merges interrupted frozen nodes by their fractional seqs, and a window whose checkpoint cites a shadowed range outside it renders the marker with nothing logged. The marker's summary text comes from the checkpoint's `compact/summary` provenance; a window cut that left the provenance outside makes the row non-expandable rather than empty, and a later page that supplies it resolves the text. Performance contract: one append materializes at most one node and copies the projection only when it adds that node; an event that changes no node keeps the previous array reference (a chunk storm costs nothing), and unchanged nodes keep their object identity. diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index c05bdb6ebb..0e065e43ec 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -34,7 +34,7 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 ## 面向人的 transcript（文本记录） -`ConversationSnapshot.nodes` 是面向人的 transcript，不是模型 surface。`TranscriptAdapter` 按日志顺序投影原始窗口。每个 append 来源的 surface 事件（`isAppendSurfaceEvent`）落在它自己的日志位置上，每次落地的压缩（compaction）检查点还会贡献一个 `CompactionSummaryNode` 标记；适配器从不查询 surface 顺序。分页得到的 `tool/result` 会先与窗口内的 `tool/call` 配对，再与 Host 携带的完整日志调用注解配对；只有持久结果确实没有配对调用时，`ToolResultNode.call` 才为 null，因此分页边界无法改变键控 toolview 分派、由参数派生的标签或耗时。调用事件位于窗口外时，调用侧渲染意图仍为 null，而结果侧渲染意图已经由 Host 基于完整配对计算完成。`SteeringHistory` 会重放该窗口中的持久 `agent/inbox/spliced` 记录：用户来源的消息从 `next-step` 被领取，并以相同身份落成 `user/message` 时，会投影为 `SteeringMessageNode`；从 `next-turn` 领取的消息仍是用户节点，非用户来源的 next-step 输入仍是上下文。`ConversationSnapshot.turnEnds` 把该窗口中的每个已完成轮次映射到其 `turn/end` seq；它独立于 transcript 保留轮次完成状态，使呈现层能够在启用操作前要求存在真实边界。于是一次落地的压缩会保留它在模型侧遮蔽掉的对话：标记报告模型从哪里开始看不见那段历史，而不是把它抹掉。仅模型可见的 replacement 副本不进入记录：被裁剪的 `tool/result` 和重新生成的 `assistant/message` 只为模型重写一个节点，不标记任何边界。检查点是携带压缩 seam 插件来源、且**替换**了一段 surface 范围的 `user/message`；一条 append 的插件来源 `user/message` 是注入上下文，不是压缩。每个上下文节点还携带一份 `provenance` 视图：`contextProvenance()` 只读取持久来源，据此判定该行是 `inject`（注入）还是跨会话的 `recall`（召回），并用该来源已经记录的指令文件路径、被引用会话标题或插件 id 命名其生产者。客户端不保存任何插件 id 表，因此重命名或新挂载的生产者无需客户端发版即可保持可辨识，恢复的会话日志与外部日志的投影结果和实时会话完全一致；没有可读 kind 的来源则降级为无名注入。与之并列的 `contextForm()` 读取生产方声明的 `ContextForm`，这是相互独立的第二根轴：`kind` 说明上下文由谁产生，`form` 说明它是何种形态的信息，因此多个生产方可以共用一种形态。本 UI 版本不呈现的形态投影为 null，按 opaque 渲染。适配器的插件字面量通过对无 cordis 的 [`dsh-compact/checkpoint`](../../compact/compact/README.md) 叶子做仅类型导入，钉在压缩 seam 自己的声明上：在那里改名会让此处 `tsc` 失败；而对该包（package）做**值**导入会被客户端纯度门禁拒绝，包的**根**即便作为类型也无法到达（它会到达 `dsh-session` 的根，其 `Context` 合并会让 host 的 `sessions` 与本程序的冲突）。 +`ConversationSnapshot.nodes` 是面向人的 transcript，不是模型 surface。`TranscriptAdapter` 按日志顺序投影原始窗口。每个 append 来源的 surface 事件（`isAppendSurfaceEvent`）落在它自己的日志位置上，每次落地的压缩（compaction）检查点还会贡献一个 `CompactionSummaryNode` 标记；适配器从不查询 surface 顺序。`SteeringHistory` 会重放该窗口中的持久 `agent/inbox/spliced` 记录：用户来源的消息从 `next-step` 被领取，并以相同身份落成 `user/message` 时，会投影为 `SteeringMessageNode`；从 `next-turn` 领取的消息仍是用户节点，非用户来源的 next-step 输入仍是上下文。`ConversationSnapshot.turnEnds` 把该窗口中的每个已完成轮次映射到其 `turn/end` seq；它独立于 transcript 保留轮次完成状态，使呈现层能够在启用操作前要求存在真实边界。于是一次落地的压缩会保留它在模型侧遮蔽掉的对话：标记报告模型从哪里开始看不见那段历史，而不是把它抹掉。仅模型可见的 replacement 副本不进入记录：被裁剪的 `tool/result` 和重新生成的 `assistant/message` 只为模型重写一个节点，不标记任何边界。检查点是携带压缩 seam 插件来源、且**替换**了一段 surface 范围的 `user/message`；一条 append 的插件来源 `user/message` 是注入上下文，不是压缩。每个上下文节点还携带一份 `provenance` 视图：`contextProvenance()` 只读取持久来源，据此判定该行是 `inject`（注入）还是跨会话的 `recall`（召回），并用该来源已经记录的指令文件路径、被引用会话标题或插件 id 命名其生产者。客户端不保存任何插件 id 表，因此重命名或新挂载的生产者无需客户端发版即可保持可辨识，恢复的会话日志与外部日志的投影结果和实时会话完全一致；没有可读 kind 的来源则降级为无名注入。与之并列的 `contextForm()` 读取生产方声明的 `ContextForm`，这是相互独立的第二根轴：`kind` 说明上下文由谁产生，`form` 说明它是何种形态的信息，因此多个生产方可以共用一种形态。本 UI 版本不呈现的形态投影为 null，按 opaque 渲染。适配器的插件字面量通过对无 cordis 的 [`dsh-compact/checkpoint`](../../compact/compact/README.md) 叶子做仅类型导入，钉在压缩 seam 自己的声明上：在那里改名会让此处 `tsc` 失败；而对该包（package）做**值**导入会被客户端纯度门禁拒绝，包的**根**即便作为类型也无法到达（它会到达 `dsh-session` 的根，其 `Context` 合并会让 host 的 `sessions` 与本程序的冲突）。 由于投影按日志顺序，节点数组天然按 seq 单调：仅日志的 `command/run` / `command/done` 节点按 seq 插入，`Session` 按分数 seq 归并被打断的冻结节点，而检查点所引范围落在窗口之外的窗口会渲染出标记且不打印任何日志。标记的摘要文本来自检查点的 `compact/summary` 溯源；窗口切分把溯源留在窗口外时该行不可展开而非空白，后续补上溯源的分页会解析出文本。性能契约：一次追加最多物化一个节点，并且仅在加入该节点时复制投影；不改变任何节点的事件保持上一次的数组引用（分片风暴零成本），未变化的节点保持其对象标识。 diff --git a/packages/client/runtime/src/client/session-history/history-fold.ts b/packages/client/runtime/src/client/session-history/history-fold.ts index 83a09d3163..d792fd2b76 100644 --- a/packages/client/runtime/src/client/session-history/history-fold.ts +++ b/packages/client/runtime/src/client/session-history/history-fold.ts @@ -362,8 +362,7 @@ export function projectConversationHistory( let contextGeneration = 0 for (const [index, event] of events.entries()) { - const entry = entries[index] - const view = entry?.view + const view = entries[index]?.view if (event.type === 'tool/call') { callIndex.set(String(event.data.callId), { name: event.data.name, @@ -371,17 +370,8 @@ export function projectConversationHistory( time: event.time, callView: view?.for === 'call' ? view.view : null, }) - } else if (event.type === 'tool/result') { - const callId = String(event.data.message.source.callId) - if (!callIndex.has(callId) && entry?.call !== undefined) { - callIndex.set(callId, { - name: entry.call.name, - argsRaw: entry.call.arguments, - time: entry.call.time, - callView: null, - }) - } - if (view?.for === 'result') resultViews.set(event.seq, view.view) + } else if (event.type === 'tool/result' && view?.for === 'result') { + resultViews.set(event.seq, view.view) } if (isSurfaceEvent(event) && event.surfaceOp !