mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into worktree/fix-multi-select-custom-answer
# Conflicts: # apps/web/tests/snapshots/question-composer/answered.expected.md # apps/web/tests/snapshots/question-composer/session.jsonl # docs/core-data-structures/user-interaction.i18n.yaml # packages/client/ui-question/README.i18n.yaml # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/README.md # packages/host/apiproxy/README.zh.md # packages/ui/tui/README.i18n.yaml # packages/ui/user-interaction/README.i18n.yaml
This commit is contained in:
Yichen Jiang
@@ -1,6 +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
|
||||
approval.md: 0de13eb1504b5ecc4ac0eafefefa2c87562c89b4
|
||||
approval.zh.md: b7ba10449fccfdb0dd5b52374e14038e3ec76ff8
|
||||
# pnpm run verify-translation-pairing --write docs/core-data-structures/approval.md
|
||||
approval.md: f1889b25e2bbbcb157b0bced070b1f157a867504
|
||||
approval.zh.md: c460ec2cb847a9e9a3e772987830b58e93fc3715
|
||||
|
||||
@@ -42,13 +42,12 @@ type ApprovalOutcome = 'allowed-once' | 'rejected' | 'cancelled' | 'unavailable'
|
||||
* (exactly today's behavior).
|
||||
* - `'never'` — never prompt anyone: every ask resolves `'rejected'`
|
||||
* deterministically. The strict headless stance (CI, unattended runs) and
|
||||
* the only policy value stated in the system prompt — unlike `'ask'`, its
|
||||
* outcome is knowable without asking, so stating it cannot overclaim.
|
||||
* the policy whose outcome is knowable without asking.
|
||||
*/
|
||||
type ApprovalPolicy = 'ask' | 'never'
|
||||
```
|
||||
|
||||
The prompt section states the deterministic `never` behavior and records either policy with a source-owned marker. The pre-step narrator reads that marker from the logged request header after restart; it does not infer state from deployment persona prose.
|
||||
Both policies contribute their complete current meaning to the cache-safe runtime-context snapshot. The sourced `user/message` is the durable model-visible input; changing approval state appends a new full snapshot after retained history without rewriting the request header's system prompt.
|
||||
|
||||
## Approval request
|
||||
|
||||
@@ -87,4 +86,4 @@ interface ApprovalRequest {
|
||||
|
||||
`ctx.approval.request(req)` requires the requesting session to be inside an open turn. It appends `approval/asked`, obtains one outcome, appends the matching `approval/decided`, and resolves with that outcome. The `never` policy is enforced inside the service before waterfall dispatch, so even an answerer registered later with `prepend` cannot bypass it. Answerers return an outcome when they own the request or call `next()` to delegate; the first answer occupies the single decision slot.
|
||||
|
||||
The audit events are log-only and do not enter the model transcript. Model-visible behavior is the caller's derived tool result, while the request header records the prompt policy that the model actually saw. Service disposal removes its prompt section and pre-step narrator together; answerer listeners are independently effect-bound to their owning plugins.
|
||||
The audit events are log-only and do not enter the model transcript. Model-visible behavior is the caller's derived tool result plus the current runtime-context snapshot. Service disposal removes its context contribution; answerer listeners are independently effect-bound to their owning plugins.
|
||||
|
||||
@@ -42,13 +42,12 @@ type ApprovalOutcome = 'allowed-once' | 'rejected' | 'cancelled' | 'unavailable'
|
||||
* (exactly today's behavior).
|
||||
* - `'never'` — never prompt anyone: every ask resolves `'rejected'`
|
||||
* deterministically. The strict headless stance (CI, unattended runs) and
|
||||
* the only policy value stated in the system prompt — unlike `'ask'`, its
|
||||
* outcome is knowable without asking, so stating it cannot overclaim.
|
||||
* the policy whose outcome is knowable without asking.
|
||||
*/
|
||||
type ApprovalPolicy = 'ask' | 'never'
|
||||
```
|
||||
|
||||
提示词段落会声明 `never` 的确定性行为，并以服务自有的标记记录当前策略。重启后，步骤前叙述器从已记录的请求头中读取该标记，而非从部署 persona 行文中推断状态。
|
||||
两种策略都会将各自完整的当前含义贡献给缓存安全的运行时上下文快照。带来源的 `user/message` 是持久化且模型可见的输入；批准状态变化时，会在保留的历史后追加一份新的完整快照，而不改写请求头中的系统提示词。
|
||||
|
||||
## 审批请求
|
||||
|
||||
@@ -87,4 +86,4 @@ interface ApprovalRequest {
|
||||
|
||||
`ctx.approval.request(req)` 要求发起请求的会话处于一个打开的轮次内。它追加 `approval/asked`，获取一个结果，追加对应的 `approval/decided`，然后以该结果 resolve。`never` 策略在服务内部、waterfall 分发之前强制执行，因此即使后来以 `prepend` 注册的应答者也无法绕过它。应答者在拥有该请求时返回结果，否则调用 `next()` 委托；第一个应答占据唯一的决策槽位。
|
||||
|
||||
审计事件仅写入日志，不进入模型 transcript（文本记录）。模型可见的行为是调用方派生的工具结果，而请求头记录的是模型实际看到的提示词策略。服务 dispose（资源释放）时会一并移除其提示词段落和步骤前叙述器；应答者监听器独立地通过 effect 绑定到其所属插件。
|
||||
审计事件仅写入日志，不进入模型 transcript（文本记录）。模型可见的行为是调用方派生的工具结果与当前运行时上下文快照。服务 dispose（资源释放）时会移除其上下文贡献；应答者监听器独立地通过 effect 绑定到其所属插件。
|
||||
|
||||
@@ -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/compaction.md
|
||||
compaction.md: 911b71d00fa4b42e9cdfa67f67d4e9b29e354a4a
|
||||
compaction.zh.md: 643a116ff2edbbb53d300b4f5ff0ad36d401130b
|
||||
compaction.md: 070adc65fb25b2536c88701c375cc0b2a5308559
|
||||
compaction.zh.md: 9167882f63b2931ba3ce49697e0c87164394af89
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
English | [中文](compaction.zh.md)
|
||||
|
||||
The compaction seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)).
|
||||
The compaction seam — a [capability seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and human consumer ([dsh-command-compact](../../packages/compact/command-compact)). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam Agent Note](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)).
|
||||
|
||||
Source: [`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts)
|
||||
|
||||
@@ -12,12 +12,14 @@ Compaction extends [`SessionEventMap`](session.md) with three event types via de
|
||||
|
||||
| Event | Payload | Role |
|
||||
|---|---|---|
|
||||
| `compact/start` | `{ turn }` | acquires the log-recorded lock |
|
||||
| `compact/start` | `{ turn }` | acquires the log-recorded lock; a number identifies the open automatic turn, while `null` identifies a standalone manual attempt |
|
||||
| `compact/summary` | `{ summary, rawOutput?, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens?, usage? }` | provenance: the safe summary projection, optional complete provider output and usage, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`provider`, `model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability Agent Note) |
|
||||
| `compact/end` | `{ turn, error? }` | releases the lock (`error` set when summarization threw) |
|
||||
| `compact/end` | `{ turn, error? }` | releases the lock with the same numeric-or-null owner (`error` records an unsuccessful attempt) |
|
||||
|
||||
The lock brackets the **whole** operation: `compact/start` is appended first, then summarization, the `compact/summary` provenance record, and the `user/message` replacement all land, and only then `compact/end`. Releasing the lock last turns a crash mid-operation into a detectable orphaned lock (a `compact/start` with no matching `compact/end`) rather than a `compact/end` that falsely claims compaction finished.
|
||||
|
||||
The markers are lock time points, not an exclusive container. An unrelated idle injection can appear between a standalone manual start and end while summarization is pending. The manual path revalidates only its selected positional span, so that injected context survives after the replacement checkpoint. A live unmatched start blocks every entry point; an unmatched start before a newer `session/end-seed` is stale evidence from a prior lifecycle and is ignored.
|
||||
|
||||
These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` block, so — unlike the top-level types on the other sub-pages — they are not pasted as a drift-checked ` ```ts type-equiv ` block (the `verify-type-equiv` extractor matches only top-level declarations by name). The payload table above is the catalog entry; follow the source link for the authoritative shapes.
|
||||
|
||||
## `CompactionResult`
|
||||
@@ -60,7 +62,16 @@ Automatic callers state why policy is running; implementations may treat confirm
|
||||
type CompactionTrigger = 'pressure' | 'context-overflow'
|
||||
```
|
||||
|
||||
`CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Every backend marks its replacement `user/message` with the package-exported `COMPACT_CHECKPOINT_SOURCE`; consumers call `isCompactCheckpointSource()` instead of coupling checkpoint recognition to one backend. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration.
|
||||
`CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, `compactNow(agent, signal)` for one useful idle-session reduction even below pressure, and `compactRegion(...)` for an explicit inclusive surface range. `compactNow()` synchronously reserves the agent's next-turn admission, returns `null` without writing when no useful range exists, records a standalone `turn: null` bracket before summarization, flushes a closed attempt, and then releases admission so ordinary queued prompts derive from the new surface. Every backend marks its replacement `user/message` with `COMPACT_CHECKPOINT_SOURCE`; client and wire consumers import that value and `isCompactCheckpointSource()` from the cordis-free `@deepseek-ai/dsh-compact/checkpoint` subpath, while the package root re-exports both for host consumers. The predicate keeps checkpoint recognition independent of any one backend. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration.
|
||||
|
||||
Expected manual failures use `ManualCompactionErrorCode`:
|
||||
|
||||
```ts type-equiv
|
||||
/** Expected failure classes for an explicit idle-session compaction request. */
|
||||
type ManualCompactionErrorCode = 'busy' | 'changed' | 'summary' | 'commit' | 'persistence'
|
||||
```
|
||||
|
||||
`changed` and `summary` leave the conversation surface unchanged but still close and persist the failed attempt in the log. `commit` may follow partial mutation; `persistence` means the in-memory bracket closed but its flush failed. Cancellation remains separate and throws the exact abort reason after required cleanup.
|
||||
|
||||
Pressure compaction runs at serial `agent/step` before request derivation. Once pressure or canonical overflow qualifies, compact-basic invokes optional [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md) before range selection, remeasures through `ctx.tokenMeter`, and can advance the surface without a summary. Failed-request recovery runs through `agent/request-error` after the failed step closes and returns a retry action only when the surface replacement generation advances, even if later summary work throws after pruning; cancellation still wins. Region boundaries preserve tool-call/result pairing but not whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling.
|
||||
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
[English](compaction.md) | 中文
|
||||
|
||||
压缩 seam 是一个[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)，与 bash 一样分为接口（[dsh-compact](../../packages/compact/compact)，`ctx.compact`）、实现（例如 [dsh-compact-basic](../../packages/compact/compact-basic) 后端）和消费方（延期实现的 `/compact` 工具）。压缩是**一项可选能力**，不属于 agent loop（智能体循环）主干，因此其词汇定义在此而非 [core.md](core.md) 中。基于 tokenizer 或模板的后端是实现同一接口的兄弟包（package）。与 bash 不同，该接口必然依赖 `dsh-session` 和 `dsh-llm`：其动词作用于 agent 所有的 `Session`，而其持久摘要事件使用 `ContentBlock` 词汇（见[压缩能力 seam Agent Note（agent 决策记录）](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)）。
|
||||
压缩 seam 是一个[能力 seam](../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)，与 bash 一样分为接口（[dsh-compact](../../packages/compact/compact)，`ctx.compact`）、实现（例如 [dsh-compact-basic](../../packages/compact/compact-basic) 后端）和面向用户的消费方（[dsh-command-compact](../../packages/compact/command-compact)）。压缩是**一项可选能力**，不属于 agent loop（智能体循环）主干，因此其词汇定义在此而非 [core.md](core.md) 中。基于 tokenizer 或模板的后端是实现同一接口的兄弟包（package）。与 bash 不同，该接口必然依赖 `dsh-session` 和 `dsh-llm`：其动词作用于 agent 所有的 `Session`，而其持久摘要事件使用 `ContentBlock` 词汇（见[压缩能力 seam Agent Note（agent 决策记录）](../../.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md)）。
|
||||
|
||||
源码：[`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts)
|
||||
|
||||
@@ -12,12 +12,14 @@
|
||||
|
||||
| 事件 | 载荷 | 作用 |
|
||||
|---|---|---|
|
||||
| `compact/start` | `{ turn }` | 获取日志记录的锁 |
|
||||
| `compact/start` | `{ turn }` | 获取日志记录的锁；数字标识打开的自动轮次，`null` 标识独立手动尝试 |
|
||||
| `compact/summary` | `{ summary, rawOutput?, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens?, usage? }` | provenance：安全摘要投影、可选的完整 provider 输出与 usage、被遮蔽的 surface 边界对（`start`/`end` seq——位置跨度，而非数值区间）、按 surface 顺序排列的被遮蔽 seq、估算 token 数，以及摘要调用的 envelope（`provider`、`model`，若有生成上限则还包括该上限）——写入日志后，该一次性请求可由日志 + 代码重建（见可重建性 Agent Note） |
|
||||
| `compact/end` | `{ turn, error? }` | 释放锁（摘要调用抛出异常时设置 `error`） |
|
||||
| `compact/end` | `{ turn, error? }` | 使用相同的数字或 `null` 归属值释放锁（`error` 记录失败尝试） |
|
||||
|
||||
锁括住**整个**操作：先追加 `compact/start`，然后执行摘要生成、写入 `compact/summary` 来源记录与 `user/message` 替换，最后才追加 `compact/end`。最后释放锁意味着操作中途崩溃会表现为可检测的遗留锁（有 `compact/start` 而无匹配的 `compact/end`），而非一个虚假声称压缩已完成的 `compact/end`。
|
||||
|
||||
这些标记表示锁的时间点，而不是排他的容器。摘要等待期间，不相关的空闲注入可以出现在独立的手动 start 与 end 之间。手动路径只重新验证所选位置 span，因此替换检查点之后仍保留该注入上下文。活动的未匹配 start 会阻塞所有入口点；较新 `session/end-seed` 之前的未匹配 start 是先前生命周期留下的陈旧证据，会被忽略。
|
||||
|
||||
这些变体在 `declare module '@deepseek-ai/dsh-session'` 块内合并，因此——与其他子页面上的顶层类型不同——它们不以漂移检查的 ` ```ts type-equiv ` 块粘贴（`verify-type-equiv` 提取器只按名称匹配顶层声明）。上方的载荷表即为目录条目；权威形状请循源码链接查看。
|
||||
|
||||
## `CompactionResult`
|
||||
@@ -60,7 +62,16 @@ interface CompactionResult {
|
||||
type CompactionTrigger = 'pressure' | 'context-overflow'
|
||||
```
|
||||
|
||||
`CompactService` 暴露 `compactIfNeeded(agent, trigger, signal)` 以执行自动 `pressure` 或 `context-overflow` 策略；没有可安全执行的工作时返回 `null`。它还针对显式、两端均包含的 surface 范围暴露 `compactRegion(...)`。每个后端都使用包导出的 `COMPACT_CHECKPOINT_SOURCE` 标记其替换用的 `user/message`；消费方调用 `isCompactCheckpointSource()`，而不是把检查点识别逻辑耦合到某一个后端。实现必须把传入的 signal 转发给摘要流程。该 seam 不拥有计价 API：单例 [`ctx.tokenMeter`](token-meter.md) 直接拥有估算与回放，而 `dsh-compact-basic` 拥有保留策略、事件排序、按路由执行的摘要调用及其配置。
|
||||
`CompactService` 暴露 `compactIfNeeded(agent, trigger, signal)` 以执行自动 `pressure` 或 `context-overflow` 策略，暴露 `compactNow(agent, signal)` 以便即使未达到压力也对空闲会话进行一次有效缩减，还针对显式、两端均包含的 surface 范围暴露 `compactRegion(...)`。`compactNow()` 会同步预留 agent 的下一轮次接纳；没有有效范围时返回 `null` 且不写入；在摘要前记录独立的 `turn: null` 标记对；flush 已闭合尝试；随后释放接纳预留，使普通排队提示词从新表层派生。每个后端都使用 `COMPACT_CHECKPOINT_SOURCE` 标记其替换用的 `user/message`；client 与 wire 消费方从无 cordis 的 `@deepseek-ai/dsh-compact/checkpoint` 子路径导入该值和 `isCompactCheckpointSource()`，包根则为 host 消费方重新导出两者。该判定函数使检查点识别不依赖任一特定后端。实现必须把传入的 signal 转发给摘要流程。该 seam 不拥有计价 API：单例 [`ctx.tokenMeter`](token-meter.md) 直接拥有估算与回放，而 `dsh-compact-basic` 拥有保留策略、事件排序、按路由执行的摘要调用及其配置。
|
||||
|
||||
预期的手动失败使用 `ManualCompactionErrorCode`：
|
||||
|
||||
```ts type-equiv
|
||||
/** Expected failure classes for an explicit idle-session compaction request. */
|
||||
type ManualCompactionErrorCode = 'busy' | 'changed' | 'summary' | 'commit' | 'persistence'
|
||||
```
|
||||
|
||||
`changed` 和 `summary` 保持会话表层不变，但仍会闭合失败尝试并将其持久化到日志。`commit` 可能发生在部分变更之后；`persistence` 表示内存中的标记对已闭合，但 flush 失败。取消独立于这些失败，并在完成必要清理后抛出原始 abort 原因。
|
||||
|
||||
压力压缩在串行 `agent/step` 中运行，先于请求推导。一旦压力或规范化溢出满足条件，compact-basic 会在选择范围前调用可选的 [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md)，再通过 `ctx.tokenMeter` 重新测量，并且可以在不生成摘要的情况下推进 surface。失败请求的恢复在失败的步骤关闭后通过 `agent/request-error` 运行；仅当 surface replacement generation 前进时才返回重试动作，即便后续摘要工作在剪枝后抛异常亦如此；取消仍然优先。区域边界保持工具调用/结果配对，但不保持整个轮次，因此一个过大轮次中较早关闭的步骤可以被压缩。`dsh-compact-basic` 拥有阈值、保留尾部策略、溢出上限与失败处理。
|
||||
|
||||
|
||||
@@ -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: dad533cee00646a40f57bd9097b2cceb8e9de9e2
|
||||
core.zh.md: 9e8afac0744fcf0df8c35dad5debce746d6614c6
|
||||
core.md: 1b5704384157688b45ae0900bf2d9924426bbd6b
|
||||
core.zh.md: 05802039920163ac8185703ab483c5603087ed96
|
||||
|
||||
@@ -24,6 +24,8 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
|
||||
| [commands.md](commands.md) | the human-command seam: definitions, adapter discovery, direct invocation, results, and parsing views |
|
||||
| [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, execution enclosure, and standalone events |
|
||||
| [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` |
|
||||
| [settings.md](settings.md) | the user-settings seam: `SettingsNamespace` registration, layered resolution (defaults → composition `base` → user document), owner scopes, hot commits |
|
||||
| [credentials.md](credentials.md) | the credential seam: `CredentialRef` references (never values) in configuration, per-operation resolution, UI-safe `CredentialInfo`, provider source layers |
|
||||
| [session-query.md](session-query.md) | logical records, bounded exact-event reads, relationship traces, semantic filters/documents, and full-text result pages |
|
||||
| [session-title.md](session-title.md) | durable title snapshots, source provenance, and the asynchronous provider contract |
|
||||
| [system-prompt.md](system-prompt.md) | per-assembly context, tool-provider results, prompt sections, and cooperative assembly |
|
||||
@@ -181,6 +183,34 @@ Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts)
|
||||
|
||||
Provider and model discovery uses small provider-neutral descriptors. A model catalog is advisory: routing still keys on a registered provider, and an adapter may accept unlisted model ids.
|
||||
|
||||
Registering an adapter returns a handle: the disposer, plus the atomic route replacement a plugin whose route set is user-configurable needs.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* What {@link LlmService.registerAdapter} returns: the disposer, plus an
|
||||
* atomic route replacement for the same adapter instance.
|
||||
*/
|
||||
interface AdapterRegistrationHandle {
|
||||
/** Release every route this registration currently holds. */
|
||||
(): void
|
||||
/**
|
||||
* Replace this registration's routes with `providers`, keeping the same
|
||||
* adapter instance. The candidate set is validated in full first — a
|
||||
* conflict with another adapter, an invalid name, or bad provider metadata
|
||||
* throws and leaves the current routes untouched — and the swap itself is
|
||||
* one synchronous section, so no request can observe a gap. An empty array
|
||||
* is legal here (a settings section that emptied holds zero routes while
|
||||
* staying registered), unlike an empty initial registration.
|
||||
*
|
||||
* Throws `LlmError` with code `REGISTRATION_DISPOSED` once the registration
|
||||
* has been released: its routes are gone and its disposer has already run,
|
||||
* so anything registered afterwards would have no owner left to release it.
|
||||
* @param providers - the complete next route set for this registration.
|
||||
*/
|
||||
replace(providers: string[]): void
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Display metadata for one registered provider route. */
|
||||
interface LlmProviderInfo {
|
||||
@@ -191,6 +221,30 @@ interface LlmProviderInfo {
|
||||
}
|
||||
```
|
||||
|
||||
Adapter plugins additionally declare which routes *could* run through `registerConfigurableProviders()`, addressing each one's user-settings section, so configuration surfaces can offer dormant providers before any route registers.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* One provider route an adapter plugin can activate through configuration,
|
||||
* whether or not the route is currently registered. Configuration surfaces
|
||||
* merge this directory with `listProviders()` to offer every configurable
|
||||
* provider alongside its live/dormant state.
|
||||
*/
|
||||
interface LlmConfigurableProvider {
|
||||
/** Provider route key this entry activates when configured. */
|
||||
provider: string
|
||||
/** Human-readable provider name for configuration surfaces. */
|
||||
displayName: string
|
||||
/** User-settings namespace whose section configures this provider. */
|
||||
settingsNs: string
|
||||
/**
|
||||
* Path from that namespace's section root to this provider's profile
|
||||
* object; empty when the whole section is the profile.
|
||||
*/
|
||||
settingsPath: readonly string[]
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** One adapter-discovered model; catalog membership is advisory, not request validation. */
|
||||
interface LlmModelInfo {
|
||||
@@ -205,7 +259,7 @@ interface LlmModelInfo {
|
||||
}
|
||||
```
|
||||
|
||||
Correctness-sensitive metadata is resolved separately from the advisory catalog and is owned by the adapter serving the exact route. Context capacity and reasoning choices share one exact-model result so consumers do not repeat authoritative model resolution.
|
||||
Correctness-sensitive metadata is resolved separately from the advisory catalog and is owned by the adapter serving the exact route. Context capacity, adapter call defaults, and reasoning choices share one exact-model result so consumers do not repeat authoritative model resolution.
|
||||
|
||||
```ts type-equiv
|
||||
/** Provider-owned context capacity for one exact provider/model route. */
|
||||
@@ -252,6 +306,8 @@ interface LlmModelReasoningInfo {
|
||||
interface LlmResolvedModelInfo extends LlmModelInfo {
|
||||
/** Provider-owned context capacity when known. */
|
||||
context?: LlmModelContext
|
||||
/** Adapter-configured per-request output cap materialized when callers omit one. */
|
||||
defaultMaxTokens?: number
|
||||
/** Adapter-owned selectable reasoning levels when exposed. */
|
||||
reasoning?: LlmModelReasoningInfo
|
||||
}
|
||||
@@ -338,9 +394,9 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition`
|
||||
|
||||
### The request envelope: `LlmCallConfig` and the logged header
|
||||
|
||||
The loop builds each request from logged state. `EpochHeader` records call config, rendered prompt, and authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset) through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability Agent Note](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md).
|
||||
The loop builds each request from logged state. `EpochHeader` records call config, adapter-default provenance, rendered prompt, and authoritative returned tool order (configured by `toolOrder`, or lexicographic when unset) through full `request/header` snapshots. Together with derived history, this makes the request reconstructable from the session log. See [session.md](session.md#the-request-header-event-requestheader) and the [reconstructability Agent Note](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md).
