From a8a12ffc232655d3c300d90eb0c7bd45695e6591 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 8 Aug 2026 00:04:41 +0800 Subject: [PATCH] cleanup: replace FIXMEs with tracked issues --- ...21-mandatory-app-attribution-headers.i18n.yaml | 4 ++-- ...026-06-21-mandatory-app-attribution-headers.md | 4 ++-- ...-06-21-mandatory-app-attribution-headers.zh.md | 4 ++-- .../2026-07-02-tool-render-intent-union.i18n.yaml | 4 ++-- .../2026-07-02-tool-render-intent-union.md | 2 +- .../2026-07-02-tool-render-intent-union.zh.md | 2 +- ...ariables-and-tool-guidance-ownership.i18n.yaml | 4 ++-- ...rompt-variables-and-tool-guidance-ownership.md | 2 +- ...pt-variables-and-tool-guidance-ownership.zh.md | 2 +- .../2026-07-05-reconstructable-requests.i18n.yaml | 4 ++-- .../2026-07-05-reconstructable-requests.md | 1 - .../2026-07-05-reconstructable-requests.zh.md | 1 - ...026-06-18-compaction-capability-seam.i18n.yaml | 4 ++-- .../2026-06-18-compaction-capability-seam.md | 2 +- .../2026-06-18-compaction-capability-seam.zh.md | 2 +- .../2026-08-02-pwsh-tool-bash-parity.i18n.yaml | 4 ++-- .../feature/2026-08-02-pwsh-tool-bash-parity.md | 2 +- .../2026-08-02-pwsh-tool-bash-parity.zh.md | 2 +- ...1-installer-adopts-existing-checkout.i18n.yaml | 4 ++-- ...26-07-31-installer-adopts-existing-checkout.md | 2 +- ...07-31-installer-adopts-existing-checkout.zh.md | 2 +- .../2026-06-19-acp-snapshot-tests.i18n.yaml | 4 ++-- .../testing/2026-06-19-acp-snapshot-tests.md | 2 +- .../testing/2026-06-19-acp-snapshot-tests.zh.md | 2 +- .github/workflows/ci.yml | 3 ++- docs/core-data-structures/core.i18n.yaml | 4 ++-- docs/core-data-structures/core.md | 2 -- docs/core-data-structures/core.zh.md | 2 -- docs/glossary.i18n.yaml | 4 ++-- docs/glossary.md | 2 -- docs/glossary.zh.md | 2 -- examples/acp-agent/tests/acp.snapshot.ts | 4 ++-- examples/headless-agent/tests/compaction.e2e.ts | 4 ++-- packages/client/runtime/src/client/slots.ts | 15 +++++---------- packages/cordis/tool-cordis/README.i18n.yaml | 4 ++-- packages/cordis/tool-cordis/README.md | 2 +- packages/cordis/tool-cordis/README.zh.md | 2 +- packages/cordis/tool-cordis/src/guard.ts | 1 - packages/hooks/hooks-claude/tests/bridge.spec.ts | 4 ++-- packages/llm/llm/README.i18n.yaml | 4 ++-- packages/llm/llm/README.md | 2 +- packages/llm/llm/README.zh.md | 2 +- packages/llm/llm/src/attribution.ts | 4 ++-- packages/sdk/telemetry/README.i18n.yaml | 4 ++-- packages/sdk/telemetry/README.md | 4 ++-- packages/sdk/telemetry/README.zh.md | 4 ++-- packages/sdk/telemetry/src/reporter.ts | 9 ++++----- scripts/install.sh | 2 -- 48 files changed, 69 insertions(+), 87 deletions(-) diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml index 56c9e53319..946d5a6117 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.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/architecture/2026-06-21-mandatory-app-attribution-headers.md -2026-06-21-mandatory-app-attribution-headers.md: a8ffe91c431cdc7907626bbc3eaf8096035777de -2026-06-21-mandatory-app-attribution-headers.zh.md: ac4affce583d5d81253f320ff022f670d4d66cc8 +2026-06-21-mandatory-app-attribution-headers.md: 28432008c354cbbb6e364746338627a26b464b0c +2026-06-21-mandatory-app-attribution-headers.zh.md: 4fb3acd72aba4bebe751f57ac0f89f776d1f1f39 diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md index a8ffe91c43..28432008c3 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md @@ -32,7 +32,7 @@ The provider-neutral identity is owned by `dsh-llm` (`packages/llm/llm/src/attri - product token for `User-Agent`: `deepseek-harness` (continuity with the pre-Agent Note wire value and the repo/org identity) - version: read from the owning package's manifest via `createRequire`, never a hand-copied constant -- app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home; a `FIXME` in `attribution.ts` blocks release until that repository actually exists +- app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home; [#1972](https://github.com/deepseek-harness/deepseek-harness/issues/1972) tracks making it reachable before release The default is mandatory and non-empty. White-label deployments pass their own `AppIdentity` to `attributionHeaders(identity)` - the override seam is the function parameter, with no deployment config plumbing until a consumer needs it - and omission falls back to the harness default rather than suppressing attribution. There is no per-request API for the model, user prompt, session id, cwd, user email, API key owner, or local machine identity to influence these fields. @@ -77,7 +77,7 @@ The landed contract: **Providers see that traffic comes from the harness.** That is the point, but it means deployments that previously blended into generic SDK traffic become identifiable. Mitigation: send only static public product data and let forks/white-label deployments pass their own `AppIdentity`. -**The app URL points at a repository that does not exist yet.** `deepseek-ai/deepseek-harness-sdk` is the planned public home; until it is created the URL is a dangling promise. The `FIXME` marker on the constant blocks a release from shipping with it unresolved (see `docs/development.md` marker semantics). +**The app URL points at a repository that does not exist yet.** `deepseek-ai/deepseek-harness-sdk` is the planned public home; until it is created the URL is a dangling promise. [#1972](https://github.com/deepseek-harness/deepseek-harness/issues/1972) owns creating it or correcting the final URL before release. **Header support differs by client library.** The hand-rolled adapter sets headers directly; the pi-ai-backed adapter depends on pi-ai continuing to honor `StreamOptions.headers` (merged last over provider defaults). The wire-level mock-server tests are the guard: if a pi-ai upgrade stops delivering the header, the suite goes red. This is useful pressure on the abstraction: a provider adapter that cannot set mandatory headers cannot fully implement the harness LLM contract. diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md index ac4affce58..4fb3acd72a 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md @@ -32,7 +32,7 @@ LLM（大语言模型）提供方请求应当标识发出请求的产品。这 - `User-Agent` 的产品 token：`deepseek-harness`（与 Agent Note 之前的线路值及仓库/组织身份保持连续性） - 版本：通过 `createRequire` 从所属包的 manifest（元数据清单）读取，绝不手动复制常量 -- 应用 URL：`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页；`attribution.ts` 中的 `FIXME` 标记在该仓库实际存在之前阻塞发布 +- 应用 URL：`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页；[#1972](https://github.com/deepseek-harness/deepseek-harness/issues/1972) 跟踪在发布前使其可访问 默认值是强制的且非空。