diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml index cc25329fed..01334b2d8b 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md -2026-07-30-session-end-seed-log-boundary.md: 268646e192d0b8e0a5dde03957a18ef155b7038e -2026-07-30-session-end-seed-log-boundary.zh.md: dca87e16de5e567ff85d2b32b8243f76ebed1c4a +2026-07-30-session-end-seed-log-boundary.md: ca6145f3ce404b88d2a144483c6f1145fe0a9a7e +2026-07-30-session-end-seed-log-boundary.zh.md: d492c4ac5f39328e75d991b285004e2d19c56283 diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md index 268646e192..ca6145f3ce 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md @@ -52,4 +52,4 @@ Cost: a seeded session's log is one event longer, including an empty resumed log `session/end-seed` joins the on-disk vocabulary. Under the pre-release stance (`SESSION_FORMAT_VERSION` pinned at `0`, no compatibility promise) older logs simply lack it, and a log without a boundary correctly classifies nothing as constructor-seed history. -Not built here: no plugin reads the boundary yet. Wiring the compaction seam's staleness check to it is the follow-up that motivated this boundary; the predicate helper belongs with that seam, where a real consumer decides its shape, rather than shipping into core untested against one. +The [queued manual compaction decision](../feature/2026-07-30-queued-manual-compaction.md) now supplies the first consumer. Its tail scan independently finds the unmatched `compact/start` and newest end-seed, treats only a start after that boundary as live, and clears the invariant trace on the same replay transition. The predicate remains in the compaction package rather than becoming a generic core helper. diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md index dca87e16de..d492c4ac5f 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md @@ -52,4 +52,4 @@ Status: implemented `session/end-seed` 加入了落盘词汇表。在预发布立场下（`SESSION_FORMAT_VERSION` 固定为 `0`，不作兼容承诺），更旧的日志只是没有它，而没有边界的日志会正确地判定没有任何内容属于构造种子历史。 -此处未做：还没有任何插件读取该边界。把压缩 seam 的陈旧性检查接到它上面，是催生这条边界的后续工作；谓词辅助函数应当归属那个 seam——在那里由真实消费方决定它的形状——而不是未经真实消费方检验就先落进核心。 +[排队手动压缩决策](../feature/2026-07-30-queued-manual-compaction.md)如今提供了第一个消费方。其尾部扫描会分别查找未匹配的 `compact/start` 与最新 end-seed，只把位于该边界之后的 start 视为活动锁，并在同一个回放转换上清除不变量追踪状态。该谓词仍位于压缩包中，不会成为通用核心辅助函数。 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml index 414c63211a..714b75d942 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md -2026-06-18-compaction-capability-seam.md: 3c219b734e148b963fb5857de89c16f28c2bd402 -2026-06-18-compaction-capability-seam.zh.md: b2c7e9720b596705b60a284e6ccf1448a782b7fc +2026-06-18-compaction-capability-seam.md: ef37313bc6fb984689793fa5a3e7ac4d9238ea88 +2026-06-18-compaction-capability-seam.zh.md: 9f123a8c40f303a2635af78cafd34de448e27e03 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md index 3c219b734e..ef37313bc6 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -18,10 +18,10 @@ Two forces shape the design. First, compaction policy and reusable token measure Per the [capability-seams Agent Note](../architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently: -1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, the `compact/*` session events, and the canonical checkpoint message source. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. +1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, the `compact/*` session events, the manual failure taxonomy, and the canonical checkpoint message source. It declares `compactIfNeeded()`, `compactNow()`, and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. 2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, post-step pressure, and canonical context-overflow recovery. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. 3. **Model-free companion** — `@deepseek-ai/dsh-compact-tool-result-prune`: a concrete optional service that rewrites oversized current `tool/result` nodes before the backend selects a summary range. It is not a second compaction implementation and does not implement `CompactService`. -4. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. +4. **Human consumer** — `@deepseek-ai/dsh-command-compact` registers argument-free `/compact` through `ctx.commands` and calls the backend-independent `compactNow()` operation. It is direct human control, not a model-facing tool. ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation @@ -29,11 +29,11 @@ The capability-seams Agent Note states the interface package "depends only on co This is not a coupling smell — it is the contract's domain. The "only cordis" guidance was always shorthand for "the interface depends only on what the contract genuinely names, and never on an implementation." `dsh-session` and `dsh-llm` are themselves interface/vocabulary packages, not implementations; `dsh-compact` still imports no backend. The seam's real invariant — *consumers and implementations evolve independently behind an abstract service* — holds intact. -### Abstract `compactIfNeeded` / `compactRegion`, algorithm in the backend +### Three abstract operations, algorithm in the backend -An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold. +An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making all three operations abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold. -`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for manual callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`. +`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactNow(agent, signal)` reserves idle turn admission and performs one useful balanced reduction even below pressure, returning `null` without writes when none exists. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for explicit callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`. ### Automatic pressure runs after successful durable step work @@ -91,42 +91,44 @@ The basic backend wraps the summary as established checkpoint context and tags i ### Blocking via a log-recorded lock, plus a crash/recoverable failure taxonomy -The `compact/start … compact/end` bracket is justified, in order of what now does the work: +The `compact/start … compact/end` bracket is justified by two roles: 1. **Crash-detectable orphan + provenance** (primary). Summarization is a slow model call persisted *after* `compact/start`. A crash mid-summarization leaves a `compact/start` with no matching `compact/end` — a detectable orphan. Releasing the lock last (rather than first) converts the crash window from *silent corruption* into that detectable orphan. -2. **Prevents concurrent compaction.** `compactRegion` refuses to start if the current turn holds an unmatched `compact/start`. (The loop is single-threaded across either awaited automatic seam, so this is also a re-entry tripwire — a thrown "already in progress" signals a real bug.) +2. **Prevents concurrent compaction.** Every automatic, manual, and explicit-range entry point refuses a live unmatched `compact/start`. The bracket is the single lock; no process-local mutex duplicates it. -The lock excludes another compaction, not unrelated log-only facts. The basic backend snapshots the token meter's surface nodes after `compact/start` and compares them again after asynchronous summarization; any surface mutation rejects before replacement, while a title or other log-only append leaves the selected span valid. +The lock excludes another compaction, not unrelated facts. Its markers are time points rather than an exclusive container, so idle injected context may appear between a standalone manual start and end. Automatic work requires whole-surface stability inside its turn. Manual work revalidates only the selected positional span, letting append-only context outside it remain visible after replacement. -Two failure paths, both documented: +The lifecycle boundary makes crash state unambiguous: -- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — no summary replacement lands. The derived surface remains the durable surface present at `compact/start`: full history when pruning made no replacement, or the already-pruned history when it did. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash cannot wedge future compaction. -- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set and lands no summary replacement. Post-step pressure warns and continues from the latest durable surface — full history if no replacement preceded the attempt, or the pruned surface if pruning already landed. Overflow recovery delegates only before any replacement; generation progress from earlier pruning authorizes a retry from that durable surface unless cancellation or disposal wins. +- **Current lifecycle:** a dangling `compact/start` after the newest `session/end-seed` is the live durable lock and reports busy. +- **Later lifecycle:** a newer constructor-written `session/end-seed` proves that the older unmatched start is stale, so resume, fork, and adoption do not remain wedged by a dead writer. +- **Recoverable failure:** once start lands, the backend makes exactly one `compact/end { error }` attempt. Summary or stability failure leaves the conversation surface unchanged while preserving the failed attempt in the log. If the close append fails, the unmatched start remains intentionally blocking. `compact/end` keeps its `error?` field (mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling). There is no separate `compact/error` event. -**Core session repair stays compaction-agnostic — deliberately.** `interruptedTurnClosers` is never taught about `compact/*`. Teaching it would force every future `xxx/start … xxx/end` plugin pair to patch a core module — exactly the coupling the capability-seam architecture exists to avoid. Because the log-only orphan is inert, no special repair is needed: generic turn-repair plus the inertness of an un-landed surface mutation is sufficient. +**Core session repair stays compaction-agnostic — deliberately.** `interruptedTurnClosers` is never taught about `compact/*`. The general `session/end-seed` lifecycle boundary supplies the evidence the compaction owner needs; the compaction invariant and backend interpret it without adding plugin-specific repair to core. ## Alternatives considered -- **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. Both core methods are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. +- **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. All three operations are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. - **Compaction on `agent/request` or provisional `agent/pre-step` inputs** — rejected because neither proves the final durable request and both couple generic lifecycle to compaction-specific envelope data. Post-step replay plus canonical overflow recovery covers both successful and rejected calls. - **A `compact` boolean or untyped request metadata map** — rejected because multiple auxiliary call kinds would become mutually exclusive flags, while an open bag would discard compiler-checked vocabulary. One typed `purpose` discriminant extends with additional call kinds without adding another `GenerateOptions` field. - **A separate `compact/error` event** — rejected: `compact/end` keeps an `error?` field, mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling. -- **Teaching core turn-repair about `compact/*`** — rejected: the log-only orphan is inert, and a core module patched for every future `xxx/start … xxx/end` plugin pair is exactly the coupling the capability-seam architecture exists to avoid. +- **Teaching core turn-repair about `compact/*`** — rejected: the general end-seed boundary already distinguishes prior-lifecycle history, and patching core for every future `xxx/start … xxx/end` pair is exactly the coupling the capability-seam architecture exists to avoid. ## Consequences -- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, and `compact-tool-result-prune` supplies optional deterministic rewriting. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. +- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, `compact-tool-result-prune` supplies optional deterministic rewriting, and `command-compact` supplies human `/compact`. `packages/llm/token-meter` owns replay-aware measurement independently. - **Automatic seams**: `agent/post-step` (`@mode serial`) handles successful-call pressure and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. Generic `agent/pre-step` remains a four-argument checkpoint with no compaction-only prompt/prefix payload. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `COMPACT_CHECKPOINT_SOURCE`, `isCompactCheckpointSource(source)`, `toolPairingBalancedBefore(session, seq)`, and `toolPairingBalancedAfter(session, seq)`. The marker identifies replacement summaries across backend implementations. The cached surface-edge checks prevent `compactRegion` and `compactIfNeeded` from splitting a tool-call/result pair, validate current membership by seq, answer both edges from one per-cut balance sequence, and reject stale or missing seqs and orphan results. -- **`dsh-session`** validates positional replacement, complete provenance, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call; validated replacements remain turn-enclosed rewrites. -- **Wiring**: `examples/tui-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-compact-tool-result-prune`, then `dsh-compact-basic`; service-wide defaults make the composition usable without repeated numeric policy. +- **`dsh-session`** validates positional replacement, complete provenance, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call, while the compaction companion owns numeric-turn versus standalone-null bracket relations. +- **Wiring**: `examples/tui-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-compact-tool-result-prune`, `dsh-compact-basic`, then `dsh-command-compact`; service-wide defaults make the composition usable without repeated numeric policy. ## Testing - **Unit:** Real Loader and invariant plugins cover whole-unit retention, pruning configuration and replay, rich-block ordering, metadata preservation, convergence, both `compact/end` outcomes, open-tail refusal, pruning-only and summarized overflow recovery, generation proof, caps, and original-error preservation. - **Loop:** Tests pin post-step after durable tool results and before `step/end`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition. +- **Manual:** Admission, marker ordering, injection retention, live/stale orphan classification, cancellation, close/flush failures, command mapping, and the queued TUI journey are pinned without a model key. - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task. - **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work. diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md index b2c7e9720b..9f123a8c40 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md @@ -18,10 +18,10 @@ Status: implemented 遵循[能力 seam Agent Note（agent 决策记录）](../architecture/2026-06-13-capability-seams.md)，压缩以独立包（package）发布，使契约、算法和（后续的）消费方 surface 各自独立演进： -1. **接口** — `@deepseek-ai/dsh-compact`：抽象 `CompactService`，拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件以及规范的检查点消息来源。它将 `compactIfNeeded()` 和 `compactRegion()` 声明为**抽象方法**——契约说明压缩*做什么*，而非*怎么做*。 +1. **接口** — `@deepseek-ai/dsh-compact`：抽象 `CompactService`，拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件、手动失败分类体系以及规范的检查点消息来源。它将 `compactIfNeeded()`、`compactNow()` 和 `compactRegion()` 声明为**抽象方法**——契约说明压缩*做什么*，而非*怎么做*。 2. **实现** — `@deepseek-ai/dsh-compact-basic`：具体的 `BasicCompactService`，消费 `ctx.tokenMeter`，并拥有尾→头保留遍历、通过 `ctx.llm.stream()` 生成摘要、surface 替换、锁、步骤后压力处理和规范的上下文溢出恢复。`summarize()` 是其唯一的子类钩子；计价与回放仍归 meter 所有。 3. **无模型配套服务** — `@deepseek-ai/dsh-compact-tool-result-prune`：一个具体的可选服务，在后端选择摘要范围之前，重写当前过大的 `tool/result` 节点。它不是第二种压缩实现，也不实现 `CompactService`。 -4. **消费方** — 推迟。一个 `/compact` 工具和斜杠命令将 `inject: ['compact']` 并调用契约；它们被有意排除在本 Agent Note 范围之外，以便 seam 先稳定下来。 +4. **面向用户的消费方** — `@deepseek-ai/dsh-command-compact` 通过 `ctx.commands` 注册无参数 `/compact`，并调用后端无关的 `compactNow()` 操作。它是供用户直接控制的命令，不是面向模型的工具。 ### 契约依赖 `dsh-session` 和 `dsh-llm`——有意为之的偏离 @@ -29,11 +29,11 @@ Status: implemented 这不是耦合异味，而是契约的领域所在。「仅 cordis」的指导原则一直是「接口仅依赖契约真正需要命名的东西，绝不依赖实现」的简写。`dsh-session` 和 `dsh-llm` 本身是接口/词汇包，不是实现；`dsh-compact` 仍然不导入任何后端。seam 的真正不变式——*消费方和实现在抽象服务背后独立演进*——完好无损。 -### 抽象 `compactIfNeeded` / `compactRegion`，算法在后端 +### 三个抽象操作，算法在后端 -早期草案将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法。这会将契约重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将两个核心方法都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。 +早期草案将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法。这会将契约重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将三个操作都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。 -`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为手动调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。 +`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactNow(agent, signal)` 会预留空闲轮次接纳，即使未达到压力也进行一次有效的平衡缩减；不存在这种范围时返回 `null`，且不写入任何内容。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为显式调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。 ### 成功的持久步骤工作完成后运行自动压力检查 @@ -91,42 +91,44 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab ### 通过日志记录的锁实现阻塞，加上崩溃/可恢复失败的分类 -`compact/start … compact/end` 括号的存在理由，按当前实际承担的职责排序： +`compact/start … compact/end` 标记对承担两项职责： 1. **可检测的崩溃孤儿 + 来源追溯**（首要）。摘要生成是一次慢速模型调用，持久化在 `compact/start` *之后*。摘要生成中途崩溃会留下一个没有匹配 `compact/end` 的 `compact/start`——一个可检测的孤儿。最后释放锁（而非最先）将崩溃窗口从*静默损坏*转变为可检测的孤儿。 -2. **防止并发压缩。** 如果当前轮次持有未匹配的 `compact/start`，`compactRegion` 拒绝启动。（循环在任一 awaited 自动 seam 上都是单线程的，因此这也是重入绊线——抛出「already in progress」表示真正的 bug。） +2. **防止并发压缩。** 每个自动、手动和显式范围入口点都会拒绝活动的未匹配 `compact/start`。该标记对就是唯一的锁；没有进程本地 mutex 重复承担同一职责。 -该锁只排除另一项压缩，不排除无关的仅日志事实。基础后端会在 `compact/start` 之后对 token meter 的 surface 节点取快照，并在异步摘要后再次比较；任何 surface 变更都会使替换前的检查失败，而标题或其他仅日志追加不会使已选范围失效。 +该锁只排除另一项压缩，不排除无关事实。其标记是时间点，而不是排他的容器，因此空闲注入的上下文可以出现在独立手动 start 与 end 之间。自动工作要求其轮次内的整个 surface 保持稳定。手动工作只重新验证所选位置 span，使其外部的仅追加上下文在替换后保持可见。 -两种失败路径，均有文档记录： +生命周期边界使崩溃状态含义明确： -- **崩溃**（循环在摘要生成中途死亡）：悬空的 `compact/start`，无关闭事件。由于 `compact/*` 是**仅日志**事件，孤儿是**惰性的**，不会落地摘要替换。派生 surface 保持为 `compact/start` 时已经持久化的 surface：如果修剪未产生替换，就是完整历史；如果已经修剪，就是已修剪历史。通用轮次修复（`interruptedTurnClosers`）用合成的 `turn/end` 关闭轮次；孤儿位于该 `turn/end` *之前*，因此轮次范围内的进行中检查永远看不到它，崩溃不会卡住未来的压缩。 -- **可恢复**（摘要生成抛出异常但循环存活）：后端追加设置了 **`error`** 字段的 `compact/end`，但不落地摘要替换。步骤后压力处理发出警告，并从最新的持久 surface 继续：如果尝试前没有替换，就是完整历史；如果修剪已经落地，就是已修剪 surface。溢出恢复只会在没有任何替换前委托；先前修剪带来的 generation 进展允许从该持久 surface 重试，除非取消或资源释放胜出。 +- **当前生命周期：** 最新 `session/end-seed` 之后悬空的 `compact/start` 是活动的持久锁，并报告 busy。 +- **后续生命周期：** 构造函数写入的较新 `session/end-seed` 证明更早的未匹配 start 已陈旧，因此恢复、fork 和接手不会被已死的写入方持续卡住。 +- **可恢复失败：** start 落地后，后端会恰好尝试一次 `compact/end { error }`。摘要或稳定性失败会保持会话 surface 不变，同时在日志中保留失败尝试。如果追加闭合事件失败，未匹配 start 会继续有意阻塞。 `compact/end` 保留其 `error?` 字段（与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败，无需关联兄弟事件）。没有单独的 `compact/error` 事件。 -**核心会话修复保持对压缩无感知——这是有意为之。** `interruptedTurnClosers` 从不被教导 `compact/*`。如果教导它，每个未来的 `xxx/start … xxx/end` 插件对都必须修补核心模块——这恰好是能力 seam 架构存在的意义所要避免的耦合。由于仅日志的孤儿是惰性的，不需要特殊修复：通用轮次修复加上未落地 surface 变更的惰性就足够了。 +**核心会话修复保持对压缩无感知——这是有意为之。** `interruptedTurnClosers` 从不被教导 `compact/*`。通用 `session/end-seed` 生命周期边界提供压缩所有方所需的证据；压缩不变量与后端负责解释它，无需向核心添加插件专属修复。 ## 曾考虑的替代方案 -- **完整算法作为接口的具体方法**——否决，因为它将契约重新耦合到一种保留策略。两个核心方法都是抽象的；可复用测量属于单独的 LLM 系列服务，`summarize()` 是 basic 唯一的钩子。 +- **完整算法作为接口的具体方法**——否决，因为它将契约重新耦合到一种保留策略。三个操作都是抽象的；可复用测量属于单独的 LLM 系列服务，`summarize()` 是 basic 唯一的钩子。 - **在 `agent/request` 或临时 `agent/pre-step` 输入上执行压缩**——否决，因为两者都无法证明最终的持久请求，而且都会将通用生命周期耦合到压缩专属的信封数据。步骤后回放与规范溢出恢复同时覆盖成功和被拒绝的调用。 - **`compact` 布尔值或无类型的请求元数据 map**——否决，因为多个辅助调用种类会变成互斥标志，而开放 map 会丢弃由编译器检查的词汇。一个类型化的 `purpose` 判别字段可以扩展其他调用种类，而无需再为 `GenerateOptions` 添加字段。 - **单独的 `compact/error` 事件**——否决：`compact/end` 保留 `error?` 字段，与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败，无需关联兄弟事件。 -- **教导核心轮次修复识别 `compact/*`**——否决：仅日志的孤儿是惰性的，为每个未来的 `xxx/start … xxx/end` 插件对修补核心模块恰好是能力 seam 架构存在的意义所要避免的耦合。 +- **教导核心轮次修复识别 `compact/*`**——否决：通用 end-seed 边界已经能够区分先前生命周期的历史；为每个未来的 `xxx/start … xxx/end` 插件对修补核心模块，恰好是能力 seam 架构存在的意义所要避免的耦合。 ## 后果 -- **包**：`packages/compact/compact` 提供接口，`compact-basic` 提供后端，`compact-tool-result-prune` 提供可选的确定性重写。`packages/llm/token-meter` 独立拥有回放感知的测量。消费方层推迟。 +- **包**：`packages/compact/compact` 提供接口，`compact-basic` 提供后端，`compact-tool-result-prune` 提供可选的确定性重写，`command-compact` 提供面向用户的 `/compact`。`packages/llm/token-meter` 独立拥有回放感知的测量。 - **自动 seam**：`agent/post-step`（`@mode serial`）处理成功调用的压力，`agent/request-error`（`@mode waterfall`）处理失败步骤关闭后的最终请求失败。通用 `agent/pre-step` 保持为四参数检查点，不携带压缩专属的提示词/前缀 payload。 - **`SessionEventMap`** 通过可合并扩展的声明合并获得 `compact/start` / `compact/summary` / `compact/end`；`SurfaceEventType` **未被**触及。这些是会话事件，不是 cordis `Events`，因此事件分类门禁无需新增条目。 - **`dsh-compact`** 拥有 `COMPACT_CHECKPOINT_SOURCE`、`isCompactCheckpointSource(source)`、`toolPairingBalancedBefore(session, seq)` 与 `toolPairingBalancedAfter(session, seq)`。该标记用于跨后端实现识别替换摘要。带缓存的 surface 边缘检查会防止 `compactRegion` 和 `compactIfNeeded` 拆分工具调用/结果对，按 seq 校验当前成员关系，从每个切割点的一条平衡序列回答两侧边缘，并拒绝陈旧或缺失的 seq 与孤立结果。 -- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行，要求存在已打开的步骤与待处理调用；已校验的替换仍是位于轮次内的重写。 -- **接线**：`examples/tui-agent/cordis.yml` 依次加载零配置的 `dsh-token-meter`、`dsh-compact-tool-result-prune` 和 `dsh-compact-basic`；服务级默认值使组合无需重复数值策略即可使用。 +- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行，要求存在已打开的步骤与待处理调用，而压缩配套组件拥有数字轮次归属与独立 `null` 归属标记对之间的关系。 +- **接线**：`examples/tui-agent/cordis.yml` 依次加载零配置的 `dsh-token-meter`、`dsh-compact-tool-result-prune`、`dsh-compact-basic`，然后加载 `dsh-command-compact`；服务级默认值使组合无需重复数值策略即可使用。 ## 测试 - **单元测试：** 使用真实 Loader 和 invariant 插件覆盖完整单元保留、修剪配置与回放、富块顺序、元数据保留、收敛、`compact/end` 的两种结果、开放尾部拒绝、仅修剪与带摘要的溢出恢复、generation 证明、上限和原始错误保留。 - **循环测试：** 测试固定步骤后处理发生在持久工具结果之后、`step/end` 之前，使用实际 `agent/request` 路由，关闭失败步骤，分配新的重试编号，并覆盖完整的抛出/带内溢出 → 压缩 → 重建重试组合。 +- **手动测试：** 无需模型密钥即可固定接纳、标记顺序、注入保留、活动／陈旧未匹配标记分类、取消、闭合／flush 失败、命令映射以及排队 TUI 流程。 - **带密钥 e2e：** 真实模型和 bash 会话在降低的限制下触发压缩，记录完整的 `compact/start…end` 对，缩小 surface，并完成任务。 - **快照缺口：** 失控轮次压缩尚无法回放，因为摘要调用未记录 `assistant/chunk` 事件或 `sessionId`；交错摘要调用的回放仍是后续工作。 diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml new file mode 100644 index 0000000000..33740e2b31 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md +2026-07-30-queued-manual-compaction.md: 05676ef824bc62ddbdbd8895a325570e91e4bafd +2026-07-30-queued-manual-compaction.zh.md: b2e40a42451570887a194c215df07e98aa1bd864 diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md new file mode 100644 index 0000000000..05676ef824 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md @@ -0,0 +1,110 @@ +# Agent Note: Queued manual compaction with one durable lock + +Status: implemented + +English | [中文](2026-07-30-queued-manual-compaction.zh.md) + +## Problem + +Automatic compaction protects the context window, but an interactive user also needs a deterministic way to condense accumulated history before pressure policy fires. Sending `/compact` as prompt text would spend a model turn and let the conversation model reinterpret a direct control action. Implementing it inside one UI would duplicate command discovery, lifecycle logging, cancellation, and backend policy. + +The human command arrives between turns and must summarize asynchronously. A prompt accepted during that wait must keep its ordinary identity, FIFO position, and wakeup behavior, but it must not derive a request from history that compaction is about to replace. A status check is insufficient: a waking send schedules the driver's claim as a microtask, leaving a same-tick interval where status still reads idle even though the prompt already has right of way. + +Compaction also needs one mutual-exclusion fact shared by manual, pressure, overflow, and explicit-range entry points. A process-local flag alone cannot explain a crash-recovered log, while a summarize-first transaction leaves no durable evidence during the expensive interval. Conversely, treating marker pairs as exclusive containers would forbid valid idle injection even though injection is explicitly non-waking and immediate between turns. + +This note extends the [compaction capability seam](2026-06-18-compaction-capability-seam.md), the [session end-seed boundary](../architecture/2026-07-30-session-end-seed-log-boundary.md), and the [removal of synthetic log-only turns](../simplification/2026-07-28-remove-synthetic-log-only-turns.md). The supersession audit found partial overlap only: each remains active and owns its broader decision. + +## Decision + +### `/compact` is a command over a backend-independent seam + +`@deepseek-ai/dsh-command-compact` registers one argument-free human command through `ctx.commands`. It calls the third abstract `CompactService` operation, `compactNow(agent, signal)`, and maps the closed `ManualCompactionError` taxonomy (`busy | changed | summary | commit | persistence`) to direct UI results. `command/run` and `command/done` preserve the command lifecycle without entering model history or consuming a model-loop turn. + +The command plugin tracks each real handler promise independently of the command executor's abort-aware wait. Its composite lifecycle effect unregisters `/compact` before asynchronously draining handlers that already started, so root teardown reaches quiescence only after backend close and flush work settles. + +The seam's `ManualCompactAgentContext` adds only `reserveTurnAdmission()` to the session and routing facts compaction already needs. Retention, balancing, summarization, marker ordering, replacement, and durability remain backend responsibilities. + +### Idle turn admission is synchronously reservable + +`Agent.reserveTurnAdmission(): (() => void) | undefined` claims the boundary before the next ordinary turn. It succeeds only when the driver is idle, no reservation exists, and no accepted waking item already owns the next turn, including a wake whose claim is still a pending microtask. + +The reservation does not create a second queue. Later sends keep their `InboxItemId`, placement, FIFO order, and wakeup facts. `acceptsNextStep` remains false, so waking next-step input becomes an ordinary queued follow-up rather than steering. Release is idempotent and re-arms the existing driver path. `inject()` is not withheld. + +`whenIdle()` treats a reservation as unfinished activity, including when it holds a waking item. Lifecycle teardown still drains the driver's own activity promise rather than awaiting an external operation, so disposal can cancel and unwind without depending on the reservation holder. + +### One parameterized transaction owns every bracket + +`dsh-compact-basic` has one region transaction parameterized by bracket owner (`number | null`), stability rule (whole surface or selected span), and an optional flush. It performs one ordering: + +1. validate the selected positional range and inspect the durable tail; +2. reject a live unmatched compaction marker; +3. append `compact/start` synchronously; +4. prepare and await summarization; +5. revalidate the required stability; +6. append `compact/summary` and the replacement `user/message`; +7. make exactly one `compact/end` attempt; +8. flush when the manual caller requested durability. + +Automatic and explicit-region work use the numeric owner recovered from the open turn and require whole-surface stability. Manual work reserves admission first, selects a useful range before the transaction, and writes nothing when selection returns `null`. Its bracket uses `turn: null`, requires only selected-span stability, and flushes every successfully closed attempt before releasing admission in `finally`. + +`compact/start` is therefore the only compaction lock. There is no `WeakSet`, wrapper mutex, locked/unlocked method split, or redundant activity check around the transaction. + +### Bracket-first deliberately differs from the surveyed implementations + +Codex models manual compaction as a `CompactTask` occupying its active-turn slot while automatic compaction runs inline. Pi uses the existence of a compaction abort controller as its mutex and appends compaction only after success. Claude Code shares one compaction routine between automatic and manual paths but constructs its boundary after summary streaming. + +DSH deliberately records `compact/start` before calling the summarizer. A slow or crashed attempt is observable, automatic and manual paths share the same durable lock, and a later writer cannot mistake an in-flight summary for an unlocked session. This is a conscious divergence from summarize-first behavior, not an accidental event-order difference. + +### Markers are time points, not an event container + +`compact/start` and `compact/end` mean lock acquisition and release. They do not claim exclusive ownership of every event between their seqs. An idle `inject()` may append a `user/message` while a manual summary is pending, so that unrelated event can sit inside the marker interval. + +Manual stability checks only the selected span: it must remain present, contiguous, ordered, equally priced, and balanced. Append-only context outside it does not stale the summary. Positional replacement places the checkpoint at the old span's surface position and leaves injected context after it in derived model history, even though the injection's log seq precedes the later summary and replacement events. + +Failed `changed` or `summary` attempts leave the conversation surface unchanged, but the log is not unchanged: it contains `compact/start` and `compact/end { error }`. User-facing text states that distinction. + +### End-seed distinguishes live and stale orphans + +Tail scanning finds the current turn, unmatched compaction start, and newest `session/end-seed` independently. An unmatched start after the newest end-seed is live and blocks every compaction entry point. An unmatched start before a later end-seed belongs to an earlier session lifecycle and is stale, so it does not wedge the resumed or forked session. + +The compaction invariant uses the same transition logic during seed replay: `session/end-seed` clears an open historical trace. The boundary need not publish live from the constructor for this case; replay is the load-bearing path. + +The client request projection closes an unmatched compaction request as interrupted at the `session/end-seed` time and clears its active index. A later `compact/start` therefore creates an independent request instead of leaving or overwriting a permanently running orphan. + +Once a transaction has appended its start, every later failure makes one closing attempt. A failed close leaves the unmatched start deliberately visible and blocking, and no flush is attempted. A closed manual attempt is flushed even when it reports an expected failure. Cancellation retains exact-reason precedence after required close and flush cleanup. + +### Reference implementation boundaries + +[PR #835](https://github.com/deepseek-harness/deepseek-harness/pull/835) was used as a reference implementation for the command, reservation, tests, and snapshot shape, but was not merged. Its process-local `WeakSet` lock and locked/unlocked method splits were considered and not adopted because the durable bracket is the single reachable lock. + +That reference also carried client-side replacement-anchor machinery to preserve transcript placement. The log-ordered transcript projection already consumes compaction from event order and does not consult mutable surface positions, so those anchors were considered and not adopted. + +## Alternatives considered + +**Check `agent.status` without reserving admission.** Rejected because an accepted waking send can still be waiting on its claim microtask while status reads idle. + +**Queue the command itself.** Rejected because `/compact` is direct control, not model input, and a prompt already accepted first must retain right of way rather than being reordered around a second command queue. + +**Summarize before appending `compact/start`.** Rejected because the expensive in-flight operation would be invisible and would not participate in the lock shared by automatic compaction. + +**Use both a durable marker and a process-local mutex.** Rejected because two authorities can disagree after replay and require wrapper branches for states the bracket already expresses. + +**Hold injection with waking prompts.** Rejected because idle injection is non-waking durable context by contract; delaying it would make plugin ordering depend on a UI command. + +**Require the marker interval to contain only compaction events.** Rejected because markers represent lock time points. Provenance names the selected and shadowed seqs exactly; exclusivity would add no correctness and would reject valid injection. + +**Treat every unmatched marker as permanently busy.** Rejected because a crash-recovered or forked session would remain wedged. `session/end-seed` is the explicit lifecycle evidence that distinguishes stale history from a live process-local attempt. + +## Verification + +Agent-loop tests cover same-tick right of way, preserved IDs and FIFO lifecycle, waking and quiet queued work, idempotent release, `whenIdle()`, cancellation, and teardown. Compact tests cover standalone and numbered invariant ownership, end-seed replay, live versus stale orphans, re-entrant listeners, selected-span drift, commit and close failures, flush ordering, exact cancellation causes, raw output and usage preservation, and automatic/manual mutual exclusion. + +The command package pins registration, Loader composition, argument rejection, exact success/failure text, cancellation, absence from model history, and disposal waiting across separate close and flush boundaries after an abort stops the executor from awaiting the handler. The client runtime projection test pins end-seed interruption followed by an independent completed attempt. The `queued-manual-compact` terminal snapshot drives real keystrokes through the assembled TUI: `/help` discovers the command, a held summary admits a queued prompt and immediate injection, `turn: null` markers and the flush precede the queued prompt turn, command lifecycle stays log-only, and the derived order is checkpoint → injection → queued prompt. + +## Consequences + +Interactive users can compact useful history without spending a conversation-model turn. A prompt accepted before the command wins; one submitted during the command waits with its original queue identity. Manual compaction consumes session seqs but no turn number. + +The log exposes slow, failed, crashed, and successful attempts through the same bracket. A stale pre-boundary orphan no longer wedges a new lifecycle, while a current unmatched start remains a hard busy signal. Marker intervals may contain unrelated events, so consumers use provenance and relative ordering rather than assuming a contiguous compaction-only slice. + +The shared transaction keeps one ordering and one lock across every entry point. Failure reporting is precise about whether only the log changed, the surface may have partially changed, or the in-memory commit could not be persisted. diff --git a/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md new file mode 100644 index 0000000000..b2e40a4245 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.zh.md @@ -0,0 +1,110 @@ +# Agent Note: 使用单一持久锁实现排队手动压缩 + +Status: implemented + +[English](2026-07-30-queued-manual-compaction.md) | 中文 + +## 问题 + +自动压缩（compaction）可以保护上下文窗口，但交互用户还需要一种确定性方法，在压力策略触发前压缩累积的历史。把 `/compact` 作为提示词文本发送会消耗一个模型轮次，还会让会话模型重新解释一项直接控制操作。在某个 UI 内实现该功能，则会重复命令发现、生命周期日志记录、取消与后端策略。 + +面向用户的命令在轮次之间到达，并且必须异步生成摘要。在等待期间获接纳的提示词必须保留普通身份、FIFO 位置与唤醒行为，但不得从即将被压缩替换的历史派生请求。仅检查状态并不足够：唤醒发送会把驱动器的认领安排为 microtask，因此在同一 tick 内存在一段间隔，此时状态仍显示 idle，但提示词已经拥有优先权。 + +手动、压力、溢出和显式范围入口点还需要共享同一项互斥事实。仅使用进程本地标志无法解释一份崩溃恢复后的日志，而先摘要再记录的事务在开销较大的等待期间不会留下持久证据。反过来，把标记对视为排他容器又会禁止有效的空闲注入，尽管注入按定义不会唤醒，并且会在轮次之间立即执行。 + +本 Agent Note 扩展[压缩能力 seam](2026-06-18-compaction-capability-seam.md)、[会话 end-seed 边界](../architecture/2026-07-30-session-end-seed-log-boundary.md)和[移除纯日志事件的合成轮次](../simplification/2026-07-28-remove-synthetic-log-only-turns.md)。取代关系审计只发现部分重叠：三者均保持活动状态，并拥有各自更广泛的决策。 + +## 决策 + +### `/compact` 是基于后端无关 seam 的命令 + +`@deepseek-ai/dsh-command-compact` 通过 `ctx.commands` 注册一个无参数、面向用户的命令。它调用第三个抽象 `CompactService` 操作 `compactNow(agent, signal)`，并把封闭的 `ManualCompactionError` 分类体系（`busy | changed | summary | commit | persistence`）映射为直接 UI 结果。`command/run` 和 `command/done` 保留命令生命周期，同时不进入模型历史，也不消耗模型循环轮次。 + +命令插件会独立跟踪每个实际处理器 promise，不依赖命令执行器的中止感知等待。其复合生命周期 effect 先注销 `/compact`，再异步等待所有已开始的处理器结算，因此根级 teardown 只有在后端的闭合与 flush 工作结算后才会完全停稳。 + +该 seam 的 `ManualCompactAgentContext` 只在压缩已需使用的会话与路由事实之上增加 `reserveTurnAdmission()`。保留、平衡、摘要、标记排序、替换与持久性仍由后端负责。 + +### 可以同步预留空闲轮次接纳 + +`Agent.reserveTurnAdmission(): (() => void) | undefined` 会在下一个普通轮次之前认领边界。仅当驱动器空闲、没有既存预留，而且尚无已获接纳的唤醒项拥有下一轮次时，它才会成功；仍在等待 microtask 认领的唤醒项也包括在内。 + +该预留不会创建第二个队列。之后发送的项保留其 `InboxItemId`、位置、FIFO 顺序与唤醒信息。`acceptsNextStep` 保持 false，因此唤醒的 next-step 输入会成为普通的排队 follow-up，而不是 steering（中途引导）。