== 'append') { contextGeneration++ diff --git a/packages/client/runtime/src/client/sessions/conversation.ts b/packages/client/runtime/src/client/sessions/conversation.ts index 14bd0dc9ed..d24b963d6b 100644 --- a/packages/client/runtime/src/client/sessions/conversation.ts +++ b/packages/client/runtime/src/client/sessions/conversation.ts @@ -155,16 +155,16 @@ export interface TurnErrorNode { code?: string } -/** A tool result paired with its durable call head when the Host can resolve it. */ +/** A tool result paired (when in-window) with its call head. */ export interface ToolResultNode { kind: 'tool-result' seq: number /** Unix epoch ms from the tool/result session event. */ time: number callId: string - /** Call head from the window or history envelope; null only when the durable log has no pair (card head shows callId). */ + /** Call head backfilled from the in-window tool/call; null when window truncation left the call outside (card head shows callId). */ call: { name: string; argsRaw: string } | null - /** Unix epoch ms of the paired tool/call; null when the durable log has no pair. */ + /** Unix epoch ms of the paired tool/call when the call is still in-window; used for call-row duration. */ callTime: number | null content: readonly ContentBlock[] isError: boolean diff --git a/packages/client/runtime/src/client/sessions/session.ts b/packages/client/runtime/src/client/sessions/session.ts index e663af8bf6..776f4494fd 100644 --- a/packages/client/runtime/src/client/sessions/session.ts +++ b/packages/client/runtime/src/client/sessions/session.ts @@ -5,7 +5,7 @@ import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' import type { LlmRetryEventData } from '@deepseek-ai/dsh-llm-retry/types' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import type { - HistoryEntry, HistoryToolCall, IApiClient, MessageId, MuxFrame, QueueAction, RpcError, + HistoryEntry, IApiClient, MessageId, MuxFrame, QueueAction, RpcError, RpcId, RpcResponse, RpcResult, SessionId, SubagentAddress, ToolEventView, } from '@deepseek-ai/dsh-client-connection/client' // Value import from the inline-safe wire layer (not the connection plugin): @@ -85,8 +85,6 @@ export class Session implements SessionFace { /** Wire views aligned with `events` by index (envelope-level annotations; undefined = no view). * Kept parallel rather than merged so `events` stays the raw log slice (model-visible ⟺ logged). */ private views: (ToolEventView | undefined)[] = [] - /** Host-carried call metadata aligned with result entries when the call event is outside the page. */ - private historyCalls: (HistoryToolCall | undefined)[] = [] private baseSeq = 0 private hasMore = false private openState: OpenState = 'cold' @@ -383,11 +381,10 @@ export class Session implements SessionFace { } this.events = [...older.map(e => e.event), ...this.events] this.views = [...older.map(e => e.view), ...this.views] - this.historyCalls = [...older.map(e => e.call), ...this.historyCalls] /* v8 ignore next -- the ?? arm needs older[0] undefined, but the empty-page branch above already returned. */ this.baseSeq = older[0]?.event.seq ?? this.baseSeq this.hasMore = result.value.hasMore - this.transcript.reset(this.events, this.views, this.historyCalls) // prepend forces a rebuild (the window grew at the head) + this.transcript.reset(this.events, this.views) // prepend forces a rebuild (the window grew at the head) this.rebuildDerivedFromWindow() } catch (error) { console.error('[web-runtime] loadOlder failed:', error) @@ -414,7 +411,6 @@ export class Session implements SessionFace { this.openError = null this.events = [] this.views = [] - this.historyCalls = [] this.baseSeq = 0 // Superseded, not settled: the baseline replay re-sends still-pending requested frames verbatim // (same rpcId), re-minting fresh waits; a stale reference's respond() still reaches the host. @@ -648,10 +644,9 @@ export class Session implements SessionFace { private installWindow(entries: HistoryEntry[], hasMore: boolean, projections?: ProjectionsBaseline): void { this.events = entries.map(e => e.event) this.views = entries.map(e => e.view) - this.historyCalls = entries.map(e => e.call) this.baseSeq = this.events[0]?.seq ?? 0 this.hasMore = hasMore - this.transcript.reset(this.events, this.views, this.historyCalls) + this.transcript.reset(this.events, this.views) this.rebuildDerivedFromWindow() if (projections !== undefined) this.projections.seed(projections) const buffered = this.liveBuffer @@ -666,7 +661,6 @@ export class Session implements SessionFace { if (tailSeq !== null && event.seq <= tailSeq) return // replay overlap, drop this.events.push(event) this.views.push(view) - this.historyCalls.push(undefined) this.transcript.append(event, view) this.handoffPendingSteering(event) this.applyEventSideEffects(event, view) diff --git a/packages/client/runtime/src/client/sessions/transcript-adapter.ts b/packages/client/runtime/src/client/sessions/transcript-adapter.ts index b1d952b804..306571b2bf 100644 --- a/packages/client/runtime/src/client/sessions/transcript-adapter.ts +++ b/packages/client/runtime/src/client/sessions/transcript-adapter.ts @@ -19,9 +19,7 @@ import type { CommandId } from '@deepseek-ai/dsh-commands/brand' // `sessions: ISessions` (TS2717, the one-program-per-side rule in // docs/development.md). import type { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact/checkpoint' -import type { - HistoryToolCall, ToolCallView, ToolEventView, ToolResultView, -} from '@deepseek-ai/dsh-client-connection/client' +import type { ToolCallView, ToolEventView, ToolResultView } from '@deepseek-ai/dsh-client-connection/client' import type { CommandNode, CompactionSummaryNode, ConversationNode } from './conversation.ts' import { toAssistantBlocks } from './conversation.ts' import { contextForm, contextProvenance } from './context-provenance.ts' @@ -215,13 +213,8 @@ export class TranscriptAdapter { * and re-project the transcript. * @param events - the new window contents (seq-ascending). * @param views - per-event wire views aligned with `events` by index (undefined slots for view-less events). - * @param calls - host-carried result pairs aligned with `events` by index. */ - reset( - events: readonly SessionEvent[], - views?: readonly (ToolEventView | undefined)[], - calls?: readonly (HistoryToolCall | undefined)[], - ): void { + reset(events: readonly SessionEvent[], views?: readonly (ToolEventView | undefined)[]): void { this.rev++ this.eventIndex = new Map() this.callIdx = new Map() @@ -235,7 +228,7 @@ export class TranscriptAdapter { /* v8 ignore next -- dense-array guard: i stays within events.length, so the undefined arm needs a sparse array no caller builds. */ if (event === undefined) continue this.eventIndex.set(event.seq, event) - this.indexCall(event, views?.[i], calls?.[i]) + this.indexCall(event, views?.[i]) this.indexCommand(event) if (this.steeringHistory.apply(event)) steeringSeqs.add(event.seq) indexAssistantStepTiming(this.stepTimings, event) @@ -345,20 +338,9 @@ export class TranscriptAdapter { return true } - private indexCall(event: SessionEvent, view?: ToolEventView, pairedCall?: HistoryToolCall): void { + private indexCall(event: SessionEvent, view?: ToolEventView): void { if (event.type === 'tool/result') { if (view?.for === 'result') this.resultViews.set(event.seq, view.view) - const callId = String(event.data.message.source.callId) - if (!this.callIdx.has(callId) && pairedCall !== undefined) { - this.callIdx.set(callId, { - name: pairedCall.name, - argsRaw: pairedCall.arguments, - turn: event.data.turn, - step: event.data.step, - time: pairedCall.time, - callView: null, - }) - } return } if (event.type !== 'tool/call') return diff --git a/packages/client/runtime/tests/fake-api.ts b/packages/client/runtime/tests/fake-api.ts index b13e27f3c4..e50574d102 100644 --- a/packages/client/runtime/tests/fake-api.ts +++ b/packages/client/runtime/tests/fake-api.ts @@ -3,7 +3,7 @@ // deferred-controlled timing). Streams are hand pumps: pushMux/pushHost. import type { CommandId } from '@deepseek-ai/dsh-commands/brand' import type { - ClientResponse, CommandDescriptor, HistoryEntry, HostFrame, IApiClient, ModelTarget, MuxFrame, + ClientResponse, CommandDescriptor, HostFrame, IApiClient, ModelTarget, MuxFrame, RpcError, RpcReceipt, RpcRequest, RpcResponse, SessionId, SessionModels, SessionSearchItem, SkillEntry, WorkspaceId, WorkspaceView, } from '@deepseek-ai/dsh-client-connection/client' @@ -68,7 +68,7 @@ export class FakeApiClient implements IApiClient { onRename: (payload: unknown) => Promise> = () => Promise.resolve(ok({ title: 'fk-renamed', seq: 0 })) onFork: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-fork' as SessionId })) onHistory: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number }) - => Promise> = + => Promise> = () => Promise.resolve(ok({ events: [], hasMore: false })) onModels: (payload: unknown) => Promise> = () => Promise.resolve(ok({ diff --git a/packages/client/runtime/tests/history-fold.spec.ts b/packages/client/runtime/tests/history-fold.spec.ts index f9b40bdb7c..083bdc3566 100644 --- a/packages/client/runtime/tests/history-fold.spec.ts +++ b/packages/client/runtime/tests/history-fold.spec.ts @@ -53,20 +53,6 @@ describe('projectConversationHistory', () => { }]) }) - it('projects a paged tool result from its host-carried call pair', () => { - const result = ev.toolResult(50, 3, 'outside-call', '已加载 skill') - const projection = projectConversationHistory([{ - event: result, - call: { name: 'skill', arguments: '{"name":"dsh-code-review"}', time: 40 }, - }]) - expect(projection.eventNodes).toMatchObject([{ - kind: 'tool-result', - call: { name: 'skill', argsRaw: '{"name":"dsh-code-review"}' }, - callTime: 40, - callView: null, - }]) - }) - it('projects a high-sequence history window without synthesizing its unloaded prefix', () => { const baseSeq = 400_000 const events = [ diff --git a/packages/client/runtime/tests/session.spec.ts b/packages/client/runtime/tests/session.spec.ts index 02753fe09e..c288c044ee 100644 --- a/packages/client/runtime/tests/session.spec.ts +++ b/packages/client/runtime/tests/session.spec.ts @@ -53,23 +53,6 @@ describe('open', () => { expect(snapshot.turnEnds.get(3)).toBe(15) }) - it('installs host-carried call metadata for a result-only tail page', async () => { - const { api, session } = makeSession() - api.onHistory = () => Promise.resolve(ok({ - events: [{ - event: ev.toolResult(50, 3, 'outside-call', '已加载 skill'), - call: { name: 'skill', arguments: '{"name":"dsh-code-review"}', time: 40 }, - }], - hasMore: true, - })) - await session.open() - expect(session.getSnapshot().nodes).toMatchObject([{ - kind: 'tool-result', - call: { name: 'skill', argsRaw: '{"name":"dsh-code-review"}' }, - callTime: 40, - }]) - }) - it('is idempotent: concurrent opens share one history call, reopening when open is a no-op', async () => { const { api, session } = makeSession() await Promise.all([session.open(), session.open()]) diff --git a/packages/client/runtime/tests/transcript-adapter.spec.ts b/packages/client/runtime/tests/transcript-adapter.spec.ts