|
||||
|
||||
`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, reasoning effort, or sampling. After the waterfall, the loop prepares the exact model capability under the turn signal, rejects unsupported explicit effort ids without clamping, materializes an adapter-configured default, and logs the effective value. The prepared call keeps one adapter registration through dispatch. Requests reaching `llm/stream` are deep-frozen, so mutation throws, and carry a process-local loop identity so observers do not confuse separately logged frozen auxiliary calls with conversation requests.
|
||||
`agent/request` receives a frozen call-config seed and may return a replacement to switch provider, model, reasoning effort, or sampling. Before the waterfall, the loop removes values marked as adapter defaults so exact-model preparation materializes the selected route's current values; unmarked explicit settings remain in the proposal. After the waterfall, preparation rejects unsupported explicit effort ids without clamping and logs the effective config plus provenance under the turn signal. The prepared call keeps one adapter registration through dispatch. Requests reaching `llm/stream` are deep-frozen, so mutation throws, and carry a process-local loop identity so observers do not confuse separately logged frozen auxiliary calls with conversation requests.
|
||||
|
||||
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.
|
||||
|
||||
@@ -363,6 +419,17 @@ interface LlmCallConfig {
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Effective config fields supplied by exact-model adapter resolution rather
|
||||
* than by the caller's request proposal.
|
||||
*/
|
||||
interface LlmCallConfigAdapterDefaults {
|
||||
reasoningEffort?: true
|
||||
maxTokens?: true
|
||||
}
|
||||
```
|
||||
|
||||
## Sessions
|
||||
|
||||
A `Session` is an **append-only log** of typed `SessionEvent`s — the single source of truth. The LLM message history is *derived* from the log (`deriveMessages()`), not stored separately. The event vocabulary derives from `SessionEventMap`:
|
||||
@@ -449,11 +516,12 @@ interface InboxItem {
|
||||
type InboxAction =
|
||||
| { readonly kind: 'edit'; readonly content: ContentBlock[] }
|
||||
| { readonly kind: 'remove' }
|
||||
| { readonly kind: 'steer' }
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Result of applying an inbox action at the synchronous ownership boundary. */
|
||||
type InboxActionResult = 'applied' | 'not-found'
|
||||
type InboxActionResult = 'applied' | 'not-found' | 'steer-unavailable'
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
@@ -479,7 +547,7 @@ interface SendOptions {
|
||||
}
|
||||
```
|
||||
|
||||
The fixed-preset aliases own `target` and `wakeup`; their already identified `UserMessage` carries role, content, and provenance. Its `MessageId` remains stable when an edit replaces the message content, while the enclosing `InboxItemId` identifies one accepted occurrence across `agent/inbox/enqueue`, `agent/inbox/update`, and its terminal dequeue or discard. Injection bypasses the FIFOs and never appears on those events.
|
||||
The fixed-preset aliases own `target` and `wakeup`; their already identified `UserMessage` carries role, content, and provenance. Its `MessageId` remains stable when an edit replaces content or strict steer transfers the immutable message. The original queued occurrence ends and strict steer accepts a new steering occurrence with a distinct `InboxItemId`. Injection bypasses the FIFOs and never appears on inbox lifecycle events.
|
||||
|
||||
```ts type-equiv
|
||||
/** Options for {@link Agent.cancel}. */
|
||||
@@ -493,6 +561,8 @@ interface CancelOptions {
|
||||
}
|
||||
```
|
||||
|
||||
`SteeringReceipt.outcome` always resolves. `admitted` identifies the turn and step whose immutable request history contains that exact message; `rejected` means lifecycle or terminal policy discarded it first. Synchronous input validation still throws from `steer()`.
|
||||
|
||||
```ts type-equiv
|
||||
/** Stable runtime cause accepted by {@link Agent.cancel}. */
|
||||
type AgentCancelCause =
|
||||
@@ -547,13 +617,30 @@ interface Agent {
|
||||
*/
|
||||
send(message: UserMessage, options: SendOptions): void
|
||||
|
||||
/**
|
||||
* Reserve admission of the next ordinary turn while this agent is idle, so an
|
||||
* operation can mutate durable history before any queued prompt derives a
|
||||
* request from it. Already-accepted waking work has right of way, including a
|
||||
* send whose wake is still a pending microtask. Later sends keep their
|
||||
* ordinary placement, FIFO order, and `wakeup` facts, and
|
||||
* {@link acceptsNextStep} stays `false`, so a waking `next-step` send becomes
|
||||
* a queued follow-up rather than steering; cancellation and disposal may
|
||||
* still discard them. {@link inject} is not withheld. {@link whenIdle} treats
|
||||
* a live reservation as activity, while lifecycle teardown does not await it.
|
||||
* @returns the idempotent release, or `undefined` when the agent is running, already reserved, or already committed to waking work.
|
||||
*/
|
||||
reserveTurnAdmission(): (() => void) | undefined
|
||||
|
||||
/**
|
||||
* Mutate one still-pending queued occurrence synchronously. Editing preserves
|
||||
* the message identity and queue position; removal publishes its terminal
|
||||
* discard. Steering occurrences and driver-claimed items return `not-found`.
|
||||
* discard. Steer strictly transfers the message into the current next-step
|
||||
* window, or returns `steer-unavailable` without changing the queued
|
||||
* occurrence. Steering occurrences and driver-claimed items return
|
||||
* `not-found`.
|
||||
* @param id - independently addressable queued occurrence.
|
||||
* @param action - edit or remove operation.
|
||||
* @returns whether the pending occurrence was found and updated.
|
||||
* @param action - edit, remove, or strict steer operation.
|
||||
* @returns the applied outcome or the reason no mutation occurred.
|
||||
*/
|
||||
updateInbox(id: InboxItemId, action: InboxAction): InboxActionResult
|
||||
|
||||
@@ -580,16 +667,18 @@ interface Agent {
|
||||
followup(message: UserMessage): void
|
||||
|
||||
/**
|
||||
* Submit steering during prompt admission or an open turn — the
|
||||
* `next-step`/wakeup preset of {@link send}. It stages for the next steering
|
||||
* checkpoint before a request or stop decision. If the activity fails before
|
||||
* that boundary, the remainder stays staged without waking the agent; retry
|
||||
* or a later prompt takes it. Outside that window steering falls back to a
|
||||
* woken follow-up turn, while cancellation or disposal may discard pending
|
||||
* steering.
|
||||
* Submit steering with a message-owned admission receipt — the
|
||||
* `next-step`/wakeup preset of {@link send}. During prompt admission or an
|
||||
* open turn, the message waits in the steering FIFO until a committed step
|
||||
* snapshots it; outside that window it enters the ordinary queued FIFO. The
|
||||
* receipt resolves `admitted` only after the message joins that step's
|
||||
* immutable request history, or `rejected` when terminal policy,
|
||||
* cancellation, or disposal discards it first. A non-terminal turn close may
|
||||
* leave it staged for a later admitted prompt without settling the receipt.
|
||||
* @param message - identified steering content and its producer provenance.
|
||||
* @returns the receipt for this exact message's eventual admission outcome.
|
||||
*/
|
||||
steer(message: UserMessage): void
|
||||
steer(message: UserMessage): SteeringReceipt
|
||||
|
||||
/**
|
||||
* Append model-facing context without running the model — the
|
||||
@@ -604,7 +693,7 @@ interface Agent {
|
||||
}
|
||||
```
|
||||
|
||||
`AgentStatus` is `'idle' | 'running'`, and `SessionId` is branded. Disposal removes the agent from the registry and emits `agent/disposed`; it is not a terminal status value. `running` describes the driver-wide drain interval and may span consecutive queued turns; it does not prove a turn is still open. `acceptsNextStep` is the narrower routing predicate for callers that must choose between steering the current admission/turn and submitting a fresh admitted prompt. `AgentOptions` is merge-extensible: core declares `provider?`, `model?`, and `maxTokens?` (dispatch requires provider and model after `agent/request`). When present, `maxTokens` must be a positive safe integer and caps every conversation-model request; omission leaves the provider default in control. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default.
|
||||
`AgentStatus` is `'idle' | 'running'`, and `SessionId` is branded. Disposal removes the agent from the registry and emits `agent/disposed`; it is not a terminal status value. `running` describes the driver-wide drain interval and may span consecutive queued turns; it does not prove a turn is still open. `acceptsNextStep` is the narrower routing predicate for callers that must choose between steering the current admission/turn and submitting a fresh admitted prompt. A live turn-admission reservation is quiescence-relevant without changing `status` or turning later queue entries into steering; its only authority is to defer the next driver claim until release. `AgentOptions` is merge-extensible: core declares `provider?`, `model?`, and `maxTokens?` (dispatch requires provider and model after `agent/request`). When present, `maxTokens` must be a positive safe integer and caps every conversation-model request; omission allows the exact-model adapter default to materialize before the request header, or otherwise leaves provider behavior unchanged. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default.
|
||||
|
||||
The cause is a TypeScript-enforced same-process input. An active `TurnCancellation` holder copies its discriminant into the runtime-only `AbortSignal.reason` and is retired before `turn/end` publication; the frozen `AbortSignal.reason` remains readable after that retirement. Only the loop reads the cause (`user`, `parent`, or lifecycle-only `disposed`) back off its own machine-private signal at settlement — there is no public reader, and a signal grants cooperating listeners no classification authority. Durable `turn/end` retains the coarse `{ kind: 'aborted' }` outcome; request provenance would require a separate durable event rather than overloading the terminal result.
|
||||
|
||||
|
||||
@@ -24,6 +24,8 @@ harness 是一个微内核：一个极小的核心加上众多插件。大多数
|
||||
| [commands.md](commands.md) | 人类命令 seam：定义、适配器发现、直接调用、结果与解析视图 |
|
||||
| [session.md](session.md) | 完整的 `SessionEventMap` 变体目录、`TurnTrigger`/`TurnEndReason`、`deriveMessages()`、执行封闭与独立事件 |
|
||||
| [persistence.md](persistence.md) | 持久性 seam：`SessionPersistence`、JSONL + SQLite 后端、`session/flush`、崩溃恢复、`SessionHeader` |
|
||||
| [settings.md](settings.md) | 用户设置 seam：`SettingsNamespace` 注册、分层解析（默认值 → 组合 `base` → 用户文档）、owner scope、热提交 |
|
||||
| [credentials.md](credentials.md) | 凭据 seam：配置中的 `CredentialRef` 引用（绝不含值）、按操作解析、对 UI 安全的 `CredentialInfo`、provider 来源层 |
|
||||
| [session-query.md](session-query.md) | 逻辑记录、有界精确事件读取、关系追踪、语义筛选器/文档与全文检索结果页 |
|
||||
| [session-title.md](session-title.md) | 持久标题快照、来源 provenance 与异步提供方契约 |
|
||||
| [system-prompt.md](system-prompt.md) | 逐次组装的上下文、工具提供方结果、提示词段落与协作式组装 |
|
||||
@@ -187,6 +189,34 @@ interface MessageSourceMap {
|
||||
|
||||
提供方与模型发现使用小型、提供方无关的描述符。模型目录仅供参考：路由仍以已注册提供方为键，适配器也可以接受未列出的模型 id。
|
||||
|
||||
注册适配器会返回一个句柄：既是释放器，也带有原子的路由替换——路由集合由用户配置决定的插件正需要它。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* What {@link LlmService.registerAdapter} returns: the disposer, plus an
|
||||
* atomic route replacement for the same adapter instance.
|
||||
*/
|
||||
interface AdapterRegistrationHandle {
|
||||
/** Release every route this registration currently holds. */
|
||||
(): void
|
||||
/**
|
||||
* Replace this registration's routes with `providers`, keeping the same
|
||||
* adapter instance. The candidate set is validated in full first — a
|
||||
* conflict with another adapter, an invalid name, or bad provider metadata
|
||||
* throws and leaves the current routes untouched — and the swap itself is
|
||||
* one synchronous section, so no request can observe a gap. An empty array
|
||||
* is legal here (a settings section that emptied holds zero routes while
|
||||
* staying registered), unlike an empty initial registration.
|
||||
*
|
||||
* Throws `LlmError` with code `REGISTRATION_DISPOSED` once the registration
|
||||
* has been released: its routes are gone and its disposer has already run,
|
||||
* so anything registered afterwards would have no owner left to release it.
|
||||
* @param providers - the complete next route set for this registration.
|
||||
*/
|
||||
replace(providers: string[]): void
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Display metadata for one registered provider route. */
|
||||
interface LlmProviderInfo {
|
||||
@@ -197,6 +227,30 @@ interface LlmProviderInfo {
|
||||
}
|
||||
```
|
||||
|
||||
适配器插件还会通过 `registerConfigurableProviders()` 声明哪些路由*可以*运行，并指明每条路由的用户设置分节，使配置界面能在任何路由注册之前就呈现休眠的提供方。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* One provider route an adapter plugin can activate through configuration,
|
||||
* whether or not the route is currently registered. Configuration surfaces
|
||||
* merge this directory with `listProviders()` to offer every configurable
|
||||
* provider alongside its live/dormant state.
|
||||
*/
|
||||
interface LlmConfigurableProvider {
|
||||
/** Provider route key this entry activates when configured. */
|
||||
provider: string
|
||||
/** Human-readable provider name for configuration surfaces. */
|
||||
displayName: string
|
||||
/** User-settings namespace whose section configures this provider. */
|
||||
settingsNs: string
|
||||
/**
|
||||
* Path from that namespace's section root to this provider's profile
|
||||
* object; empty when the whole section is the profile.
|
||||
*/
|
||||
settingsPath: readonly string[]
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** One adapter-discovered model; catalog membership is advisory, not request validation. */
|
||||
interface LlmModelInfo {
|
||||
@@ -211,7 +265,7 @@ interface LlmModelInfo {
|
||||
}
|
||||
```
|
||||
|
||||
对正确性敏感的元数据与参考目录分开解析，并归服务该确切路由的适配器所有。上下文容量和推理选项共用同一个确切模型结果，消费方因而无需重复执行权威模型解析。
|
||||
对正确性敏感的元数据与参考目录分开解析，并归服务该确切路由的适配器所有。上下文容量、适配器调用默认值和推理选项共用同一个确切模型结果，消费方因而无需重复执行权威模型解析。
|
||||
|
||||
```ts type-equiv
|
||||
/** Provider-owned context capacity for one exact provider/model route. */
|
||||
@@ -258,6 +312,8 @@ interface LlmModelReasoningInfo {
|
||||
interface LlmResolvedModelInfo extends LlmModelInfo {
|
||||
/** Provider-owned context capacity when known. */
|
||||
context?: LlmModelContext
|
||||
/** Adapter-configured per-request output cap materialized when callers omit one. */
|
||||
defaultMaxTokens?: number
|
||||
/** Adapter-owned selectable reasoning levels when exposed. */
|
||||
reasoning?: LlmModelReasoningInfo
|
||||
}
|
||||
@@ -344,9 +400,9 @@ interface ToolSchema {
|
||||
|
||||
### 请求信封：`LlmCallConfig` 与记录的 header
|
||||
|
||||
循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、渲染后的提示词以及权威返回工具顺序（由 `toolOrder` 配置；未配置时按字典序）。结合派生历史，请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note（agent 决策记录）](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。
|
||||
循环从已记录状态构建每个请求。`EpochHeader` 通过完整的 `request/header` 快照记录调用配置、适配器默认值来源、渲染后的提示词以及权威返回工具顺序（由 `toolOrder` 配置；未配置时按字典序）。结合派生历史，请求便可由会话日志重建。见 [session.md](session.md#the-request-header-event-requestheader) 与[可重建性 Agent Note（agent 决策记录）](../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md)。
|
||||
|
||||
`agent/request` 接收冻结的调用配置种子，并可返回替代值以切换提供方、模型、推理强度或采样参数。waterfall 结束后，循环会在轮次信号控制下完成确切模型的能力准备，拒绝显式指定但不受支持的推理强度 ID（不自动调整），填入适配器配置的默认值，并记录最终生效值。准备完成的调用直至分派完成始终持有同一项适配器注册。到达 `llm/stream` 的请求会被深度冻结，因此变更会抛异常；请求还携带进程本地循环标识，使观察者不会把单独记录的冻结辅助调用误认成对话请求。
|
||||
`agent/request` 接收冻结的调用配置种子，并可返回替代值以切换提供方、模型、推理强度或采样参数。waterfall 开始前，循环会移除标记为适配器默认值的值，使确切模型准备过程填入所选路由的当前值；未带标记的显式设置仍保留在提议中。waterfall 结束后，准备过程会在轮次信号控制下拒绝显式指定但不受支持的推理强度 ID（不自动调整），并记录生效配置及其来源。准备完成的调用直至分派完成始终持有同一项适配器注册。到达 `llm/stream` 的请求会被深度冻结，因此变更会抛异常；请求还携带进程本地循环标识，使观察者不会把单独记录的冻结辅助调用误认成对话请求。
|
||||
|
||||
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。
|
||||
|
||||
@@ -369,6 +425,17 @@ interface LlmCallConfig {
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Effective config fields supplied by exact-model adapter resolution rather
|
||||
* than by the caller's request proposal.
|
||||
*/
|
||||
interface LlmCallConfigAdapterDefaults {
|
||||
reasoningEffort?: true
|
||||
maxTokens?: true
|
||||
}
|
||||
```
|
||||
|
||||
## 会话
|
||||
|
||||
`Session` 是一份类型化 `SessionEvent` 的**仅追加日志**——唯一的真源。LLM（大语言模型）消息历史从日志*派生*（`deriveMessages()`），而非单独存储。事件词汇从 `SessionEventMap` 派生：
|
||||
@@ -457,11 +524,12 @@ interface InboxItem {
|
||||
type InboxAction =
|
||||
| { readonly kind: 'edit'; readonly content: ContentBlock[] }
|
||||
| { readonly kind: 'remove' }
|
||||
| { readonly kind: 'steer' }
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Result of applying an inbox action at the synchronous ownership boundary. */
|
||||
type InboxActionResult = 'applied' | 'not-found'
|
||||
type InboxActionResult = 'applied' | 'not-found' | 'steer-unavailable'
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
@@ -487,7 +555,7 @@ interface SendOptions {
|
||||
}
|
||||
```
|
||||
|
||||
固定预设的别名方法自带 `target` 与 `wakeup`；其已有标识的 `UserMessage` 会携带角色、内容与 provenance。编辑替换消息内容时，其 `MessageId` 保持稳定；外层 `InboxItemId` 则在 `agent/inbox/enqueue`、`agent/inbox/update` 及终态 dequeue 或 discard 之间标识同一次入队。注入绕过两个 FIFO，从不出现在这些事件中。
|
||||
固定预设的别名方法自带 `target` 与 `wakeup`；其已有标识的 `UserMessage` 会携带角色、内容与 provenance。编辑替换内容或严格 steering（中途引导）转移不可变消息时，其 `MessageId` 都保持稳定。原 queued 单次入队项会结束，严格 steering 则接受一个具有不同 `InboxItemId` 的新 steering 单次入队项。注入绕过两个 FIFO，从不出现在 inbox 生命周期事件中。
|
||||
|
||||
```ts type-equiv
|
||||
/** Options for {@link Agent.cancel}. */
|
||||
@@ -501,6 +569,8 @@ interface CancelOptions {
|
||||
}
|
||||
```
|
||||
|
||||
`SteeringReceipt.outcome` 始终会解析。`admitted` 标识其不可变请求历史包含该确切消息的轮次与步骤；`rejected` 表示生命周期或终止策略先丢弃了该消息。同步输入校验仍会从 `steer()` 抛出异常。
|
||||
|
||||
```ts type-equiv
|
||||
/** Stable runtime cause accepted by {@link Agent.cancel}. */
|
||||
type AgentCancelCause =
|
||||
@@ -555,13 +625,30 @@ interface Agent {
|
||||
*/
|
||||
send(message: UserMessage, options: SendOptions): void
|
||||
|
||||
/**
|
||||
* Reserve admission of the next ordinary turn while this agent is idle, so an
|
||||
* operation can mutate durable history before any queued prompt derives a
|
||||
* request from it. Already-accepted waking work has right of way, including a
|
||||
* send whose wake is still a pending microtask. Later sends keep their
|
||||
* ordinary placement, FIFO order, and `wakeup` facts, and
|
||||
* {@link acceptsNextStep} stays `false`, so a waking `next-step` send becomes
|
||||
* a queued follow-up rather than steering; cancellation and disposal may
|
||||
* still discard them. {@link inject} is not withheld. {@link whenIdle} treats
|
||||
* a live reservation as activity, while lifecycle teardown does not await it.
|
||||
* @returns the idempotent release, or `undefined` when the agent is running, already reserved, or already committed to waking work.
|
||||
*/
|
||||
reserveTurnAdmission(): (() => void) | undefined
|
||||
|
||||
/**
|
||||
* Mutate one still-pending queued occurrence synchronously. Editing preserves
|
||||
* the message identity and queue position; removal publishes its terminal
|
||||
* discard. Steering occurrences and driver-claimed items return `not-found`.
|
||||
* discard. Steer strictly transfers the message into the current next-step
|
||||
* window, or returns `steer-unavailable` without changing the queued
|
||||
* occurrence. Steering occurrences and driver-claimed items return
|
||||
* `not-found`.
|
||||
* @param id - independently addressable queued occurrence.
|
||||
* @param action - edit or remove operation.
|
||||
* @returns whether the pending occurrence was found and updated.
|
||||
* @param action - edit, remove, or strict steer operation.
|
||||
* @returns the applied outcome or the reason no mutation occurred.
|
||||
*/
|
||||
updateInbox(id: InboxItemId, action: InboxAction): InboxActionResult
|
||||
|
||||
@@ -588,16 +675,18 @@ interface Agent {
|
||||
followup(message: UserMessage): void
|
||||
|
||||
/**
|
||||
* Submit steering during prompt admission or an open turn — the
|
||||
* `next-step`/wakeup preset of {@link send}. It stages for the next steering
|
||||
* checkpoint before a request or stop decision. If the activity fails before
|
||||
* that boundary, the remainder stays staged without waking the agent; retry
|
||||
* or a later prompt takes it. Outside that window steering falls back to a
|
||||
* woken follow-up turn, while cancellation or disposal may discard pending
|
||||
* steering.
|
||||
* Submit steering with a message-owned admission receipt — the
|
||||
* `next-step`/wakeup preset of {@link send}. During prompt admission or an
|
||||
* open turn, the message waits in the steering FIFO until a committed step
|
||||
* snapshots it; outside that window it enters the ordinary queued FIFO. The
|
||||
* receipt resolves `admitted` only after the message joins that step's
|
||||
* immutable request history, or `rejected` when terminal policy,
|
||||
* cancellation, or disposal discards it first. A non-terminal turn close may
|
||||
* leave it staged for a later admitted prompt without settling the receipt.
|
||||
* @param message - identified steering content and its producer provenance.
|
||||
* @returns the receipt for this exact message's eventual admission outcome.