释放操作可幂等调用，并重新启用既有驱动器路径。`inject()` 不受阻塞。 + +`whenIdle()` 会把预留视为尚未完成的活动，包括预留持有唤醒项的情况。生命周期 teardown 仍会排空驱动器自身的 activity promise，而不会等待外部操作，因此 dispose（资源释放）可以执行取消并完成退出清理，无需依赖预留持有方。 + +### 一个参数化事务拥有每一对标记 + +`dsh-compact-basic` 只有一个区域事务，由标记归属值（`number | null`）、稳定性规则（整个 surface 或所选 span）与可选 flush 参数化。它按同一顺序执行： + +1. 验证所选位置范围，并检查持久日志尾部； +2. 拒绝活动的未匹配压缩标记； +3. 同步追加 `compact/start`； +4. 准备并等待摘要； +5. 重新验证所需稳定性； +6. 追加 `compact/summary` 与替换用的 `user/message`； +7. 恰好尝试一次 `compact/end`； +8. 当手动调用方要求持久性时执行 flush。 + +自动和显式区域工作使用从开放轮次恢复的数字归属值，并要求整个 surface 保持稳定。手动工作会先预留接纳，在进入事务前选择有效范围；选择结果为 `null` 时不写入任何内容。其标记对使用 `turn: null`，只要求所选 span 保持稳定，并在 `finally` 中释放接纳预留前 flush 每次成功闭合的尝试。 + +因此，`compact/start` 是唯一的压缩锁。不存在 `WeakSet`、包装层 mutex、locked／unlocked 方法拆分，也不存在事务外部重复的活动状态检查。 + +### 先记录标记有意不同于调研过的实现 + +Codex 将手动压缩建模为占用其活动轮次槽位的 `CompactTask`，自动压缩则以内联方式运行。Pi 使用压缩 abort controller 是否存在作为 mutex，并仅在成功后追加压缩。Claude Code 的自动和手动路径共享同一个压缩例程，但会在摘要流结束后才构造边界。 + +DSH 有意在调用摘要器前记录 `compact/start`。缓慢或崩溃的尝试因此可观察，自动与手动路径共享同一个持久锁，之后的写入方也不会把正在生成的摘要误判为未锁定会话。这是对先摘要行为的主动偏离，而不是偶然的事件顺序差异。 + +### 标记是时间点，而不是事件容器 + +`compact/start` 和 `compact/end` 表示获取与释放锁。它们不声称排他拥有二者 seq 之间的每个事件。手动摘要等待期间，空闲的 `inject()` 可以追加 `user/message`，因此该不相关事件可能位于标记区间内。 + +手动稳定性只检查所选 span：它必须仍然存在、连续、有序、计价相同且保持平衡。其外部的仅追加上下文不会使摘要陈旧。位置替换会把检查点放在旧 span 的 surface 位置，并使注入上下文在派生模型历史中位于其后，即使注入的日志 seq 早于后续摘要和替换事件。 + +失败的 `changed` 或 `summary` 尝试会保持会话 surface 不变，但日志并非没有变化：其中会包含 `compact/start` 和 `compact/end { error }`。面向用户的文本会明确说明这一区别。 + +### End-seed 区分活动与陈旧的未匹配标记 + +尾部扫描会分别查找当前轮次、未匹配的 compaction start 与最新 `session/end-seed`。位于最新 end-seed 之后的未匹配 start 是活动锁，会阻塞每个压缩入口点。位于较新 end-seed 之前的未匹配 start 属于更早的会话生命周期，已经陈旧，因此不会卡住恢复或 fork 后的会话。 + +压缩不变量在 seed 回放期间使用同一项转换逻辑：`session/end-seed` 会清除开放的历史追踪状态。此场景不要求构造函数实时发布该边界；回放才是承重路径。 + +客户端请求投影会在 `session/end-seed` 时刻将未匹配的压缩请求以中断状态结束，并清除其活动索引。因此，后续 `compact/start` 会创建一个独立请求，而不是让该遗留的未匹配请求永久保持运行状态或将其覆盖。 + +事务追加 start 后，每次后续失败都会进行一次闭合尝试。闭合失败会有意留下可见且具有阻塞作用的未匹配 start，并且不尝试 flush。已闭合的手动尝试即使报告预期失败也会 flush。完成必需的闭合与 flush 清理后，取消仍保留原始原因优先级。 + +### 参考实现边界 + +[PR #835](https://github.com/deepseek-harness/deepseek-harness/pull/835) 用作命令、预留、测试与快照结构的参考实现，但未被合并。它的进程本地 `WeakSet` 锁与 locked／unlocked 方法拆分经过评估后未被采用，因为持久标记对是唯一可达的锁。 + +该参考实现还包含客户端侧替换锚点机制，用于保留 transcript（文本记录）位置。按日志顺序排列的 transcript 投影已经从事件顺序消费压缩，并且不会查询可变 surface 位置，因此这些锚点经过评估后未被采用。 + +## 曾考虑的替代方案 + +**仅检查 `agent.status`，不预留接纳。** 不予采用，因为已获接纳的唤醒发送可能仍在等待其认领 microtask，而状态仍显示 idle。 + +**把命令本身加入队列。** 不予采用，因为 `/compact` 是直接控制而非模型输入；先获接纳的提示词必须保留优先权，不能围绕第二个命令队列重新排序。 + +**在追加 `compact/start` 前生成摘要。** 不予采用，因为开销较大的进行中操作将不可见，也不会参与自动压缩共享的锁。 + +**同时使用持久标记与进程本地 mutex。** 不予采用，因为两项权威在回放后可能产生分歧，还会要求用包装层分支处理标记对已经表达的状态。 + +**与唤醒提示词一起阻塞注入。** 不予采用，因为按契约，空闲注入是不会唤醒的持久上下文；延迟注入会使插件排序依赖某个 UI 命令。 + +**要求标记区间只包含压缩事件。** 不予采用，因为标记表示锁的时间点。溯源信息会精确指明所选 seq 与被遮蔽 seq；排他性不会增加正确性，只会拒绝有效注入。 + +**把每个未匹配标记都永久视为 busy。** 不予采用，因为崩溃恢复或 fork 后的会话会永久卡住。`session/end-seed` 是区分陈旧历史与当前进程活动尝试的显式生命周期证据。 + +## 验证 + +Agent loop 测试覆盖同一 tick 内的优先权、保留 ID 与 FIFO 生命周期、会唤醒和静默的排队工作、幂等释放、`whenIdle()`、取消与 teardown。压缩测试覆盖独立与数字形式的不变量 owner、end-seed 回放、活动与陈旧未匹配标记、listener 重入、所选 span 漂移、commit 与闭合失败、flush 顺序、原始取消原因、raw output 与 usage 保留，以及自动／手动互斥。 + +命令包固定注册行为、Loader 组合、参数拒绝、精确的成功／失败文本、取消、不进入模型历史的保证，以及处置操作在中止使执行器停止等待处理器后，仍会跨越相互独立的闭合与 flush 边界等待该处理器结算。客户端运行时投影测试固定 end-seed 中断，以及随后一次独立尝试的完成。`queued-manual-compact` 终端快照通过已组装 TUI 驱动真实按键：`/help` 可发现该命令；被暂停的摘要会接纳一个排队提示词和即时注入；`turn: null` 标记与 flush 先于排队提示词轮次；命令生命周期保持纯日志；派生顺序固定为检查点 → 注入 → 排队提示词。 + +## 后果 + +交互用户无需消耗会话模型轮次即可压缩有效历史。在命令前获接纳的提示词胜出；命令期间提交的提示词会以原有队列身份等待。手动压缩会消耗会话 seq，但不消耗轮次编号。 + +日志通过同一对标记暴露缓慢、失败、崩溃与成功的尝试。边界前的陈旧未匹配标记不会再卡住新的生命周期，而当前未匹配 start 仍是严格的 busy 信号。标记区间可以包含不相关事件，因此消费方使用溯源信息与相对顺序，而不假定存在连续且仅含压缩事件的切片。 + +共享事务让每个入口点保持同一种顺序并使用同一把锁。失败报告会精确区分只有日志发生变化、surface 可能部分改变，以及内存 commit 无法持久化这三种情况。 diff --git a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml index 9031dc8eb0..75e8ca8d37 100644 --- a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md -2026-07-28-remove-synthetic-log-only-turns.md: af4da00f4fe1d7aebff845cd55053bb5b807c979 -2026-07-28-remove-synthetic-log-only-turns.zh.md: 9d72781d6b7cf396a830790d108f4ff25adc816a +2026-07-28-remove-synthetic-log-only-turns.md: fc76667924ec839301aad993efd996112c9a6b09 +2026-07-28-remove-synthetic-log-only-turns.zh.md: 7520c33e2219c5fe7ab7d8da6312247e42cc69b0 diff --git a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md index af4da00f4f..fc76667924 100644 --- a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md +++ b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.md @@ -18,11 +18,11 @@ The generic seam also duplicated domain policy. Its marker map said which plugin Core session invariants continue to enforce core-owned execution relations: turn and step numbering, enclosure of steering, assistant, tool, todo, and request-header events, and same-step tool call/result pairing. Core permits merge-extensible events between turns because only their declaring plugin knows whether they are execution-scoped or standalone. Plugin invariant companions remain responsible for their own event relations. -The title service appends `session/title` directly after its existing service, revision, cancellation, and live-session checks. The bundled model helper appends its literal `session/title-llm-request` record before dispatch. Persistence observes both through the eager `session/event` path and drains them at ordinary checkpoints and lifecycle teardown; neither append forces a flush merely because it is between turns. A fallback, auxiliary request record, or accepted provider title may therefore appear after `turn/end` and before the next `turn/start`. +The title service appends `session/title` directly after its existing service, revision, cancellation, and live-session checks. The bundled model helper appends its literal `session/title-llm-request` record before dispatch. Persistence observes both through the eager `session/event` path and drains them at ordinary checkpoints and lifecycle teardown; neither append forces a flush merely because it is between turns. A fallback, auxiliary request record, or accepted provider title may therefore appear after `turn/end` and before the next `turn/start`. Manual compaction uses the same between-turn capability for a `compact/* { turn: null }` bracket, but explicitly flushes the closed attempt because `/compact` promises durability before releasing queued prompt admission. A session fork may end at any stable event position outside an open turn, not only at `turn/end`. This preserves standalone title and context records in a default fork while still rejecting a prefix cut through active execution. -The historical [universal turn-enclosure decision](../../archived/architecture/2026-06-15-turn-enclosure-invariant.md) remains useful only as the reason the synthetic mechanism was introduced. The [context-injection decision](../architecture/2026-07-24-separate-context-injection-from-turn-execution.md) established the current meaning: one turn represents one model-loop execution. +The historical [universal turn-enclosure decision](../../archived/architecture/2026-06-15-turn-enclosure-invariant.md) remains useful only as the reason the synthetic mechanism was introduced. The [context-injection decision](../architecture/2026-07-24-separate-context-injection-from-turn-execution.md) established the current meaning: one turn represents one model-loop execution. The [queued manual compaction decision](../feature/2026-07-30-queued-manual-compaction.md) applies that rule to a durable multi-event bracket and owns its marker and admission semantics. ## Alternatives considered @@ -36,8 +36,8 @@ The historical [universal turn-enclosure decision](../../archived/architecture/2 ## Verification -Core invariant tests accept an unknown plugin event between turns while continuing to reject built-in execution events there. Hook, compaction, plan-mode, Code Mode dispatch, and approval invariant companions replay existing logs and reject the same execution-scoped events before commit when no turn is open. Session-title service tests pin one direct fallback event under concurrent refresh, detached-session rejection, and newest-revision acceptance. JSONL and SQLite round trips preserve a title appended after `turn/end` through the persistence lifecycle drain, and fork tests retain a standalone log-only tail while rejecting boundaries inside an open turn. A keyless assembled ACP snapshot delays the model-backed title until after `turn/end` and pins one standalone provider title with no synthetic turn. Generated API and type-equivalence catalogs contain no removed symbol. +Core invariant tests accept an unknown plugin event between turns while continuing to reject built-in execution events there. Hook, plan-mode, Code Mode dispatch, and approval invariant companions reject their execution-scoped events when no turn is open; the compaction companion separately accepts a balanced `turn: null` manual bracket between turns and requires numeric owners to match an open turn. Session-title service tests pin one direct fallback event under concurrent refresh, detached-session rejection, and newest-revision acceptance. JSONL and SQLite round trips preserve a title appended after `turn/end` through the persistence lifecycle drain, and fork tests retain a standalone log-only tail while rejecting boundaries inside an open turn. A keyless assembled ACP snapshot delays the model-backed title until after `turn/end` and pins one standalone provider title with no synthetic turn. Generated API and type-equivalence catalogs contain no removed symbol. ## Consequences -Turn counts and outcomes again describe model-loop executions only. Standalone events consume session seqs, start eager persistence like every other append, and require owners to request an explicit durability barrier only when their operation promises one. Generic plugin mistakes no longer fail under a core default enclosure rule, so each plugin that needs an execution relation must state and test that relation itself. The title capability keeps revision ordering and lifecycle persistence with less core state, no duplicate type seam, and no turn-number collision. +Turn counts and outcomes again describe model-loop executions only. Standalone events and manual compaction brackets consume session seqs without consuming a turn number, start eager persistence like every other append, and require owners to request an explicit durability barrier only when their operation promises one. Generic plugin mistakes no longer fail under a core default enclosure rule, so each plugin that needs an execution relation must state and test that relation itself. The title capability keeps revision ordering and lifecycle persistence with less core state, and manual compaction gains durable control with no synthetic-turn or turn-number collision. diff --git a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md index 9d72781d6b..7520c33e22 100644 --- a/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md +++ b/.agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.zh.md @@ -18,11 +18,11 @@ Status: implemented 核心会话不变量继续强制核心所属的执行关系：轮次与步骤编号、steering、助手、工具、待办和请求头事件的封闭，以及同一步骤内的工具调用／结果配对。核心允许可合并扩展事件位于轮次之间，因为只有声明它们的插件知道这些事件受执行作用域约束，还是可以独立存在。插件的不变量配套组件仍负责其自身的事件关系。 -标题服务会在完成既有的服务状态、修订、取消和实时会话检查后，直接追加 `session/title`。随附模型辅助函数会在发起调用前追加其字面量 `session/title-llm-request` 记录。持久化通过尽快处理的 `session/event` 路径观察两者，并在常规检查点与生命周期 teardown 时排空；二者都不会仅因为位于轮次之间就强制 flush。因此，回退标题、辅助请求记录或已接受的提供方标题可以出现在 `turn/end` 之后、下一个 `turn/start` 之前。 +标题服务会在完成既有的服务状态、修订、取消和实时会话检查后，直接追加 `session/title`。随附模型辅助函数会在发起调用前追加其字面量 `session/title-llm-request` 记录。持久化通过尽快处理的 `session/event` 路径观察两者，并在常规检查点与生命周期 teardown 时排空；二者都不会仅因为位于轮次之间就强制 flush。因此，回退标题、辅助请求记录或已接受的提供方标题可以出现在 `turn/end` 之后、下一个 `turn/start` 之前。手动压缩（compaction）利用同一项轮次间能力记录 `compact/* { turn: null }` 标记对，但会显式 flush 已闭合的尝试，因为 `/compact` 承诺在释放排队提示词接纳预留前完成持久化。 会话 fork 可以结束于开放轮次之外的任意稳定事件位置，而不限于 `turn/end`。这样，默认 fork 会保留独立标题和上下文记录，同时仍拒绝在活跃执行过程中截断前缀。 -历史上的[通用轮次封闭决策](../../archived/architecture/2026-06-15-turn-enclosure-invariant.md)如今只适合用于解释为何曾引入合成机制。[上下文注入决策](../architecture/2026-07-24-separate-context-injection-from-turn-execution.md)确立了当前语义：一个轮次表示一次模型循环执行。 +历史上的[通用轮次封闭决策](../../archived/architecture/2026-06-15-turn-enclosure-invariant.md)如今只适合用于解释为何曾引入合成机制。[上下文注入决策](../architecture/2026-07-24-separate-context-injection-from-turn-execution.md)确立了当前语义：一个轮次表示一次模型循环执行。[排队手动压缩决策](../feature/2026-07-30-queued-manual-compaction.md)将该规则应用于持久多事件标记对，并拥有其标记与接纳语义。 ## 曾考虑的替代方案 @@ -36,8 +36,8 @@ Status: implemented ## 验证 -核心不变量测试会接受轮次之间的未知插件事件，同时继续拒绝位于该处的内置执行事件。钩子、压缩（compaction）、plan-mode、Code Mode 分发和审批的不变量配套组件会回放既有日志，并在没有开放轮次时，于提交前拒绝相同的执行作用域事件。会话标题服务测试会在并发刷新、会话脱离拒绝和最新修订接受场景下，固定一个直接追加的回退事件。JSONL 和 SQLite 往返测试会通过持久化生命周期排空保留追加在 `turn/end` 之后的标题；fork 测试会保留独立纯日志尾部，同时拒绝位于开放轮次内的边界。一个无密钥、经完整组装的 ACP（Agent Client Protocol）快照会将模型生成的标题延迟到 `turn/end` 之后，并固定一个不含合成轮次的独立提供方标题。生成的 API 和类型等价性目录不含任何已移除符号。 +核心不变量测试会接受轮次之间的未知插件事件，同时继续拒绝位于该处的内置执行事件。钩子、plan-mode、Code Mode 分发和审批的不变量配套组件会在没有开放轮次时拒绝其执行作用域事件；压缩配套组件则另外接受轮次之间平衡的 `turn: null` 手动标记对，并要求数字 owner 匹配一个开放轮次。会话标题服务测试会在并发刷新、会话脱离拒绝和最新修订接受场景下，固定一个直接追加的回退事件。JSONL 和 SQLite 往返测试会通过持久化生命周期排空保留追加在 `turn/end` 之后的标题；fork 测试会保留独立纯日志尾部，同时拒绝位于开放轮次内的边界。一个无密钥、经完整组装的 ACP（Agent Client Protocol）快照会将模型生成的标题延迟到 `turn/end` 之后，并固定一个不含合成轮次的独立提供方标题。生成的 API 和类型等价性目录不含任何已移除符号。 ## 后果 -轮次计数和结果重新只描述模型循环执行。独立事件会占用会话 seq，像其他追加一样启动尽快持久化，并且仅当操作承诺持久性时，才要求事件所有方请求显式持久性屏障。通用插件错误不再因核心默认的封闭规则而失败，因此每个需要执行关系的插件都必须自行声明并测试该关系。标题功能保留修订排序和生命周期持久化，同时减少了核心状态，不再重复类型 seam，并消除了轮次编号冲突。 +轮次计数和结果重新只描述模型循环执行。独立事件和手动压缩标记对会占用会话 seq，但不占用轮次编号；它们像其他追加一样启动尽快持久化，并且仅当操作承诺持久性时，才要求事件所有方请求显式持久性屏障。通用插件错误不再因核心默认的封闭规则而失败，因此每个需要执行关系的插件都必须自行声明并测试该关系。标题功能保留修订排序和生命周期持久化，同时减少了核心状态；手动压缩则获得持久控制，不产生合成轮次或轮次编号冲突。 diff --git a/apps/cli/README.i18n.yaml b/apps/cli/README.i18n.yaml index e7a4161df1..4d185f0adb 100644 --- a/apps/cli/README.i18n.yaml +++ b/apps/cli/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write apps/cli/README.md -README.md: aee08225febe34bb10ee1001c798db9d7daa8905 -README.zh.md: 8f38fd342a0433ca5f7645f896b81aa5392033ae +README.md: 4231aac2fe306b869c73d39e6ca6ebf54b255943 +README.zh.md: 81f6b94b88232fe44720358096c619893ef0244b diff --git a/apps/cli/README.md b/apps/cli/README.md index aee08225fe..4231aac2fe 100644 --- a/apps/cli/README.md +++ b/apps/cli/README.md @@ -12,6 +12,7 @@ The TUI surface: - treats the **invoking directory** as the workspace — sessions, relative paths, and workspace instructions resolve from the cwd (`dsh meta` is the sole exception, below); - tells the agent where its own source lives: after boot it adds a prompt section naming this harness checkout, resolved from the launcher's real path so it holds under a PATH symlink and an arbitrary cwd, so the self-referential `cordis` toolset can read and modify it; - applies the personal overlay from `~/.dsh` (see [app-boot's Personal config](../../packages/ui/app-boot/README.md#personal-config)): `config.yaml` patches the booted tree, while `.env` there is the credential provider's own store (never hoisted into the environment, so keys stay rotatable). Environment precedence is ambient > project `.env`. +- registers bare `/compact`: while the agent is idle, it summarizes useful older history even below automatic pressure, rejects arguments, and reports success only after the standalone replacement bracket is durable. A prompt submitted during compaction keeps its queue identity and starts after that checkpoint; injected context remains visible. `dsh meta` is that same TUI with this harness checkout as the workspace, so working on dsh itself needs no `cd`. It chdirs to the checkout root — resolved from the launcher's real path, the same root the source-path prompt section names — after the environment is settled, so precedence is unchanged while the session cwd and HMR watch root move together. Meta always starts a fresh session and accepts no default-surface options; use ordinary `dsh --resume ` to resume a persisted session. diff --git a/apps/cli/README.zh.md b/apps/cli/README.zh.md index 8f38fd342a..81f6b94b88 100644 --- a/apps/cli/README.zh.md +++ b/apps/cli/README.zh.md @@ -12,6 +12,7 @@ TUI 界面： - 将 **调用目录** 视为 workspace：会话、相对路径和 workspace 指令都从 cwd 解析（`dsh meta` 是唯一例外，见下文）； - 告知 agent 自身源码所在位置：启动后添加一个命名此 harness checkout 的提示词段。该路径从启动器的真实路径解析，因此在 PATH 符号链接和任意 cwd 下仍然有效，使自指的 `cordis` 工具集可以读取并修改它； - 应用 `~/.dsh` 中的个人覆盖（参见 [app-boot 的个人配置](../../packages/ui/app-boot/README.md#personal-config)）：`config.yaml` 修补已启动的树，而那里的 `.env` 是凭据 provider 自己的存储（绝不会被提升进环境，因此密钥始终可轮换）。环境优先级为环境中已有的值 > 项目 `.env`。 +- 注册裸 `/compact`：agent 空闲时，即使未达到自动压力，也会摘要有效的较早历史；该命令拒绝参数，并只在独立替换标记对持久化后报告成功。压缩（compaction）期间提交的提示词保留其队列身份，并在该检查点之后启动；注入的上下文仍保持可见。 `dsh meta` 是以本 harness checkout 为 workspace 的同一个 TUI，因此开发 dsh 自身无需 `cd`。它在环境确定之后才 chdir 到 checkout 根目录（从启动器的真实路径解析，与源码路径提示词段所指的根目录相同），因此环境优先级不变，而会话 cwd 与 HMR 监视根目录会一并移动。Meta 始终创建新会话，不接受默认界面的任何选项；恢复已持久化会话应使用普通的 `dsh --resume `。 diff --git a/apps/cli/composition.md b/apps/cli/composition.md index 870b926054..1339cf1153 100644 --- a/apps/cli/composition.md +++ b/apps/cli/composition.md @@ -76,6 +76,8 @@ flowchart LR cfg --> plugin_tui_token_meter plugin_tui_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] cfg --> plugin_tui_compact_basic + plugin_tui_command_compact["command-compact
@deepseek-ai/dsh-command-compact"] + cfg --> plugin_tui_command_compact plugin_tui_subagent["subagent
@deepseek-ai/dsh-subagent"] cfg --> plugin_tui_subagent plugin_tui_subagent_spawn["subagent-spawn