index 99b4cdf261..031acf1780 100644 --- a/packages/client/runtime/tests/transcript-adapter.spec.ts +++ b/packages/client/runtime/tests/transcript-adapter.spec.ts @@ -365,22 +365,6 @@ describe('TranscriptAdapter', () => { expect(adapter.nodes()[0]).toMatchObject({ kind: 'tool-result', callId: 'outside-call', call: null }) }) - it('materializes a paged tool-result from its host-carried call pair', () => { - const adapter = new TranscriptAdapter() - adapter.reset( - [ev.toolResult(50, 3, 'outside-call', '已加载 skill')], - [undefined], - [{ name: 'skill', arguments: '{"name":"dsh-code-review"}', time: 40 }], - ) - expect(adapter.nodes()[0]).toMatchObject({ - kind: 'tool-result', - callId: 'outside-call', - call: { name: 'skill', argsRaw: '{"name":"dsh-code-review"}' }, - callTime: 40, - callView: null, - }) - }) - it('materializes a tool-result error field when present', () => { const adapter = new TranscriptAdapter() adapter.reset([ diff --git a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts index b1c4cbe757..8a0c887990 100644 --- a/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts +++ b/packages/client/ui-conversation/src/client/contract/terminal-card-model.ts @@ -168,12 +168,11 @@ function collapse(body: string, rooted: boolean, separator = '/'): string { * returns a generic fenced card for an execution error or a background * start, whose text and error styling the generic path preserves. * - * Window truncation can drop the call event and its call-side view from a - * settled result (see `ToolResultNode.callView` in dsh-client-runtime), leaving - * a terminal result with no presentation call side even though the history - * envelope preserves its name and arguments. That still renders: the command - * falls back to the result view's replacement title, then to an empty command - * (the prompt line draws bare), and the prompt shows no cwd. + * Window truncation can drop the call head from a settled result (see + * `ToolResultNode.call`/`callView` in dsh-client-runtime), leaving a terminal + * result with no call side. That still renders: the command falls back to the + * result view's replacement title, then to an empty command (the prompt line + * draws bare), and the prompt shows no cwd. * @param block - RunningToolCall or ToolResultNode off the snapshot caches. * @param sessionCwd - the session workspace root, which resolves an omitted or * relative view cwd (see {@link resolveTerminalCwd}); absent leaves both unresolved. diff --git a/packages/client/ui-conversation/tests/chat-view.spec.tsx b/packages/client/ui-conversation/tests/chat-view.spec.tsx index f0ed99da14..2369e8f1d6 100644 --- a/packages/client/ui-conversation/tests/chat-view.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-view.spec.tsx @@ -285,12 +285,12 @@ describe('chat-flow derivation', () => { }) describe('ChatView', () => { - it('an orphan tool result renders through the generic fallback', () => { + it('a windowless tool result (call head truncated) renders with an empty tool name', () => { const h = makeHarness({ nodes: [{ ...toolResult(3, 'w1'), call: null }], }) const view = render() - // No durable call exists for this id, so the summary falls back to callId. + // classifyTool('') → others; the summary slot falls back to the callId. expect(view.container.querySelector('[data-variant="others"]')).not.toBeNull() expect(view.getByText('w1')).toBeTruthy() }) diff --git a/packages/client/ui-skill/README.i18n.yaml b/packages/client/ui-skill/README.i18n.yaml index 5c50d22b89..57a1ff1676 100644 --- a/packages/client/ui-skill/README.i18n.yaml +++ b/packages/client/ui-skill/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-skill/README.md -README.md: ba9f1faae0f70a0f7bed4641e02703cc26bcb692 -README.zh.md: f8210a885d201cbdc89d7a34704a819e80463d2c +README.md: a9506fe563b94fb4d1f9afd882216e023b0c2d13 +README.zh.md: 6af5d3eb8820dacc2ab569be8b830481dd45fb9a diff --git a/packages/client/ui-skill/README.md b/packages/client/ui-skill/README.md index ba9f1faae0..a9506fe563 100644 --- a/packages/client/ui-skill/README.md +++ b/packages/client/ui-skill/README.md @@ -10,7 +10,7 @@ The `/client` export surface is the plugin body (`apply`/`inject`) only; the sou ## Skill tool row -The browser plugin also registers a keyed `skill` toolview in `conversation.chat.toolview`. A collapsed row renders the 16-pixel skill document-and-sparkle glyph, `Skill` title, separator, and requested skill name with the same neutral hierarchy as the Bash row; running calls carry the transcript shimmer, failures replace the name with the first error line, and interrupted calls use the warning state. A settled row expands as one whole-row disclosure into a bounded `Instructions` card containing the exact durable tool output, with the standard trajectory `Inspect` affordance when available. The row derives its name, lifecycle, and body only from the logged call/result slice, using the history envelope's host-carried durable pair when pagination left the call event outside the window; it never reads the current catalog, so cold replay remains stable across page cuts and when installed skills or their descriptions change. +The browser plugin also registers a keyed `skill` toolview in `conversation.chat.toolview`. A collapsed row renders the 16-pixel skill document-and-sparkle glyph, `Skill` title, separator, and requested skill name with the same neutral hierarchy as the Bash row; running calls carry the transcript shimmer, failures replace the name with