feat(session)!: add released format migration

2026-09-01 22:12:21 +08:00
1 parent 3efd4b51e0
commit d1521ea783
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-14-session-persistence.md
-2026-06-14-session-persistence.md: 50ec79de83f0cef4a3ec94b689cc25937e334016
-2026-06-14-session-persistence.zh.md: 7b66aed6f077ac484802cfa1e23e1ba7ac3ae985
+2026-06-14-session-persistence.md: 989beb6f8cc65c8d033206a61b4408f3aecdbbc7
+2026-06-14-session-persistence.zh.md: 9dcdbffc7df89ce6fcd5341ef77f99e47643aa92
@@ -20,7 +20,7 @@ Persistence is a **capability seam** with an abstract Service Definition ([capab
 Key durable, contested choices:

 - **The canonical durable log persists every `SessionEvent` losslessly, including `assistant/chunk`.** JSONL storage may encode a consecutive delta run as one packed row, but logical readers reconstruct the exact event boundaries, sequence numbers, and timestamps. `deriveMessages()` skips chunks, and a chunk-filtered rollout (Codex's `policy.rs`) is tempting — but `seq = log.length` and validation of `events[i].seq === i` require a *contiguous* logical log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log.
- **Append-only; a crashed turn is closed, never truncated.** Flushed events are never rewritten. The [semantic checkpoint policy](../bug-fix/2026-07-21-semantic-session-checkpoints.md) drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, cold inspection preserves its contiguous, parseable events and adds risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }` to the in-memory logical view. `prepare` or `load` commits those closers before returning a recoverable view; the synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded during committed repair; a parse error or sequence gap at or before the last real `turn/end` is corruption and makes the session unloadable.
+- **Ordinary writes append; a crashed turn is closed, never truncated.** Flushed current-generation events are never rewritten by normal persistence. A format migration leaves the exact physical source path, bytes, and inode unchanged, then publishes one re-encoded current successor at a previously absent canonical versioned filename after only edge-owned normalization and current crash repair. The [semantic checkpoint policy](../bug-fix/2026-07-21-semantic-session-checkpoints.md) drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, cold inspection preserves its contiguous, parseable events and adds risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }` to the in-memory logical view. `prepare` or `load` commits those closers before returning a recoverable view; the synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded during committed repair; a parse error or sequence gap at or before the last real `turn/end` is corruption and makes the session unloadable.
 - **The file backend is canonical while the service remains extensible.** `dsh-session-persistence-jsonl` is the sole first-party provider and passes `runPersistenceContract`; the abstract service and coordinator remain available to out-of-tree providers. The [JSONL-only persistence decision](../simplification/2026-08-30-jsonl-only-session-persistence.md) owns removal of the first-party database provider and its deliberate compatibility cut.
 - **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. `createdAt` is non-negative safe-integer Unix epoch milliseconds: live creation and persistence registration reject fractional values, and JSONL validates the decoded header. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header boundary is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).)
 - **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` obtains the exact unpublished Session through `ctx.sessionPersistence.prepare()`, publishes it under the persisted id, and continues its projections. The [Session preparation decision](2026-08-05-session-preparation.md) owns reuse between history inspection and resume. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent.
@@ -29,7 +29,7 @@ Key durable, contested choices:

 Each key choice above records its rejected alternative where the choice is stated: a **chunk-filtered canonical log** (Codex's `policy.rs` shape) — breaks the contiguous-seq contract; **truncating a crashed turn** — silently destroys a long autonomous run's real work; an **in-log `session/meta` event as log line 0** — metadata is not replayable state; **finite fractional `createdAt` values** — have no producer and diverge from integer Unix-millisecond storage; **hard-injecting `sessionPersistence` into the loop** — would pend non-persistent demos forever.

-Format versioning: the header carries a `version`; cold reads reject any non-current version. The pre-release session format stays pinned at `SESSION_FORMAT_VERSION = 0` and carries no broad compatibility promise, while the coordinator may own an explicit narrow import upgrade when persisted user data requires it ([pre-identity message recovery](../bug-fix/2026-07-28-load-pre-identity-session-messages.md)). Append-only + flush is robust to partial trailing writes tolerated during cold preparation; a future provider or write-ahead log needs its own power-loss and recovery contract.
+Format versioning: the header carries a `version`; current Session and coordinator code accept only `SESSION_FORMAT_VERSION = 1`. JSONL event-body reads compose the static adjacent migration chain before constructing a Session, and the v0-to-v1 edge owns the former narrow import upgrades such as [pre-identity message recovery](../bug-fix/2026-07-28-load-pre-identity-session-messages.md). V0 remains at suffixless `session.jsonl[.zstd]`, while v1 and later use immutable lowercase `session.vN.jsonl[.zstd]` names ([released Session migration](2026-08-31-released-session-format-migrations.md)). Current-generation append and flush are robust to partial trailing writes tolerated during cold preparation; a future provider or write-ahead log needs its own power-loss and recovery contract.

 ## Consequences

@@ -20,7 +20,7 @@ Status: implemented
 长期有效、存在争议的关键选择：

 - **规范的持久日志无损保留每个 `SessionEvent`，包括 `assistant/chunk`。** JSONL 存储可以将一段连续的增量事件编码为一条打包行，但逻辑读取方会重建精确的事件边界、序号与时间戳。`deriveMessages()` 跳过分片，而过滤分片的方案（Codex 的 `policy.rs`）很有吸引力，但 `seq = log.length` 以及 `events[i].seq === i` 验证要求*连续*的逻辑日志；过滤掉分片会留下空洞，同时破坏约定和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现（带有自己的重新编号），但它不是规范日志。
- **仅追加；崩溃的轮次被关闭，而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.zh.md)会在调用模型前排空请求、在调用工具前排空已记录的顶层调用，并在步骤结束后排空完整的响应/结果批次；循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作，冷检查会保留其连续、可解析的事件，并在内存逻辑视图中为未应答的 assistant 调用添加按风险分类的错误结果、补一个缺失的 `step/end`，以及带 `{ kind: 'interrupted' }` 的 `turn/end`。`prepare` 或 `load` 在返回可恢复视图前提交这些收尾事件；合成结果保证恢复后的提供方 transcript（文本记录）仍然有效。只有不完整的最后一条记录会在提交修复时被丢弃；在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙，属于数据损坏，会使该会话不可加载。
+- **普通写入仅追加；崩溃的轮次被关闭，而非截断。** 正常持久化绝不重写已刷入当前 generation 的事件。格式迁移保持精确物理源路径、字节与 inode 不变，再只经过迁移边拥有的归一化与当前崩溃修复，在此前不存在的规范具名版本文件下发布一个重新编码的当前后继。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.zh.md)会在调用模型前排空请求、在调用工具前排空已记录的顶层调用，并在步骤结束后排空完整的响应/结果批次；循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作，冷检查会保留其连续、可解析的事件，并在内存逻辑视图中为未应答的 assistant 调用添加按风险分类的错误结果、补一个缺失的 `step/end`，以及带 `{ kind: 'interrupted' }` 的 `turn/end`。`prepare` 或 `load` 在返回可恢复视图前提交这些收尾事件；合成结果保证恢复后的提供方 transcript（文本记录）仍然有效。只有不完整的最后一条记录会在提交修复时被丢弃；在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙，属于数据损坏，会使该会话不可加载。
 - **文件后端为规范实现，服务保持可扩展。** `dsh-session-persistence-jsonl` 是唯一 first-party provider，并通过 `runPersistenceContract`；抽象服务与 coordinator 继续供仓库外 provider 使用。[JSONL-only 持久化决策](../simplification/2026-08-30-jsonl-only-session-persistence.zh.md)负责 first-party 数据库 provider 的删除及其明确 compatibility cut。
 - **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点，不是可回放的对话状态，因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中，并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`，永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数：运行时创建和持久化注册会拒绝小数值，JSONL 会验证解码后的 header。替代方案（一个可合并扩展的 `session/meta` 事件作为日志第 0 行）被否决：日志内事件会自然随 seed/fork 的会话携带，但元数据不是可回放状态，因此显式的日志外 header 边界是更清晰的取舍。（header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`，二者的联合类型为 `SessionMeta`；可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.zh.md)。）
 - **`ctx.agents.create()` 和 `ctx.agents.resume()` 是异步工厂；恢复还跨越持久化边界。** `ctx.agents.resume({ resumeSessionId })` 通过 `ctx.sessionPersistence.prepare()` 取得精确的未发布 Session，以持久化 id 发布它，并继续其投影。[Session 准备阶段决策](2026-08-05-session-preparation.zh.md)定义历史检查与恢复之间的复用。agent loop（智能体循环）不会硬注入 `sessionPersistence`（那样会让非持久化的演示永远挂起）；当它不存在时，`resume` 会以明确的错误拒绝。
@@ -29,7 +29,7 @@ Status: implemented

 上述每个关键选择都在陈述处记录了被否决的替代方案：**过滤分片的规范日志**（Codex 的 `policy.rs` 形式）破坏连续 seq 约定；**截断崩溃的轮次**会静默销毁长时间自主运行中的真实工作；**日志内 `session/meta` 事件作为第 0 行**——元数据不是可回放状态；**有限的非整数 `createdAt` 值**没有生产方，且与整数 Unix 毫秒存储不一致；**将 `sessionPersistence` 硬注入循环**会让非持久化的演示永远挂起。

-格式版本控制：header 携带一个 `version`；冷读取拒绝任何非当前版本。预发布阶段的会话格式仍固定为 `SESSION_FORMAT_VERSION = 0`，不承诺广泛兼容；当持久化用户数据确有需要时，协调器可以负责显式且范围受限的导入升级（[消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.zh.md)）。仅追加 + 刷写能承受冷准备时可容忍的尾部不完整写入；未来 provider 或 write-ahead log 需要自有的断电与恢复约定。
+格式版本控制：header 携带一个 `version`；当前 Session 与协调器代码只接受 `SESSION_FORMAT_VERSION = 1`。JSONL 的事件正文读取会在构造 Session 前组合静态相邻迁移链，v0-to-v1 边拥有原有的范围受限导入升级，例如[消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.zh.md)。V0 保留在无后缀 `session.jsonl[.zstd]`，v1 及后续版本使用不可变的小写 `session.vN.jsonl[.zstd]` 名称（[已发布 Session 迁移](2026-08-31-released-session-format-migrations.zh.md)）。当前 generation 的追加与 flush 能承受冷准备时可容忍的尾部不完整写入；未来 provider 或 write-ahead log 需要自有的断电与恢复约定。

 ## 后果

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-session-surface.md
-2026-06-18-session-surface.md: 95298da0e4bd16e822cb5960718d23ecda7a1b5c
-2026-06-18-session-surface.zh.md: 7dd05d79f635b193b2c11cb3599264ebf2424d79
+2026-06-18-session-surface.md: e9331ca2f827edd291d6365ef1356520c8f1927a
+2026-06-18-session-surface.zh.md: 26b58afe6aec3a192da94b2c29d4ec0c95d88a6b
@@ -41,7 +41,7 @@ Delta processing is O(1) when no new events and O(new events) when new events ar

 ### Persistence

-The new fields are serialized as top-level JSON properties. JSONL storage requires no separate column mapping: its lossless JSON boundary preserves both values. The session format `version` is pinned at `SESSION_FORMAT_VERSION = 0`; the optional surface fields are absorbed without bumping it.
+The new fields are serialized as top-level JSON properties. JSONL storage requires no separate column mapping: its lossless JSON boundary preserves both values. Released v0 and v1 share this surface representation, and the identity v0-to-v1 edge preserves it exactly; a future structural representation change increments `SESSION_FORMAT_VERSION` and owns an adjacent migration.

 ### Crash recovery

@@ -51,7 +51,7 @@ The `repair.ts` module synthesizes `tool/result` closers for orphaned tool calls

 `Session` validates `sourceEventSeqs` and `surfaceOp` at the always-on seed/append boundary: only `assistant/message` may use an empty source-event list; references are unique, earlier, and known; replacement endpoints exist in surface order; and `sourceEventSeqs` covers every shadowed node. These are single-record acceptance and storage-projection rules, not optional invariant-service contributions.

-Every surface-eligible event must carry `surfaceOp` or it would disappear from derived history. Typed `append` overloads enforce this for literal event types; runtime checks in `append` and the seed constructor cover widened unions and loaded logs. Invalid seeds are rejected rather than upgraded under the pre-release format policy.
+Every surface-eligible event must carry `surfaceOp` or it would disappear from derived history. Typed `append` overloads enforce this for literal event types; runtime checks in `append` and the seed constructor cover widened unions and current loaded logs. Historical v0 validation and normalization belong to the v0-to-v1 edge rather than generic Session code.

 ## Alternatives considered

@@ -41,7 +41,7 @@ export type SurfaceOp =

 ### 持久化

-新字段作为顶层 JSON 属性序列化。JSONL 存储无需单独列映射：其无损 JSON 边界会保留两个值。会话格式 `version` 固定为 `SESSION_FORMAT_VERSION = 0`；可选 surface 字段被吸收而不递增版本号。
+新字段作为顶层 JSON 属性序列化。JSONL 存储无需单独列映射：其无损 JSON 边界会保留两个值。已发布 v0 与 v1 共享该 surface 表示，恒等的 v0-to-v1 边会精确保留它；未来结构性表示变更会递增 `SESSION_FORMAT_VERSION` 并拥有一项相邻迁移。

 ### 崩溃恢复

@@ -51,7 +51,7 @@ export type SurfaceOp =

 `Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`：只有 `assistant/message` 可以使用空的源事件列表；引用必须唯一、更早且已知；替换端点必须存在于 surface 顺序中；`sourceEventSeqs` 必须覆盖每个被遮蔽的节点。这些是单记录接纳与存储投影规则，不是由可选的不变式服务提供的规则。

-每个可进入 surface 的事件都必须携带 `surfaceOp`，否则它将从派生历史中消失。类型化的 `append` 重载对字面事件类型强制执行此规则；`append` 和种子构造函数中的运行时检查覆盖宽化联合类型和加载的日志。按照预发布格式策略，无效的种子被拒绝而非升级。
+每个可进入 surface 的事件都必须携带 `surfaceOp`，否则它将从派生历史中消失。类型化的 `append` 重载对字面事件类型强制执行此规则；`append` 和种子构造函数中的运行时检查覆盖宽化联合类型和当前已加载日志。历史 v0 的校验与规范化属于 v0-to-v1 边，而不属于通用 Session 代码。

 ## 曾考虑的替代方案

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md
-2026-06-18-shared-persistence-write-coordinator.md: a61ceb9b2197a6dd8ed86c1c971373a2706607aa
-2026-06-18-shared-persistence-write-coordinator.zh.md: 777d5f5972ac1096c2e3434f9e0ac5aec27e8c26
+2026-06-18-shared-persistence-write-coordinator.md: 83cfbf65cf27b79c9deef2f58943931f402feb22
+2026-06-18-shared-persistence-write-coordinator.zh.md: a7b69add8be5a96ad7b9f25484d9601200c551f3
@@ -24,15 +24,14 @@ The coordinator retires a session from `session/disposed`: it waits for the cont

 ### The hook interface (`PersistenceBackend<TornMarker>`)

-Five required members plus optional empty-materialization and lifecycle hooks form the only boundary between the coordinator and storage:
+Six required durable primitives plus optional format-fusion, seek, empty-materialization, artifact, and lifecycle hooks form the only boundary between the coordinator and storage:

- `name` — backend label for the dispose-failure `AggregateError`.
- `loadStored(id)` — read one stored prefix by id across every storage scope. Preparation, logical load/inspection, physical suffix reads, live adoption, and the create-collision probe share this lookup. The coordinator asserts the returned id and rejects a stored/live cwd mismatch before repair or state publication.
- `appendBatch(meta, events, isMaterialized)` — durably append a contiguous batch, lazily materializing the session ATOMICALLY when not yet materialized. Ordinary creation therefore cannot leave an abandoned materialized-but-empty session.
- `materializeHeader?(meta)` — explicitly persist a header-only session for `SessionPersistence.ensureMaterialized(session)`. This is reserved for a lifecycle frontend that treats an empty session itself as a resumable durable resource; [standard ACP automation controls](../feature/2026-08-22-standard-acp-automation-controls.md) are the first consumer. Backends that support that lifecycle implement the hook; lazy creation remains the default.
- `commitRepair(meta, tornMarker, closers)` — make a crash repair durable: truncate the torn tail (iff `tornMarker !== undefined`) and append `closers`. **NOT required to be atomic** — JSONL legitimately truncates then appends in two fsync'd steps. Used by `prepare`/`load` (truncate + synthetic closers) and live adoption (truncate only, `closers = []`).
- `list()` — list all stored metadata.
- `close?()` — optional lifecycle teardown for a provider with owned resources; JSONL omits it. The dispose effect awaits it after the quiescence drain so a close failure never masks a drain error.
+- `name` labels an aggregate disposal failure; `loadStored(id)` reads one already-current detached prefix; and `readStoredRevision(id)` returns its cheap source identity. The coordinator asserts ids and rejects a stored/live cwd mismatch before repair or state publication.
+- `ensureCurrent?(id)` lets a backend publish any supported historical generation's current successor before a current read. `loadCurrentStored?(id)` fuses that operation with prefix decoding over one stable selected-generation snapshot; otherwise the coordinator calls `ensureCurrent` and `loadStored` in order. The same split exists for raw artifacts through `readCurrentRawStored?` and `readRawStored?`.
+- `loadStoredFrom?(id, fromSeq)` is an optional seek-capable current suffix read. Sequential backends omit it and reuse the full current prefix.
+- `appendBatch(meta, events, isMaterialized)` durably appends a contiguous batch and atomically performs lazy first materialization. `materializeHeader?(meta)` explicitly persists an empty resumable Session for lifecycle frontends such as [standard ACP automation controls](../feature/2026-08-22-standard-acp-automation-controls.md).
+- `commitRepair(meta, tornMarker, closers)` makes crash repair durable by truncating the torn tail when present and appending closers when present. It need not be atomic: JSONL legitimately truncates then appends in two synced steps. Preparation and load commit truncation plus synthetic closers; live adoption commits truncation only.
+- `list()` returns one header-only descriptor for every stored artifact; `locate?()` resolves a backend-owned artifact without I/O; and `close?()` releases backend resources after the coordinator's quiescence drain.

 ### The opaque torn marker

@@ -40,13 +39,13 @@ The single design choice that keeps the seam clean: the crash-repair "where is t

 ## Testing

-The shared `runPersistenceContract` proves that JSONL `inspect` balances an interrupted logical view without changing storage or revisions before `prepare` or `load` commits recovery. `runCoordinatorContract` (`tests/coordinator-contract.ts`) covers adoption, HMR, collision, Session and provider disposal drains, and crash-tail repair through an in-memory reference and JSONL. `persistence.spec.ts`, `preparations.spec.ts`, and `write-behind.spec.ts` cover preparation reuse and reservation, bounded prepared-state eviction, fixed-window follow-up batches, live-controller cleanup, same-id chain-tail races, failed-batch retry, and close ordering. JSONL specs retain storage mechanics and the through-coordinator torn-tail case that exercises the opaque-marker branch.
+The shared `runPersistenceContract` proves that already-current JSONL `inspect` balances an interrupted logical view without changing storage or revisions before `prepare` or `load` commits recovery; a supported historical inspection first publishes its migrated and repaired current successor beside the unchanged source. `runCoordinatorContract` (`tests/coordinator-contract.ts`) covers adoption, HMR, collision, Session and provider disposal drains, and crash-tail repair through an in-memory reference and JSONL. `persistence.spec.ts`, `preparations.spec.ts`, and `write-behind.spec.ts` cover preparation reuse and reservation, bounded prepared-state eviction, fixed-window follow-up batches, live-controller cleanup, same-id chain-tail races, failed-batch retry, and close ordering. JSONL specs retain storage mechanics and the through-coordinator torn-tail case that exercises the opaque-marker branch.

 ## Alternatives considered

 - **A base class the backends extend** — rejected for composition: a backend exposes only the hooks, cannot reach the coordinator's private orchestration state, and a third-party backend may still implement the abstract service directly without the coordinator at all.
- **A wider hook API** — each candidate hook folds away: there is no scope-specific live lookup because `loadStored` plus the coordinator's cwd check preserves the collision boundary, no storage-locator generic because validated JSONL metadata reproduces its path, no separate `materialize` hook because the first batch must commit atomically with materialization, no separate create-collision probe because it is `loadStored(id) !== undefined`, and no coordinator pass-through for `list()` because listing needs none of the orchestration.
+- **Put historical formats in the coordinator or require two physical reads** — rejected because format framing, highest-generation selection, immutable successor publication, and stable-source decoding belong to the backend. Optional fused current reads preserve one coordinator lifecycle while letting JSONL classify or migrate and decode one exact snapshot; the ordinary hooks remain the fallback for other backends.

 ## Consequences

-The coordinator adds one indirection, an opaque torn marker, detached Session-retirement tasks, and bounded prepared Session state, but centralizes correctness-heavy orchestration for the JSONL provider and future implementations. Session disposal remains an observe-only event, so the Session owner does not await persistence retirement; the coordinator contains failures, preserves pending events in the live controller, and makes provider teardown the quiescence boundary. Its hook surface stays narrow: identity, adoption, collision checks, preparation, and immutable inspection reuse `loadStored`; materialization stays atomic inside `appendBatch`; and listing bypasses the coordinator. Read models use `inspect` rather than `load`, so observing a persisted open turn does not commit interruption closers; the [Session preparation decision](2026-08-05-session-preparation.md) owns reuse, reservation, and publication. A new provider implements storage primitives rather than copy the bounded write lifecycle.
+The coordinator adds one indirection, an opaque torn marker, detached Session-retirement tasks, and bounded prepared Session state, but centralizes correctness-heavy orchestration for the JSONL provider and future implementations. Session disposal remains an observe-only event, so the Session owner does not await persistence retirement; the coordinator contains failures, preserves pending events in the live controller, and makes provider teardown the quiescence boundary. Its hooks stay tied to current consumers: identity, adoption, collision checks, preparation, and immutable inspection share the serialized current-prefix path; materialization stays atomic inside `appendBatch`; and listing bypasses stateful orchestration. For already-current input, read models use `inspect` rather than `load`, so observing an open turn does not commit interruption closers; historical input first publishes a separate migrated and repaired successor. The [Session preparation decision](2026-08-05-session-preparation.md) owns reuse, reservation, and publication. A new provider implements storage primitives rather than copying the bounded write lifecycle.
@@ -24,15 +24,14 @@ JSONL provider 需要在其存储原语周围执行对正确性要求很高的

 ### 钩子接口（`PersistenceBackend<TornMarker>`）

-五个必需成员加可选的空会话实体化与生命周期钩子，构成协调器与存储之间唯一的边界：
+六个必需的持久原语，加上可选的格式融合、seek、空会话物化、产物与生命周期钩子，构成协调器与存储之间唯一的边界：

- `name`——后端标签，用于 dispose 失败时的 `AggregateError`。
- `loadStored(id)`——按 id 跨所有存储范围读取一个已存储前缀。准备、逻辑加载/检查、物理后缀读取、存活会话接管与创建碰撞探测共用此查找。协调器会断言返回的 id，并在修复或发布状态之前拒绝已存储记录与存活会话的 cwd 不匹配。
- `appendBatch(meta, events, isMaterialized)`——持久追加一个连续批次，在尚未物化时原子地惰性物化会话。因此，普通创建不会留下被放弃的已物化空会话。
- `materializeHeader?(meta)`——为 `SessionPersistence.ensureMaterialized(session)` 显式持久化仅含 header 的会话。它只供把空会话本身视为可恢复持久资源的生命周期前端使用；[标准 ACP 自动化控制](../feature/2026-08-22-standard-acp-automation-controls.zh.md)是第一个 consumer。支持该生命周期的后端实现此钩子；惰性创建仍是默认行为。
- `commitRepair(meta, tornMarker, closers)`——使崩溃修复持久化：截断损坏的尾部（当且仅当 `tornMarker !== undefined`）并追加 `closers`。**不要求原子性**——JSONL 合理地分两步 fsync，先截断再追加。用于 `prepare`/`load`（截断 + 合成收尾事件）和存活会话接管（仅截断，`closers = []`）。
- `list()`——列出所有已存储的元数据。
- `close?()`——供拥有资源的 provider 使用的可选生命周期清理；JSONL 省略该钩子。dispose effect 在排空至完全停稳后 await 它，因此 close 失败不会掩盖排空错误。
+- `name` 标记聚合 dispose 失败；`loadStored(id)` 读取一个已经是当前格式的分离前缀；`readStoredRevision(id)` 返回其低成本来源标识。协调器会断言 id，并在修复或发布状态之前拒绝存储记录与活动会话的 cwd 不匹配。
+- `ensureCurrent?(id)` 让后端在当前格式读取前发布任何受支持历史 generation 的当前后继。`loadCurrentStored?(id)` 把该操作与基于一个稳定选定 generation 快照的前缀解码融合；否则协调器依次调用 `ensureCurrent` 与 `loadStored`。原始产物通过 `readCurrentRawStored?` 与 `readRawStored?` 使用同一分工。
+- `loadStoredFrom?(id, fromSeq)` 是可选的可 seek 当前格式后缀读取。顺序后端省略它并复用完整当前前缀。
+- `appendBatch(meta, events, isMaterialized)` 持久追加一个连续批次，并原子执行惰性首次物化。`materializeHeader?(meta)` 为 [标准 ACP 自动化控制](../feature/2026-08-22-standard-acp-automation-controls.zh.md)这类生命周期前端显式持久化空的可恢复 Session。
+- `commitRepair(meta, tornMarker, closers)` 在存在 torn tail 时截断它，在存在 closer 时追加它，从而持久化崩溃修复。它不要求原子性：JSONL 合理地分两步同步，先截断再追加。准备与加载提交截断和合成 closer；活动接管只提交截断。
+- `list()` 为每个存储产物返回一个仅 header descriptor；`locate?()` 不经 I/O 解析后端拥有的产物；`close?()` 在协调器排空至完全停稳后释放后端资源。

 ### 不透明的 torn marker

@@ -40,13 +39,13 @@ JSONL provider 需要在其存储原语周围执行对正确性要求很高的

 ## 测试

-共享 `runPersistenceContract` 证明 JSONL 的 `inspect` 会配平被中断的逻辑视图但不改变存储或修订版本，随后由 `prepare` 或 `load` 提交恢复。`runCoordinatorContract`（`tests/coordinator-contract.ts`）通过内存参考实现与 JSONL 覆盖接管、HMR、碰撞、Session 与 provider dispose 排空和崩溃尾部修复。`persistence.spec.ts`、`preparations.spec.ts` 与 `write-behind.spec.ts` 覆盖准备复用与预留、有界准备状态淘汰、固定窗口后续批次、存活控制器清理、同 id 链尾竞态、失败批次重试与关闭顺序。JSONL 规格保留存储机制，以及覆盖不透明 marker 分支的经由协调器崩溃尾部用例。
+共享 `runPersistenceContract` 证明已经是当前格式的 JSONL `inspect` 会配平被中断的逻辑视图但不改变存储或 revision，随后由 `prepare` 或 `load` 提交恢复；受支持的历史检查会先在不改变源文件的情况下于其旁边发布迁移并修复后的当前后继。`runCoordinatorContract`（`tests/coordinator-contract.ts`）通过内存参考实现与 JSONL 覆盖接管、HMR、碰撞、Session 与 provider dispose 排空和崩溃尾部修复。`persistence.spec.ts`、`preparations.spec.ts` 与 `write-behind.spec.ts` 覆盖准备复用与预留、有界准备状态淘汰、固定窗口后续批次、存活 controller 清理、同 id 链尾竞态、失败批次重试与关闭顺序。JSONL spec 保留存储机制，以及覆盖不透明 marker 分支的经由协调器崩溃尾部用例。

 ## 曾考虑的替代方案

 - **后端继承的基类**——否决，改用组合：后端只暴露钩子，无法触及协调器的私有编排状态，且第三方后端仍可完全不使用协调器、直接实现抽象服务。
- **更宽的钩子 API**——每个候选钩子都被折叠掉：没有限定存储范围的存活会话查找，因为 `loadStored` 加上协调器的 cwd 检查即可维持碰撞边界；没有存储定位器泛型，因为经验证的 JSONL 元数据可还原其路径；没有单独的 `materialize` 钩子，因为首批事件必须与物化原子提交；没有单独的创建碰撞探测，因为它就是 `loadStored(id) !== undefined`；`list()` 也不经由协调器透传，因为列举不需要任何编排。
+- **把历史格式放入协调器，或要求两次物理读取**——不予采用，因为格式 framing、最高 generation 选择、不可变后继发布与稳定来源解码属于后端。可选的融合当前格式读取保留一个协调器生命周期，同时让 JSONL 对同一个精确快照完成分类或迁移与解码；普通钩子继续作为其他后端的 fallback。

 ## 后果

-协调器增加一层间接、一个不透明 torn marker、脱离 Session 生命周期的退役任务，以及有界的已准备 Session 状态，但为 JSONL provider 与未来实现集中管理对正确性要求很高的编排。Session dispose 仍是仅观察事件，因此 Session owner 不等待持久化退役；协调器收容失败、在存活控制器中保留待处理事件，并以 provider teardown 为完全停稳边界。其钩子面保持窄小：标识校验、接管、碰撞检查、准备与不可变检查共用 `loadStored`；物化保持在 `appendBatch` 内原子完成；列举绕过协调器。读模型使用 `inspect` 而非 `load`，因此观察已持久化但仍开放的轮次时不会提交中断收尾事件；复用、预留与发布由 [Session 准备阶段决策](2026-08-05-session-preparation.zh.md)定义。新 provider 只需实现存储原语，而无需复制有界写入生命周期。
+协调器增加一层间接、一个不透明 torn marker、脱离 Session 生命周期的退役任务，以及有界的已准备 Session 状态，但为 JSONL provider 与未来实现集中管理对正确性要求很高的编排。Session dispose 仍是仅观察事件，因此 Session owner 不等待持久化退役；协调器收容失败、在活动 controller 中保留待处理事件，并以 provider teardown 为完全停稳边界。其钩子只服务当前 consumer：标识、接管、碰撞检查、准备与不可变检查共用串行化当前前缀路径；物化保持在 `appendBatch` 内原子完成；列举绕过有状态编排。对已经是当前格式的输入，读模型使用 `inspect` 而非 `load`，因此观察开放轮次时不会提交中断 closer；历史输入会先发布一个独立的迁移并修复后继。复用、预留与发布由 [Session 准备阶段决策](2026-08-05-session-preparation.zh.md)定义。新 provider 只需实现存储原语，而无需复制有界写入生命周期。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
-2026-07-05-reconstructable-requests.md: 3786de02d06c0b6c094297ae89ac3f84053e408d
-2026-07-05-reconstructable-requests.zh.md: 851045aca7dababd0da859f3b04b721c65382fc3
+2026-07-05-reconstructable-requests.md: bc8ba640c400b18598f18aa303f2bd1b5c5b9cdc
+2026-07-05-reconstructable-requests.zh.md: de1802aac83f1e0980172d2d541a093f2d729e4a
@@ -53,5 +53,5 @@ Like MiniCode, the conversation advances append-only and resets only when model-
 - `agent/pre-step` is the current-request message channel; direct inbox mutation is the eventual later-request channel.
 - Tool-result trimming needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic.
 - Unreadable referenced attachment objects still fail model requests; [automatic attachment quarantine](../../proposed/bug-fix/2026-08-20-attachment-read-quarantine.md) records the proposed recovery without weakening byte-exact reconstruction.
- Session logs grow one `request/header` snapshot per loop instance, real change, and later model-message series. Repeating the full system prompt and tool catalog is larger than a delta codec but small beside chunk-heavy logs and retains one self-contained replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated.
+- Session logs grow one `request/header` snapshot per loop instance, real change, and later model-message series. Repeating the full system prompt and tool catalog is larger than a delta codec but small beside chunk-heavy logs and retains one self-contained replay representation. Current v1 retains this single representation; the frozen v0-to-v1 edge explicitly refuses legacy delta events before current Session construction.
 - Snapshot fixtures include each repeated series header. Keyless refresh owns those deterministic log changes, while the snapshot harness pins prompt and tool sidecars only for the initial and actual change revisions and reuses the current revision for `series` snapshots. Filesystem-writing fixtures remain in normalized authored form with cwd-relative tool arguments because replay only round-trips cwd-independent argument paths.
@@ -53,5 +53,5 @@ Status: implemented
 - `agent/pre-step` 是当前请求的消息通道；直接修改 inbox 则是最终进入后续请求的通道。
 - 工具结果裁剪无需新机制：一个已记录的单条目 surface replace（`start === end`），携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族，回放正确，缓存失效由相同的压力逻辑批量处理。
 - 无法读取的被引用附件对象仍会让模型请求失败；[附件自动隔离](../../proposed/bug-fix/2026-08-20-attachment-read-quarantine.zh.md)记录了不削弱字节精确重建的拟议恢复方案。
- 会话日志会为每个循环实例、真实变更和后续模型消息序列增加一个 `request/header` 快照。重复完整系统提示词与工具目录比 delta 编解码器更大，但相对分片密集型日志仍然很小，并保留一种自包含的回放表示。`SESSION_FORMAT_VERSION` 保持 `0`；旧的 delta 事件被拒绝而非迁移。
- 快照 fixture 包含每个重复的 series header。无密钥 refresh 负责这些确定性日志变化；快照 harness 只为 initial 与真实 change 修订固定提示词和工具 sidecar，并让 `series` 快照复用当前修订。写入文件系统的 fixture 继续以规范化的撰写形式存储，工具参数使用 cwd 相对路径，因为回放只对 cwd 无关的参数路径做往返。
+- 会话日志会为每个循环实例、真实变更和后续模型消息序列增加一个 `request/header` 快照。重复完整系统提示词与工具目录比 delta 编解码器更大，但相对分片密集型日志仍然很小，并保留一种自包含的回放表示。当前 v1 保留这一种表示；冻结的 v0-to-v1 迁移边会在构造当前 Session 前显式拒绝旧版 delta 事件。
+- 快照 fixture 包含每个重复的 series header。无密钥 refresh 负责这些确定性日志变化；快照 harness 只为 initial 与真实 change 修订固定提示词和工具 sidecar，并让 `series` 快照复用当前修订。写入文件系统的 fixture 继续以规范化的撰写形式存储，工具参数使用 cwd 相对路径，因为回放只对 cwd 无关的参数路径做往返。
@@ -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/2026-07-14-provider-routed-llm-adapters.md
-2026-07-14-provider-routed-llm-adapters.md: 78c8d6788006c503b532ff2bbddd30342415f0a4
-2026-07-14-provider-routed-llm-adapters.zh.md: af8bc4fe27a50d47d7b49b51eada67afe889fc13
+2026-07-14-provider-routed-llm-adapters.md: ab4c485b79f37d9360da9a9a32f38063cae99755
+2026-07-14-provider-routed-llm-adapters.zh.md: c431d710af95352a2ecfc7b76b6393428ebedfec
@@ -54,7 +54,7 @@ Compaction configuration gains `summarizationProvider` beside `summarizationMode

 The JSON-RPC runtime receives provider and model explicitly. Its convenience fallback mounts `dsh-llm-deepseek` only for provider `deepseek` when that provider has no registered owner; other missing providers fail without guessing an adapter.