白标部署通过向 `attributionHeaders(identity)` 传入自己的 `AppIdentity` 来覆盖——覆盖 seam 就是函数参数，在有消费方需要之前不做部署配置管道——省略时回退到 harness 默认值而非抑制归属。没有逐请求 API 允许模型、用户提示词、会话 id、cwd、用户邮箱、API key 所有者或本地机器身份影响这些字段。 @@ -77,7 +77,7 @@ LLM（大语言模型）提供方请求应当标识发出请求的产品。这 **提供方看到流量来自 harness。** 这正是目的，但意味着此前混在通用 SDK 流量中的部署变得可识别。缓解措施：仅发送静态公开产品数据，并允许 fork/白标部署传入自己的 `AppIdentity`。 -**应用 URL 指向一个尚不存在的仓库。** `deepseek-ai/deepseek-harness-sdk` 是计划中的公开主页；在它创建之前，该 URL 是一个悬空承诺。常量上的 `FIXME` 标记阻塞发布，不允许带着未解决的问题出门（见 `docs/development.md` 标记语义）。 +**应用 URL 指向一个尚不存在的仓库。** `deepseek-ai/deepseek-harness-sdk` 是计划中的公开主页；在它创建之前，该 URL 是一个悬空承诺。[#1972](https://github.com/deepseek-harness/deepseek-harness/issues/1972) 负责在发布前创建该仓库或校正最终 URL。 **不同客户端库的头部支持有差异。** 手写适配器直接设置头部；基于 pi-ai 的适配器依赖 pi-ai 继续尊重 `StreamOptions.headers`（最后合并覆盖提供方默认值）。线路级 mock 服务器测试是守卫：如果 pi-ai 升级后不再投递该头部，套件会变红。这对抽象施加了有益的压力：一个无法设置强制头部的提供方适配器不能完整实现 harness 的 LLM 契约。 diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml index 48d3522a70..072823d0dc 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.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/architecture/2026-07-02-tool-render-intent-union.md -2026-07-02-tool-render-intent-union.md: d82141f519bff66df000f1316093aacd38b8e42b -2026-07-02-tool-render-intent-union.zh.md: e145908e019e71765a475b0ca9d22414e9b42d23 +2026-07-02-tool-render-intent-union.md: 67607b2848305439513503d7e03ad5e2a2e4020a +2026-07-02-tool-render-intent-union.zh.md: 9cbab75ce87f6d313ca4b6ac8dda043733361f0d diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md index d82141f519..67607b2848 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md @@ -14,7 +14,7 @@ A tool declares how its calls render in a UI (an editor's tool-call card) throug - Which combinations are *valid* is unwritten: a `terminal` call that also sets `content` means "description above the card"; a generic call that sets `terminal` is meaningless but representable. The type permits nonsense. - There is no way to express the one file-tool affordance an editor most wants — a **diff card** (`{path, oldText, newText}`, which Zed renders as an inline diff / new-file preview). `ToolCallPresentation.content` is the *LLM* `ContentBlock[]` vocabulary (text/image), so a tool literally cannot ask for a diff. -The existing `FIXME(tool-presentation)` in `packages/core/tools/src/index.ts` named the fix: "redesign the type so a tool declares its render INTENT once (e.g. a tagged union over card kinds) rather than a bag of optional fields the bridge stitches together." An earlier rejected collapse-tool-owned-presentation proposal deferred it explicitly: rich rendering "should return later as a tagged render-intent union after there are at least two real tools and two real consumers to validate the vocabulary." That bar is met by multiple producer families plus the TUI and host/client-runtime (Web) consumers. +An earlier rejected collapse-tool-owned-presentation proposal deferred rich rendering until it could "return later as a tagged render-intent union after there are at least two real tools and two real consumers to validate the vocabulary." That bar is met by multiple producer families plus the TUI and host/client-runtime (Web) consumers. ## Decision diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md index e145908e01..9cbab75ce8 100644 --- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md @@ -14,7 +14,7 @@ Status: implemented - 哪些组合是*合法的*没有文档说明：一个设置了 `content` 的 `terminal` 调用意味着「卡片上方的描述」；一个设置了 `terminal` 的 generic 调用毫无意义但类型上可表达。类型允许无意义的状态存在。 - 无法表达编辑器最需要的文件工具能力：**diff 卡片**（`{path, oldText, newText}`，Zed 将其渲染为内联 diff / 新文件预览）。`ToolCallPresentation.content` 使用的是 *LLM（大语言模型）* 的 `ContentBlock[]` 词汇（text/image），工具根本无法请求 diff 展示。 -`packages/core/tools/src/index.ts` 中已有的 `FIXME(tool-presentation)` 指出了修复方向：「重新设计类型，让工具一次性声明其渲染意图（例如按卡片种类的带标签联合类型），而非一堆由 bridge 拼接的可选字段。」一个早先被否决的折叠工具自有呈现提案明确推迟了此事：富渲染「应当在至少有两个真实工具和两个真实消费方验证词汇之后，以带标签 render-intent 联合类型的形式回归。」该条件已由多个生产者族，加上 TUI 与宿主/客户端运行时（Web）这些消费方满足。 +一个早先被否决的折叠工具自有呈现提案把富渲染推迟到它能够「在至少有两个真实工具和两个真实消费方验证词汇之后，以带标签 render-intent 联合类型的形式回归」之时。该条件已由多个生产者族，加上 TUI 与宿主/客户端运行时（Web）这些消费方满足。 ## 决策 diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml index 8a2190b500..26354042d7 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.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/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md -2026-07-05-prompt-variables-and-tool-guidance-ownership.md: 94f5fa409e7b539b48750d12576c7a342a30c9ba -2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 341b3a89f423c9cc7d2fc56f1ea25a1985680d0d +2026-07-05-prompt-variables-and-tool-guidance-ownership.md: a3b5021daf323971308760bde4f97651db8edbda +2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 490d41302ea4f4e14e11e301acbf47170f95cace diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 94f5fa409e..a3b5021daf 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -10,7 +10,7 @@ The assembled system prompt had four defects, all of one family: facts the harne **The model could not know its own name.** `AgentOptions.model` drives every request, but no prompt text carried it — and nothing COULD carry it: sections in `dsh-system-prompt` were context-global while the model name is per-agent, and `assemble()` took no per-agent input at all. -**Tool guidance was hand-written prose in leaf YAML.** The bash/subagent/todo_write usage guidance lived in the coding-agent and ACP persona strings — two drifting copies (the ACP one was already abridged) — while `dsh-tool-fs` and `dsh-tool-web` owned their guidance as `ctx.systemPrompt.section()` contributions. Loading or dropping a tool plugin meant editing every deployment's persona by hand; both YAMLs carried a `FIXME(config-comments)` apologizing for a symptom of the split, and the old terminal welcome banner hand-enumerated the tool set too. +**Tool guidance was hand-written prose in leaf YAML.** The bash/subagent/todo_write usage guidance lived in the coding-agent and ACP persona strings — two drifting copies (the ACP one was already abridged) — while `dsh-tool-fs` and `dsh-tool-web` owned their guidance as `ctx.systemPrompt.section()` contributions. Loading or dropping a tool plugin meant editing every deployment's persona by hand, and the old terminal welcome banner hand-enumerated the tool set too. **The persona rendered after tool guidance.