the first error line, and interrupted calls use the warning state. A settled row expands as one whole-row disclosure into a bounded `Instructions` card containing the exact durable tool output, with the standard trajectory `Inspect` affordance when available. The row derives its name, lifecycle, and body only from a paired call/result slice in the current runtime window, never from the current catalog, so replay remains stable when installed skills or their descriptions change. ## Model Experience @@ -30,6 +30,7 @@ Append-only: the reference is part of a new user message appended after the reus ## Known Limitations and Deferred Work +- **Result-only history pages use the generic row** — keyed dispatch needs the paired call in the runtime window; pagination that leaves the call outside has no tool identity. This client presentation feature does not extend the history wire contract to recover it. - **Non-deterministic skill loading** — the reference is a collaboration cue, not a guarantee; the model may ignore it. The rework path when hit rate proves insufficient (a host-side `context/skill-reference` guidance package, or full-text injection) sits in the design ledger; the wire text shape would not change. - **First keystroke may race the prewarm** — the scope-birth warm launches the catalog fetch, but a menu opened before it settles shows no skill candidates for that keystroke. Accepted by design: skill references do not participate in enter adjudication, so nothing correctness-bearing waits on the catalog. - **Text is the truth** — the reference is plain draft text; a hand-typed identical token is the same reference. Chip visuals derive from the lexicon scan; no occurrence identity or position tracking (componentized chips are a ledger item). diff --git a/packages/client/ui-skill/README.zh.md b/packages/client/ui-skill/README.zh.md index f8210a885d..6af5d3eb88 100644 --- a/packages/client/ui-skill/README.zh.md +++ b/packages/client/ui-skill/README.zh.md @@ -10,7 +10,7 @@ skill（技能）引用 source 的浏览器端：把 `/` 触发的 `skill` sourc ## skill 工具行 -浏览器插件还会把一个 key 为 `skill` 的 toolview 注册进 `conversation.chat.toolview`。收起的行以与 Bash 行相同的中性色层级显示 16 像素的 skill 文档与闪光组合图标、`Skill` 标题、分隔符和请求加载的 skill 名称；运行中的调用带有 transcript（文本记录）的扫光效果，失败时用错误首行替换名称，中断调用则使用警告状态。已结算的行以整行作为展开入口，展开后显示一个尺寸受限的 `Instructions` 卡片，其中原样呈现持久化的工具输出；可用时还会提供标准执行轨迹的 `Inspect` 入口。该行的名称、生命周期和正文只派生自已记录的调用／结果片段；分页将调用事件留在窗口外时，则使用 history envelope 中由 Host 携带的持久配对。该行绝不读取当前 skill 目录，因此冷回放在跨分页时，以及已安装的 skill 或其描述发生变化时均保持稳定。 +浏览器插件还会把一个 key 为 `skill` 的 toolview 注册进 `conversation.chat.toolview`。收起的行以与 Bash 行相同的中性色层级显示 16 像素的 skill 文档与闪光组合图标、`Skill` 标题、分隔符和请求加载的 skill 名称；运行中的调用带有 transcript（文本记录）的扫光效果，失败时用错误首行替换名称，中断调用则使用警告状态。已结算的行以整行作为展开入口，展开后显示一个尺寸受限的 `Instructions` 卡片，其中原样呈现持久化的工具输出；可用时还会提供标准执行轨迹的 `Inspect` 入口。该行的名称、生命周期和正文只派生自当前 runtime 窗口中已配对的调用／结果片段，绝不读取当前 skill 目录，因此即使已安装的 skill 或其描述发生变化，回放仍保持稳定。 ## 模型体验 @@ -30,6 +30,7 @@ skill（技能）引用 source 的浏览器端：把 `/` 触发的 `skill` sourc ## 已知限制与暂缓事项 +- **仅含结果的 history 页使用通用行**：键控分派要求配对调用位于 runtime 窗口内；分页将调用留在窗口外时，结果没有工具身份。这项客户端呈现功能不会为了恢复该身份而扩展 history 协议契约。 - **skill 加载具有非确定性**：引用是协作线索，不是保证；模型可能忽略它。针对命中率不足情况的返工路径（host 侧 `context/skill-reference` 引导包，或全文注入）记录在设计台账中；协议中的文本形态不会改变。 - **首次击键可能与预热竞速**：scope 创建时的预热会启动目录拉取，但目录落定之前打开的菜单，在那次击键下不会显示 skill 候选。这是设计上接受的取舍：skill 引用不参与回车裁决，因此没有任何攸关正确性的环节等待目录。 - **文本是唯一依据**：引用是普通的草稿文本；手动键入的相同 token 就是同一个引用。chip 视觉由 lexicon 扫描派生；没有 occurrence 身份或位置跟踪（组件化 chip 是台账事项）。 diff --git a/packages/host/apiproxy/README.i18n.yaml b/packages/host/apiproxy/README.i18n.yaml index f587ca109e..38c79f4617 100644 --- a/packages/host/apiproxy/README.i18n.yaml +++ b/packages/host/apiproxy/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/host/apiproxy/README.md -README.md: bd8ad485980348a23054d5446d292ef0c24536dd -README.zh.md: 7906ca224930736f335dcbdedc63b6af3019c070 +README.md: 0963476a767801b465a6ead24feb0ecc9988b5f5 +README.zh.md: e3634c5f92f3a3723eb3c14e39223d9d9550c6f9 diff --git a/packages/host/apiproxy/README.md b/packages/host/apiproxy/README.md index bd8ad48598..0963476a76 100644 --- a/packages/host/apiproxy/README.md +++ b/packages/host/apiproxy/README.md @@ -12,7 +12,7 @@ The layering/protocol decisions are recorded in the [GUI layering and RPC protoc Question responses are validated against their pending request before the first answer claims it. A multi-select item may carry both requested option labels in `selected` and non-empty `custom` text; a single-select item must use one or the other. Duplicate labels, unknown labels, mismatched ids, incomplete batches, and empty custom text are rejected as `bad-response`. -`session.history` reads an attached Session in memory or inspects a cold log through persistence without resuming or publishing an Agent, then pages on append-origin message boundaries. `maxMessages` counts `user/message` and `assistant/message` events that entered the surface by appending, so a model-only replacement copy consumes no quota. Each page stays one contiguous raw event range, which keeps a compaction's log-only provenance on the same page as the replacement that cites it. A `tool/result` entry additionally carries its paired call's name, exact arguments JSON, and event time as a transient history annotation derived from the complete log, so a page cut cannot erase keyed toolview dispatch, argument-derived summaries, or duration. Result render intents use that same complete-log pair; an orphan result or malformed arguments still soft-fall to the generic presentation path. +`session.history` reads