|
||||
*/
|
||||
steer(message: UserMessage): void
|
||||
steer(message: UserMessage): SteeringReceipt
|
||||
|
||||
/**
|
||||
* Append model-facing context without running the model — the
|
||||
@@ -612,7 +701,7 @@ interface Agent {
|
||||
}
|
||||
```
|
||||
|
||||
`AgentStatus` 为 `'idle' | 'running'`，`SessionId` 是品牌类型。dispose（资源释放）会把 agent 从注册表移除并发出 `agent/disposed`；它不是一个终态 status 值。`running` 描述整个驱动器的排空区间，可能跨越连续的排队轮次；它不能证明某个轮次仍然打开。对于需要在把输入作为 steering 加入当前提示词准入／轮次，还是提交为一个新的待准入提示词之间做选择的调用方，`acceptsNextStep` 才是更窄且准确的路由判断条件。`AgentOptions` 可合并扩展：core 声明 `provider?`、`model?` 与 `maxTokens?`（在 `agent/request` 后，分发要求 provider 与 model 都存在）。提供 `maxTokens` 时，它必须是正安全整数，并限制每次对话模型请求的输出；省略时由提供方默认值控制。Persona 归 `dsh-system-prompt` 所有：agent 作用域的 `deployment:persona` 可以遮蔽全局默认值。
|
||||
`AgentStatus` 为 `'idle' | 'running'`，`SessionId` 是品牌类型。dispose（资源释放）会把 agent 从注册表移除并发出 `agent/disposed`；它不是一个终态 status 值。`running` 描述整个驱动器的排空区间，可能跨越连续的排队轮次；它不能证明某个轮次仍然打开。对于需要在把输入作为 steering 加入当前提示词准入／轮次，还是提交为一个新的待准入提示词之间做选择的调用方，`acceptsNextStep` 才是更窄且准确的路由判断条件。活动的轮次接纳预留与完全停稳相关，但不会改变 `status`，也不会把之后的队列项变成 steering；它的唯一权限是将驱动器的下一次认领延迟到释放时。`AgentOptions` 可合并扩展：core 声明 `provider?`、`model?` 与 `maxTokens?`（在 `agent/request` 后，分发要求 provider 与 model 都存在）。提供 `maxTokens` 时，它必须是正安全整数，并限制每次对话模型请求的输出；省略时，系统会在写入请求 header 前填入确切模型的适配器默认值，否则提供方行为保持不变。Persona 归 `dsh-system-prompt` 所有：agent 作用域的 `deployment:persona` 可以遮蔽全局默认值。
|
||||
|
||||
cause 是由 TypeScript 强制约束的同进程输入。活跃的 `TurnCancellation` 持有者会把其判别字段复制到仅运行时的 `AbortSignal.reason`，并在发布 `turn/end` 前退役；冻结后的 `AbortSignal.reason` 仍可读取。只有 loop 会在结算时从自己机器私有的 signal 上读回 cause（`user`、`parent` 或仅用于生命周期的 `disposed`）——不存在公开的读取器，signal 也不授予协作监听器任何分类权限。持久 `turn/end` 保留粗粒度 `{ kind: 'aborted' }` 结果；若需记录请求 provenance，应使用单独的持久事件，而不是让终态结果承担额外含义。
|
||||
|
||||
|
||||
6
docs/core-data-structures/credentials.i18n.yaml
Normal file
6
docs/core-data-structures/credentials.i18n.yaml
Normal file
@@ -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 docs/core-data-structures/credentials.md
|
||||
credentials.md: 3f6fcd127d01e2c49e17c70c002bebe9f363e951
|
||||
credentials.zh.md: b5d2d9e164a85ce090790635c438b768cae4c9ca
|
||||
50
docs/core-data-structures/credentials.md
Normal file
50
docs/core-data-structures/credentials.md
Normal file
@@ -0,0 +1,50 @@
|
||||
# User Credentials
|
||||
|
||||
English | [中文](credentials.zh.md)
|
||||
|
||||
The credential seam of [dsh-credentials](../../packages/credentials/credentials) keeps secrets out of configuration: settings sections and `cordis.yml` entries carry *references* (environment-variable names), providers such as [dsh-credentials-local](../../packages/credentials/credentials-local) own the values, and consumers resolve a reference once per operation — the LLM adapters resolve once per model request, so a rotated credential reaches the very next request without any restart. One seam-wide rule binds every provider: an empty stored value is absent everywhere.
|
||||
|
||||
Source: [`packages/credentials/credentials/src/index.ts`](../../packages/credentials/credentials/src/index.ts)
|
||||
|
||||
## Identity
|
||||
|
||||
A reference names one credential as a POSIX-style environment-variable name. The brand keeps references from mixing with other cross-boundary strings; construction validates the shell-identifier shape.
|
||||
|
||||
```ts type-equiv
|
||||
/** Nominal reference to one credential: a POSIX-style environment-variable name. */
|
||||
type CredentialRef = Branded<'CredentialRef'>
|
||||
```
|
||||
|
||||
## Resolution
|
||||
|
||||
`resolve(ref)` returns the value with the provider-defined source layer that supplied it, or `undefined` while unconfigured. Consumers re-resolve at each operation and never cache across operations — that per-operation read is the hot-update mechanism.
|
||||
|
||||
```ts type-equiv
|
||||
/** One resolved credential value and the source layer that supplied it. */
|
||||
interface ResolvedCredential {
|
||||
/** The non-empty secret value. */
|
||||
value: string
|
||||
/** Provider-defined source layer id (the local provider uses `env` and `file`). */
|
||||
source: string
|
||||
}
|
||||
```
|
||||
|
||||
## Description
|
||||
|
||||
`describe(ref)` answers configuration surfaces without ever exposing a value: whether the reference resolves, from which layer, and whether `set` would currently succeed. The local provider reports a reference supplied by the live process environment as `writable: false` — a write would appear to succeed while resolution kept returning the shadowing value, so the seam rejects it and the UI can render the reference read-only up front.
|
||||
|
||||
```ts type-equiv
|
||||
/** Source and writability facts for one reference, safe for configuration UIs — never the value. */
|
||||
interface CredentialInfo {
|
||||
/** Whether {@link Credentials.resolve} would currently return a value. */
|
||||
configured: boolean
|
||||
/** Source layer currently supplying the value; absent while unconfigured. */
|
||||
source?: string
|
||||
/** Whether {@link Credentials.set} would currently succeed for this reference. */
|
||||
writable: boolean
|
||||
}
|
||||
```
|
||||
|
||||
## Change commits
|
||||
|
||||
`credentials/updated (ref)` fires after a committed change to a provider-managed source — a `set`, an `unset`, or an external edit observed in storage. Ambient process-environment changes are not observable and never emit. Consumers do not need the event (they re-resolve per operation); it exists for configuration surfaces refreshing a "configured" badge.
|
||||
50
docs/core-data-structures/credentials.zh.md
Normal file
50
docs/core-data-structures/credentials.zh.md
Normal file
@@ -0,0 +1,50 @@
|
||||
# 用户凭据
|
||||
|
||||
[English](credentials.md) | 中文
|
||||
|
||||
[dsh-credentials](../../packages/credentials/credentials) 的凭据 seam 把机密挡在配置之外：settings 分节与 `cordis.yml` 条目携带的是*引用*（环境变量名），值归 [dsh-credentials-local](../../packages/credentials/credentials-local) 这类 provider 所有，消费方每个操作解析一次引用——LLM 适配器每次模型请求解析一次，因此轮换后的凭据无需任何重启即可作用于紧随其后的下一次请求。一条 seam 级规则约束每个 provider：空的存储值在任何地方都视为不存在。
|
||||
|
||||
Source: [`packages/credentials/credentials/src/index.ts`](../../packages/credentials/credentials/src/index.ts)
|
||||
|
||||
## 标识
|
||||
|
||||
引用以 POSIX 风格环境变量名命名一条凭据。brand 使引用不与其他跨边界字符串混用；构造时校验 shell 标识符形态。
|
||||
|
||||
```ts type-equiv
|
||||
/** Nominal reference to one credential: a POSIX-style environment-variable name. */
|
||||
type CredentialRef = Branded<'CredentialRef'>
|
||||
```
|
||||
|
||||
## 解析
|
||||
|
||||
`resolve(ref)` 返回值，连同供出该值、由 provider 定义的来源层；未配置期间返回 `undefined`。消费方在每个操作中重新解析，绝不跨操作缓存——这次按操作进行的读取正是热更新机制。
|
||||
|
||||
```ts type-equiv
|
||||
/** One resolved credential value and the source layer that supplied it. */
|
||||
interface ResolvedCredential {
|
||||
/** The non-empty secret value. */
|
||||
value: string
|
||||
/** Provider-defined source layer id (the local provider uses `env` and `file`). */
|
||||
source: string
|
||||
}
|
||||
```
|
||||
|
||||
## 描述
|
||||
|
||||
`describe(ref)` 在绝不暴露值的前提下回应配置界面：引用当前是否可解析、来自哪一层、`set` 当前能否成功。本地 provider 把由活跃进程环境供值的引用报告为 `writable: false`——那样的写入会表面成功而解析持续返回遮蔽值，因此 seam 直接拒绝，界面也得以提前把该引用渲染为只读。
|
||||
|
||||
```ts type-equiv
|
||||
/** Source and writability facts for one reference, safe for configuration UIs — never the value. */
|
||||
interface CredentialInfo {
|
||||
/** Whether {@link Credentials.resolve} would currently return a value. */
|
||||
configured: boolean
|
||||
/** Source layer currently supplying the value; absent while unconfigured. */
|
||||
source?: string
|
||||
/** Whether {@link Credentials.set} would currently succeed for this reference. */
|
||||
writable: boolean
|
||||
}
|
||||
```
|
||||
|
||||
## 变更提交
|
||||
|
||||
`credentials/updated (ref)` 在 provider 管理的来源发生已提交变更后触发——`set`、`unset` 或在存储中观察到的外部编辑。进程环境自身的变化不可观测，永不发出事件。消费方不需要该事件（它们按操作重新解析）；它服务于配置界面刷新「已配置」徽标。
|
||||
@@ -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/llm-streaming.md
|
||||
llm-streaming.md: 6811611768a0ec577360a8ff82792899cf3b8fec
|
||||
llm-streaming.zh.md: 35374af6a20086f15384840689dba5aa24351750
|
||||
llm-streaming.md: 28f775f81049d3aa0198e75fbb6c4544302e772d
|
||||
llm-streaming.zh.md: 76282018f0cfa119199e221985bd09eaac69c839
|
||||
|
||||
@@ -162,13 +162,17 @@ declare class BlockAssembler {
|
||||
|
||||
## The seam
|
||||
|
||||
`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerRetryPolicy()` is captured per route with normal defaults, while `providerInfo()` and asynchronous `listModels()` feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. One asynchronous `resolveModel()` query returns exact model identity plus optional correctness-sensitive context capacity and ordered model-owned reasoning ids with an optional deployment default; absent fields mean unavailable metadata or capability, not invalid catalog membership. The resolver receives optional cancellation and must settle promptly after abort. `LlmService.resolveModelInfo()` validates and detaches the aggregate. The service validates and materializes reasoning through `resolveCallConfig()` at the final adapter boundary, so direct calls cannot bypass unsupported-effort rejection; direct dispatch captures one registration before awaiting that resolution. The agent loop instead uses `prepareCall()` to keep the same registration across model resolution, durable header logging, and dispatch. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm).
|
||||
`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerRetryPolicy()` is captured per route with normal defaults, while `providerInfo()` and asynchronous `listModels()` feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. One asynchronous `resolveModel()` query returns exact model identity plus optional correctness-sensitive context capacity, an adapter-configured `defaultMaxTokens`, and ordered model-owned reasoning ids with an optional deployment default; absent fields mean unavailable metadata or provider-owned behavior, not invalid catalog membership. The resolver receives optional cancellation and must settle promptly after abort. `LlmService.resolveModelInfo()` validates and detaches the aggregate. At the final adapter boundary, `resolveCallConfig()` materializes the output default only when `maxTokens` is absent and validates and materializes reasoning, so direct calls cannot bypass either configured behavior; direct dispatch captures one registration before awaiting that resolution. The agent loop instead uses `prepareCall()` to keep the same registration across model resolution, durable header logging, and dispatch, retain detached context metadata from that exact lookup, and report which config fields the adapter defaulted. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. AgentLoop observes a request attempt once the outer waterfall returns a stream handle; that limited boundary does not prove a lazy terminal adapter was constructed or began provider I/O. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm).
|
||||
|
||||
```ts type-equiv
|
||||
/** One model call whose config and adapter registration were resolved together. */
|
||||
interface PreparedLlmCall {
|
||||
/** Detached, deep-frozen config with any adapter-owned default materialized. */
|
||||
readonly config: LlmCallConfig
|
||||
/** Detached context metadata resolved with the registration-bound call. */
|
||||
readonly context?: LlmModelContext
|
||||
/** Config fields materialized by the captured adapter rather than proposed by the caller. */
|
||||
readonly adapterDefaults: LlmCallConfigAdapterDefaults
|
||||
/**
|
||||
* Dispatch this call once through the registration captured during
|
||||
* preparation. The request's call-config fields must match {@link config};
|
||||
@@ -215,7 +219,7 @@ declare abstract class LlmAdapter {
|
||||
* @param model - exact model id passed to {@link GenerateOptions.model}.
|
||||
* @param _signal - cancellation for this exact-model lookup; asynchronous
|
||||
* implementations must settle promptly after it aborts.
|
||||
* @returns provider/model identity plus any context and reasoning metadata.
|
||||
* @returns provider/model identity plus any context, call-default, and reasoning metadata.
|
||||
*/
|
||||
resolveModel(
|
||||
provider: string,
|
||||
|
||||
@@ -162,13 +162,17 @@ declare class BlockAssembler {
|
||||
|
||||
## seam
|
||||
|
||||
`LlmAdapter` 是提供方 seam：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerRetryPolicy()` 会按路由捕获并填入 normal 默认值，`providerInfo()` 与异步 `listModels()` 方法则为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单次异步 `resolveModel()` 查询返回确切模型身份，以及可选的对正确性敏感的上下文容量、由模型持有的有序推理强度 ID 和部署默认值；字段缺失表示元数据或能力不可用，而不表示目录成员关系无效。解析器会接收可选的取消信号，并且必须在信号中止后迅速完成结算。`LlmService.resolveModelInfo()` 会校验聚合结果并返回分离值。服务通过最终适配器边界的 `resolveCallConfig()` 校验推理强度并填入默认值，因此直接调用也无法绕过对不支持推理强度的拒绝；直接分派会在等待解析前捕获一项适配器注册。agent loop 则使用 `prepareCall()`，使模型解析、请求头持久记录和分派全程使用同一项注册。适配器查找发生在 `llm/stream` waterfall（瀑布式事件）的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface（`ctx.llm.stream()`）与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。
|
||||
`LlmAdapter` 是提供方 seam：创建子类、实现 `stream()`，再用 `ctx.llm.registerAdapter(providers, adapter)` 注册一个适配器实例。`GenerateOptions.provider` 选择已注册适配器；`GenerateOptions.model` 会传给该适配器，无需在生命周期启动时注册。重复提供方路由会原子失败。可选的 `providerRetryPolicy()` 会按路由捕获并填入 normal 默认值，`providerInfo()` 与异步 `listModels()` 方法则为 `LlmService.listProviders()` / `listModels()` 提供分离的 selector 元数据。该目录仅供参考，不是请求白名单：适配器仍是权威，并可接受未列出的模型 id。单次异步 `resolveModel()` 查询返回确切模型身份，以及可选的对正确性敏感的上下文容量、适配器配置的 `defaultMaxTokens`、由模型持有的有序推理强度 ID 和部署默认值；字段缺失表示元数据不可用或保留提供方持有的行为，而不表示目录成员关系无效。解析器会接收可选的取消信号，并且必须在信号中止后迅速完成结算。`LlmService.resolveModelInfo()` 会校验聚合结果并返回分离值。在最终适配器边界，`resolveCallConfig()` 仅在 `maxTokens` 缺失时填入输出默认值，并校验和填入推理强度，因此直接调用也无法绕过任何一项已配置行为；直接分派会在等待解析前捕获一项适配器注册。agent loop 则使用 `prepareCall()`，使模型解析、请求头持久记录和分派全程使用同一项注册，保留来自同一次查询的分离上下文元数据，并报告适配器填入的配置字段。适配器查找发生在 `llm/stream` waterfall（瀑布式事件）的终端 continuation，因此 listener 可以在查找前短路调用，或路由一个可变的一次性请求。AgentLoop 在外层 waterfall 返回流句柄时观察到一次请求尝试；这个有限边界不能证明惰性终端适配器已构造完成或开始提供方 I/O。`block-start` / `block-end` 的 `index` 关联与 assembler 共同意味着适配器只需 emit 格式正确的分片——块重组不是每个适配器各自的问题。消费方 surface（`ctx.llm.stream()`）与 `llm/stream` waterfall 见 [architecture.md § 内容块与流式传输](../architecture.md#content-blocks-and-streaming-dsh-llm)。
|
||||
|
||||
```ts type-equiv
|
||||
/** One model call whose config and adapter registration were resolved together. */
|
||||
interface PreparedLlmCall {
|
||||
/** Detached, deep-frozen config with any adapter-owned default materialized. */
|
||||
readonly config: LlmCallConfig
|
||||
/** Detached context metadata resolved with the registration-bound call. */
|
||||
readonly context?: LlmModelContext
|
||||
/** Config fields materialized by the captured adapter rather than proposed by the caller. */
|
||||
readonly adapterDefaults: LlmCallConfigAdapterDefaults
|
||||
/**
|
||||
* Dispatch this call once through the registration captured during
|
||||
* preparation. The request's call-config fields must match {@link config};
|
||||
@@ -215,7 +219,7 @@ declare abstract class LlmAdapter {
|
||||
* @param model - exact model id passed to {@link GenerateOptions.model}.
|
||||
* @param _signal - cancellation for this exact-model lookup; asynchronous
|
||||
* implementations must settle promptly after it aborts.
|
||||
* @returns provider/model identity plus any context and reasoning metadata.
|
||||
* @returns provider/model identity plus any context, call-default, and reasoning metadata.
|
||||
*/
|
||||
resolveModel(
|
||||
provider: string,
|
||||
|
||||
@@ -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/persistence.md
|
||||
persistence.md: 0280093883b9fbd4c4bbc788bce7193d59bb7182
|
||||
persistence.zh.md: d32274bbc2e96e3754a8061ba37427e34b6205f6
|
||||
persistence.md: 237ce268691fa6f4b0546c6c1c14c21eaa462612
|
||||
persistence.zh.md: 9cb555f2e157844704896d9b04feb822428540e5
|
||||
|
||||
@@ -66,6 +66,11 @@ interface SessionHeader {
|
||||
* boundary lets resume and replay distinguish parent history from child work.
|
||||
*/
|
||||
readonly seedLength?: number
|
||||
/**
|
||||
* Coarse product classification for a session created as a subagent child.
|
||||
* This is presentation metadata, not proof that the child is continuable.
|
||||
*/
|
||||
readonly origin?: 'subagent'
|
||||
/**
|
||||
* Delegation depth: absent (zero) for a top-level session, parent depth + 1
|
||||
* for a subagent child. Persisted so a recursion budget survives restart and
|
||||
@@ -77,7 +82,7 @@ interface SessionHeader {
|
||||
|
||||
## `CreateSessionOptions` — seeding and metadata
|
||||
|
||||
Creating a `Session` through the store takes a `seed` (initial replay or fork history) and `meta` (the storage-level fields the store folds into a `SessionHeader`). The store fills in `version`/`id` and defaults `createdAt`; the caller supplies the validated absolute `cwd`, the `parentSession` lineage, the `seedLength` seed boundary, the `delegationDepth`, and — only when reconstructing a persisted session — the original `createdAt` to preserve it.
|
||||
Creating a `Session` through the store takes a `seed` (initial replay or fork history) and `meta` (the storage-level fields the store folds into a `SessionHeader`). The store fills in `version`/`id` and defaults `createdAt`; the caller supplies the validated absolute `cwd`, the `parentSession` lineage, the `seedLength` seed boundary, the optional coarse `origin`, the `delegationDepth`, and — only when reconstructing a persisted session — the original `createdAt` to preserve it. `origin: 'subagent'` lets product navigation hide duplicate child rows; it does not prove that a descriptor is valid or that the child can resume.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -97,6 +102,7 @@ interface CreateSessionOptions {
|
||||
readonly parentSession?: SessionId
|
||||
readonly createdAt?: number
|
||||
readonly seedLength?: number
|
||||
readonly origin?: 'subagent'
|
||||
readonly delegationDepth?: number
|
||||
}
|
||||
}
|
||||
|
||||
@@ -66,6 +66,11 @@ interface SessionHeader {
|
||||
* boundary lets resume and replay distinguish parent history from child work.
|
||||
*/
|
||||
readonly seedLength?: number
|
||||
/**
|
||||
* Coarse product classification for a session created as a subagent child.
|
||||
* This is presentation metadata, not proof that the child is continuable.
|
||||
*/
|
||||
readonly origin?: 'subagent'
|
||||
/**
|
||||
* Delegation depth: absent (zero) for a top-level session, parent depth + 1
|
||||
* for a subagent child. Persisted so a recursion budget survives restart and
|
||||
@@ -77,7 +82,7 @@ interface SessionHeader {
|
||||
|
||||
## `CreateSessionOptions`：seed 与元数据
|
||||
|
||||
通过 store 创建 `Session` 时会接收 `seed`（初始回放或 fork 历史）与 `meta`（store 折叠进 `SessionHeader` 的存储层字段）。store 填充 `version`/`id` 并为 `createdAt` 提供默认值；调用方提供已校验的绝对 `cwd`、`parentSession` 谱系、`seedLength` 种子边界、`delegationDepth`，以及——仅在重建已持久化会话时——需要保留的原始 `createdAt`。
|
||||
通过 store 创建 `Session` 时会接收 `seed`（初始回放或 fork 历史）与 `meta`（store 折叠进 `SessionHeader` 的存储层字段）。store 填充 `version`/`id` 并为 `createdAt` 提供默认值；调用方提供已校验的绝对 `cwd`、`parentSession` 谱系、`seedLength` 种子边界、可选的粗粒度 `origin`、`delegationDepth`，以及——仅在重建已持久化会话时——需要保留的原始 `createdAt`。`origin: 'subagent'` 让产品导航能够隐藏重复的 child 行；它不证明描述符有效，也不证明 child 可以恢复。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -97,6 +102,7 @@ interface CreateSessionOptions {
|
||||
readonly parentSession?: SessionId
|
||||
readonly createdAt?: number
|
||||
readonly seedLength?: number
|
||||
readonly origin?: 'subagent'
|
||||
readonly delegationDepth?: number
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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/session.md
|
||||
session.md: 769d5db301e3e81664c732ab1685c859a00cceb2
|
||||
session.zh.md: 7af459949eda1b939596c20adf1c9e55f6d2b2b4
|
||||
session.md: 6369c956df03c0d786db696c208b000300d5bfbc
|
||||
session.zh.md: c39382b7e6c9b14f91c311cc80526a6fd8898e4c
|
||||
|
||||
@@ -91,10 +91,22 @@ interface SessionEventMap {
|
||||
* It is log-only; the latest snapshot reconstructs the request header.
|
||||
*/
|
||||
'request/header': { header: EpochHeader; reason: RequestHeaderReason }
|
||||
/**
|
||||
* Registration-bound context metadata for the route a request resolved to,
|
||||
* appended inside its step beside `request/header` and only when the route
|
||||
* or capacity differs from the last record. It is log-only and deliberately
|
||||
* NOT part of {@link EpochHeader}: capacity is adapter metadata about a
|
||||
* route, not an input the request was built from, so it must not participate
|
||||
* in request reconstruction or header equality. `contextWindow` is absent
|
||||
* when the route's adapter advertises no capacity.
|
||||
*/
|
||||
'request/context': RequestContext
|
||||
/**
|
||||
* Marks the end of a constructor seed. Events before it have smaller seq
|
||||
* values and came from the seed (resume, fork, or replay); this lifecycle
|
||||
* produced none of them. This log-only event is the durable projection of
|
||||
* produced none of them. An explicitly supplied empty seed puts the marker
|
||||
* at seq 0, distinguishing an empty resumed session from a fresh session.
|
||||
* This log-only event is the durable projection of
|
||||
* {@link Session.firstLiveSeq}. Its payload is empty — position and `time`
|
||||
* carry the meaning.
|
||||
*
|
||||
@@ -144,7 +156,7 @@ interface TodoItem {
|
||||
|
||||
### The request header event: `request/header`
|
||||
|
||||
The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas) — is logged session state, so every conversation request is a pure function of the log (the reconstructability Agent Note). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message.
