Merge remote-tracking branch 'origin/master' into dshw/pr-deepseek-harness-deepseek-harness-2672

# Conflicts:
#	docs/event-producer-consumer.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/event-producer-consumer.zh.md
#	docs/module-graph.i18n.yaml
#	docs/module-graph.md
#	docs/module-graph.zh.md
#	packages/api/session-controller/README.i18n.yaml
#	packages/api/session-controller/README.md
#	packages/api/session-controller/README.zh.md
#	packages/api/session-controller/tests/session-projections.host.spec.ts
#	packages/bundle/headless/tests/headless.spec.ts
#	packages/core/agent-loop/README.i18n.yaml
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/README.zh.md
#	packages/core/agent/src/runtime-types.ts
#	packages/fs/tool-str-replace-editor/tests/tools.spec.ts
#	packages/llm/llm-retry/tests/retry.spec.ts
#	packages/llm/llm-retry/tests/transport-recovery.spec.ts
#	packages/shell/tool-bash-persistent/tests/loader-composition.spec.ts
#	packages/shell/tool-bash-persistent/tests/tools.spec.ts
#	packages/shell/tool-pwsh-persistent/tests/loader-composition.spec.ts
#	packages/shell/tool-pwsh-persistent/tests/tools.spec.ts
#	packages/terminal/terminal-bash/tests/index.spec.ts
#	packages/test-support/agent-loop-testkit/package.json

.agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.md
+2026-07-26-packed-chunk-rows-by-default.md: c230c1f1faf5e597321654ebd01d60fae725f518
+2026-07-26-packed-chunk-rows-by-default.zh.md: e354efdf6bb68c02f30dc17c8d4ba17a495b61bd

.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md → .agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.md

@@ -1,6 +1,7 @@
 # Agent Note: Make packed chunk rows the default JSONL layout
 
 Status: implemented
+Archived: 2026-09-01
 
 English | [中文](2026-07-26-packed-chunk-rows-by-default.zh.md)
 

.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md → .agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md

@@ -1,6 +1,7 @@
 # Agent Note: 将打包分片行设为默认 JSONL 布局
 
 Status: implemented
+Archived: 2026-09-01
 
 [English](2026-07-26-packed-chunk-rows-by-default.md) | 中文
 

.agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.md
+2026-08-15-packed-session-history-transport.md: 1fe8c78a89a0541475d10fae9ad643203f144c30
+2026-08-15-packed-session-history-transport.zh.md: b2aa5bf0bc0bc4952df29674f0b9ffe836368f73

.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md → .agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.md

@@ -1,6 +1,7 @@
 # Agent Note: Carry packed chunk rows through session history
 
 Status: implemented
+Archived: 2026-09-01
 
 English | [中文](2026-08-15-packed-session-history-transport.zh.md)
 

.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.zh.md → .agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.zh.md