an attached Session in memory or inspects a cold log through persistence without resuming or publishing an Agent, then pages on append-origin message boundaries. `maxMessages` counts `user/message` and `assistant/message` events that entered the surface by appending, so a model-only replacement copy consumes no quota. Each page stays one contiguous raw event range, which keeps a compaction's log-only provenance on the same page as the replacement that cites it. `session.history`'s tail page (`beforeSeq` absent) additionally carries an optional `projections` block — the watermark snapshot of every unit registered on `ctx.sessionProjections` (`@deepseek-ai/dsh-session-projection`), with `asOfSeq` = the last event seq the values reflect (`-1` on an empty log). The gateway also subscribes to the registry's change feed and mints a `session/projection` mux frame per changed unit (`{sessionId, key, value, seq}` — live push state, never logged; clients hold one generic per-session value store under higher-seq-wins). The carrier holds zero domain knowledge (each value passed its unit's own schema inside the registry; the wire schemas keep `values`/`value` wide); loadOlder pages never carry the block, and a composition without the registry serves histories without either surface. diff --git a/packages/host/apiproxy/README.zh.md b/packages/host/apiproxy/README.zh.md index 7906ca2249..e3634c5f92 100644 --- a/packages/host/apiproxy/README.zh.md +++ b/packages/host/apiproxy/README.zh.md @@ -12,7 +12,7 @@ 首个回答认领待处理请求之前，系统会对照该请求校验问题响应。多选题的回答项可以同时携带 `selected` 中的请求选项标签与非空 `custom` 文本；单选题的回答项必须二选一。标签重复、标签未知、id 不匹配、批次不完整以及自定义文本为空都会以 `bad-response` 拒绝。 -`session.history` 按追加来源的消息边界分页：`maxMessages` 统计以追加方式进入 surface 的 `user/message` 和 `assistant/message` 事件，因此仅供模型使用的替换副本不占用配额。每一页仍是一段连续的原始事件区间，从而让压缩（compaction）的仅日志溯源信息与引用它的替换留在同一页。`tool/result` 条目还会携带其配对调用的名称、精确的 arguments JSON 和事件时间，作为从完整日志派生的瞬时 history 注解，因此分页切分无法抹掉键控 toolview 分派、由参数派生的摘要或耗时。结果渲染意图使用完整日志中的同一配对；无配对结果或参数损坏时，仍会软降级到通用呈现路径。 +`session.history` 按追加来源的消息边界分页：`maxMessages` 统计以追加方式进入 surface 的 `user/message` 和 `assistant/message` 事件，因此仅供模型使用的替换副本不占用配额。每一页仍是一段连续的原始事件区间，从而让压缩（compaction）的仅日志溯源信息与引用它的替换留在同一页。 `session.history` 的尾页（不带 `beforeSeq`）额外携带一个可选的 `projections` 块——`ctx.sessionProjections`（`@deepseek-ai/dsh-session-projection`）上每个已注册单元的水位线快照，`asOfSeq` = 这些值共同反映到的最后一个事件 seq（空日志为 `-1`）。网关还订阅注册表的变更流，为每个状态发生变化的单元生成一个 `session/projection` mux 帧（`{sessionId, key, value, seq}`——实时推送状态，绝不入日志；客户端按 seq 高者胜维护一个按会话的通用值仓）。载体不持有任何领域知识（每个值在注册表内部已过其单元自己的 schema；协议 schema 对 `values`/`value` 保持宽松）；loadOlder 页永不携带该块，未装注册表的组合则两个面都不提供。 diff --git a/packages/host/apiproxy/src/api-proxy.ts b/packages/host/apiproxy/src/api-proxy.ts index 998e8d3ac5..19fb0fe8a2 100644 --- a/packages/host/apiproxy/src/api-proxy.ts +++ b/packages/host/apiproxy/src/api-proxy.ts @@ -26,7 +26,7 @@ import { // Type-only: brings the `ctx.tools` Context merge into this program (viewFor reads presenters). import type {} from '@deepseek-ai/dsh-tools' import type { - ApiProxy, CredentialView, GoalRef, HistoryEntry, HistoryToolCall, HostFrame, ModelCatalogFailure, ModelProviderGroup, + ApiProxy, CredentialView, GoalRef, HistoryEntry, HostFrame, ModelCatalogFailure, ModelProviderGroup, ModelReasoning, MuxFrame, QuestionResponsePayload, SessionProjectionsBlock, SessionSearchItem, QueuedInboxItem, SessionSummary, SettingsNamespaceView, SubagentAddress, ToolEventView, WorkspaceId, WorkspaceView, @@ -408,9 +408,9 @@ function matchesQuestions(payload: QuestionResponsePayload, pending: PendingQues * Compute the render intent for a tool/call or tool/result event through the * presenters registered at this moment; every other event type gets none. A * result's presenter needs its call's parsed args — `argsFor` supplies them - * (live: the per-session call table; history: the full-log pairing index), - * returning undefined when the pairing is unavailable, which soft-falls to no - * view. Presenter or JSON.parse throws also soft-fall: + * (live: the per-session call table; history: an in-page backscan), returning + * undefined when the pairing is unavailable (e.g. the call fell off the page), + * which soft-falls to no view. Presenter or JSON.parse throws also soft-fall: * the client's documented default (generic JSON card) covers every miss. */ function viewFor(ctx: Context, event: SessionEvent, argsFor: (callId: string) => unknown): ToolEventView | undefined { @@ -442,8 +442,10 @@ function viewFor(ctx: Context, event: SessionEvent, argsFor: (callId: string) => } /** - * Resolve a tool/result's call pairing by scanning a live session backwards - * for the matching tool/call after the open-call table missed. + * Resolve a tool/result's call pairing by scanning a window of events backwards + * for the matching tool/call. Used by the history path (the page is the + * window — a cross-page pairing soft-falls to no view) and by live-path table + * misses after a reconnect-eviction. */ function backscanArgs(events: readonly SessionEvent[], callId: string): { name: string; args: unknown } | undefined { for (let i = events.length - 1; i >= 0; i--) { @@ -461,34 +463,6 @@ function backscanArgs(events: readonly SessionEvent[], callId: string): { name: return undefined } -/** Index durable call metadata once so every history result keeps its pair across page cuts. */ -function historyCallIndex(events: readonly SessionEvent[]): ReadonlyMap { - const calls = new Map() - for (const event of events) { - if (event.type !