|
||||
The request envelope — the `EpochHeader` (call config + adapter-default provenance + rendered system prompt + assembled tool schemas) — is logged session state, so every conversation request is a pure function of the log (the reconstructability Agent Note). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -155,6 +167,8 @@ The request envelope — the `EpochHeader` (call config + rendered system prompt
|
||||
interface EpochHeader {
|
||||
/** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */
|
||||
config: LlmCallConfig
|
||||
/** Effective config fields materialized from the exact adapter rather than proposed by a caller. */
|
||||
adapterDefaults?: LlmCallConfigAdapterDefaults
|
||||
/** Rendered system prompt text; absent for a system-less request. */
|
||||
system?: string
|
||||
/** Assembled tool schemas; absent for a tool-less request. */
|
||||
@@ -164,6 +178,26 @@ interface EpochHeader {
|
||||
|
||||
Canonical form represents an empty system prompt or tool list as an absent field, matching how requests are built. Legacy v0 logs containing the removed `request/header-delta` event or its full-snapshot `fallback` reason are rejected at seed, append, and persistence-load boundaries rather than replayed incompletely.
|
||||
|
||||
### The route capacity event: `request/context`
|
||||
|
||||
The context metadata of the route a request resolved to is separate logged state, appended beside `request/header` inside the same step and only when the provider, model, or capacity differs from the previous record. It stays outside `EpochHeader` because that type is the reconstruction contract compared field-wise by `headerEquals`: capacity describes a route, not a request input, so folding it in would let a capacity change register as a request-envelope `change` and would pull adapter metadata into the loop's reconstruction invariant. Like `request/header`, it is not a `SurfaceEventType` and produces no LLM message. `session.requestContext()` folds the latest record incrementally. A route whose adapter advertises no capacity is recorded with `contextWindow` absent, so the new record clears an older route's capacity.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Registration-bound context metadata of one resolved model route. Adapter
|
||||
* metadata about a route rather than a request input, which is why it lives
|
||||
* outside {@link EpochHeader}.
|
||||
*/
|
||||
interface RequestContext {
|
||||
/** Registered provider route the metadata was resolved through. */
|
||||
provider: string
|
||||
/** Provider-owned model id the metadata belongs to. */
|
||||
model: string
|
||||
/** Maximum combined request and response context in tokens; absent when the adapter advertises none. */
|
||||
contextWindow?: number
|
||||
}
|
||||
```
|
||||
|
||||
## `SessionEvent<T>` — one log entry
|
||||
|
||||
A proper discriminated union over `type` (not independent `type`/`data` unions), so `switch (event.type)` narrows `event.data` without casts. `seq` is the monotonic position in the log (`seq = log.length`); `time` is epoch ms.
|
||||
@@ -269,7 +303,7 @@ interface SurfaceIntent {
|
||||
}
|
||||
```
|
||||
|
||||
Required for `SurfaceEventType` events — every message-producing event must declare how it joins the surface, the sole source of derived history. Non-surface types reject it at compile time.
|
||||
Required for `SurfaceEventType` events — every message-producing event must declare how it joins the surface, the sole source of derived model history. A human-facing transcript is the other projection and reads the log's append-origin events instead, because the surface deliberately shadows the ranges a replacement summarizes (`isAppendSurfaceEvent` in [dsh-session](../../packages/core/session/README.md)). Non-surface types reject it at compile time.
|
||||
|
||||
The same provenance distinction applies here: only `assistant/message` may carry a present empty `sourceEventSeqs`; omission does not assert that its source stream was empty.
|
||||
|
||||
@@ -350,7 +384,9 @@ declare class Session {
|
||||
* start here. Distinct from `header.seedLength`, the DURABLE fork-lineage
|
||||
* boundary: a resumed session's constructor seed is its full stored log,
|
||||
* while its header keeps the original fork value — this field is the
|
||||
* in-process construction fact.
|
||||
* in-process construction fact. An explicitly supplied empty seed has the
|
||||
* same value as no seed (0); its `session/end-seed` event preserves the
|
||||
* lifecycle distinction.
|
||||
*
|
||||
* Not persisted itself: a seeded session projects it into the log as the
|
||||
* `session/end-seed` event, which is what a consumer reading STORED history
|
||||
@@ -388,7 +424,8 @@ declare class Session {
|
||||
* the ordered surface; `sourceEventSeqs` records provenance (the seq
|
||||
* numbers of events this one derives from). REQUIRED for
|
||||
* {@link SurfaceEventType} events (every message-producing event must
|
||||
* declare how it joins the surface, the sole source of derived history) and
|
||||
* declare how it joins the surface, the sole source of derived model
|
||||
* history) and
|
||||
* rejected by the compiler for non-surface types like `turn/start` or
|
||||
* `assistant/chunk`.
|
||||
* @returns the logged event — its assigned `seq`/`time` plus the SNAPSHOT of
|
||||
@@ -422,6 +459,14 @@ declare class Session {
|
||||
* @returns the folded header, or undefined when no header event exists yet.
|
||||
*/
|
||||
requestHeader(): EpochHeader | undefined;
|
||||
/**
|
||||
* The route metadata in force after the log's last `request/context` event —
|
||||
* what the NEXT request deduplicates against — or undefined before any such
|
||||
* record. Maintained incrementally like {@link requestHeader}, so a per-step
|
||||
* read costs O(new events).
|
||||
* @returns the folded context record, or undefined when none exists yet.
|
||||
*/
|
||||
requestContext(): RequestContext | undefined;
|
||||
/**
|
||||
* Derive the LLM message history by walking the ordered sequences of
|
||||
* message-producing events maintained by `surfaceOp` markers. The
|
||||
@@ -545,7 +590,7 @@ The optional `dsh-session/invariant` companion enforces the relations owned by c
|
||||
|
||||
A seeded session — resume, fork, or replay — appends this log-only event immediately after its constructor seed, as its first live write. Events before it have smaller seq values and came from the seed. It is the durable projection of `firstLiveSeq`: that field answers where this lifecycle's writes start for a consumer holding the object, while the event answers the same question for one holding only stored bytes. The payload is empty, so position and `time` carry the whole meaning, and it produces no message. `Session`'s constructor is the only legitimate writer.
|
||||
|
||||
An empty seed writes nothing, and a seed already ending in `session/end-seed` is not re-marked, so reopening an untouched session does not grow its log per pickup. Locate the LAST `session/end-seed` in stored history rather than assuming one exists at `firstLiveSeq`: after a pickup with no work, the event has a smaller seq than the next lifecycle's `firstLiveSeq`.
|
||||
An explicitly supplied empty seed writes `session/end-seed` at seq 0, which distinguishes an empty resumed session from a fresh one. A seed already ending in `session/end-seed` is not re-marked, so reopening an untouched session does not grow its log per pickup. Locate the LAST `session/end-seed` in stored history rather than assuming one exists at `firstLiveSeq`: after a pickup with no work, the event has a smaller seq than the next lifecycle's `firstLiveSeq`.
|
||||
|
||||
It exists because seed history and live work are otherwise byte-identical, which defeats any plugin owning a standalone open/close bracket: an unmatched `compact/start` reads the same whether the writer crashed mid-compaction or is compacting right now. An opening marker before `session/end-seed` came from the constructor seed and belongs to an ended lifecycle, whatever ended it (a crash, a succeeding process, or a fork out of a still-running parent), so its owner may treat it as dead. That covers only brackets *this* session inherited: a concurrently live session holding an open bracket over the same history has its own boundary elsewhere, so tolerating concurrent writers needs a liveness signal beyond the log. Core writes the boundary and reads nothing from it — a bracket's vocabulary stays with its owning plugin, which is why crash repair closes turn/step/tool boundaries and never `compact/*`.
|
||||
|
||||
|
||||
@@ -91,10 +91,22 @@ interface SessionEventMap {
|
||||
* It is log-only; the latest snapshot reconstructs the request header.
|
||||
*/
|
||||
'request/header': { header: EpochHeader; reason: RequestHeaderReason }
|
||||
/**
|
||||
* Registration-bound context metadata for the route a request resolved to,
|
||||
* appended inside its step beside `request/header` and only when the route
|
||||
* or capacity differs from the last record. It is log-only and deliberately
|
||||
* NOT part of {@link EpochHeader}: capacity is adapter metadata about a
|
||||
* route, not an input the request was built from, so it must not participate
|
||||
* in request reconstruction or header equality. `contextWindow` is absent
|
||||
* when the route's adapter advertises no capacity.
|
||||
*/
|
||||
'request/context': RequestContext
|
||||
/**
|
||||
* Marks the end of a constructor seed. Events before it have smaller seq
|
||||
* values and came from the seed (resume, fork, or replay); this lifecycle
|
||||
* produced none of them. This log-only event is the durable projection of
|
||||
* produced none of them. An explicitly supplied empty seed puts the marker
|
||||
* at seq 0, distinguishing an empty resumed session from a fresh session.
|
||||
* This log-only event is the durable projection of
|
||||
* {@link Session.firstLiveSeq}. Its payload is empty — position and `time`
|
||||
* carry the meaning.
|
||||
*
|
||||
@@ -146,7 +158,7 @@ interface TodoItem {
|
||||
|
||||
### 请求头事件：`request/header`
|
||||
|
||||
请求信封（即 `EpochHeader`：调用配置 + 渲染后的系统提示词 + 已组装的工具 schema）会作为会话状态写入日志，因此每个对话请求都是日志的纯函数（见可重建性 Agent Note）。带有 reason `'initial'` 或 `'resume'` 的完整 `request/header` 快照记录每个 agent loop 实例的边界；之后请求发生变化时，系统会以 reason `'change'` 记录另一份完整快照。`foldRequestHeader(events)` 通过选择最新快照重建请求头。该事件不是 `SurfaceEventType`，不产生 LLM 消息。
|
||||
请求信封（即 `EpochHeader`：调用配置 + 适配器默认值来源 + 渲染后的系统提示词 + 已组装的工具 schema）会作为会话状态写入日志，因此每个对话请求都是日志的纯函数（见可重建性 Agent Note）。带有 reason `'initial'` 或 `'resume'` 的完整 `request/header` 快照记录每个 agent loop 实例的边界；之后请求发生变化时，系统会以 reason `'change'` 记录另一份完整快照。`foldRequestHeader(events)` 通过选择最新快照重建请求头。该事件不是 `SurfaceEventType`，不产生 LLM 消息。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -157,6 +169,8 @@ interface TodoItem {
|
||||
interface EpochHeader {
|
||||
/** The conversation's call configuration (provider, model, reasoning effort, and sampling scalars). */
|
||||
config: LlmCallConfig
|
||||
/** Effective config fields materialized from the exact adapter rather than proposed by a caller. */
|
||||
adapterDefaults?: LlmCallConfigAdapterDefaults
|
||||
/** Rendered system prompt text; absent for a system-less request. */
|
||||
system?: string
|
||||
/** Assembled tool schemas; absent for a tool-less request. */
|
||||
@@ -166,6 +180,26 @@ interface EpochHeader {
|
||||
|
||||
规范形式：空系统提示词和空工具列表都表示为字段缺失，与请求构建方式一致。包含已移除的 `request/header-delta` 事件或完整快照原因为 `fallback` 的旧版 v0 日志，会在 seed、append 和持久化加载边界被拒绝，而不会以不完整方式回放。
|
||||
|
||||
### 路由容量事件：`request/context`
|
||||
|
||||
请求所解析到的路由的上下文元数据是独立的已记录状态，在同一步骤内紧随 `request/header` 追加，且仅在提供方、模型或容量与上一条记录不同时追加。它保持在 `EpochHeader` 之外，因为该类型是由 `headerEquals` 逐字段比较的重建契约：容量描述的是路由，不是请求输入，把它折叠进去会让一次容量变化被登记为请求信封的 `change`，也会把适配器元数据拉进 loop 的重建不变式。与 `request/header` 一样，它不是 `SurfaceEventType`，也不产生 LLM 消息。`session.requestContext()` 以增量方式归并最新一条记录。适配器不公布容量的路由会以缺失 `contextWindow` 的形式记录，因此新记录可以清除较早路由的容量。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Registration-bound context metadata of one resolved model route. Adapter
|
||||
* metadata about a route rather than a request input, which is why it lives
|
||||
* outside {@link EpochHeader}.
|
||||
*/
|
||||
interface RequestContext {
|
||||
/** Registered provider route the metadata was resolved through. */
|
||||
provider: string
|
||||
/** Provider-owned model id the metadata belongs to. */
|
||||
model: string
|
||||
/** Maximum combined request and response context in tokens; absent when the adapter advertises none. */
|
||||
contextWindow?: number
|
||||
}
|
||||
```
|
||||
|
||||
## `SessionEvent<T>`：一条日志条目
|
||||
|
||||
基于 `type` 的真正可辨识联合（而非独立的 `type`/`data` 联合），因此 `switch (event.type)` 能直接收窄 `event.data`，无需类型断言。`seq` 是日志中的单调递增位置（`seq = log.length`）；`time` 为 epoch 毫秒。
|
||||
@@ -271,7 +305,7 @@ interface SurfaceIntent {
|
||||
}
|
||||
```
|
||||
|
||||
对 `SurfaceEventType` 事件必填：每个产生消息的事件都必须声明它如何加入 surface（派生历史的唯一来源）。非 surface 类型在编译期拒绝此参数。
|
||||
对 `SurfaceEventType` 事件必填：每个产生消息的事件都必须声明它如何加入 surface（派生模型历史的唯一来源）。面向人类的记录（transcript）是另一个投影，读取的是日志中追加来源的事件，因为 surface 会有意遮蔽替换所概括的范围（见 [dsh-session](../../packages/core/session/README.md) 的 `isAppendSurfaceEvent`）。非 surface 类型在编译期拒绝此参数。
|
||||
|
||||
此处适用相同的溯源区分：只有 `assistant/message` 可以携带存在但为空的 `sourceEventSeqs`；省略该字段并不表示其源流为空。
|
||||
|
||||
@@ -352,7 +386,9 @@ declare class Session {
|
||||
* start here. Distinct from `header.seedLength`, the DURABLE fork-lineage
|
||||
* boundary: a resumed session's constructor seed is its full stored log,
|
||||
* while its header keeps the original fork value — this field is the
|
||||
* in-process construction fact.
|
||||
* in-process construction fact. An explicitly supplied empty seed has the
|
||||
* same value as no seed (0); its `session/end-seed` event preserves the
|
||||
* lifecycle distinction.
|
||||
*
|
||||
* Not persisted itself: a seeded session projects it into the log as the
|
||||
* `session/end-seed` event, which is what a consumer reading STORED history
|
||||
@@ -390,7 +426,8 @@ declare class Session {
|
||||
* the ordered surface; `sourceEventSeqs` records provenance (the seq
|
||||
* numbers of events this one derives from). REQUIRED for
|
||||
* {@link SurfaceEventType} events (every message-producing event must
|
||||
* declare how it joins the surface, the sole source of derived history) and
|
||||
* declare how it joins the surface, the sole source of derived model
|
||||
* history) and
|
||||
* rejected by the compiler for non-surface types like `turn/start` or
|
||||
* `assistant/chunk`.
|
||||
* @returns the logged event — its assigned `seq`/`time` plus the SNAPSHOT of
|
||||
@@ -424,6 +461,14 @@ declare class Session {
|
||||
* @returns the folded header, or undefined when no header event exists yet.
|
||||
*/
|
||||
requestHeader(): EpochHeader | undefined;
|
||||
/**
|
||||
* The route metadata in force after the log's last `request/context` event —
|
||||
* what the NEXT request deduplicates against — or undefined before any such
|
||||
* record. Maintained incrementally like {@link requestHeader}, so a per-step
|
||||
* read costs O(new events).
|
||||
* @returns the folded context record, or undefined when none exists yet.
|
||||
*/
|
||||
requestContext(): RequestContext | undefined;
|
||||
/**
|
||||
* Derive the LLM message history by walking the ordered sequences of
|
||||
* message-producing events maintained by `surfaceOp` markers. The
|
||||
@@ -549,7 +594,7 @@ interface TurnEndReasonMap {
|
||||
|
||||
带种子的会话（恢复、fork 或回放）紧接构造种子之后追加这个仅日志事件，作为自己的第一次实时写入。在它之前的事件具有更小的 seq，且来自种子。它是 `firstLiveSeq` 的持久投影：该字段为持有对象的消费方回答本生命周期的写入从哪里开始，该事件则为只持有存储字节的消费方回答同一问题。payload 为空，因此位置与 `time` 承载全部含义，且不产生任何消息。`Session` 的构造函数是唯一合法的写入方。
|
||||
|
||||
空种子不写入任何内容；种子本身已以 `session/end-seed` 结尾时不会重复标记，因此重新打开一个未被改动的会话不会每次拾起都增长日志。应定位存储历史中的最后一条 `session/end-seed`，而不是假定 `firstLiveSeq` 处一定有一条：在一次没有产生工作的拾起之后，该事件的 seq 会小于下一个生命周期的 `firstLiveSeq`。
|
||||
显式传入的空种子会在 seq 0 写入 `session/end-seed`，从而把从空日志恢复的会话与全新会话区分开来。种子本身已以 `session/end-seed` 结尾时不会重复标记，因此重新打开一个未被改动的会话不会每次拾起都增长日志。应定位存储历史中的最后一条 `session/end-seed`，而不是假定 `firstLiveSeq` 处一定有一条：在一次没有产生工作的拾起之后，该事件的 seq 会小于下一个生命周期的 `firstLiveSeq`。
|
||||
|
||||
它之所以必要，是因为种子历史与实时工作在字节层面完全相同，这会让任何拥有独立开／闭括号的插件失效：一个未配对的 `compact/start`，无论写入方是在压缩中途崩溃、还是此刻正在压缩，读起来都一样。在 `session/end-seed` 之前的开启标记来自构造种子，并且属于一个已结束的生命周期，无论结束原因为何（崩溃、进程接替，或从仍在运行的父会话 fork 出来），因此其所有方可以视之为已死。这只覆盖*本*会话继承的括号：另一个并发存活的会话可能在同一段历史上持有开放括号，而它自己的边界在别处，因此容忍并发写入方还需要日志之外的存活信号。核心写入该边界但不从中读取任何内容——括号的词汇表仍归其所属插件，这也正是崩溃修复只关闭轮次／步骤／工具边界而从不处理 `compact/*` 的原因。
|
||||
|
||||
|
||||
6
docs/core-data-structures/settings.i18n.yaml
Normal file
6
docs/core-data-structures/settings.i18n.yaml
Normal file
@@ -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 docs/core-data-structures/settings.md
|
||||
settings.md: 1cabfae5d8dc72a9cd79341d250ee79820693872
|
||||
settings.zh.md: d63a1384646fa38199e7d65e9f0504f0440597be
|
||||
140
docs/core-data-structures/settings.md
Normal file
140
docs/core-data-structures/settings.md
Normal file
@@ -0,0 +1,140 @@
|
||||
# User Settings
|
||||
|
||||
English | [中文](settings.zh.md)
|
||||
|
||||
The user-settings seam of [dsh-settings](../../packages/settings/settings) holds one user-owned document of per-namespace sections and resolves each registered namespace as schema defaults, then the registrant's composition `base`, then the user section. Providers such as [dsh-settings-local](../../packages/settings/settings-local) store the raw document and push external edits; consumer plugins register a schema and read or observe the resolved value. Composition config stays in `cordis.yml` — a namespace carries only the user-editable subset.
|
||||
|
||||
Source: [`packages/settings/settings/src/index.ts`](../../packages/settings/settings/src/index.ts)
|
||||
|
||||
## Identity
|
||||
|
||||
A namespace names one plugin-owned section of the user document. The brand keeps namespaces from mixing with other cross-boundary ids; construction validates the lowercase kebab-case shape.
|
||||
|
||||
```ts type-equiv
|
||||
/** Nominal id of one registered settings namespace. */
|
||||
type SettingsNamespace = Branded<'SettingsNamespace'>
|
||||
```
|
||||
|
||||
## Registration
|
||||
|
||||
Registration binds a schemastery schema to a namespace on the calling plugin's fiber — disposing that fiber removes the namespace and its observers. The options carry the composition layer and the owner's effect timing.
|
||||
|
||||
```ts type-equiv
|
||||
/** Registration options beyond the namespace schema. */
|
||||
interface SettingsRegisterOptions<T> {
|
||||
/** Composition-layer values resolved below the user layer (entry-config subset). */
|
||||
base?: Partial<T>
|
||||
/** Owner's effect timing, surfaced to configuration UIs; defaults to `live`. */
|
||||
applies?: SettingsApplies
|
||||
}
|
||||
```
|
||||
|
||||
`applies` is a UI hint, not a mechanism: a `restart` owner simply never watches, so its value is read once at construction and configuration surfaces can badge the pending change.
|
||||
|
||||
```ts type-equiv
|
||||
/** When a namespace's changes take effect for its owner. */
|
||||
type SettingsApplies = 'live' | 'restart'
|
||||
```
|
||||
|
||||
## Owner scope
|
||||
|
||||
The scope is the owner-facing handle. `update` merges a sparse patch over the user section only (never into `base`); `replace` sets the section wholesale, which is the removal/reset path — keys absent from the replacement re-inherit `base` and schema defaults. Writes to one namespace are serialized in call order, and resolved values are deep-frozen snapshots.
|
||||
|
||||
```ts type-equiv
|
||||
/** Owner-facing handle for one registered namespace. */
|
||||
interface SettingsScope<T> {
|
||||
/** Current resolved value: schema defaults, then `base`, then the user layer. */
|
||||
get(): T
|
||||
/**
|
||||
* Observe committed changes to this namespace's resolved value. Invocations
|
||||
* of one callback run asynchronously, one at a time, in commit order; a
|
||||
* rejection is contained and logged like a sync throw. After the disposer
|
||||
* returns, no further invocation starts — one already queued is skipped;
|
||||
* one already started still settles, and service disposal waits for it.
|
||||
* @param callback - invoked after each commit with the next and previous values.
|
||||
* @returns the disposer removing this observer.
|
||||
*/
|
||||
watch(callback: (next: T, prev: T) => void | Promise<void>): () => void
|
||||
/**
|
||||
* Merge a partial patch into this namespace's user layer and persist it.
|
||||
* @param patch - plain-object patch over the user section; JSON-shaped data
|
||||
* only (non-JSON values reject with their path before anything persists).
|
||||
*/
|
||||
update(patch: object): Promise<void>
|
||||
/**
|
||||
* Replace this namespace's user section wholesale; absent keys re-inherit
|
||||
* the composition `base` and schema defaults (`replace({})` resets all).
|
||||
* @param section - the complete next user section; JSON-shaped data only,
|
||||
* as for {@link update}.
|
||||
*/
|
||||
replace(section: object): Promise<void>
|
||||
}
|
||||
```
|
||||
|
||||
## Descriptors
|
||||
|
||||
`describe()` serializes every registered namespace for configuration surfaces: the schemastery `toJSON()` envelope drives schema-rendered forms, the resolved value fills them, and the detached `base`/`user` layers let a form mark user-overridden fields by presence. `describe({ redactSecrets: true })` — mandatory on every wire surface — strips `role('secret')` fields from all three layers and enumerates their `{path, set}` slots so a page can render write-only inputs without ever receiving a secret.
|
||||
|
||||
```ts type-equiv
|
||||
/** One registered namespace as surfaced to configuration UIs. */
|
||||
interface SettingsDescriptor {
|
||||
/** The registered namespace. */
|
||||
ns: SettingsNamespace
|
||||
/** Serialized schemastery schema (`schema.toJSON()`). */
|
||||
schema: unknown
|
||||
/** Current resolved value. */
|
||||
value: unknown
|
||||
/**
|
||||
* Monotonic revision of the raw user section this descriptor was read at.
|
||||
* Send it back as `expectedRevision` on a write to refuse a stale one.
|
||||
*/
|
||||
revision: number
|
||||
/** Registrant's composition `base` layer (detached), when one was declared. */
|
||||
base?: unknown
|
||||
/**
|
||||
* Raw user section from the stored document (detached), when one exists and
|
||||
* is well-formed; a field's presence here is what marks it user-overridden.