@deepseek-ai/dsh-subagent-spawn"] @@ -144,6 +146,7 @@ flowchart LR | `plan-mode` | `@deepseek-ai/dsh-plan-mode` | | `token-meter` | `@deepseek-ai/dsh-token-meter` | | `compact-basic` | `@deepseek-ai/dsh-compact-basic` | +| `command-compact` | `@deepseek-ai/dsh-command-compact` | | `subagent` | `@deepseek-ai/dsh-subagent` | | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | | `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` | diff --git a/apps/cli/config/base.cordis.yml b/apps/cli/config/base.cordis.yml index 4bde1e4b6a..fe94be48cf 100644 --- a/apps/cli/config/base.cordis.yml +++ b/apps/cli/config/base.cordis.yml @@ -201,6 +201,11 @@ - id: compact-basic name: '@deepseek-ai/dsh-compact-basic' +# Human `/compact`: one useful reduction below the automatic threshold. Backend +# independent, so it follows whichever compaction service this leaf mounts. +- id: command-compact + name: '@deepseek-ai/dsh-command-compact' + - id: subagent name: '@deepseek-ai/dsh-subagent' diff --git a/apps/cli/package.json b/apps/cli/package.json index 997cea8e5f..106a838774 100644 --- a/apps/cli/package.json +++ b/apps/cli/package.json @@ -47,6 +47,7 @@ "@deepseek-ai/dsh-client-ui-trajectory": "workspace:^", "@deepseek-ai/dsh-client-ui-workspace": "workspace:^", "@deepseek-ai/dsh-code-runtime-worker": "workspace:^", + "@deepseek-ai/dsh-command-compact": "workspace:^", "@deepseek-ai/dsh-command-goal": "workspace:^", "@deepseek-ai/dsh-commands": "workspace:^", "@deepseek-ai/dsh-compact-basic": "workspace:^", diff --git a/apps/cli/tests/snapshots/queued-manual-compact/terminal.expected.txt b/apps/cli/tests/snapshots/queued-manual-compact/terminal.expected.txt new file mode 100644 index 0000000000..0df46a7018 --- /dev/null +++ b/apps/cli/tests/snapshots/queued-manual-compact/terminal.expected.txt @@ -0,0 +1,128 @@ +terminal 100x36 buffer=normal length=66 base=30 viewport=30 +lifecycle started=1 stopped=0 progress=inactive +title "Reply with exactly the word: — DSH TUI snapshot" +cursor hidden column=7 viewportRow=35 bufferRow=65 +buffer +0| " DEEPSEEK HARNESS" + style 1-8 fg=bright-magenta bold + style 10-16 bold +1| " Reply with exactly the word:" + style 1-28 dim +2| " main-session" + style 1-12 dim +3| +4| "Context · snapshot-seed" + style 0-22 dim +5| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +6| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +7| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +8| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +9| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +10| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +11| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +12| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +13| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +14| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +15| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +16| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +17| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +18| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-99 dim +19| "Older snapshot context. Older snapshot context. Older snapshot context. Older snapshot context. " + style 0-94 dim +20| +21| "You " + style 0-2 fg=bright-magenta bold underline +22| "Reply with exactly the word: ONE. No tools. " +23| +24| "Assistant " + style 0-8 fg=bright-magenta bold underline +25| "Reasoning " + style 0-8 dim italic +26| "The user wants me to reply with exactly the word \"ONE\" and use no tools. " + style 0-71 dim italic +27| "ONE " +28| "Model wait 0.0s · Completed 2026-07-21 12:00:00 " + style 0-46 dim +29| +30| "Keyboard shortcuts " + style 0-17 fg=bright-magenta bold +31| "Enter send • Shift/Alt+Enter newline • Up/Down prompt history " + style 0-60 dim +32| "Esc cancel turn • Ctrl+O cycle cards (collapse/expand/hide) • Ctrl+R toggle reasoning • Ctrl+L " + style 0-99 dim +33| "redraw " + style 0-5 dim +34| "Ctrl+C cancel while running; clear input or exit while idle • Ctrl+D exit " + style 0-72 dim +35| " " +36| "/clear — Clear the transcript view (session history is unchanged) " + style 0-64 dim +37| "/compact — Compact older conversation history " + style 0-44 dim +38| "/exit — Exit after the active turn reaches idle " + style 0-46 dim +39| "/help — Show keyboard shortcuts and commands " + style 0-43 dim +40| "/model [[provider/]model] — Show or switch this session's model " + style 0-62 dim +41| "/palette — Show every color and attribute role this terminal renders " + style 0-67 dim +42| "/quit — Exit after the active turn reaches idle " + style 0-46 dim +43| "/reload — EXPERIMENTAL (dev): re-read loader config files and apply the diff (idle only) " + style 0-87 dim +44| "/resume — List this workspace's resumable sessions " + style 0-49 dim +45| "/status — Show session diagnostics, system prompt, and registered tools " + style 0-70 dim +46| "/skill: [instructions] — load a skill into the conversation " + style 0-64 dim +47| +48| "Context · snapshot-injector" + style 0-26 dim +49| "Injected while compaction was running. " + style 0-37 dim +50| +51| "… earlier context was compacted … " + style 0-32 dim +52| +53| "You " + style 0-2 fg=bright-magenta bold underline +54| "Reply with exactly the word: TWO. No tools. " +55| +56| "Compacted 2 history items (~387 tokens). " + style 0-39 dim +57| +58| "Assistant " + style 0-8 fg=bright-magenta bold underline +59| "Reasoning " + style 0-8 dim italic +60| "The user wants me to reply with exactly the word \"TWO\" and no tools. " + style 0-67 dim italic +61| "TWO " +62| "Model wait 0.0s · Completed 2026-07-21 12:00:00 " + style 0-46 dim +63| +64| "/workspace/project deepseek-v4-flash ↑2.9k ↓41 cache 49% 3% cont" + style 0-49 fg=bright-magenta bold + style 52-68 dim + style 71-90 dim + style 93-99 dim +65| " dsh ◍ " + style 1-3 fg=bright-magenta bold + style 5-6 dim + style 7-7 inverse diff --git a/apps/cli/tests/tui.snapshot.ts b/apps/cli/tests/tui.snapshot.ts index 078e4c191e..01adeb91b8 100644 --- a/apps/cli/tests/tui.snapshot.ts +++ b/apps/cli/tests/tui.snapshot.ts @@ -11,8 +11,12 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local' import WorkerCodeRuntime from '@deepseek-ai/dsh-code-runtime-worker' import CommandService from '@deepseek-ai/dsh-commands' +import * as CommandCompact from '@deepseek-ai/dsh-command-compact' +import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' +import type { SummarizationInput } from '@deepseek-ai/dsh-compact-basic/src/summarizer.ts' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' import * as FsPolicy from '@deepseek-ai/dsh-fs-policy' +import { createUserMessage } from '@deepseek-ai/dsh-llm' import * as ToolFs from '@deepseek-ai/dsh-tool-fs' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import { installLlmReplay, parseSessionLog } from '@deepseek-ai/dsh-llm-replay' @@ -45,6 +49,8 @@ type ScenarioInteraction = 'skill-invocation-policy' interface Scenario { name: string + /** Replay fixture owned by an earlier scenario, for a derived presentation case. */ + fixture?: string composition: Composition expectedTools: string[] expectedEventCounts?: Record @@ -68,6 +74,13 @@ interface Scenario { spillMaxInlineBytes?: number /** Run scenario-specific terminal input instead of replaying recorded user prompts. */ interaction?: ScenarioInteraction + /** + * Mount a deterministic compaction backend plus `/compact`, then run the + * human command with a held summary while a prompt and injected context + * arrive. Proves queued input waits for the standalone bracket's durability + * checkpoint instead of racing the replacement. + */ + manualCompact?: boolean } const SCENARIOS: Scenario[] = [ @@ -80,6 +93,14 @@ const SCENARIOS: Scenario[] = [ leavePlanModeAfterFirstTurn: true, recorded: true, }, + { + name: 'queued-manual-compact', + fixture: 'multi-turn-conversation', + composition: 'native', + expectedTools: [], + recorded: false, + manualCompact: true, + }, { name: 'todo-plan', composition: 'native', @@ -149,6 +170,44 @@ function snapshotModeFromEnv(value: string | undefined): SnapshotMode { const MODE = snapshotModeFromEnv(process.env.DSH_SNAPSHOT) const observedScenarios = new Set() +const workerState = Reflect.get(globalThis, '__vitest_worker__') as + | { readonly config?: { readonly testNamePattern?: RegExp } } + | undefined +// Worker argv omits the parent CLI's `-t`; the serialized runner config is the +// authoritative distinction between a focused replay and the full suite. +const TEST_NAME_FILTERED = workerState?.config?.testNamePattern !== undefined + +/** + * Deterministic keyless summary that pauses so the scenario can submit a real + * prompt and inject context while manual compaction holds turn admission. + */ +class DeferredSnapshotCompactService extends BasicCompactService { + readonly summaryStarted = Promise.withResolvers() + readonly releaseSummary = Promise.withResolvers() + + override async summarize( + _input: SummarizationInput, + _agent: Agent, + signal?: AbortSignal, + ): Promise<{ summary: [{ type: 'text'; text: string }]; provider: string; model: string }> { + this.summaryStarted.resolve(undefined) + await this.releaseSummary.promise + signal?.throwIfAborted() + return { + summary: [{ type: 'text', text: 'Keyless manual compaction checkpoint.' }], + provider: 'snapshot', + model: 'snapshot-compactor', + } + } +} + +/** Seed between-turn model-visible history without inventing a loop execution. */ +function seedCompactableHistory(agent: Agent): void { + agent.inject(createUserMessage({ + content: [{ type: 'text', text: 'Older snapshot context. '.repeat(60) }], + source: { kind: 'plugin', plugin: 'snapshot-seed' }, + })) +} function snapshotDisplayPath(displayPath: string, cwd: string, displayCwd: string): string { const rel = relative(cwd, displayPath) @@ -161,10 +220,15 @@ function scenarioDir(scenario: Scenario): string { return join(SNAPSHOTS_DIR, scenario.name) } +/** Directory owning the replay fixture: the scenario's own, or the one it derives from. */ +function fixtureDir(scenario: Scenario): string { + return join(SNAPSHOTS_DIR, scenario.fixture ?? scenario.name) +} + function childFixturePaths(scenario: Scenario): string[] { return Array.from( { length: scenario.childSessions ?? 0 }, - (_, index) => join(scenarioDir(scenario), `session.${index + 1}.jsonl`), + (_, index) => join(fixtureDir(scenario), `session.${index + 1}.jsonl`), ) } @@ -206,6 +270,24 @@ async function settleTerminal(terminal: HeadlessTerminal): Promise { if (stable < 3) throw new Error('TUI frames did not quiesce within 200ms') } +/** Bound deterministic in-process coordination waits with actionable state. */ +async function snapshotDeadline( + operation: Promise, + detail: () => string, +): Promise { + let timer: ReturnType | undefined + try { + return await Promise.race([ + operation, + new Promise((_resolve, reject) => { + timer = setTimeout(() => { reject(new Error(detail())) }, 5_000) + }), + ]) + } finally { + if (timer !== undefined) clearTimeout(timer) + } +} + async function mountScenarioContext( scenario: Scenario, cwd: string, @@ -232,6 +314,9 @@ async function mountScenarioContext( skills: { local: { agentsHome: join(cwd, '.agents') } }, }) await ctx.plugin(TokenMeterService) + if (scenario.manualCompact === true) { + await ctx.plugin(DeferredSnapshotCompactService, { auto: false }) + } await ctx.plugin(LocalSubprocessService) await ctx.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 }) await ctx.plugin(SnapshotLocalFileSystem, { cwd: '/' }) @@ -249,6 +334,7 @@ async function mountScenarioContext( await ctx.plugin(ToolWorkflow) await ctx.plugin(ToolRalph) await ctx.plugin(CommandService) + if (scenario.manualCompact === true) await ctx.plugin(CommandCompact) if (scenario.enterPlanMode === true) { await ctx.plugin(PlanModeService, { section: 'Snapshot plan mode instructions.' }) } @@ -277,8 +363,7 @@ interface ScenarioResult { async function runScenario(scenario: Scenario): Promise { const clock = vi.spyOn(Date, 'now').mockReturnValue(new Date(2026, 6, 21, 12, 0, 0).getTime()) - const dir = scenarioDir(scenario) - const fixtureFile = join(dir, 'session.jsonl') + const fixtureFile = join(fixtureDir(scenario), 'session.jsonl') const childFiles = childFixturePaths(scenario) const prompts = userPrompts(await readFile(fixtureFile, 'utf8')) if (scenario.interaction === undefined) { @@ -292,7 +377,7 @@ async function runScenario(scenario: Scenario): Promise { const terminal = new HeadlessTerminal(100, 36) try { if (scenario.seedWorkspace === true) { - const source = join(scenarioDir(scenario), 'workspace') + const source = join(fixtureDir(scenario), 'workspace') await cp(source, cwd, { recursive: true }) } ctx = await mountScenarioContext(scenario, cwd, displayCwd, fixtureFile, childFiles) @@ -308,6 +393,7 @@ async function runScenario(scenario: Scenario): Promise { agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, }) const agent: Agent = handle.agent + if (scenario.manualCompact === true) seedCompactableHistory(agent) controller = createTuiChat(ctx, { sessionId: 'main-session', theme: { color: true }, @@ -380,6 +466,14 @@ async function runScenario(scenario: Scenario): Promise { } let remainingPrompts = prompts + let queuedPrompt: string | undefined + let manualOrder: string[] | undefined + let manualCommandId: string | undefined + if (scenario.manualCompact === true) { + expect(prompts.length, 'queued manual compaction needs a second replayed prompt').toBeGreaterThanOrEqual(2) + queuedPrompt = prompts.at(-1) + remainingPrompts = prompts.slice(0, -1) + } if (scenario.enterPlanMode === true) { const firstPrompt = prompts[0]! terminal.send(`/plan ${firstPrompt}`) @@ -396,12 +490,86 @@ async function runScenario(scenario: Scenario): Promise { } for (const prompt of remainingPrompts) { + const admitted = agent.session.events.filter(event => + event.type === 'user/message' && event.data.source.kind === 'user').length terminal.send(prompt) terminal.send('\r') + await terminal.flush() + await expect.poll(() => agent.session.events.filter(event => + event.type === 'user/message' && event.data.source.kind === 'user').length).toBe(admitted + 1) await agent.whenIdle() await settleTerminal(terminal) } + if (scenario.manualCompact === true && queuedPrompt !== undefined) { + terminal.send('/help') + terminal.send('\r') + await settleTerminal(terminal) + expect(await terminal.snapshot({ includeScrollback: true })) + .toContain('/compact — Compact older conversation history') + + const compact = ctx.compact as DeferredSnapshotCompactService + const inbox: string[] = [] + manualOrder = [] + ctx.on('agent/inbox/enqueue', (subject, item) => { + if (subject === agent) inbox.push(`enqueue:${item.placement}:${item.id}`) + }) + ctx.on('agent/inbox/dequeue', (subject, message) => { + if (subject === agent) inbox.push(`dequeue:${message.id}`) + }) + ctx.on('session/event', (session, event) => { + if (session !== agent.session) return + if (event.type === 'command/run' && event.data.name === 'compact') { + manualCommandId = event.data.commandId + manualOrder?.push('command/run') + } + if (event.type === 'command/done' && event.data.commandId === manualCommandId) { + manualOrder?.push('command/done') + } + if (event.type.startsWith('compact/')) manualOrder?.push(event.type) + if (event.type === 'user/message' + && event.data.source.kind === 'plugin' + && event.data.source.plugin === 'compact') manualOrder?.push('checkpoint') + if (event.type === 'turn/start') manualOrder?.push(`turn/start:${event.data.trigger.kind}`) + }) + ctx.on('session/flush', (session) => { + if (session === agent.session) manualOrder?.push('flush') + }) + + terminal.send('/compact') + terminal.send('\r') + await terminal.flush() + await snapshotDeadline(compact.summaryStarted.promise, () => + `manual summary did not start; status=${agent.status}; tail=${ + agent.session.events.slice(-8).map(event => event.type).join(',') + }`) + + // Real keystrokes: the prompt keeps its ordinary queue identity while + // admission is reserved, and an injection appends immediately. + terminal.send(queuedPrompt) + terminal.send('\r') + await terminal.flush() + await expect.poll(() => inbox.length).toBe(1) + agent.inject(createUserMessage({ + content: [{ type: 'text', text: 'Injected while compaction was running.' }], + source: { kind: 'plugin', plugin: 'snapshot-injector' }, + })) + expect(inbox[0]).toMatch(/^enqueue:queued:/u) + expect(agent.status).toBe('idle') + expect(agent.session.events.some(event => event.type === 'user/message' + && event.data.source.kind === 'user' + && event.data.content.some(block => block.type === 'text' && block.text === queuedPrompt))).toBe(false) + + const idle = agent.whenIdle() + compact.releaseSummary.resolve(undefined) + await snapshotDeadline(idle, () => + `manual compaction did not reach idle; status=${agent.status}; order=${manualOrder?.join(',') ?? ''}; tail=${ + agent.session.events.slice(-12).map(event => event.type).join(',') + }`) + await settleTerminal(terminal) + expect(inbox).toEqual([inbox[0], `dequeue:${inbox[0]?.slice('enqueue:queued:'.length) ?? ''}`]) + } + const events: SessionEvent[] = [...agent.session.events] const firstHeader = events.find(event => event.type === 'request/header') expect(firstHeader?.type === 'request/header' && firstHeader.data.header.system) @@ -437,6 +605,87 @@ async function runScenario(scenario: Scenario): Promise { expect(events.filter(event => event.type === 'user/message' && event.data.source.kind === 'plugin').map(event => (event.data as { content: unknown }).content)) .toContainEqual([{ type: 'text', text: 'The user switched this session back to the default mode.' }]) } + if (scenario.manualCompact === true) { + const compactStart = events.find(event => event.type === 'compact/start') + const compactSummary = events.find(event => event.type === 'compact/summary') + const compactCheckpoint = events.find(event => event.type === 'user/message' + && event.data.source.kind === 'plugin' && event.data.source.plugin === 'compact') + const injectedEvent = events.find(event => event.type === 'user/message' + && event.data.source.kind === 'plugin' && event.data.source.plugin === 'snapshot-injector') + const compactEnd = events.find(event => event.type === 'compact/end') + expect(compactStart?.data.turn).toBeNull() + expect(compactEnd?.data.turn).toBeNull() + expect(events.filter(event => event.type === 'compact/summary')).toHaveLength(1) + if (compactStart === undefined || compactSummary === undefined + || compactCheckpoint === undefined || injectedEvent === undefined + || compactEnd === undefined) { + throw new Error('manual compaction snapshot is missing its durable marker, summary, checkpoint, or injection') + } + // The markers are time points, not an exclusive container: unrelated + // idle injection is allowed between them while the selected span stays stable. + expect(compactStart.seq).toBeLessThan(injectedEvent.seq) + expect(injectedEvent.seq).toBeLessThan(compactSummary.seq) + expect(compactSummary.seq).toBeLessThan(compactCheckpoint.seq) + expect(compactCheckpoint.seq).toBeLessThan(compactEnd.seq) + + const manualTimeline = manualOrder ?? [] + const commandRunIndex = manualTimeline.indexOf('command/run') + const compactStartIndex = manualTimeline.indexOf('compact/start') + const compactEndIndex = manualTimeline.indexOf('compact/end') + const firstFlushIndex = manualTimeline.indexOf('flush') + const queuedTurnIndex = manualTimeline.indexOf('turn/start:message') + const commandDoneIndex = manualTimeline.indexOf('command/done') + expect(manualTimeline.filter(item => item === 'command/run')).toHaveLength(1) + expect(manualTimeline.filter(item => item === 'command/done')).toHaveLength(1) + expect(compactStartIndex).toBeGreaterThan(commandRunIndex) + expect(compactEndIndex).toBeGreaterThan(compactStartIndex) + expect(firstFlushIndex).toBeGreaterThan(compactEndIndex) + expect(queuedTurnIndex).toBeGreaterThan(firstFlushIndex) + expect(commandDoneIndex).toBeGreaterThan(firstFlushIndex) + + const commandRun = events.find(event => event.type === 'command/run' + && event.data.name === 'compact') + const commandRunId = commandRun?.type === 'command/run' + ? commandRun.data.commandId + : undefined + const commandDone = events.find(event => event.type === 'command/done' + && event.data.commandId === commandRunId) + expect(commandRun?.type === 'command/run' && commandRun.data).toEqual({ + commandId: commandRunId, + name: 'compact', + args: '', + source: { kind: 'user' }, + }) + expect(commandDone?.type === 'command/done' && commandDone.data).toEqual({ + commandId: commandRunId, + kind: 'success', + text: 'Compacted 2 history items (~387 tokens).', + }) + expect(commandRun !