** The loop string-joined `agent.options.systemPrompt` AFTER the assembled sections, so the model read "Use the read tool…" before "You are a coding agent" — backwards relative to the identity-first convention (Claude Code, Codex) and a second composition path besides the section pipeline. diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md index 341b3a89f4..490d41302e 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md @@ -10,7 +10,7 @@ Status: implemented **模型无法知道自己的名字。** `AgentOptions.model` 驱动每个请求，但没有任何提示词文本携带它——也不可能携带：`dsh-system-prompt` 中的 section 是上下文全局的，而模型名称是 per-agent 的，`assemble()` 根本不接受任何 per-agent 输入。 -**工具指导是 leaf YAML 中的手写行文。** bash/subagent/todo_write 的使用指导存放在 coding-agent 和 ACP persona 字符串里——两份漂移的副本（ACP 那份已经被删减）——而 `dsh-tool-fs` 和 `dsh-tool-web` 则通过 `ctx.systemPrompt.section()` 贡献各自的指导。加载或卸载一个工具插件意味着手动编辑每个部署的 persona；两份 YAML 都带着一条 `FIXME(config-comments)` 为这种分裂的症状道歉，旧终端欢迎横幅也手动枚举了工具集。 +**工具指导是 leaf YAML 中的手写行文。** bash/subagent/todo_write 的使用指导存放在 coding-agent 和 ACP persona 字符串里——两份漂移的副本（ACP 那份已经被删减）——而 `dsh-tool-fs` 和 `dsh-tool-web` 则通过 `ctx.systemPrompt.section()` 贡献各自的指导。加载或卸载一个工具插件意味着手动编辑每个部署的 persona，旧终端欢迎横幅也手动枚举了工具集。 **Persona 渲染在工具指导之后。** agent loop（智能体循环）将 `agent.options.systemPrompt` 字符串拼接在已组装的 section 之后，于是模型先读到「Use the read tool…」再读到「You are a coding agent」——与 identity-first 约定（Claude Code、Codex）相反，且是 section 流水线之外的第二条组合路径。 diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml index d326b413bb..2926746ee1 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.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/architecture/2026-07-05-reconstructable-requests.md -2026-07-05-reconstructable-requests.md: 2f559a3052b9fb84f788975a64799e4f020b0d3e -2026-07-05-reconstructable-requests.zh.md: 26abdc024a166856e51ebf09f086c7868fc8236d +2026-07-05-reconstructable-requests.md: ebca9b99cad791159302da9c2bbce9f4df147aab +2026-07-05-reconstructable-requests.zh.md: 91ef3fd04502f2c2f092da60a8bd909cf7fa25df diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md index 2f559a3052..ebca9b99ca 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -53,4 +53,3 @@ Like MiniCode, the conversation advances append-only and resets only when model- - Tool-result trimming (planned) needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic. - Session logs grow one `request/header` snapshot per loop instance plus snapshots on real changes. This is larger than a delta codec but small beside chunk-heavy logs and retains one replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated. - Snapshot expected outputs changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths. -- FIXME(call-config-shape): revisit `LlmCallConfig`'s exact field set — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit there out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them. diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md index 26abdc024a..91ef3fd045 100644 --- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md @@ -53,4 +53,3 @@ Status: implemented - 工具结果裁剪（计划中）无需新机制：一个已记录的单条目 surface replace（`start === end`），携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族，回放正确，缓存击穿由相同的压力逻辑批量处理。 - 会话日志每个循环实例增长一个 `request/header` 快照，并在真正变更时增加快照。它比 delta 编解码器更大，但相对分片密集型日志仍然很小，并只保留一种回放表示。`SESSION_FORMAT_VERSION` 保持 `0`；旧的 delta 事件被拒绝而非迁移。 - 快照预期输出变更一次（每个 transcript（文本记录）增加其 header 事件）；写入文件系统的 fixture（测试前置数据）以规范化的撰写形式存储，工具参数使用 cwd 相对路径，因为回放只对 cwd 无关的参数路径做往返。 -- FIXME(call-config-shape)：重新审视 `LlmCallConfig` 的确切字段集——哪些字段对缓存而言真正属于 epoch 级别（`model` 毫无疑问；采样标量出于谨慎放在那里），以及当适配器需要时，提供方特定的额外项（推理（reasoning）选项、额外 body 参数）应归属何处。 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml index c981d84400..f071577bdd 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.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/2026-06-18-compaction-capability-seam.md -2026-06-18-compaction-capability-seam.md: 26e6e2468c7bea661d85c8fb994adf8b109105ee -2026-06-18-compaction-capability-seam.zh.md: 8f9cd1f6bc31e648a5b923e816cad75ebc1a0bd8 +2026-06-18-compaction-capability-seam.md: efb37482270a7952f6af6596f9afd12f17048bcc +2026-06-18-compaction-capability-seam.zh.md: 214832923c4e24835e7b25a5bbf2b1bcd62dff42 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md index 26e6e2468c..efb3748227 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -131,4 +131,4 @@ The lifecycle boundary makes crash state unambiguous: - **Loop:** Tests pin pre-step after the preceding `step/end` and before the next `step/start`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition. - **Manual:** Maintenance serialization, marker ordering, injection retention, live/stale orphan classification, cancellation, close/flush failures, command mapping, and the queued TUI journey are pinned without a model key. - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task. -- **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work. +- **Snapshot gap:** The summarization call is session-associated and logs `compact/summary`, but ordinary transcript replay does not derive its auxiliary response. [#1971](https://github.com/deepseek-harness/deepseek-harness/issues/1971) tracks a keyless assembled scenario with an explicit replay override. diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md index 8f9cd1f6bc..214832923c 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md @@ -131,4 +131,4 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab - **循环测试：** 测试固定 pre-step 发生在前一个 `step/end` 之后、下一个 `step/start` 之前，使用实际 `agent/request` 路由，关闭失败步骤，分配新的重试编号，并覆盖完整的抛出/带内溢出 → 压缩 → 重建重试组合。 - **手动测试：** 无需模型密钥即可固定 maintenance 串行化、标记顺序、注入保留、活动／陈旧未匹配标记分类、取消、闭合／flush 失败、命令映射以及排队 TUI 流程。 - **带密钥 e2e：** 真实模型和 bash 会话在降低的限制下触发压缩，记录完整的 `compact/start…end` 对，缩小 surface，并完成任务。 -- **快照缺口：** 失控轮次压缩尚无法回放，因为摘要调用未记录 `assistant/chunk` 事件或 `sessionId`；交错摘要调用的回放仍是后续工作。 +- **快照缺口：** 摘要调用与会话关联并记录 `compact/summary`，但普通 transcript（文本记录）回放不会派生其辅助响应。[#1971](https://github.com/deepseek-harness/deepseek-harness/issues/1971) 跟踪一个带显式回放 override 的无密钥组装场景。 diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml index eea7ced3d2..40e24e9ac2 100644 --- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.