-The on-disk session format remains the pre-release pinned version `0`, with no compatibility promise. Seed/load validation rejects request headers and assistant messages that omit required provider/model fields instead of accepting an old shape that can no longer reconstruct the request.
+Current v1 seed/load validation rejects request headers and assistant messages that omit required provider/model fields. The frozen v0-to-v1 edge requires the same reconstructable routing identity before migration; it never guesses a missing provider or model, and malformed shapes refuse before publication.

 ## Alternatives considered

@@ -78,7 +78,7 @@ The on-disk session format remains the pre-release pinned version `0`, with no c
 - pi-ai credentials, transport knobs, SDK timeouts, and the five-minute-default `streamIdleTimeoutMs` watchdog are scoped per provider profile. Hidden provider retries are disabled; bounded retries belong to the separately composed agent recovery policy.
 - `dsh-llm-pi-ai` rejects stop sequences because pi-ai's common stream API cannot express them; the native DeepSeek adapter retains its stop support.
 - Replay state is portable only within the adapter instance that owns both the historical and target providers. Cross-provider and cross-model restoration is an adapter responsibility, and another adapter receives provider-neutral history without the opaque state.
- Current pre-release session JSONL requires provider/model on request headers and assistant messages. Older shapes remain version `0` but are rejected rather than migrated.
+- Current v1 Session JSONL requires provider/model on request headers and assistant messages. The v0 edge migrates only frozen shapes that already carry reconstructable request identity.

 ## Testing

@@ -88,4 +88,4 @@ The on-disk session format remains the pre-release pinned version `0`, with no c

 ## Risks

-This is a repo-wide pre-release API break: model-only request construction, adapter registration, app protocols, fixtures, and persisted version-0 event shapes all change together, with no compatibility aliases. The provider exclusivity rule deliberately prevents two implementations of the same upstream from coexisting in one context. A pi-ai dependency update can change the accepted provider/model catalog, so the lockfile and adapter e2e matrix define the tested set. Custom `baseURL` endpoints inherit the chosen catalog model's protocol assumptions and cannot repair an incompatible proxy. Catalog-external model descriptors and multimodal content remain unsupported. pi-ai replay state may contain opaque encrypted reasoning signatures; it is persisted because the provider requires it for continuity, but it is never rendered or logged outside the existing session record.
+This was a repo-wide API break when introduced: model-only request construction, adapter registration, app protocols, fixtures, and persisted v0 event shapes changed together, with no compatibility aliases. Released historical recovery now belongs to the adjacent Session-format edge. The provider exclusivity rule deliberately prevents two implementations of the same upstream from coexisting in one context. A pi-ai dependency update can change the accepted provider/model catalog, so the lockfile and adapter e2e matrix define the tested set. Custom `baseURL` endpoints inherit the chosen catalog model's protocol assumptions and cannot repair an incompatible proxy. Catalog-external model descriptors and multimodal content remain unsupported. pi-ai replay state may contain opaque encrypted reasoning signatures; it is persisted because the provider requires it for continuity, but it is never rendered or logged outside the existing session record.
@@ -54,7 +54,7 @@ pi-ai 回放状态用其成功 `AssistantMessage` 的带版本最小投影填充

 JSON-RPC 运行时显式接收提供方与模型。仅当 `deepseek` 提供方没有注册所有者时，其便利回退才会挂载 `dsh-llm-deepseek`；其他缺失的提供方会直接失败，不会猜测适配器。

-磁盘会话格式仍使用预发布阶段固定的版本 `0`，且不承诺兼容性。seed/load 验证会拒绝省略必需提供方/模型字段的请求头和助手消息，不会接受已无法重建请求的旧格式。
+当前 v1 的 seed/load 验证会拒绝省略必需提供方／模型字段的请求头和助手消息。冻结的 v0-to-v1 迁移边要求迁移前已具备同一套可重建路由身份；它绝不会猜测缺失的提供方或模型，畸形结构会在发布前被拒绝。

 ## 考虑过的替代方案

@@ -78,7 +78,7 @@ JSON-RPC 运行时显式接收提供方与模型。仅当 `deepseek` 提供方
 - pi-ai 凭据、传输选项、SDK 超时，以及默认五分钟的 `streamIdleTimeoutMs` 空闲超时机制均按提供方配置隔离。系统禁用隐藏的提供方重试；有界重试由单独组合的 agent 恢复策略负责。
 - pi-ai 的通用流 API 无法表达停止序列，因此 `dsh-llm-pi-ai` 会拒绝停止序列；原生 DeepSeek 适配器仍支持停止序列。
 - 仅当历史提供方与目标提供方归同一个适配器实例所有时，回放状态才可移植。适配器负责跨提供方和跨模型恢复；其他适配器只接收不含不透明状态的提供方无关历史。
- 当前预发布会话 JSONL 要求请求头和助手消息都包含提供方/模型。旧格式仍使用版本 `0`，但会被拒绝，不执行迁移。
+- 当前 v1 Session JSONL 要求请求头和助手消息都包含提供方／模型。v0 边只迁移已经携带可重建请求身份的冻结结构。

 ## 测试

@@ -88,4 +88,4 @@ JSON-RPC 运行时显式接收提供方与模型。仅当 `deepseek` 提供方

 ## 风险

-这是一次覆盖全仓库的预发布 API 破坏性变更：仅模型的请求构造、适配器注册、应用协议、fixture，以及持久化版本 0 事件格式会同时变化，不提供兼容别名。提供方排他规则有意禁止同一上游的两个实现共存于同一上下文。pi-ai 依赖升级可能改变可接受的提供方/模型目录，因此锁文件与适配器 e2e 矩阵定义已验证集合。自定义 `baseURL` 端点会继承所选目录模型的协议假设，无法修复不兼容的代理。目录外模型描述符与多模态内容仍不受支持。pi-ai 回放状态可能包含不透明的加密推理签名；提供方需要该信息维持连续性，因此系统会持久化该状态，但不会在现有会话记录之外渲染或记录它。
+这项变更在引入时是覆盖全仓库的 API 破坏性变更：仅模型的请求构造、适配器注册、应用协议、fixture，以及持久化 v0 事件结构同时变化，不提供兼容别名。已发布历史恢复现在属于相邻 Session 格式边。提供方排他规则有意禁止同一上游的两个实现共存于同一上下文。pi-ai 依赖升级可能改变可接受的提供方／模型目录，因此锁文件与适配器 e2e 矩阵定义已验证集合。自定义 `baseURL` 端点会继承所选目录模型的协议假设，无法修复不兼容的代理。目录外模型描述符与多模态内容仍不受支持。pi-ai 回放状态可能包含不透明的加密推理签名；提供方需要该信息维持连续性，因此系统会持久化该状态，但不会在现有会话记录之外渲染或记录它。
@@ -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/2026-07-19-zstandard-jsonl-session-logs.md
-2026-07-19-zstandard-jsonl-session-logs.md: 93fc20f931c75552352834b9340e7d38680d4254
-2026-07-19-zstandard-jsonl-session-logs.zh.md: d58f89430ab91de6beabba83c2a31f43e4a7d275
+2026-07-19-zstandard-jsonl-session-logs.md: a79bc3907c4f6c02851ba1814f733684ce373898
+2026-07-19-zstandard-jsonl-session-logs.zh.md: 178420c126b68689983d5b01f4ffae29b17fe657
@@ -14,9 +14,9 @@ The encoding also has to remain explicit at the deployment boundary. Snapshot fi

 ### Configuration and suffix ownership

-`dsh-session-persistence-jsonl` accepts `compression?: 'zstd' | 'none'` and explicitly resolves omission to `'zstd'`. Zstandard artifacts end in `.jsonl.zstd`; `'none'` retains the original newline-delimited UTF-8 `.jsonl` representation. `SessionLocation.kind` remains `'jsonl'`, because both encodings carry the same logical record format, and `SESSION_FORMAT_VERSION` remains `0` under the repository's pre-release reject-without-migration policy.
+`dsh-session-persistence-jsonl` accepts `compression?: 'zstd' | 'none'` and explicitly resolves omission to `'zstd'`. Zstandard artifacts end in `.jsonl.zstd`; `'none'` retains the newline-delimited UTF-8 `.jsonl` representation. Within either configured suffix, v0 uses suffixless `session.jsonl[.zstd]` and every positive format generation uses lowercase `session.vN.jsonl[.zstd]`. `SessionLocation.kind` remains `'jsonl'`, because both encodings carry the same logical record format. Session-format migration uses the configured full suffix and one shared logical chain, so compression does not branch generation selection or publication.

-Each persistence root belongs to one encoding. A one-time discovery preflight rejects any opposite suffix, and targeted load, live-adoption, listing, and materialization paths repeat the relevant suffix check after an initially empty preflight. The error names the incompatible artifact and directs the deployment to the matching configuration or a separate root. There is no migration, dual read, dual write, or extension-based fallback.
+Each persistence root belongs to one encoding. A one-time discovery preflight rejects any opposite suffix, and targeted load, live-adoption, listing, and materialization paths repeat the relevant suffix check after an initially empty preflight. The error names the incompatible artifact and directs the deployment to the matching configuration or a separate root. There is no compression conversion, dual read, dual write, or extension-based fallback; logical version migration stays within the configured suffix, preserves the source generation, and exclusively publishes the final version-named successor.

 ### Frame and write path

@@ -14,9 +14,9 @@ JSONL 持久化后端会逐字保留每个 `SessionEvent`，其中包括数量

 ### 配置与后缀归属

-`dsh-session-persistence-jsonl` 接受 `compression?: 'zstd' | 'none'`，并将省略值显式解析为 `'zstd'`。Zstandard 产物使用 `.jsonl.zstd` 后缀；`'none'` 保留原有的换行分隔 UTF-8 `.jsonl` 表示。`SessionLocation.kind` 仍为 `'jsonl'`，因为两种编码承载同一逻辑记录格式；按照仓库的预发布拒绝且不迁移策略，`SESSION_FORMAT_VERSION` 仍为 `0`。
+`dsh-session-persistence-jsonl` 接受 `compression?: 'zstd' | 'none'`，并将省略值显式解析为 `'zstd'`。Zstandard 产物使用 `.jsonl.zstd` 后缀；`'none'` 保留换行分隔 UTF-8 `.jsonl` 表示。在任一已配置后缀内，v0 使用无版本后缀 `session.jsonl[.zstd]`，每个正格式 generation 使用小写 `session.vN.jsonl[.zstd]`。`SessionLocation.kind` 仍为 `'jsonl'`，因为两种编码承载同一逻辑记录格式。Session 格式迁移使用配置后的完整后缀和同一条逻辑链，因此压缩不会分叉 generation 选择或发布。

-每个持久化根目录只归属于一种编码。一次性的发现预检会拒绝任何相反后缀，而针对性的加载、活跃采用、列举与物化路径会在最初空目录预检之后再次执行对应后缀检查。错误会指出不兼容产物，并要求部署选择匹配配置或单独根目录。系统不提供迁移、双重读取、双重写入或基于扩展名的兜底。
+每个持久化根目录只归属于一种编码。一次性的发现预检会拒绝任何相反后缀，而针对性的加载、活跃采用、列举与物化路径会在最初空目录预检之后再次执行对应后缀检查。错误会指出不兼容产物，并要求部署选择匹配配置或单独根目录。系统不提供压缩转换、双重读取、双重写入或基于扩展名的 fallback；逻辑版本迁移始终留在配置后缀内，保留源 generation，并排他发布最终具名版本后继。

 ### 帧与写入路径

@@ -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/2026-07-24-project-session-directories.md
-2026-07-24-project-session-directories.md: 0aa3f513d5a1bb3e44cf33a0ae1eb791ee3a46c2
-2026-07-24-project-session-directories.zh.md: 932b1d29c41d2a854abfc0bab0e47a0ff8c96fe9
+2026-07-24-project-session-directories.md: 199a2b273b791e1ee566e566fb59e1b83c63cdea
+2026-07-24-project-session-directories.zh.md: 8b6327e349c25aa438b2ad409152cd2c8b720822
@@ -19,9 +19,10 @@ The JSONL backend stores sessions under a readable project key and gives every s
  --<normalized-cwd>--/
    <encoded-session-id>/
      session.jsonl.zstd
+      session.v1.jsonl.zstd
 ```

-Raw mode uses `session.jsonl`, and sessions without a cwd use `_no-cwd`. Filesystem and drive separators become `-`, unsafe code units use `~XXXX`, and the readable name is bounded to keep the component within filesystem limits.
+The two files illustrate retained v0 plus current v1; raw mode omits `.zstd`, positive versions use lowercase `.vN`, and Sessions without a cwd use `_no-cwd`. Filesystem and drive separators become `-`, unsafe code units use `~XXXX`, and the readable name is bounded to keep the component within filesystem limits.

 The project key intentionally has no hash suffix. This follows the common human-readable convention used by coding agents and keeps the normalized project path as the complete directory name. The normalization is lossy: paths such as `/a/b-c` and `/a-b/c`, or long paths with the same retained prefix, share one project directory. Their distinct session ids still select separate session directories; reuse of the same session id remains a storage collision and is rejected.

@@ -29,9 +30,9 @@ Case-insensitive filesystems can also make differently cased project keys refer

 The configured root remains a deployment choice. The layout neither selects a global root nor requires projects to share one. When a deployment does centralize storage, project paths remain recognizable; a project-local root uses the same deterministic structure.

-The encoded session id names an ownership directory rather than the transcript itself. `SessionPersistence.locate()` continues to return the fixed transcript path, preserving hook `transcript_path` and `DSH_SESSION_JSONL` semantics. Discovery ignores other entries inside the session directory so the backend can add session-owned artifacts without another layout change.
+The encoded Session id names an ownership directory rather than one transcript. `SessionPersistence.locate(meta)` returns the canonical target for `meta.version`; header-only discovery scans canonical generation names and selects the numerically highest one, while ignoring unrelated entries. The directory can therefore retain prior generations and add other Session-owned artifacts without another layout change.

-Lazy materialization remains tied to the transcript: `create()` performs no filesystem I/O, and the first append creates the project/session directories before collision-safe transcript publication. Empty directories are not listed as sessions. The backend rejects flat `<project>/<id>.jsonl*` artifacts with an explicit layout error; the pre-release format provides no automatic data migration.
+Lazy materialization remains tied to the current generation: `create()` performs no filesystem I/O, and the first append creates the project/Session directories before no-overwrite publication at the current version's canonical name. Empty directories are not listed as Sessions. The backend rejects flat `<project>/<id>.jsonl*` artifacts with an explicit layout error; it provides no automatic migration from that obsolete directory layout.

 ## Alternatives considered

@@ -47,6 +48,6 @@ Lazy materialization remains tied to the transcript: `create()` performs no file

 ## Consequences

-Shared stores can be navigated by recognizable project names, while local and custom roots keep their existing configuration freedom. Every session has a directory available for future backend-owned artifacts, and existing transcript consumers still receive a file path.
+Shared stores can be navigated by recognizable project names, while local and custom roots keep their existing configuration freedom. Every Session has a directory for immutable generation names and other future backend-owned artifacts; callers receive either a version-qualified `locate` target or the exact highest path discovered by listing.

 Project directory names are longer than the former 12-hex cwd hashes. Very long paths show only a bounded prefix. Moving a project usually selects a different directory, but distinct cwd strings that normalize to the same name share one project directory by design.
@@ -19,9 +19,10 @@ JSONL 后端按可读的项目键存储会话，并为每个会话提供独立
  --<normalized-cwd>--/
    <encoded-session-id>/
      session.jsonl.zstd
+      session.v1.jsonl.zstd
 ```

-原始模式使用 `session.jsonl`，没有 cwd 的会话使用 `_no-cwd`。文件系统路径分隔符和驱动器分隔符会转换为 `-`，不安全的代码单元使用 `~XXXX`，可读名称则限制长度，以确保目录项不超过文件系统限制。
+这两个文件表示保留的 v0 与当前 v1；raw 模式省略 `.zstd`，正版本使用小写 `.vN`，没有 cwd 的 Session 使用 `_no-cwd`。文件系统路径分隔符和驱动器分隔符会转换为 `-`，不安全的代码单元使用 `~XXXX`，可读名称则限制长度，以确保目录项不超过文件系统限制。

 项目键有意不带哈希后缀。这遵循 coding agent（智能体）常用的易读约定，使规范化后的项目路径本身就是完整的目录名。规范化过程有损：`/a/b-c` 与 `/a-b/c` 等路径，或者保留前缀相同的长路径，会共用同一个项目目录。不同的会话 id 仍会选择不同的会话目录；复用相同的会话 id 仍构成存储冲突，系统会予以拒绝。

@@ -29,9 +30,9 @@ JSONL 后端按可读的项目键存储会话，并为每个会话提供独立

 根目录由部署配置决定。这种布局既不选择全局根目录，也不要求项目共享根目录。部署选择集中存储时，目录名仍能让项目路径易于辨认；使用项目本地根目录时，也采用同样的确定性结构。

-编码后的会话 id 用于命名归属目录，而不是 transcript 文件本身。`SessionPersistence.locate()` 仍返回固定的 transcript 路径，从而保持钩子 `transcript_path` 和 `DSH_SESSION_JSONL` 的语义不变。发现过程会忽略会话目录中的其他条目，因此后端以后添加会话自有产物时无需再次改变布局。
+编码后的 Session id 用于命名归属目录，而不是某一份 transcript。`SessionPersistence.locate(meta)` 返回 `meta.version` 的规范目标；仅 header 的发现会扫描规范 generation 名并选择数值最高的一项，同时忽略无关条目。因此，该目录可以保留先前 generation，也能添加其他 Session 自有产物，无需再次改变布局。

-延迟物化仍以 transcript 为界：`create()` 不执行文件系统 I/O，首次追加会先创建项目目录和会话目录，再以无冲突方式发布 transcript。空目录不会被列为会话。后端会显式报告布局错误并拒绝扁平的 `<project>/<id>.jsonl*` 产物；预发布格式不提供自动数据迁移。
+延迟物化仍以当前 generation 为界：`create()` 不执行文件系统 I/O，首次 append 会先创建项目目录和 Session 目录，再在当前版本的规范名称下以不覆盖方式发布。空目录不会被列为 Session。后端会显式报告布局错误并拒绝扁平的 `<project>/<id>.jsonl*` 产物；它不提供从该废弃目录布局自动迁移数据的能力。

 ## 考虑过的替代方案

@@ -47,6 +48,6 @@ JSONL 后端按可读的项目键存储会话，并为每个会话提供独立

 ## 后果

-共享存储可以通过易于辨认的项目名进行浏览，本地根目录和自定义根目录则继续保有现有的配置自由。每个会话都有一个可供后端未来存放自有产物的目录，而现有 transcript 消费方仍会收到文件路径。
+共享存储可以通过易于辨认的项目名进行浏览，本地根目录和自定义根目录则继续保有现有的配置自由。每个 Session 都有一个用于不可变 generation 名称与其他未来后端自有产物的目录；调用方会收到版本限定的 `locate` 目标，或列表发现的精确最高路径。

 项目目录名比原先由 12 个十六进制字符组成的 cwd 哈希更长。路径很长时，目录名只显示长度受限的前缀。移动项目通常会选择不同的目录，但按设计，不同的 cwd 字符串如果规范化成相同名称，就会共用同一个项目目录。
@@ -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: c6ed3911a797480804d064273922d85412664c79
-2026-07-30-session-end-seed-log-boundary.zh.md: 1e9517f9a5aed819fdaff6194ab952c322c85b82
+2026-07-30-session-end-seed-log-boundary.md: 79323c9b987bc220bc634393bc542baea409fbbb
+2026-07-30-session-end-seed-log-boundary.zh.md: b51c47ff5667c90e394c42f3ef1084c7ecd6b7ba
@@ -48,8 +48,8 @@ The predicate holds for a bracket *this* session inherited, not as a liveness si

 Bought: one boundary, written in one place, correct for all six seeded-start paths — including the fork gap the persistence-layer version could not reach. The persistence packages keep a pure read path. `firstLiveSeq` gains a durable twin rather than a second, competing notion of the same boundary.

-Cost: a seeded session's log is one event longer, including an empty resumed log. Seq expectations move with that boundary. Two updates are load-bearing rather than mechanical: telemetry's adoption tests assert the boundary IS exported, because it is this lifecycle's own write, and the property suite's replay invariant is "seed reproduced verbatim, plus one log-only boundary" with idempotence as its own property.
+Cost: a seeded session's log is one event longer, including an empty resumed log. Seq expectations move with that boundary. Two updates are load-bearing rather than mechanical: telemetry's adoption tests assert the boundary is exported as part of complete canonical-log replay, including when it arrived in a resumed constructor seed, and the property suite's replay invariant is "seed reproduced verbatim, plus one log-only boundary" with idempotence as its own property.

-`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.
+`session/end-seed` joins the on-disk vocabulary. Current v1 requires the validated marker semantics owned by Session; the frozen v0 codec and migration edge own which historical v0 seed layouts remain admissible. The exact inherited cut stays separate from the logical header and is available after a body read.

 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 `compaction/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.
@@ -48,8 +48,8 @@ Status: implemented

 买到的：一条边界，在一处写入，对全部六条带种子启动路径都正确——包括持久化层方案触及不到的 fork 缺口。持久化各包保留纯读取路径。`firstLiveSeq` 获得一个持久孪生体，而不是关于同一边界的第二套彼此竞争的概念。

-代价：带种子会话的日志长了一个事件，空日志恢复也包括在内。seq 期望会随这条边界移动。两处更新是承重的而非机械的：telemetry 的接管测试断言该边界*会*被导出，因为它是本生命周期的自有写入；属性测试套件的回放不变式则是「种子逐字节复现，外加一个仅日志边界」，并把幂等性作为独立属性。
+代价：带种子会话的日志长了一个事件，空日志恢复也包括在内。seq 期望会随这条边界移动。两处更新是承重的而非机械的：telemetry 的接管测试断言该边界会作为完整权威日志回放的一部分导出，包括它经由 resume constructor seed 进入时；属性测试套件的回放不变式则是「种子逐字节复现，外加一个仅日志边界」，并把幂等性作为独立属性。

-`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。
+`session/end-seed` 加入了落盘词汇表。当前 v1 要求由 Session 拥有的已校验 marker 语义；冻结的 v0 codec 与迁移边负责哪些历史 v0 seed 布局仍可接受。精确继承 cut 与逻辑 header 分离，并在读取正文后可用。

 [排队手动压缩决策](../feature/2026-07-30-queued-manual-compaction.zh.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 `compaction/start` 与最新 end-seed，只把位于该边界之后的 start 视为存活，并在同一个回放转换上清除不变量追踪状态。该谓词仍位于压缩功能所在的包中，不会成为通用核心辅助函数。
@@ -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/2026-08-05-session-preparation.md
-2026-08-05-session-preparation.md: 50f1ea38e671c6aa7b0f4adaf2fecbf83decc23c
-2026-08-05-session-preparation.zh.md: cd918d126b56b081bcc1b6aa43a10d662668102d
+2026-08-05-session-preparation.md: a8adcc577993f749be3658ee952e087c6943f462
+2026-08-05-session-preparation.zh.md: abe805505be351ecb9dc5face3e152c2f820a6be
@@ -22,7 +22,7 @@ This refines the publication boundary from the [Agent lifecycle and ownership de

 A coordinator-backed persistence implementation loads one cold source into a prepared Session. The backend transfers fresh, mutually unaliased metadata and events together with the source-qualified revision that identifies those exact values; the Session restore path validates and freezes the graphs in place instead of cloning them. The coordinator computes interrupted-turn closers and constructs the exact unpublished Session once. Its immutable header and balanced logical event log form the `SessionInspection` borrowed by readers, while the revision remains internal to persistence.

-`inspect(id, signal?)` does not mutate storage. Synthetic closers exist only in the prepared in-memory view, and a torn physical tail remains untouched. Same-id callers share an in-flight cold read. Once ready, the preparation may remain in a per-coordinator LRU whose capacity defaults to five and is configurable by first-party backends. Before reusing a retained source, the coordinator reads that id's current revision; a mismatch evicts a ready source and repeats the cold materialization. A source already committing or reserved for resume remains exclusively owned, so concurrent inspection borrows that immutable view until publication or release.
+For already-current input, `inspect(id, signal?)` does not mutate storage: synthetic closers exist only in the prepared in-memory view, and a torn physical tail remains untouched. A supported historical body read first publishes its migrated and repaired current generation. Same-id callers share an in-flight cold read. Once ready, the preparation may remain in a per-coordinator LRU whose capacity defaults to five and is configurable by first-party backends. Before reusing a retained source, the coordinator reads that id's current revision; a mismatch evicts a ready source and repeats the cold materialization. A source already committing or reserved for resume remains exclusively owned, so concurrent inspection borrows that immutable view until publication or release.

 `prepare(id, signal?)` exclusively reserves the prepared Session. It confirms the retained revision before committing any torn-tail and interrupted-turn repair, establishes the durable cursor, then returns a disposable preparation. A stale source is discarded and reloaded instead of being repaired or published. A successful repair also discards the pre-repair source and materializes the committed log again before reservation, so a newer revision is never associated with an older event graph. Another same-id preparation waits until the reservation is published or released. Publication accepts only the exact reserved Session and attaches the committed cursor without rebuilding its history. Failed setup or cancellation returns an unchanged unpublished Session to the LRU; mutation or attachment consumes the reservation.

@@ -38,7 +38,7 @@ Cold continuable-subagent access follows the same path. Descriptor authorization

 ## Boundaries

- `readFrom()` remains a detached physical-suffix API. It neither creates nor consumes a preparation, synthesizes logical closers, or joins the LRU.
+- `readFrom()` remains a detached physical-suffix API. It neither creates nor consumes a preparation nor joins the LRU. Current input synthesizes no logical closers; historical input may first publish its repaired current generation.
 - HMR adoption keeps the live Session authoritative and reads the stored prefix directly. It may truncate a torn physical fragment but never closes the live open turn as interrupted.
 - The cache belongs to one persistence coordinator, not a process-global Session map. Live Sessions are owned by the existing stores and never occupy preparation capacity.
 - A fresh create never claims a cold persisted preparation with the same id. Persistence collisions continue to reject.
@@ -47,7 +47,7 @@ Cold continuable-subagent access follows the same path. Descriptor authorization

 ## Verification

-The shared persistence contract pins non-mutating balanced cold inspection and later repair. `persistence.spec.ts` and `preparations.spec.ts` pin same-id in-flight sharing, exact Session reuse across inspect and prepare, revision-triggered refresh before history and resume, single repair commit, exclusive reservation, release after failed setup, ready-entry LRU eviction, append rejection during reservation, and publication of only the reserved Session. Backend tests pin that full and lightweight reads use the same revision identity. Agent-loop and continuable-subagent tests pin the common publication pipeline and inspection-to-resume path across cancellation and teardown.
+The shared persistence contract pins non-mutating balanced cold inspection for current input, historical migration-before-inspection, and later current repair. `persistence.spec.ts` and `preparations.spec.ts` pin same-id in-flight sharing, exact Session reuse across inspect and prepare, revision-triggered refresh before history and resume, single repair commit, exclusive reservation, release after failed setup, ready-entry LRU eviction, append rejection during reservation, and publication of only the reserved Session. Backend tests pin that full and lightweight reads use the same revision identity. Agent-loop and continuable-subagent tests pin the common publication pipeline and inspection-to-resume path across cancellation and teardown.

 ## Alternatives considered

@@ -65,4 +65,4 @@ The shared persistence contract pins non-mutating balanced cold inspection and l

 One cold materialization can serve history pagination, subagent descriptor inspection, and a later resume. Ownership transfer removes redundant restoration clones, while the bounded per-coordinator LRU limits memory and avoids creating live Agents for queries. Create and resume share one publication protocol without merging Agent and Session responsibilities.