== undefined && commandRun.seq < compactStart.seq).toBe(true) + expect(commandDone !== undefined && commandDone.seq > compactEnd.seq).toBe(true) + expect(agent.session.surface.nodes).not.toContain(commandRun?.seq) + expect(agent.session.surface.nodes).not.toContain(commandDone?.seq) + + // The command line itself never becomes a prompt. + expect(events.some(event => event.type === 'user/message' + && event.data.source.kind === 'user' + && event.data.content.some(block => block.type === 'text' && block.text.trim() === '/compact'))).toBe(false) + const derived = agent.session.deriveMessages().map(message => message.content + .map(block => block.type === 'text' ? block.text : '') + .join('')) + const checkpoint = derived.findIndex(text => text.includes('Keyless manual compaction checkpoint.')) + const injected = derived.findIndex(text => text.includes('Injected while compaction was running.')) + const queued = derived.findIndex(text => text === queuedPrompt) + expect(checkpoint).toBe(0) + expect(injected).toBeGreaterThan(checkpoint) + expect(queued).toBeGreaterThan(injected) + expect(derived).not.toContain('/compact') + expect(derived).not.toContain('Compacted 2 history items (~387 tokens).') + expect(derived.filter(text => text.includes('Injected while compaction was running.'))).toHaveLength(1) + expect(compactSummary.data.shadowedSeqs).not.toContain(injectedEvent.seq) + const queuedTurn = events.findLast(event => event.type === 'turn/start') + expect(queuedTurn !== undefined && compactEnd.seq < queuedTurn.seq).toBe(true) + } if (scenario.spillMaxInlineBytes !== undefined) { // The REAL pipeline ran (tools execute on replay too): the durable // dispatch copy is bounded to a preview + locator under the run cwd, @@ -514,7 +763,23 @@ describe('TUI recorded-session terminal snapshots', () => { }) afterAll(async () => { - expect([...observedScenarios].sort()).toEqual(SCENARIOS.map(scenario => scenario.name).sort()) + const scenarioNames = SCENARIOS.map(scenario => scenario.name).sort() + const observedNames = [...observedScenarios].sort() + if (TEST_NAME_FILTERED) { + expect(observedNames).not.toHaveLength(0) + expect(scenarioNames).toEqual(expect.arrayContaining(observedNames)) + } else { + expect(observedNames).toEqual(scenarioNames) + } + for (const [index, scenario] of SCENARIOS.entries()) { + if (scenario.fixture === undefined) continue + const sourceIndex = SCENARIOS.findIndex(candidate => candidate.name === scenario.fixture) + expect(sourceIndex, `${scenario.name} fixture source ${scenario.fixture} must exist`).toBeGreaterThanOrEqual(0) + expect(sourceIndex, `${scenario.name} fixture source must precede it`).toBeLessThan(index) + const source = SCENARIOS[sourceIndex] + expect(source?.fixture, `${scenario.name} fixture source must own its replay files`).toBeUndefined() + expect(source?.recorded, `${scenario.name} fixture source must be recordable`).toBe(true) + } const directories = (await readdir(SNAPSHOTS_DIR, { withFileTypes: true })) .filter(entry => entry.isDirectory()) .map(entry => entry.name) @@ -522,14 +787,14 @@ afterAll(async () => { expect(directories).toEqual(SCENARIOS.map(scenario => scenario.name).sort()) for (const scenario of SCENARIOS) { const expected = [ - 'session.jsonl', + ...scenario.fixture === undefined ? ['session.jsonl'] : [], 'terminal.expected.txt', - ...scenario.seedWorkspace === true ? ['workspace'] : [], + ...scenario.seedWorkspace === true && scenario.fixture === undefined ? ['workspace'] : [], ...Array.from({ length: scenario.childSessions ?? 0 }, (_, index) => `session.${index + 1}.jsonl`), ].sort() expect((await readdir(scenarioDir(scenario))).sort()).toEqual(expected) for (const fixture of ['session.jsonl', ...childFixturePaths(scenario).map(path => basename(path))]) { - const content = await readFile(join(scenarioDir(scenario), fixture), 'utf8') + const content = await readFile(join(fixtureDir(scenario), fixture), 'utf8') expect(scrubRequestHeaders(content), `${scenario.name}/${fixture} carries request-header bulk`).toBe(content) } } diff --git a/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md index 47ba98cf05..1da9b9a45e 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md @@ -1,6 +1,7 @@ - listbox "Trigger suggestions": - text: Commands - - option "goal set or view the goal for a long-running task" [selected] + - option "compact Compact older conversation history" [selected] + - option "goal set or view the goal for a long-running task" - option "permission Switch the permission preset (sandbox mode + approval policy)" - option "plan Enter or leave plan mode" - option "model Select the model for this conversation" diff --git a/docs/architecture.i18n.yaml b/docs/architecture.i18n.yaml index 1ee5e3a3aa..e305eb5f42 100644 --- a/docs/architecture.i18n.yaml +++ b/docs/architecture.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/architecture.md -architecture.md: 929d2d28fd93d06cf18abeeac968860048657faf -architecture.zh.md: c9e495359d804c49181e78b6099c4aa2b1125d92 +architecture.md: 75340b6fb3e4e109974bcb9d9ccabec004d853e1 +architecture.zh.md: 0955a40f3571fe9146c75a6b1094f945fcc5219c diff --git a/docs/architecture.md b/docs/architecture.md index 929d2d28fd..75340b6fb3 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -130,11 +130,11 @@ Adapter failures close their step before `agent/request-error` receives the exac Other failures use `agent/error`. Cancellation and disposal beat recovery. Before request-header commit, the turn signal cancels asynchronous model-capability preparation; undispatched tools get synthetic `tool/call`/`ABORTED_BEFORE_DISPATCH` pairs. Effective `cancel(cause)` emits its cause before queue clearing and abort; observers cannot veto; idle calls emit nothing. Durability records user or parent cancellation as `aborted`, teardown as `disposed`; teardown awaits quiescence. The cause affects reporting, not late result-context handling ([decision](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)). -Turn and step events are turn-enclosed; idle injected `user/message` events may sit between turns. Reload closes an interrupted tail with a synthetic turn end. After close, only `agent/error` reports failures. Each turn has one [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). +Turn and step events are turn-enclosed. Idle `user/message` and standalone `compact/* { turn: null }` consume no turn; their lock-time markers may interleave with injection. Reload synthesizes interrupted turn ends; `session/end-seed` distinguishes stale compaction orphans from live locks. After close, only `agent/error` reports failures. Each turn has one [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). ### Agent Handles -`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins use full `send()` options or `followup()`, `steer()`, and `inject()` presets; `cancel()` and `whenIdle()` control lifecycle. One awaited disposer coordinates teardown ownership. +`ctx.agents` owns agents, returning `AgentHandle { agent, dispose() }`. Plugins use `send()` or `followup()`, `steer()`, and `inject()` presets; [`reserveTurnAdmission()`](../packages/core/agent/README.md#agent-interface-typests) synchronously reserves idle for durable work without changing queued prompt identity. `cancel()` and `whenIdle()` control lifecycle. Awaited disposal owns teardown. ### Agent Scope @@ -150,7 +150,7 @@ The session log is authoritative. `deriveMessages()` projects model history; raw Durability is a plugin concern. Backends eagerly drain synchronous `session/event` notifications. `session/flush` barriers precede each request and top-level tool dispatch, then follow `turn/end` before another queued turn or idle observation. `SessionPersistence` stores `SessionEvent` directly and metadata in `SessionHeader`; JSONL defaults to checksummed Zstandard, while SQLite shares the contract ([decision](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md)). -Log-only events may sit between turns. Owners append through `Session`, flushing only for durability. `session/title` relies on eager persistence and lifecycle drains. Latest title wins with provenance; fallback and provider work never delays responses. Such records are fork boundaries, so forks inherit titles ([decision](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md)). +Between turns, owners append log-only events through `Session`, flushing only for durability. `session/title` needs eager persistence and lifecycle drains; manual compaction flushes its bracket before releasing admission. Title work never delays responses; latest wins with provenance. Title records are inherited fork boundaries ([decision](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md)). ### Model Content diff --git a/docs/architecture.zh.md b/docs/architecture.zh.md index c9e495359d..0955a40f35 100644 --- a/docs/architecture.zh.md +++ b/docs/architecture.zh.md @@ -130,11 +130,11 @@ idle inject: 其他故障使用 `agent/error`。取消和资源释放优先于恢复。在提交请求头之前，轮次信号会取消异步模型能力准备；尚未分派的工具会得到合成的 `tool/call`/`ABORTED_BEFORE_DISPATCH` 对。实际生效的 `cancel(cause)` 在清空队列和中止前发出原因；观察方不能否决；空闲调用不发事件。持久化层将用户或父级取消记录为 `aborted`，拆卸记录为 `disposed`；拆卸会等待完全停稳。原因只影响报告方式，不影响延迟完成的结果上下文处理（[决策](../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md)）。 -轮次和步骤事件均位于轮次边界内；空闲时注入的 `user/message` 可以位于两个轮次之间。重新加载会用合成的轮次结束事件闭合中断尾部。关闭后仅由 `agent/error` 报告故障。每个轮次有一个 [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap)。 +轮次和步骤事件均位于轮次边界内。空闲 `user/message` 与独立的 `compact/* { turn: null }` 不占用轮次；其锁定时刻标记可以与注入交错。重新加载会为中断的轮次合成结束事件；`session/end-seed` 区分陈旧的压缩遗留项与活跃锁。关闭后仅由 `agent/error` 报告故障。每个轮次有一个 [TurnEndReason](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap)。 ### Agent 句柄 -`ctx.agents` 拥有活跃 agent，并返回 `AgentHandle { agent, dispose() }`。插件使用全部 `send()` 选项，或 `followup()`、`steer()` 和 `inject()` 预设；`cancel()` 与 `whenIdle()` 控制生命周期。一个需等待完成的 disposer 协调拆卸归属。 +`ctx.agents` 拥有 agent，返回 `AgentHandle { agent, dispose() }`。插件使用 `send()`，或使用 `followup()`、`steer()` 和 `inject()` 预设；[`reserveTurnAdmission()`](../packages/core/agent/README.md#agent-interface-typests) 为持久工作同步预留空闲状态，同时不改变排队提示词身份。`cancel()` 与 `whenIdle()` 控制生命周期。需等待完成的资源释放负责拆卸。 ### Agent 作用域 @@ -150,7 +150,7 @@ idle inject: 持久性由插件负责。后端会尽快排空同步的 `session/event` 通知。`session/flush` 屏障位于每次请求与顶层工具分发之前，并在 `turn/end` 之后、处理另一个已排队轮次或观察到空闲状态之前执行。`SessionPersistence` 直接存储 `SessionEvent`，并将元数据存入 `SessionHeader`；JSONL 默认采用带校验和的 Zstandard，SQLite 遵循同一契约（[决策](../.agents/notes/implemented/bug-fix/2026-07-21-semantic-session-checkpoints.md)）。 -纯日志事件可以位于轮次之间。事件所有方通过 `Session` 追加，仅为持久性而刷写。`session/title` 依赖尽快持久化与生命周期排空。最新标题按后写覆盖并携带来源信息；回退与提供方工作绝不会延迟响应。这类记录可作为 fork 边界，因此 fork 会继承标题（[决策](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md)）。 +在轮次之间，事件所有方通过 `Session` 追加纯日志事件，仅为持久性而刷写。`session/title` 需要尽快持久化与生命周期排空；手动压缩会在释放轮次接纳预留前 flush 其标记对。标题工作绝不延迟响应；最新标题按后写覆盖并携带来源信息。标题记录是可继承的 fork 边界（[决策](../.agents/notes/implemented/feature/2026-07-21-log-backed-session-titles.md)）。 ### 模型内容 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 12bde08080..c862dc7f93 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -349,7 +349,7 @@ Source: [`packages/code-runtime/code-runtime-worker/src/index.ts:25`](../package ## `@deepseek-ai/dsh-compact-basic` -Requires: `llm` · `tokenMeter` +Requires: `llm` · `tokenMeter` · `sessions` ```ts config-catalog /** Basic compaction configuration with an optional exact-target policy table. */ @@ -2308,6 +2308,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co - `@deepseek-ai/dsh-client-ui-theme` ([`packages/client/ui-theme/src/index.ts`](../packages/client/ui-theme/src/index.ts)) - `@deepseek-ai/dsh-client-ui-trajectory` ([`packages/client/ui-trajectory/src/index.ts`](../packages/client/ui-trajectory/src/index.ts)) - `@deepseek-ai/dsh-client-ui-workspace` ([`packages/client/ui-workspace/src/index.ts`](../packages/client/ui-workspace/src/index.ts)) +- `@deepseek-ai/dsh-command-compact` — requires `commands` · `compact` ([`packages/compact/command-compact/src/index.ts`](../packages/compact/command-compact/src/index.ts)) - `@deepseek-ai/dsh-command-goal` — requires `commands` · `goals` ([`packages/goal/command-goal/src/index.ts`](../packages/goal/command-goal/src/index.ts)) - `@deepseek-ai/dsh-commands` ([`packages/ui/commands/src/index.ts`](../packages/ui/commands/src/index.ts)) - `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts)) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 497e0d220d..a7ff21e2f4 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -32,7 +32,7 @@ Effective broad cancellation was requested, before queued/outbox work is cleared Types: [Agent](../core-data-structures/core.md) · [AgentCancelCause](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) ### `agent/created` — emit @@ -54,7 +54,7 @@ A fully configured agent and live session were published. Setup is composition-o Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:264`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -74,7 +74,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence and sco Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:259`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:273`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -96,7 +96,7 @@ A step or turn errored. The machine reports a failure here (plus the logger) eve Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:433`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:447`](../../packages/core/agent/src/types.ts) ### `agent/inbox/dequeue` — emit @@ -117,7 +117,7 @@ The driver claimed one item out of the inbox: a queued item at a turn boundary, Types: [Agent](../core-data-structures/core.md) · [InboxItem](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:297`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:311`](../../packages/core/agent/src/types.ts) ### `agent/inbox/discard` — emit @@ -140,7 +140,7 @@ Pending inbox items were dropped without delivering them, so every enqueue occur Types: [Agent](../core-data-structures/core.md) · [InboxItem](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:309`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:323`](../../packages/core/agent/src/types.ts) ### `agent/inbox/enqueue` — emit @@ -161,7 +161,7 @@ An item entered the queued or steering inbox. `placement` is the acceptance-time Types: [Agent](../core-data-structures/core.md) · [InboxItem](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:278`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:292`](../../packages/core/agent/src/types.ts) ### `agent/inbox/update` — emit @@ -181,7 +181,7 @@ A still-pending queued item changed content. The item id, placement, and positio Types: [Agent](../core-data-structures/core.md) · [InboxItem](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:287`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:301`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -204,7 +204,7 @@ Allow, rewrite, or block one claimed prompt before it becomes a user message or Types: [Agent](../core-data-structures/core.md) · [PromptDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [UserMessage](../core-data-structures/session.md) -Source: [`packages/core/agent/src/types.ts:346`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -228,7 +228,7 @@ Replace the frozen call configuration. `await next()` yields the config the mach Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:372`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:386`](../../packages/core/agent/src/types.ts) ### `agent/request-error` — waterfall @@ -258,7 +258,7 @@ Handle a model-request failure after its failed step has closed but before the f Types: [Agent](../core-data-structures/core.md) · [LlmFailure](../core-data-structures/llm-streaming.md) · [RequestError](../core-data-structures/core.md) · [RequestErrorAction](../core-data-structures/core.md) · [ResolvedRetryPolicy](../core-data-structures/llm-streaming.