== 'tool/call') continue - calls.set(String(event.data.callId), { - name: event.data.name, - arguments: event.data.arguments, - time: event.time, - }) - } - return calls -} - -/** Parse one indexed history pair for a result presenter, soft-falling malformed arguments. */ -function historyArgs( - calls: ReadonlyMap, - callId: string, -): { name: string; args: unknown } | undefined { - const call = calls.get(callId) - if (call === undefined) return undefined - try { - return { name: call.name, args: JSON.parse(call.arguments) } - } catch { - return undefined - } -} - /** Render one detached history page through the same presenter path as ordinary history. */ function historyPage( ctx: Context, @@ -497,18 +471,10 @@ function historyPage( maxMessages: number | undefined, ): { events: HistoryEntry[]; hasMore: boolean } { const page = paginate(events, beforeSeq, maxMessages ?? DEFAULT_MAX_MESSAGES) - const calls = historyCallIndex(events) return { events: page.events.map((event) => { - const view = viewFor(ctx, event, callId => historyArgs(calls, callId)) - const call = event.type === 'tool/result' - ? calls.get(String(event.data.message.source.callId)) - : undefined - return { - event, - ...view === undefined ? {} : { view }, - ...call === undefined ? {} : { call }, - } + const view = viewFor(ctx, event, callId => backscanArgs(page.events, callId)) + return { event, ...view === undefined ? {} : { view } } }), hasMore: page.hasMore, } diff --git a/packages/host/apiproxy/src/api/index.ts b/packages/host/apiproxy/src/api/index.ts index 697e5bdeae..4f10d92853 100644 --- a/packages/host/apiproxy/src/api/index.ts +++ b/packages/host/apiproxy/src/api/index.ts @@ -36,7 +36,7 @@ export interface ApiProxy { // ---- Domain interfaces and payload entities ---- export type { - HistoryEntry, HistoryToolCall, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, + HistoryEntry, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, ModelReasoningEffort, ModelTarget, QueueAction, SessionModels, SessionProjectionsBlock, SessionSearchItem, SessionsApi, SessionSummary, } from './sessions.ts' diff --git a/packages/host/apiproxy/src/api/sessions.schema.ts b/packages/host/apiproxy/src/api/sessions.schema.ts index f47289e77b..9f9c4329e6 100644 --- a/packages/host/apiproxy/src/api/sessions.schema.ts +++ b/packages/host/apiproxy/src/api/sessions.schema.ts @@ -11,7 +11,7 @@ import type { MessageId } from '@deepseek-ai/dsh-llm/brand' import type { RequestPayload, ResponseValue } from './rpc-map.ts' import type { Wire } from './rpc.schema.ts' import type { - HistoryEntry, HistoryToolCall, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, + HistoryEntry, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, ModelReasoningEffort, ModelTarget, SessionProjectionsBlock, SessionSearchItem, SessionSummary, } from './sessions.ts' import type { ToolEventView } from './events.ts' @@ -193,18 +193,10 @@ export const toolEventViewSchema = z.discriminatedUnion('for', [ z.object({ for: z.literal('result'), view: z.looseObject({ card: z.string() }) }), ]) as unknown as z.ZodType -/** Paired tool/call metadata carried with a paged tool/result. */ -export const historyToolCallSchema: z.ZodType> = z.object({ - name: z.string(), - arguments: z.string(), - time: z.number(), -}) - -/** One session.history item: raw event plus optional host-computed tool annotations. */ +/** One session.history item: the session event plus its optional host-computed tool view. */ export const historyEntrySchema: z.ZodType> = z.object({ event: sessionEventSchema, view: toolEventViewSchema.optional(), - call: historyToolCallSchema.optional(), }) as unknown as z.ZodType> /** diff --git a/packages/host/apiproxy/src/api/sessions.ts b/packages/host/apiproxy/src/api/sessions.ts index 2a6da96db9..18315eef19 100644 --- a/packages/host/apiproxy/src/api/sessions.ts +++ b/packages/host/apiproxy/src/api/sessions.ts @@ -26,26 +26,14 @@ declare module '@deepseek-ai/dsh-llm' { } } -/** Paired tool/call metadata carried beside a paged result whose call may be outside the page. */ -export interface HistoryToolCall { - /** Registered tool name used for keyed presentation dispatch. */ - name: string - /** Exact durable arguments JSON from the paired tool/call. */ - arguments: string - /** Unix epoch ms of the paired tool/call event. */ - time: number -} - /** - * One history page entry: the raw event plus optional host-computed render - * intent and result pairing. Both annotations are pagination-time derivations, - * never persisted; `call` preserves a tool/result's identity when its call - * event lies outside this page. + * One history page entry: the raw event plus the optional host-computed render + * intent (same semantics as the mux frame's `view` slot — a pagination-time + * derivation, never persisted). */ export interface HistoryEntry { event: SessionEvent view?: ToolEventView - call?: HistoryToolCall } /** diff --git a/packages/host/apiproxy/tests/api-proxy-view.spec.ts b/packages/host/apiproxy/tests/api-proxy-view.spec.ts index 3b19a26b5e..43083545db 100644 --- a/packages/host/apiproxy/tests/api-proxy-view.spec.ts +++ b/packages/host/apiproxy/tests/api-proxy-view.spec.ts @@ -231,50 +231,9 @@ describe('mux live view computation', () => { ])) expect(byKey.get('tool/call:h-term')?.view).toEqual({ for: 'call', view: { card: 'terminal', title: 'ls' } }) expect(byKey.get('tool/result:h-term')?.view).toEqual({ for: 'result', view: { card: 'terminal', output: 'done' } }) - expect(byKey.get('tool/result:h-term')?.call).toEqual({ - name: 