@@ -1,6 +1,7 @@
 # Agent Note: 在会话历史中传输打包分片行
 
 Status: implemented
+Archived: 2026-09-01
 
 [English](2026-08-15-packed-session-history-transport.md) | 中文
 

.agents/notes/archived/manifest.json

@@ -40,6 +40,9 @@
     "architecture/2026-07-24-dsh-commander-argument-adapter.i18n.yaml": "sha256:cf99eda0e58b49630d5f95792459d7095666fafbef61f614165d5cdd031b7118",
     "architecture/2026-07-24-dsh-commander-argument-adapter.md": "sha256:705654c8a43bcd199f72c21a77d24ca8bfa02447aff1c7f3e4e820be61dcd562",
     "architecture/2026-07-24-dsh-commander-argument-adapter.zh.md": "sha256:3844f02d7659d18caf5d39e1131ed775c789cbf92dc44b4a446c7d6468aa5d00",
+    "architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml": "sha256:41aa86c65f78e125ca2178295d02d5994d5e0f2e9359b1465777db1aba4a105b",
+    "architecture/2026-07-26-packed-chunk-rows-by-default.md": "sha256:2b4e14675d12a1fc07eb373ab8566c3e63c7c15e2b5a0b391e6acbc896c7359d",
+    "architecture/2026-07-26-packed-chunk-rows-by-default.zh.md": "sha256:e0b0e8a4ab529a3461c22f434cbbe1e7b0ea381592871caf7e3fe5157ef844ba",
     "architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml": "sha256:7b9dbe8b4a340640610abe7e54fb29492d77a187c176996a53d0e1fc7c8e1945",
     "architecture/2026-07-27-tui-chat-channel-module-split.md": "sha256:3e2cd43f306a18b3eaf9bac23e6bdc3a5dbdc7388b7c399ce71e4f71b8f71d2a",
     "architecture/2026-07-27-tui-chat-channel-module-split.zh.md": "sha256:d6b84fdcd91a2693b72cf6884b3a0c39e56e571b2b694f630805d894a6ba292f",
@@ -55,6 +58,9 @@
     "architecture/2026-08-11-plugin-settings-tabs.i18n.yaml": "sha256:0365da2b317fc5f94dd190064198565f4c624afc91d2e62161ab9170f79d11bc",
     "architecture/2026-08-11-plugin-settings-tabs.md": "sha256:fdd92cfe55b6c4cd31b3f768dd46a2ecf129a04c9818249cbdd33857cf722bbf",
     "architecture/2026-08-11-plugin-settings-tabs.zh.md": "sha256:8993df1a0178aba1ea35c460ee67c522900344a4b386287bba9dfac2bfb87efa",
+    "architecture/2026-08-15-packed-session-history-transport.i18n.yaml": "sha256:547b89497b009593db5acfae2a3b989f17b8392f5df73ef631b38f8f68f629f1",
+    "architecture/2026-08-15-packed-session-history-transport.md": "sha256:ec7f84d59eea95668a8cb6c92ae433a2b7e7b76446a27e57dd5dba05856f563f",
+    "architecture/2026-08-15-packed-session-history-transport.zh.md": "sha256:0d8eb5444557a18f76c68ce5ae9f0779c580eaddb921ee8651464baea34e0e53",
     "architecture/2026-08-18-sqlite-physical-chunk-row-compression.i18n.yaml": "sha256:42bce930799cb511e9fb245dec5e26efd78bdab4c9b75f7393e37b40fbee4d10",
     "architecture/2026-08-18-sqlite-physical-chunk-row-compression.md": "sha256:4fe241f1b272278d9f3ca1a4431971220e1fa54411df043826ef6f59225bf949",
     "architecture/2026-08-18-sqlite-physical-chunk-row-compression.zh.md": "sha256:73178c9ec5abf571680d8facfb145cbadc1efbb2e67e3f039747c2f9cf4bb730",
@@ -391,6 +397,9 @@
     "process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml": "sha256:dde0041399b253e3758045f0858488db8178ffc563ce889c8b396c87af6c3730",
     "process/2026-08-12-documentation-site-navigation-and-chrome.md": "sha256:56cb836ed862378afd33eb5c1a9dc159958b35a0aed3bf4336fcf26ab0b84b8b",
     "process/2026-08-12-documentation-site-navigation-and-chrome.zh.md": "sha256:f2dd4adde38a09fe312866a1e6dad0f465684d809287862f40f1a488acd4fe18",
+    "process/2026-08-31-pr-opened-issue-start-dates.i18n.yaml": "sha256:c522daca5e126bf64227d6259f447648a589831125113dcf49814817d4b28f17",
+    "process/2026-08-31-pr-opened-issue-start-dates.md": "sha256:749f343576006b0d4950b9c67f434cea0bb9ae21a5fd8d74fefe77b59289ffbf",
+    "process/2026-08-31-pr-opened-issue-start-dates.zh.md": "sha256:a227dc6cba6e62d08a15b1c6b69b5941297c2d10035d257d6f3bc95d6ea54591",
     "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml": "sha256:ad3d1263cb0051b885173bf064de62065e2c646ccaae2d7250723da3b4eab90c",
     "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md": "sha256:8fb061d51c8c23b47d2367814bab3623c6d5b972f38d207a273caa9030b579bd",
     "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md": "sha256:2ffeaca91f82844a5616d6dcce6b4af514bb8a7c46f78e47f668b204ac6edc04",

.agents/notes/implemented/process/2026-08-31-pr-opened-issue-start-dates.i18n.yaml → .agents/notes/archived/process/2026-08-31-pr-opened-issue-start-dates.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-31-pr-opened-issue-start-dates.md
-2026-08-31-pr-opened-issue-start-dates.md: f8976b8b0499aa5c68c9637e8571805b78ce6d48
-2026-08-31-pr-opened-issue-start-dates.zh.md: 3142bad5007cbbdd27e1f564bc3ccec9101d3d79
+2026-08-31-pr-opened-issue-start-dates.md: f17e1bf0dcfdc541952312d1b504bdaa2e2817cc
+2026-08-31-pr-opened-issue-start-dates.zh.md: 3aab8f5528ad125210fbb3839fd334d99ad49bb0

.agents/notes/implemented/process/2026-08-31-pr-opened-issue-start-dates.md → .agents/notes/archived/process/2026-08-31-pr-opened-issue-start-dates.md

@@ -1,31 +1,34 @@
 # Agent Note: PR-opened Issue start dates
 
 Status: implemented
+Archived: 2026-09-02
 
 English | [中文](2026-08-31-pr-opened-issue-start-dates.zh.md)
 
 ## Problem
 
-The Issue Project records planned work in a `Start date` field, but adding or linking an Issue does not provide a date value. A pull request can identify both Issues it resolves and Issues that supply related implementation context, and either relationship marks the start of repository work.
+The organization-level `Start date` Issue field records when work begins, but adding an Issue to the Issue Project or linking it from a pull request does not provide a date value. A pull request can identify both Issues it resolves and Issues that supply related implementation context, and either relationship marks the start of repository work.
 
 Updating the field on every pull-request event would assign dates to existing work after edits, pushes, or reopenings. Replacing an existing date would also discard a manually planned date or a date recorded by an earlier pull request.
 