|
||||
*/
|
||||
user?: unknown
|
||||
/** Owner's declared effect timing. */
|
||||
applies: SettingsApplies
|
||||
/** Schema-declared secret positions; present only under `redactSecrets`. */
|
||||
secrets?: RedactedSecret[]
|
||||
}
|
||||
```
|
||||
|
||||
A caller that holds only the redacted descriptor cannot safely rebuild a section, so removals travel as path ops instead. Each descriptor also carries a `revision` over the raw section; a write may send it back as `expectedRevision`, and one that no longer matches is refused rather than applied over the writer that landed first.
|
||||
```ts type-equiv
|
||||
/**
|
||||
* One path-addressed edit to a namespace's user section. Path mutation exists
|
||||
* for a caller holding an INCOMPLETE view of the section — a configuration UI
|
||||
* reads the redacted descriptor, which by construction never received the
|
||||
* `role('secret')` fields. Such a caller can name the field it means without
|
||||
* restating the section: a wholesale `replace` rebuilt from a redacted
|
||||
* document silently deletes every secret the wire never returned.
|
||||
*/
|
||||
type SettingsPathOp =
|
||||
| { op: 'set'; path: readonly string[]; value: unknown }
|
||||
| { op: 'unset'; path: readonly string[] }
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Options for {@link Settings.describe}. */
|
||||
interface SettingsDescribeOptions {
|
||||
/**
|
||||
* Strip `role('secret')` fields from `value`/`base`/`user` and enumerate
|
||||
* them in each descriptor's `secrets`. Every wire surface MUST pass this;
|
||||
* the verbatim default exists for same-process configuration UIs only.
|
||||
*/
|
||||
redactSecrets?: boolean
|
||||
}
|
||||
```
|
||||
|
||||
## Change commits
|
||||
|
||||
Every committed change — an in-process write or an externally observed provider edit — emits `settings/updated (ns, next, prev, source)` after the new value is authoritative, and never when the resolved value is deep-equal. The source tag separates the two entry paths.
|
||||
|
||||
```ts type-equiv
|
||||
/** Origin of one committed settings change. */
|
||||
type SettingsUpdateSource = 'update' | 'provider'
|
||||
```
|
||||
140
docs/core-data-structures/settings.zh.md
Normal file
140
docs/core-data-structures/settings.zh.md
Normal file
@@ -0,0 +1,140 @@
|
||||
# 用户设置
|
||||
|
||||
[English](settings.md) | 中文
|
||||
|
||||
[dsh-settings](../../packages/settings/settings) 的用户设置 seam 持有一份按 namespace 分节的用户文档，并把每个已注册 namespace 解析为：schema 默认值，然后注册方的组合 `base`，最后用户分节。[dsh-settings-local](../../packages/settings/settings-local) 这类 provider 存储原始文档并推送外部编辑；消费插件注册 schema 后读取或观察解析值。组合配置仍留在 `cordis.yml`——namespace 只承载用户可编辑子集。
|
||||
|
||||
Source: [`packages/settings/settings/src/index.ts`](../../packages/settings/settings/src/index.ts)
|
||||
|
||||
## 标识
|
||||
|
||||
namespace 命名用户文档中一个插件所有的分节。brand 使其不与其他跨边界 id 混用；构造时校验小写 kebab-case 形态。
|
||||
|
||||
```ts type-equiv
|
||||
/** Nominal id of one registered settings namespace. */
|
||||
type SettingsNamespace = Branded<'SettingsNamespace'>
|
||||
```
|
||||
|
||||
## 注册
|
||||
|
||||
注册把 schemastery schema 绑定到调用方插件 fiber 上的 namespace——dispose 该 fiber 即移除 namespace 及其观察者。options 携带组合层与 owner 的生效时机。
|
||||
|
||||
```ts type-equiv
|
||||
/** Registration options beyond the namespace schema. */
|
||||
interface SettingsRegisterOptions<T> {
|
||||
/** Composition-layer values resolved below the user layer (entry-config subset). */
|
||||
base?: Partial<T>
|
||||
/** Owner's effect timing, surfaced to configuration UIs; defaults to `live`. */
|
||||
applies?: SettingsApplies
|
||||
}
|
||||
```
|
||||
|
||||
`applies` 是 UI 提示而非机制：`restart` 的 owner 只是从不 watch，其值在构造期读取一次，配置界面可为待生效变更加标。
|
||||
|
||||
```ts type-equiv
|
||||
/** When a namespace's changes take effect for its owner. */
|
||||
type SettingsApplies = 'live' | 'restart'
|
||||
```
|
||||
|
||||
## Owner scope
|
||||
|
||||
scope 是面向 owner 的句柄。`update` 把稀疏 patch 只合并进用户分节（绝不进 `base`）；`replace` 整体替换分节，是删除/重置路径——替换中缺席的键重新继承 `base` 与 schema 默认值。同一 namespace 的写入按调用顺序串行，解析值是深冻结快照。
|
||||
|
||||
```ts type-equiv
|
||||
/** Owner-facing handle for one registered namespace. */
|
||||
interface SettingsScope<T> {
|
||||
/** Current resolved value: schema defaults, then `base`, then the user layer. */
|
||||
get(): T
|
||||
/**
|
||||
* Observe committed changes to this namespace's resolved value. Invocations
|
||||
* of one callback run asynchronously, one at a time, in commit order; a
|
||||
* rejection is contained and logged like a sync throw. After the disposer
|
||||
* returns, no further invocation starts — one already queued is skipped;
|
||||
* one already started still settles, and service disposal waits for it.
|
||||
* @param callback - invoked after each commit with the next and previous values.
|
||||
* @returns the disposer removing this observer.
|
||||
*/
|
||||
watch(callback: (next: T, prev: T) => void | Promise<void>): () => void
|
||||
/**
|
||||
* Merge a partial patch into this namespace's user layer and persist it.
|
||||
* @param patch - plain-object patch over the user section; JSON-shaped data
|
||||
* only (non-JSON values reject with their path before anything persists).
|
||||
*/
|
||||
update(patch: object): Promise<void>
|
||||
/**
|
||||
* Replace this namespace's user section wholesale; absent keys re-inherit
|
||||
* the composition `base` and schema defaults (`replace({})` resets all).
|
||||
* @param section - the complete next user section; JSON-shaped data only,
|
||||
* as for {@link update}.
|
||||
*/
|
||||
replace(section: object): Promise<void>
|
||||
}
|
||||
```
|
||||
|
||||
## 描述符
|
||||
|
||||
`describe()` 为配置界面序列化每个已注册 namespace：schemastery 的 `toJSON()` 信封驱动 schema 渲染的表单，解析值填充表单，分离出的 `base`/`user` 层让表单按字段是否出现在 user 层标注「用户已覆盖」。`describe({ redactSecrets: true })`——每个 wire 面都必须传入——从三层剥离 `role('secret')` 字段并枚举其 `{path, set}` 槽位，页面因此能渲染只写输入框而永远收不到机密值。
|
||||
|
||||
```ts type-equiv
|
||||
/** One registered namespace as surfaced to configuration UIs. */
|
||||
interface SettingsDescriptor {
|
||||
/** The registered namespace. */
|
||||
ns: SettingsNamespace
|
||||
/** Serialized schemastery schema (`schema.toJSON()`). */
|
||||
schema: unknown
|
||||
/** Current resolved value. */
|
||||
value: unknown
|
||||
/**
|
||||
* Monotonic revision of the raw user section this descriptor was read at.
|
||||
* Send it back as `expectedRevision` on a write to refuse a stale one.
|
||||
*/
|
||||
revision: number
|
||||
/** Registrant's composition `base` layer (detached), when one was declared. */
|
||||
base?: unknown
|
||||
/**
|
||||
* Raw user section from the stored document (detached), when one exists and
|
||||
* is well-formed; a field's presence here is what marks it user-overridden.
|
||||
*/
|
||||
user?: unknown
|
||||
/** Owner's declared effect timing. */
|
||||
applies: SettingsApplies
|
||||
/** Schema-declared secret positions; present only under `redactSecrets`. */
|
||||
secrets?: RedactedSecret[]
|
||||
}
|
||||
```
|
||||
|
||||
只持有脱敏 descriptor 的调用方无法安全地重建分节，因此删除改以路径 op 传递。每个 descriptor 还携带针对原始分节的 `revision`；写入可以把它作为 `expectedRevision` 送回，不再匹配的写入会被拒绝，而不是覆盖在先落地的那个写方之上。
|
||||
```ts type-equiv
|
||||
/**
|
||||
* One path-addressed edit to a namespace's user section. Path mutation exists
|
||||
* for a caller holding an INCOMPLETE view of the section — a configuration UI
|
||||
* reads the redacted descriptor, which by construction never received the
|
||||
* `role('secret')` fields. Such a caller can name the field it means without
|
||||
* restating the section: a wholesale `replace` rebuilt from a redacted
|
||||
* document silently deletes every secret the wire never returned.
|
||||
*/
|
||||
type SettingsPathOp =
|
||||
| { op: 'set'; path: readonly string[]; value: unknown }
|
||||
| { op: 'unset'; path: readonly string[] }
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Options for {@link Settings.describe}. */
|
||||
interface SettingsDescribeOptions {
|
||||
/**
|
||||
* Strip `role('secret')` fields from `value`/`base`/`user` and enumerate
|
||||
* them in each descriptor's `secrets`. Every wire surface MUST pass this;
|
||||
* the verbatim default exists for same-process configuration UIs only.
|
||||
*/
|
||||
redactSecrets?: boolean
|
||||
}
|
||||
```
|
||||
|
||||
## 变更提交
|
||||
|
||||
每次提交的变更——进程内写入或 provider 观察到的外部编辑——在新值成为权威值之后发出 `settings/updated (ns, next, prev, source)`，解析值深相等时绝不发出。source 标记区分两条入口路径。
|
||||
|
||||
```ts type-equiv
|
||||
/** Origin of one committed settings change. */
|
||||
type SettingsUpdateSource = 'update' | 'provider'
|
||||
```
|
||||
@@ -1,6 +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
|
||||
subagent.md: 2497dbab9cfc8304eb7aaeba7109404ac614bbff
|
||||
subagent.zh.md: 2d96e9bc635951746e72ed58a7c3638dc2598cc2
|
||||
# pnpm run verify-translation-pairing --write docs/core-data-structures/subagent.md
|
||||
subagent.md: c5fbf80ae71f99606dd86e38f06a4511b4ae4c73
|
||||
subagent.zh.md: 42c1fa7cb10863c1aa4ae975171b901207c08b85
|
||||
|
||||
@@ -4,23 +4,25 @@ English | [中文](subagent.zh.md)
|
||||
|
||||
The subagent seam — an agent delegating work to a child agent. Like [bash](bash.md) it is **one optional capability**, not part of the agent-loop spine, so its vocabulary lives here rather than in [core.md](core.md). But it differs from every other seam on one axis: **multiple provider implementations coexist** in one context, registered by name (`ctx.subagents`), where bash allows only one executor. The registry shape mirrors the [LLM adapter registry](llm-streaming.md), not the single-service bash executor.
|
||||
|
||||
Interface: [dsh-subagent](../../packages/subagent/subagent) (`ctx.subagents` + the vocabulary below). Implementations are sibling packages (`dsh-subagent-spawn`, `-fork`, `-acp`); the model-facing consumer is [dsh-tool-subagent](../../packages/subagent/tool-subagent). The proposal and rationale: [the subagent Agent Note](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md).
|
||||
Interface: [dsh-subagent](../../packages/subagent/subagent) (`ctx.subagents` + the vocabulary below). Implementations are sibling packages (`dsh-subagent-spawn`, `-fork`, `-acp`); the model-facing consumers are [dsh-tool-subagent](../../packages/subagent/tool-subagent) (per-provider delegation), [dsh-tool-subagent-control](../../packages/subagent/tool-subagent-control) (the optional global `send_message` and `list_agents` controls), and [dsh-tool-subagent-report](../../packages/subagent/tool-subagent-report) (the optional child-scoped `report` return channel). The same `ctx.subagents` service owns continuable-child orchestration through an internal activation manager and read-only direct-child discovery through optional session query. The rationale lives in [the subagent Agent Note](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md), [the continuable subagents Agent Note](../../.agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md), [the report-tool Agent Note](../../.agents/notes/implemented/feature/2026-07-30-continuable-subagent-report-tool.md), [the durable catalog Agent Note](../../.agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.md), and [the merged-service Agent Note](../../.agents/notes/implemented/simplification/2026-07-26-merge-subagent-control-service.md).
|
||||
|
||||
Source: [`packages/subagent/subagent/src/types.ts`](../../packages/subagent/subagent/src/types.ts)
|
||||
Sources: [`packages/subagent/subagent/src/types.ts`](../../packages/subagent/subagent/src/types.ts), [`packages/subagent/subagent/src/index.ts`](../../packages/subagent/subagent/src/index.ts), and [`packages/subagent/subagent/src/continuation.ts`](../../packages/subagent/subagent/src/continuation.ts)
|
||||
|
||||
## Two kinds of capability, discovered two ways
|
||||
|
||||
A provider advertises its **start-time** features on a static descriptor the service checks BEFORE a run exists; a request that needs one the provider lacks is rejected loud (`SubagentError('UNSUPPORTED_CAPABILITY')`), never accepted-then-ignored. **Runtime** features (steering, resume) are instead optional methods on [`SubagentRun`](#a-live-run-subagentrun) — the method's presence IS the capability, and TS narrowing is the discovery mechanism.
|
||||
A provider advertises its **start-time** features on a static descriptor the service checks BEFORE a one-shot run exists; a request that needs one the provider lacks is rejected loud (`SubagentError('UNSUPPORTED_CAPABILITY')`), never accepted-then-ignored. Those flags describe only the one-shot [`start()`](#the-provider-seam-subagentprovider) path, where the provider composes the child. **Continuable** children are composed by the continuation manager itself, so they are gated by one optional method whose presence IS the capability, with TS narrowing as the discovery mechanism: [`SubagentProvider.prepareContinuable`](#the-provider-seam-subagentprovider).
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Which START-TIME features a provider supports. Checked by the service before delegating to
|
||||
* {@link SubagentProvider.start}: a request that needs a capability the chosen provider lacks
|
||||
* is rejected with a typed error rather than accepted-then-ignored (the "fail loud, no silent
|
||||
* degradation" rule). These static flags cover features needed before a run exists; runtime
|
||||
* capabilities such as steering and resume are optional {@link SubagentRun} methods whose presence
|
||||
* is the capability. Each flag corresponds one-to-one to a {@link SubagentStartRequest} option:
|
||||
* `depthLimit` to `maxDepth`; the other names match.
|
||||
* degradation" rule). These flags describe the ONE-SHOT
|
||||
* {@link SubagentProvider.start} path, where the provider composes the child;
|
||||
* continuable children are composed by the continuation manager itself and are
|
||||
* gated by {@link SubagentProvider.prepareContinuable} instead. Each flag
|
||||
* corresponds one-to-one to a {@link SubagentStartRequest} option: `depthLimit`
|
||||
* to `maxDepth`; the other names match.
|
||||
*/
|
||||
interface SubagentCapabilities {
|
||||
readonly outputSchema: boolean
|
||||
@@ -30,18 +32,21 @@ interface SubagentCapabilities {
|
||||
}
|
||||
```
|
||||
|
||||
## The start request
|
||||
## The one-shot start request
|
||||
|
||||
The tool layer builds this request from the model input and its own config; the service validates it against the named provider before `start`. Required `parent` supplies the session cwd, lineage, and delegation depth. Optional output schema, depth, tool filter, and persona require matching capability flags. Unsupported schemas fail at start; in-process backends scope filters and personas to child creation and implement the supported object-rooted schema with a forced capture tool.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* What a caller asks for when starting a subagent. The tool layer builds this
|
||||
* from the model's `{ description, prompt }` plus its own config; the service
|
||||
* validates {@link SubagentCapabilities} against the named provider, then
|
||||
* passes it to {@link SubagentProvider.start}.
|
||||
* What a caller asks for when starting a ONE-SHOT subagent. The tool layer
|
||||
* builds this from the model's `{ description, prompt }` plus its own config;
|
||||
* the service validates {@link SubagentCapabilities} against the named provider
|
||||
* and resolves the durable descriptor before dispatching to
|
||||
* {@link SubagentProvider.start}.
|
||||
*/
|
||||
interface SubagentStartRequest {
|
||||
/** Optional short display label persisted with a session-backed child. */
|
||||
readonly label?: string
|
||||
/** Content delivered as the child's user message. */
|
||||
readonly prompt: ContentBlock[]
|
||||
/**
|
||||
@@ -54,8 +59,8 @@ interface SubagentStartRequest {
|
||||
* Cancellation signal from the spawning context (the tool's `exec.signal`).
|
||||
* This is the canonical cancellation channel both before and after startup:
|
||||
* a provider rejects `start()` after cleaning partial resources when it
|
||||
* fires before publication, and cancels a published child when it fires
|
||||
* afterward.
|
||||
* fires before the run is published, and cancels the published run's
|
||||
* remaining turn work when it fires afterward.
|
||||
*/
|
||||
readonly signal: AbortSignal
|
||||
readonly agentOptions?: AgentOptions
|
||||
@@ -93,9 +98,161 @@ interface SubagentStartRequest {
|
||||
|
||||
`signal` is the single cancellation channel before and after readiness. The [subagent composition-controls Agent Note](../../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) owns the persona, live global-tool filter, absolute-depth, and visibility-not-authority rationale.
|
||||
|
||||
The caller-facing request does not carry catalog format details or continuation state. `SubagentService.start()` resolves the detached one-shot descriptor after capability checks, then passes this provider-facing request to the selected transport; a continuable child never reaches `SubagentProvider.start()`:
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Provider-facing one-shot request after {@link SubagentService.start} resolves
|
||||
* the durable child descriptor.
|
||||
*/
|
||||
interface ResolvedSubagentStartRequest extends SubagentStartRequest {
|
||||
/** Detached descriptor a session-backed provider persists in the child log. */
|
||||
readonly descriptor: SubagentDescriptorData
|
||||
}
|
||||
```
|
||||
|
||||
## Continuable children and activations
|
||||
|
||||
A **continuable background subagent** is one durable child Session with at most one process-local **Activation** — a residency epoch for a reconstructed child Agent. An Activation is not a request, result, cancellation, or Task boundary: it may execute many FIFO turns and stays resident while descendants it created are still running. The continuation manager owns activation admission, direct-parent authorization, the live ownership graph, cold resume, and child-first disposal; the Agent loop owns all turn ordering and execution. No continuable path creates a Task or an intermediate result-bearing wrapper.
|
||||
|
||||
```text
|
||||
persisted Session
|
||||
-> optional live Activation
|
||||
-> one retained AgentHandle
|
||||
-> Agent inbox as the only turn FIFO
|
||||
-> zero or more owned child Activations
|
||||
```
|
||||
|
||||
`SubagentService.startContinuable()` reserves the stable child id, snapshots the versioned `subagent/descriptor` payload, asks the named provider for its detached `ContinuableCreateSpec`, creates the child Agent through a private activation-owner scope, establishes any continuable-parent ownership, and submits the initial prompt. It resolves with `{ childId, messageId }` when inbox acceptance yields the message id — without waiting for the turn to start or for the message to enter the Session log. Every failure before that acceptance rejects with neither id, disposing any created handle and rolling back the Activation and parent ownership.
|
||||
|
||||
`SubagentService.followup()` is the sole continuation-message operation, and routing depends only on Activation residency:
|
||||
|
||||
| Activation state | `followup` |
|
||||
|---|---|
|
||||
| `running` | enqueue in the same Activation |
|
||||
| `waiting` | wake the same Activation |
|
||||
| no Activation | cold-resume a new Activation |
|
||||
|
||||
`running` means the Agent has an active admission or turn, or waking inbox work; `waiting` means it is quiescent but still owns at least one child Activation that has not completed disposal; `settled` means quiescent with every owned child disposed, at which point the manager disposes the `AgentHandle` and removes the Activation. The manager derives these internal conditions from Agent quiescence and the owned-child set rather than maintaining a second execution state machine.
|
||||
|
||||
The Agent inbox is the only queue. Every continuation message becomes one `Agent.followup()` FIFO turn, so accepted messages have one observable order and a follow-up cannot redirect a turn already underway. Successful delivery returns the accepted `MessageId`; the existing `agent/inbox/enqueue`, `agent/inbox/dequeue`, and `agent/inbox/discard` events remain the message-lifecycle observations, and the continuation layer defines no subagent-specific delivery route.
|
||||
|
||||
Follow-up authority comes from an exact live Agent tool context. The authenticated Agent must be the durable child's direct parent recorded in `SessionHeader.parentSession`. `MessageSource` and `senderSessionId` are durable provenance after admission and grant no authority; the optional model-facing tool uses `CoordinatorMessageSource`.
|
||||
|
||||
For both operations the caller signal owns lookup, materialization, and admission only until inbox acceptance. Afterwards the manager owns the Activation independently: later caller cancellation neither cancels the accepted turn nor disposes the child, and the seam exposes no public subagent cancellation or steering operation.
|
||||
|
||||
Every Activation owns its `AgentHandle` and an `ownedChildren: Set<SessionId>`; because one Session has at most one live Activation, the child Session id identifies the live child without another runtime-incarnation reference. Starting a child or submitting parent-originated work registers the child in a continuation-managed parent's set before the child can run, and that parent cannot settle while the set is non-empty. A top-level or other non-continuation Agent has no Activation and stays outside the waiting graph. Child release happens only after the child Agent is quiescent, every child of that child is disposed, the best-effort final session flush settles, and the child's `AgentHandle` completes disposal.
|
||||
|
||||
Final settlement awaits `ctx.sessions.flush(session)` but ignores its participation boolean because an arbitrary listener cannot prove that a persistence backend stored the state. Rejection is logged without failing the Activation, and the manager still disposes the handle and releases ownership; the persisted child state may then be missing or stale on a later resume. Manager unload invokes an internal manager-wide drain that closes admission and disposes every live forest; `drainContinuableDescendants(parents)` closes admission only below exact live host-owned Agents and disposes their continuable descendants while unrelated forests remain live. Both await already-admitted materializations in their scope, propagate cancellation top-down, release handles child-first, and await every selected branch despite individual failures. Durable child Sessions survive that process-local teardown.
|
||||
|
||||
```ts type-equiv
|
||||
/** Attribution for a model coordinator's follow-up to one of its children. */
|
||||
interface CoordinatorMessageSource {
|
||||
readonly kind: 'coordinator'
|
||||
/** Session id of the agent whose tool call produced the follow-up. */
|
||||
readonly senderSessionId: SessionId
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Options for following up with one continuable child. */
|
||||
interface SubagentFollowupOptions {
|
||||
/** Durable attribution retained on the delivered message; it grants no authority. */
|
||||
readonly source: MessageSource
|
||||
/** Caller cancellation, owning the operation only until inbox acceptance. */
|
||||
readonly signal: AbortSignal
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Identities returned once a continuable child accepted its initial prompt. */
|
||||
interface ContinuableStart {
|
||||
/** The durable child session id, stable across activations. */
|
||||
readonly childId: SessionId
|
||||
/** The accepted initial prompt's inbox message id. */
|
||||
readonly messageId: MessageId
|
||||
}
|
||||
```
|
||||
|
||||
An optional continuable-child setup contribution can install scope-local capabilities after base child composition and before Activation publication. The registry is ordered and transactional: a failed or revoked setup rolls back the unpublished Activation, child-scope disposal releases every installation, new registrations affect the next Activation, and registration removal revokes every resident installation immediately.
|
||||
|
||||
`SubagentService.reportFrom()` uses that extension seam without adding a second queue or a result-bearing child wrapper. The exact live child Agent authorizes the call; callers cannot name a recipient. The manager derives the only recipient from the child's durable `parentSession`, requires that parent Agent to be live, frames the selected content as one `subagent-report` user message, and returns the message's stable `MessageId`. Quiet delivery uses `Agent.inject()` and creates no inbox occurrence or parent turn; waking delivery uses `Agent.followup()` and creates one ordinary later parent turn. Neither mode concludes the child's turn, and no final answer reports implicitly.