'term', arguments: '{"cmd":"ls"}', time: byKey.get('tool/call:h-term')?.event.time, - }) expect('view' in (byKey.get('tool/result:h-orphan') ?? {})).toBe(false) - expect('call' in (byKey.get('tool/result:h-orphan') ?? {})).toBe(false) expect('view' in (byKey.get('tool/result:h-bad') ?? {})).toBe(false) - expect(byKey.get('tool/result:h-bad')?.call?.arguments).toBe('{broken') expect('view' in (byKey.get('tool/result:h-plain') ?? {})).toBe(false) - expect(byKey.get('tool/result:h-plain')?.call?.name).toBe('plain') - }) - - it('carries a result pair and computes its view when the call is outside the history page', async () => { - const { ctx } = await harness() - const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' }) - const session = ctx.sessions.create() - ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent) - session.append('turn/start', { turn: 1 }) - const call = session.append('tool/call', { - turn: 1, step: 1, callId: CallId('cross-page'), name: 'term', arguments: '{"cmd":"tail"}', - }) - session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - session.append('turn/start', { turn: 2 }) - appendUserText(session, 'newer message cuts the page') - const result = session.append('tool/result', { - turn: 1, step: 1, - message: createToolResultMessage({ - callId: CallId('cross-page'), - content: [{ type: 'text', text: 'late result' }], - isError: false, - }), - }, { surfaceOp: 'append' }) - - const response = await api.sessions.history({ - rpcId: RpcId('t-hist-cross-page'), - payload: { sessionId: session.id, maxMessages: 1 }, - }) - if (!response.result.ok) throw new Error('unreachable') - const entries = response.result.value.events - expect(entries.some(entry => entry.event.seq === call.seq)).toBe(false) - const entry = entries.find(candidate => candidate.event.seq === result.seq) - expect(entry).toMatchObject({ - call: { name: 'term', arguments: '{"cmd":"tail"}', time: call.time }, - view: { for: 'result', view: { card: 'terminal', output: 'done' } }, - }) }) it('counts only append-origin messages toward maxMessages and keeps compaction provenance whole', async () => { diff --git a/packages/host/apiproxy/tests/rpc-schemas.spec.ts b/packages/host/apiproxy/tests/rpc-schemas.spec.ts index 3a76dd9b07..b65861c1ae 100644 --- a/packages/host/apiproxy/tests/rpc-schemas.spec.ts +++ b/packages/host/apiproxy/tests/rpc-schemas.spec.ts @@ -190,16 +190,10 @@ describe('sessions domain schemas', () => { expect(sessionHistoryRequestSchema.parse({ sessionId: 's1', beforeSeq: 3, maxMessages: 5 }).beforeSeq).toBe(3) expect(() => sessionHistoryRequestSchema.parse({ sessionId: 's1', maxMessages: 0 })).toThrow() expect(sessionHistoryValueSchema.parse({ - events: [{ - event: { type: 'tool/result', seq: 3, time: 30, data: {} }, - call: { name: 'skill', arguments: '{"name":"review"}', time: 20 }, - }], + events: [], hasMore: false, modelTarget: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, - })).toMatchObject({ - events: [{ call: { name: 'skill', arguments: '{"name":"review"}', time: 20 } }], - hasMore: false, - }) + }).hasMore).toBe(false) expect(sessionModelsRequestSchema.parse({ sessionId: 's1' }).sessionId).toBe('s1') expect(sessionModelsValueSchema.parse({ current: { provider: 'deepseek-official', model: 'deepseek-v4-flash', reasoningEffort: 'max' }, From 3a0703f8ac0275af93205c8f644882de71d95f08 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 7 Aug 2026 16:20:05 +0800 Subject: [PATCH 21/22] chore(docs): re-record the packages README pairing after the master merge --- packages/README.i18n.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/README.i18n.yaml b/packages/README.i18n.yaml index d10f476f79..e023e3c9a8 100644 --- a/packages/README.i18n.yaml +++ b/packages/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/README.md -README.md: 8fbb6069a784a5bd45423a4e1ae11834a597750d -README.zh.md: 42a8d691344c716021188df6fd870a841d543f36 +README.md: baf1680dda6f379f61f91afe327034e2aa82e202 +README.zh.md: bb5c9cd610c4051e586d9ad323c36305613d6c20 From 342b5c4830cc13d8d6d957b737141290736c4ea3 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 7 Aug 2026 16:22:02 +0800 Subject: [PATCH 22/22] fix(web): keep both agents distinct in the shipped-composition test The preset catalog assertion and master's new command-catalog assertion each create an agent in the same test; the second is now named for what it is. --- apps/web/tests/shipped-composition.e2e.ts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/apps/web/tests/shipped-composition.e2e.ts b/apps/web/tests/shipped-composition.e2e.ts index b82c0db75d..930966f290 100644 --- a/apps/web/tests/shipped-composition.e2e.ts +++ b/apps/web/tests/shipped-composition.e2e.ts @@ -98,18 +98,18 @@ it('assembles the shipped Web catalog with the confined access default', async ( expect(scaffold.ctx.approval.config.policy).toBe('ask') expect(scaffold.ctx.permission.defaultPreset).toBe('workspace-write') - const handle = await scaffold.ctx.agents.create({ + const commandHandle = await scaffold.ctx.agents.create({ sessionId: SessionId('shipped-command-catalog'), meta: { cwd: scaffold.workspaceCwd }, agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, }) try { - expect(scaffold.ctx.commands.list(handle.agent)).toContainEqual({ + expect(scaffold.ctx.commands.list(commandHandle.agent)).toContainEqual({ name: 'feedback', description: 'record feedback about this session', input: { hint: '' }, }) } finally { - await handle.dispose() + await commandHandle.dispose() } }, 120_000)