-The first cold inspection now pays the complete validation and Session-construction cost and may retain that unpublished Session until eviction. Persistence must coordinate reservation, append, repair, and publication, and callers must treat inspection values as immutable borrowed state. Backends that rely on the default `prepare()` remain correct but do not receive the reuse optimization.
+The first cold inspection now pays the complete validation and Session-construction cost and may retain that unpublished Session until eviction; historical input also pays one durable migration and repair publication first. Persistence must coordinate reservation, append, repair, and publication, and callers must treat inspection values as immutable borrowed state. Backends that rely on the default `prepare()` remain correct but do not receive the reuse optimization.
@@ -22,7 +22,7 @@ agent loop（智能体循环）通过同一条设置与发布流水线消费这

 使用协调器的持久化实现会将一个冷源加载为准备完成的 Session。后端转移新鲜、彼此无别名的元数据和事件，以及标识这些精确值的来源限定 revision；Session 恢复路径直接验证并冻结这些对象图，不再复制。协调器计算中断轮次的 closer，并且只构造一次精确的未发布 Session。其不可变 header 与已配平的逻辑事件日志构成读取方借用的 `SessionInspection`，revision 则保留在持久化内部。

-`inspect(id, signal?)` 不修改存储。合成 closer 只存在于准备完成的内存视图中，撕裂的物理尾部保持不变。同 id 调用方共享进行中的冷读。准备完成后，该对象可以进入每个协调器自己的 LRU；第一方后端可配置容量，默认保留五个。协调器复用保留源之前会读取该 id 的当前 revision；如果不匹配，就淘汰处于就绪阶段的源并重新完成冷实体化。已经进入提交或为恢复而预留的源仍由其所有者独占，因此并发检查会借用该不可变视图，直至发布或释放。
+对于已经是当前格式的输入，`inspect(id, signal?)` 不修改存储：合成 closer 只存在于准备完成的内存视图中，撕裂的物理尾部保持不变。受支持的历史正文读取会先发布迁移并修复后的当前 generation。同 id 调用方共享进行中的冷读。准备完成后，该对象可以进入每个协调器自己的 LRU；第一方后端可配置容量，默认保留五个。协调器复用保留源之前会读取该 id 的当前 revision；如果不匹配，就淘汰处于就绪阶段的源并重新完成冷实体化。已经进入提交或为恢复而预留的源仍由其所有者独占，因此并发检查会借用该不可变视图，直至发布或释放。

 `prepare(id, signal?)` 独占预留准备完成的 Session。它先确认保留的 revision，再提交撕裂尾部和中断轮次修复、建立持久游标，最后返回可 dispose 的准备对象。陈旧源会被丢弃并重新读取，不会参与修复或发布。修复成功后也会丢弃修复前的源，并在预留前重新实体化已提交日志，以免把较新的 revision 关联到较旧的事件对象图。同 id 的另一个准备请求会等待当前预留发布或释放。发布只接受精确的预留 Session，并直接附接已提交游标，无需重建历史。设置失败或取消时，未发生变化的未发布 Session 会返回 LRU；发生变更或完成附接后，系统会消费该预留。

@@ -38,7 +38,7 @@ agent loop（智能体循环）通过同一条设置与发布流水线消费这

 ## 边界

- `readFrom()` 仍是脱离的物理后缀 API。它不会创建或消费准备对象，不会合成逻辑 closer，也不会进入 LRU。
+- `readFrom()` 仍是脱离的物理后缀 API。它不会创建或消费准备对象，也不会进入 LRU。当前输入不会合成逻辑 closer；历史输入可能先发布已修复的当前 generation。
 - HMR（热模块替换）接管继续以实时 Session 为权威，并直接读取已存储前缀。它可以截断撕裂的物理碎片，但绝不把实时开放轮次关闭为中断状态。
 - 缓存属于单个持久化协调器，而不是进程全局 Session map。实时 Session 由现有存储持有，绝不占用准备容量。
 - 新建流程绝不认领相同 id 的冷持久化准备对象。持久化冲突仍会被拒绝。
@@ -47,7 +47,7 @@ agent loop（智能体循环）通过同一条设置与发布流水线消费这

 ## 验证

-共享持久化约定规定冷检查不得修改存储且须保持配平，并覆盖后续修复。`persistence.spec.ts` 与 `preparations.spec.ts` 覆盖同 id 进行中读取共享、检查与准备之间的精确 Session 复用、在历史读取与恢复前由 revision 触发刷新、修复只提交一次、独占预留、设置失败后释放、就绪项 LRU 淘汰、预留期间拒绝 append，以及只允许发布预留 Session。后端测试覆盖完整读取与轻量读取使用同一 revision 身份。agent loop 与 continuable subagent 测试覆盖统一发布流水线，以及取消和清理期间从检查到恢复的路径。
+共享持久化约定规定当前格式冷检查不修改存储且须保持配平，并覆盖历史迁移先于检查与后续当前修复。`persistence.spec.ts` 与 `preparations.spec.ts` 覆盖同 id 进行中读取共享、检查与准备之间的精确 Session 复用、在历史读取与恢复前由 revision 触发刷新、修复只提交一次、独占预留、设置失败后释放、就绪项 LRU 淘汰、预留期间拒绝 append，以及只允许发布预留 Session。后端测试覆盖完整读取与轻量读取使用同一 revision 身份。agent loop 与 continuable subagent 测试覆盖统一发布流水线，以及取消和清理期间从检查到恢复的路径。

 ## 考虑过的替代方案

@@ -65,4 +65,4 @@ agent loop（智能体循环）通过同一条设置与发布流水线消费这

 一次冷实体化可以同时服务历史分页、subagent descriptor 检查和后续恢复。所有权转移去除了恢复阶段的冗余复制；每个协调器的有界 LRU 限制内存占用，也避免查询创建实时 agent。新建和恢复共享同一发布协议，同时保持 agent 与 Session 职责分离。

-首次冷检查需要承担完整验证与 Session 构造成本，并可能保留该未发布 Session 直至淘汰。持久化层必须协调预留、append、修复和发布；调用方必须把检查结果视为借用的不可变状态。依赖默认 `prepare()` 的后端仍然正确，但无法获得复用优化。
+首次冷检查需要承担完整验证与 Session 构造成本，并可能保留该未发布 Session 直至淘汰；历史输入还会先承担一次持久迁移与修复发布。持久化层必须协调预留、append、修复和发布；调用方必须把检查结果视为借用的不可变状态。依赖默认 `prepare()` 的后端仍然正确，但无法获得复用优化。
@@ -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/2026-08-10-message-feedback-sidecar.md
-2026-08-10-message-feedback-sidecar.md: eb1f8786f9ec0363b3c98d5b80a796b9c0fc0b4c
-2026-08-10-message-feedback-sidecar.zh.md: 573d3b30e3bd14b492925f4a00424db588736943
+2026-08-10-message-feedback-sidecar.md: 94c607e14704a9a41a4ff0beca084c97e982d959
+2026-08-10-message-feedback-sidecar.zh.md: dbebb77febde3a111595d828005f79c552c6799b
@@ -16,7 +16,7 @@ A sidecar keyed only by `SessionId` can outlive the log lifecycle it describes w

 Every usable row is bound to the inspected Session header identity `{createdAt, cwd}`, not merely its `SessionId`. A lifecycle mismatch is treated as absence: `list` returns no items, and `put` may replace the stale row with one bound to the current identity. An id reused with a different header identity therefore cannot inherit stale feedback. A fork receives its own Session identity and no sidecar copy: even when the fork seed contains the same assistant messages, feedback remains attached to the Session in which the human recorded it.

-`put` accepts a target only when `SessionPersistence.inspect()` observes a non-empty, append-origin `assistant/message` with that `MessageId`. Replacement-origin messages, empty usage-only assistant records, and non-assistant targets are rejected. Inspection is the cold-safe authority: it neither publishes or resumes an Agent nor commits cold-log repair merely to validate feedback. A cold `listSnapshots()` preflight classifies definite absence; inspection failure for a catalogued Session remains an infrastructure failure. A request in the narrow live-detach-to-header-materialization interval can therefore return `session-not-found`, and the caller retries after retirement materialization.
+`put` accepts a target only when `SessionPersistence.inspect()` observes a non-empty, append-origin `assistant/message` with that `MessageId`. Replacement-origin messages, empty usage-only assistant records, and non-assistant targets are rejected. Inspection is the cold-safe authority: it never publishes or resumes an Agent; already-current repair stays in memory, while a supported historical body read may first publish migration and repair. A cold `listSnapshots()` preflight classifies definite absence; inspection failure for a catalogued Session remains an infrastructure failure. A request in the narrow live-detach-to-header-materialization interval can therefore return `session-not-found`, and the caller retries after retirement materialization.

 Before `put` commits a sidecar row, it puts the target log behind a durability barrier. A matching live Session passes through the canonical `ctx.sessions.flush` checkpoint, then both live and cold paths are physically read from sequence zero through `SessionPersistence.readFrom`. The resulting observation's header identity and target are checked again. A missing flush participant, changed identity, vanished target, or physical-read failure prevents the sidecar write, so a committed feedback item never precedes the durable assistant message it references.

@@ -16,7 +16,7 @@ Status: implemented

 每条可用记录都绑定到经检查的 Session header 身份 `{createdAt, cwd}`，而不只是其 `SessionId`。生命周期不匹配按不存在处理：`list` 返回空条目，`put` 可以用绑定当前身份的新记录替换陈旧行。因此，以不同 header 身份复用的 id 不会继承陈旧反馈。fork 拥有自己的 Session 身份，且不复制伴随记录：即使 fork 种子包含相同的 assistant 消息，反馈仍只属于人类记录它的那个 Session。

-`put` 只接受由 `SessionPersistence.inspect()` 观测到的非空、append-origin `assistant/message`，且其 `MessageId` 必须与目标相同。replacement-origin 消息、仅承载 usage 的空 assistant 记录以及非 assistant 目标都会被拒绝。检查使用 cold-safe 权威路径：它不会仅为验证反馈而发布或恢复 Agent，也不会提交 cold 日志修复。cold 路径由 `listSnapshots()` 预检明确不存在；已进入目录的 Session 若检查失败，仍按基础设施故障处理。因此，请求若恰落在 live detach 到 header materialization 的极短窗口，可能返回 `session-not-found`，调用方在 retirement materialization 后重试。
+`put` 只接受由 `SessionPersistence.inspect()` 观测到的非空、append-origin `assistant/message`，且其 `MessageId` 必须与目标相同。replacement-origin 消息、仅承载 usage 的空 assistant 记录以及非 assistant 目标都会被拒绝。检查使用 cold-safe 权威路径：它绝不发布或恢复 Agent；已经是当前格式的修复留在内存中，受支持的历史正文读取则可能先发布迁移与修复。cold 路径由 `listSnapshots()` 预检明确不存在；已进入目录的 Session 若检查失败，仍按基础设施故障处理。因此，请求若恰落在 live detach 到 header materialization 的极短窗口，可能返回 `session-not-found`，调用方在 retirement materialization 后重试。

 `put` 提交伴随记录前，会先让目标日志通过 durability barrier。身份匹配的 live Session 经过权威 `ctx.sessions.flush` checkpoint，随后 live 与 cold 路径都会通过 `SessionPersistence.readFrom` 从序列零做物理复读。之后再次校验所得观测的 header 身份与目标。缺少 flush 参与方、身份变化、目标消失或物理读取失败都会阻止伴随记录写入，因此已提交反馈绝不会先于它引用的持久 assistant 消息。

@@ -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/2026-08-10-session-log-version-mechanism.md
-2026-08-10-session-log-version-mechanism.md: 0d4c9e73acc6abd4a67123e3d7b0e4f94e0b5a23
-2026-08-10-session-log-version-mechanism.zh.md: 6c57da618a09c1d423323940ea36dbd4caccde02
+2026-08-10-session-log-version-mechanism.md: 19650ca6a02139d6ad138c6914185f210386ce49
+2026-08-10-session-log-version-mechanism.zh.md: a54a1f30d2d30e55b7c03d529e1ca337346ce2d2
@@ -14,17 +14,17 @@ Session logs must be upgradable after release, and the runtime that ships first

 **The writer decides bumps, not the reader.** A bump is required exactly when an old runtime could no longer handle a new log with full semantic correctness. "Parses without error" is not the bar: silently skipping content that shapes reconstruction is a wrong read. Only structural changes qualify — header shape, event envelope, core event semantics, the surface mechanism (`SurfaceEventType` set, `SurfaceOp` variants). When unsure, bump: a near-identity upgrader is almost free, a missed bump silently corrupts old readers.

-**Read rules by direction.** Equal version: read normally. Newer than the reader: refuse, name the direction ("written by a newer harness — upgrade"), and point at the raw log artifact so the user can still see the text (`SessionFormatUnsupportedError`, distinct from `SessionPersistenceCorruptionError` because nothing is damaged). Older than the reader: convert in memory through the chain of n→n+1 upgraders for viewing; persist the converted log only when the session is actually continued (atomic temp-file replace, original kept as backup). A step whose upgrader cannot be written is left empty, which cuts off every version at or below it — those degrade to raw-text viewing.
+**Read rules by direction.** Equal version: read normally. Newer than the reader: refuse, name the direction ("written by a newer harness — upgrade"), and point at the raw log artifact so the user can still see the text (`SessionFormatUnsupportedError`, distinct from `SessionPersistenceCorruptionError` because nothing is damaged). Older than the reader: every event-body operation first runs the complete adjacent chain in memory, leaves the source path, bytes, and inode unchanged, exclusively publishes only the final current generation under its canonical versioned filename, and reopens it before current restoration. Header-only listing remains non-mutating and reports the numerically highest canonical generation. Catalog generation and module initialization reject a missing adjacent step, so a published first-party build never exposes a partial historical chain. Retained lower generations are not automatic fallback or a downgrade compatibility promise.

 **A per-event `ignorable` marker covers vocabulary growth, so ordinary event additions never bump the version.** The event vocabulary is decided by which plugins are mounted, which a single version integer cannot describe. A reader meeting an unrecognized event type refuses to interpret the log unless the event carries `ignorable: true` in its envelope. The default is *required*: forgetting the marker over-refuses a resumable session (an inconvenience), while a default of ignorable would make the same mistake silently resume a gutted one (a safety failure). The architecture makes this sound: model-visible content flows only through the three `surfaceOp`-marked surface event types plus the `request/header`/`request/context` folds, so the dangerous unknowns are exactly the non-surface events that change how the rest of the log is read (`session/end-seed` is the existing example).

 ## Consequences

-What shipped in v0 (release 0812): direction-aware refusal with the raw-log path; the unknown-event guard against a generated known-vocabulary list (`KNOWN_SESSION_EVENT_TYPES`, emitted by `gen-persistence-catalog` from every `SessionEventMap` merge and kept fresh by `verify-persistence-catalog`); the `ignorable` envelope field accepted by seed validation, JSONL, and the BFF wire schema. The upgrader chain itself is deferred until the first real v0→v1 step exists to test it against. First-party writers do not set `ignorable` through `Session.append`, while a repository-external plugin is a current consumer; its retention and replacement condition lives in the [external-plugin retention decision](2026-08-30-retain-ignorable-external-session-events.md). An external informational event carrying the marker remains reloadable, while an unknown required event refuses resume. The unknown-type guard is read-side only: `appendCore` keeps rejecting retired legacy shapes but does not vocabulary-check new types, because an append-time refusal would stall a live session's durability mid-flight, which costs more than a loud refusal at the log's next load. The JSONL provider refuses a foreign version from the raw header line before validating this format version's header or decoding any event row, so a structurally different future format still reports the upgrade direction instead of "corrupt".
+What shipped in v0 (release 0812): direction-aware refusal with the raw-log path; the unknown-event guard against a generated known-vocabulary list (`KNOWN_SESSION_EVENT_TYPES`, emitted by `gen-persistence-catalog` from every `SessionEventMap` merge and kept fresh by `verify-persistence-catalog`); the `ignorable` envelope field accepted by seed validation, JSONL, and the BFF wire schema. V1 adds the static adjacent catalog, the identity v0-to-v1 edge, header-only descriptors, exact-generation JSONL publication, and current-only restoration described in [Released Session formats](2026-08-31-released-session-format-migrations.md). First-party writers do not set `ignorable` through `Session.append`, while a repository-external plugin is a current consumer; equal-version retention lives in the [external-plugin retention decision](2026-08-30-retain-ignorable-external-session-events.md), and the stricter historical rule lives in the [alpha migration refusal decision](2026-08-31-alpha-historical-unknown-event-refusal.md). The unknown-type guard remains read-side because append-time vocabulary refusal would stall a live session's durability. JSONL classifies foreign versions from the minimal raw header before current-header or event parsing, so a structurally different future format reports the upgrade direction instead of "corrupt".

 ## Alternatives considered

 - **Major/minor versioning** — the "is it convertible" bit lives on each step's upgrader, and pre-committing it into a number shape invites wrong promises.
 - **Default-ignorable unknown events** — inverts the failure mode of a forgotten marker from visible over-refusal into silent corruption.
- **Auto-migrating on view** — rewriting the artifact on open turns a read into a destructive write: a converter bug corrupts logs at browse time, and a same-directory older runtime loses access because a newer one merely looked.
+- **Migrating during header-only listing** — makes cheap inventory mutate storage and requires event bodies to compute facts that a header cannot prove. Listing returns descriptors; event-body reads own publication.
 - **Per-plugin runtime registration of known event types** — rejected because it would make the known set composition-dependent and register event names without classifying whether omission is safe. The persisted `ignorable` marker keeps that classification with each record; the [external-plugin retention decision](2026-08-30-retain-ignorable-external-session-events.md) owns the current consumer constraint.
@@ -14,17 +14,17 @@ Session log 在发布后必须能升级格式，而最先发布的运行时决

 **升不升版本由写入方决定，与读取方能力无关。**当且仅当老运行时无法在语义上完全正确地处理新日志时才必须升版本。"解析不报错"不是标准：静默跳过影响重建的内容就是读错。只有结构性变更够得上这条线：header 形状、事件信封、核心事件语义、surface 机制（`SurfaceEventType` 集合、`SurfaceOp` 变体）。拿不准就升：近似恒等的升级器几乎没有成本，漏升一次会让老读取器静默读坏。

-**读取规则按方向区分。**版本相等：正常读。比读取器新：拒绝，说明方向（"由更新的 harness 写入，请升级"），并给出原始日志文件的路径，用户仍能看到文本（`SessionFormatUnsupportedError`，与 `SessionPersistenceCorruptionError` 区分，因为数据没有损坏）。比读取器旧：查看时经 n→n+1 升级器链在内存中逐级转换；只有会话真正被继续时才把转换落盘（临时文件原子替换，原文件留备份）。写不出升级器的那一步留空，这会切断该步及更早所有版本的升级路径，它们降级为只能看原文。
+**读取规则按方向区分。**版本相等：正常读。比读取器新：拒绝，说明方向（"由更新的 harness 写入，请升级"），并给出原始日志文件的路径，用户仍能看到文本（`SessionFormatUnsupportedError`，与 `SessionPersistenceCorruptionError` 区分，因为数据没有损坏）。比读取器旧：每个事件正文操作先在内存中运行完整相邻链，保持源路径、字节与 inode 不变，只在规范具名版本文件下排他发布最终当前 generation，再在当前恢复前重新打开。仅 header 的列表保持不变更，并报告数值最高的规范 generation。catalog 生成与模块初始化会拒绝缺失的相邻步骤，因此已发布第一方 build 绝不会暴露不完整历史链。保留的低 generation 不是自动 fallback，也不构成 downgrade compatibility 承诺。

 **逐事件的 `ignorable` 标记吸收词汇表增长，普通的新增事件永远不用升版本。**事件词汇表由挂载了哪些插件决定，单个版本整数描述不了它。读取器遇到不认识的事件类型时拒绝解读日志，除非该事件的信封带 `ignorable: true`。默认为必需：忘写标记的后果是把一个本可恢复的会话拒绝过头（体验问题），而默认可忽略会让同样的疏忽静默恢复出残缺会话（安全事故）。架构保证了这条规则成立：模型可见内容只经三种带 `surfaceOp` 标记的 surface 事件加 `request/header`、`request/context` 折叠进入重建，危险的未知事件恰好是那些不进 surface 但改变日志其余部分解读方式的事件（`session/end-seed` 是现存例子）。

 ## 影响

-v0（0812 发布）交付的内容：分方向的拒绝并带原始日志路径；基于生成的已知词汇清单（`KNOWN_SESSION_EVENT_TYPES`，由 `gen-persistence-catalog` 从所有 `SessionEventMap` 声明合并生成，`verify-persistence-catalog` 保证新鲜）的未知事件守卫；`ignorable` 信封字段被种子校验、JSONL 和 BFF 线上 schema 接受。升级器链本身推迟到第一个真实的 v0→v1 变更出现、有真实对象可测时再建。第一方写入方不通过 `Session.append` 设置 `ignorable`，但当前有一个仓库外插件依赖该字段；其保留条件与替代机制要求由[外部插件保留决策](2026-08-30-retain-ignorable-external-session-events.zh.md)定义。带该标记的外部信息性事件可以继续重新加载，未知必需事件则会拒绝恢复。未知类型守卫只在读取侧生效：`appendCore` 继续拒绝已淘汰的 legacy 形状，但不对新类型做词汇检查，因为写入时拒绝会让活跃会话的持久化中途停摆，代价大于下次加载时的显式拒绝。JSONL provider 会在校验本格式版本的 header、解码任何事件行之前，直接从原始 header 行拒绝外来版本，因此结构完全不同的未来格式仍会报告升级方向而不是"损坏"。
+v0（0812 发布）交付的内容：分方向的拒绝并带原始日志路径；基于生成的已知词汇清单（`KNOWN_SESSION_EVENT_TYPES`，由 `gen-persistence-catalog` 从所有 `SessionEventMap` 声明合并生成，`verify-persistence-catalog` 保证新鲜）的未知事件守卫；`ignorable` 信封字段被种子校验、JSONL 和 BFF 线上 schema 接受。V1 添加静态相邻 catalog、恒等 v0-to-v1 迁移边、仅 header descriptor、精确代际 JSONL 发布与[已发布 Session 格式](2026-08-31-released-session-format-migrations.zh.md)定义的当前专用恢复。第一方 writer 不通过 `Session.append` 设置 `ignorable`，而一个仓库外插件仍依赖该字段；同版本保留由[外部插件保留决策](2026-08-30-retain-ignorable-external-session-events.zh.md)定义，更严格的历史规则由 [alpha 迁移拒绝决策](2026-08-31-alpha-historical-unknown-event-refusal.zh.md)定义。未知类型守卫仍只在读取侧生效，因为 append 时的词汇拒绝会中断活跃 Session 的持久化。JSONL 会在当前 header 或事件解析前从最小原始 header 分类外来版本，因此结构完全不同的未来格式会报告升级方向而不是"损坏"。

 ## 曾考虑的替代方案

 - **大小两级版本号**：能否转换这一位信息属于每一步的升级器，把它预先固化进编号形状会做出错误承诺。
 - **未知事件默认可忽略**：把忘写标记的后果从可见的过度拒绝反转成静默损坏。
- **查看时自动迁移落盘**：打开即改写把读操作变成破坏性写操作，转换器的 bug 会在浏览时损坏日志，同目录的旧版本运行时也会因为新版本只是看了一眼就失去访问能力。
+- **在仅 header 列表期间迁移**：让便宜清单改变存储，而且需要读取事件正文才能计算 header 无法证明的事实。列表返回 descriptor，事件正文读取负责发布。
 - **插件运行时注册已知事件类型**：不予采用，因为该方案会让已知集依赖插件组合，而且只注册事件名称，无法判定省略事件是否安全。持久化的 `ignorable` 标记把该分类保留在每条记录中；[外部插件保留决策](2026-08-30-retain-ignorable-external-session-events.zh.md)定义当前消费方约束。
@@ -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/2026-08-25-rename-code-mode-to-ptc.md
-2026-08-25-rename-code-mode-to-ptc.md: 618167516aefc54445d37cb1ce3939419e707bf5
-2026-08-25-rename-code-mode-to-ptc.zh.md: d6cf5cdea1154bd2b8cb424653b76315bb20b05d
+2026-08-25-rename-code-mode-to-ptc.md: 10c81fdca8acc67ab0e5e3b29c785ab4aec1d925
+2026-08-25-rename-code-mode-to-ptc.zh.md: 881ea86030ae09f198f12ac769d5ccd07159dba2
@@ -21,7 +21,7 @@ Renamed in this PR:
 - prompt rule `tools:code-only` → `tools:ptc-only`
 - prose "Code Mode" → "PTC mode" / "PTC 模式" in docs, READMEs, and the eight implemented Agent Notes whose topic names the feature (those files were renamed in place)

-Deferred to the stacked persistence PR: the session-persistent vocabulary — the durable event types `tool/code-dispatch` / `tool/code-dispatch-start`, the logged plugin name `tools-code-mode`, and the sub-call id segment `:code:`. That PR is blocked until the `SESSION_FORMAT_VERSION` v0→v1 migration lands with it.
+The session-persistent vocabulary remains deferred: the durable event types `tool/code-dispatch` / `tool/code-dispatch-start`, the logged plugin name `tools-code-mode`, and the sub-call id segment `:code:`. Renaming those values is a structural Session-format change and requires its own adjacent edge after the identity v0-to-v1 foundation.

 Kept unchanged: `run_code` and its `code` parameter (they name the program payload, not the mode), `CodeSdkLanguage`, `CodeRunFailedError`, the `dsh-code-runtime*` package family, the third-party `codex-code-mode-host` binary name, and every frozen archived note.

@@ -30,8 +30,8 @@ Kept unchanged: `run_code` and its `code` parameter (they name the program paylo
 - **`ptc-mode` identifiers** — rejected: PTC is a tool-presentation transport, not a mode in the plan-mode sense, and the identifier should not claim that kinship.
 - **Surface-only rename** — rejected: the pre-release stance updates every reference together.
 - **Renaming `run_code` too** — rejected: the tool name describes running a program, not the mode, and is model-facing API surface.
- **Renaming the durable event vocabulary in this PR** — rejected: renaming `tool/code-dispatch*` without a format bump would make pre-rename session logs unreadable; that rename belongs to the stacked persistence PR that lands together with the v0→v1 migration.
+- **Renaming the durable event vocabulary without an adjacent edge** — rejected: renaming `tool/code-dispatch*` in place would make pre-rename Session logs unreadable; that rename requires a later structural format version and explicit migration.

 ## Consequences

-Configs with `mode: code` and preset ids `code` are unsupported on this build. The session-persistent vocabulary still says `tool/code-dispatch*`, `tools-code-mode`, and `:code:`, so existing session logs load unchanged and no `SESSION_FORMAT_VERSION` bump is needed yet. The stacked persistence PR renames that vocabulary and is blocked until the v0→v1 migration lands with it (the version mechanics are in the [session-log versioning note](2026-08-10-session-log-version-mechanism.md)). Keyless snapshot refreshes carry this PR's vocabulary; the persistence PR refreshes the dispatch-bearing fixtures. The shipped decision this note renames is [the PTC foundation note](../feature/2026-06-15-ptc.md).
+Configs with `mode: code` and preset ids `code` are unsupported on this build. The session-persistent vocabulary still says `tool/code-dispatch*`, `tools-code-mode`, and `:code:`; the identity v0-to-v1 edge preserves those values, so no structural version change belongs to this rename. A later adjacent edge must rename that vocabulary and refresh the dispatch-bearing fixtures ([version mechanics](2026-08-10-session-log-version-mechanism.md)). The shipped decision this note renames is [the PTC foundation note](../feature/2026-06-15-ptc.md).
@@ -21,7 +21,7 @@ Status: implemented
 - 提示词规则 `tools:code-only` → `tools:ptc-only`
 - 文档、README 与八个以该功能命名的 implemented Agent Note 中的文案 "Code Mode" → "PTC mode"／"PTC 模式"（这些 Note 文件一并就地改名）

-延后到堆叠的持久化 PR：会话持久词汇——持久事件类型 `tool/code-dispatch`／`tool/code-dispatch-start`、日志中的插件名 `tools-code-mode`、子调用 id 段 `:code:`。该 PR 被阻塞，直到 `SESSION_FORMAT_VERSION` v0→v1 迁移与其一同落地。
+会话持久词汇继续延后处理：持久事件类型 `tool/code-dispatch`／`tool/code-dispatch-start`、日志中的插件名 `tools-code-mode`、子调用 id 段 `:code:`。重命名这些值属于结构性 Session 格式变更，必须在恒等 v0-to-v1 基础之后拥有自己的相邻迁移边。

 保持不变：`run_code` 及其 `code` 参数（它们描述程序载荷，而非模式）、`CodeSdkLanguage`、`CodeRunFailedError`、`dsh-code-runtime*` 包族、第三方二进制名 `codex-code-mode-host`，以及所有冻结的 archived Note。

@@ -30,8 +30,8 @@ Status: implemented
 - **使用 `ptc-mode` 标识符**——否决：PTC 是工具呈现传输层，不是 plan-mode 意义上的模式，标识符不应宣示这种亲缘关系。
 - **仅重命名表面**——否决：预发布立场要求一次性更新所有引用。
 - **连 `run_code` 一起改名**——否决：该工具名描述的是运行程序，不是模式，而且是对模型可见的 API 表面。
- **在本 PR 中一并重命名持久事件词汇**——否决：在没有格式版本提升的情况下重命名 `tool/code-dispatch*` 会让更名前的会话日志无法读取；该重命名属于与 v0→v1 迁移一同落地的堆叠持久化 PR。
+- **不提供相邻迁移边就重命名持久事件词汇**——否决：就地重命名 `tool/code-dispatch*` 会让更名前的 Session 日志无法读取；该重命名需要后续结构格式版本与显式迁移。

 ## 后果

-配置中写 `mode: code`、预设 id 为 `code`，在本构建上不再受支持。会话持久词汇仍为 `tool/code-dispatch*`、`tools-code-mode` 与 `:code:`，因此既有会话日志照常读取，无需 `SESSION_FORMAT_VERSION` 提升。堆叠的持久化 PR 负责重命名该词汇，并被阻塞到 v0→v1 迁移与其一同落地（版本机制见 [Session log 版本 Note](2026-08-10-session-log-version-mechanism.zh.md)）。无密钥的 snapshot refresh 携带本 PR 的词汇；持久化 PR 刷新包含分发的夹具。本 Note 所更名的已发布决策是 [PTC 基础 Note](../feature/2026-06-15-ptc.zh.md)。
+配置中写 `mode: code`、预设 id 为 `code`，在本构建上不再受支持。会话持久词汇仍为 `tool/code-dispatch*`、`tools-code-mode` 与 `:code:`；恒等 v0-to-v1 迁移边会保留这些值，因此本次更名不包含结构版本变更。后续相邻迁移边必须重命名该词汇并刷新包含分发的 fixture（参见[版本机制](2026-08-10-session-log-version-mechanism.zh.md)）。本 Note 所更名的已发布决策是 [PTC 基础 Note](../feature/2026-06-15-ptc.zh.md)。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-30-retain-ignorable-external-session-events.md
-2026-08-30-retain-ignorable-external-session-events.md: c796a8dab1a9d127473a341fc98bc9934429fbdf
-2026-08-30-retain-ignorable-external-session-events.zh.md: 0c635b1082a31a0a35d01669ff9f933a1f218bee
+2026-08-30-retain-ignorable-external-session-events.md: 60d78d452e854f9c82e6edb739bdd1060b6376d3
+2026-08-30-retain-ignorable-external-session-events.zh.md: cf845ef1e6fad20ee6cc9059436d6cf7a1d75ed7
@@ -16,6 +16,8 @@ The canonical `SessionEvent` envelope retains `ignorable?: true`, and every repr

 The field is removable only after a replacement supports the current third-party plugin across event production, persistence, reload, and transport, with an explicit cutover for sessions already containing the marker. The [session log versioning decision](2026-08-10-session-log-version-mechanism.md) continues to own the default-required safety rule and format-version policy.