|
||||
|
||||
```ts type-equiv
|
||||
/** Durable attribution for a continuable child's explicit parent report. */
|
||||
interface SubagentReportMessageSource {
|
||||
readonly kind: 'subagent-report'
|
||||
/** Session id of the reporting child. */
|
||||
readonly senderSessionId: SessionId
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Deployment scheduling policy for accepted child reports. */
|
||||
type SubagentReportDelivery = 'quiet' | 'wakeup'
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Options for one continuable child's report to its direct parent. */
|
||||
interface SubagentReportOptions {
|
||||
/** Already-resolved parent scheduling policy. */
|
||||
readonly delivery: SubagentReportDelivery
|
||||
/** Caller cancellation, owning authorization and admission until acceptance. */
|
||||
readonly signal: AbortSignal
|
||||
}
|
||||
```
|
||||
|
||||
The provider participates only in preparing the initial creation spec, where `spawn` and `fork` differ. Its returned spec carries only detached provider-specific creation inputs — today the optional parent-history seed — and no Agent, `AgentHandle`, prompt delivery, result, disposal, or resume operation. Cold resume does not dispatch through a provider at all: the manager folds the generic descriptor, calls `ctx.agents.resume()` through the same activation-owner scope, and submits the waiting turn.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* What the continuation manager asks a provider for while materializing one
|
||||
* continuable child's FIRST activation. The manager has already reserved the
|
||||
* durable child identity and owns every later operation, so this request
|
||||
* carries only what distinguishes a fresh child from one seeded with parent
|
||||
* history.
|
||||
*/
|
||||
interface ContinuableCreateRequest {
|
||||
/** The reserved durable child session id, for provider diagnostics. */
|
||||
readonly sessionId: SessionId
|
||||
/** The delegating parent agent whose history a seeding provider reads. */
|
||||
readonly parent: Agent
|
||||
/**
|
||||
* Caller cancellation, which owns preparation only until the manager accepts
|
||||
* the initial prompt into the child's inbox.
|
||||
*/
|
||||
readonly signal: AbortSignal
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* A provider's detached contribution to one continuable child's creation. This
|
||||
* is DATA, never a capability: it carries no Agent, `AgentHandle`, prompt
|
||||
* delivery, result, disposal, or resume operation, because the continuation
|
||||
* manager owns the child's whole lifecycle after preparation.
|
||||
*/
|
||||
interface ContinuableCreateSpec {
|
||||
/**
|
||||
* Completed-turn prefix of the parent's log to seed the child session with,
|
||||
* or absent for a fresh child. Same durable contract as
|
||||
* `CreateAgentOptions.seed`: contiguous from seq 0, lossless JSON, balanced.
|
||||
*/
|
||||
readonly seed?: readonly SessionEvent[]
|
||||
}
|
||||
```
|
||||
|
||||
The descriptor (`SubagentDescriptorData` in [descriptor.ts](../../packages/subagent/subagent/src/descriptor.ts)) is a mode-discriminated durable identity for every session-backed subagent. Both modes carry the provider name. A `one-shot` descriptor optionally carries a caller-owned display `label`; a `continuable` descriptor requires the delegation `description` as its durable creation label and additionally snapshots resolved child `agentOptions.provider`/`model` and optional `persona`/`toolFilter` for cold resume. It never snapshots the merge-extensible `AgentOptions` object, so an unrelated extension value cannot break continuation and a later composition input is a deliberate version change. It omits `subagentDepth` (cold resume trusts the persisted header's `delegationDepth` as the monotone floor) and `outputSchema` (one run or Activation's result contract, not durable identity).
|
||||
|
||||
A local one-shot provider appends the descriptor inside the child's initial turn before its first request. The continuation manager appends the descriptor after any provider-supplied lineage and before the initial prompt is admitted; `header.seedLength` remains the fork-lineage boundary, so descriptor lookup reads the child's own suffix. The event is log-only: no `surfaceOp`, never in model history, and retained across compaction by the append-only log. Malformed current-version descriptors are corrupt; unsupported versions cannot be classified by this runtime.
|
||||
|
||||
## Durable enumeration: `listChildren()` and `SubagentListEntry`
|
||||
|
||||
`SubagentService.listChildren(parentSessionId)` enumerates the parent's direct session-backed subagents from one `ctx.sessionQuery.traceSession()` observation, without loading or resuming any Agent. Session lineage is broader than subagent identity — ordinary forks share `parentSession` — so exactly one supported `subagent/descriptor` event in the child's own suffix (after `seedLength`, so a fork seed cannot leak an ancestor's descriptor) is the sole subagent discriminator. `SessionHeader.origin: 'subagent'` is only a coarse product-navigation classifier stamped before publication; it can suppress duplicate sidebar rows but cannot establish a valid descriptor, resumability, or authorization. The result is one `SubagentListEntry[]` in the trace's `createdAt`-then-id candidate order: a valid descriptor yields a `child` entry with `mode: 'one-shot' | 'continuable'` and `activity: 'running' | 'inactive'`; continuable entries always carry `label`, while one-shot entries carry it only when the start caller supplied presentation metadata. A per-child inspection failure yields a `diagnostic` entry (`corrupt`, `unsupported`, or `unavailable`) so one damaged sibling cannot hide healthy children; a missing descriptor yields no entry. Activity snapshots only whether the logical record is live in `ctx.sessions`, not outcome or resumability. A service consumer such as a UI can display both modes and choose an unlabeled one-shot fallback, while the model-facing `list_agents` adapter (the separately loadable `/list-agents` plugin of [dsh-tool-subagent-control](../../packages/subagent/tool-subagent-control)) keeps only continuable entries and maps activity to its existing `running`/`complete` vocabulary. A failure while building the initial trace fails the whole call — per-child isolation begins only after a trustworthy candidate set exists. The service keeps `sessionQuery` optional for by-id continuation: `listChildren()` throws `SubagentError` with code `SUBAGENT_CONTROL_SESSION_QUERY_UNAVAILABLE` when it is absent, while the list tool requires `ctx.subagents` and `ctx.sessionQuery` at plugin load. Listing does not consult the continuation manager's Activation map, Agent registry, or provider availability; `send_message` remains the authoritative delivery-time operation, and a listed running continuable child may still reject delivery as an ownership conflict.
|
||||
|
||||
## The terminal result: `SubagentResult`
|
||||
|
||||
The outcome of a run, resolved by `SubagentRun.result`. `structured` is present only after a requested `outputSchema` was successfully satisfied; requesting a schema does not guarantee it, and a provider may return `stopReason: 'error'` when the child fails or finishes without a valid capture. A non-`completed` `stopReason` means `output` may be partial — the consumer maps it to an `isError` tool result rather than reporting partial output as success.
|
||||
The outcome of a one-shot run, resolved by `SubagentRun.result`. `structured` is present only after a requested `outputSchema` was successfully satisfied; requesting a schema does not guarantee it, and a provider may return `stopReason: 'error'` when the child fails or finishes without a valid capture. A non-`completed` `stopReason` means `output` may be partial — the consumer maps it to an `isError` tool result rather than reporting partial output as success.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -140,15 +297,19 @@ interface SubagentStopReasonMap {
|
||||
}
|
||||
```
|
||||
|
||||
## A live run: `SubagentRun`
|
||||
## A one-shot run: `SubagentRun`
|
||||
|
||||
`SubagentRun` is the consumer-owned handle for a ready child. Consumers await `result` and always dispose the run to reach quiescence. Child failures resolve with a non-completed stop reason; only unrepresentable infrastructure faults reject. Optional `sendMessage` and `resume` methods advertise their runtime capabilities by presence.
|
||||
`SubagentRun` is the consumer-owned handle for a published one-shot child — one disposable foreground delegation with one result, never a durable child handle. Prompt submission, turn work, and infrastructure faults after publication belong to `result`. Consumers await that result and always dispose the run to reach quiescence. Child failures resolve with a non-completed stop reason; only unrepresentable infrastructure faults reject. A run has no steering and no resume: continuable conversations have no run at all, because the continuation manager holds their `AgentHandle` directly and orders every turn through the child's own inbox.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Child handle returned only after readiness. Consumers await {@link result} and must always
|
||||
* {@link dispose} to cancel remaining work and reach quiescence. Optional methods are runtime
|
||||
* capability discovery; narrow their presence before calling.
|
||||
* ONE-SHOT child handle returned after publication. Prompt submission, turn
|
||||
* work, and infrastructure faults after that boundary belong to {@link result}.
|
||||
* Consumers await that result and must always {@link dispose} to cancel
|
||||
* remaining work and reach quiescence. A run is one disposable foreground
|
||||
* delegation with one result; continuable conversations have no run — the
|
||||
* continuation manager holds their `AgentHandle` directly and orders every
|
||||
* turn through the child's own inbox.
|
||||
*/
|
||||
interface SubagentRun {
|
||||
/**
|
||||
@@ -167,8 +328,8 @@ interface SubagentRun {
|
||||
* Resolves with the child's terminal {@link SubagentResult} when the run
|
||||
* settles. Does NOT reject on a child-level failure — a model/transport
|
||||
* failure resolves with `stopReason: 'error'` so the consumer maps it to an
|
||||
* `isError` tool result. Rejects only on an infrastructure fault the seam
|
||||
* cannot represent as a stop reason.
|
||||
* `isError` tool result. Rejects on an infrastructure fault the seam cannot
|
||||
* represent as a stop reason.
|
||||
*/
|
||||
readonly result: Promise<SubagentResult>
|
||||
/**
|
||||
@@ -176,24 +337,14 @@ interface SubagentRun {
|
||||
* Idempotent.
|
||||
*/
|
||||
dispose(): Promise<void>
|
||||
/**
|
||||
* OPTIONAL (steering capability): send additional content to the running
|
||||
* child between steps. Present only on providers that support live steering.
|
||||
*/
|
||||
sendMessage?(content: ContentBlock[]): void
|
||||
/**
|
||||
* OPTIONAL (resume capability): send a follow-up task to a settled child,
|
||||
* continuing its session, and return a fresh run for the continuation.
|
||||
*/
|
||||
resume?(content: ContentBlock[]): Promise<SubagentRun>
|
||||
}
|
||||
```
|
||||
|
||||
A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, expose the exact child as `localAgent`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope. A remote provider instead returns a parent-scoped lifecycle id and `localAgent: undefined`.
|
||||
A local one-shot run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, expose the exact child as `localAgent`, record `request.parent.session.id` in the child's `parentSession` header, and append the resolved descriptor inside the child's initial turn before its first request. Runtime ownership may place the child under the parent, provider, or root scope. A remote provider instead returns a parent-scoped lifecycle id and `localAgent: undefined`; without a local child Session, it is absent from trace-backed enumeration.
|
||||
|
||||
## The provider seam: `SubagentProvider`
|
||||
|
||||
Each provider is a named child-agent transport, and multiple providers may coexist. The service validates requested start-time capabilities before `start()`. `inheritsParentContext` describes only conversation seeding (`fork`: true; `spawn` and `acp`: false), allowing consumers to generate accurate model-facing wording without implying inherited tools, services, or authority.
|
||||
Each provider is a named child-agent transport, and multiple providers may coexist. The service validates requested start-time capabilities before `start()`, and rejects a continuable start on a provider without `prepareContinuable`. `inheritsParentContext` describes only conversation seeding (`fork`: true; `spawn` and `acp`: false), allowing consumers to generate accurate model-facing wording without implying inherited tools, services, or authority.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -213,22 +364,38 @@ interface SubagentProvider {
|
||||
*/
|
||||
readonly inheritsParentContext: boolean
|
||||
/**
|
||||
* Establish a child and return its handle only after publication. The
|
||||
* service has already validated that every requested start-time capability
|
||||
* is supported, so an implementation may assume e.g. `request.maxDepth` is
|
||||
* honorable when present. If setup fails or `request.signal` aborts before
|
||||
* fulfillment, the provider owns and cleans all partial resources before this
|
||||
* promise rejects. Ownership transfers to the caller only on fulfillment.
|
||||
* Establish a ONE-SHOT child and return its handle after publication.
|
||||
* The service has already validated that every requested start-time
|
||||
* capability is supported and resolved `request.descriptor`, so a
|
||||
* session-backed implementation appends that descriptor inside the child's
|
||||
* initial turn. Before fulfillment, the provider owns setup and cleans any
|
||||
* unpublished partial resources before rejecting. Ownership transfers on
|
||||
* fulfillment; subsequent turn or infrastructure failure settles through
|
||||
* the returned run.
|
||||
*/
|
||||
start(request: SubagentStartRequest): Promise<SubagentRun>
|
||||
start(request: ResolvedSubagentStartRequest): Promise<SubagentRun>
|
||||
/**
|
||||
* OPTIONAL (continuable-creation capability): contribute the detached
|
||||
* creation inputs that distinguish this provider's continuable children —
|
||||
* today only whether the child session is seeded with parent history. Method
|
||||
* presence IS the capability: the service rejects continuable starts on
|
||||
* providers without it, while a provider that has it may still serve
|
||||
* ordinary one-shot delegations.
|
||||
*
|
||||
* This is the provider's ONLY participation in a continuable child. The
|
||||
* continuation manager owns identity reservation, composition, Agent
|
||||
* creation, prompt delivery, cold resume, ownership, and disposal, so a
|
||||
* provider never sees the child's Agent, handle, turns, or teardown.
|
||||
*/
|
||||
prepareContinuable?(request: ContinuableCreateRequest): Promise<ContinuableCreateSpec>
|
||||
}
|
||||
```
|
||||
|
||||
`start()` fulfills only with a ready run. The service mints a unique `runId`, snapshots `local` from the provider's exact `localAgent`, observes the result, emits `subagent/start`, and returns the same run; rejection implies provider cleanup and emits no lifecycle pair. The paired `subagent/end` carries the same identity and the final output or infrastructure failure. Both events are observe-only and contain listener exceptions.
|
||||
Provider `start()` fulfills with a published run. The service mints a unique `runId`, snapshots `local` from the provider's exact `localAgent`, observes the result, emits `subagent/start`, and returns the same run; a `start()` rejection implies cleanup of unpublished resources and emits no lifecycle pair, while a post-publication result rejection closes the emitted pair. Each continuable Activation emits the same observe-only pair for its residency epoch, so a cold resume is a new epoch with its own `runId`. The paired `subagent/end` carries the same identity and the final output or infrastructure failure. Both events are observe-only and contain listener exceptions. Their `provider` field is provenance for the run or Activation epoch, not a claim that the provider remains registered when the edge is emitted.
|
||||
|
||||
## In-process backends: depth and seed
|
||||
|
||||
The spawn and fork backends create an ordinary agent through `parent.ctx`, pass cancellation into core creation, and dispose through `AgentHandle`. Provider removal blocks new starts without revoking accepted runs. Each child gets a new flat scope rather than inheriting parent registrations. Depth and fork seeding reuse existing agent and session vocabulary:
|
||||
The spawn and fork backends create an ordinary one-shot agent through `parent.ctx`, pass cancellation into core creation, and dispose through `AgentHandle`; a continuable child is instead created by the continuation manager through its own activation-owner scope. Provider removal blocks new starts without revoking accepted runs. Each child gets a new flat scope rather than inheriting parent registrations. Depth and fork seeding reuse existing agent and session vocabulary:
|
||||
|
||||
- **Delegation depth** is durable `SessionHeader.delegationDepth` plus the merge-extensible runtime field `AgentOptions.subagentDepth`; absence means top-level depth zero, and the greater present value is authoritative. The seam owns both fields — the loop neither sets nor reads them — so an in-process child persists parent depth + 1, resume cannot lower it, and every start rejects a derived depth outside the safe-integer domain or above a defined absolute `request.maxDepth` cap.
|
||||
- **Fork seeding** uses `CreateAgentOptions.seed` (a `SessionEvent[]` prefix threaded through `AgentLoop.createAgent` → `ctx.sessions.prepare({ seed })`, the same primitive `resume` uses). The fork backend passes a *balanced completed-turn prefix* of the parent's log — the parent's events up to and including its last `turn/end` — so the seed is contiguous-from-0 and the [invariants](../../packages/support/invariants) replay accepts it (the in-flight, unbalanced turn is excluded).
|
||||
- **Delegation depth** is durable `SessionHeader.delegationDepth` plus the merge-extensible runtime field `AgentOptions.subagentDepth`; absence means top-level depth zero, and the greater present value is authoritative. The seam owns both fields — the loop neither sets nor reads them — so an in-process child persists parent depth + 1, cold resume cannot lower it, and every start rejects a derived depth outside the safe-integer domain or above a defined absolute `request.maxDepth` cap.
|
||||
- **Fork seeding** uses `CreateAgentOptions.seed` (a `SessionEvent[]` prefix threaded through `AgentLoop.createAgent` → `ctx.sessions.prepare({ seed })`, the same primitive `ctx.agents.resume()` uses). The fork backend passes a *balanced completed-turn prefix* of the parent's log — the parent's events up to and including its last `turn/end` — so the seed is contiguous-from-0 and the [invariants](../../packages/support/invariants) replay accepts it (the in-flight, unbalanced turn is excluded).
|
||||
|
||||
@@ -4,23 +4,25 @@
|
||||
|
||||
subagent seam：一个 agent（智能体）将工作委派给子 agent。与 [bash](bash.md) 一样，它是**一项可选能力**，不属于 agent loop（智能体循环）主干，因此其词汇定义在此而非 [core.md](core.md) 中。但它在一个维度上与其他所有 seam 不同：**同一上下文中可共存多个提供方实现**，按名称注册（`ctx.subagents`），而 bash 只允许一个执行器。注册表的形状参照 [LLM（大语言模型）适配器注册表](llm-streaming.md)，而非单服务的 bash 执行器。
|
||||
|
||||
接口：[dsh-subagent](../../packages/subagent/subagent)（`ctx.subagents` + 下文词汇）。实现为三个兄弟包（package）：`dsh-subagent-spawn`、`-fork`、`-acp`；面向模型的消费方是 [dsh-tool-subagent](../../packages/subagent/tool-subagent)。提案与设计理由见 [subagent Agent Note（agent 决策记录）](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md)。
|
||||
接口：[dsh-subagent](../../packages/subagent/subagent)（`ctx.subagents` + 下文词汇）。实现为三个兄弟包（package）：`dsh-subagent-spawn`、`-fork`、`-acp`；面向模型的消费方包括 [dsh-tool-subagent](../../packages/subagent/tool-subagent)（按提供方委派）、[dsh-tool-subagent-control](../../packages/subagent/tool-subagent-control)（可选的全局 `send_message` 与 `list_agents` 控制工具）和 [dsh-tool-subagent-report](../../packages/subagent/tool-subagent-report)（可选的 child 作用域 `report` 返回通道）。同一个 `ctx.subagents` 服务通过内部激活管理器负责可继续子 agent 编排，并通过可选的会话查询负责只读的直接 child 发现。设计理由见 [subagent Agent Note（agent 决策记录）](../../.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md)、[可继续 subagent Agent Note](../../.agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md)、[report 工具 Agent Note](../../.agents/notes/implemented/feature/2026-07-30-continuable-subagent-report-tool.md)、[持久化目录 Agent Note](../../.agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.md)和[服务合并 Agent Note](../../.agents/notes/implemented/simplification/2026-07-26-merge-subagent-control-service.md)。
|
||||
|
||||
源码：[`packages/subagent/subagent/src/types.ts`](../../packages/subagent/subagent/src/types.ts)
|
||||
源码：[`packages/subagent/subagent/src/types.ts`](../../packages/subagent/subagent/src/types.ts)、[`packages/subagent/subagent/src/index.ts`](../../packages/subagent/subagent/src/index.ts)和 [`packages/subagent/subagent/src/continuation.ts`](../../packages/subagent/subagent/src/continuation.ts)
|
||||
|
||||
## 两类能力，两种发现方式
|
||||
|
||||
提供方通过一个静态描述符公布其**启动时**特性，服务在 run 存在之前即行检查；如果请求依赖提供方不具备的特性，会被大声拒绝（`SubagentError('UNSUPPORTED_CAPABILITY')`），绝不会被接受后静默忽略。**运行时**特性（steering（中途引导）、恢复）则是 [`SubagentRun`](#a-live-run-subagentrun) 上的可选方法——方法的存在即为能力，TypeScript 的类型收窄即为发现机制。
|
||||
提供方通过一个静态描述符公布其**启动时**特性，服务会在单次 run 存在之前即行检查；如果请求依赖提供方不具备的特性，会被大声拒绝（`SubagentError('UNSUPPORTED_CAPABILITY')`），绝不会被接受后静默忽略。这些 flag 仅描述单次 [`start()`](#the-provider-seam-subagentprovider) 路径，即由提供方组合子 agent 的路径。**可继续**子 agent 由继续执行管理器自行组合，因此它们由唯一一个可选方法把关，方法存在即为能力，并以 TypeScript 的类型收窄作为发现机制：[`SubagentProvider.prepareContinuable`](#the-provider-seam-subagentprovider)。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Which START-TIME features a provider supports. Checked by the service before delegating to
|
||||
* {@link SubagentProvider.start}: a request that needs a capability the chosen provider lacks
|
||||
* is rejected with a typed error rather than accepted-then-ignored (the "fail loud, no silent
|
||||
* degradation" rule). These static flags cover features needed before a run exists; runtime
|
||||
* capabilities such as steering and resume are optional {@link SubagentRun} methods whose presence
|
||||
* is the capability. Each flag corresponds one-to-one to a {@link SubagentStartRequest} option:
|
||||
* `depthLimit` to `maxDepth`; the other names match.
|
||||
* degradation" rule). These flags describe the ONE-SHOT
|
||||
* {@link SubagentProvider.start} path, where the provider composes the child;
|
||||
* continuable children are composed by the continuation manager itself and are
|
||||
* gated by {@link SubagentProvider.prepareContinuable} instead. Each flag
|
||||
* corresponds one-to-one to a {@link SubagentStartRequest} option: `depthLimit`
|
||||
* to `maxDepth`; the other names match.
|
||||
*/
|
||||
interface SubagentCapabilities {
|
||||
readonly outputSchema: boolean
|
||||
@@ -30,18 +32,21 @@ interface SubagentCapabilities {
|
||||
}
|
||||
```
|
||||
|
||||
## 启动请求
|
||||
## 单次启动请求
|
||||
|
||||
工具层根据模型输入和自身配置构建此请求；服务在 `start` 之前针对指定提供方进行校验。必填的 `parent` 提供会话 cwd、谱系与委派深度。可选的 output schema、depth、工具过滤器和 persona 需要对应的能力 flag 匹配。不支持的 schema 在启动时即失败；进程内后端将 filter 和 persona 的作用域限定在子 agent 创建阶段，并通过强制 capture 工具实现所支持的 object-rooted schema。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* What a caller asks for when starting a subagent. The tool layer builds this
|
||||
* from the model's `{ description, prompt }` plus its own config; the service
|
||||
* validates {@link SubagentCapabilities} against the named provider, then
|
||||
* passes it to {@link SubagentProvider.start}.
|
||||
* What a caller asks for when starting a ONE-SHOT subagent. The tool layer
|
||||
* builds this from the model's `{ description, prompt }` plus its own config;
|
||||
* the service validates {@link SubagentCapabilities} against the named provider
|
||||
* and resolves the durable descriptor before dispatching to
|
||||
* {@link SubagentProvider.start}.
|
||||
*/
|
||||
interface SubagentStartRequest {
|
||||
/** Optional short display label persisted with a session-backed child. */
|
||||
readonly label?: string
|
||||
/** Content delivered as the child's user message. */
|
||||
readonly prompt: ContentBlock[]
|
||||
/**
|
||||
@@ -54,8 +59,8 @@ interface SubagentStartRequest {
|
||||
* Cancellation signal from the spawning context (the tool's `exec.signal`).