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/2026-08-02-pwsh-tool-bash-parity.md -2026-08-02-pwsh-tool-bash-parity.md: 945d2d5243162fe8e7fb3f76cbc3bcf0b5c2fdee -2026-08-02-pwsh-tool-bash-parity.zh.md: f537e313a0c895927c6e2319b11b98619a70d461 +2026-08-02-pwsh-tool-bash-parity.md: e35a903892d5d50a0d3ca12b23daa53f26d6aade +2026-08-02-pwsh-tool-bash-parity.zh.md: d7a68f0cab5281b25c3321e7ffff61c358b21a0a diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md index 945d2d5243..e35a903892 100644 --- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md +++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.md @@ -14,7 +14,7 @@ The first Windows-native foundation shipped `dsh-tool-pwsh` as a deliberately mi - **Rendering adopts the bash story verbatim**: stdout, a marked `[stderr]` section, truncation notices with spill paths, `(no output)` for an empty body, and exit markers only for non-zero exits — a clean exit produces no marker. The description and the `tool:pwsh` prompt section state this precisely ("Non-zero exits are reported as `[exit code: N]` markers"), deliberately not copying the bash prompt's "every result" phrasing, which its own renderer contradicts. - **`run_in_background` is wired through the generic task runtime** exactly like the bash tool: preflight, owner registration, `task_output`/`task_kill` control, and the same outcome mapping. `pwsh-local`'s already-mirrored `start()` handle backs it. -- **The `DSH_*` environment is shared, not duplicated**: `BashEnvRegistry` moved out of `dsh-tool-bash` into a new tool-independent `@deepseek-ai/dsh-bash-env` package (`ctx.bashEnv` + built-ins + the session-persistence contributor), and both shell tools inject it. Contributors apply to pwsh calls exactly as they do to bash calls, resolving the bash tool's `FIXME(bash-env-ownership)`. +- **The `DSH_*` environment is shared, not duplicated**: `BashEnvRegistry` moved out of `dsh-tool-bash` into a new tool-independent `@deepseek-ai/dsh-bash-env` package (`ctx.bashEnv` + built-ins + the session-persistence contributor), and both shell tools inject it. Contributors apply to pwsh calls exactly as they do to bash calls; shared environment ownership therefore sits outside either model-facing shell tool. - **Windows reality is pinned where bash has no analog**: every command runs under a UTF-8 output preamble so the Windows PowerShell 5.1 fallback cannot garble non-ASCII output through the UTF-8-decoding collector, and the prompts teach that Windows forced termination settles as exit 1 without a signal marker. - **Out of scope, unchanged**: sandbox escalation (waits for a Windows-confining executor) and persistent PTY shells (backends are Linux/macOS-only; ConPTY is roadmap work). The pwsh-specific terminal card with an exit pill shipped separately in the [pwsh UI presentation matches bash](2026-08-05-pwsh-ui-bash-parity.md) decision. diff --git a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md index f537e313a0..d7a68f0cab 100644 --- a/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md +++ b/.agents/notes/implemented/feature/2026-08-02-pwsh-tool-bash-parity.zh.md @@ -14,7 +14,7 @@ Status: implemented - **渲染完全采用 bash 故事**：stdout、带标记的 `[stderr]` 段、带 spill 路径的截断通知、空体渲染 `(no output)`、退出 marker 仅限非零退出——干净退出不产生 marker。描述与 `tool:pwsh` prompt section 精确陈述这一点（"Non-zero exits are reported as `[exit code: N]` markers"），刻意不复制 bash prompt 中与其自身渲染矛盾的 "every result" 措辞。 - **`run_in_background` 经通用任务运行时接线**，与 bash 工具完全一致：预检、owner 注册、`task_output`/`task_kill` 控制与相同的结果映射。其背后是 `pwsh-local` 早已镜像好的 `start()` 句柄。 -- **`DSH_*` 环境共享而非复制**：`BashEnvRegistry` 从 `dsh-tool-bash` 迁入新的工具无关包 `@deepseek-ai/dsh-bash-env`（`ctx.bashEnv` + 内置事实 + session-persistence contributor），两个 shell 工具都注入它。contributor 对 pwsh 调用与 bash 调用一视同仁，并消化了 bash 工具的 `FIXME(bash-env-ownership)`。 +- **`DSH_*` 环境共享而非复制**：`BashEnvRegistry` 从 `dsh-tool-bash` 迁入新的工具无关包 `@deepseek-ai/dsh-bash-env`（`ctx.bashEnv` + 内置事实 + session-persistence contributor），两个 shell 工具都注入它。contributor 对 pwsh 调用与 bash 调用一视同仁；因此，共享环境的所有权不属于任何一个面向模型的 shell 工具。 - **Windows 现实在 bash 无对应处钉死**：每条命令都在 UTF-8 输出 preamble 下运行，使 Windows PowerShell 5.1 兜底无法经 UTF-8 解码的 collector 破坏非 ASCII 输出；prompt 教授 Windows 强制终止以无 signal 的 exit 1 结算。 - **范围外，不变**：sandbox 升级（等待 Windows-confining 执行器）与持久 PTY shell（后端仅限 Linux/macOS；ConPTY 属路线图）。带退出 pill 的 pwsh 专属 terminal 卡已随 [pwsh UI 呈现与 bash 对齐](2026-08-05-pwsh-ui-bash-parity.md) 决策另行交付。 diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml index 1a179748f9..79ea52067d 100644 --- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.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/process/2026-07-31-installer-adopts-existing-checkout.md -2026-07-31-installer-adopts-existing-checkout.md: de3cd052f94a0d5256c7687e9a1a38ee69fd2caf -2026-07-31-installer-adopts-existing-checkout.zh.md: 2e8be804b4af6151e77e36f8b109616aab3a18e9 +2026-07-31-installer-adopts-existing-checkout.md: ff02fe837f2ad4deb3fb852f610f3cd3ff9a23d7 +2026-07-31-installer-adopts-existing-checkout.zh.md: 28816c80764acc0d4a2fcd13b3b8a38807021fd6 diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md index de3cd052f9..ff02fe837f 100644 --- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md +++ b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md @@ -46,6 +46,6 @@ A container adopting an outside clone is also no longer self-contained: deleting ## Testing -`scripts/install.sh` has no automated test, and this change does not add one: the user directed that `install.spec.ts` be left out of scope. That is a known gap on a shipped user-facing path, and the `/var` resolution defect above is exactly the class of bug a test would have caught first. The standing [`FIXME(install-ts)`](../../../../scripts/install.sh) asking for this workflow to move into a tested TypeScript entrypoint is correspondingly more pressing. +`scripts/install.sh` now has a real-shell PTY regression suite in `apps/cli/tests/install-script.spec.ts`, covering adoption and curl-style paths with stubbed dependencies. The installer's longer-term deletion in favor of pnpm/npx is tracked in [#1890](https://github.com/deepseek-harness/deepseek-harness/issues/1890). Verification was manual, through a throwaway harness driving the real script with a stubbed `pnpm`: adopting a standalone clone; adopting from a linked worktree into its existing container; an explicit `DSH_SOURCE` still opting back into cloning; a dirty tree adopting silently with no prompt or warning while its uncommitted file stays behind; a non-git checkout failing with guidance; and a `curl`-style clone install asserting the built layout, which is the regression that caught the unresolved-`REPO_ROOT` defect. The interactive path was exercised under tmux from a dirty checkout, confirming the run reaches the launcher with no adoption prompt and ends with `dsh` running from the new staging worktree while the original checkout keeps its branch and its uncommitted file. diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md index 2e8be804b4..28816c8076 100644 --- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md +++ b/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md @@ -46,6 +46,6 @@ Status: implemented ## Testing -`scripts/install.sh`没有自动化测试，本次变更也未添加：用户明确要求把`install.spec.ts`排除在范围之外。