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:391`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:405`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -280,7 +280,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:332`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:346`](../../packages/core/agent/src/types.ts) ### `agent/settled` — emit @@ -305,7 +305,7 @@ One drain chain reached its terminal turn: that turn's `turn/end` is already com Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SettleReason](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:420`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:434`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -325,7 +325,7 @@ Agent status changed (`idle` ⇄ `running`). `send()` does not enter `running` s Types: [Agent](../core-data-structures/core.md) · [AgentStatus](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:268`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:282`](../../packages/core/agent/src/types.ts) ### `agent/step` — serial @@ -349,7 +349,7 @@ Awaited serial checkpoint before EVERY request of a turn is built (the first as Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:359`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:373`](../../packages/core/agent/src/types.ts) ### `agent/turn-stopping` — serial @@ -375,7 +375,7 @@ The turn is about to close: the model owes no response (no live tool calls, no f Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:406`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:420`](../../packages/core/agent/src/types.ts) ## `agent-loop/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 478a147361..f2c0b9f07e 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -463,6 +463,26 @@ Abstract compaction service. Implementations own trigger policy, retention, and */ abstract compactIfNeeded( agent: CompactAgentContext, trigger: CompactionTrigger, signal: AbortSignal, ): Promise +/** + * Explicitly compact useful history even below automatic pressure thresholds. + * Implementations reserve idle turn admission synchronously before any + * asynchronous work, select a useful range without writing on a no-op, then + * append a standalone `compact/start` before summarization. That durable + * marker is the compaction lock until one `compact/end` attempt. Later waking + * prompts remain accepted in FIFO order and start only after the optional + * durability checkpoint and admission release. Context injected while the + * summary runs may sit between the marker pair; only the selected span must + * remain stable. + * + * @param agent - idle agent whose durable history should be compacted. + * @param signal - command-owned cancellation forwarded to summarization. + * @returns the compaction result, or `null` when no safe useful range exists. + * @throws {@link ManualCompactionError} for expected busy, changed-span, + * summarization/shrink, commit-stage, or persistence failures, and the exact + * abort reason when cancelled. Failed attempts remain visible in the log. + */ +abstract compactNow( agent: ManualCompactAgentContext, signal: AbortSignal, ): Promise + /** * Forcibly compact a range of surface nodes into a single summary node. * `start` and `end` name an inclusive span by surface position, not numeric seq @@ -486,7 +506,7 @@ abstract compactRegion( start: number, end: number, agent: CompactAgentContext, Types: [CompactionResult](../core-data-structures/compaction.md) · [CompactionTrigger](../core-data-structures/compaction.md) -Source: [`packages/compact/compact/src/index.ts:45`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:80`](../../packages/compact/compact/src/index.ts) ## `ctx.credentials` — `Credentials` (abstract seam) diff --git a/docs/core-data-structures/compaction.i18n.yaml b/docs/core-data-structures/compaction.i18n.yaml index a933e793c4..972521f7c0 100644 --- a/docs/core-data-structures/compaction.i18n.yaml +++ b/docs/core-data-structures/compaction.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/core-data-structures/compaction.md -compaction.md: 3ae4d7e50452b549654b7a7162141a4be505d784 -compaction.zh.md: 448c3aaf298b65ebe88565190c5b3978b975f5f3 +compaction.md: 070adc65fb25b2536c88701c375cc0b2a5308559 +compaction.zh.md: 9167882f63b2931ba3ce49697e0c87164394af89 diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 3ae4d7e504..070adc65fb 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -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 `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. 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. diff --git a/docs/core-data-structures/compaction.zh.md b/docs/core-data-structures/compaction.zh.md index 448c3aaf29..9167882f63 100644 --- a/docs/core-data-structures/compaction.zh.md +++ b/docs/core-data-structures/compaction.zh.md @@ -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 `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。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。 diff --git a/docs/core-data-structures/core.i18n.yaml b/docs/core-data-structures/core.i18n.yaml index 82ef063bec..b1bdfb1a14 100644 --- a/docs/core-data-structures/core.i18n.yaml +++ b/docs/core-data-structures/core.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/core-data-structures/core.md -core.md: 5ed6a47c5488005d41fdac9349e4c9d1c550d13d -core.zh.md: 1b16b7ec994c6fccd6fedf1508dec6b1b057edf3 +core.md: 70c63d8a84963f56468b5fcdacb580a798de2e10 +core.zh.md: 280529b7de6c3e8546b71791367710c588ad9282 diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 5ed6a47c54..70c63d8a84 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -614,6 +614,20 @@ 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 @@ -671,7 +685,7 @@ 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 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. +`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. diff --git a/docs/core-data-structures/core.zh.md b/docs/core-data-structures/core.zh.md index 1b16b7ec99..280529b7de 100644 --- a/docs/core-data-structures/core.zh.md +++ b/docs/core-data-structures/core.zh.md @@ -622,6 +622,20 @@ 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 @@ -679,7 +693,7 @@ 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，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。 +`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。 diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index cce2258651..f2007c814a 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -8,22 +8,22 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | | `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:157`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`tui`](../packages/ui/tui) | -| `agent/cancel-requested` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`goal-session`](../packages/goal/goal-session) | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:259`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:433`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `apiproxy`, [`goal-session`](../packages/goal/goal-session), [`session-telemetry`](../packages/telemetry/session-telemetry), [`tui`](../packages/ui/tui) | -| `agent/inbox/dequeue` | `emit` | [`packages/core/agent/src/types.ts:297`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`tui`](../packages/ui/tui) | -| `agent/inbox/discard` | `emit` | [`packages/core/agent/src/types.ts:309`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`tui`](../packages/ui/tui) | -| `agent/inbox/enqueue` | `emit` | [`packages/core/agent/src/types.ts:278`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`goal-session`](../packages/goal/goal-session) | -| `agent/inbox/update` | `emit` | [`packages/core/agent/src/types.ts:287`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `apiproxy` | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:346`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`tui`](../packages/ui/tui) | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:372`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`agent`](../packages/core/agent) | -| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:391`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic), [`llm-retry`](../packages/llm/llm-retry) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:332`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`workspace-context`](../packages/context/workspace-context) | -| `agent/settled` | `emit` | [`packages/core/agent/src/types.ts:420`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`compact-basic`](../packages/compact/compact-basic) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:268`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | -| `agent/step` | `serial` | [`packages/core/agent/src/types.ts:359`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`plan-mode`](../packages/plan/plan-mode), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`time-context`](../packages/context/time-context), [`tmux-context`](../packages/context/tmux-context), [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | -| `agent/turn-stopping` | `serial` | [`packages/core/agent/src/types.ts:406`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/cancel-requested` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`goal-session`](../packages/goal/goal-session) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:264`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:273`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:447`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `apiproxy`, [`goal-session`](../packages/goal/goal-session), [`session-telemetry`](../packages/telemetry/session-telemetry), [`tui`](../packages/ui/tui) | +| `agent/inbox/dequeue` | `emit` | [`packages/core/agent/src/types.ts:311`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`tui`](../packages/ui/tui) | +| `agent/inbox/discard` | `emit` | [`packages/core/agent/src/types.ts:323`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`tui`](../packages/ui/tui) | +| `agent/inbox/enqueue` | `emit` | [`packages/core/agent/src/types.ts:292`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`goal-session`](../packages/goal/goal-session) | +| `agent/inbox/update` | `emit` | [`packages/core/agent/src/types.ts:301`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `apiproxy` | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`tui`](../packages/ui/tui) | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:386`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`agent`](../packages/core/agent) | +| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:405`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic), [`llm-retry`](../packages/llm/llm-retry) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:346`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`workspace-context`](../packages/context/workspace-context) | +| `agent/settled` | `emit` | [`packages/core/agent/src/types.ts:434`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`compact-basic`](../packages/compact/compact-basic) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:282`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | [`agent`](../packages/core/agent), `apiproxy`, [`goal-session`](../packages/goal/goal-session), [`tui`](../packages/ui/tui) | +| `agent/step` | `serial` | [`packages/core/agent/src/types.ts:373`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`plan-mode`](../packages/plan/plan-mode), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`time-context`](../packages/context/time-context), [`tmux-context`](../packages/context/tmux-context), [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | +| `agent/turn-stopping` | `serial` | [`packages/core/agent/src/types.ts:420`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:30`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/acp/acp), `apiproxy` | | `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:154`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | `apiproxy`, [`tui`](../packages/ui/tui) | | `credentials/updated` | `emit` | [`packages/credentials/credentials/src/index.ts:67`](../packages/credentials/credentials/src/index.ts) | [`credentials`](../packages/credentials/credentials) (`events.dispatch`) | `apiproxy`, [`credentials`](../packages/credentials/credentials) | diff --git a/docs/module-graph.md b/docs/module-graph.md index 99660d1eab..eb2f7d887d 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -57,6 +57,7 @@ flowchart TD pkg_tool_skill["tool-skill"] end subgraph group_compact["packages/compact"] + pkg_command_compact["command-compact"] pkg_compact["compact"] pkg_compact_basic["compact-basic"] pkg_compact_tool_result_prune["compact-tool-result-prune"] @@ -617,6 +618,9 @@ flowchart TD pkg_fs_sandbox --> pkg_invariants pkg_fs_sandbox --> pkg_sandbox pkg_fs_sandbox --> pkg_sandbox_policy + pkg_command_compact --> pkg_commands + pkg_command_compact --> pkg_compact + pkg_command_compact --> pkg_invariants pkg_compact_basic --> pkg_agent pkg_compact_basic --> pkg_compact pkg_compact_basic --> pkg_compact_tool_result_prune @@ -1157,6 +1161,7 @@ flowchart TD | [`goal-session`](../packages/goal/goal-session) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | | [`fs-sandbox`](../packages/fs/fs-sandbox) | `fs` | [`fs`](../packages/fs/fs), [`fs-local`](../packages/fs/fs-local), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | +| [`command-compact`](../packages/compact/command-compact) | `compact` | [`commands`](../packages/ui/commands), [`compact`](../packages/compact/compact), [`invariants`](../packages/support/invariants) | | [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`compact-tool-result-prune`](../packages/compact/compact-tool-result-prune), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) | | [`session-query`](../packages/session-query/session-query) | `session-query` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-title`](../packages/session-title/session-title) | | [`session-title-llm`](../packages/session-title/session-title-llm) | `session-title` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-title`](../packages/session-title/session-title), [`timeout`](../packages/util/timeout) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index ab62f07184..b02dd1d6be 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -209,20 +209,27 @@ Source: [`packages/ui/commands/src/index.ts:132`](../packages/ui/commands/src/in #### `compact/end` — log-only ```ts persistence-catalog -/** Marks the end of a compaction — log-only, releases the lock. `error` set if summarization failed. */ -'compact/end': { turn: number; error?: string } +/** + * Marks the end of a compaction — log-only, releases the lock. Its owner + * matches `compact/start`; `error` records an unsuccessful attempt. + */ +'compact/end': { turn: number | null; error?: string } ``` -Source: [`packages/compact/compact/src/types.ts:44`](../packages/compact/compact/src/types.ts) +Source: [`packages/compact/compact/src/types.ts:51`](../packages/compact/compact/src/types.ts) #### `compact/start` — log-only ```ts persistence-catalog -/** Marks the start of a compaction — log-only, holds the lock until `compact/end`. */ -'compact/start': { turn: number } +/** + * Marks the start of a compaction — log-only, holds the lock until + * `compact/end`. A numbered owner is strictly enclosed by that open turn; + * `null` identifies a standalone manual transaction between turns. + */ +'compact/start': { turn: number | null } ``` -Source: [`packages/compact/compact/src/types.ts:15`](../packages/compact/compact/src/types.ts) +Source: [`packages/compact/compact/src/types.ts:19`](../packages/compact/compact/src/types.ts) #### `compact/summary` — log-only @@ -258,7 +265,7 @@ Source: [`packages/compact/compact/src/types.ts:15`](../packages/compact/compact Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md) -Source: [`packages/compact/compact/src/types.ts:22`](../packages/compact/compact/src/types.ts) +Source: [`packages/compact/compact/src/types.ts:26`](../packages/compact/compact/src/types.ts) ### `hook/*` diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl index c8321da3bb..43a87440a2 100644 --- a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl @@ -13,7 +13,7 @@ {"type":"assistant/chunk","seq":11,"time":1785487622703,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":12,"time":1785487622703,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"7c207b09-7f6e-4e53-a5d2-77e0d2bbb474"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[7,8,9,10,11],"surfaceOp":"append"} {"type":"tool/call","seq":13,"time":1785487622703,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}} -{"type":"tool/result","seq":14,"time":1785487622726,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly acceptsNextStep: boolean;\n readonly ctx: Context;\n send(message: UserMessage, options: SendOptions): void;\n updateInbox(id: InboxItemId, action: InboxAction): InboxActionResult;\n cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise;\n followup(message: UserMessage): void;\n steer(message: UserMessage): void;\n inject(message: UserMessage): void;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n maxTokens?: number;\n }\n export type AgentStatus = 'idle' | 'running';\n export interface AssistantMessage extends Message {\n readonly role: 'assistant';\n readonly source: ModelMessageSource;\n }\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n adapterDefaults?: LlmCallConfigAdapterDefaults;\n system?: string;\n tools?: ToolSchema[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export type InboxAction = {\n readonly kind: 'edit';\n readonly content: ContentBlock[];\n } | {\n readonly kind: 'remove';\n };\n export type InboxActionResult = 'applied' | 'not-found';\n export type InboxItemId = Branded<'InboxItemId'>;\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmCallConfigAdapterDefaults {\n reasoningEffort?: true;\n maxTokens?: true;\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n readonly id: MessageId;\n readonly role: 'system' | 'user' | 'assistant';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n }\n export type MessageId = Branded<'MessageId'>;\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n model: ModelMessageSource;\n tool: ToolMessageSource;\n }\n export interface ModelMessageSource extends AssistantProvenance {\n kind: 'model';\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReadFileLine {\n number: number;\n text: string;\n }\n export interface ReadResultView {\n card: 'read';\n title?: string;\n path: string;\n offset: number;\n lines: ReadFileLine[];\n totalLines: number;\n lang?: string;\n content?: ContentBlock[];\n }\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export interface RequestContext {\n provider: string;\n model: string;\n contextWindow?: number;\n }\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\n export interface SearchFileMatches {\n path: string;\n matches: SearchLineMatch[];\n }\n export interface SearchLineMatch {\n lineNumber: number;\n line: string;\n }\n export interface SearchMatchesResultView {\n card: 'search';\n shape: 'matches';\n title?: string;\n files: SearchFileMatches[];\n truncated: boolean;\n total: number;\n }\n export interface SearchPathsResultView {\n card: 'search';\n shape: 'paths';\n title?: string;\n paths: string[];\n truncated: boolean;\n total: number;\n }\n export type SearchResultView = SearchMatchesResultView | SearchPathsResultView;\n export interface SendOptions {\n target: SendTarget;\n wakeup: boolean;\n }\n export type SendTarget = 'next-turn' | 'next-step';\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n readonly firstLiveSeq: number;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent;\n requestHeader(): EpochHeader | undefined;\n requestContext(): RequestContext | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n trigger: TurnTrigger;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': UserMessage;\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n message: AssistantMessage;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n message: ToolResultMessage;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'steering/message': {\n turn: number;\n message: UserMessage;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n 'request/context': RequestContext;\n 'session/end-seed': Record;\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result' | 'steering/message';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise;\n finalizeContent?