+Historical format migration is deliberately stricter in the alpha implementation. The v0-to-v1 edge refuses every unknown v0 type, including an ignorable one, because an opaque payload may contain references that a format edge cannot validate. The [alpha historical-event decision](2026-08-31-alpha-historical-unknown-event-refusal.md) owns that bounded exception; equal-version append and reload continue to follow this note.
+
 ## Alternatives considered

 **Require every unknown event on read.** Rejected because the current third-party plugin emits an informational event outside the repository-generated vocabulary. A first-party reload would reject that session even though omitting the event is safe.
@@ -16,6 +16,8 @@ Status: implemented

 只有替代机制在事件生产、持久化、重新加载与传输中都支持当前第三方插件，并为已包含该标记的会话提供显式切换方案后，才能删除此字段。[Session log 版本决策](2026-08-10-session-log-version-mechanism.zh.md)继续定义默认读取必需的安全规则与格式版本策略。

+Alpha 实现中的历史格式迁移有意更严格。v0-to-v1 迁移边会拒绝每个未知 v0 类型，包括 ignorable 类型，因为不透明 payload 可能包含格式迁移边无法校验的引用。[Alpha 历史事件决策](2026-08-31-alpha-historical-unknown-event-refusal.zh.md)定义该有限例外；同版本 append 与 reload 继续遵循本记录。
+
 ## 曾考虑的替代方案

 **要求读取所有未知事件。** 不予采用，因为当前第三方插件会发出仓库生成词汇之外的信息性事件。即使省略该事件是安全的，第一方重新加载仍会拒绝该会话。
@@ -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/architecture/2026-08-31-alpha-historical-unknown-event-refusal.md
+2026-08-31-alpha-historical-unknown-event-refusal.md: a052c76e37ff3d4649f3fdd1e172a2f569ade857
+2026-08-31-alpha-historical-unknown-event-refusal.zh.md: ac6fd0631187735e7ddbdda0ca90f12c8417291c
@@ -0,0 +1,37 @@
+# Agent Note: Alpha Session migration refuses every unknown historical event
+
+Status: implemented
+
+English | [中文](2026-08-31-alpha-historical-unknown-event-refusal.zh.md)
+
+## Problem
+
+Equal-version Session reading can safely skip an unknown event only when its producer marked the envelope `ignorable: true`. A cardinality-preserving migration has a stricter obligation: it must prove that every preserved payload remains semantically valid in the target generation. An unknown JSON payload may contain Session sequence numbers, lifecycle facts, or model-visible state that compile-time brands cannot discover.
+
+Silently copying such an event can leave stale numeric references after a later edge changes event positions. Silently omitting it loses durable data. Retaining the exact immutable v0 generation does not make either transformed v1 result lossless.
+
+## Decision
+
+The alpha v0-to-v1 edge owns a frozen complete released-v0 event and payload inventory. It refuses every unknown historical event type before target staging, including an event marked `ignorable: true`, and refuses unexpected members of known payloads except fields explicitly classified as owner-opaque JSON. The diagnostic names the event type, its sequence number, and the unchanged source generation.
+
+The rule applies only while crossing a historical format edge. Ordinary current-format reading retains the established envelope behavior: an unknown required event refuses, while an unknown event carrying `ignorable: true` remains readable. New v1 external events therefore keep the existing equal-version extension seam, but they do not become implicitly migratable by a future format edge.
+
+Every first-party source event type has an executable disposition and target validator in the edge package. The catalog is build-static and profile-independent, so mounting or omitting the producer plugin cannot change whether an old artifact migrates.
+
+## Consequences
+
+Some v0 Sessions produced by repository-external informational plugins may refuse alpha migration even though the v0 codec can decode them. Refusal publishes no successor, so the suffixless v0 path, bytes, and inode remain authoritative and unchanged. Operators can identify the blocking type from the diagnostic and retain full access to its raw text.
+
+Community feedback will determine the next policy. A later release may add an explicit external-owner migration interface, permit omission of explicitly ignorable historical events while retaining the exact source generation, or keep strict refusal. No option is implied by the alpha marker.
+
+`SessionSeq` and `SessionLogOffset` make known first-party numeric fields auditable, but they cannot classify numbers inside an unknown runtime object. The migration rule therefore cannot infer safety from the absence of a recognized branded field.
+
+This note supersedes [Retain ignorable external Session events](2026-08-30-retain-ignorable-external-session-events.md) only for historical format migration. That decision remains current for equal-version append and reload.
+
+## Alternatives considered
+
+- **Copy unknown ignorable events verbatim** — preserves bytes but cannot prove that opaque numeric or lifecycle facts remain valid after structural edges.
+- **Drop unknown ignorable events** — keeps migration available but is not lossless and makes the marker authorize data deletion.
+- **Search unknown JSON for number-like field names** — heuristics cannot establish semantic identity and create false confidence.
+- **Dynamically ask mounted plugins** — makes migration availability depend on one deployment composition and fails before an absent producer can mount.
+- **Refuse only when the first structural edge ships** — would let v1 contain historical values whose safe interpretation was never established; the identity rehearsal is the point where the policy must become executable.
@@ -0,0 +1,37 @@
+# Agent Note: Alpha Session 迁移拒绝所有未知历史事件
+
+Status: implemented
+
+[English](2026-08-31-alpha-historical-unknown-event-refusal.md) | 中文
+
+## 问题
+
+同版本 Session 读取只有在 producer 把信封标记为 `ignorable: true` 时，才可以安全跳过未知事件。保持基数的迁移有更严格义务：它必须证明每个保留 payload 在目标代际中仍具备正确语义。未知 JSON payload 可能包含编译期品牌无法发现的 Session 序号、生命周期事实或模型可见状态。
+
+静默复制这类事件，会在后续迁移边改变事件位置时留下陈旧数字引用。静默省略它会丢失持久数据。保留精确且不可变的 v0 generation 不能让任何一种转换后的 v1 结果变得无损。
+
+## 决策
+
+Alpha v0-to-v1 迁移边拥有冻结且完整的已发布 v0 事件与 payload 清单。它在目标 staging 前拒绝每个未知历史事件类型，包括标记了 `ignorable: true` 的事件；除明确分类为 owner 不透明 JSON 的字段外，它也拒绝已知 payload 的意外成员。诊断会点名事件类型、序号和保持不变的源 generation。
+
+该规则只适用于跨越历史格式迁移边。普通当前格式读取保留既有信封行为：未知必需事件被拒绝，带 `ignorable: true` 的未知事件仍可读取。因此新的 v1 外部事件继续使用既有同版本扩展 seam，但不会自动获得未来格式迁移能力。
+
+每个第一方源事件类型都在迁移边包中拥有可执行 disposition 与目标 validator。catalog 在构建时静态确定且与 profile 无关，因此 producer 插件是否挂载不会改变旧产物能否迁移。
+
+## 后果
+
+某些由仓库外信息型插件产生的 v0 Session 可能拒绝 alpha 迁移，即使 v0 codec 能解码它们。拒绝不会发布后继，因此无后缀 v0 路径、字节与 inode 仍然权威且不变。操作者可以从诊断识别阻塞类型，并完整访问其原始文本。
+
+社区反馈将决定下一步策略。后续版本可以添加显式外部 owner 迁移接口、在保留精确源代际时允许省略明确 ignorable 的历史事件，或继续严格拒绝。Alpha 标记不预先承诺任何选项。
+
+`SessionSeq` 与 `SessionLogOffset` 让已知第一方数字字段可审计，但无法分类未知 runtime 对象中的数字。因此迁移规则不能根据没有识别到品牌字段来推断安全。
+
+本记录仅在历史格式迁移方面取代 [保留可忽略外部 Session 事件](2026-08-30-retain-ignorable-external-session-events.zh.md)。原决定对同版本 append 与 reload 仍然有效。
+
+## 考虑过的替代方案
+
+- **逐字复制未知 ignorable 事件**——保留字节，但不能证明不透明数字或生命周期事实在结构迁移后仍有效。
+- **丢弃未知 ignorable 事件**——让迁移保持可用，但不再无损，并让该标记授权删除数据。
+- **在未知 JSON 中搜索类似数字字段的名称**——启发式无法建立语义身份，还会制造虚假信心。
+- **动态询问已挂载插件**——让迁移可用性取决于某个部署组合，并在缺席 producer 能挂载前失败。
+- **等到第一条结构迁移边再拒绝**——会让 v1 包含从未建立安全解释的历史值；恒等演练正是把策略变成可执行规则的时点。
@@ -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/architecture/2026-08-31-released-session-format-migrations.md
+2026-08-31-released-session-format-migrations.md: 5fcc3d7d99abfb8e1c0b96e2056a1a13b95984c9
+2026-08-31-released-session-format-migrations.zh.md: fe5bb82bce5c838ef30675df1a35dec96ca73bb3
@@ -0,0 +1,55 @@
+# Agent Note: Released Session formats migrate on body read through adjacent pure edges
+
+Status: implemented
+
+English | [中文](2026-08-31-released-session-format-migrations.zh.md)
+
+## Problem
+
+Session format v0 shipped in an alpha release, so a structural writer change can no longer treat existing JSONL as disposable pre-release state. The runtime also has several ways to read event bodies besides explicit resume: inspect, query, export, fork, continuation, suffix reads, and raw-artifact export. Migrating only one entry path would let callers observe different logical generations or fail only when a later writer reaches the old file.
+
+Migration must retain the exact source path, bytes, and inode, including a torn physical tail, while giving every published format one unambiguous canonical filename. Plain JSONL and Zstandard are encoding choices for the same logical format and must not create parallel migration implementations.
+
+## Decision
+
+`SESSION_FORMAT_VERSION` is a monotonic current-writer integer. One profile-independent pure package owns each adjacent `vN -> vN+1` conversion. `@deepseek-ai/dsh-session-format` supplies only lossless snapshots, unique gap-free planning, header-only conversion, and whole-artifact composition; `@deepseek-ai/dsh-session-format-catalog` statically imports the complete chain independently of mounted Cordis plugins. Historical codecs and normalizers live in the named edge package, while current Session and persistence code accept only the latest logical types.
+
+Each edge freezes strict source and target semantics, while its target physical codec remains vocabulary-neutral so ordinary event growth can stay within one format version. The catalog restores the final generation through the installed peer `@deepseek-ai/dsh-session` and its current `KNOWN_SESSION_EVENT_TYPES`, preventing a frozen historical edge from becoming the current vocabulary owner.
+
+Every event-body operation crosses the persistence coordinator's per-Session serialization chain and completes provider-owned ensure-current work before current values escape. JSONL fuses highest-generation resolution, classification or migration, and current decoding over one physical snapshot; fallback backends retain separate `ensureCurrent` and current-read hooks. The six public reads are prepare, load, inspect, borrowSession, readFrom, and readRaw; cold append adoption uses the same body path. Header-only list and listSnapshots never migrate: they rescan each Session directory and return one descriptor for its numerically highest canonical generation, so a future, unsupported, or malformed highest file remains visible instead of silently falling back.
+
+For `prepare`, `inspect`, and `borrowSession`, cancellation belongs to the observing call rather than shared preparation or migration. A cancelled observer stops waiting, while already-started work may finish for another inspector or later resume; durable publication is never rolled back to satisfy observer cancellation. Detached `readFrom` and `readRaw` operations instead pass cancellation into their serialized backend read.
+
+The configured JSONL encoding owns one full suffix, `.jsonl` or `.jsonl.zstd`. Migration reads a stable exact source, decodes the recoverable logical prefix, composes every required edge in memory, applies current interrupted-turn repair, validates and syncs a same-directory temporary stage for only the final target, rechecks the source fingerprint, publishes that previously absent target without overwrite, syncs the namespace, and reopens it through the ordinary current reader before a Session is constructed. The source never moves or changes; only disposable temporary stages may be moved, linked, or removed.
+
+Canonical filenames encode the physical format generation: v0 is `session.jsonl` or `session.jsonl.zstd`; every positive generation is lowercase `session.vN.jsonl` or `session.vN.jsonl.zstd`. Publication never renames, replaces, or deletes a committed generation path. If the target already exists, it is accepted only as a regular current-format file with exactly the expected bytes; any other target refuses. Lower generations remain for operator inspection or explicit copying, but normal runtime operations select the numerically highest canonical name and never use retained predecessors as automatic fallback, restore, or downgrade support.
+
+The current-format fast path classifies the header from one stable source snapshot, invokes no historical converter or generation write, and passes that snapshot to current decoding without another file read. A validated current selection is cached for later opens in the same backend instance under the one-writer assumption, while listing deliberately rescans. Multiple edges leave the original generation unchanged and publish only the final target; intermediate versions exist only in memory. Same-process operations are serialized, and a source fingerprint recheck restarts the complete attempt when content changes. Cross-process writer fencing remains outside this guarantee.
+
+The first edge, `@deepseek-ai/dsh-session-format-v0-to-v1`, is intentionally identity-shaped: aside from the version and bounded historical normalizations already accepted by v0, it preserves logical headers, events, sequence numbers, references, timestamps, payloads, and the configured compression choice. The exact `session.jsonl[.zstd]` source remains byte- and inode-identical, while the current writer encodes the new `session.v1.jsonl[.zstd]` successor. This exercises the complete publication lifecycle before a cardinality-changing format needs it.
+
+## Consequences
+
+Reading event bodies with a newer build may durably add a higher generation. The exact old generation remains available, but the runtime thereafter selects the highest canonical filename; retention does not promise that an older build can safely downgrade or that the newer build will fall back when the successor is corrupt. A read-only filesystem reports an actionable migration failure instead of returning an in-memory current view that differs from disk.
+
+JSONL publication uses POSIX hard-link creation plus directory sync, and Windows uses no-overwrite `MoveFileExW` with write-through. A competing writer that wins target creation is accepted only when the committed bytes exactly match. One process-local writer per Session is the supported concurrency model. A future per-Session cross-process lock can close the remaining source-check-to-publication race without changing the format edge interface.
+
+Retained generations are not a live-stream write-ahead log. A future optional WAL sidecar may preserve unfinished assistant streams across a hard crash. Explicit generation inspection or copying, retention tooling, compression conversion, and streamed whole-artifact transformation are separate features; automatic fallback and downgrade compatibility are not implied future work.
+
+This note supersedes the continue-only persistence rule and the deferred-chain status in [Session log versioning](2026-08-10-session-log-version-mechanism.md). That note remains the authority for when to bump the version and for ordinary equal-version `ignorable` event behavior.
+
+## Verification
+
+Release verification ran the committed Session-format corpus gate over 152 versioned persisted-or-projected `session*.jsonl` fixtures under `snapshots/`, `packages/`, and `scripts/snapshots/python-sdk-single-exe/`. Fixture-only omitted envelopes and request-header tokens are materialized before the real static catalog; 150 fixtures reached the current v1 view through current restoration or historical migration. Released-v0 replay inputs remain suffixless, while fresh v1 writer outputs use `session.v1.jsonl` for a parent and `session.<ordinal>.v1.jsonl` for children; older role generations remain beside the selected highest file. The two exact alpha refusals were `snapshots/session/agent-instructions/session.jsonl`, whose projected compaction checkpoint has no matching start, and `snapshots/web/schedule-catalog/session.jsonl`, whose title source contradicts its citations. The continuing gate discovers the corpus dynamically and fails any refusal outside that closed manifest; separate assembled JSONL tests own exact physical-byte migration.
+
+Current-head performance used three independent runs, each with 100 warmups and 600 alternating samples per case; a pooled 1,800-sample marginal estimator compared the immutable resolver with the same-commit dispatch-disabled baseline. Hot median/p95 deltas were raw small `-1.864%/-1.109%`, raw 100-turn `-0.711%/-0.445%`, Zstandard small `-0.880%/-5.025%`, and Zstandard 100-turn `-0.301%/-2.090%`, all within the five-percent regression ceiling. Cold enabled-path median/p95 costs were raw small `220.125/294.708 µs`, raw 100-turn `580.625/730.834 µs`, Zstandard small `248.042/960.083 µs`, and Zstandard 100-turn `636.291/1421.208 µs`. Repeated hot body reads performed zero directory scans; two listing calls performed two scans.
+
+The assembled headless profile test stages `session.jsonl`, resumes it through the shipped composition, observes v1 before Session construction, verifies that the exact v0 bytes and inode remain while `session.v1.jsonl` appears, and proves the next append targets v1. JSONL contract tests exercise raw and Zstandard exclusive publication, torn-tail preservation, source changes, target collisions, future-highest refusal, current-selection caching, listing rescans, temporary cleanup, committed reopen, and current-format bypass.
+
+## Alternatives considered
+
+- **Migrate only on continuation** — leaves query, export, fork, and suffix consumers on old generations and duplicates restoration policy.
+- **Return a migrated in-memory view without persisting** — lets one process observe state that does not match the highest committed generation and postpones failure until a later writer.
+- **Persist every intermediate version** — consumes space and creates recovery states with no runtime consumer; only the source and final generation are durable.
+- **Let mounted event-owner plugins register migrations** — makes historical readability deployment-dependent; the static catalog must work before feature plugins mount.
+- **Reuse one filename for every current format and relocate its predecessor** — rejected because migration would move or overwrite committed evidence, require collision and retention rules, and make the filename disagree with the stored format. Canonical immutable generation names let discovery select the highest version directly.
@@ -0,0 +1,55 @@
+# Agent Note: 已发布 Session 格式在读取正文时通过相邻纯迁移边升级
+
+Status: implemented
+
+[English](2026-08-31-released-session-format-migrations.md) | 中文
+
+## 问题
+
+Session 格式 v0 已随 alpha 版本发布，因此结构化 writer 变更不能再把已有 JSONL 当作可丢弃的预发布状态。除显式恢复外，runtime 还有多个读取事件正文的入口：检查、查询、导出、分叉、继续、后缀读取和原始产物导出。只迁移一个入口会让调用方看到不同的逻辑 generation，或只在后续 writer 到达旧文件时失败。
+
+迁移必须保留精确源路径、字节与 inode，包括撕裂的物理尾部，同时为每个已发布格式提供一个无歧义的规范文件名。普通 JSONL 与 Zstandard 是同一逻辑格式的编码选择，不能产生两套并行迁移实现。
+
+## 决策
+
+`SESSION_FORMAT_VERSION` 是单调递增的当前 writer 整数。每个相邻 `vN -> vN+1` 转换由一个与 profile 无关的纯包负责。`@deepseek-ai/dsh-session-format` 只提供无损快照、唯一且无缺口的规划、仅 header 转换与整产物组合；`@deepseek-ai/dsh-session-format-catalog` 静态导入完整链，不依赖已挂载的 Cordis 插件。历史 codec 和归一化器位于具名迁移边包中，而当前 Session 与持久化代码只接纳最新逻辑类型。
+
+每条迁移边都会冻结严格的源与目标语义，其目标物理 codec 则保持词汇中立，使普通事件增长可以留在同一格式版本内。目录通过已安装的 peer `@deepseek-ai/dsh-session` 及其当前 `KNOWN_SESSION_EVENT_TYPES` 还原最终代，避免冻结的历史迁移边反过来成为当前词汇 owner。
+
+每个事件正文操作都经过持久化协调器的逐 Session 串行链，并在当前值离开前完成 provider 拥有的 ensure-current 工作。JSONL 会基于同一个物理快照融合最高 generation 解析、分类或迁移与当前格式解码；fallback 后端保留分离的 `ensureCurrent` 与当前读取钩子。六个公开读取是 prepare、load、inspect、borrowSession、readFrom 与 readRaw；冷 append 接管使用同一正文路径。仅 header 的 list 与 listSnapshots 从不迁移：它们重新扫描每个 Session 目录，并为数值最高的规范 generation 返回一个 descriptor，因此未来、不支持或 malformed 的最高文件会保持可见，而不会静默 fallback。
+
+对于 `prepare`、`inspect` 与 `borrowSession`，取消属于观察调用，而不属于共享准备或迁移。被取消的观察者会停止等待，而已经开始的工作可以为另一检查者或后续恢复继续完成；持久发布绝不会为了满足观察者取消而回滚。分离的 `readFrom` 与 `readRaw` 操作则会把取消传入其串行化后端读取。
+
+配置的 JSONL 编码拥有一个完整后缀：`.jsonl` 或 `.jsonl.zstd`。迁移读取稳定的精确源，解码可恢复逻辑前缀，在内存中组合全部必需迁移边，应用当前的中断轮次修复，只为最终目标校验并同步同目录临时 stage，重新检查源 fingerprint，以不覆盖方式发布此前不存在的目标，同步 namespace，并在构造 Session 前通过普通当前 reader 重新打开。源永不移动或改变；只有可丢弃临时 stage 可以被移动、链接或移除。
+
+规范文件名编码物理格式 generation：v0 是 `session.jsonl` 或 `session.jsonl.zstd`；每个正 generation 都是小写 `session.vN.jsonl` 或 `session.vN.jsonl.zstd`。发布绝不重命名、替换或删除已提交 generation 路径。目标已经存在时，只有它是普通当前格式文件且字节与预期完全相同时才接受；其他目标都会拒绝。低 generation 为 operator 检查或显式复制而保留，但普通 runtime 操作选择数值最高的规范名称，绝不把保留的前任当作自动 fallback、restore 或 downgrade 支持。
+
+当前格式快速路径从一个稳定源快照分类 header，不调用历史 converter，不写 generation，并把该快照交给当前格式解码，而不再次读取文件。后端会在单 writer 假设下缓存已校验的当前选择，供同一实例后续打开使用，而列表会有意重新扫描。多条迁移边保持原 generation 不变，并只发布最终目标；中间版本只存在于内存。同一进程内的操作会串行化，源 fingerprint 重新检查会在内容变化时重启完整尝试。跨进程 writer 隔离不在此保证内。
+
+第一条迁移边 `@deepseek-ai/dsh-session-format-v0-to-v1` 有意保持恒等形态：除版本和 v0 已接纳的有限历史归一化外，它保留逻辑 header、事件、序号、引用、时间戳、payload 与已配置的压缩选择。精确的 `session.jsonl[.zstd]` 源保持字节与 inode 相同，当前 writer 则编码新的 `session.v1.jsonl[.zstd]` 后继。这样可在出现改变基数的格式前先验证完整发布生命周期。
+
+## 后果
+
+较新 build 读取事件正文时可能持久增加一个更高 generation。精确旧 generation 仍然可用，但 runtime 此后选择最高规范文件名；保留不承诺旧 build 能安全 downgrade，也不保证新 build 在后继损坏时 fallback。只读文件系统会报告可操作的迁移失败，而不会返回与磁盘不一致的内存当前视图。
+
+JSONL 发布在 POSIX 上使用硬链接创建与目录同步，在 Windows 上使用 write-through 且不覆盖的 `MoveFileExW`。竞争 writer 已先创建目标时，只有已提交字节完全匹配才接受。每个 Session 只支持一个进程内 writer。未来逐 Session 跨进程锁可以关闭剩余的源检查到发布竞态，而无需改变格式迁移边接口。
+
+保留的 generation 不是实时流 WAL。未来可选 WAL sidecar 可以在硬崩溃间保留未完成 assistant 流。显式 generation 检查或复制、保留策略工具、压缩转换与流式整产物转换都是独立功能；自动 fallback 与 downgrade compatibility 并非隐含 future work。
+
+本记录取代 [Session 日志版本机制](2026-08-10-session-log-version-mechanism.zh.md) 中仅在继续时持久化和迁移链仍推迟的规则。原记录继续负责何时递增版本，以及普通同版本 `ignorable` 事件行为。
+
+## 验证
+
+发布验证针对 `snapshots/`、`packages/` 与 `scripts/snapshots/python-sdk-single-exe/` 下 152 个带版本、来自持久化或投影的 `session*.jsonl` fixture 运行了已提交 Session 格式语料门禁。fixture 专用的缺失信封与 request-header token 会先被实体化，再进入真实静态 catalog；其中 150 个通过当前格式 restore 或历史迁移得到当前 v1 视图。Released-v0 replay 输入保持无后缀，而新鲜 v1 writer 输出对 parent 使用 `session.v1.jsonl`、对 child 使用 `session.<ordinal>.v1.jsonl`；较旧角色 generation 保留在选定最高文件旁边。两个精确 alpha 拒绝分别是 `snapshots/session/agent-instructions/session.jsonl`（投影出的 compaction checkpoint 没有匹配 start）与 `snapshots/web/schedule-catalog/session.jsonl`（title 来源与其 citation 矛盾）。持续运行的门禁会动态发现语料，并拒绝封闭 manifest 之外的任何失败；独立组装式 JSONL 测试负责精确物理字节迁移。
+
+当前 head 性能证据来自 3 次独立运行，每个 case 含 100 次 warmup 与 600 个 alternating sample；pooled 1,800-sample marginal estimator 把不可变 resolver 与同一 commit 下禁用 dispatch 的 baseline 比较。Hot median/p95 delta 分别为 raw small `-1.864%/-1.109%`、raw 100-turn `-0.711%/-0.445%`、Zstandard small `-0.880%/-5.025%`、Zstandard 100-turn `-0.301%/-2.090%`，全部满足 5% regression ceiling。Cold enabled-path median/p95 cost 分别为 raw small `220.125/294.708 µs`、raw 100-turn `580.625/730.834 µs`、Zstandard small `248.042/960.083 µs`、Zstandard 100-turn `636.291/1421.208 µs`。重复 hot body read 执行 0 次目录扫描；两次 listing 调用执行 2 次扫描。
+
+组装后的 headless profile 测试会暂存 `session.jsonl`，通过随附组合恢复它，在构造 Session 前观察到 v1，验证精确 v0 字节与 inode 保持不变而 `session.v1.jsonl` 出现，并证明下一次 append 以 v1 为目标。JSONL 约定测试覆盖 raw 与 Zstandard 排他发布、撕裂尾部保留、源变化、目标冲突、最高未来版本拒绝、当前选择 cache、列表重新扫描、临时文件清理、已提交重开与当前格式直通。
+
+## 考虑过的替代方案
+
+- **只在继续时迁移**——让查询、导出、分叉与后缀消费者停留在旧代际，并重复恢复策略。
+- **返回迁移后的内存视图但不持久化**——让进程观察到与最高已提交 generation 不一致的状态，并把失败推迟到后续 writer。
+- **持久化每个中间版本**——消耗空间并产生没有 runtime 消费者的恢复状态；只有源与最终代际应持久。
+- **让已挂载事件 owner 插件注册迁移**——使历史可读性依赖部署；静态 catalog 必须在功能插件挂载前工作。
+- **让每个当前格式复用同一个文件名并迁走前任**——不予采用，因为迁移会移动或覆盖已提交证据，需要冲突与保留规则，并让文件名与存储格式不一致。规范不可变 generation 名让发现流程直接选择最高版本。
@@ -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/bug-fix/2026-07-20-jsonl-storage-identity.md
-2026-07-20-jsonl-storage-identity.md: e249640b1cd8900fdb7a136e9ab56abbf474ac86
-2026-07-20-jsonl-storage-identity.zh.md: 4775d6b7aa02abbd58ef89cdfa9377dc4f94b8de
+2026-07-20-jsonl-storage-identity.md: 5224ebf6bebc42b4b72e14243c1af6c02f366372
+2026-07-20-jsonl-storage-identity.zh.md: 05b7150edb99cdf336b9df90bc8e3cc1df9848a3
@@ -10,7 +10,7 @@ JSONL lookup selects a physical log from the requested session id across project

 ## Decision

-`loadStored(id)` is the coordinator's single stored-prefix lookup. The JSONL backend scans every project directory, requires at most one matching encoded session directory with a transcript, parses that file, then validates `header.id === id` and that the selected path either equals `logPath(root, header.cwd, header.id)` or filesystem canonicalization resolves both spellings to the same transcript. `list()` applies the same path validation and rejects duplicate ids across project directories.
+`findLog(id)` is the JSONL provider's single physical resolver. It scans every project directory and requires at most one matching encoded session directory with a transcript. For a supported historical snapshot, the generation operation translates its header in memory, then validates `header.id === id` and that the selected path either equals `logPath(root, header.cwd, header.id)` or filesystem canonicalization resolves both spellings to the same transcript before any write. The fused `loadCurrentStored(id)` decodes the resulting current prefix without another file read; an already-current snapshot takes the no-write fast path and applies the same identity check during that decode. The ordinary current `loadStored(id)` hook retains the identity validation for coordinator fallbacks. `list()` applies the same path validation and rejects duplicate ids across project directories.

 The coordinator independently asserts the returned id and compares the stored cwd with a live session's cwd before repair, state publication, or suffix persistence. It keeps a detached copy of validated metadata; JSONL append and repair derive their path from that copy. The `PersistenceBackend<TornMarker>` interface therefore needs neither a scope-specific live lookup nor a storage-locator type.

@@ -10,7 +10,7 @@ JSONL 查找会根据请求的会话 id 在各个项目目录中选出物理日

 ## 决策

-`loadStored(id)` 是协调器唯一的已存前缀查找操作。JSONL 后端扫描所有项目目录，要求名称与该 id 的编码值匹配且其中包含 transcript（文本记录）的会话目录至多有一个，解析其中的 transcript，然后验证 `header.id === id`，并验证选定路径要么等于 `logPath(root, header.cwd, header.id)`，要么经文件系统路径规范化后，两种写法解析为同一份 transcript。`list()` 执行相同的路径验证，并拒绝跨项目目录重复的 id。
+`findLog(id)` 是 JSONL provider 唯一的物理解析器。它扫描所有项目目录，并要求名称与该 id 的编码值匹配且其中包含 transcript（文本记录）的会话目录至多有一个。对于受支持的历史快照，generation 操作会在内存中转换其 header，然后验证 `header.id === id`，并验证选定路径要么等于 `logPath(root, header.cwd, header.id)`，要么经文件系统路径规范化后，两种写法解析为同一份 transcript；任何写入都必须在该检查之后。融合的 `loadCurrentStored(id)` 会在不再次读取文件的情况下解码所得当前前缀；已经是当前格式的快照采用无写入快速路径，并在该次解码中执行相同的身份检查。普通当前格式 `loadStored(id)` 钩子为协调器 fallback 保留身份校验。`list()` 执行相同的路径校验，并拒绝跨项目目录重复的 id。

 协调器会独立断言返回的 id，并在修复、发布状态或持久化后缀之前比较已存 cwd 和活动会话的 cwd。协调器保留一份已验证元数据的独立副本；JSONL 的追加和修复操作根据该副本派生路径。因此，`PersistenceBackend<TornMarker>` 接口既不需要限定范围的活动会话查找，也不需要存储定位器类型。

@@ -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/bug-fix/2026-07-28-load-pre-identity-session-messages.md
-2026-07-28-load-pre-identity-session-messages.md: 6d022cb4b37345cd61cc9a89c6fc55c19ad402a5
-2026-07-28-load-pre-identity-session-messages.zh.md: 86439337b3c646a72b7584fbf4640799226fc9ca
+2026-07-28-load-pre-identity-session-messages.md: 003331cd66ce0f299f1ef7c03684dbd0bee148b8
+2026-07-28-load-pre-identity-session-messages.zh.md: cf15b5434b66708ae70620326fe3e975738e68d1
@@ -12,17 +12,17 @@ Changing the message representation without a version bump made those logs indis

 ## Decision

-`PersistenceCoordinator` normalizes the four exact pre-identity message payloads after backend decoding and before current message validation. It wraps their existing semantic fields in the current role-specific message shape and assigns `legacy-message:<session-id>:<event-seq>` as the deterministic imported `MessageId`. A legacy `tool/result` content replacement inherits the imported id of its replacement target, preserving the current content-only rewrite invariant.
+The frozen `@deepseek-ai/dsh-session-format-v0-to-v1` edge normalizes the four exact pre-identity message payloads after v0 decoding and before v1 validation. It wraps their existing semantic fields in the current role-specific message shape and assigns `legacy-message:<session-id>:<event-seq>` as the deterministic imported `MessageId`. A legacy `tool/result` content replacement inherits the imported id of its replacement target, preserving the current content-only rewrite invariant.