这是一条已交付的、面向用户的安装路径上的已知缺口，而上文那个`/var`解析缺陷，恰恰属于测试本应最先捕获的那类 bug。相应地，要求把这套流程迁移到有测试覆盖的 TypeScript 入口的既有[`FIXME(install-ts)`](../../../../scripts/install.sh)也变得更为紧迫。 +`scripts/install.sh` 现有一套位于 `apps/cli/tests/install-script.spec.ts` 的真实 shell PTY 回归测试，使用 stub 依赖覆盖接管路径和 curl 风格路径。[#1890](https://github.com/deepseek-harness/deepseek-harness/issues/1890) 跟踪安装器的长期删除工作，届时将改用 pnpm/npx。 验证是手工完成的，通过一个一次性测试装置以打桩的`pnpm`驱动真实脚本：接管独立克隆；从 linked worktree 接管进其已有容器；显式`DSH_SOURCE`仍回到克隆路径；工作树不干净时静默接管、既不提示也不警告，且其未提交文件留在原处；非 git 检出失败并给出指引；以及`curl`式克隆安装断言所构建的布局——正是这项回归测试捕获了`REPO_ROOT`未解析的缺陷。交互路径在 tmux 下从一个不干净的检出走通，确认整个过程不出现接管提示即可到达启动器，最终`dsh`从新的 staging worktree 运行，而原检出保持其分支不变、未提交文件仍在。 diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml index fe97a7b717..b7d396e007 100644 --- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.i18n.yaml +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.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/testing/2026-06-19-acp-snapshot-tests.md -2026-06-19-acp-snapshot-tests.md: e118ada58230fe31fbb2a6bffb83e5612757ab1f -2026-06-19-acp-snapshot-tests.zh.md: e292dbf3bf3c4c5198dc77d122bb6b8c36014ebf +2026-06-19-acp-snapshot-tests.md: 39d3b7a3f4699ea96262f43c63a7d60574ba064f +2026-06-19-acp-snapshot-tests.zh.md: 7dd3a3fa83682c35945314c7cd9531ca72bbb1fb diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md index e118ada582..39d3b7a3f4 100644 --- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md @@ -80,6 +80,6 @@ Tool determinism comes from a generated cwd, scrubbed environment, fresh non-log ## Consequences -The tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures, plus one file for each distinct pinned prompt and tool-schema sequence. Workspace seeds are copied into the generated cwd for both record and replay. In return the tier provides deterministic keyless coverage through the real Loader and tool composition. Most retained scenarios exercise the assembled backend rather than ACP; the [automation-only ACP decision](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary) keeps that corpus here and defers any move to a transport-neutral headless suite as an independent testing change (the suite-level FIXME marks it). +The tier adds reviewed per-scenario input, session, stdout, optional override, and optional workspace fixtures, plus one file for each distinct pinned prompt and tool-schema sequence. Workspace seeds are copied into the generated cwd for both record and replay. In return the tier provides deterministic keyless coverage through the real Loader and tool composition. Most retained scenarios exercise the assembled backend rather than ACP; the [automation-only ACP decision](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary) keeps that corpus here, while [#1970](https://github.com/deepseek-harness/deepseek-harness/issues/1970) tracks moving it to a transport-neutral headless suite without losing coverage. This Agent Note relates to but does not supersede the [proposed determinism Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md): that proposal's "universal replay fixture" re-derives session *message history* after every test (an internal-consistency invariant), whereas these snapshots pin assembled behavior plus the external automation output. They are complementary until the backend corpus moves off ACP. diff --git a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md index e292dbf3bf..7dd3a3fa83 100644 --- a/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md +++ b/.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.zh.md @@ -80,6 +80,6 @@ Status: implemented ## 后果 -该测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture，并为每个不同的已固定提示词序列、每个不同的已固定工具 schema 序列各增加一个文件。记录与回放都会把 workspace seed 复制到生成的 cwd。作为回报，该层通过真实 Loader 和工具组合提供确定性的无密钥覆盖。保留下来的大多数场景测试的是组装后的后端而非 ACP；[仅面向自动化的 ACP 决策](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)将该语料保留在此处，并把向传输无关 headless 套件的任何迁移推迟为一项独立的测试变更（套件级 FIXME 标记了这一点）。 +该测试层为每个场景增加经过评审的输入、会话、stdout、可选 override 和可选 workspace fixture，并为每个不同的已固定提示词序列、每个不同的已固定工具 schema 序列各增加一个文件。记录与回放都会把 workspace seed 复制到生成的 cwd。作为回报，该层通过真实 Loader 和工具组合提供确定性的无密钥覆盖。保留下来的大多数场景测试的是组装后的后端而非 ACP；[仅面向自动化的 ACP 决策](../simplification/2026-07-23-acp-automation-only-protocol.md#snapshot-boundary)将该语料保留在此处，而 [#1970](https://github.com/deepseek-harness/deepseek-harness/issues/1970) 跟踪在不损失覆盖的情况下将其迁移到传输无关的 headless 套件。 本 Agent Note 与[拟议的确定性 Agent Note](../../proposed/testing/2026-06-11-deterministic-and-stress-testing.md)相关，但不取代它：该提案的“通用回放 fixture”在每次测试后重新派生会话*消息历史*（内部一致性不变量），而这些快照固定组装后的行为与外部自动化输出。在后端语料迁出 ACP 之前，两者相互补充。 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 821948f873..66b3a5399e 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -30,7 +30,8 @@ env: jobs: - # FIXME: Re-enable the three hosted serial reference jobs before cutting a release. + # https://github.com/deepseek-harness/deepseek-harness/issues/1967 tracks + # restoring the three hosted serial reference jobs before release. # The self-hosted standby remains active on every master push. # Three enterprise jobs isolate coverage, static analysis, and the diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml index 461d1ef4fc..e79d5dac2f 100644 --- a/docs/core-data-structures/core.i18n.yaml +++ b/docs/core-data-structures/core.