|
||||
* This is the canonical cancellation channel both before and after startup:
|
||||
* a provider rejects `start()` after cleaning partial resources when it
|
||||
* fires before publication, and cancels a published child when it fires
|
||||
* afterward.
|
||||
* fires before the run is published, and cancels the published run's
|
||||
* remaining turn work when it fires afterward.
|
||||
*/
|
||||
readonly signal: AbortSignal
|
||||
readonly agentOptions?: AgentOptions
|
||||
@@ -93,6 +98,158 @@ interface SubagentStartRequest {
|
||||
|
||||
`signal` 是就绪前后唯一的取消通道。[subagent 组合控制 Agent Note](../../.agents/notes/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)规定 persona、live 全局工具过滤、绝对深度以及「可见性而非权限」的设计理由。
|
||||
|
||||
面向调用方的请求不携带目录格式细节或继续执行状态。`SubagentService.start()` 会在功能检查后解析分离的一次性描述符，再将以下面向提供方的请求传给所选传输；可继续子 agent 绝不会到达 `SubagentProvider.start()`：
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Provider-facing one-shot request after {@link SubagentService.start} resolves
|
||||
* the durable child descriptor.
|
||||
*/
|
||||
interface ResolvedSubagentStartRequest extends SubagentStartRequest {
|
||||
/** Detached descriptor a session-backed provider persists in the child log. */
|
||||
readonly descriptor: SubagentDescriptorData
|
||||
}
|
||||
```
|
||||
|
||||
## 可继续子 agent 与激活
|
||||
|
||||
**可继续后台 subagent** 是一份持久化子 agent 会话（Session），至多关联一个进程内的 **Activation（激活）**——即被重建的子 Agent 的一段驻留纪元（residency epoch）。Activation 不是请求、结果、取消或 Task 边界：它可以执行多个 FIFO 轮次，并在其创建的后代仍在运行期间保持驻留。继续执行管理器负责 activation 准入、直接父级鉴权、实时所有权图、冷恢复（cold resume）与子级优先释放；agent loop 负责一切轮次排序与执行。任何可继续路径都不会创建 Task，也不会创建承载中间结果的包装层。
|
||||
|
||||
```text
|
||||
persisted Session
|
||||
-> optional live Activation
|
||||
-> one retained AgentHandle
|
||||
-> Agent inbox as the only turn FIFO
|
||||
-> zero or more owned child Activations
|
||||
```
|
||||
|
||||
`SubagentService.startContinuable()` 会预留稳定的子 agent id，对版本化的 `subagent/descriptor` payload 建立快照，向指定提供方索取其分离的 `ContinuableCreateSpec`，通过私有的 activation-owner 作用域创建子 Agent，建立任何可继续父级的所有权，并提交初始 prompt。当收件箱（inbox）准入产出消息 id 时，它以 `{ childId, messageId }` resolve——无需等待轮次开始，也无需等待消息进入会话日志。在该准入之前的任何失败都会以两个 id 都不返回的方式 reject，并 dispose 任何已创建的 handle，回滚 Activation 与父级所有权。
|
||||
|
||||
`SubagentService.followup()` 是唯一的继续执行消息操作，其路由仅取决于 Activation 的驻留状态：
|
||||
|
||||
| Activation 状态 | `followup` |
|
||||
|---|---|
|
||||
| `running` | 在同一 Activation 中入队 |
|
||||
| `waiting` | 唤醒同一 Activation |
|
||||
| 无 Activation | 冷恢复一个新的 Activation |
|
||||
|
||||
`running` 表示 Agent 拥有活跃的准入或轮次，或正在唤醒收件箱工作；`waiting` 表示它已停稳，但仍拥有至少一个尚未完成 dispose 的子 Activation；`settled` 表示已停稳且其拥有的每个子级都已 dispose，此时管理器会 dispose `AgentHandle` 并移除该 Activation。管理器根据 Agent 的完全停稳状态与其拥有的子级集合推导这些内部条件，而非维护第二套执行状态机。
|
||||
|
||||
Agent 收件箱是唯一的队列。每条继续执行消息都会成为一个 `Agent.followup()` FIFO 轮次，因此已接受的消息共享同一个可观测顺序，且后续消息无法改变已在进行中的轮次。投递成功会返回被接受的 `MessageId`；既有的 `agent/inbox/enqueue`、`agent/inbox/dequeue` 与 `agent/inbox/discard` 事件仍是消息生命周期的观测点，继续执行层不定义任何 subagent 专属的投递路由。
|
||||
|
||||
后续操作的权限来自确切的在线 Agent 工具上下文。已认证的 Agent 必须是持久化子 agent 在 `SessionHeader.parentSession` 中记录的直接父级。`MessageSource` 与 `senderSessionId` 在准入之后是持久的来源凭据，不授予任何权限；可选的面向模型工具使用 `CoordinatorMessageSource`。
|
||||
|
||||
对于这两种操作，调用方 signal 仅在收件箱接受之前掌管查找、物化与准入。此后管理器独立掌管该 Activation：之后的调用方取消既不会取消已接受的轮次，也不会 dispose 子 agent，并且该 seam 不对外暴露任何 subagent 取消或 steering（中途引导）操作。
|
||||
|
||||
每个 Activation 都拥有自己的 `AgentHandle` 和一个 `ownedChildren: Set<SessionId>`；由于一份会话至多有一个存活 Activation，子会话 id 无需另一个运行时化身引用即可标识存活的子 agent。启动子 agent 或提交源自 parent 的工作，会在子 agent 能够运行之前将其注册到受继续执行管理的父级集合中；只要该集合非空，该父级就无法 settle。顶层或其他非继续执行的 Agent 没有 Activation，处于 waiting 图之外。只有当子 Agent 已停稳、该子 agent 的每个子级都已 dispose、best-effort 的最终会话 flush 结算完毕，且子 agent 的 `AgentHandle` 完成 dispose 之后，才会释放子 agent。
|
||||
|
||||
最终结算会等待 `ctx.sessions.flush(session)`，但会忽略其参与布尔值，因为任意 listener 都无法证明某个持久化后端已存储该状态。rejection 会被记录，但不会使 Activation 失败；管理器仍会 dispose 该 handle 并释放所有权，此后持久化的子 agent 状态在后续恢复时可能缺失或陈旧。管理器卸载会调用内部的管理器全局 drain，关闭准入并 dispose 每片在线森林；`drainContinuableDescendants(parents)` 只关闭由 host 确切拥有的在线 Agent 之下的准入，并 dispose 其可继续后代，而无关森林保持在线。两者都会等待各自作用域内已获准的物化过程，自顶向下传播取消，按 child-first 顺序释放 handle，并且即使个别分支失败也会等待所有选中分支。持久化子会话不受该进程内拆卸的影响。
|
||||
|
||||
```ts type-equiv
|
||||
/** Attribution for a model coordinator's follow-up to one of its children. */
|
||||
interface CoordinatorMessageSource {
|
||||
readonly kind: 'coordinator'
|
||||
/** Session id of the agent whose tool call produced the follow-up. */
|
||||
readonly senderSessionId: SessionId
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Options for following up with one continuable child. */
|
||||
interface SubagentFollowupOptions {
|
||||
/** Durable attribution retained on the delivered message; it grants no authority. */
|
||||
readonly source: MessageSource
|
||||
/** Caller cancellation, owning the operation only until inbox acceptance. */
|
||||
readonly signal: AbortSignal
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Identities returned once a continuable child accepted its initial prompt. */
|
||||
interface ContinuableStart {
|
||||
/** The durable child session id, stable across activations. */
|
||||
readonly childId: SessionId
|
||||
/** The accepted initial prompt's inbox message id. */
|
||||
readonly messageId: MessageId
|
||||
}
|
||||
```
|
||||
|
||||
可选的可继续 child 设置贡献可以在 child 基础组合完成后、Activation 发布前安装限定在作用域内的能力。该注册表按顺序执行且具有事务性：设置失败或被撤销时会回滚未发布的 Activation；child 作用域 dispose 时会释放所有安装；新注册项在下一个 Activation 生效；移除注册项时则会立即撤销每个驻留中的安装。
|
||||
|
||||
`SubagentService.reportFrom()` 通过该扩展 seam 实现报告，无需新增第二条队列或承载结果的 child 包装层。调用由确切的在线 child Agent 授权，调用方不能指定接收方。管理器从 child 的持久化 `parentSession` 中推导唯一接收方，要求该 parent Agent 必须在线，将选中内容封装为一条 `subagent-report` 用户消息，并返回该消息的稳定 `MessageId`。静默投递使用 `Agent.inject()`，不产生 inbox 条目实例或 parent 轮次；唤醒投递使用 `Agent.followup()`，会产生一个普通的后续 parent 轮次。两种模式都不会结束 child 轮次，最终回答也不会隐式报告。
|
||||
|
||||
```ts type-equiv
|
||||
/** Durable attribution for a continuable child's explicit parent report. */
|
||||
interface SubagentReportMessageSource {
|
||||
readonly kind: 'subagent-report'
|
||||
/** Session id of the reporting child. */
|
||||
readonly senderSessionId: SessionId
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Deployment scheduling policy for accepted child reports. */
|
||||
type SubagentReportDelivery = 'quiet' | 'wakeup'
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Options for one continuable child's report to its direct parent. */
|
||||
interface SubagentReportOptions {
|
||||
/** Already-resolved parent scheduling policy. */
|
||||
readonly delivery: SubagentReportDelivery
|
||||
/** Caller cancellation, owning authorization and admission until acceptance. */
|
||||
readonly signal: AbortSignal
|
||||
}
|
||||
```
|
||||
|
||||
提供方只参与准备初始创建 spec，`spawn` 与 `fork` 在此有所不同。其返回的 spec 只携带分离的、提供方专属的创建输入——目前是可选的父级历史种子——不含 Agent、`AgentHandle`、prompt 投递、结果、dispose 或 resume 操作。冷恢复根本不经由提供方分发：管理器折叠通用描述符，通过同一个 activation-owner 作用域调用 `ctx.agents.resume()`，并提交等待中的轮次。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* What the continuation manager asks a provider for while materializing one
|
||||
* continuable child's FIRST activation. The manager has already reserved the
|
||||
* durable child identity and owns every later operation, so this request
|
||||
* carries only what distinguishes a fresh child from one seeded with parent
|
||||
* history.
|
||||
*/
|
||||
interface ContinuableCreateRequest {
|
||||
/** The reserved durable child session id, for provider diagnostics. */
|
||||
readonly sessionId: SessionId
|
||||
/** The delegating parent agent whose history a seeding provider reads. */
|
||||
readonly parent: Agent
|
||||
/**
|
||||
* Caller cancellation, which owns preparation only until the manager accepts
|
||||
* the initial prompt into the child's inbox.
|
||||
*/
|
||||
readonly signal: AbortSignal
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* A provider's detached contribution to one continuable child's creation. This
|
||||
* is DATA, never a capability: it carries no Agent, `AgentHandle`, prompt
|
||||
* delivery, result, disposal, or resume operation, because the continuation
|
||||
* manager owns the child's whole lifecycle after preparation.
|
||||
*/
|
||||
interface ContinuableCreateSpec {
|
||||
/**
|
||||
* Completed-turn prefix of the parent's log to seed the child session with,
|
||||
* or absent for a fresh child. Same durable contract as
|
||||
* `CreateAgentOptions.seed`: contiguous from seq 0, lossless JSON, balanced.
|
||||
*/
|
||||
readonly seed?: readonly SessionEvent[]
|
||||
}
|
||||
```
|
||||
|
||||
描述符（[descriptor.ts](../../packages/subagent/subagent/src/descriptor.ts) 中的 `SubagentDescriptorData`）是每个由会话支撑的 subagent 所使用、按模式判别的持久化身份。两种模式都携带提供方名称。`one-shot` 描述符可以携带调用方拥有的可选显示 `label`；`continuable` 描述符要求以委派 `description` 作为持久化创建标签，并另外对已解析的子 agent `agentOptions.provider`／`model` 与可选的 `persona`／`toolFilter` 建立快照，用于冷恢复。它绝不会对可合并扩展的 `AgentOptions` 对象建立快照，因此无关的扩展值不会破坏继续执行，后续新增组合配置输入则是一次有意的版本更改。描述符省略 `subagentDepth`（冷恢复以持久化 header 中的 `delegationDepth` 作为单调下界）和 `outputSchema`（单次运行或 Activation 的结果契约，而非持久化身份）。
|
||||
|
||||
本地一次性提供方会在子 agent 的初始轮次内、首次请求前追加描述符。继续执行管理器会在任何提供方提供的谱系之后、初始 prompt 获准之前追加描述符；`header.seedLength` 仍是 fork 谱系边界，因此描述符查找会读取子 agent 自身的后缀。该事件只进入日志：不含 `surfaceOp`，绝不进入模型历史，并由仅追加日志跨压缩保留。格式错误的当前版本描述符属于损坏；本运行时无法对不受支持的版本进行分类。
|
||||
|
||||
## 持久化枚举：`listChildren()` 与 `SubagentListEntry`
|
||||
|
||||
`SubagentService.listChildren(parentSessionId)` 从一次 `ctx.sessionQuery.traceSession()` 观测中枚举 parent 直接且由会话支撑的 subagent，而不会加载或恢复任何 Agent。会话谱系的范围比 subagent 身份更广——普通 fork 也会共享 `parentSession`——因此，child 自身后缀中恰好一个受支持的 `subagent/descriptor` 事件（位于 `seedLength` 之后，避免 fork seed 泄漏祖先描述符）是唯一的 subagent 判别信息。`SessionHeader.origin: 'subagent'` 只是在发布前写入的粗粒度产品导航分类器；它可以隐藏重复的侧边栏行，却不能证明描述符有效、child 可恢复或操作已获授权。结果是一个按追踪结果中 `createdAt`、再按 id 排列候选顺序的 `SubagentListEntry[]`：有效描述符生成带有 `mode: 'one-shot' | 'continuable'` 和 `activity: 'running' | 'inactive'` 的 `child` 条目；可继续条目始终携带 `label`，一次性条目则只在启动调用方提供展示元数据时携带该字段。逐 child 检查失败生成 `diagnostic` 条目（`corrupt`、`unsupported` 或 `unavailable`），因此一个损坏的 sibling 不会隐藏健康 child；缺少描述符则不生成条目。活动状态只表示逻辑记录是否在 `ctx.sessions` 中存活，而不表示结果或可恢复性。UI 等服务消费方可以展示两种模式，并为无标签的一次性 child 选择回退展示；面向模型的 `list_agents` 适配器（[dsh-tool-subagent-control](../../packages/subagent/tool-subagent-control) 中可单独加载的 `/list-agents` 插件）则只保留可继续条目，并将活动状态映射到现有的 `running`／`complete` 词汇。构建初始追踪时的失败会让整个调用失败——只有得到可信候选集后才开始逐 child 隔离。服务将 `sessionQuery` 保持为按 id 继续执行时的可选依赖：缺少该服务时，`listChildren()` 抛出 `SubagentError`，并携带错误码 `SUBAGENT_CONTROL_SESSION_QUERY_UNAVAILABLE`；列表工具则在插件加载时要求 `ctx.subagents` 与 `ctx.sessionQuery`。枚举不会查询继续执行管理器的 Activation map、Agent 注册表或提供方可用性；`send_message` 仍是消息送达时的权威操作，列表中的运行中可继续 child 仍可能因所有权冲突而拒绝投递。
|
||||
|
||||
## 终态结果：`SubagentResult`
|
||||
|
||||
一次 run 的最终产出，由 `SubagentRun.result` resolve。`structured` 仅在请求了 `outputSchema` 且成功满足时才存在；请求 schema 不保证一定能得到它，当子 agent 失败或结束时未产出有效 capture 时，提供方可能返回 `stopReason: 'error'`。非 `completed` 的 `stopReason` 意味着 `output` 可能不完整——消费方将其映射为 `isError` 的工具结果，而非将部分输出报告为成功。
|
||||
@@ -140,17 +297,19 @@ interface SubagentStopReasonMap {
|
||||
}
|
||||
```
|
||||
|
||||
<a id="a-live-run-subagentrun"></a>
|
||||
## 单次 run：`SubagentRun`
|
||||
|
||||
## 活跃 run：`SubagentRun`
|
||||
|
||||
`SubagentRun` 是消费方持有的、指向一个就绪子 agent 的句柄。消费方 await `result` 并始终 dispose（资源释放）该 run，直至其完全停稳。子 agent 失败时以非 completed 的 stop reason resolve；只有不可表示的基础设施故障才会 reject。可选的 `sendMessage` 和 `resume` 方法通过自身的存在来公布运行时能力。
|
||||
`SubagentRun` 是消费方持有的、指向一个已发布单次子 agent 的句柄——一次可 dispose 的前台委派，只有一个结果，绝不是持久化子 agent handle。发布后的提示词提交、轮次工作与基础设施故障归 `result` 所有。消费方 await 该结果并始终 dispose 该 run，直至完全停稳。子 agent 失败时以非 completed 的 stop reason resolve；只有无法表示的基础设施故障才会 reject。run 没有 steering，也没有 resume：可继续对话根本没有 run，因为继续执行管理器直接持有它们的 `AgentHandle`，并通过子 agent 自己的收件箱为每个轮次排序。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Child handle returned only after readiness. Consumers await {@link result} and must always
|
||||
* {@link dispose} to cancel remaining work and reach quiescence. Optional methods are runtime
|
||||
* capability discovery; narrow their presence before calling.
|
||||
* ONE-SHOT child handle returned after publication. Prompt submission, turn
|
||||
* work, and infrastructure faults after that boundary belong to {@link result}.
|
||||
* Consumers await that result and must always {@link dispose} to cancel
|
||||
* remaining work and reach quiescence. A run is one disposable foreground
|
||||
* delegation with one result; continuable conversations have no run — the
|
||||
* continuation manager holds their `AgentHandle` directly and orders every
|
||||
* turn through the child's own inbox.
|
||||
*/
|
||||
interface SubagentRun {
|
||||
/**
|
||||
@@ -169,8 +328,8 @@ interface SubagentRun {
|
||||
* Resolves with the child's terminal {@link SubagentResult} when the run
|
||||
* settles. Does NOT reject on a child-level failure — a model/transport
|
||||
* failure resolves with `stopReason: 'error'` so the consumer maps it to an
|
||||
* `isError` tool result. Rejects only on an infrastructure fault the seam
|
||||
* cannot represent as a stop reason.
|
||||
* `isError` tool result. Rejects on an infrastructure fault the seam cannot
|
||||
* represent as a stop reason.
|
||||
*/
|
||||
readonly result: Promise<SubagentResult>
|
||||
/**
|
||||
@@ -178,24 +337,16 @@ interface SubagentRun {
|
||||
* Idempotent.
|
||||
*/
|
||||
dispose(): Promise<void>
|
||||
/**
|
||||
* OPTIONAL (steering capability): send additional content to the running
|
||||
* child between steps. Present only on providers that support live steering.
|
||||
*/
|
||||
sendMessage?(content: ContentBlock[]): void
|
||||
/**
|
||||
* OPTIONAL (resume capability): send a follow-up task to a settled child,
|
||||
* continuing its session, and return a fresh run for the continuation.
|
||||
*/
|
||||
resume?(content: ContentBlock[]): Promise<SubagentRun>
|
||||
}
|
||||
```
|
||||
|
||||
本地 run 必须在 `start()` fulfill 前发布一个普通子 agent/会话，将该子会话 id 作为 `SubagentRun.id` 返回，以 `localAgent` 暴露确切子 agent，并在子 agent 的 `parentSession` header 中记录 `request.parent.session.id`。运行时所有权可以把子 agent 放在 parent、提供方或 root 作用域下。远程提供方则返回 parent 作用域的生命周期 id 与 `localAgent: undefined`。
|
||||
本地单次 run 必须在 `start()` fulfill 之前发布一个普通子 agent／会话，将该子会话 id 作为 `SubagentRun.id` 返回，以 `localAgent` 暴露确切的子 agent，在子 agent 的 `parentSession` header 中记录 `request.parent.session.id`，并在子 agent 的初始轮次内、首次请求前追加已解析的描述符。运行时所有权可以把子 agent 放在 parent、提供方或 root 作用域下。远程提供方则返回 parent 作用域的生命周期 id 与 `localAgent: undefined`；由于没有本地 child Session，它不会出现在基于追踪的枚举结果中。
|
||||
|
||||
<a id="the-provider-seam-subagentprovider"></a>
|
||||
|
||||
## 提供方 seam：`SubagentProvider`
|
||||
|
||||
每个提供方是一个具名的子 agent 传输层，多个提供方可以共存。服务在 `start()` 之前校验请求的启动时能力。`inheritsParentContext` 仅描述对话种子注入（`fork`：true；`spawn` 和 `acp`：false），使消费方能生成准确的面向模型的措辞，而不暗示继承了工具、服务或权限。
|
||||
每个提供方都是一个具名的子 agent 传输层，多个提供方可以共存。服务在 `start()` 之前校验请求的启动时能力，并拒绝在没有 `prepareContinuable` 的提供方上发起可继续 start。`inheritsParentContext` 仅描述对话种子注入（`fork`：true；`spawn` 和 `acp`：false），使消费方能生成准确的面向模型措辞，而不暗示继承了工具、服务或权限。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -215,22 +366,38 @@ interface SubagentProvider {
|
||||
*/
|
||||
readonly inheritsParentContext: boolean
|
||||
/**
|
||||
* Establish a child and return its handle only after publication. The
|
||||
* service has already validated that every requested start-time capability
|
||||
* is supported, so an implementation may assume e.g. `request.maxDepth` is
|
||||
* honorable when present. If setup fails or `request.signal` aborts before
|
||||
* fulfillment, the provider owns and cleans all partial resources before this
|
||||
* promise rejects. Ownership transfers to the caller only on fulfillment.
|
||||
* Establish a ONE-SHOT child and return its handle after publication.
|
||||
* The service has already validated that every requested start-time
|
||||
* capability is supported and resolved `request.descriptor`, so a
|
||||
* session-backed implementation appends that descriptor inside the child's
|
||||
* initial turn. Before fulfillment, the provider owns setup and cleans any
|
||||
* unpublished partial resources before rejecting. Ownership transfers on
|
||||
* fulfillment; subsequent turn or infrastructure failure settles through
|
||||
* the returned run.
|
||||
*/
|
||||
start(request: SubagentStartRequest): Promise<SubagentRun>
|
||||
start(request: ResolvedSubagentStartRequest): Promise<SubagentRun>
|
||||
/**
|
||||
* OPTIONAL (continuable-creation capability): contribute the detached
|
||||
* creation inputs that distinguish this provider's continuable children —
|
||||
* today only whether the child session is seeded with parent history. Method
|
||||
* presence IS the capability: the service rejects continuable starts on
|
||||
* providers without it, while a provider that has it may still serve
|
||||
* ordinary one-shot delegations.
|
||||
*
|
||||
* This is the provider's ONLY participation in a continuable child. The
|
||||
* continuation manager owns identity reservation, composition, Agent
|
||||
* creation, prompt delivery, cold resume, ownership, and disposal, so a
|
||||
* provider never sees the child's Agent, handle, turns, or teardown.