-The same normalization runs for `load`, `inspect`, an ownerless loaded state claiming its live session, and HMR prefix adoption. Prefix comparisons therefore compare the live current-shape seed with the same normalized stored view. Current-looking wrappers with missing or invalid fields are not repaired, and unsupported event vocabulary, request headers, versions, and surface relations retain their existing rejection paths.
+Every event-body operation runs the same edge through the build-static catalog before current Session construction. `load`, `inspect`, ownerless-state adoption, HMR prefix adoption, query, export, fork, and suffix reads therefore see one normalized current generation. Current-looking wrappers with missing or invalid fields are not repaired, and unsupported event vocabulary, request headers, versions, and surface relations retain their refusal paths.

-The upgrade is read-only. Stored legacy records remain unchanged; a resumed session appends only current-shape events after them. Deterministic identities make repeated loads and a mixed legacy/current log reproduce the same message ids without a backend-specific rewrite transaction.
+JSONL migration leaves the exact suffixless v0 artifact path, bytes, and inode unchanged and exclusively publishes `session.v1.jsonl[.zstd]` beside it. Deterministic identities make repeated restoration reproduce the same message ids, and subsequent appends target only v1.

 ## Alternatives considered

-**Reject the logs under the pre-release compatibility stance.** This is the default for unrelated v0 churn, but it strands real first-party sessions even though every old field maps unambiguously to the current message representation.
+**Reject the released logs.** This strands real first-party sessions even though every old field maps unambiguously to the current message representation.

-**Rewrite the complete stored log in place.** This would canonicalize the artifact but violate the append-only storage contract, require an atomic replacement mechanism, and expand a read compatibility fix into a migration system.
+**Keep a same-version importer inside the coordinator.** This avoids a format edge but leaves historical payloads in current Session code and provides neither immutable source/successor naming nor independently testable publication. The released adjacent migration system owns canonical publication instead.

 **Mint random ids on each load.** The messages would satisfy the type shape but lose stable identity across inspect, resume, restart, and mixed legacy/current appends.

@@ -30,7 +30,7 @@ The upgrade is read-only. Stored legacy records remain unchanged; a resumed sess

 Pre-identity JSONL Sessions resume with their original message content, sources, assistant provider/model fields, tool correlation, errors, metadata, and surface replacements. The returned events are otherwise indistinguishable from current imported message snapshots and remain deeply frozen.

-This is one explicit same-version import exception, not a general v0 compatibility layer. Adding another exception requires another complete, unambiguous mapping at the persistence boundary; malformed current data continues to fail rather than being guessed into validity. The shared coordinator contract exercises the upgrade against the in-memory reference and JSONL provider, including deterministic reload and tool-result replacement identity.
+This is one explicit released-v0 normalization, not a permissive compatibility layer. Adding another normalization requires another complete, unambiguous mapping in the frozen edge; malformed current data continues to fail rather than being guessed into validity. Edge and JSONL generation tests exercise deterministic restoration and tool-result replacement identity.

 ## Related

@@ -12,17 +12,17 @@ Status: implemented

 ## 决策

-`PersistenceCoordinator` 会在后端解码之后、当前消息验证之前，规范化消息标识机制引入前的四种特定消息载荷。它将载荷现有的语义字段包装进当前按角色区分的消息形状，并为其分配确定性的导入用 `MessageId`：`legacy-message:<session-id>:<event-seq>`。旧版 `tool/result` 的内容替换会继承替换目标导入后的 id，从而保持当前仅改写内容的不变量。
+冻结的 `@deepseek-ai/dsh-session-format-v0-to-v1` 迁移边会在 v0 解码之后、v1 验证之前，规范化消息标识机制引入前的四种特定消息载荷。它将载荷现有的语义字段包装进当前按角色区分的消息结构，并为其分配确定性的导入用 `MessageId`：`legacy-message:<session-id>:<event-seq>`。旧版 `tool/result` 的内容替换会继承替换目标导入后的 id，从而保持当前仅改写内容的不变量。

-同一项规范化也用于 `load`、`inspect`、无 owner 的已加载状态认领其活跃会话，以及 HMR（热模块替换）前缀接管。因此，前缀比较会将活跃会话的当前形状 seed 与同一份规范化存储视图进行比较。看似当前形状、但字段缺失或无效的包装层不会被修复；不受支持的事件词汇、请求 header、版本和 surface 关系仍沿用现有拒绝路径。
+每项事件正文操作都会在构造当前 Session 前，通过构建期静态目录运行同一条迁移边。因此，`load`、`inspect`、无 owner 状态接管、HMR（热模块替换）前缀接管、查询、导出、fork 与后缀读取都会看到同一份规范化当前代际。看似当前结构、但字段缺失或无效的包装层不会被修复；不受支持的事件词汇、请求 header、版本和 surface 关系仍沿用现有拒绝路径。

-这项升级只发生在读取时。存储中的旧版记录保持不变；会话恢复后，只会在其后追加当前形状的事件。确定性标识使重复加载以及新旧形状混合的日志无需执行后端专用的重写事务，也能复现相同的消息 id。
+JSONL 迁移会保持精确的无后缀 v0 产物路径、字节与 inode 不变，并在其旁边排他发布 `session.v1.jsonl[.zstd]`。确定性标识使重复恢复能够复现相同的消息 id，后续 append 只以 v1 为目标。

 ## 考虑过的替代方案

-**按照预发布兼容性立场拒绝这些日志。** 这是处理其他 v0 形状变动的默认方式，但即使每个旧字段都能明确映射到当前消息表示，它仍会导致真实的第一方会话无法恢复。
+**拒绝这些已发布日志。** 即使每个旧字段都能明确映射到当前消息表示，这也会导致真实的第一方会话无法恢复。

-**就地重写完整的存储日志。** 这会使产物规范化，但违反仅追加存储约定，还需要原子替换机制，并将一次读取兼容性修复扩大为迁移系统。
+**在协调器中保留同版本导入器。** 这可以避免迁移边，但会把历史 payload 留在当前 Session 代码中，而且既没有不可变源／后继命名，也没有可独立测试的发布。已发布相邻迁移系统负责规范发布。

 **每次加载时随机生成 id。** 这些消息会满足类型形状，却无法在检查、恢复、重启以及新旧形状混合追加之间保持稳定标识。

@@ -30,7 +30,7 @@ Status: implemented

 消息标识机制引入前的 JSONL Session 可以恢复，并保留原始消息内容、来源、assistant 的 provider／model 字段、工具调用关联、错误、元数据和 surface 替换。除此之外，返回事件与当前导入的消息快照无法区分，并且仍然经过深度冻结。

-这是一个显式的同版本导入例外，而非通用的 v0 兼容层。若要增加另一个例外，必须在持久化边界提供另一套完整且无歧义的映射；当前数据若格式错误，系统仍会拒绝，而不会猜测如何将其变成有效数据。共享协调器约定会通过内存参考实现与 JSONL provider 验证这项升级，包括重新加载时的确定性，以及工具结果替换时的标识继承。
+这是一项显式的已发布 v0 规范化，而非宽松的兼容层。若要增加另一项规范化，必须在冻结迁移边中提供另一套完整且无歧义的映射；当前数据若格式错误，系统仍会拒绝，而不会猜测如何将其变成有效数据。迁移边与 JSONL 代际测试会验证恢复的确定性，以及工具结果替换时的标识继承。

 ## 相关

@@ -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/bug-fix/2026-08-04-load-pre-react-loop-sessions.md
-2026-08-04-load-pre-react-loop-sessions.md: e95817ee60647ca002060a4f90c2263d4fe7ce42
-2026-08-04-load-pre-react-loop-sessions.zh.md: 98fb1f530f5168fc02b312775d1bb8e6d305b8f8
+2026-08-04-load-pre-react-loop-sessions.md: beda9c9984f37a5ee6fa4e1a5bbff07d3b1e363c
+2026-08-04-load-pre-react-loop-sessions.zh.md: ace424476a96c4abc46fc8afeb3920d564bb65ae
@@ -12,29 +12,29 @@ The new durable inbox is not part of this compatibility problem. The base emitte

 ## Decision

-`PersistenceCoordinator` recognizes the exact pre-react-loop shapes after backend decoding and projects them into the current read view. It removes the obsolete `turn/start.trigger`, converts `steering/message` to the same identified `user/message`, maps old failure facts into the current structured error, folds `disposed` into an aborted turn with the `disposed` cause, and represents coarse aborted records with the persistence-only `{ kind: 'legacy' }` cause because their caller is unavailable.
+The frozen `@deepseek-ai/dsh-session-format-v0-to-v1` edge recognizes the exact pre-react-loop shapes after v0 decoding and projects them into v1. It removes the obsolete `turn/start.trigger`, converts `steering/message` to the same identified `user/message`, maps old failure facts into the current structured error, folds `disposed` into an aborted turn with the `disposed` cause, and represents coarse aborted records with the persistence-only `{ kind: 'legacy' }` cause because their caller is unavailable.

-The coordinator applies the projection to `load`, `inspect`, adoption, HMR prefix comparison, and `readFrom`. A seek-capable `readFrom` normally reads only its suffix; when that suffix contains a legacy event needing an earlier replacement identity, the coordinator loads and normalizes the complete prefix before returning the requested seq range.
+Every persistence event-body entry point first migrates the complete detached artifact through the build-static catalog. `load`, `inspect`, adoption, HMR prefix comparison, and `readFrom` therefore receive the same validated v1 view; suffix reading happens only after immutable successor publication and current restoration.

-The importer does not synthesize inbox splices. A resumed pre-react-loop agent begins with empty pending lists, matching the base runtime's inability to persist pending inbox work. The stored artifact remains append-only and later events use the current format.
+The edge does not synthesize inbox splices. A resumed pre-react-loop agent begins with empty pending lists, matching the base runtime's inability to persist pending inbox work. Migration leaves the exact suffixless v0 generation unchanged and publishes one `session.v1.jsonl[.zstd]` successor before later events append.

 ## Alternatives considered

-**Treat the same-version records as unsupported.** This follows the pre-release default but strands sessions produced by the PR base even though the removed steering content and terminal facts have complete mappings.
+**Treat the released records as unsupported.** This strands sessions produced by the supported first-party writer even though the removed steering content and terminal facts have complete mappings.

 **Replay old inbox notifications into durable splices.** Those notifications were not session events and do not provide a trustworthy pending-state snapshot. Inferring insertions without every claim and discard would re-run consumed work.

 **Assign coarse aborted records to an existing caller.** Mapping them to `user`, `parent`, or `hook` would invent a caller that the old record did not name. A dedicated `legacy` cause keeps the stop classification without making a false audit claim.

-**Rewrite stored JSONL records.** A rewrite would violate the append-only contract and require atomic migration machinery for a read compatibility boundary.
+**Keep a generic same-version importer in the coordinator.** This lets current Session code accumulate historical forms and gives no immutable physical generation naming or independently testable adjacent edge. The released migration lifecycle owns the conversion instead.

 ## Consequences

-Sessions written in the refactor's base format resume through the current AgentLoop with their steering content, turn boundaries, error facts, and stop classification intact. The shared coordinator contract covers in-memory and JSONL `load`/`inspect`/`readFrom`; an assembled JSONL Agent resume verifies that the historical transcript is visible while both new inbox lists start empty.
+Sessions written in the refactor's base format resume through the current AgentLoop with their steering content, turn boundaries, error facts, and stop classification intact. The frozen edge and JSONL generation contract cover `load`/`inspect`/`readFrom`; an assembled JSONL Agent resume verifies that the historical transcript is visible while both new inbox lists start empty.

 This exception supports the base format, not intermediate formats produced during development of the refactor. In particular, it defines no migration for earlier experimental `agent/inbox/spliced` payloads. Exact-shape recognition keeps malformed current-looking records on their rejection path instead of guessing them into validity.

 ## Related

- [Load sessions persisted before message identity](2026-07-28-load-pre-identity-session-messages.md) — owns deterministic identities and the general read-only import boundary for another same-version format change.
+- [Load sessions persisted before message identity](2026-07-28-load-pre-identity-session-messages.md) — owns deterministic identities for another released v0 normalization in the same edge.
 - [Session persistence as an abstract service](../architecture/2026-06-14-session-persistence.md) — owns append-only backend storage and resume.
@@ -12,29 +12,29 @@ react-loop 简化在保持 `SESSION_FORMAT_VERSION` 为 0 的同时更改了持

 ## 决策

-`PersistenceCoordinator` 会在后端解码后识别 react-loop 重构前的确切形状，并将其投影为当前读取视图。它移除已废弃的 `turn/start.trigger`，把 `steering/message` 转换为同一条带标识的 `user/message`，将旧版失败事实映射为当前结构化错误，把 `disposed` 折叠为带 `disposed` 原因的已中止轮次，并用仅供持久化导入使用的 `{ kind: 'legacy' }` 原因表示粗粒度中止记录，因为无法获得其调用方。
+冻结的 `@deepseek-ai/dsh-session-format-v0-to-v1` 迁移边会在 v0 解码后识别 react-loop 重构前的确切结构，并将其投影为 v1。它移除已废弃的 `turn/start.trigger`，把 `steering/message` 转换为同一条带标识的 `user/message`，将旧版失败事实映射为当前结构化错误，把 `disposed` 折叠为带 `disposed` 原因的已中止轮次，并用仅供持久化导入使用的 `{ kind: 'legacy' }` 原因表示粗粒度中止记录，因为无法获得其调用方。

-协调器会把该投影应用于 `load`、`inspect`、接管、HMR（热模块替换）前缀比较和 `readFrom`。可寻址的 `readFrom` 通常只读取后缀；如果后缀包含需要更早替换标识的旧版事件，协调器会先加载并规范化完整前缀，再返回所请求的 seq 范围。
+每个持久化事件正文入口都会先通过构建期静态目录迁移完整且分离的产物。因此，`load`、`inspect`、接管、HMR（热模块替换）前缀比较和 `readFrom` 会收到同一份经过校验的 v1 视图；系统只会在不可变后继发布和当前格式恢复后读取后缀。

-导入器不会合成 inbox splice。恢复后的 react-loop 重构前 agent（智能体）从空的待处理列表开始，这与基线运行时无法持久化待处理 inbox 工作的行为一致。已存储产物仍然仅追加，后续事件使用当前格式。
+该迁移边不会合成 inbox splice。恢复后的 react-loop 重构前 agent（智能体）从空的待处理列表开始，这与基线运行时无法持久化待处理 inbox 工作的行为一致。迁移会保持精确的无后缀 v0 generation 不变，并在后续事件 append 前发布一个 `session.v1.jsonl[.zstd]` 后继。

 ## 考虑过的替代方案

-**将同版本记录视为不受支持。** 这符合预发布阶段的默认立场，但会使 PR（Pull Request）基线产生的会话无法恢复，尽管已移除的 steering 内容和终止事实都有完整映射。
+**将已发布记录视为不受支持。** 这会使受支持的第一方 writer 所产生的 Session 无法恢复，尽管已移除的 steering 内容和终止事实都有完整映射。

 **将旧 inbox 通知回放为持久 splice。** 这些通知不是会话事件，也无法提供可信的待处理状态快照。如果无法获知每一次领取和丢弃，就推断插入操作，会让已消费的工作再次执行。

 **将粗粒度中止记录归因于现有调用方。** 将其映射到 `user`、`parent` 或 `hook` 会凭空指定旧记录未注明的调用方。专用的 `legacy` 原因既能保留停止分类，也不会产生虚假的审计事实。

-**重写已存储的 JSONL 记录。** 重写会违反仅追加约定，并要求为读取兼容边界建立原子迁移机制。
+**在协调器中保留通用同版本导入器。** 这会让当前 Session 代码不断积累历史结构，而且没有不可变物理 generation 命名或可独立测试的相邻迁移边。已发布迁移生命周期负责该转换。

 ## 后果

-以重构基线格式写入的会话可以通过当前 AgentLoop 恢复，并完整保留 steering 内容、轮次边界、错误事实和停止分类。共享协调器约定覆盖内存与 JSONL 的 `load`／`inspect`／`readFrom`；组装后的 JSONL agent 恢复用例会验证历史 transcript（文本记录）可见，同时两个新 inbox 列表都从空状态开始。
+以重构基线格式写入的会话可以通过当前 AgentLoop 恢复，并完整保留 steering 内容、轮次边界、错误事实和停止分类。冻结迁移边与 JSONL 代际约定覆盖 `load`／`inspect`／`readFrom`；组装后的 JSONL agent 恢复用例会验证历史 transcript（文本记录）可见，同时两个新 inbox 列表都从空状态开始。

 此例外支持基线格式，不支持重构开发期间产生的中间格式。具体而言，它没有为更早的实验性 `agent/inbox/spliced` 载荷定义迁移。通过确切形状识别，当前格式外观相似但结构错误的记录仍会走拒绝路径，不会被猜测性地转换为有效记录。

 ## 相关资料

- [加载消息标识机制引入前持久化的会话](2026-07-28-load-pre-identity-session-messages.zh.md)：负责另一项同版本格式变更的确定性标识和通用只读导入边界。
+- [加载消息标识机制引入前持久化的会话](2026-07-28-load-pre-identity-session-messages.zh.md)：负责同一迁移边中另一项已发布 v0 规范化的确定性标识。
 - [以抽象服务实现会话持久化](../architecture/2026-06-14-session-persistence.zh.md)：负责仅追加后端存储和恢复。
@@ -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/bug-fix/2026-08-20-turn-error-survives-same-turn-retry-history.md
-2026-08-20-turn-error-survives-same-turn-retry-history.md: 68b09fc32f2d409a9060bb8e53f11837dd365657
-2026-08-20-turn-error-survives-same-turn-retry-history.zh.md: 1aa78aa405113fecc890fb2213f41cf41afec6b4
+2026-08-20-turn-error-survives-same-turn-retry-history.md: 9280d59d020a88d0f0f703d2e2adc54656687b16
+2026-08-20-turn-error-survives-same-turn-retry-history.zh.md: 1856d72e05c6261535df5f94c41cb3ff86c69362
@@ -28,4 +28,4 @@ The Definition suite drives the real assembler through a same-turn retry chain e

 ## Consequences

-Exhausted recovery now leaves durable, replayable feedback: the red terminal row with the display-safe message and code, plus the collapsed retry chain as recovery context. Session logs recorded under the retired new-turn retry model would render one `turn-error` row per failed turn on replay; the pre-release format stance accepts that, and no shipped log producer has emitted that shape since same-turn retries landed.
+Exhausted recovery now leaves durable, replayable feedback: the red terminal row with the display-safe message and code, plus the collapsed retry chain as recovery context. Session logs recorded under the retired new-turn retry model render one `turn-error` row per failed turn on replay; the v0-to-v1 edge preserves those terminal facts, and no shipped log producer has emitted that shape since same-turn retries landed.
@@ -28,4 +28,4 @@ Definition 套件驱动真实 assembler 走完同轮次重试链并以 error 原

 ## 影响

-恢复耗尽后现在留下持久、可回放的反馈：红色终态行带展示安全的消息与错误码，加上折叠的重试链作为恢复上下文。按已退役的"新轮次重试"模型录制的会话日志在回放时会为每个失败轮次各渲染一条 `turn-error` 行；预发布格式立场接受这一点，且自同轮次重试落地以来，没有任何已交付的日志生产方再发出过那种形态。
+恢复耗尽后现在留下持久、可回放的反馈：红色终态行带展示安全的消息与错误码，加上折叠的重试链作为恢复上下文。按已退役的“新轮次重试”模型录制的会话日志在回放时会为每个失败轮次各渲染一条 `turn-error` 行；v0-to-v1 迁移边会保留这些终态事实，且自同轮次重试落地以来，没有任何已交付的日志生产方再发出过那种结构。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-10-sqlite-session-query-provider.md
-2026-07-10-sqlite-session-query-provider.md: 76ebbc24e16a9429be63d0e45ec84b14c29d43f6
-2026-07-10-sqlite-session-query-provider.zh.md: 6d8518252d0a79906fd9438876d4a92ba414363e
+2026-07-10-sqlite-session-query-provider.md: 46af02d39ed687a1f4b418109a1da4b071b9e409
+2026-07-10-sqlite-session-query-provider.zh.md: ccb833886a459c5a6888637c6cb8354e9e9f7977
@@ -34,13 +34,13 @@ Both persistent and live FTS5 tables use `unicode61`. The implementation experim

 The shared extractor includes message text, reasoning, nested tool-call/result content, tool names and arguments, blocked-prompt reasons, todo status/content, and error or terminal status detail. Structural boundaries, stream chunks, request headers, successful completion markers, and unknown declaration-merged event/content variants produce no document. Surface classification reuses `foldSurface()` so search agrees with model-history derivation.

-One serialized operation reads the provider-neutral `SessionPersistence` snapshot listing, compares each source-qualified opaque revision with the revision stored beside the indexed session, loads only new or changed logs, reconciles rows in one transaction, and executes the query. It passes the caller's exact abort signal into snapshot listing and non-mutating inspection, directly awaits every started backend operation, and checks cancellation after each await and before starting more work. Cancellation therefore rejects only after active backend work is quiescent, starts no subsequent observation or reconciliation step, and keeps a following search serialized behind cleanup even if a backend ignores the signal. The operation never calls the backend's mutating `load()` for an id currently owned by `ctx.sessions`; the TEMP overlay records persisted availability, and the durable base refreshes after the live owner detaches. A revision identifies its backing persistence store as well as the backend-local log revision, so reopening against the same store reuses indexed rows while switching to an independent store cannot collide on a session id and local counter. Observation repeats when listing changes during a load; this incorporates a mutating load repair's refreshed revision before commit. Repeated queries and unchanged reopen load no full persisted logs. New, changed, and deleted sessions update on the next stable search. A source or extraction failure cannot mark a row current, and a transaction failure rolls back so a later search retries.
+One serialized operation reads the provider-neutral `SessionPersistence` snapshot listing, compares each source-qualified opaque revision with the revision stored beside the indexed session, loads only new or changed logs, reconciles rows in one transaction, and executes the query. It passes the caller's exact abort signal into snapshot listing and inspection, awaits each observer operation, and checks cancellation after each await and before starting more work. Already-current inspection keeps recovery in memory; a supported historical body read may first publish migration and repair. Cancellation settles this query observer without starting another observation or reconciliation step; a shared persistence load or migration already admitted for another observer may continue behind its per-id chain. The operation never calls the backend's mutating `load()` for an id currently owned by `ctx.sessions`; the TEMP overlay records persisted availability, and the durable base refreshes after the live owner detaches. A revision identifies its backing persistence store as well as the backend-local log revision, so reopening against the same store reuses indexed rows while switching to an independent store cannot collide on a session id and local counter. Observation repeats when listing changes during a load; this incorporates migration or mutating load repair's refreshed revision before commit. Repeated queries and unchanged reopen load no full persisted logs. New, changed, and deleted sessions update on the next stable search. A source or extraction failure cannot mark a row current, and a transaction failure rolls back so a later search retries.

 Persisted documents survive restarts. Live sessions use connection-local TEMP tables, shadow the persisted base for the same id, and reveal that base on detach. Closing the database drops live rows. Unmounting persistence hides durable rows without treating absence as authoritative deletion; remounting observes and reconciles the backend again. Conflicting immutable live and durable headers fail rather than combining sources.

 The derived schema has its own application id and monotonic schema version. Persistent and TEMP session metadata store the integer `SessionHeader.createdAt` contract in strict `INTEGER` columns. A recognized incompatible version resets only this derived database. A database with a foreign application id or unrecognized user tables is refused before journal-mode mutation, which prevents an accidentally configured canonical session database from being changed. On POSIX filesystems, missing directories and database files are created owner-only so new SQLite sidecars inherit that mode; existing modes are preserved. One service in one process exclusively owns a derived-index path; cross-process writers are unsupported because generations and live TEMP shadow state are connection-owned.

-Cancellation rejects queued operations promptly. Once asynchronous source observation starts, the caller waits for that backend promise to settle before rejection, without committing an aborted observation or starting more source/index work. Node's synchronous `DatabaseSync` metadata and MATCH calls cannot be interrupted once executing on the JavaScript thread, so the service checks the signal around those calls but does not promise mid-statement preemption.
+Cancellation rejects queued operations promptly. Once source observation starts, cancellation rejects the query observer without committing its result or starting more source/index work; persistence may keep a shared cold load or migration alive for another observer. Node's synchronous `DatabaseSync` metadata and MATCH calls cannot be interrupted once executing on the JavaScript thread, so the service checks the signal around those calls but does not promise mid-statement preemption.

 ## Alternatives considered

@@ -54,6 +54,6 @@ Cancellation rejects queued operations promptly. Once asynchronous source observ

 Search has a small provider-neutral API while its only backend owns every derived-index state transition. The separate database adds configuration and a lightweight snapshot read before queries, but index corruption, reset, and tokenizer changes cannot endanger canonical logs. Durable revisions avoid full-log reads and rewrites for unchanged sessions; TEMP live overlays preserve current-session truth without making uncheckpointed events durable.

-The chosen tokenizer supports short tokens with a smaller index but does not promise substring recall. Literal phrases make query syntax safe and predictable at the cost of excluding boolean/full MATCH expressions. Cancellation is prompt while queued and quiescent while awaiting sources; synchronous SQLite execution remains a non-preemptible section bracketed by signal checks.
+The chosen tokenizer supports short tokens with a smaller index but does not promise substring recall. Literal phrases make query syntax safe and predictable at the cost of excluding boolean/full MATCH expressions. Cancellation is prompt while queued and observer-local during shared source work; synchronous SQLite execution remains a non-preemptible section bracketed by signal checks.

 Unit coverage pins extraction, filters, both search scopes, all default surfaces, metadata-before-ranking, snippets, literal escaping, deterministic ties, complete pagination, scoped cursor invalidation, dynamic persistence mount/unmount, restart reconciliation, live shadow/reveal/reopen, schema safety, rollback retry, and queued/in-flight source-wait cancellation. A keyless real-Loader-path test combines the derived SQLite index with the real JSONL persistence provider.
@@ -34,13 +34,13 @@ Service Definition 包还拥有共享的第一方语义提取与提供方无关

 共享提取器会提取消息文本、推理（reasoning）、嵌套的工具调用/结果内容、工具名称与参数、被阻止提示词的原因、待办事项状态与内容，以及错误或结束状态详情。结构性边界、流分片、请求头、成功完成标记，以及通过声明合并扩展的未知事件/内容变体都不会产生文档。surface 分类复用 `foldSurface()`，使搜索与模型历史派生保持一致。

-一个串行化操作会读取提供方无关的 `SessionPersistence` 快照清单，将每个包含源身份的不透明修订号与同已索引会话一并存储的修订号比较，只加载新增或变更的日志，在一个事务中对齐各行，然后执行查询。它将调用方传入的原始中止信号传给快照清单查询和不会修改状态的检查，直接等待每个已启动的后端操作，并在每次等待结束后、启动更多工作之前检查取消状态。因此，即使后端忽略该信号，取消也只会在活跃的后端工作完全停稳后才拒绝，不会启动后续观察或对齐步骤；后续搜索仍会串行等待清理完成。它绝不会调用后端会修改状态的 `load()` 来处理当前由 `ctx.sessions` 拥有的 id；TEMP 覆盖层会记录持久化可用性，实时所有者分离后，持久化基础层随之刷新。修订号同时标识其底层持久化存储与后端本地日志修订版本，因此针对同一存储重新打开服务可以复用已索引行，而切换到独立存储时不会因会话 id 与本地计数器相同而发生冲突。如果加载期间清单发生变化，系统会重复观察；因此，会修改状态的加载修复所产生的新修订号会在提交前纳入结果。重复查询与针对未变更存储的重新打开都不会加载完整的持久化日志。新增、变更与删除的会话会在下一次稳定搜索中更新。源读取或提取失败时，不能将相应行标记为最新状态，事务失败则会回滚，使后续搜索能够重试。
+一个串行化操作会读取提供方无关的 `SessionPersistence` 快照清单，将每个包含源身份的不透明修订号与同已索引会话一并存储的修订号比较，只加载新增或变更的日志，在一个事务中对齐各行，然后执行查询。它将调用方传入的原始中止信号传给快照清单查询与检查，等待每项观察操作，并在每次等待结束后、启动更多工作之前检查取消状态。已经是当前格式的检查只在内存中保留恢复；受支持的历史正文读取可能先发布迁移与修复。取消会结算本次查询观察方，且不启动后续观察或对齐步骤；已经为其他观察方接纳的共享持久化加载或迁移仍可能在其逐 id 链后继续。它绝不会调用后端会修改状态的 `load()` 来处理当前由 `ctx.sessions` 拥有的 id；TEMP 覆盖层会记录持久化可用性，实时所有者分离后，持久化基础层随之刷新。修订号同时标识其底层持久化存储与后端本地日志修订版本，因此针对同一存储重新打开服务可以复用已索引行，而切换到独立存储时不会因会话 id 与本地计数器相同而发生冲突。如果加载期间清单发生变化，系统会重复观察；因此，迁移或会修改状态的加载修复所产生的新修订号会在提交前纳入结果。重复查询与针对未变更存储的重新打开都不会加载完整的持久化日志。新增、变更与删除的会话会在下一次稳定搜索中更新。源读取或提取失败时，不能将相应行标记为最新状态，事务失败则会回滚，使后续搜索能够重试。

 持久化文档在重启后仍然存在。实时会话使用连接本地的 TEMP 表，遮蔽相同 id 的持久化基础行，并在实时所有者分离时重新显露该基础行。关闭数据库会删除实时行。卸载持久化服务会隐藏持久化行，但不会把缺失视为权威删除；重新挂载后，系统会再次观察并对齐后端。实时会话头与持久化会话头的不可变字段发生冲突时，系统会失败，而不会合并两个来源。

 派生 schema 拥有独立的 application id 与单调递增的 schema 版本。持久化与 TEMP 会话元数据均遵循 `SessionHeader.createdAt` 的整数约定，将其存入严格的 `INTEGER` 列。系统识别到不兼容版本时，只会重置该派生数据库。如果数据库具有不属于本应用的 application id 或无法识别的用户表，系统会在修改日志模式前拒绝该数据库，防止意外配置的规范会话数据库遭到修改。在 POSIX 文件系统上，缺失的目录与数据库文件会以仅所有者可访问的权限创建，使新的 SQLite 伴随文件沿用该模式；现有权限模式保持不变。一个进程中的一个服务独占一条派生索引路径；代际与实时 TEMP 遮蔽状态都归连接所有，因此不支持跨进程写入方。

-取消会使排队中的操作及时被拒绝。异步源观察一旦开始，调用方必须等待该后端 Promise 结算后才会收到拒绝；系统不会提交已中止的观察结果，也不会启动更多源观察或索引工作。Node 的同步 `DatabaseSync` 元数据与 MATCH 调用一旦开始在 JavaScript 线程上执行就无法中断，因此服务会在这些调用前后检查信号，但不承诺在语句执行期间抢占。
+取消会使排队中的操作及时被拒绝。源观察开始后，取消会拒绝查询观察方，不提交其结果，也不启动更多源观察或索引工作；持久化层仍可能为其他观察方保留共享 cold load 或迁移。Node 的同步 `DatabaseSync` 元数据与 MATCH 调用一旦开始在 JavaScript 线程上执行就无法中断，因此服务会在这些调用前后检查信号，但不承诺在语句执行期间抢占。

 ## 曾考虑的替代方案

@@ -54,6 +54,6 @@ Service Definition 包还拥有共享的第一方语义提取与提供方无关

 搜索只公开精简的提供方无关 API，而唯一后端负责派生索引的全部状态转换。独立数据库增加了配置与查询前的轻量快照读取，但索引损坏、重置与分词器变更都不会危及规范日志。持久化修订号使未变更会话无需读取或重写完整日志；TEMP 实时覆盖层保留当前会话事实，同时不会让尚未经过检查点的事件具有持久性。

-选定的分词器以较小的索引体积支持短 token，但不承诺子串召回。字面短语使查询语法安全且可预测，代价是不支持布尔表达式或完整 MATCH 表达式。取消在操作排队期间会及时生效，在等待数据源期间则会等待其完全停稳；同步 SQLite 执行仍是不可抢占区段。
+选定的分词器以较小的索引体积支持短 token，但不承诺子串召回。字面短语使查询语法安全且可预测，代价是不支持布尔表达式或完整 MATCH 表达式。取消在排队期间及时生效，在共享源工作期间只影响当前观察方；同步 SQLite 执行仍是不可抢占区段。

 单元测试将以下行为固化为约定：提取、过滤器、两种搜索范围、所有默认 surface、先过滤元数据再排序、摘要片段、字面量转义、确定性平局处理、完整分页、按范围的游标失效、动态挂载/卸载持久化服务、重启对齐、实时遮蔽、显露与重新打开、schema 安全、回滚重试，以及排队中或进行中的数据源等待取消。一个无需密钥的真实 Loader 路径测试会把派生 SQLite 索引与真实 JSONL 持久化 provider 组合使用。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-20-ptc-typed-tool-returns.md
-2026-07-20-ptc-typed-tool-returns.md: a4651eef89d32cdc2330eb5a2562bd34d617a3df
-2026-07-20-ptc-typed-tool-returns.zh.md: d8e68e273bd18fe60d8ba8e0bbf435dbb773a9c2
+2026-07-20-ptc-typed-tool-returns.md: cc784ca8c9b1565135bc59c11ae0af973845fe5f
+2026-07-20-ptc-typed-tool-returns.zh.md: c4dd52d3c136569610beb8a65303809a1fe5fe4d
@@ -73,7 +73,7 @@ Temporary Cordis Plugins follow the same rule: `cordis_mount` returns `{ id, plu

 ### Persistence, metadata, and spill

-Nested dispatch logs the sub-call's full rendered `content`/`isError` on `tool/code-dispatch` but does not persist canonical values. `tool/result` continues to persist only rendered content, error, and optional metadata. A successful final content sequence containing an image is also wrapped in a source-attributed user message and deferred through the outer result; the normal session event makes that model-visible input reconstructable. `SESSION_FORMAT_VERSION` remains unchanged (pre-release shape churn does not bump it) and replay cannot recreate intermediate canonical program values.
+Nested dispatch logs the sub-call's full rendered `content`/`isError` on `tool/code-dispatch` but does not persist canonical values. `tool/result` continues to persist only rendered content, error, and optional metadata. A successful final content sequence containing an image is also wrapped in a source-attributed user message and deferred through the outer result; the normal session event makes that model-visible input reconstructable. This feature did not itself require a structural Session-format change; the released v0-to-v1 identity edge preserves these records, and replay still cannot recreate intermediate canonical program values.