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 docs/core-data-structures/core.md -core.md: f7cf288715a3aec2f7037f12fc983e3172a77cef -core.zh.md: c17fd1335503c95e7f7f6f96cc286f567a8384e6 +core.md: dbd584f10b3daf873bc14210472efb6cd315717e +core.zh.md: 1fe1616a0c96abb4e8b91417cc4eae292416e42a diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index f7cf288715..dbd584f10b 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -530,8 +530,6 @@ The loop builds each request from logged state. `EpochHeader` records call confi On the wire, a loop-built request reads the `system` slot (the rendered prompt assembly) followed by the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The dev invariant recomputes exactly this equation against every loop-built request. -FIXME(call-config-shape): revisit which remaining fields are genuinely epoch-level for cache purposes (`model` and the model-owned reasoning effort are explicit; the sampling scalars sit here out of caution). - ```ts type-equiv /** * Provider, model, reasoning effort, and sampling scalars of one conversation's diff --git a/docs/core-data-structures/core.zh.md b/docs/core-data-structures/core.zh.md index c17fd13355..1fe1616a0c 100644 --- a/docs/core-data-structures/core.zh.md +++ b/docs/core-data-structures/core.zh.md @@ -536,8 +536,6 @@ interface ToolSchema { 在协议格式上，循环构建的请求先读取 `system` 槽位（渲染后的提示词组装），再读取派生历史——边界快照，其尾部在轮次首步是最新的 `user/message`，在后续步骤是上一步的工具结果。开发不变式针对每个循环构建的请求精确重算此等式。 -FIXME(call-config-shape)：重新审视其余哪些字段出于缓存目的确实属于 epoch 层级（`model` 和模型持有的推理强度已明确属于；采样标量目前出于谨慎保留在此）。 - ```ts type-equiv /** * Provider, model, reasoning effort, and sampling scalars of one conversation's diff --git a/docs/glossary.i18n.yaml b/docs/glossary.i18n.yaml index 5c6f7d4630..2dfe08c2fd 100644 --- a/docs/glossary.i18n.yaml +++ b/docs/glossary.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 docs/glossary.md -glossary.md: 0270a2d0dba558483e8e458a932a27b0151f2c93 -glossary.zh.md: c3584731cc08b23cf7f47c09620a77b7bff65689 +glossary.md: 16409517bff623a80d6e1e00888d95f63b42f780 +glossary.zh.md: fe3138ac81f2681d7fc69cc2aede96edeb7ec176 diff --git a/docs/glossary.md b/docs/glossary.md index 0270a2d0db..16409517bf 100644 --- a/docs/glossary.md +++ b/docs/glossary.md @@ -4,8 +4,6 @@ English | [中文](glossary.zh.md) Domain vocabulary for the DeepSeek Harness SDK uses one canonical term per concept. Terms link to their entries with standard Markdown anchors; implementation detail stays in package READMEs and Agent Notes. -FIXME(glossary-completeness): Expand this glossary before the first release so it covers the SDK's other core and capability subsystems, not only agent scope. - ## agent-scope - **scope** — the unit of per-agent registration: a contribution (tool, prompt section, variable, restriction, listener) is either *global* (visible to every agent) or *scoped* (owned by exactly one [scope key](#scope-key)). Two levels, flat: scoped registrations do not inherit down to subagents; subtree behavior is expressed with [lineage](#lineage) data, never scope structure. diff --git a/docs/glossary.zh.md b/docs/glossary.zh.md index c3584731cc..fe3138ac81 100644 --- a/docs/glossary.zh.md +++ b/docs/glossary.zh.md @@ -4,8 +4,6 @@ DeepSeek Harness SDK 的领域词汇为每个概念规定一个规范术语。各术语通过标准 Markdown 锚点链接到相应条目；实现细节留在各包的 README 与 Agent Note 中。 -FIXME(glossary-completeness): 首次发布前扩充本术语表，使其覆盖 SDK 的其他核心与能力子系统，而非仅限于 agent scope。 - ## agent-scope - **scope**：按 agent（智能体）划分的注册单位。一项贡献（工具、提示词片段、变量、限制、监听器）要么是*全局的*（对所有 agent 可见），要么是*带作用域的*（归属于恰好一个 [scope key](#scope-key)）。只有两层，采用扁平结构：带作用域的注册不会向下继承给 subagent；子树行为通过 [lineage](#lineage) 数据表达，从不通过 scope 结构。 diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index bf4f7ac972..b2fd25eb4e 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -90,8 +90,8 @@ async function prepareFsSearchWorkspace(cwd: string): Promise { } } -// FIXME: Migrate backend-oriented scenarios to the headless stream-json suite; -// this ACP suite should eventually retain only automation-protocol contracts. +// https://github.com/deepseek-harness/deepseek-harness/issues/1970 tracks moving +// backend/product scenarios to headless while retaining ACP protocol contracts here. function fixtureRecords(name: string): unknown[] { return readFileSync(join(SNAPSHOTS_DIR, name, 'session.jsonl'), 'utf8') diff --git a/examples/headless-agent/tests/compaction.e2e.ts b/examples/headless-agent/tests/compaction.e2e.ts index 07f239a73e..fdae11d2c7 100644 --- a/examples/headless-agent/tests/compaction.e2e.ts +++ b/examples/headless-agent/tests/compaction.e2e.ts @@ -10,9 +10,9 @@ import { SessionId } from '@deepseek-ai/dsh-session' /** * Key-gated smoke for mid-session compaction. It verifies the compact event * pair, replacement of older surface nodes, and a final answer after compaction. + * A keyless assembled snapshot with an explicit summarization replay override + * is tracked in https://github.com/deepseek-harness/deepseek-harness/issues/1971. */ -// FIXME(compaction-snapshot): this is the only full compaction coverage because -// replay cannot serve the summarizer's unlogged model call. let workdir: string | undefined let ctx: Context | undefined diff --git a/packages/client/runtime/src/client/slots.ts b/packages/client/runtime/src/client/slots.ts index 3698f62aab..9da8755b2d 100644 --- a/packages/client/runtime/src/client/slots.ts +++ b/packages/client/runtime/src/client/slots.ts @@ -19,7 +19,7 @@ import type { Context } from 'cordis' import { SlotCore } from '@deepseek-ai/dsh-client-ui-slots' import type { LocaleFace, OwnerOf, SlotEntryDef, SlotMap, SlotRenderer, SlotRendererHost, - SlotScope, SlotSpec, StoreDecl, StoredEntry, StoreInstanceLike, + SlotScope, SlotSpec, StoreDecl, StoreFactory, StoredEntry, StoreInstanceLike, } from '@deepseek-ai/dsh-client-ui-slots' declare module '@deepseek-ai/dsh-client-ui-slots' { @@ -35,16 +35,11 @@ export interface RootOwnerProps { children?: never } /** Instance key for root-scoped store records (session records key by session id, so the literal cannot collide). */ const ROOT_INSTANCE_KEY = 'root' -// FIXME(slot-parity): the engine's arbitrated persist extensions — create() -// takes the scope key (per-session localStorage suffix) and instances expose -// clearPersisted() — are not yet on ui-slots' StoreHandle/StoreInstanceLike; -// these local structural faces bridge until fw-slots lifts them. +/** Canonical type-erased store handle used by the runtime lifecycle map. */ +type EngineStoreHandle = Exclude -/** Store handle face as the engine actually ships it (scope-key-aware create). */ -interface EngineStoreHandle { create(scopeKey?: string): EngineStoreInstance } - -/** Engine instance face: the host-contract shape plus persisted-state cleanup. */ -interface EngineStoreInstance extends StoreInstanceLike { clearPersisted(): void } +/** Canonical engine instance derived from the handle's create contract. */ +type EngineStoreInstance = ReturnType /** Store