|
||||
*/
|
||||
prepareContinuable?(request: ContinuableCreateRequest): Promise<ContinuableCreateSpec>
|
||||
}
|
||||
```
|
||||
|
||||
`start()` 仅在 run 就绪时 fulfill。服务铸造唯一 `runId`，从提供方的确切 `localAgent` 快照 `local`，观察结果，emit `subagent/start`，并返回同一个 run；rejection 意味着提供方已清理，且不会 emit 生命周期事件对。配对的 `subagent/end` 携带相同标识与最终输出或基础设施失败。两个事件都仅用于观察，每个 listener 异常都会被独立隔离。
|
||||
提供方的 `start()` 会以已发布的 run fulfill。服务铸造唯一的 `runId`，从提供方确切的 `localAgent` 快照 `local`，观察结果，emit `subagent/start`，并返回同一个 run；`start()` rejection 意味着未发布资源已清理，且不会 emit 生命周期事件对，而发布后的结果 rejection 会结束已经 emit 的事件对。每个可继续 Activation 都会为其驻留纪元 emit 相同的仅观察事件对，因此一次冷恢复就是一段拥有自己 `runId` 的新纪元。配对的 `subagent/end` 携带相同标识与最终输出或基础设施失败。两个事件都仅用于观察，且会隔离各自的 listener 异常。其中的 `provider` 字段是 run 或 Activation 时段的来源信息，并不声明该 edge 发出时提供方仍处于注册状态。
|
||||
|
||||
## 进程内后端：深度与种子
|
||||
|
||||
spawn 和 fork 后端通过 `parent.ctx` 创建一个普通 agent，将取消信号传入核心创建流程，并通过 `AgentHandle` 进行 dispose。移除提供方会阻止新的 start，但不会撤销已接受的 run。每个子 agent 获得一个新的扁平作用域，而非继承父级注册。深度与 fork 种子注入复用既有的 agent 和会话词汇：
|
||||
spawn 和 fork 后端通过 `parent.ctx` 创建一个普通的单次 agent，将取消信号传入核心创建流程，并通过 `AgentHandle` 进行 dispose；而可继续子 agent 则由继续执行管理器通过其自己的 activation-owner 作用域创建。移除提供方会阻止新的 start，但不会撤销已接受的 run。每个子 agent 获得一个新的扁平作用域，而非继承父级注册。深度与 fork 种子注入复用既有的 agent 和会话词汇：
|
||||
|
||||
- **委派深度**由持久 `SessionHeader.delegationDepth` 与可合并扩展的运行时字段 `AgentOptions.subagentDepth` 共同表示；缺失表示顶层深度为零，存在的较大值具有权威性。两个字段都归该 seam 所有——循环既不设置也不读取它们——因此进程内子 agent 会持久保存 parent 深度 + 1，恢复无法降低深度，而且每次 start 都会拒绝超出安全整数域、或高于已定义绝对 `request.maxDepth` 上限的派生深度。
|
||||
- **Fork 种子注入**使用 `CreateAgentOptions.seed`（一个 `SessionEvent[]` 前缀，经由 `AgentLoop.createAgent` → `ctx.sessions.prepare({ seed })` 传递，与 `resume` 使用的原语相同）。fork 后端传入父级日志的一段*平衡的已完成轮次前缀*——父级事件直到并包括其最后一个 `turn/end`——因此种子从 0 连续，[invariants](../../packages/support/invariants) 回放可以接受它（进行中的、未平衡的轮次被排除在外）。
|
||||
- **委派深度**由持久 `SessionHeader.delegationDepth` 与可合并扩展的运行时字段 `AgentOptions.subagentDepth` 共同表示；缺失表示顶层深度为零，存在的较大值具有权威性。两个字段都归该 seam 所有——循环既不设置也不读取它们——因此进程内子 agent 会持久保存 parent 深度 + 1，冷恢复无法降低深度，而且每次 start 都会拒绝超出安全整数域、或高于已定义绝对 `request.maxDepth` 上限的派生深度。
|
||||
- **Fork 种子注入**使用 `CreateAgentOptions.seed`（一个 `SessionEvent[]` 前缀，经由 `AgentLoop.createAgent` → `ctx.sessions.prepare({ seed })` 传递，与 `ctx.agents.resume()` 使用的原语相同）。fork 后端传入父级日志的一段*平衡的已完成轮次前缀*——父级事件直到并包括其最后一个 `turn/end`——因此种子从 0 连续，[invariants](../../packages/support/invariants) 回放可以接受它（进行中的、未平衡的轮次被排除在外）。
|
||||
|
||||
@@ -1,6 +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
|
||||
system-prompt.md: 63a750c74300b4353f132d3dae9da52a10631f23
|
||||
system-prompt.zh.md: 3f7ab9aee5743616f00e95e81fb9a3a4af2c6e8a
|
||||
# pnpm run verify-translation-pairing --write docs/core-data-structures/system-prompt.md
|
||||
system-prompt.md: 5abb8f46c13045c7d37bbe12ecf6c3744ee063b5
|
||||
system-prompt.zh.md: 1088b20ba4289ad5912a193eead39d069c1a6e17
|
||||
|
||||
@@ -60,3 +60,23 @@ interface PromptSection {
|
||||
readonly text: string | ((context: AssembleContext) => string)
|
||||
}
|
||||
```
|
||||
|
||||
## Dynamic prompt context
|
||||
|
||||
`PromptContext` is the cache-safe counterpart to `PromptSection`. The assembly resolves and orders these contributions, while agent-loop logs their complete current snapshot after retained model history only when it changed or compaction removed it.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* One dynamic model-context contribution. Unlike a {@link PromptSection}, its
|
||||
* rendered text is materialized as a durable user-role snapshot at the request
|
||||
* tail, so changing runtime state preserves the stable system/history prefix.
|
||||
*/
|
||||
interface PromptContext {
|
||||
/** Unique name — a duplicate registration throws (see {@link SystemPrompt.context}). */
|
||||
readonly name: string
|
||||
/** Contexts are joined in ascending order, independently of system-section order. */
|
||||
readonly order: number
|
||||
/** Static text or a provider evaluated for each assembly. Empty text contributes nothing. */
|
||||
readonly text: string | ((context: AssembleContext) => string)
|
||||
}
|
||||
```
|
||||
|
||||
@@ -60,3 +60,23 @@ interface PromptSection {
|
||||
readonly text: string | ((context: AssembleContext) => string)
|
||||
}
|
||||
```
|
||||
|
||||
## 动态提示词上下文
|
||||
|
||||
`PromptContext` 是与 `PromptSection` 对应的缓存安全结构。组装会解析这些贡献并排序；agent loop（智能体循环）仅在完整当前快照发生变化或被压缩（compaction）移除时，才会将其记录在保留的模型历史之后。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* One dynamic model-context contribution. Unlike a {@link PromptSection}, its
|
||||
* rendered text is materialized as a durable user-role snapshot at the request
|
||||
* tail, so changing runtime state preserves the stable system/history prefix.
|
||||
*/
|
||||
interface PromptContext {
|
||||
/** Unique name — a duplicate registration throws (see {@link SystemPrompt.context}). */
|
||||
readonly name: string
|
||||
/** Contexts are joined in ascending order, independently of system-section order. */
|
||||
readonly order: number
|
||||
/** Static text or a provider evaluated for each assembly. Empty text contributes nothing. */
|
||||
readonly text: string | ((context: AssembleContext) => string)
|
||||
}
|
||||
```
|
||||
|
||||
@@ -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/tools.md
|
||||
tools.md: dad7f7421caa94940801407fd4ef7fd936eb05c9
|
||||
tools.zh.md: 8386e5870e665e90ee0dbada8cb98084281001a7
|
||||
tools.md: acaf5d32dd5481aec495ac49f727c9b64f25211e
|
||||
tools.zh.md: 5c39226fdf5d1406dab7383d40227c26ff1e447c
|
||||
|
||||
@@ -200,20 +200,23 @@ interface ToolExecutionInput {
|
||||
}
|
||||
```
|
||||
|
||||
A tool body receives the runtime extension. `deferContext()` is the composite-tool channel: it records nested-dispatch context without injecting inside the still-open outer call.
|
||||
A tool body receives the runtime extension. `deferContext()` attaches context to the execution's own result — the composite-tool nested-dispatch channel, also usable by a leaf tool minting a plugin-sourced instruction — without injecting inside the still-open outer call.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Runtime context handed to a tool implementation after the registry has
|
||||
* accepted a {@link ToolExecution}. A composite tool uses
|
||||
* {@link deferContext} to ferry context produced by nested dispatches back to
|
||||
* the outer result; the loop appends it only after the outer `tool/result`.
|
||||
* accepted a {@link ToolExecution}. {@link deferContext} attaches context to
|
||||
* this execution's own result — a composite tool ferries nested-dispatch
|
||||
* context back to the outer result, and a leaf tool may mint a fresh
|
||||
* plugin-sourced instruction; the loop appends it only after the
|
||||
* `tool/result`.
|
||||
*/
|
||||
interface ToolRunContext extends ToolExecution {
|
||||
/**
|
||||
* Defer one nested-dispatch context until this tool's final result reaches
|
||||
* the agent loop. Contexts retain their individual source and metadata and
|
||||
* are emitted in call order.
|
||||
* Defer one context — typically a nested-dispatch context ferried by a
|
||||
* composite tool, or a fresh plugin-sourced instruction — until this tool's
|
||||
* final result reaches the agent loop. Contexts retain their individual
|
||||
* source and metadata and are emitted in call order.
|
||||
*/
|
||||
deferContext(context: UserMessage): void
|
||||
/**
|
||||
@@ -447,8 +450,8 @@ type ObjectJsonSchema = JsonSchemaNode & { type: 'object' }
|
||||
How a tool wants its call shown in a UI (an editor tool-call card, a CLI log line), provider-neutral so a tool describes itself without depending on any client protocol. `presentCall`/`presentResult` return a **`card`-tagged render intent** — a discriminated union a UI bridge switches on:
|
||||
|
||||
- `ToolCallView` (pending): `{ card: 'generic', title, kind?, rawInput?, content?, locations? }` (the default card; `locations` is `{ path, line? }[]` files the call reads/modifies, for editor follow-along), `{ card: 'terminal', title, description?, cwd? }` (a shell command → a terminal card), or `{ card: 'diff', title, diffs, locations? }` (a file create/modify → an inline diff card; `diffs` is `{ path, oldText, newText }[]`, `oldText: null` for a new file).
|
||||
- `ToolResultView` (completed): `{ card: 'generic', title?, content? }`, `{ card: 'terminal', title?, output?, exitCode?, signal? }` (the captured run output + exit; a capable UI shows an exit-status pill, while another may derive a fenced ` ```console ` fallback), or `{ card: 'diff', title?, diffs }` (a completed file mutation → the change to show, typically the applied hunks with context lines computed from the before/after content, or a whole-file diff when there is no before-image). Completed views replace pending views, so mutation tools return a diff result even when it duplicates the call-time snippet.
|
||||
- `ToolResultView` (completed): `{ card: 'generic', title?, content? }`, `{ card: 'terminal', title?, output?, exitCode?, signal? }` (the captured run output + exit; a capable UI shows an exit-status pill, while another may derive a fenced ` ```console ` fallback), `{ card: 'diff', title?, diffs }` (a completed file mutation → the change to show, typically the applied hunks with context lines computed from the before/after content, or a whole-file diff when there is no before-image), `{ card: 'search', shape, title?, truncated, total, … }` (a completed discovery search → grouped-by-file matches for `shape: 'matches'` (grep) or a flat path list for `shape: 'paths'` (glob); `truncated`/`total` report whether the inline result was capped so a UI never presents a partial result as complete; the view carries no result text — a UI without a search card falls back to the raw result content), `{ card: 'read', title?, path, offset, lines, totalLines, lang?, content? }` (a completed file read → a line-numbered, optionally syntax-highlighted code view; `offset` is the 1-based first line the window requested, kept even when `lines` is empty; `lang` is a language hint from the extension, and `content` is the envelope-stripped text a UI without read support falls back to), or `{ card: 'web', kind: 'search' | 'fetch', title?, … }` (a completed web retrieval; `kind: 'search'` carries the structured `sources`/`answer?`/`truncated`, `kind: 'fetch'` carries `url`/`statusCode`/`truncated`, and a UI without the `web` capability falls back to the raw result content — the body is not duplicated into the view). Completed views replace pending views, so mutation tools return a diff result even when it duplicates the call-time snippet; a search and a web retrieval have no `card` call-time analogue (their pending state stays a generic card, since the structured result exists only after `execute`).
|
||||
|
||||
`ToolCallKind` (`'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other'`) picks an icon on a generic card. `FileLocation` (`{ path, line? }`) and `FileDiff` (`{ path, oldText, newText }`) are the shared file-card vocabulary. The design is pinned in [the render-intent-union Agent Note](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md); the TUI and host/client runtime project this neutral vocabulary into their own views.
|
||||
`ToolCallKind` (`'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other'`) picks an icon on a generic card. `FileLocation` (`{ path, line? }`), `FileDiff` (`{ path, oldText, newText }`), and `ReadFileLine` (`{ number, text }`, one 1-based numbered line of a read window) are the shared file-card vocabulary. The design is pinned in [the render-intent-union Agent Note](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md); the TUI and host/client runtime project this neutral vocabulary into their own views.
|
||||
|
||||
The full presentation field docs live in [`packages/core/tools/src/presentation.ts`](../../packages/core/tools/src/presentation.ts). The `bash` schema and executor are on [bash.md](bash.md); generic background controls are on [tasks.md](tasks.md).
|
||||
|
||||
@@ -200,20 +200,23 @@ interface ToolExecutionInput {
|
||||
}
|
||||
```
|
||||
|
||||
工具函数体接收运行时扩展。`deferContext()` 是组合工具的通道：它记录嵌套分派产生的上下文，而不会在外层调用尚未结束时注入这些上下文。
|
||||
工具函数体接收运行时扩展。`deferContext()` 把上下文附着到本次执行自己的结果上——既是组合工具转运嵌套分派上下文的通道，也可供叶子工具铸造插件来源指令——而不会在外层调用尚未结束时注入这些上下文。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Runtime context handed to a tool implementation after the registry has
|
||||
* accepted a {@link ToolExecution}. A composite tool uses
|
||||
* {@link deferContext} to ferry context produced by nested dispatches back to
|
||||
* the outer result; the loop appends it only after the outer `tool/result`.
|
||||
* accepted a {@link ToolExecution}. {@link deferContext} attaches context to
|
||||
* this execution's own result — a composite tool ferries nested-dispatch
|
||||
* context back to the outer result, and a leaf tool may mint a fresh
|
||||
* plugin-sourced instruction; the loop appends it only after the
|
||||
* `tool/result`.
|
||||
*/
|
||||
interface ToolRunContext extends ToolExecution {
|
||||
/**
|
||||
* Defer one nested-dispatch context until this tool's final result reaches
|
||||
* the agent loop. Contexts retain their individual source and metadata and
|
||||
* are emitted in call order.
|
||||
* Defer one context — typically a nested-dispatch context ferried by a
|
||||
* composite tool, or a fresh plugin-sourced instruction — until this tool's
|
||||
* final result reaches the agent loop. Contexts retain their individual
|
||||
* source and metadata and are emitted in call order.
|
||||
*/
|
||||
deferContext(context: UserMessage): void
|
||||
/**
|
||||
@@ -447,8 +450,8 @@ type ObjectJsonSchema = JsonSchemaNode & { type: 'object' }
|
||||
工具希望其调用在 UI 中如何呈现（编辑器工具调用卡片、CLI（命令行界面）日志行），提供方无关，使工具在不依赖任何客户端协议的情况下描述自身。`presentCall`/`presentResult` 返回一个 **`card` 标签的渲染意图**——一个可辨识联合类型，UI 桥接层据此分发：
|
||||
|
||||
- `ToolCallView`（待执行）：`{ card: 'generic', title, kind?, rawInput?, content?, locations? }`（默认卡片；`locations` 是 `{ path, line? }[]`，表示调用读取/修改的文件，供编辑器跟随）、`{ card: 'terminal', title, description?, cwd? }`（shell 命令→终端卡片）、或 `{ card: 'diff', title, diffs, locations? }`（文件创建/修改→行内 diff 卡片；`diffs` 是 `{ path, oldText, newText }[]`，新文件时 `oldText: null`）。
|
||||
- `ToolResultView`（已完成）：`{ card: 'generic', title?, content? }`、`{ card: 'terminal', title?, output?, exitCode?, signal? }`（捕获的运行输出 + 退出状态；有能力的 UI 显示退出状态标签，其他 UI 可以派生围栏 ` ```console ` 回退）、或 `{ card: 'diff', title?, diffs }`（已完成的文件变更→要展示的变更，通常是从变更前后内容计算出带上下文行的已应用 hunk，或在没有前像时的整文件 diff）。已完成视图会替换待执行视图，因此变更工具即使与调用时的片段重复也要返回 diff 结果。
|
||||
- `ToolResultView`（已完成）：`{ card: 'generic', title?, content? }`、`{ card: 'terminal', title?, output?, exitCode?, signal? }`（捕获的运行输出 + 退出状态；有能力的 UI 显示退出状态标签，其他 UI 可以派生围栏 ` ```console ` 回退）、`{ card: 'diff', title?, diffs }`（已完成的文件变更→要展示的变更，通常是从变更前后内容计算出带上下文行的已应用 hunk，或在没有前像时的整文件 diff）、`{ card: 'search', shape, title?, truncated, total, … }`（已完成的发现型搜索→`shape: 'matches'`（grep）为按文件分组的匹配，`shape: 'paths'`（glob）为扁平路径列表；`truncated`/`total` 报告内联结果是否被截断，使 UI 永不把部分结果当作完整结果呈现；该视图不携带结果文本——无 search 卡片的 UI 回退到原始结果内容）、`{ card: 'read', title?, path, offset, lines, totalLines, lang?, content? }`（已完成的文件读取→带行号、可选语法高亮的代码视图；`offset` 是窗口请求的 1-based 起始行，即使 `lines` 为空也保留；`lang` 是从扩展名推得的语言提示，`content` 是无读取能力的 UI 回退时使用的去信封文本）、或 `{ card: 'web', kind: 'search' | 'fetch', title?, … }`（已完成的 web 检索；`kind: 'search'` 携带结构化的 `sources`/`answer?`/`truncated`，`kind: 'fetch'` 携带 `url`/`statusCode`/`truncated`，不具备 `web` 能力的 UI 回退到原始结果内容——正文不会重复进视图）。已完成视图会替换待执行视图，因此变更工具即使与调用时的片段重复也要返回 diff 结果；搜索和 web 检索都没有 `card` 的调用时对应视图（其 pending 状态保持为 generic 卡片，因为结构化结果只在 `execute` 之后才存在）。
|
||||
|
||||
`ToolCallKind`（`'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other'`）用于为通用卡片选择图标。`FileLocation`（`{ path, line? }`）与 `FileDiff`（`{ path, oldText, newText }`）是共享的文件卡片词汇。该设计由[渲染意图联合类型 Agent Note（agent 决策记录）](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md)固定；TUI 和 host/client 运行时将这套中性词汇投影为各自的视图。
|
||||
`ToolCallKind`（`'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other'`）用于为通用卡片选择图标。`FileLocation`（`{ path, line? }`）、`FileDiff`（`{ path, oldText, newText }`）与 `ReadFileLine`（`{ number, text }`，读取窗口中一行带 1-based 行号的内容）是共享的文件卡片词汇。该设计由[渲染意图联合类型 Agent Note（agent 决策记录）](../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md)固定；TUI 和 host/client 运行时将这套中性词汇投影为各自的视图。
|
||||
|
||||
完整的展示字段文档见 [`packages/core/tools/src/presentation.ts`](../../packages/core/tools/src/presentation.ts)。`bash` schema 与执行器见 [bash.md](bash.md)；通用后台控制见 [tasks.md](tasks.md)。
|
||||
|
||||
@@ -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/user-interaction.md
|
||||
user-interaction.md: db6ac5010ada9d02319bf148566792659711d2e4
|
||||
user-interaction.zh.md: a8306b421a03563ba9ae2ee48d04898d00eb668e
|
||||
user-interaction.md: 16478168c8fcfeafbd3fdbbf30e732de81a3a8dd
|
||||
user-interaction.zh.md: 7c8baaf189d759ca609c1d51652120f973ae48b6
|
||||
|
||||
@@ -20,6 +20,30 @@ interface AskUserQuestionOption {
|
||||
}
|
||||
```
|
||||
|
||||
## Presentation intent
|
||||
|
||||
`AskUserQuestionIntent` is the optional declaration that a question IS a decision of a known shape. It is tagged on `kind` so intents can be added; a UI that does not recognise a tag renders the generic option list. An intent shapes presentation only — a UI honouring it answers with the same option labels a generic UI would send, so the caller reads one answer shape either way. `approve` names the affirmative option instead of relying on option order. `ask()` rejects the two assertions no type can carry: an `approve` naming none of its own question's options, and an intent on a question with no `detail`.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* A caller-declared presentation intent: the question IS a decision of this
|
||||
* shape, so a UI that recognises the tag may present it as such instead of as a
|
||||
* generic option list. Tagged so further intents can be added; a UI that does
|
||||
* not know a tag renders the generic flow, and the answer encoding is identical
|
||||
* either way — an intent shapes presentation only, never the protocol.
|
||||
*/
|
||||
type AskUserQuestionIntent = {
|
||||
/** A plan submitted for review: `detail` is the plan markdown `ask()` requires, and the decision approves or declines it. */
|
||||
kind: 'plan-review'
|
||||
/**
|
||||
* The option label that approves the plan; every other option declines it.
|
||||
* Named rather than positional so no UI infers the verdict from option order.
|
||||
* An `approve` naming no option of its own question is rejected at `ask()`.
|
||||
*/
|
||||
approve: string
|
||||
}
|
||||
```
|
||||
|
||||
## Question item
|
||||
|
||||
`AskUserQuestionItem` is one question in a request. The caller supplies a stable `id`, which is echoed back with the answer so batched questions remain routable. Optional `detail` carries supporting text that providers render with the question but keep out of selectable option labels.
|
||||
@@ -39,6 +63,8 @@ interface AskUserQuestionItem {
|
||||
options?: AskUserQuestionOption[]
|
||||
/** Whether more than one option may be selected. Defaults to single-select. */
|
||||
multiSelect?: boolean
|
||||
/** Optional presentation intent for capable UIs; absent asks for the generic option list. */
|
||||
intent?: AskUserQuestionIntent
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
@@ -20,6 +20,30 @@ interface AskUserQuestionOption {
|
||||
}
|
||||
```
|
||||
|
||||
## 呈现意图
|
||||
|
||||
`AskUserQuestionIntent` 是一项可选声明：某个问题本身就是一次已知形状的决定。它按 `kind` 打标签，因此意图可以扩充；不认识某个标签的 UI 渲染通用选项列表。意图只塑造呈现 —— 遵循它的 UI 回答的仍是通用 UI 会发送的那些 option label，因此调用方两种情况下读到的都是同一种回答形态。`approve` 指名肯定选项，而不依赖选项顺序。有两项断言是任何类型都承载不了的，`ask()` 会拒绝它们：`approve` 未命中该问题自身的任一选项，以及意图落在没有 `detail` 的问题上。
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* A caller-declared presentation intent: the question IS a decision of this
|
||||
* shape, so a UI that recognises the tag may present it as such instead of as a
|
||||
* generic option list. Tagged so further intents can be added; a UI that does
|
||||
* not know a tag renders the generic flow, and the answer encoding is identical
|
||||
* either way — an intent shapes presentation only, never the protocol.
|
||||
*/
|
||||
type AskUserQuestionIntent = {
|
||||
/** A plan submitted for review: `detail` is the plan markdown `ask()` requires, and the decision approves or declines it. */
|
||||
kind: 'plan-review'
|
||||
/**
|
||||
* The option label that approves the plan; every other option declines it.
|
||||
* Named rather than positional so no UI infers the verdict from option order.
|
||||
* An `approve` naming no option of its own question is rejected at `ask()`.
|
||||
*/
|
||||
approve: string
|
||||
}
|
||||
```
|
||||
|
||||
## 问题条目
|
||||
|
||||
`AskUserQuestionItem` 是请求中的一个问题。调用方提供稳定的 `id`，它会随答案原样返回，使批量问题仍可路由。可选的 `detail` 携带辅助文本；提供方会将其随问题渲染，但不会放入可选 option label。
|
||||
@@ -39,6 +63,8 @@ interface AskUserQuestionItem {
|
||||
options?: AskUserQuestionOption[]
|
||||
/** Whether more than one option may be selected. Defaults to single-select. */
|
||||
multiSelect?: boolean
|
||||
/** Optional presentation intent for capable UIs; absent asks for the generic option list. */
|
||||
intent?: AskUserQuestionIntent
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
Reference in New Issue
Block a user