 The opaque `exec.parent` token marks nested calls. Presentation metadata and generic or tool-owned spill projections skip those calls because they have no direct result card and their canonical values never enter context. The outer `run_code` call alone produces one card and may spill its final post-policy presentation; `run_code` intentionally declares neither a result presenter nor presentation metadata, so UI adapters complete the card through their generic raw-content fallback using durable `tool/result.content`.

@@ -73,7 +73,7 @@ PTC mode 通过运行时请求中的 `{ name: "ToolCallError", memberNamePropert

 ### 持久化、元数据与 spill

-嵌套分发在 `tool/code-dispatch` 上记录子调用完整渲染后的 `content`/`isError`，但不会持久化规范值。`tool/result` 继续只持久化渲染后的内容、错误和可选元数据。包含图片的成功最终内容序列还会包装成带来源归属的用户消息，并经外层结果延后；普通会话事件使该模型可见输入可以重建。`SESSION_FORMAT_VERSION` 保持不变（预发布阶段的形状变动不递增版本号），回放也无法重建程序的规范中间值。
+嵌套分发在 `tool/code-dispatch` 上记录子调用完整渲染后的 `content`/`isError`，但不会持久化规范值。`tool/result` 继续只持久化渲染后的内容、错误和可选元数据。包含图片的成功最终内容序列还会包装成带来源归属的用户消息，并经外层结果延后；普通会话事件使该模型可见输入可以重建。该功能本身不要求结构性 Session 格式变更；已发布的 v0-to-v1 恒等边会保留这些记录，回放仍无法重建程序的规范中间值。

 不透明的 `exec.parent` token 用于标识嵌套调用。由于这些调用没有直接对应的结果卡片，而且其规范值永远不会进入上下文，展示元数据以及通用或工具自有的 spill 投影都会跳过它们。只有外层 `run_code` 调用会生成一张卡片，并且可能对 post-policy 处理后的最终展示执行 spill；`run_code` 有意既不声明结果展示器，也不声明展示元数据，因此 UI 适配器会通过通用的原始内容回退机制，使用持久化的 `tool/result.content` 补全该卡片。

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-21-instruction-load-all-dedup.md
-2026-07-21-instruction-load-all-dedup.md: 4cf8ae025cd04d02d00eba7b5b26a661a354e11a
-2026-07-21-instruction-load-all-dedup.zh.md: 2dbccc4ac6336ce48cabcfd2ab3842a2f86f152e
+2026-07-21-instruction-load-all-dedup.md: fc88b4ea6fcbdcda76b9a7da763a04ead2557f50
+2026-07-21-instruction-load-all-dedup.zh.md: f74585850ddaf814fce1cb36239bc666a4142696
@@ -34,4 +34,4 @@ Dedup is enforced during reconciliation, not only at baseline composition. Each

 ## Consequences

-A directory with two distinct real instruction files now surfaces both; a directory whose second file merely mirrors the first still renders once, and the ubiquitous symlink case is unchanged. The visible behavior difference is confined to transition repositories that carry two distinct real files. The scope-key shape changed from a tier sentinel to a per-candidate key and `previousPath` disappeared from the durable change metadata; `dsh-session` keeps no compatibility promise for older sessions, so both are free changes. The version cache row grew a `trimmedDigest` field, and reconciliation now compares trimmed content per directory, so an unchanged file can be removed by a sibling's convergence — a transition the [state model](2026-06-24-workspace-context.md) previously could not produce.
+A directory with two distinct real instruction files now surfaces both; a directory whose second file merely mirrors the first still renders once, and the ubiquitous symlink case is unchanged. The visible behavior difference is confined to transition repositories that carry two distinct real files. The released v0 baseline uses the per-candidate scope key and omits `previousPath` from durable change metadata. The version cache row carries `trimmedDigest`, and reconciliation compares trimmed content per directory, so an unchanged file can be removed by a sibling's convergence — a transition the [state model](2026-06-24-workspace-context.md) previously could not produce.
@@ -34,4 +34,4 @@ Status: implemented

 ## 后果

-一个携带两个不同真实指令文件的目录现在会把两者都暴露；一个第二个文件仅仅是镜像的目录仍只渲染一次，而无处不在的符号链接场景保持不变。可见的行为差异被限定在携带两个不同真实文件的迁移期仓库中。scope 键的形态从层级哨兵改为按候选划分，`previousPath` 也从持久化的变更元数据中消失；`dsh-session` 对旧会话不作兼容承诺，因此两者都是无成本的改动。版本缓存行新增了一个 `trimmedDigest` 字段，协调过程现在按目录比较去空白后的内容，因此一个未变更的文件可以被同级文件的收敛所移除——这是[状态模型](2026-06-24-workspace-context.zh.md)此前无法产生的转换。
+一个携带两个不同真实指令文件的目录现在会把两者都暴露；一个第二个文件仅仅是镜像的目录仍只渲染一次，而无处不在的符号链接场景保持不变。可见的行为差异被限定在携带两个不同真实文件的迁移期仓库中。已发布 v0 基线使用按候选划分的 scope 键，并从持久化变更元数据中省略 `previousPath`。版本缓存行携带 `trimmedDigest` 字段，协调过程按目录比较去空白后的内容，因此一个未变更的文件可以被同级文件的收敛所移除——这是[状态模型](2026-06-24-workspace-context.zh.md)此前无法产生的转换。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-21-local-instruction-overlay.md
-2026-07-21-local-instruction-overlay.md: 9706285f4e699bfb6db9591f9850e4f95f1d2a15
-2026-07-21-local-instruction-overlay.zh.md: b375455dcb1f7e5c157907501f342cbd29a51667
+2026-07-21-local-instruction-overlay.md: 0574cb3568ce1dc41f49f9de2b76131ce75c409b
+2026-07-21-local-instruction-overlay.zh.md: cd7406374cb6f39ff3c24fb95fee5f53410e11a0
@@ -34,4 +34,4 @@ The base and local candidates in one directory must stay independent across base

 ## Consequences

-`.local.` guidance is read by default across all products with no per-deployment configuration, matching neighboring tools. Each project directory can contribute a durable scope per existing candidate rather than one, so dynamic discovery, edits, and removals reconcile the base and local files independently. The scope key is now [per-candidate](2026-07-21-instruction-load-all-dedup.md); `dsh-session` keeps no compatibility promise for older sessions, so this is a free change. The user-global scope remains base-only, recorded as a Known Limitation in the package README.
+`.local.` guidance is read by default across all products with no per-deployment configuration, matching neighboring tools. Each project directory can contribute a durable scope per existing candidate rather than one, so dynamic discovery, edits, and removals reconcile the base and local files independently. The released v0 baseline already records the [per-candidate](2026-07-21-instruction-load-all-dedup.md) scope key. The user-global scope remains base-only, recorded as a Known Limitation in the package README.
@@ -34,4 +34,4 @@ Status: implemented

 ## 后果

-`.local.` 指导在所有产品中默认被读取，无需按部署单独配置，与邻近工具保持一致。每个项目目录可以为每个存在的候选贡献一个持久 scope 而非仅一个，因此动态发现、编辑和移除会分别独立地协调基础文件与本地文件。scope 键现在[按候选划分](2026-07-21-instruction-load-all-dedup.zh.md)；`dsh-session` 对旧会话不作兼容承诺，因此这是一次无成本的改动。用户全局 scope 仍然只有基础文件，这一点作为已知限制记录在包 README 中。
+`.local.` 指导在所有产品中默认被读取，无需按部署单独配置，与邻近工具保持一致。每个项目目录可以为每个存在的候选贡献一个持久 scope 而非仅一个，因此动态发现、编辑和移除会分别独立地协调基础文件与本地文件。已发布 v0 基线已经记录[按候选划分](2026-07-21-instruction-load-all-dedup.zh.md)的 scope 键。用户全局 scope 仍然只有基础文件，这一点作为已知限制记录在包 README 中。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.md
-2026-07-22-durable-subagent-catalog-and-list-agents.md: 813ad0a57bf5399cf641f8a7271671da57ce3966
-2026-07-22-durable-subagent-catalog-and-list-agents.zh.md: ab5351647da32384645c036c0c5e3e2281ba645a
+2026-07-22-durable-subagent-catalog-and-list-agents.md: df7298b542a71e043cf00e0aae1201586f94321e
+2026-07-22-durable-subagent-catalog-and-list-agents.zh.md: 93fe9a7d5b2728febeeebfb1f8b0dfa8c15b8719
@@ -39,7 +39,7 @@ The subagent service keeps `sessionQuery` optional so start and follow-up remain

 `listChildren(parentSessionId, signal?)` forwards the caller's signal to `traceSession()` and the conditional exact `readEvent()` operation. `listEvents()` has no cancellation parameter, so the listing path checks the signal before and after that await and after each candidate settles. If any query operation rejects after the signal aborts, the service normalizes the result to `SubagentError` with stable code `CANCELLED`; a backend abort error or a diagnostic-mapped query error cannot escape or become a successful partial listing.

-This descriptor-read path is the correctness baseline, not a claim that work is linear only in the number of direct children. Let D be the number of direct-child candidates, C be the number of persisted sessions scanned by each persistence listing, and L_i be the size of candidate i's full log. One corpus trace is followed by `sessionQuery.listEvents(childId)` for every candidate. A candidate with no descriptor is omitted, and one with multiple descriptors is diagnosed without another read; only a candidate with exactly one descriptor is loaded again through `sessionQuery.readEvent({ sessionId: childId, seq })`. The read must return the same immutable session header observed by the trace, including the direct-parent relationship, and its target must still be the located descriptor event; a mismatch is per-child corruption. In the persisted-only worst case, each exact read repeats `persistence.list()`, loads the full child log, and clones its events, for O(D × C + Σ L_i) work up to constant factors; a candidate with exactly one descriptor pays those costs twice, while other candidates pay them once. A live candidate similarly takes one detached in-memory snapshot of its full log, or two when its descriptor is read. Session query resolves persisted candidates through the persistence seam's non-mutating `inspect()` read, which returns the valid stored prefix without repairing a torn tail or closing an interrupted turn, so listing is storage-read-only; repair remains the resume path's concern. The first version accepts these repeated reads as the no-index correctness baseline, but deployments must treat total corpus and child-log size—not only direct-child count—as the capacity constraint. Listing creates no Agent and appends no catalog, descriptor, or repair event. The model-hidden descriptor remains outside the conversation surface and survives compaction, so compacted and uncompacted children must enumerate identically.
+This descriptor-read path is the correctness baseline, not a claim that work is linear only in the number of direct children. Let D be the number of direct-child candidates, C be the number of persisted sessions scanned by each persistence listing, and L_i be the size of candidate i's full log. One corpus trace is followed by `sessionQuery.listEvents(childId)` for every candidate. A candidate with no descriptor is omitted, and one with multiple descriptors is diagnosed without another read; only a candidate with exactly one descriptor is loaded again through `sessionQuery.readEvent({ sessionId: childId, seq })`. The read must return the same immutable session header observed by the trace, including the direct-parent relationship, and its target must still be the located descriptor event; a mismatch is per-child corruption. In the persisted-only worst case, each exact read repeats `persistence.list()`, loads the full child log, and clones its events, for O(D × C + Σ L_i) work up to constant factors; a candidate with exactly one descriptor pays those costs twice, while other candidates pay them once. A live candidate similarly takes one detached in-memory snapshot of its full log, or two when its descriptor is read. Session query resolves persisted candidates through `inspect()`: already-current recovery remains in memory, while a supported historical body read may first publish its migrated and repaired current generation. Listing creates no Agent and appends no catalog, descriptor, or repair event, but its first historical read is not storage-read-only. The first version accepts these repeated reads as the no-index correctness baseline, but deployments must treat total corpus and child-log size—not only direct-child count—as the capacity constraint. The model-hidden descriptor remains outside the conversation surface and survives compaction, so compacted and uncompacted children must enumerate identically.

 If measured scale later requires an index, that index is derived state: session headers and child descriptors remain authoritative, and rebuilding or corruption fallback must reproduce the same results. An index cannot become a second authorization source or make an unpublished child visible.

@@ -86,7 +86,7 @@ The first version has no child deletion operation. If later product behavior del

 **Return separate child and diagnostic arrays.** Separate arrays introduce two ordering domains or require exposing another sort key to reconstruct candidate order. One discriminated entry array preserves the trace order while keeping child and diagnostic fields type-safe.

-**Read candidates through the repairing `load()` path.** Reusing resume's `load()` semantics would let discovery durably close an interrupted tail early, but turns a listing query into a mutating operation and couples its failure modes to write coordination. Session query's corpus reads already use the non-mutating `inspect()` contract, so listing stays storage-read-only and leaves tail repair to the resume path that needs it.
+**Read candidates through the repairing `load()` path.** For already-current input, reusing resume's `load()` semantics would durably close an interrupted tail on every discovery, while `inspect()` keeps those closers in memory. Historical inspection may already publish one migration and repair, but it does not make recurring current listings mutating or couple them to `load()` repair on every read.

 **Paginate or cap the query now (deferred).** This bounds one result, but makes model discovery stateful and can hide older children unless the model follows a cursor. The first version has no cursor, page arguments, or candidate-limit configuration and returns the complete stably ordered set; a service-level bound remains a later decision if measured scale requires it.

@@ -103,7 +103,7 @@ The first version has no child deletion operation. If later product behavior del

 - Session tracing observes the complete logical corpus, then descriptor validation reads every direct-child log once and candidates with exactly one descriptor twice. In the persisted-only worst case, work is O(D × C + Σ L_i), not merely O(D), because each exact read rescans persistence and loads and clones the full candidate log. A later derived index must preserve the same authorization, per-child diagnostic, and fallback behavior.
 - Corpus construction is an all-or-nothing trust boundary: one live/persisted header conflict fails the initial trace and hides otherwise healthy siblings. Per-child isolation begins only after that trace succeeds.
- A torn child tail is surfaced, not repaired: the non-mutating `inspect()` read returns the valid stored prefix, so a child interrupted mid-write may list from a shorter log until the resume path's repairing load closes it.
+- For already-current storage, a torn child tail is surfaced rather than repaired: `inspect()` returns the valid stored prefix, so a child interrupted mid-write may list from a shorter log until the resume path's repairing load closes it. Historical input is migrated and repaired before this current inspection behavior applies.
 - There is no deletion operation, so persisted children remain listed for as long as their sessions remain in persistence even though live Agent resources remain bounded by resident Activations.
 - The service returns every direct session-backed subagent and diagnostic without a cursor or candidate cap. Stable ordering makes the result deterministic; the model projection avoids one-shot context growth but remains unbounded in the number of continuable children.
 - `running` and `inactive` are process-local corpus snapshots, not outcomes or delivery promises. Another process may activate a persisted child while this process reports it as `inactive`; cross-process accuracy requires a shared lease.
@@ -39,7 +39,7 @@ subagent 服务将 `sessionQuery` 保持为可选依赖，因此没有该服务

 `listChildren(parentSessionId, signal?)` 会把调用方的取消信号转发给 `traceSession()` 和条件性精确 `readEvent()` 操作。`listEvents()` 不接受取消参数，因此列表查询路径会在等待该操作的前后，以及每个候选处理完成后检查信号。如果取消信号触发后有查询操作以拒绝结算，服务会将结果归一化为 `SubagentError`，并携带稳定错误码 `CANCELLED`；后端中止错误或可映射为 diagnostic 的查询错误均不会逃逸，也不会使调用以成功的部分列表返回。

-这条描述符读取路径是正确性基线，并不声称工作量只与直接 child 数量呈线性关系。令 D 为直接 child 候选数量，C 为每次持久化列表查询所扫描的持久化会话数量，L_i 为候选 i 的完整日志大小。一次语料追踪后，每个候选都会执行 `sessionQuery.listEvents(childId)`。没有描述符的候选会被排除；含有多个描述符的候选会直接产生 diagnostic，无需再次读取；只有恰好含有一个描述符的候选才会通过 `sessionQuery.readEvent({ sessionId: childId, seq })` 再次加载。此次读取返回的不可变会话 header 必须与追踪时观测到的相同，包括直接 parent 关系，并且读取目标仍必须是先前定位的描述符事件；任何不一致均视为该 child 损坏。对于只存在于持久化存储中的最坏情况，每次精确读取都会重复执行 `persistence.list()`、加载完整 child 日志并克隆其中的事件，因此忽略常数因子后的工作量为 O(D × C + Σ L_i)；恰好含有一个描述符的候选承担两次这类成本，其他候选只承担一次。存活候选同样会对其完整日志取得一份分离的内存快照；读取其描述符时则会取得两份。会话查询通过持久化 seam 的非变更 `inspect()` 读取解析持久化候选：它返回有效的已存储前缀，既不修复撕裂的尾部，也不关闭中断的 turn，因此列表查询是存储只读操作；修复仍是恢复路径的职责。第一版接受这些重复读取，将其作为无索引的正确性基线，但部署必须将语料总量和 child 日志大小，而不仅是直接 child 数量，视为容量约束。列表查询不会创建 Agent，也不会追加任何目录、描述符或修复事件。对模型隐藏的描述符始终位于对话 surface 之外，并且会在压缩后保留，因此经过压缩和未经压缩的 child 必须枚举出相同结果。
+这条描述符读取路径是正确性基线，并不声称工作量只与直接 child 数量呈线性关系。令 D 为直接 child 候选数量，C 为每次持久化列表查询所扫描的持久化会话数量，L_i 为候选 i 的完整日志大小。一次语料追踪后，每个候选都会执行 `sessionQuery.listEvents(childId)`。没有描述符的候选会被排除；含有多个描述符的候选会直接产生 diagnostic，无需再次读取；只有恰好含有一个描述符的候选才会通过 `sessionQuery.readEvent({ sessionId: childId, seq })` 再次加载。此次读取返回的不可变会话 header 必须与追踪时观测到的相同，包括直接 parent 关系，并且读取目标仍必须是先前定位的描述符事件；任何不一致均视为该 child 损坏。对于只存在于持久化存储中的最坏情况，每次精确读取都会重复执行 `persistence.list()`、加载完整 child 日志并克隆其中的事件，因此忽略常数因子后的工作量为 O(D × C + Σ L_i)；恰好含有一个描述符的候选承担两次这类成本，其他候选只承担一次。存活候选同样会对其完整日志取得一份分离的内存快照；读取其描述符时则会取得两份。会话查询通过 `inspect()` 解析持久化候选：已经是当前格式的恢复留在内存中，受支持的历史正文读取则可能先发布迁移并修复后的当前 generation。列表查询不会创建 Agent，也不会追加目录、描述符或修复事件，但其首次历史读取并非存储只读。第一版接受这些重复读取，将其作为无索引的正确性基线，但部署必须将语料总量和 child 日志大小，而不仅是直接 child 数量，视为容量约束。对模型隐藏的描述符始终位于对话 surface 之外，并且会在压缩后保留，因此经过压缩和未经压缩的 child 必须枚举出相同结果。

 如果实测规模日后需要索引，该索引属于派生状态：会话 header 和 child 描述符仍是权威信息，重建或损坏回退必须复现相同结果。索引不能成为第二个鉴权来源，也不能让尚未发布的 child 变得可见。

@@ -86,7 +86,7 @@ diagnostic 是瞬时查询结果，不属于会话事件或目录状态。推导

 **分别返回 child 和 diagnostic 数组。** 分离的数组会引入两个排序域，或者要求公开另一个排序键才能重建候选顺序。一个带判别字段的条目数组既能保留追踪顺序，也能保证 child 与 diagnostic 字段的类型安全。

-**通过会触发修复的 `load()` 路径读取候选。** 复用恢复路径的 `load()` 语义可以让发现提前持久化地关闭中断尾部，但会把列表查询变成变更操作，并使其失败模式与写协调耦合。会话查询的语料读取本就使用非变更的 `inspect()` 约定，因此列表查询保持存储只读，尾部修复留给真正需要它的恢复路径。
+**通过会触发修复的 `load()` 路径读取候选。** 对已经是当前格式的输入，复用恢复路径的 `load()` 语义会让每次发现都持久关闭中断尾部，而 `inspect()` 只在内存中保留这些 closer。历史检查可能已经发布一次迁移与修复，但这不会让重复的当前列表变成修改操作，也不会让它们每次都耦合到 `load()` 修复。

 **立即为查询分页或设置上限（暂缓）。** 这可以限制一次结果的大小，但会使模型发现成为有状态操作，而且除非模型继续跟随 cursor，否则可能隐藏更早的 child。第一版没有 cursor、分页参数或候选数量上限配置，而是返回经稳定排序的完整集合；如果实测规模需要限制，服务级限制仍留待后续决策。

@@ -103,7 +103,7 @@ diagnostic 是瞬时查询结果，不属于会话事件或目录状态。推导

 - 会话追踪会观察完整的逻辑语料，随后描述符校验会读取每个直接 child 的日志一次，并对恰好含有一个描述符的候选读取两次。对于只存在于持久化存储中的最坏情况，工作量为 O(D × C + Σ L_i)，而不只是 O(D)，因为每次精确读取都会重新扫描持久化存储，并加载和克隆候选的完整日志。后续的派生索引必须保持相同的鉴权、逐 child diagnostic 和回退行为。
 - 语料构建是一个全有或全无的信任边界：一处存活／持久化 header 冲突就会导致初始追踪失败，并隐藏原本健康的 sibling。只有初始追踪成功后，逐 child 隔离才会生效。
- 撕裂的 child 尾部会被呈现而非修复：非变更的 `inspect()` 读取返回有效的已存储前缀，因此写入中途被打断的 child 在恢复路径的修复加载将其关闭之前，可能以较短的日志形式出现在列表中。
+- 对已经是当前格式的存储，撕裂的 child 尾部会被呈现而非修复：`inspect()` 返回有效的已存储前缀，因此写入中途被打断的 child 在恢复路径的修复加载将其关闭之前，可能以较短的日志形式出现在列表中。历史输入会先迁移并修复，再应用这项当前检查行为。
 - 没有删除操作，因此只要 child 会话仍保留在持久化存储中，它们就会继续出现在列表里，但存活 Agent 资源仍由驻留 Activation 数量限制。
 - 服务会返回每个直接且由会话支撑的 subagent 和 diagnostic，不设 cursor 或候选数量上限。稳定排序可使结果确定；模型投影避免了一次性 child 带来的上下文增长，但可继续 child 的数量仍无上限。
 - `running` 和 `inactive` 是进程本地语料快照，而非结果或消息送达承诺。另一个进程可能在当前进程将某个持久化 child 报告为 `inactive` 时激活它；跨进程准确性需要共享租约。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md
-2026-07-23-session-telemetry-otel-revival.md: 1110db4b0dfcfd68bde97f9964383ddd041f328b
-2026-07-23-session-telemetry-otel-revival.zh.md: 6c046c5f963760638deacacda51f8d94a13e0efd
+2026-07-23-session-telemetry-otel-revival.md: 27e9eb9d073c3d4f726595a16bf4b63293207e22
+2026-07-23-session-telemetry-otel-revival.zh.md: 6928d7086c47460e33660dbf3ced6cea7119f456
@@ -6,17 +6,17 @@ English | [中文](2026-07-23-session-telemetry-otel-revival.zh.md)

 ## Problem

-Every deployment that wants harness sessions in an observability stack must hand-roll a session-log consumer: subscription, lifecycle handoff, and — hardest — redaction, since the raw log carries file contents and command output that may embed credentials. A telemetry seam and OTel backend shipped once on the `session-telemetry-otlp-rfc` branch (PR #222/#231) but never reached master: the proposal exported raw session events verbatim, which legal review declined. The capture-side design (backend contract, coordinator, handoff cursor, chunk projection) was sound and reviewed; the export-side stance was the blocker.
+Every deployment that wants harness sessions in an observability stack must hand-roll a session-log consumer: subscription, lifecycle handoff, and — hardest — redaction, since the raw log carries file contents and command output that may embed credentials. A telemetry seam and OTel backend shipped once on the `session-telemetry-otlp-rfc` branch (PR #222/#231) but never reached master: the proposal exported raw session events verbatim, which legal review declined. The reusable capture-side design comprised the backend contract, coordinator, handoff cursor, and session-event subscription; the export-side stance was the blocker.

 ## Decision

 `packages/session/` (formerly `telemetry/`) revives the two reviewed packages under the SDK stance — the harness provides the capability, the deployment configures where records go and owns what leaves in them:

- **`@deepseek-ai/dsh-session-telemetry`** — the seam. `SessionTelemetrySink` (`emit`/`flush?`/`shutdown`), the service-registered `SessionTelemetryBackend` form, and `SessionTelemetryCoordinator` owning capture: live adoption with cursor read-back and the per-append firehose (project → `structuredClone` → redact → `emit`, zero I/O), buffer-free on-demand replay from the canonical log, the fixed first-chunk-per-(turn, step) projection, the live `agent/error` relay, and live dispose-time `shutdown` records.
+- **`@deepseek-ai/dsh-session-telemetry`** — the seam. `SessionTelemetrySink` (`emit`/`flush?`/`shutdown`), the service-registered `SessionTelemetryBackend` form, and `SessionTelemetryCoordinator` own complete capture: each new Session object replays every canonical event from seq 0, then the per-append firehose deep-copies, redacts, and hands off every event with zero I/O; re-adopting the same object resumes after its module-scope cursor. Buffer-free on-demand capture uses the same one-record-per-event mapping through an optional inclusive boundary. Ledger identity includes `session.id`, `session.format_version`, and `event.seq`; live capture also relays `agent/error` and creates dispose-time `shutdown` records.
 - **The `session-telemetry/record` waterfall** — the delta over the branch version and the seam's redaction extension point. Every record passes it before reaching any backend; the seam ships NO rules of its own — the innermost `next()` is a pass-through, deployments mount their rules as listeners (stacking by transforming `next()`'s return value), and a throwing rule withholds the record fail-closed. Redaction applies to the exported copy only; the canonical log is never rewritten.
 - **`@deepseek-ai/dsh-session-telemetry-otel`** — the reference backend: OTel JS SDK log pipeline (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter), configured verbatim through `exporter`/`processor` passthroughs. `DISABLED` is the default and constructs no transport; the [feedback-gated telemetry decision](2026-08-05-feedback-gated-session-telemetry.md) defines the explicit `FULL` and `FEEDBACK_ONLY` delivery modes, which require `exporter.url`, without moving the redaction or backend boundary. [Buffer-free feedback replay](../simplification/2026-08-06-buffer-free-feedback-telemetry.md) avoids a second in-memory copy of the session prefix.

-The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry, queueing, and loss policy are the reporting SDK's, configured through passthroughs — delivery is best-effort (at-most-once across a crash), which the READMEs state plainly.
+The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry, queueing, and loss policy are the reporting SDK's, configured through passthroughs. Delivery is best-effort: a crash can lose queued records, while constructing the Session again can replay records already delivered before the crash. Receivers therefore deduplicate ledger rows on `(session.id, session.format_version, event.seq)`.

 ## Alternatives considered

@@ -28,10 +28,10 @@ The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry

 **Map onto OTel spans (GenAI semantic conventions) instead of logs.** Rejected for this revival: the branch implementation's log mapping is reviewed and shipped-shaped; the span model is lossy for forkable, interruptible sessions and belongs to a future consumer with real span queries to serve.