axis record: one per live handle, dropped when the last holding entry unloads. */ interface StoreAxisRecord { diff --git a/packages/cordis/tool-cordis/README.i18n.yaml b/packages/cordis/tool-cordis/README.i18n.yaml index 0a55bfc7f6..fd2b5443ef 100644 --- a/packages/cordis/tool-cordis/README.i18n.yaml +++ b/packages/cordis/tool-cordis/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/cordis/tool-cordis/README.md -README.md: eda135d93e2912bbb4e111af40d176409b383b5b -README.zh.md: 773d4100f1be6c54f491838b65205b85ec61cdbc +README.md: 9986310160c2b56126155a4c3ef84d66018d31c2 +README.zh.md: d955306e1e5d4154f58c771704782ece44a15c99 diff --git a/packages/cordis/tool-cordis/README.md b/packages/cordis/tool-cordis/README.md index eda135d93e..9986310160 100644 --- a/packages/cordis/tool-cordis/README.md +++ b/packages/cordis/tool-cordis/README.md @@ -85,5 +85,5 @@ Mounting or unmounting a prompt or tool contribution changes later request prefi ## Known Limitations and Deferred Work - **The sandbox is containment for honest code, not a security boundary** — host-realm helpers on the sandbox global are reachable, so mount code can reach Node; load this plugin as deliberately as you would grant a bash tool (see § Trust stance). -- **The `ctx` façade exposes no `effect()`** — mount code cannot register a bespoke disposer; `on`/`provide`/`tools.register` cover every mount seen so far, and a guarded `effect` waits on a real need (`FIXME(sandbox-effect)`). +- **The `ctx` façade exposes no `effect()`** — mount code cannot register a bespoke disposer; `on`/`provide`/`tools.register` are the supported cleanup paths. - **`vmTimeoutMs` bounds only synchronous evaluation** — an async mount body escapes it; there is no async budget on mount code. diff --git a/packages/cordis/tool-cordis/README.zh.md b/packages/cordis/tool-cordis/README.zh.md index 773d4100f1..d955306e1e 100644 --- a/packages/cordis/tool-cordis/README.zh.md +++ b/packages/cordis/tool-cordis/README.zh.md @@ -85,5 +85,5 @@ Namespace 插件：命名导出 `name`／`inject`／`Config`／`apply`，无默 ## 已知限制与暂缓事项 - **沙箱只用于约束诚实代码，并非安全边界**：可以访问沙箱全局变量上的 host realm helper，因此挂载代码可以触达 Node；加载该插件时，应当像授予 bash 工具一样慎重（见 § 信任立场）。 -- **`ctx` façade 不公开 `effect()`**：挂载代码无法注册定制 disposer；`on`／`provide`／`tools.register` 已覆盖目前出现的每项挂载，受保护的 `effect` 会等待真实需求（`FIXME(sandbox-effect)`）。 +- **`ctx` façade 不公开 `effect()`**：挂载代码无法注册定制 disposer；`on`／`provide`／`tools.register` 是受支持的清理路径。 - **`vmTimeoutMs` 只限制同步求值**：async 挂载主体可逃出该边界；挂载代码没有 async 预算。 diff --git a/packages/cordis/tool-cordis/src/guard.ts b/packages/cordis/tool-cordis/src/guard.ts index 595dc462e0..22d85936f4 100644 --- a/packages/cordis/tool-cordis/src/guard.ts +++ b/packages/cordis/tool-cordis/src/guard.ts @@ -749,7 +749,6 @@ export function isPlugin(value: unknown): value is Plugin { * @param plugin - the plugin the mount code returned. * @returns an equivalent plugin whose `apply` sees the sandbox context façade. */ -// FIXME(sandbox-effect): expose guarded custom effects when a mount needs bespoke cleanup. export function guardedPlugin(plugin: Plugin): Plugin { if (typeof plugin === 'function') { const functionPlugin = plugin as (ctx: Context, config?: unknown) => unknown diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 1da2771257..244abae423 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -225,7 +225,7 @@ describe('hooks-claude bridge — PostToolUse', () => { expect(ctxMsg?.type === 'user/message' && ctxMsg.data.content.some(b => b.type === 'text' && b.text.includes('tool was slow'))).toBe(true) }) - it('a PreToolUse permissionDecision:ask degrades to ask (the tool is gated, not run)', async () => { + it('a PreToolUse permissionDecision:ask fails closed without an approval service', async () => { const dir = mkdtempSync(join(tmpdir(), 'dsh-hooks-claude-')) dirs.push(dir) const s = join(dir, 'ask.sh') @@ -241,7 +241,7 @@ describe('hooks-claude bridge — PostToolUse', () => { agent.followup(createUserMessage({ content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } })) await waitForIdle(ctx, agent) - // `ask` degrades to deny today (FIXME permissions): the tool does not run and the result is isError. + // No approval service is mounted, so `ask` fails closed: the tool does not run and the result is isError. expect(ran).toBe(false) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.message.content[0].isError).toBe(true) diff --git a/packages/llm/llm/README.i18n.yaml b/packages/llm/llm/README.i18n.yaml index 0ad49faa17..5225ba9d8c 100644 --- a/packages/llm/llm/README.i18n.yaml +++ b/packages/llm/llm/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/llm/llm/README.md -README.md: d15b2c996d6d47371a3d6c5542eb5c253029dbae -README.zh.md: d965f15298f09ff9c2a953a69346c4e83136934b +README.md: 956bfa112d6fe50c35359cebdf3710064da8c130 +README.zh.md: 42f2da18089e7dcfc9acb95076ab8786c798444b diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index d15b2c996d..956bfa112d 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -97,5 +97,5 @@ Pass-through; the registry preserves the assembled request prefix, while the sel - **`GenerateOptions` sampling is `temperature`/`maxTokens`/`stop` only** — no `tool_choice`, `top_p`, or penalty fields; the vocabulary grows when a producer lands ([dropped inert knobs](../../../.agents/notes/archived/simplification/2026-07-04-drop-inert-request-knobs.md)). - **Producer-gated variants stay out until produced** — `prefill`, per-tool `strict`, block `cache` hints, and the `agent` message-source variant were pruned as producerless ([Agent Note](../../../.agents/notes/archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)). - **`BlockAssembler` handles core block kinds only** — a plugin-added block type whose stream is never closed by `block-end` makes `blocks()` throw. -- **`APP_IDENTITY.url` names a repository that does not exist yet** — `FIXME`: creating the public `deepseek-ai/deepseek-harness-sdk` repo gates the first release. +- **`APP_IDENTITY.url` names a repository that does not exist yet** — [#1972](https://github.com/deepseek-harness/deepseek-harness/issues/1972) tracks making the public home reachable before release. - **`GenerateOptions.sessionId` is a locally-declared brand** — importing dsh-session's `SessionId` would cycle; a future ids-owning package would dissolve the workaround. diff --git a/packages/llm/llm/README.zh.md b/packages/llm/llm/README.zh.md index d965f15298..42f2da1808 100644 --- a/packages/llm/llm/README.zh.md +++ b/packages/llm/llm/README.zh.md @@ -97,5 +97,5 @@ - **`GenerateOptions` 采样只包含 `temperature`／`maxTokens`／`stop`**：没有 `tool_choice`、`top_p` 或 penalty 字段；有产生方落地时词汇才会增长（见 [已删除惰性旋钮](../../../.agents/notes/archived/simplification/2026-07-04-drop-inert-request-knobs.md)）。 - **受产生方约束的变体在实际产生前不会加入**：`prefill`、每工具 `strict`、块 `cache` 提示与 `agent` 消息源变体因没有产生方而被剪除（见 [Agent Note](../../../.agents/notes/archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)）。 - **`BlockAssembler` 只处理核心块类型**：如果插件添加块类型的流从未由 `block-end` 关闭，`blocks()` 会抛出异常。 -- **`APP_IDENTITY.url` 指向一个尚不存在的仓库**：`FIXME`：创建公开 `deepseek-ai/deepseek-harness-sdk` 仓库是首次发布的前置条件。 +- **`APP_IDENTITY.url` 指向一个尚不存在的仓库**：[#1972](https://github.com/deepseek-harness/deepseek-harness/issues/1972) 跟踪在首次发布前让该公开主页可访问。 - **`GenerateOptions.sessionId` 是本地声明的品牌类型**：导入 dsh-session 的 `SessionId` 会产生循环；未来拥有 id 的包可以消除该权宜之计。 diff --git a/packages/llm/llm/src/attribution.ts b/packages/llm/llm/src/attribution.ts index cdaea4b96b..b9375b6ef9 100644 --- a/packages/llm/llm/src/attribution.ts +++ b/packages/llm/llm/src/attribution.ts @@ -40,8 +40,8 @@ export interface AppIdentity { export const APP_IDENTITY: AppIdentity = { product: 'deepseek-harness', version, - // FIXME: create the public deepseek-ai/deepseek-harness-sdk repository this - // URL promises before the first release ships attribution pointing at it. + // The public-home release blocker is tracked in + // https://github.com/deepseek-harness/deepseek-harness/issues/1972. url: 'https://github.com/deepseek-ai/deepseek-harness-sdk', } diff --git a/packages/sdk/telemetry/README.i18n.yaml b/packages/sdk/telemetry/README.i18n.yaml index 9baaa2ebff..987dc8197c 100644 --- a/packages/sdk/telemetry/README.i18n.yaml +++ b/packages/sdk/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/sdk/telemetry/README.md -README.md: 1d33915f36e0af10eedac5f9ab34f2534268a327 -README.zh.md: af54cc2c78cb360d4305eeaf584c8330a0b7efa5 +README.md: c9f66a2415c91b75105b0ed025470da234b2523d +README.zh.md: bfb154e4c7c017292b5479e50ff376cbb9470682 diff --git a/packages/sdk/telemetry/README.md b/packages/sdk/telemetry/README.md index 1d33915f36..c9f66a2415 100644 --- a/packages/sdk/telemetry/README.md +++ b/packages/sdk/telemetry/README.md @@ -14,7 +14,7 @@ Launcher-side telemetry primitives for the dsh-sdk toolchain. This is a plain li Consent is carried by the telemetry entry in `cordis.yml`, so disabling telemetry is disabling that entry. Telemetry reports by default and is off only when a present telemetry entry is explicitly `disabled`: a missing `cordis.yml` (first `create`), an enabled entry, or a `cordis.yml` with no telemetry entry all report. `DO_NOT_TRACK`/CI always deny. The no-config and absent-entry defaults are configurable on `ConsentResolver`. -The collection endpoint is a fixed constant (`DSH_TELEMETRY_ENDPOINT`); its `.invalid` placeholder must be replaced with the real endpoint before release. +The collection endpoint is a fixed constant (`DSH_TELEMETRY_ENDPOINT`); [#1973](https://github.com/deepseek-harness/deepseek-harness/issues/1973) tracks deploying the service and replacing its fail-safe `.invalid` placeholder before release. ## Model Experience @@ -26,5 +26,5 @@ None; this package neither assembles nor sends a provider request. ## Known Limitations and Deferred Work -- **Placeholder endpoint** — `DSH_TELEMETRY_ENDPOINT` points at `.invalid` until the real endpoint is set. +- **Placeholder endpoint** — `DSH_TELEMETRY_ENDPOINT` points at `.invalid` until the service tracked in [#1973](https://github.com/deepseek-harness/deepseek-harness/issues/1973) is ready. - **Redaction is heuristic** — a conservative backstop, not a guarantee; secrets belong in `.env`, which is never read or reported. diff --git a/packages/sdk/telemetry/README.zh.md b/packages/sdk/telemetry/README.zh.md index af54cc2c78..bfb154e4c7 100644 --- a/packages/sdk/telemetry/README.zh.md +++ b/packages/sdk/telemetry/README.zh.md @@ -14,7 +14,7 @@ Consent 由 `cordis.yml` 中的 telemetry 配置项承载，因此禁用 telemetry 就是禁用该配置项。telemetry 默认上报，只有已经存在的 telemetry 配置项被显式设为 `disabled` 时才关闭：缺少 `cordis.yml`（首次 `create`）、配置项已启用，或 `cordis.yml` 中没有 telemetry 配置项时都会上报。`DO_NOT_TRACK`／CI 始终拒绝。无配置与缺少配置项的默认值可以通过 `ConsentResolver` 配置。 -收集端点是固定常量（`DSH_TELEMETRY_ENDPOINT`）；发布前必须将其 `.invalid` 占位值替换为真实端点。 +收集端点是固定常量（`DSH_TELEMETRY_ENDPOINT`）；[#1973](https://github.com/deepseek-harness/deepseek-harness/issues/1973) 跟踪服务部署，以及发布前将作为安全兜底的 `.invalid` 占位值替换为真实端点。 ## 模型体验 @@ -26,5 +26,5 @@ Consent 由 `cordis.yml` 中的 telemetry 配置项承载，因此禁用 telemet ## 已知限制与暂缓事项 -- **占位端点**：`DSH_TELEMETRY_ENDPOINT` 指向 `.invalid`，直到设置真实端点。 +- **占位端点**：`DSH_TELEMETRY_ENDPOINT` 指向 `.invalid`，直至 [#1973](https://github.com/deepseek-harness/deepseek-harness/issues/1973) 跟踪的服务就绪。 - **脱敏依赖启发式规则**：这只是保守后备，不是保证；密钥应存放于 `.env`，而该文件绝不会被读取或上报。 diff --git a/packages/sdk/telemetry/src/reporter.ts b/packages/sdk/telemetry/src/reporter.ts index d41c1db9b7..3ad7b4b62e 100644 --- a/packages/sdk/telemetry/src/reporter.ts +++ b/packages/sdk/telemetry/src/reporter.ts @@ -16,11 +16,10 @@ import { getOrCreateAnonymousId, type AnonymousId } from './anonymous-id.ts' import { SecretRedactor } from './secret-redactor.ts' /** - * Placeholder collection endpoint. This is a fixed protocol constant, not a - * deployment tunable. - * - * FIXME(ccyu): replace with the real telemetry endpoint before release. The - * `.invalid` TLD guarantees delivery fails harmlessly until then. + * Fail-safe placeholder collection endpoint. The `.invalid` TLD guarantees + * delivery fails harmlessly until the service tracked in + * https://github.com/deepseek-harness/deepseek-harness/issues/1973 is ready. + * This is a fixed protocol constant, not a deployment tunable. */ export const DSH_TELEMETRY_ENDPOINT = 'https://telemetry.example.invalid/v1/dsh-sdk' diff --git a/scripts/install.sh b/scripts/install.sh index 5c9d892f73..59184d91ab 100755 --- a/scripts/install.sh +++ b/scripts/install.sh @@ -47,8 +47,6 @@ # DSH_CURRENT stable symlink to the active worktree (default: $DSH_SOURCE/current) # DSH_BIN_DIR directory the `dsh` symlink lands in (default: ~/.local/bin) # DSH_HOME Harness home holding profiles and user patches (default: ~/.dsh) -# FIXME(install-ts): Move the post-checkout workflow into a tested TypeScript -# entrypoint; keep this POSIX shell file as the curl/source bootstrap. set -eu DSH_REF=${DSH_REF:-master}