(exec: Readonly, result: Readonly): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: never;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: true;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolMessageSource {\n kind: 'tool';\n callId: CallId;\n }\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export interface ToolResultMessage extends Message {\n readonly role: 'user';\n readonly content: [\n ToolResultBlock\n ];\n readonly source: ToolMessageSource;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView | SearchResultView | ReadResultView | WebResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: UserMessage): void;\n concludeTurn(): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n };\n error: {\n kind: 'error';\n step: number;\n } & ({\n failure: LlmFailure;\n message?: never;\n code?: never;\n } | {\n message: string;\n code?: string;\n failure?: never;\n });\n disposed: {\n kind: 'disposed';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];\n export interface TurnTriggerMap {\n message: {\n kind: 'message';\n source: MessageSource;\n };\n retry: {\n kind: 'retry';\n };\n injection: {\n kind: 'injection';\n source: MessageSource;\n };\n }\n export interface UserMessage extends Message {\n readonly role: 'user';\n }\n export interface WebFetchResultView {\n card: 'web';\n kind: 'fetch';\n title?: string;\n url: string;\n statusCode: number;\n truncated: boolean;\n }\n export type WebResultView = WebSearchResultView | WebFetchResultView;\n export interface WebSearchResultView {\n card: 'web';\n kind: 'search';\n title?: string;\n sources: WebSource[];\n answer?: string;\n truncated: boolean;\n }\n export interface WebSource {\n url: string;\n title?: string;\n snippet?: string;\n publishedAt?: string;\n }"}],"isError":false}],"role":"user","id":"a4ec9786-5e3f-45b2-a6de-efdf953287f9"}},"sourceEventSeqs":[13],"surfaceOp":"append"} +{"type":"tool/result","seq":14,"time":1785487622726,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly acceptsNextStep: boolean;\n readonly ctx: Context;\n send(message: UserMessage, options: SendOptions): void;\n reserveTurnAdmission(): (() => void) | undefined;\n updateInbox(id: InboxItemId, action: InboxAction): InboxActionResult;\n cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise;\n followup(message: UserMessage): void;\n steer(message: UserMessage): void;\n inject(message: UserMessage): void;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n maxTokens?: number;\n }\n export type AgentStatus = 'idle' | 'running';\n export interface AssistantMessage extends Message {\n readonly role: 'assistant';\n readonly source: ModelMessageSource;\n }\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n adapterDefaults?: LlmCallConfigAdapterDefaults;\n system?: string;\n tools?: ToolSchema[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export type InboxAction = {\n readonly kind: 'edit';\n readonly content: ContentBlock[];\n } | {\n readonly kind: 'remove';\n };\n export type InboxActionResult = 'applied' | 'not-found';\n export type InboxItemId = Branded<'InboxItemId'>;\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmCallConfigAdapterDefaults {\n reasoningEffort?: true;\n maxTokens?: true;\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n readonly id: MessageId;\n readonly role: 'system' | 'user' | 'assistant';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n }\n export type MessageId = Branded<'MessageId'>;\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n model: ModelMessageSource;\n tool: ToolMessageSource;\n }\n export interface ModelMessageSource extends AssistantProvenance {\n kind: 'model';\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReadFileLine {\n number: number;\n text: string;\n }\n export interface ReadResultView {\n card: 'read';\n title?: string;\n path: string;\n offset: number;\n lines: ReadFileLine[];\n totalLines: number;\n lang?: string;\n content?: ContentBlock[];\n }\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export interface RequestContext {\n provider: string;\n model: string;\n contextWindow?: number;\n }\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\n export interface SearchFileMatches {\n path: string;\n matches: SearchLineMatch[];\n }\n export interface SearchLineMatch {\n lineNumber: number;\n line: string;\n }\n export interface SearchMatchesResultView {\n card: 'search';\n shape: 'matches';\n title?: string;\n files: SearchFileMatches[];\n truncated: boolean;\n total: number;\n }\n export interface SearchPathsResultView {\n card: 'search';\n shape: 'paths';\n title?: string;\n paths: string[];\n truncated: boolean;\n total: number;\n }\n export type SearchResultView = SearchMatchesResultView | SearchPathsResultView;\n export interface SendOptions {\n target: SendTarget;\n wakeup: boolean;\n }\n export type SendTarget = 'next-turn' | 'next-step';\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n readonly firstLiveSeq: number;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent;\n requestHeader(): EpochHeader | undefined;\n requestContext(): RequestContext | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n trigger: TurnTrigger;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': UserMessage;\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n message: AssistantMessage;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n message: ToolResultMessage;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'steering/message': {\n turn: number;\n message: UserMessage;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n 'request/context': RequestContext;\n 'session/end-seed': Record;\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result' | 'steering/message';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise;\n finalizeContent?(exec: Readonly, result: Readonly): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: never;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: true;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolMessageSource {\n kind: 'tool';\n callId: CallId;\n }\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export interface ToolResultMessage extends Message {\n readonly role: 'user';\n readonly content: [\n ToolResultBlock\n ];\n readonly source: ToolMessageSource;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView | SearchResultView | ReadResultView | WebResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: UserMessage): void;\n concludeTurn(): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n };\n error: {\n kind: 'error';\n step: number;\n } & ({\n failure: LlmFailure;\n message?: never;\n code?: never;\n } | {\n message: string;\n code?: string;\n failure?: never;\n });\n disposed: {\n kind: 'disposed';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];\n export interface TurnTriggerMap {\n message: {\n kind: 'message';\n source: MessageSource;\n };\n retry: {\n kind: 'retry';\n };\n injection: {\n kind: 'injection';\n source: MessageSource;\n };\n }\n export interface UserMessage extends Message {\n readonly role: 'user';\n }\n export interface WebFetchResultView {\n card: 'web';\n kind: 'fetch';\n title?: string;\n url: string;\n statusCode: number;\n truncated: boolean;\n }\n export type WebResultView = WebSearchResultView | WebFetchResultView;\n export interface WebSearchResultView {\n card: 'web';\n kind: 'search';\n title?: string;\n sources: WebSource[];\n answer?: string;\n truncated: boolean;\n }\n export interface WebSource {\n url: string;\n title?: string;\n snippet?: string;\n publishedAt?: string;\n }"}],"isError":false}],"role":"user","id":"a4ec9786-5e3f-45b2-a6de-efdf953287f9"}},"sourceEventSeqs":[13],"surfaceOp":"append"} {"type":"step/end","seq":15,"time":1785487622726,"data":{"turn":1,"step":1}} {"type":"step/start","seq":16,"time":1785487622735,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":17,"time":1784449176734,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index e3d86bb196..b022abd659 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/runtime/README.md -README.md: e8ba80790307e7123406934c1ab11b86dfc0faf3 -README.zh.md: 6eb69d9cf10959b007f3759378612dbc013a8904 +README.md: 64982c2b5af891b60055a41bc3c30c1ba4041300 +README.zh.md: 2cc2dc30bd4913c52645c76de4bc55d109a40001 diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index e8ba807903..64982c2b5a 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -30,6 +30,10 @@ SlotsService gives the renderer separate bare observables for `useSessions` and Because the projection is log-ordered, the node array is seq-monotonic by construction: log-only `command/run` / `command/done` nodes splice in by seq, `Session` merges interrupted frozen nodes by their fractional seqs, and a window whose checkpoint cites a shadowed range outside it renders the marker with nothing logged. The marker's summary text comes from the checkpoint's `compact/summary` provenance; a window cut that left the provenance outside makes the row non-expandable rather than empty, and a later page that supplies it resolves the text. Performance contract: one append materializes at most one node and copies the projection only when it adds that node; an event that changes no node keeps the previous array reference (a chunk storm costs nothing), and unchanged nodes keep their object identity. +## Request inspection + +`SessionHistoryInspection.requests` is one chronological, purpose-discriminated provider-request stream. Assistant requests always carry their numeric `turn` and `step`; compaction requests carry `step: 0` and a `turn` owner that may be `null`. That null owner means a manual compaction ran standalone between turns, not that it belongs to either adjacent turn. A `session/end-seed` boundary closes an unmatched compaction request as an error at the boundary time with `Compaction was interrupted before completion.`; a later start projects as an independent request instead of overwriting the orphan. + ## Code Mode sub-dispatch index `ConversationSnapshot.codeDispatches` groups a `run_code` call's sub-dispatches under their parent callId, in start order, using the native call-block shapes: a `tool/code-dispatch-start` event lands the `RunningToolCall` form (rows derive the running ring from the shape) and its `tool/code-dispatch` settlement replaces it in place with the `ToolResultNode` form, `callTime` carrying the paired start's time. A settle whose start fell outside the replay window appends directly with `callTime: null` (duration unknown — never a fabricated zero). Live mux frames and history replay build the identical index; sub-calls never join the transcript `nodes` flow; per-parent array and map references are memo-stable across unrelated snapshot swaps. diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index 6eb69d9cf1..2cc2dc30bd 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -30,6 +30,10 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 由于投影按日志顺序，节点数组天然按 seq 单调：仅日志的 `command/run` / `command/done` 节点按 seq 插入，`Session` 按分数 seq 归并被打断的冻结节点，而检查点所引范围落在窗口之外的窗口会渲染出标记且不打印任何日志。标记的摘要文本来自检查点的 `compact/summary` 溯源；窗口切分把溯源留在窗口外时该行不可展开而非空白，后续补上溯源的分页会解析出文本。性能契约：一次追加最多物化一个节点，并且仅在加入该节点时复制投影；不改变任何节点的事件保持上一次的数组引用（分片风暴零成本），未变化的节点保持其对象标识。 +## 请求检查 + +`SessionHistoryInspection.requests` 是一条按时间顺序排列、以用途为判别字段的提供方请求流。助手请求始终携带数值型 `turn` 与 `step`；压缩请求携带 `step: 0`，其 `turn` 所有者可以是 `null`。这个 null 所有者表示手动压缩独立运行在两个轮次之间，并不表示它属于任一相邻轮次。`session/end-seed` 边界会在边界时刻将未匹配的压缩请求以错误状态结束，错误固定为 `Compaction was interrupted before completion.`；后续 start 会投影为独立请求，而不会覆盖这项遗留的未匹配请求。 + ## Code Mode 子调用索引 `ConversationSnapshot.codeDispatches` 按父调用的 callId 和启动顺序，用原生调用块形状组织一个 `run_code` 调用的子调用：`tool/code-dispatch-start` 事件落成 `RunningToolCall` 形状（行组件从该形状推导运行中的转圈状态），其 `tool/code-dispatch` 完结事件原位替换为 `ToolResultNode` 形状，`callTime` 携带成对 start 事件的时间。start 落在回放窗口之外的完结事件则直接追加，`callTime: null`（耗时未知——绝不伪造零耗时）。live mux 帧与历史回放构建相同的索引；子调用永不进入 transcript 的 `nodes` 流；无关快照交换不会改变每个父调用对应的数组引用和映射引用，两者均保持 memo 稳定。 diff --git a/packages/client/runtime/src/client/sessions/request-inspection.ts b/packages/client/runtime/src/client/sessions/request-inspection.ts index e15ad55c8b..e57ff23f58 100644 --- a/packages/client/runtime/src/client/sessions/request-inspection.ts +++ b/packages/client/runtime/src/client/sessions/request-inspection.ts @@ -35,40 +35,55 @@ export interface RequestPromptChange { previous?: ConversationPromptSnapshot } -/** One provider request reconstructed from durable request lifecycle events. */ -export interface RequestView { - /** Request category; compaction is a purpose, not a separate projection. */ - purpose: 'assistant' | 'compaction' +/** Lifecycle fields shared by ordinary generation and compaction requests. */ +interface RequestViewBase { /** Sequence that opened the operation represented by this request. */ startSeq: number - turn: number - /** Agent-loop step, or zero for a direct compaction request. */ - step: number startedAt: number completedAt: number | null status: 'running' | 'complete' | 'error' error?: string - /** Effective ordinary request input, inherited until a later header changes it. */ - prompt?: ConversationPromptSnapshot - /** Prompt change logged while preparing this request. */ - promptChange?: RequestPromptChange provenance?: AssistantProvenanceView requestConfig?: AssistantRequestConfig usage?: unknown /** Assistant message or compaction summary sequence produced by this request. */ resultSeq?: number +} + +/** One ordinary assistant generation reconstructed from durable request events. */ +interface AssistantRequestView extends RequestViewBase { + purpose: 'assistant' + turn: number + /** Agent-loop step that issued this request. */ + step: number + /** Effective ordinary request input, inherited until a later header changes it. */ + prompt?: ConversationPromptSnapshot + /** Prompt change logged while preparing this request. */ + promptChange?: RequestPromptChange + /** Retry ordinal scheduled after a failed ordinary request. */ + retry?: number + maxRetries?: number + retryDelayMs?: number +} + +/** One compaction provider request, either turn-owned or standalone between turns. */ +interface CompactionRequestView extends RequestViewBase { + purpose: 'compaction' + /** Owning turn, or `null` when manual compaction ran between turns. */ + turn: number | null + /** Direct compaction requests do not consume an agent-loop step. */ + step: 0 /** Compaction replacement message sequence, when one was committed. */ replacementSeq?: number /** Safe compaction summary projection. */ summary?: readonly ContentBlock[] /** Complete compaction provider output before the safe projection. */ rawOutput?: readonly ContentBlock[] - /** Retry ordinal scheduled after a failed ordinary request. */ - retry?: number - maxRetries?: number - retryDelayMs?: number } +/** One provider request reconstructed from durable request lifecycle events. */ +export type RequestView = AssistantRequestView | CompactionRequestView + /** Immutable request-centric projection derived from one history window. */ export interface RequestInspectionSnapshot { requests: readonly RequestView[] @@ -110,7 +125,7 @@ interface CompactionStartEvent { type: 'compact/start' seq: number time: number - data: { turn: number } + data: { turn: number | null } } interface CompactionSummaryEvent { @@ -131,7 +146,7 @@ interface CompactionEndEvent { type: 'compact/end' seq: number time: number - data: { turn: number; error?: string } + data: { turn: number | null; error?: string } } function requestKey(turn: number, step: number): string { @@ -228,10 +243,21 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] let activePrompt: ConversationPromptSnapshot | undefined let activeCompaction: number | undefined - const update = (index: number | undefined, change: Partial): void => { + const updateAssistant = ( + index: number | undefined, + change: Partial>, + ): void => { if (index === undefined) return const request = requests[index] - if (request !== undefined) requests[index] = { ...request, ...change } + if (request?.purpose === 'assistant') requests[index] = { ...request, ...change } + } + const updateCompaction = ( + index: number | undefined, + change: Partial>, + ): void => { + if (index === undefined) return + const request = requests[index] + if (request?.purpose === 'compaction') requests[index] = { ...request, ...change } } for (const sourceEvent of events) { @@ -263,7 +289,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } const change = promptChange(activePrompt, prompt, sourceEvent) activePrompt = prompt - update(activeStep === undefined ? undefined : ordinaryByStep.get(activeStep), { + updateAssistant(activeStep === undefined ? undefined : ordinaryByStep.get(activeStep), { prompt, requestConfig: prompt.config, ...(change === undefined ? {} : { promptChange: change }), @@ -278,8 +304,11 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] requestKey(sourceEvent.data.turn, sourceEvent.data.step), ) const request = index === undefined ? undefined : requests[index] - update(index, { - usage: addTokenUsage(request?.usage, sourceEvent.data.chunk.usage), + updateAssistant(index, { + usage: addTokenUsage( + request?.purpose === 'assistant' ? request.usage : undefined, + sourceEvent.data.chunk.usage, + ), }) continue } @@ -288,7 +317,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] requestKey(sourceEvent.data.turn, sourceEvent.data.step), ) const request = index === undefined ? undefined : requests[index] - update(index, { + updateAssistant(index, { completedAt: sourceEvent.time, status: 'complete', resultSeq: sourceEvent.seq, @@ -296,7 +325,9 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] provider: sourceEvent.data.message.source.provider, model: sourceEvent.data.message.source.model, }, - ...(request?.usage !== undefined || sourceEvent.data.usage === undefined + ...(request?.purpose === 'assistant' + && request.usage !