-**Full-log replay when no handoff cursor survived (re-export constructor seeds).** Shipped in the first revival round, then narrowed: adoption now replays from the session's construction boundary (`Session.firstLiveSeq`, the constructor-seed length; `Session.inheritedEventCount` cannot serve because it is the durable fork-lineage cut and a resumed session's constructor seed is its full stored log). A resumed session's history already shipped from the previous process under the same id, and a fork's inherited prefix already shipped in the parent's stream — re-exporting either re-billed every resume for its full history and doubled query-time counts on OTLP backends with no native ingest dedupe. Receivers stitch fork lineage via `session.parent_id` + `session.seed_length`. What the narrowing gives up, consistently with the at-most-once stance: a resume no longer backfills records the previous process failed to deliver (telemetry unmounted then, or queued at crash) — the full replay's only real benefit, bought at the common case's expense. A deployment that states a backfill requirement needs the deferred outbox above, not replay. The boundary also swallows the synthetic turn closers `SessionPersistence.load()` writes when repairing a crash-interrupted log (they sit below `firstLiveSeq` despite never existing in the previous process) — deliberate, not incidental: exporting a synthetic closer cannot complete the remote turn whose real tail records died in the crashed process's queue, it can only make an incomplete turn look closed. The wire stream stays faithful to what the crashed process actually shipped; receivers read a never-closed turn on a resumed stream as "the previous process died inside it" (the OTel README states the rule), and a later clean `shutdown` marker attests only to the resumed process's exit. Threading the pre-repair boundary through load/prepare so repairs export as live events would couple three packages to un-ship that signal.
+**Start a new Session object at its constructor boundary and skip the seed prefix.** Rejected because this assumes another process or parent identity successfully delivered those records. It loses history when telemetry mounts after the original run, when the SDK queue dies in a crash, and when format migration or crash repair creates the current canonical seed before telemetry sees the restored object. Every new object instead starts without a handoff cursor and replays from seq 0, including a fork's inherited prefix and a resumed or migrated log. Re-adopting the same object still resumes after its cursor, so HMR does not duplicate the settled prefix. Full replay can duplicate previously delivered rows and intentionally repeats inherited events under a child session id; receiver-side deduplication uses `(session.id, session.format_version, event.seq)`, while `session.parent_id` and `session.seed_length` preserve lineage. This replay is opportunistic recovery, not an at-least-once guarantee: records can still be lost if no later Session object is constructed, so a deployment requiring guaranteed backfill needs the deferred outbox.

 **Forwarding the seam's turn-boundary `flush()` hint to the OTel provider's `forceFlush()`.** Shipped in the first revival round, then removed: three distinct silent-loss paths shared the wrapper state — a dispose racing an in-flight flush (the SDK's concurrent-flush guard makes shutdown's internal drain skip), overlapping hints displacing the retained promise, and the provider's fixed 30-second flush timeout rejecting while the processor still drains. Every path exists only because the forwarding made this backend the process's second flusher against undocumented SDK internals from the upstream experimental tree; with no `flush()` implemented, the batch processor is the only flusher, its `scheduledDelayMillis` (already deployment-tunable through the `processor` passthrough) governs export cadence, and `shutdown()`'s drain is complete by construction. Reinstate only if a deployment states a turn-boundary latency requirement `scheduledDelayMillis` cannot meet — and then by calling the retained `BatchLogRecordProcessor`'s own `forceFlush()`, never the provider's timeout-wrapped one.

 ## Consequences

-A deployment adds one `cordis.yml` entry with an OTLP endpoint and explicitly selects `FULL` to stream sessions into an OTel-compatible stack or `FEEDBACK_ONLY` to replay a canonical-log prefix when feedback is recorded. `DISABLED` is the [default](2026-08-10-telemetry-default-off.md) and constructs no reporting pipeline; removing the entry remains a silent opt-out, while the disabled mode keeps the local feedback warning. A rule-free deployment exports records exactly as captured — including any credentials embedded in file contents or command output — so a deployment crossing a trust boundary must mount `session-telemetry/record` listeners, and both READMEs state this plainly. Where rules are mounted, exported bodies can differ from canonical log bytes, so receivers must not treat telemetry as a byte-exact replica; the log remains the source of truth. Crash durability is explicitly out of scope until the outbox decision above is revisited.
+A deployment adds one `cordis.yml` entry with an OTLP endpoint and explicitly selects `FULL` to stream complete canonical events into an OTel-compatible stack or `FEEDBACK_ONLY` to replay a complete canonical-log prefix when feedback is recorded. `DISABLED` is the [default](2026-08-10-telemetry-default-off.md) and constructs no reporting pipeline; removing the entry remains a silent opt-out, while the disabled mode keeps the local feedback warning. A rule-free deployment exports each event body exactly as captured — including every assistant chunk and any credentials embedded in file contents or command output — so a deployment crossing a trust boundary must mount `session-telemetry/record` listeners, and both READMEs state this plainly. Where rules are mounted, exported bodies can differ from canonical log bytes, so receivers must not treat telemetry as a byte-exact replica; the log remains the source of truth. New-object replay can duplicate ledger rows, and crash durability remains out of scope until the outbox decision above is revisited.
@@ -6,18 +6,18 @@ Status: implemented

 ## 问题

-每个想把 harness 会话接入可观测性体系的部署方都得手写一个会话日志消费方：订阅、生命周期交接、以及最难的脱敏——原始日志携带文件内容与命令输出，可能内嵌凭据。遥测 seam 和 OTel 后端曾在 `session-telemetry-otlp-rfc` 分支（PR #222/#231）上完成过一版，但从未进入 master：该提案将原始会话事件原样导出，法务评审未予通过。捕获侧设计（后端约定、coordinator、handoff 游标、分片投影）本身合理且经过评审；导出侧的立场才是阻塞点。
+每个想把 harness 会话接入可观测性体系的部署方都得手写一个会话日志消费方：订阅、生命周期交接、以及最难的脱敏——原始日志携带文件内容与命令输出，可能内嵌凭据。遥测 seam 和 OTel 后端曾在 `session-telemetry-otlp-rfc` 分支（PR #222/#231）上完成过一版，但从未进入 master：该提案将原始会话事件原样导出，法务评审未予通过。可复用的捕获侧设计包括后端约定、coordinator、handoff 游标与会话事件订阅；导出侧的立场才是阻塞点。

 ## 决策

 `packages/session/`（原 `telemetry/`）以 SDK 立场复活这两个经过评审的包——harness 提供能力，部署方配置上报去向并对导出内容负责：

- **`@deepseek-ai/dsh-session-telemetry`** —— seam 本体。`SessionTelemetrySink`（`emit`/`flush?`/`shutdown`）、服务注册形态的 `SessionTelemetryBackend`、以及拥有捕获侧的 `SessionTelemetryCoordinator`：带游标回读的实时纳管与逐 append 的 firehose（投影 → `structuredClone` → 脱敏 → `emit`，零 I/O）、从权威日志进行的无缓冲按需回放、固定的每个（轮次、步骤）组合首分片投影、实时 `agent/error` 转发，以及实时 dispose（资源释放）时的 `shutdown` 记录。
+- **`@deepseek-ai/dsh-session-telemetry`** —— seam 本体。`SessionTelemetrySink`（`emit`/`flush?`/`shutdown`）、服务注册形态的 `SessionTelemetryBackend` 与 `SessionTelemetryCoordinator` 共同拥有完整捕获：每个新的 Session 对象会从 seq 0 回放全部权威事件，随后逐 append firehose 以零 I/O 深拷贝、脱敏并交接每个事件；重新收养同一对象时从模块作用域游标之后继续。无缓冲按需捕获使用同样的一事件一记录映射，直到可选的包含式边界。Ledger 身份包含 `session.id`、`session.format_version` 与 `event.seq`；实时捕获还会转发 `agent/error`，并创建 dispose（资源释放）时的 `shutdown` 记录。
 - **`session-telemetry/record` waterfall（瀑布式事件）** —— 相对分支版本的增量，也是该 seam 的脱敏扩展点。每条记录抵达任何后端前必经此处；seam 自身不带任何规则——最内层 `next()` 原样透传，部署方以监听器挂载自己的规则（通过变换 `next()` 的返回值堆叠），抛异常的规则将该记录 fail-closed 扣下。脱敏只作用于导出副本；canonical log 永不改写。
 - **`@deepseek-ai/dsh-session-telemetry-otel`** —— 参考后端：OTel JS SDK 日志流水线（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter），经 `exporter`/`processor` passthrough 原样配置。`DISABLED` 是默认值，且不构造任何传输；[反馈门控遥测决策](2026-08-05-feedback-gated-session-telemetry.zh.md)定义了需显式启用的 `FULL` 与 `FEEDBACK_ONLY` 投递模式，这两种模式要求 `exporter.url`，且不移动脱敏或后端边界。[无缓冲反馈回放](../simplification/2026-08-06-buffer-free-feedback-telemetry.zh.md)避免在内存中创建会话前缀的第二份副本。


-边界公理保持不变：harness 的职责止于 `emit()`。批处理、重试、排队与丢失策略属于 reporting SDK，经 passthrough 配置——投递是尽力而为（崩溃时至多一次），两份 README 对此如实陈述。
+边界公理保持不变：harness 的职责止于 `emit()`。批处理、重试、排队与丢失策略属于 reporting SDK，并经 passthrough 配置。投递是尽力而为：崩溃可能丢失已排队记录，而重新构造 Session 也可能回放崩溃前已经送达的记录。因此，接收端要基于 `(session.id, session.format_version, event.seq)` 对 ledger 行去重。

 ## 考虑过的替代方案

@@ -29,10 +29,10 @@ Status: implemented

 **映射到 OTel span（GenAI 语义约定）而非日志。** 本次复活否决：分支实现的日志映射已经过评审、形态可交付；span 模型对可 fork、可中断的会话有损，留给将来真正有 span 查询需求的消费方。

-**handoff 游标未存活时全量回放日志（重新导出构造函数种子）。** 首轮复活曾交付此方案，其后收窄：接管操作现在从会话的构造边界起回放（`Session.firstLiveSeq`，即构造函数种子长度；`Session.inheritedEventCount` 不能胜任，因为它是持久保存的 fork 谱系 cut，而恢复会话的构造函数种子是其完整的已存储日志）。恢复会话的历史已由上一个进程以同一 id 发出，fork 继承的前缀也已在父会话的流中发出；再次导出任何一者，都会让每次恢复为其完整历史重复付费，并在没有原生摄取去重的 OTLP 后端上使查询时的计数翻倍。接收端基于 `session.parent_id` + `session.seed_length` 拼接 fork 谱系。此次收窄放弃的内容与至多一次立场一致：恢复不再回填上一个进程未能投递的记录（彼时遥测未挂载，或崩溃时仍在队列中）——这本是全量回放唯一的真实收益，代价却由常见情形承担。提出回填要求的部署需要的是上文已推迟的 outbox，而不是回放。该边界同样吞掉 `SessionPersistence.load()` 修复被崩溃打断的日志时写入的合成轮次关闭事件（它们落在 `firstLiveSeq` 之前，尽管在上一个进程中从未存在过）。这是有意为之，而非附带效果：远端轮次的真实尾部记录已随崩溃进程的队列一同消亡，导出合成关闭事件无法补全该轮次，只会让一个未完成的轮次看起来已经关闭。导出的流忠实于崩溃进程实际发出的内容；接收端会把恢复后的流中一个从未关闭的轮次读作「上一个进程死在了该轮次之内」（OTel README 陈述了这条规则），其后干净的 `shutdown` 标记也只证明恢复后进程自身的退出。若为让修复以实时事件的身份导出而将修复前边界贯穿 load/prepare 传递，将使三个包相互耦合，只为抹除这一信号。
+**让新的 Session 对象从构造边界开始，并跳过 seed 前缀。** 不予采用，因为这种做法假设另一个进程或父身份已经成功投递那些记录。如果遥测在原始运行之后才挂载、SDK 队列随崩溃消失，或格式迁移与崩溃修复在遥测看到恢复对象前生成当前权威 seed，该假设都会丢失历史。每个新对象改为从没有 handoff 游标的状态开始，并从 seq 0 回放，包括 fork 继承前缀以及恢复或迁移后的日志。重新收养同一对象时仍从游标之后继续，因此 HMR 不会重复稳定前缀。全量回放可能重复此前已投递的行，也会有意在 child Session id 下重复继承事件；接收端基于 `(session.id, session.format_version, event.seq)` 去重，`session.parent_id` 与 `session.seed_length` 则保留谱系。这种回放是机会式恢复，而非 at-least-once 保证：如果之后没有构造新的 Session 对象，记录仍可能丢失，因此要求保证回填的部署需要上文推迟的 outbox。

 **将 seam 的轮次边界 `flush()` 提示转发到 OTel 提供方的 `forceFlush()`。** 首轮复活曾交付此转发，其后移除：三条不同的静默丢失路径共用同一份包装层状态——dispose 与进行中的 flush 之间的竞态（SDK 的并发 flush 防护会令 shutdown 的内部排空被跳过）、相互重叠的提示顶掉留存的 promise、以及提供方固定的 30 秒 flush 超时在批处理器仍在排空时便 reject。这些路径存在的唯一原因，是该转发让这个后端成为进程内第二个执行 flush 的组件，面对的还是上游实验性（experimental）源码树中未见诸文档的 SDK 内部行为；不实现 `flush()` 时，批处理器就是唯一执行 flush 的组件，其 `scheduledDelayMillis`（已可由部署方经 `processor` passthrough 调优）决定导出节奏，`shutdown()` 的排空从构造上就是完整的。仅当某个部署提出 `scheduledDelayMillis` 无法满足的轮次边界延迟要求时才恢复此转发——且届时应调用留存的 `BatchLogRecordProcessor` 自身的 `forceFlush()`，绝不调用提供方那个带超时包装的版本。

 ## 后果

-部署方在 `cordis.yml` 加一个带 OTLP endpoint 的 Cordis 配置项，并显式选择 `FULL`，即可把会话流接入任何 OTel 兼容体系；选择 `FEEDBACK_ONLY` 则会在记录反馈时回放权威日志前缀。`DISABLED` 是[默认值](2026-08-10-telemetry-default-off.zh.md)，且不构造上报流水线；删除该配置项仍是静默退出方式，而禁用模式会保留本地反馈警告。未挂载规则的部署导出的记录与捕获时完全一致，包括文件内容与命令输出中内嵌的任何凭据。因此，跨信任边界的部署必须挂载 `session-telemetry/record` 监听器，两个 README 对此如实陈述。挂载规则后，导出的 body 可能与 canonical log 字节不同，接收端不得把遥测当作字节精确副本；日志仍是真源。崩溃持久性在上述 outbox 决定重新审议前明确不在范围内。
+部署方在 `cordis.yml` 加一个带 OTLP endpoint 的 Cordis 配置项，并显式选择 `FULL`，即可把完整权威事件流接入任何 OTel 兼容体系；选择 `FEEDBACK_ONLY` 则会在记录反馈时回放完整的权威日志前缀。`DISABLED` 是[默认值](2026-08-10-telemetry-default-off.zh.md)，且不构造上报流水线；删除该配置项仍是静默退出方式，而禁用模式会保留本地反馈警告。未挂载规则的部署会按捕获原样导出每个事件 body，包括每条 assistant chunk，以及文件内容与命令输出中内嵌的任何凭据。因此，跨信任边界的部署必须挂载 `session-telemetry/record` 监听器，两份 README 对此如实陈述。挂载规则后，导出的 body 可能与 canonical log 字节不同，接收端不得把遥测当作字节精确副本；日志仍是真源。新对象回放可能重复 ledger 行，崩溃持久性则在上述 outbox 决定重新审议前继续不在范围内。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-25-subagent-policy-inheritance.md
-2026-07-25-subagent-policy-inheritance.md: 6df9ad53f8588018fca53ebae3a9dfba0d4382de
-2026-07-25-subagent-policy-inheritance.zh.md: f3f7328d558ea55379cb95e53bb010f9f2d2c792
+2026-07-25-subagent-policy-inheritance.md: 3fa8df405d9705a2bf145f1182e18fc0f7586b25
+2026-07-25-subagent-policy-inheritance.zh.md: 94c19d22db050441a6ce48fb507ccc428dbbe91e
@@ -12,7 +12,7 @@ Sandbox and approval overrides are per-session log folds. An in-process subagent

 The delegation boundary snapshots `sandboxPolicy.overrideOf(parent.session)` before its first await, through the shared child-agent helpers (`captureDelegatedPolicyOverrides`/`appendDelegatedPolicyOverrides` in `dsh-subagent`), which the one-shot driver and the [continuable start](2026-08-10-continuable-subagent-policy-inheritance.md) both call. A later parent switch belongs to the parent's future; cancel-and-redelegate takes a new snapshot. The sandbox-policy service is optional, and only the explicit session override is copied, never deployment defaults or one-shot grants. The approval policy is not inherited: the same capture pins every child to `'never'` — the [approvals-pinned decision](2026-08-10-subagent-approval-pinned-never.md) supersedes this note's original approval-override inheritance.

-Each captured value becomes a source-tagged `sandbox/mode` or `approval/policy` event appended during the child factory's unpublished setup. The session constructor has already fixed `Session.firstLiveSeq` after the constructor seed, while `Session.inheritedEventCount` keeps the exact fork-prefix length, so the inherited facts follow fork history and reach telemetry when the child is announced without changing its lineage cut. Existing last-event-wins folds therefore make the delegation snapshot beat stale fork history and let a later child switch beat the snapshot. A grandchild folds its parent's logged state, so the rule composes without another inheritance mechanism.
+Each captured value becomes a source-tagged `sandbox/mode` or `approval/policy` event appended during the child factory's unpublished setup. The session constructor has already fixed `Session.firstLiveSeq` after the constructor seed, while `Session.inheritedEventCount` keeps the exact fork-prefix length, so the inherited facts follow fork history without changing its lineage cut. Complete telemetry capture includes the entire announced child log, including both its constructor seed and these unpublished-setup events. Existing last-event-wins folds therefore make the delegation snapshot beat stale fork history and let a later child switch beat the snapshot. A grandchild folds its parent's logged state, so the rule composes without another inheritance mechanism.

 Ordinary session appends validate the inherited events before publication, and persistence captures the complete unpublished log when the session is announced. Any materialized child log therefore stores the inherited events with its first batch; there is no second policy store, schema field, or query index. The `source: 'delegation'` marker lets approval narration distinguish inheritance from a child-side user switch.

@@ -23,7 +23,7 @@ A confined child gets the ordinary denial marker, and an escalation request is r
 ## Alternatives considered

 - **Generic `SessionHeader` policy fields** — rejected: they duplicate an event-sourced fact in metadata and require propagation through core session types, persistence backends, query indexes, collision identity, and every policy consumer. Unpublished setup events have the required ordering and reuse the existing durable store.
- **Combining new policy facts with constructor history** — rejected: `Session.firstLiveSeq` classifies the complete constructor seed as replayed history, so telemetry would skip child-only facts. Unpublished setup keeps history and new facts on their existing sides of that boundary without another session option.
+- **Combining new policy facts with constructor history** — rejected because it would classify child-owned delegation policy as inherited history and blur the lifecycle ordering that makes the child snapshot override a stale fork value. Unpublished setup keeps history and new facts on their existing sides of the construction boundary without another session option; telemetry captures both sides.
 - **A first-prompt listener** — rejected: it introduces listener ordering and a later timing boundary even though the creation transaction already permits log appends before publication.
 - **Copying deployment defaults** — rejected: defaults remain operator-owned and may change; an unswitched parent stamps nothing, so its child follows the current deployment.
 - **Live resolution walking `parentSession` at each call** — rejected: it breaks the "two sessions never see each other's state" isolation invariant, requires the parent session to stay loaded for the child's lifetime, and makes a mid-run parent switch retroactively change a running child. Snapshot-at-delegation is the semantic: the child keeps the policy it was handed; cancel-and-respawn picks up a tightening.
@@ -12,7 +12,7 @@ Status: implemented

 委派边界在第一次 await 之前，经由共享的子 agent 辅助函数（`dsh-subagent` 中的 `captureDelegatedPolicyOverrides`／`appendDelegatedPolicyOverrides`）对 `sandboxPolicy.overrideOf(parent.session)` 获取快照；一次性驱动器与[可继续启动](2026-08-10-continuable-subagent-policy-inheritance.zh.md)都会调用这些辅助函数。父级后续的切换属于父级的未来；取消后重新委派会取得新快照。沙箱策略服务为可选，仅复制显式会话覆盖项，绝不复制部署默认值或一次性授权。审批策略不继承：同一次捕获会把每个子 agent 钉定为 `'never'`——[审批钉定决策](2026-08-10-subagent-approval-pinned-never.zh.md)取代了本 note 原先的审批覆盖项继承。

-每个捕获值都会成为子 agent 工厂在未发布设置阶段追加的一条带来源标记的 `sandbox/mode` 或 `approval/policy` 事件。会话构造函数已把 `Session.firstLiveSeq` 固定在 constructor seed 之后，而 `Session.inheritedEventCount` 保留精确的 fork 前缀长度，因此继承事实会排在 fork 历史之后，并在子 agent 公布时进入遥测，却不改变其谱系 cut。因此，既有的末事件胜出折叠会让委派快照压过陈旧的 fork 历史，并让子 agent 后续的切换压过该快照。孙代 agent 会折叠其父级已记录的状态，因此无需另一套继承机制即可组合此规则。
+每个捕获值都会成为子 agent 工厂在未发布设置阶段追加的一条带来源标记的 `sandbox/mode` 或 `approval/policy` 事件。会话构造函数已把 `Session.firstLiveSeq` 固定在 constructor seed 之后，而 `Session.inheritedEventCount` 保留精确的 fork 前缀长度，因此继承事实会排在 fork 历史之后，却不改变其谱系 cut。完整遥测捕获会包含已公布 child 的整份日志，其中既有 constructor seed，也有这些未发布设置事件。因此，既有的末事件胜出折叠会让委派快照压过陈旧的 fork 历史，并让子 agent 后续的切换压过该快照。孙代 agent 会折叠其父级已记录的状态，因此无需另一套继承机制即可组合此规则。

 普通的会话追加会在发布前校验继承事件，持久化层则在会话公布时捕获完整的未发布日志。因此，任何已物化的子 agent 日志都会在首批数据中存下继承事件；不存在第二套策略存储、schema 字段或查询索引。`source: 'delegation'` 标记让审批叙述能够区分继承与子 agent 侧的用户切换。

@@ -23,7 +23,7 @@ Status: implemented
 ## 考虑过的替代方案

 - **通用的 `SessionHeader` 策略字段**：不予采纳。它们会在元数据中复制一项事件溯源事实，并要求贯穿核心会话类型、持久化后端、查询索引、碰撞标识与每个策略消费方进行传播。未发布设置阶段的事件具备所需顺序，并复用现有持久化存储。
- **将新策略事实与构造历史合并**：不予采纳。`Session.firstLiveSeq` 会把完整的构造种子归类为回放历史，因此遥测会跳过仅属于子 agent 的事实。未发布设置让历史与新事实留在该边界各自原有的一侧，无需再增加会话选项。
+- **将新策略事实与构造历史合并**：不予采纳，因为这会把 child 拥有的委派策略归类为继承历史，并模糊 child 快照压过陈旧 fork 值所依赖的生命周期顺序。未发布设置让历史与新事实留在构造边界各自原有的一侧，无需再增加会话选项；遥测会捕获两侧。
 - **首个提示词监听器**：不予采纳。尽管创建事务已经允许在发布前追加日志，它仍会引入监听器顺序与更晚的时序边界。
 - **复制部署默认值**：不予采纳。默认值仍由运维人员拥有且可能变化；未切换的父级不会记录任何值，因此其子 agent 跟随当前部署。
 - **每次调用时沿 `parentSession` 实时解析**：不予采纳。这会打破「两个会话永远看不到彼此状态」的隔离不变量，要求父会话在子 agent 的整个生命周期内保持加载，还会让父级在子 agent 运行途中做的切换追溯性地改变一个正在运行的子 agent。委派时快照才是本设计的语义：子 agent 保持它被交付时的策略；取消后重新 spawn 即可拿到收紧后的策略。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-26-ptc-dispatch-ui-foundation.md
-2026-07-26-ptc-dispatch-ui-foundation.md: 793735a87b734429bfdcba91b0512ce264a8aa1f
-2026-07-26-ptc-dispatch-ui-foundation.zh.md: 68cd9c538d71db9f14e2bb4f8eae15049f0c9ad4
+2026-07-26-ptc-dispatch-ui-foundation.md: e44b67294a0c2c13809323b2aa42ec867bbcbbff
+2026-07-26-ptc-dispatch-ui-foundation.zh.md: 4b1ae0b3ebf35982449f5941d84361c530766534
@@ -28,4 +28,4 @@ Three changes, one per obstacle:

 ## Consequences

-Session format keeps `SESSION_FORMAT_VERSION` 0 (pre-release churn does not bump; old logs with `resultSummary` simply carry an extra unread field and lack `content` — v0 makes no compatibility promise). Existing ptc snapshot fixtures were re-recorded. Model-visible surface grew: the `run_code` schema (one required parameter) and every ptc system prompt/tool-schema snapshot changed. The web UI work builds directly on the new event payload; live per-sub-call running state reshaped this event into a dispatch start/end pair ([live parallel dispatch](2026-07-26-ptc-live-parallel-dispatch.md)).
+This UI change did not itself require a structural Session-format increment. The released v0 edge now freezes the accepted historical dispatch payloads and preserves them into v1; malformed mixtures refuse before publication. Existing ptc snapshot fixtures were re-recorded. Model-visible surface grew: the `run_code` schema (one required parameter) and every ptc system prompt/tool-schema snapshot changed. The web UI work builds directly on the new event payload; live per-sub-call running state reshaped this event into a dispatch start/end pair ([live parallel dispatch](2026-07-26-ptc-live-parallel-dispatch.md)).
@@ -28,4 +28,4 @@ Status: implemented

 ## 后果

-会话格式保持 `SESSION_FORMAT_VERSION` 为 0（预发布阶段的变动不递增版本号；携带 `resultSummary` 的旧日志只是多出一个不被读取的字段并缺少 `content`；v0 不作任何兼容性承诺）。既有的 PTC mode 快照 fixture（测试前置数据）已重新录制。模型可见范围扩大了：`run_code` 的 schema（新增一个必填参数）以及每一份 PTC mode 系统提示词／工具 schema 快照都发生了变化。Web UI 工作直接构建在新的事件载荷之上；每个子调用的实时运行状态已把本事件重塑为一对分发 start/end 事件（[实时并行分发](2026-07-26-ptc-live-parallel-dispatch.zh.md)）。
+该 UI 变更本身不要求结构性 Session 格式递增。已发布 v0 边现在冻结可接受的历史分发 payload 并将其保留到 v1；畸形混合结构会在发布前被拒绝。既有的 PTC mode 快照 fixture（测试前置数据）已重新录制。模型可见范围扩大了：`run_code` 的 schema（新增一个必填参数）以及每一份 PTC mode 系统提示词／工具 schema 快照都发生了变化。Web UI 工作直接构建在新的事件载荷之上；每个子调用的实时运行状态已把本事件重塑为一对分发 start/end 事件（[实时并行分发](2026-07-26-ptc-live-parallel-dispatch.zh.md)）。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-web-read-card.md
-2026-07-30-web-read-card.md: 73608391c6a8fff13f94423b07d141311fe06580
-2026-07-30-web-read-card.zh.md: 2914286c48520c3a13c5396bfddb5c10562d024f
+2026-07-30-web-read-card.md: 2023b93f44b343ce8482371b1168c8486fea703e
+2026-07-30-web-read-card.zh.md: 426b5cc1eb6050aeb87f8dcabd372ef6c2eb557e
@@ -16,7 +16,7 @@ Add a fourth `card` tag, `read`, to the [render-intent union](../architecture/20

 The read tool projects the structured window through `output.presentationMeta`, the same persisted channel write/edit use for their applied-diff hunks ([canonical tool output contract](../architecture/2026-07-20-canonical-tool-output-contract.md)). `presentationMeta` runs once for a top-level surface call, returns `{ path, offset, lines, totalLines, lang? }` as JSON the session validates and stores on the result's `meta`, and `presentResult` narrows that meta back into the `ReadResultView` on both live and replay paths. `offset` (the 1-based first line the window requested) rides along because a byte cap below the first selected line yields an empty `lines` array with a positive `totalLines`; without the persisted `offset` a replayed card of such a window could not report where it starts or where a continuation resumes, and the last-line and re-parse fallbacks are both lossy. Without this channel the line array and total would be unreachable: the raw output object is not on the wire, and re-parsing the `N: text` text is lossy and fragile against the truncation footer.

-`presentResult` returns `undefined` — the generic fallback — whenever the meta is absent or malformed (`readMetaFromMeta` narrows it defensively, so a replay of an older logged result never throws), whenever the result is an error, and whenever the single text block is not the read envelope. A pre-card logged result — a valid read envelope with no persisted `meta`, recorded before this card existed — takes that same `undefined` path deliberately: the client falls back to the raw `result.content`, so it shows the enveloped `<path>/<type>/<content>` text rather than the envelope-stripped generic card the old presenter returned. This is the accepted degradation under the [pre-release stance](../../../../AGENTS.md#pre-release-stance-foundation-over-blast-radius): reject the old on-disk format rather than add an envelope-stripping compatibility branch, since this change re-records every published fixture and the session format promises no backward compatibility. On the success path `presentResult` carries `content` (the envelope-stripped text) alongside the structured fields, so a UI without the read capability renders the file text through its generic/default card arm. The former TUI established the need for this fallback: its non-exhaustive result switch read `view.content`, while a separate dim-Markdown gate also had to admit `card: 'read'`. That frontend has since been removed, but the content fallback remains part of the view contract for any consumer without a structured read card.
+`presentResult` returns `undefined` — the generic fallback — whenever the meta is absent or malformed (`readMetaFromMeta` narrows it defensively, so a replay of an older logged result never throws), whenever the result is an error, and whenever the single text block is not the read envelope. A pre-card logged result — a valid read envelope with no persisted `meta`, recorded before this card existed — takes that same `undefined` path deliberately: the client falls back to the raw `result.content`, so it shows the enveloped `<path>/<type>/<content>` text rather than the envelope-stripped generic card the old presenter returned. This remains the accepted degradation: the presenter keeps its generic fallback instead of adding an envelope-stripping compatibility branch. The released Session edge preserves old logged bytes, and this change re-recorded every published fixture. On the success path `presentResult` carries `content` (the envelope-stripped text) alongside the structured fields, so a UI without the read capability renders the file text through its generic/default card arm. The former TUI established the need for this fallback: its non-exhaustive result switch read `view.content`, while a separate dim-Markdown gate also had to admit `card: 'read'`. That frontend has since been removed, but the content fallback remains part of the view contract for any consumer without a structured read card.