== undefined + || sourceEvent.data.usage === undefined ? {} : { usage: sourceEvent.data.usage }), }) @@ -306,8 +337,8 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] const key = requestKey(sourceEvent.data.turn, sourceEvent.data.step) const index = ordinaryByStep.get(key) const request = index === undefined ? undefined : requests[index] - if (request?.status === 'running') { - update(index, { + if (request?.purpose === 'assistant' && request.status === 'running') { + updateAssistant(index, { completedAt: sourceEvent.time, status: 'error', }) @@ -317,7 +348,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } if ((sourceEvent.type as string) === 'llm/retry') { const event = sourceEvent as unknown as RetryEvent - update(ordinaryByStep.get(requestKey(event.data.turn, event.data.step)), { + updateAssistant(ordinaryByStep.get(requestKey(event.data.turn, event.data.step)), { status: 'error', error: event.data.failure.message, retry: event.data.retry, @@ -328,7 +359,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } if (sourceEvent.type === 'turn/end' && sourceEvent.data.reason.kind === 'error') { const reason = sourceEvent.data.reason - update(ordinaryByStep.get(requestKey(sourceEvent.data.turn, reason.step)), { + updateAssistant(ordinaryByStep.get(requestKey(sourceEvent.data.turn, reason.step)), { status: 'error', error: 'failure' in reason ? reason.failure.message : reason.message, }) @@ -336,6 +367,15 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } const type = sourceEvent.type as string + if (type === 'session/end-seed' && activeCompaction !== undefined) { + updateCompaction(activeCompaction, { + completedAt: sourceEvent.time, + status: 'error', + error: 'Compaction was interrupted before completion.', + }) + activeCompaction = undefined + continue + } if (type === 'compact/start') { const event = sourceEvent as unknown as CompactionStartEvent activeCompaction = requests.length @@ -352,7 +392,7 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] } if (type === 'compact/summary' && activeCompaction !== undefined) { const event = sourceEvent as unknown as CompactionSummaryEvent - update(activeCompaction, { + updateCompaction(activeCompaction, { resultSeq: event.seq, summary: event.data.summary, ...(event.data.rawOutput === undefined ? {} : { rawOutput: event.data.rawOutput }), @@ -375,12 +415,12 @@ function deriveRequests(events: readonly SessionEvent[]): readonly RequestView[] && activeCompaction !== undefined && isCompactionSource(sourceEvent.data.source) ) { - update(activeCompaction, { replacementSeq: sourceEvent.seq }) + updateCompaction(activeCompaction, { replacementSeq: sourceEvent.seq }) continue } if (type !== 'compact/end' || activeCompaction === undefined) continue const event = sourceEvent as unknown as CompactionEndEvent - update(activeCompaction, { + updateCompaction(activeCompaction, { completedAt: event.time, status: event.data.error === undefined ? 'complete' : 'error', ...(event.data.error === undefined ? {} : { error: event.data.error }), diff --git a/packages/client/runtime/tests/request-inspection.spec.ts b/packages/client/runtime/tests/request-inspection.spec.ts index a76036c076..031109ca8c 100644 --- a/packages/client/runtime/tests/request-inspection.spec.ts +++ b/packages/client/runtime/tests/request-inspection.spec.ts @@ -85,6 +85,68 @@ describe('inspectRequests', () => { expect(snapshot.callSchemas.get('call-1')?.name).toBe('read') }) + it('preserves a standalone compaction owner without widening assistant turns', () => { + const snapshot = inspectRequests(entriesOf([ + at(0, 'compact/start', { turn: null }), + at(1, 'compact/summary', { + summary: [{ type: 'text', text: 'standalone summary' }], + provider: 'fake', + model: 'compact-model', + }), + at(2, 'compact/end', { turn: null }), + at(3, 'step/start', { turn: 2, step: 1 }), + ])) + + const [compaction, assistant] = snapshot.requests + expect(compaction).toMatchObject({ + purpose: 'compaction', + turn: null, + step: 0, + status: 'complete', + }) + expect(assistant).toMatchObject({ + purpose: 'assistant', + turn: 2, + step: 1, + status: 'running', + }) + if (assistant?.purpose === 'assistant') { + const turn: number = assistant.turn + expect(turn).toBe(2) + } + }) + + it('interrupts an orphaned compaction at end-seed before projecting a new attempt', () => { + const snapshot = inspectRequests(entriesOf([ + at(0, 'compact/start', { turn: null }), + at(1, 'session/end-seed', {}), + at(2, 'compact/start', { turn: null }), + at(3, 'compact/summary', { + summary: [{ type: 'text', text: 'replacement summary' }], + provider: 'fake', + model: 'compact-model', + }), + at(4, 'compact/end', { turn: null }), + ])) + + expect(snapshot.requests).toMatchObject([ + { + purpose: 'compaction', + startSeq: 0, + status: 'error', + completedAt: 1_700_000_000_001, + error: 'Compaction was interrupted before completion.', + }, + { + purpose: 'compaction', + startSeq: 2, + status: 'complete', + completedAt: 1_700_000_000_004, + summary: [{ type: 'text', text: 'replacement summary' }], + }, + ]) + }) + it('captures schemas for nested tool dispatches from the active request header', () => { const snapshot = inspectRequests(entriesOf([ at(0, 'request/header', { @@ -179,6 +241,7 @@ describe('inspectRequests', () => { ])) expect(snapshot.callSchemas).toEqual(new Map()) - expect(snapshot.requests[0]?.prompt?.tools).toEqual([]) + const [request] = snapshot.requests + expect(request?.purpose === 'assistant' ? request.prompt?.tools : undefined).toEqual([]) }) }) diff --git a/packages/client/ui-trajectory/README.i18n.yaml b/packages/client/ui-trajectory/README.i18n.yaml index 51ff03c8af..41c954adc0 100644 --- a/packages/client/ui-trajectory/README.i18n.yaml +++ b/packages/client/ui-trajectory/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-trajectory/README.md -README.md: b9c8b849b3454fe46e1fc37713d9d3b9449734cf -README.zh.md: 6ddc32f2f27c93f8ccc80b3d9b31d56d3cf4dd94 +README.md: a65c11aed9dd74f9b0b60795441f876c1d64b3ad +README.zh.md: 6e25d24c6b65673b3d003e624b6e0727be60c0e1 diff --git a/packages/client/ui-trajectory/README.md b/packages/client/ui-trajectory/README.md index b9c8b849b3..a65c11aed9 100644 --- a/packages/client/ui-trajectory/README.md +++ b/packages/client/ui-trajectory/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Trajectory renders a turn-aware event ledger with selectable User, Assistant, Tool, and nested Subtool records. Thick rules mark Turn boundaries, compact inline markers identify Steps, and the main ledger keeps only index, event, and content; selection opens a local inspector for token usage, duration, Input, Output, and Timing. A fixed Overview above the ledger projects real record start/duration timing from left to right; dragging an interval focuses the ledger on every record active at any point in that inclusive range, while clearing the selection restores the full branch. The runtime's independent history source supplies raw context lineage and projects cancellation-frozen Assistant and Tool records, so Trajectory neither reads nor changes the Chat conversation snapshot. The package remains a pure-consumer plugin (registers one view tab into the conversation's `'conversation.view'` slot ring, provides no service, declares no Context merge). Contract: api-contracts v3 §8. +Trajectory renders a turn-aware event ledger with selectable User, Assistant, Tool, and nested Subtool records. Thick rules mark Turn boundaries, compact inline markers identify Steps, and the main ledger keeps only index, event, and content; selection opens a local inspector for token usage, duration, Input, Output, and Timing. A standalone compaction request appears chronologically in its own `Between turns` section, while a numbered compaction remains inside its owning turn. A fixed Overview above the ledger projects real record start/duration timing from left to right; dragging an interval focuses the ledger on every record active at any point in that inclusive range, while clearing the selection restores the full branch. The runtime's independent history source supplies raw context lineage and projects cancellation-frozen Assistant and Tool records, so Trajectory neither reads nor changes the Chat conversation snapshot. The package remains a pure-consumer plugin (registers one view tab into the conversation's `'conversation.view'` slot ring, provides no service, declares no Context merge). Contract: api-contracts v3 §8. ## Model Experience diff --git a/packages/client/ui-trajectory/README.zh.md b/packages/client/ui-trajectory/README.zh.md index 6ddc32f2f2..6e25d24c6b 100644 --- a/packages/client/ui-trajectory/README.zh.md +++ b/packages/client/ui-trajectory/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -Trajectory 渲染按轮次组织的事件记录表，其中可选择用户、助手、工具和嵌套子工具记录。较粗的分割线标示轮次边界，紧凑的行内标记标识步骤，主记录表仅保留索引、事件和内容；选择记录则会打开局部检查器，查看 token 用量、耗时、输入、输出和计时。固定在记录表上方的 Overview 区域从左到右投影记录的真实开始时间与耗时；拖选一个区间会将记录表聚焦到活动区间与该闭区间有重叠的所有记录，清除选择则恢复完整分支。运行时的独立历史数据源提供原始上下文谱系，并投影因取消而冻结的助手和工具记录，因此 Trajectory 既不读取也不改变 Chat 会话快照。该包（package）保持为纯消费方插件（向会话的 `'conversation.view'` slot 环注册一个视图标签页，不提供服务，也不声明 Context 合并）。契约：api-contracts v3 §8。 +Trajectory 渲染按轮次组织的事件记录表，其中可选择用户、助手、工具和嵌套子工具记录。较粗的分割线标示轮次边界，紧凑的行内标记标识步骤，主记录表仅保留索引、事件和内容；选择记录则会打开局部检查器，查看 token 用量、耗时、输入、输出和计时。独立运行的压缩（compaction）请求会按时间顺序显示在自己的 `Between turns` 区段中，而带数值所有者的压缩仍位于其所属轮次内。固定在记录表上方的 Overview 区域从左到右投影记录的真实开始时间与耗时；拖选一个区间会将记录表聚焦到活动区间与该闭区间有重叠的所有记录，清除选择则恢复完整分支。运行时的独立历史数据源提供原始上下文谱系，并投影因取消而冻结的助手和工具记录，因此 Trajectory 既不读取也不改变 Chat 会话快照。该包（package）保持为纯消费方插件（向会话的 `'conversation.view'` slot 环注册一个视图标签页，不提供服务，也不声明 Context 合并）。契约：api-contracts v3 §8。 ## 模型体验 diff --git a/packages/client/ui-trajectory/src/client/TrajectoryTable.tsx b/packages/client/ui-trajectory/src/client/TrajectoryTable.tsx index 5a78e95a40..53db32efca 100644 --- a/packages/client/ui-trajectory/src/client/TrajectoryTable.tsx +++ b/packages/client/ui-trajectory/src/client/TrajectoryTable.tsx @@ -104,7 +104,8 @@ const KIND_ICON: Record = { } interface TableRecord { - turn: number + turn: number | null + section: number group: string groupStart: boolean turnStart: boolean @@ -146,7 +147,8 @@ interface ToolCallTextParts { } interface SelectedRequest { - turn: number + turn: number | null + section: number number: number group: string } @@ -320,15 +322,12 @@ export interface TrajectoryTableProps { onInspectApplied?: (() => void) | undefined } -/** One request identity paired with its session-global number. */ -export interface TrajectoryRequestNumber { +/** Request-inspector fields shared by ordinary generation and compaction. */ +interface TrajectoryRequestNumberBase { /** Request anchor event sequence; absent for the currently streaming ordinary request. */ seq?: number - turn: number - step: number group: string number: number - purpose?: 'compaction' status?: 'complete' | 'running' | 'error' startedAt?: number completedAt?: number | null @@ -344,6 +343,20 @@ export interface TrajectoryRequestNumber { cumulativeUsage?: TrajectoryUsage } +/** One purpose-discriminated request identity paired with its session-global number. */ +export type TrajectoryRequestNumber = TrajectoryRequestNumberBase & ( + | { + purpose?: 'assistant' + turn: number + step: number + } + | { + purpose: 'compaction' + turn: number | null + step: 0 + } +) + /** Disjoint provider token buckets for one request or a session prefix. */ export interface TrajectoryUsage { input?: number @@ -354,17 +367,18 @@ export interface TrajectoryUsage { } function flattenRecords(turns: readonly TrajectoryTurnModel[]): TableRecord[] { - return turns.flatMap((turn) => { - let firstInTurn = true + return turns.flatMap((turn, section) => { + let firstInSection = true const records = turn.groups.flatMap((group) => { return group.cells.map((cell, index) => { - const turnStart = firstInTurn + const turnStart = firstInSection && cell.requestOnly !== true && cell.kind !== 'system' - && cell.kind !== 'compacted' - if (turnStart) firstInTurn = false + && (cell.kind !== 'compacted' || turn.turn === null) + if (turnStart) firstInSection = false return { turn: turn.turn, + section, group: group.title, groupStart: index === 0, turnStart, @@ -388,18 +402,18 @@ function filterRecords( record.cell.requestOnly !== true && matches.has(record.cell.index), ) .map(record => ({ ...record, groupStart: false, turnStart: false, turnEnd: false })) - const startedTurns = new Set() + const startedSections = new Set() for (const [index, record] of filtered.entries()) { const previous = filtered[index - 1] const next = filtered[index + 1] record.groupStart = previous === undefined - || previous.turn !== record.turn + || previous.section !== record.section || previous.group !== record.group - record.turnStart = !startedTurns.has(record.turn) + record.turnStart = !startedSections.has(record.section) && record.cell.kind !== 'system' - && record.cell.kind !== 'compacted' - if (record.turnStart) startedTurns.add(record.turn) - record.turnEnd = next === undefined || next.turn !== record.turn + && (record.cell.kind !== 'compacted' || record.turn === null) + if (record.turnStart) startedSections.add(record.section) + record.turnEnd = next === undefined || next.section !== record.section } return filtered } @@ -410,10 +424,14 @@ function requestStep(group: string): number | undefined { return Number.isInteger(value) && value > 0 ? value : undefined } -function requestKey(turn: number, group: string): string { +function requestKey(turn: number | null, group: string): string { return `${turn}\u0000${group}` } +function sectionLabel(turn: number | null): string { + return turn === null ? 'Between turns' : `Turn ${turn}` +} + function indexRequestNumbers( records: readonly TableRecord[], sessionNumbers: readonly TrajectoryRequestNumber[] | undefined, @@ -455,12 +473,13 @@ function collapseTurnRecords( if (collapsedTurns.size === 0) return [...records] const recordsByTurn = new Map() for (const record of records) { + if (record.turn === null) continue const turnRecords = recordsByTurn.get(record.turn) ?? [] turnRecords.push(record) recordsByTurn.set(record.turn, turnRecords) } return records.flatMap((record) => { - if (!collapsedTurns.has(record.turn)) return [record] + if (record.turn === null || !collapsedTurns.has(record.turn)) return [record] const turnRecords = recordsByTurn.get(record.turn) ?? [record] if (record.cell.requestOnly === true || record.cell.kind === 'system') return [record] const contentRecords = turnRecords.filter(candidate => @@ -1537,6 +1556,7 @@ export function TrajectoryTable({ ? [] : allRecords.filter(record => record.turn === selectedRequest.turn + && record.section === selectedRequest.section && record.group === selectedRequest.group, ) const selectedRequestAssistant = selectedRequestRecords.find( @@ -1588,7 +1608,8 @@ export function TrajectoryTable({ const selectedRequestCumulativeUsage = selectedRequestInfo?.cumulativeUsage ?? selectedRequestUsage const selectedRequestOptions = selectedRequestInfo?.requestConfig - const activeTurn = selectedRequest?.turn ?? selected?.turn + const activeTurn = selectedRequest === null ? selected?.turn : selectedRequest.turn + const activeSection = selectedRequest === null ? selected?.section : selectedRequest.section const selectedTabs = selectedRequest !== null ? REQUEST_TABS.filter(tab => tab.id !== 'options' || selectedRequestOptions !== undefined) : selected === undefined ? [] : detailTabs(selected) @@ -1604,6 +1625,7 @@ export function TrajectoryTable({ selected !== undefined && selectedAssistantRequest !== undefined ? { turn: selected.turn, + section: selected.section, number: selectedAssistantRequest, group: selected.group, } @@ -1664,7 +1686,7 @@ export function TrajectoryTable({ const openRecordSummary = (target: TableRecord) => { const targetAt = allRecords.findIndex(record => record.cell.index === target.cell.index) - if (collapsedTurns.has(target.turn)) onToggleTurn(target.turn) + if (target.turn !== null && collapsedTurns.has(target.turn)) onToggleTurn(target.turn) if (target.cell.kind === 'tool' || target.cell.kind === 'subtool') { for (let i = targetAt - 1; i >= 0; i--) { const candidate = allRecords[i] @@ -1739,7 +1761,7 @@ export function TrajectoryTable({ && record.cell.index === allRecords[0]?.cell.index const request = record.groupStart && !isCollapsedSummary - && !collapsedTurns.has(record.turn) + && (record.turn === null || !collapsedTurns.has(record.turn)) ? requestNumbers.get(requestKey(record.turn, record.group)) : undefined const requestInfo = request === undefined @@ -1750,7 +1772,11 @@ export function TrajectoryTable({ : `Request #${request}${requestInfo?.purpose === 'compaction' ? ' · Compaction' : ''}` const requestSelected = request !== undefined && selectedRequest?.turn === record.turn + && selectedRequest.section === record.section && selectedRequest.number === request + const sectionActive = record.turn === null + ? activeSection === record.section + : activeTurn === record.turn return ( { - if (record.collapsedSummaryKind === 'turn') onToggleTurn(record.turn) - else onToggleAssistant(record.cell.index) + if (record.collapsedSummaryKind === 'turn' && record.turn !== null) { + onToggleTurn(record.turn) + } else onToggleAssistant(record.cell.index) } : () => { selectRecord(record.cell.index) }} onDoubleClick={(event) => { if (isCollapsedSummary || isRequestOnly) return - if (collapsedTurns.has(record.turn)) { + if (record.turn !== null && collapsedTurns.has(record.turn)) { event.preventDefault() onToggleTurn(record.turn) return @@ -1800,6 +1827,7 @@ export function TrajectoryTable({ return } if (!record.turnStart) return + if (record.turn === null) return if (allRecords.filter(candidate => candidate.turn === record.turn && candidate.cell.requestOnly !== true @@ -1812,8 +1840,9 @@ export function TrajectoryTable({ if (event.key !== 'Enter' && event.key !== ' ') return event.preventDefault() if (isCollapsedSummary) { - if (record.collapsedSummaryKind === 'turn') onToggleTurn(record.turn) - else onToggleAssistant(record.cell.index) + if (record.collapsedSummaryKind === 'turn' && record.turn !== null) { + onToggleTurn(record.turn) + } else onToggleAssistant(record.cell.index) return } selectRecord(record.cell.index) @@ -1833,6 +1862,7 @@ export function TrajectoryTable({ event.stopPropagation() selectRequest({ turn: record.turn, + section: record.section, number: request, group: record.group, }) @@ -1840,7 +1870,9 @@ export function TrajectoryTable({ onDoubleClick={(event) => { event.stopPropagation() }} /> )} - {activeTurn === record.turn && !isInitialSystem && ( + {record.turn !== null + && activeTurn === record.turn + && !isInitialSystem && (