 ### Language hint derivation

@@ -16,7 +16,7 @@ Status: implemented

 read 工具通过 `output.presentationMeta` 投影结构化窗口，这与 write/edit 用来投影其应用 diff hunk 的持久化通道相同（[规范化工具输出约定](../architecture/2026-07-20-canonical-tool-output-contract.zh.md)）。`presentationMeta` 对一次顶层 surface 调用运行一次，返回 `{ path, offset, lines, totalLines, lang? }` 作为会话校验并存储在结果 `meta` 上的 JSON，`presentResult` 在实时和回放路径上都把该 meta 收窄回 `ReadResultView`。`offset`（窗口请求的 1-based 起始行）一并携带，是因为当字节上限低于首个选中行时，窗口会返回空的 `lines` 数组而 `totalLines` 为正；没有持久化的 `offset`，这类窗口的回放 card 就无法报告它从哪行开始、或续读应从哪行继续，而末行推断与文本重解析两种兜底都有损。没有这个通道，行数组和总数就无法触及：原始输出对象不在线上，而重新解析 `N: text` 文本既有损又对截断尾注脆弱。

-`presentResult` 在以下情况返回 `undefined`——即 generic 回退：meta 缺失或畸形（`readMetaFromMeta` 防御性收窄它，因此回放旧的已记录结果永不抛错）、结果是错误、以及单个文本块不是 read 信封。本 card 出现之前记录的结果——信封合法但无持久化 `meta`——有意走同一条 `undefined` 路径：客户端回退到原始 `result.content`，因此显示带 `<path>/<type>/<content>` 信封的原文，而非旧展示器返回的剥信封 generic card。这是 [pre-release 立场](../../../../AGENTS.md#pre-release-stance-foundation-over-blast-radius)下接受的降级：拒绝旧的磁盘格式，而非加一个剥信封的兼容分支——本变更已重录全部已发布 fixture（测试前置数据），且会话格式不承诺向后兼容。在成功路径上，`presentResult` 在结构化字段之外携带 `content`（剥信封后的文本），因此不具备 read 能力的 UI 会通过自己的 generic/default card 分支渲染文件文本。原 TUI 证明了这条回退的必要性：它的非穷尽结果 switch 读取 `view.content`，而另一道 dim-Markdown 门控也必须接纳 `card: 'read'`。该前端随后被移除，但对任何没有结构化 read 卡片的消费方而言，content 回退仍是视图约定的一部分。
+`presentResult` 在以下情况返回 `undefined`——即 generic 回退：meta 缺失或畸形（`readMetaFromMeta` 防御性收窄它，因此回放旧的已记录结果永不抛错）、结果是错误、以及单个文本块不是 read 信封。本 card 出现之前记录的结果——信封合法但无持久化 `meta`——有意走同一条 `undefined` 路径：客户端回退到原始 `result.content`，因此显示带 `<path>/<type>/<content>` 信封的原文，而非旧展示器返回的剥信封 generic card。这仍是已接受的降级：展示器保留 generic 回退，而不添加剥信封兼容分支。已发布 Session 边会保留旧日志字节，本变更也重录了全部已发布 fixture（测试前置数据）。在成功路径上，`presentResult` 在结构化字段之外携带 `content`（剥信封后的文本），因此不具备 read 能力的 UI 会通过自己的 generic/default card 分支渲染文件文本。原 TUI 证明了这条回退的必要性：它的非穷尽结果 switch 读取 `view.content`，而另一道 dim-Markdown 门控也必须接纳 `card: 'read'`。该前端随后被移除，但对任何没有结构化 read 卡片的消费方而言，content 回退仍是视图约定的一部分。

 ### 语言提示推导

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-context-form-vocabulary.md
-2026-08-05-context-form-vocabulary.md: be792256fa3375dd2621d647d6d3074b1a6d6b18
-2026-08-05-context-form-vocabulary.zh.md: f648dd1071128b879e8c36e9fba1646b6c70cda1
+2026-08-05-context-form-vocabulary.md: 12bb0132ad779d47b1090eb1d15d692032292524
+2026-08-05-context-form-vocabulary.zh.md: 899bef0892a9ec2d865d91e51869527afea40f9d
@@ -27,7 +27,7 @@ The vocabulary is semantic, never visual. A value states that the content is a f

 Entries record the published fact **unescaped**. The pseudo-XML escaping belongs to the `<available_skills>` frame, which exists for the model, so it is applied when rendering that frame and never stored; otherwise a consumer would have to know the frame's encoding to display a description containing `<`, and the same frame knowledge this decision removes would leak back in another shape. `escapeText` is deterministic and injective, so digesting the unescaped entries preserves republish semantics exactly, and the model-facing text stays byte-identical.

-That move also relocates catalog **identity**: the republish digest now covers the durable entries rather than the rendered text, so the model-facing framing can no longer decide whether a republish is needed, and the text-slicing that recovered entries from a logged message is gone. A resumed session whose newest catalog predates this change republishes once, which the pre-release stance permits. One case does not self-heal: if that old-format catalog is the only one and the current view has no skills, the plugin sees no published catalog and emits no tombstone, so the model keeps a stale catalog nothing replaces. The pre-release stance ("backends reject old on-disk formats") permits it; it is recorded here rather than left to the optimistic path.
+That move also relocates catalog **identity**: the republish digest now covers the durable entries rather than the rendered text, so the model-facing framing can no longer decide whether a republish is needed, and the text-slicing that recovered entries from a logged message is gone. The v0-to-v1 edge preserves an accepted older catalog payload, so a resumed session whose newest catalog predates this change republishes once. One case does not self-heal: if that old-form catalog is the only one and the current view has no skills, the plugin sees no published catalog and emits no tombstone, so the model keeps a stale catalog nothing replaces. This is the context feature's explicit degradation, not a Session-format refusal.

 **`snapshot`** — current state that a later snapshot from the same producer supersedes. The runtime-context snapshot, `time-context`, and `tmux-context` declare it. `renderContextSections()` exposes the assembly's named contributions, which `renderContextSnapshot()` already joined for the model, so the body attributes each part to the subsystem that produced it without re-splitting joined prose. The two single-contribution producers record one section each. The cleared runtime-context marker has no contributions left and declares no form.

@@ -27,7 +27,7 @@ Status: implemented

 条目记录的是**未转义**的发布事实。伪 XML 转义属于 `<available_skills>` 这层为模型而设的框架，因此只在渲染该框架时施加、从不存储；否则消费方要正确展示含 `<` 的描述就得知道框架的编码方式，本决策刚移除的框架知识会换一种形式泄漏回来。`escapeText` 确定且单射，故对未转义条目取 digest 与此前完全等价，重新发布语义不变，面向模型的文本逐字节不变。

-这次迁移同时挪动了目录的**身份**：重新发布用的 digest 现在覆盖持久条目而非渲染文本，于是面向模型的包装再也无法左右是否需要重新发布，那段从已记录消息里切出条目的文本切分逻辑也随之删除。若恢复的会话中最新目录早于本次改动，会重新发布一次——预发布立场允许这样做。有一种情形不会自愈：当那份旧格式目录是唯一的一份、且当前视图没有任何 skill 时，插件看不到已发布目录，也就不会发出 tombstone，模型手里会留着一份无人替换的陈旧目录。预发布立场（「后端拒绝旧的磁盘格式」）允许这一点；此处如实记录，而不是只写乐观路径。
+这次迁移同时挪动了目录的**身份**：重新发布用的 digest 现在覆盖持久条目而非渲染文本，于是面向模型的包装再也无法左右是否需要重新发布，那段从已记录消息里切出条目的文本切分逻辑也随之删除。v0-to-v1 迁移边会保留可接纳的旧目录 payload，因此恢复的 Session 若以本变更前的目录为最新目录，就会重新发布一次。有一种情形不会自愈：当那份旧结构目录是唯一的一份、且当前视图没有任何 skill 时，插件看不到已发布目录，也就不会发出 tombstone，模型手里会留着一份无人替换的陈旧目录。这是 context 功能的显式降级，不是 Session 格式拒绝。

 **`snapshot`**——会被同一生产方后续快照取代的当前状态。运行时快照、`time-context`、`tmux-context` 声明它。`renderContextSections()` 暴露出装配时的具名贡献——`renderContextSnapshot()` 本来就是把它们拼给模型的——因此内容区能把每一段归属到产生它的子系统，而不必去切分已经拼好的散文。两个单贡献生产方各记录一段。运行时快照的「已清空」标记没有任何贡献可归属，因此不声明形态。

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md
-2026-08-05-feedback-gated-session-telemetry.md: 9dab135029bd4a5dd209157b48b6f7dca4040224
-2026-08-05-feedback-gated-session-telemetry.zh.md: 824aa1a04f3854163fdd16f4db7a7593540976e0
+2026-08-05-feedback-gated-session-telemetry.md: ecca36703e3f85f67a68348f06f35deeacc33c2a
+2026-08-05-feedback-gated-session-telemetry.zh.md: 0f5f8c89223bdbce8fe5cbe838408b9634b45a68
@@ -16,7 +16,7 @@ Session telemetry originally has one mounted behavior: every accepted record ent
 - `FEEDBACK_ONLY` reads the canonical session log when `feedback/record` is appended and hands over the unreleased prefix through that exact event. Records appended after that boundary remain local until another feedback event.
 - `DISABLED` is the [default](2026-08-10-telemetry-default-off.md), constructs no exporter, processor, or logger provider, and prints that nothing is shared and the feedback remains local when it observes `feedback/record`.

-The generic telemetry coordinator owns `live` and `on-demand` capture. Live capture projects, clones, redacts, and hands each event to the backend on the session firehose. On-demand capture registers no continuous capture listeners; `captureSession(session, throughSeq)` reads the canonical log from the handoff cursor through an inclusive boundary, then projects, clones, redacts, and hands over that prefix. The cursor advances only for handed-over records. The [buffer-free replay decision](../simplification/2026-08-06-buffer-free-feedback-telemetry.md) owns why the on-demand path uses the canonical log instead of copied records.
+The generic telemetry coordinator owns `live` and `on-demand` capture. Live capture deep-copies, redacts, and hands every canonical event to the backend on the session firehose. On-demand capture registers no continuous capture listeners; `captureSession(session, throughSeq)` reads the canonical log after the same-object handoff cursor through an inclusive boundary, then deep-copies, redacts, and hands over every event in that prefix. A new Session object starts with cursor `-1`, so its first capture includes the complete constructor seed whether the object is fresh, forked, resumed, or restored after migration; re-adopting or recapturing the same object starts after its highest handed-off seq. The [buffer-free replay decision](../simplification/2026-08-06-buffer-free-feedback-telemetry.md) owns why the on-demand path uses the canonical log instead of copied records.

 Mode resolution is a closed, fail-before-setup check: an unknown direct-construction value fails before transport configuration is read. Only `FULL` exposes the public service's `emit()` path to the SDK pipeline. `FEEDBACK_ONLY` gives its on-demand coordinator a private backend capability; its listener passes an event to `captureSession()` only when `session.eventAt(event.seq)` returns that exact `feedback/record` object. `Session.append` commits that object before publishing `session/event`, so replay includes the feedback but cannot extend past its boundary. `DISABLED` creates neither the capability nor the SDK pipeline and does not inspect exporter configuration.

@@ -32,4 +32,4 @@ Mode resolution is a closed, fail-before-setup check: an unknown direct-construc

 ## Consequences

-`FULL` retains the original source and wire behavior as an explicit opt-in. `FEEDBACK_ONLY` adds no telemetry-owned per-event buffer before feedback; direct service calls and non-canonical feedback events upload nothing, and a crash before feedback uploads nothing from that prefix. Replay applies the redaction policy mounted when feedback is recorded and excludes operational records that do not exist in the canonical log. Feedback-only streams therefore carry neither `agent-error` nor `shutdown` records, and shutdown absence is not a crash signal. Each later feedback captures the suffix accumulated since the previous boundary. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log.
+`FULL` hands off every canonical event and replays the complete log of each new Session object as an explicit opt-in. `FEEDBACK_ONLY` adds no telemetry-owned per-event buffer before feedback; direct service calls and non-canonical feedback events upload nothing, and a crash before feedback uploads nothing unless a later Session object is restored and feedback releases its log. The first feedback on a new resumed or migrated object includes its complete current canonical prefix through that feedback; later feedback on the same object captures only the suffix after its cursor. Replay applies the redaction policy mounted when feedback is recorded and excludes operational records that do not exist in the canonical log, so feedback-only streams carry neither `agent-error` nor `shutdown` records and shutdown absence is not a crash signal. New-object replay and backend retries can duplicate ledger rows; receivers deduplicate on `(session.id, session.format_version, event.seq)`. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log.
@@ -16,7 +16,7 @@ Status: implemented
 - `FEEDBACK_ONLY` 在追加 `feedback/record` 时读取权威会话日志，并交接截至该事件的未释放前缀。该边界后追加的记录会留在本地，直到另一个反馈事件。
 - `DISABLED` 是[默认值](2026-08-10-telemetry-default-off.zh.md)，不构造导出器、处理器或日志提供方，并在观察到 `feedback/record` 时输出警告，说明什么都不会共享，且反馈仍留在本地。

-通用遥测协调器拥有 `live` 与 `on-demand` 捕获。实时捕获在会话 firehose 上投影、深拷贝、脱敏每个事件，并将其交给后端。按需捕获不注册持续捕获监听器；`captureSession(session, throughSeq)` 从 handoff 游标起读取权威日志，直至含边界的指定序列号，然后投影、深拷贝、脱敏并交接该前缀。游标只为已交接记录推进。[无缓冲回放决策](../simplification/2026-08-06-buffer-free-feedback-telemetry.zh.md)说明了按需路径为何使用权威日志而非记录副本。
+通用遥测协调器拥有 `live` 与 `on-demand` 捕获。实时捕获在会话 firehose 上深拷贝、脱敏并向后端交接每个权威事件。按需捕获不注册持续捕获监听器；`captureSession(session, throughSeq)` 从同一对象 handoff 游标之后读取权威日志，直至包含式边界，然后深拷贝、脱敏并交接该前缀中的每个事件。新 Session 对象以游标 `-1` 开始，因此无论对象是全新、fork、resume 还是迁移后恢复，其首次捕获都会包含完整构造 seed；重新收养或再次捕获同一对象时，则从其已交接的最高 seq 之后开始。[无缓冲回放决策](../simplification/2026-08-06-buffer-free-feedback-telemetry.zh.md)说明了按需路径为何使用权威日志而非记录副本。

 模式解析采用封闭式检查，并在设置前失败：通过直接构造传入未知值时，会在读取传输配置前失败。只有 `FULL` 向 SDK 流水线开放公共服务的 `emit()` 路径。`FEEDBACK_ONLY` 向其按需协调器提供私有后端能力；其监听器向 `captureSession()` 传递事件的唯一条件，是 `session.eventAt(event.seq)` 返回完全相同的 `feedback/record` 对象。`Session.append` 在发布 `session/event` 前已提交该对象，因此回放包含该反馈，但不会越过其边界。`DISABLED` 既不创建该能力，也不创建 SDK 流水线，并且不检查导出器配置。

@@ -32,4 +32,4 @@ Status: implemented

 ## 后果

-`FULL` 作为显式启用模式保留原有的源码与协议行为。`FEEDBACK_ONLY` 在反馈前不增加遥测自有的逐事件缓冲；直接服务调用与非权威反馈事件均不上传任何内容，且反馈前发生崩溃时，该前缀也不上传任何内容。回放使用记录反馈时挂载的脱敏策略，并排除权威日志中不存在的运维记录。因此，仅反馈的流既不携带 `agent-error` 记录，也不携带 `shutdown` 记录，而缺少 shutdown 不是崩溃信号。每个后续反馈都会捕获从上一个边界起累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。
+`FULL` 作为显式启用模式交接每个权威事件，并回放每个新 Session 对象的完整日志。`FEEDBACK_ONLY` 在反馈前不增加遥测自有的逐事件缓冲；直接服务调用与非权威反馈事件均不上传任何内容，反馈前发生崩溃时也不上传该前缀，除非后续恢复出新的 Session 对象并由反馈释放其日志。新的 resume 或迁移对象上的首次反馈会包含截至该反馈的完整当前权威前缀；同一对象上的后续反馈只捕获游标之后的后缀。回放使用记录反馈时挂载的脱敏策略，并排除权威日志中不存在的运维记录，因此仅反馈的流既不携带 `agent-error` 也不携带 `shutdown`，且缺少 shutdown 不是崩溃信号。新对象回放与后端重试可能重复 ledger 行；接收端基于 `(session.id, session.format_version, event.seq)` 去重。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-web-session-log-export.md
-2026-08-10-web-session-log-export.md: df80ad4d264d835b2c11973ca61cf143576f11f3
-2026-08-10-web-session-log-export.zh.md: 2af86f371f9e7ed5255bb4e57a8a43427c745fe0
+2026-08-10-web-session-log-export.md: df54c0b042de14c94e78d22e066bc61a1768c76f
+2026-08-10-web-session-log-export.zh.md: 4ed9d3839dece876a45a9af18ef3bc4609f8e3a9
@@ -10,7 +10,7 @@ The Trajectory view had no way to hand a debugging artifact to a human: the raw

 ## Decision

- **The export is a host-only download, not an RPC**: `GET /api/session.export?sessionId=…&includeDescendants=true` streams one ZIP attachment. Every file is a session's **stored artifact text verbatim**: `readRaw` on the persistence service reads the backend's own durable bytes (the JSONL backend decodes its physical zstd frames, or returns plaintext) — never a reconstruction from parsed events, so packed-chunk rows, key order, and line breaks survive byte-for-byte — under its original base name (`session.jsonl` at the root, `subagents/<id>/session.jsonl` for descendants). Compression runs on the host with fflate's streaming `Zip`/`ZipDeflate` API at validated `sessionExportCompressionLevel` 0–9 (default 6), letting deployments trade CPU and latency against archive size; each entry is deflated in bounded chunks as it is produced, so the response is chunked as it is generated and the host never holds the whole archive in one buffer (at most one descendant's artifact text beyond the preloaded root). At the 64 KiB response byte high-water mark, production waits for consumer pull to restore capacity; fflate's synchronous callback can add at most one bounded input push beyond that queue bound. No manifest is written — every file is byte-identical to the durable artifact and self-describing through its own header line.
+- **The export is a host-only download, not an RPC**: `GET /api/session.export?sessionId=…&includeDescendants=true` streams one ZIP attachment. Every file is a Session's **selected generation text verbatim**: `readRaw` on the persistence service reads the backend's numerically highest canonical generation after any required migration (the JSONL backend decodes its physical zstd frames, or returns plaintext) — never a reconstruction from parsed events, so packed-chunk rows, key order, and line breaks survive byte-for-byte — under the backend-reported logical basename. The root entry is `session.jsonl` for v0 or `session.vN.jsonl` for a positive generation; descendants use `subagents/<id>/<filename>`. Compression runs on the host with fflate's streaming `Zip`/`ZipDeflate` API at validated `sessionExportCompressionLevel` 0–9 (default 6), letting deployments trade CPU and latency against archive size; each entry is deflated in bounded chunks as it is produced, so the response is chunked as it is generated and the host never holds the whole archive in one buffer (at most one descendant's artifact text beyond the preloaded root). At the 64 KiB response byte high-water mark, production waits for consumer pull to restore capacity; fflate's synchronous callback can add at most one bounded input push beyond that queue bound. No manifest is written — every file is byte-identical to the selected durable generation and self-describing through its own header line.
 - **Error vocabulary is HTTP-native**: missing services → 500, a backend without per-session raw artifacts → 501, missing root session → 404 (all decided before any byte streams), and a descendant without a stored artifact → the stream errors (fail-loud, never silent under-export). Request abort remains cancellation instead of being rewritten as 500; request and response-consumer cancellation converge on the producer signal, which reaches lineage, persistence, and attachment reads and terminates the active compressor. Connection applies the `/api` trust fence before dispatching the exact `GET`/`HEAD /api/session.export` route registered by `session-log-export`.
 - **The UI just downloads**: browser consumers may issue a bodyless `HEAD` preflight for preparation errors, then hand the GET endpoint to the browser's native download manager, so JavaScript never buffers the ZIP. The `session.log` RPC that an earlier iteration shipped was removed — the download endpoint is its only consumer, and the repo rule is no public interface without a current owner. The client bundle carries no archive implementation.
 - The current Header and `/export` consumers are defined by the [session-log export package contract](../../../../packages/session-query/session-log-export/README.md).
@@ -10,7 +10,7 @@ Trajectory 视图没有任何方式把调试工件交到人手里：原始会话

 ## 决策

- **导出是宿主侧的下载面，不是 RPC**：`GET /api/session.export?sessionId=…&includeDescendants=true` 流式返回一个 ZIP 附件。每个文件都是会话**存储工件的逐字原文**：持久化服务新增的 `readRaw` 读取后端自己的持久化字节（jsonl 后端解码其物理 zstd 帧，或直接返回明文）——绝非从解析后事件重建，因此 chunk 打包、键序、换行全部逐字节保留——放在其原始基础文件名下（根为 `session.jsonl`，子代理为 `subagents/<id>/session.jsonl`）。压缩在宿主侧使用 fflate 流式 `Zip`/`ZipDeflate` API 和已验证的 `sessionExportCompressionLevel` 0–9（默认 6），使部署可以在 CPU／延迟与归档大小之间取舍；每个条目按有界分块边产出边压缩，响应随生成分块写出，宿主从不把整个归档放进单个缓冲区（除预载的根外，最多同时持有一条后代的工件文本）。到达 64 KiB 响应字节高水位后，生产会等待 Consumer pull 恢复容量；fflate 的同步回调最多只会在该队列界限外再增加一次有界输入 push。不写清单——每个文件都与持久化工件逐字节一致，并通过自身 header 行自描述。
+- **导出是宿主侧的下载面，不是 RPC**：`GET /api/session.export?sessionId=…&includeDescendants=true` 流式返回一个 ZIP 附件。每个文件都是 Session **选定 generation 的逐字原文**：持久化服务的 `readRaw` 会在完成所需迁移后读取后端数值最高的规范 generation（JSONL 后端解码其物理 zstd frame，或直接返回明文）——绝非从解析后事件重建，因此 chunk 打包、key 顺序与换行全部逐字节保留——并使用后端报告的逻辑 basename。根条目在 v0 下为 `session.jsonl`，正 generation 下为 `session.vN.jsonl`；后代使用 `subagents/<id>/<filename>`。压缩在宿主侧使用 fflate 流式 `Zip`/`ZipDeflate` API 和已验证的 `sessionExportCompressionLevel` 0–9（默认 6），使部署可以在 CPU／延迟与 archive 大小之间取舍；每个条目按有界分块边产出边压缩，响应随生成分块写出，宿主从不把整个 archive 放进单个 buffer（除预载的根外，最多同时持有一条后代的工件文本）。到达 64 KiB 响应字节高水位后，生产会等待 consumer pull 恢复容量；fflate 的同步回调最多只会在该队列界限外再增加一次有界输入 push。不写 manifest：每个文件都与选定持久 generation 逐字节一致，并通过自身 header 行自描述。
 - **错误词汇是 HTTP 原生的**：服务缺失 → 500，后端不提供每会话原始工件 → 501，根会话缺失 → 404（三者都在任何字节流出前判定），后代缺少存储工件 → 流失败（fail-loud，绝不静默少导出）。请求中止会保持取消语义而不会改写成 500；请求取消与响应 consumer 取消汇合到生产者 signal，该 signal 会传到血缘、持久化与附件读取，并终止活跃压缩器。Connection 在分发 `session-log-export` 注册的精确 `GET`/`HEAD /api/session.export` 路由前应用 `/api` 信任围栏。
 - **UI 只负责下载**：浏览器 Consumer 可以先发出不读取 body 的 `HEAD` 预检以取得准备阶段错误，再把 GET 端点交给浏览器原生下载管理器，因此 JavaScript 不会缓冲 ZIP。早先迭代发布的 `session.log` RPC 已删除——下载端点是它唯一的消费者，仓库规则是不留无当前所有者的公共接口。客户端 bundle 不包含任何归档实现。
 - 当前 Header 与 `/export` Consumer 由 [Session 日志导出包约定](../../../../packages/session-query/session-log-export/README.zh.md)定义。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-25-feedback-gated-telemetry-default.md
-2026-08-25-feedback-gated-telemetry-default.md: 772d134da53386292083790148dce738a98f2c0f
-2026-08-25-feedback-gated-telemetry-default.zh.md: ea05d4d687bc2270f907983a71f592b880d7449c
+2026-08-25-feedback-gated-telemetry-default.md: 35d79384094ff26a5d9169da9268c264e73a63d4
+2026-08-25-feedback-gated-telemetry-default.zh.md: 28268d6dda5fd734250080c203482b423a752c8e
@@ -10,7 +10,7 @@ Diagnosing a `/feedback` report needs the session data the report describes. Wit

 ## Decision

-The shared dsh base resolves an unset or empty `DSH_TELEMETRY_MODE` to `FEEDBACK_ONLY` instead of `DISABLED`. Nothing is uploaded before the user records `/feedback`; each recorded feedback uploads the not-yet-shared session-log records — from the last handoff through that exact event — to the configured OTLP endpoint, a resumed session shares only its current lifecycle, and the acknowledgement's sharing disclosure states that recording feedback uploads the records not yet shared. `FULL` and `DISABLED` remain explicit `DSH_TELEMETRY_MODE` overrides, any non-empty `DSH_TELEMETRY_DISABLED` remains the authoritative pre-load hard opt-out, and the plugin's own omitted-`mode` default stays `DISABLED`: the default changes only in the shared base's config expression, where deployments already override it.
+The shared dsh base resolves an unset or empty `DSH_TELEMETRY_MODE` to `FEEDBACK_ONLY` instead of `DISABLED`. Nothing is uploaded before the user records `/feedback`. On a Session object already captured, each feedback uploads the suffix after the last handoff through that exact event; a newly constructed fresh, forked, resumed, or migrated object has no cursor, so its first feedback uploads the complete current canonical prefix from seq 0. The acknowledgement's sharing disclosure states that recording feedback releases the session prefix. `FULL` and `DISABLED` remain explicit `DSH_TELEMETRY_MODE` overrides, any non-empty `DSH_TELEMETRY_DISABLED` remains the authoritative pre-load hard opt-out, and the plugin's own omitted-`mode` default stays `DISABLED`: the default changes only in the shared base's config expression, where deployments already override it.

 This supersedes the session-backend default of the [default-off decision](2026-08-10-telemetry-default-off.md), accepting the user's explicit feedback action as the release authorization that note required a deployment setting for. That note's hard opt-out and its launcher-feed history remain current, and the [default-mount decision](2026-07-31-web-telemetry-default-mount.md) continues to own the endpoint, batching cadence, and exit-drain settings.

@@ -10,7 +10,7 @@ Status: implemented

 ## 决定

-共享 dsh 基础配置把未设置或为空的 `DSH_TELEMETRY_MODE` 解析为 `FEEDBACK_ONLY` 而不是 `DISABLED`。用户记录 `/feedback` 之前不上传任何数据；每条已记录的反馈把尚未共享的会话日志记录——自上次交接至该事件为止——上传到已配置的 OTLP 端点，恢复的会话只共享当前生命周期，确认信息中的共享声明会说明记录反馈将上传尚未共享的记录。`FULL` 和 `DISABLED` 仍是显式的 `DSH_TELEMETRY_MODE` 覆盖值，任何非空的 `DSH_TELEMETRY_DISABLED` 仍是加载前的强制关闭开关，插件自身省略 `mode` 的默认值仍是 `DISABLED`：默认值只在共享基础配置的配置表达式中改变，部署本来就在那里覆盖它。
+共享 dsh 基础配置把未设置或为空的 `DSH_TELEMETRY_MODE` 解析为 `FEEDBACK_ONLY` 而不是 `DISABLED`。用户记录 `/feedback` 之前不上传任何数据。对于已经捕获的 Session 对象，每条反馈会上传从上次交接之后至该事件的后缀；新构造的全新、fork、resume 或迁移对象没有游标，因此其首次反馈会从 seq 0 上传完整当前权威前缀。确认信息中的共享声明会说明记录反馈将释放会话前缀。`FULL` 和 `DISABLED` 仍是显式的 `DSH_TELEMETRY_MODE` 覆盖值，任何非空的 `DSH_TELEMETRY_DISABLED` 仍是加载前的强制关闭开关，插件自身省略 `mode` 的默认值仍是 `DISABLED`：默认值只在共享基础配置的配置表达式中改变，部署本来就在那里覆盖它。

 本决定取代[默认关闭决定](2026-08-10-telemetry-default-off.zh.md)中会话后端的默认值，把用户显式的反馈动作接受为该决定原本要求由部署设置提供的释放授权。该决定的强制关闭开关和 launcher 上报历史仍然有效，端点、批处理节奏和退出排空设置仍由[默认挂载决定](2026-07-31-web-telemetry-default-mount.zh.md)持有。

@@ -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/2026-06-20-collapse-trace-only-session-events.md
-2026-06-20-collapse-trace-only-session-events.md: a7a4ab3a2e4c008b59bc4cb1023e699c6fd8a76b
-2026-06-20-collapse-trace-only-session-events.zh.md: 3b37f55795aa76fbdc5193e751f518c713483ccb
+2026-06-20-collapse-trace-only-session-events.md: e7c40cbde6dd666542bb4022064a1be97b0e0ce8
+2026-06-20-collapse-trace-only-session-events.zh.md: b2c062fc8138a120da9467250b50772083adca75
@@ -27,7 +27,7 @@ The user conversation log contains what is needed to render, resume, audit, and

 ## Verification

-`SessionEventMap` carries no standalone `usage` or `error`; the loop appends no separate usage event and records durable failures through `turn/end { kind: 'error', step, message, code? }`; ACP snapshots and persistence tests assert no trace-only lines; recorded fixtures are on the new event shape with the session format version pinned at `0` (backends reject any non-`0` stored log per the pre-release format policy); and the docs state where token usage and operational errors are observed.
+`SessionEventMap` carries no standalone `usage` or `error`; the loop appends no separate usage event and records durable failures through `turn/end { kind: 'error', step, message, code? }`; ACP snapshots and persistence tests assert no trace-only lines; the frozen v0 codec and identity migration preserve this released representation into current v1; and the docs state where token usage and operational errors are observed.

 ## Consequences

@@ -35,6 +35,6 @@ A consumer can no longer filter the canonical log for standalone `usage` or step

 ## Implementation note

-**Format version.** This changes persisted events, but the pre-release session format remains pinned at `0` and rejects any other version without migration. `dsh-session` owns the constant used by writers and load validation. Monotonic format versions begin at the first release.
+**Format version.** This event simplification predates the released v0 baseline. `dsh-session` owns the current writer constant, while the static catalog and adjacent packages now own supported historical decoding and migration. The identity v0-to-v1 edge proves that lifecycle without changing this event representation.

 Usage is now observed on `assistant/message.usage`; an operational error's step on `turn/end.reason` for `kind: 'error'`. `agent/error` + logging are unchanged for live diagnostics.
@@ -27,7 +27,7 @@ Status: implemented

 ## 验证

-`SessionEventMap` 不再包含独立的 `usage` 或 `error`；agent loop（智能体循环）不再追加独立的 usage 事件，并通过 `turn/end { kind: 'error', step, message, code? }` 持久记录失败；ACP 快照和持久化测试断言不存在仅用于追踪的行；已录制的 fixture（测试前置数据）使用新事件形状，会话格式版本固定为 `0`（后端按预发布格式策略拒绝任何版本非 `0` 的已存储日志）；文档说明了 token 用量和运行错误的观测位置。
+`SessionEventMap` 不再包含独立的 `usage` 或 `error`；agent loop（智能体循环）不再追加独立的 usage 事件，并通过 `turn/end { kind: 'error', step, message, code? }` 持久记录失败；ACP 快照和持久化测试断言不存在仅用于追踪的行；冻结的 v0 codec 与恒等迁移会把该已发布表示保留到当前 v1；文档说明了 token 用量和运行错误的观测位置。

 ## 后果

@@ -35,6 +35,6 @@ Status: implemented

 ## 实现说明

-**格式版本。** 此变更影响已持久化的事件，但预发布会话格式仍固定为 `0`，拒绝任何其他版本且不做迁移。`dsh-session` 拥有写入方和加载校验使用的常量。单调递增的格式版本从首次正式发布开始。
+**格式版本。** 该事件简化早于已发布 v0 基线。`dsh-session` 拥有当前写入方常量，静态目录与相邻包则拥有受支持历史版本的解码和迁移。恒等的 v0-to-v1 边在不改变该事件表示的情况下证明整套生命周期。

 Usage 现在通过 `assistant/message.usage` 观测；运行错误的步骤编号通过 `turn/end.reason`（当 `kind: 'error'` 时）观测。`agent/error` 与日志用于实时诊断，保持不变。
@@ -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/2026-07-12-simplify-session-log-representation.md
-2026-07-12-simplify-session-log-representation.md: 749d0da1774d74586988cbac39e32dd783b79af4
-2026-07-12-simplify-session-log-representation.zh.md: 5f320ab7d768aa682f54c3d42f67aef50c60ad7a
+2026-07-12-simplify-session-log-representation.md: 9c8383d72b16ccd430a094515cbfd7227b222363
+2026-07-12-simplify-session-log-representation.zh.md: c77f97c3a5f3011cf76ee493ce97d2354a634428