 ## Decision
 
-The Issue lifecycle workflow initializes `Start date` only for `pull_request.opened`. It reads the pull request's live body, retains every same-repository reference that resolves to an Issue, converts `created_at` to a calendar date in the configured Project time zone, ensures the Issue is a Project item, and writes the configured Date field only when the current value is empty.
+The Issue lifecycle workflow initializes `Start date` only for `pull_request.opened`. It reads the pull request's live body, retains every same-repository reference that resolves to an Issue, converts `created_at` to a calendar date in the configured Project time zone, ensures the Issue is a Project item, and writes the configured organization Issue Date field only when the current value is empty.
 
-The configuration names the Project field and time zone. Missing configuration fails when the policy module loads; a missing field, a non-Date field, an invalid timestamp, or a failed API request fails the workflow at the first relevant pull request.
+The configuration names the field exposed in the Project and the time zone. The Project field must resolve to an organization Issue Date field; the workflow reads its Issue value and updates it through `updateIssueFieldValue`. Missing configuration fails when the policy module loads; a missing field, a non-Date or Project-local field, an invalid timestamp, or a failed API request fails the workflow at the first relevant pull request.
 
 [Event-directed PR review status commands](2026-08-10-event-directed-pr-review-status.md) continue to own Status transitions. Date initialization includes resolving and informational Issue references, runs for Draft and automated pull requests, and does not depend on PR policy enforcement.
 
 ## Verification
 
-[Issue-management tests](../../../../.github/issue-management/policy.test.mjs) cover the Shanghai date boundary, opened-only dispatch, all retained Issue references, empty-value writes, existing-value preservation, missing Project items, invalid field configuration, and the GraphQL mutation variables. [Workflow tests](../../../../scripts/ci-workflow.spec.ts) require the `pull_request.opened` subscription.
+[Issue-management tests](../../../../.github/issue-management/policy.test.mjs) cover the Shanghai date boundary, opened-only dispatch, all retained Issue references, Issue-field discovery, empty-value writes, existing-value preservation, missing Project items, invalid field configuration, and the `updateIssueFieldValue` variables. [Workflow tests](../../../../scripts/ci-workflow.spec.ts) require the `pull_request.opened` subscription.
 
 ## Alternatives considered
 
 **Use a built-in Project workflow.** The built-in workflows own fixed Project item and Status transitions; the repository workflow already owns authenticated GraphQL mutations and can supply the PR creation date.
 
+**Use a Project-local Date field.** A Project field would allow different dates for the same Issue in different Projects and would not appear on the Issue itself. Work begins for the Issue rather than for one Project membership, so the organization Issue field owns the value.
+
 **Process every subscribed PR event or run a reconciler.** Later events would fill dates for existing pull requests and references added after creation, but they would make the field a repair projection instead of a record created with the pull request and would add repeated Project reads.
 
 **Update only resolving Issue references.** Informational references also identify Issues whose implementation work begins with the pull request, so the date initializer uses the existing all-reference set while Status transitions retain resolving-only semantics.
@@ -34,6 +37,6 @@ The configuration names the Project field and time zone. Missing configuration f
 
 ## Consequences
 
-Only pull requests opened after the workflow ships initialize dates. References added after creation and existing open pull requests remain unchanged, and the workflow does not scan existing Project items or pull requests.
+Only pull requests opened after the workflow ships initialize dates. References added after creation and existing open pull requests remain unchanged, and the workflow does not scan existing Project items or pull requests. The date follows the Issue across organization Projects that expose the field.
 
-The empty-value read makes retries idempotent in ordinary operation. ProjectV2 has no conditional field update, so simultaneous pull requests that reference the same empty Issue can both write; per-PR concurrency does not serialize that Issue, and the last mutation can win.
+The empty-value read makes retries idempotent in ordinary operation. The Issue-field mutation has no compare-and-set precondition, so simultaneous pull requests that reference the same empty Issue can both write; per-PR concurrency does not serialize that Issue, and the last mutation can win.

.agents/notes/implemented/process/2026-08-31-pr-opened-issue-start-dates.zh.md → .agents/notes/archived/process/2026-08-31-pr-opened-issue-start-dates.zh.md

@@ -1,31 +1,34 @@
 # Agent Note: 在 PR 创建时设置 Issue 开始日期
 
 Status: implemented
+Archived: 2026-09-02
 
 [English](2026-08-31-pr-opened-issue-start-dates.md) | 中文
 
 ## 问题
 
-Issue Project 使用 `Start date` 字段记录已规划工作的开始日期，但加入或关联 Issue 不会提供日期值。PR 可以同时标识它所解决的 Issue 和提供相关实现上下文的 Issue；两种关系都表示仓库工作已经开始。
+组织级 `Start date` Issue 字段记录工作开始时间，但把 Issue 加入 Issue Project 或从 PR 关联它都不会提供日期值。PR 可以同时标识它所解决的 Issue 和提供相关实现上下文的 Issue；两种关系都表示仓库工作已经开始。
 
 如果每个 PR 事件都更新该字段，编辑、推送或重新打开 PR 会为已有工作补上日期。覆盖已有日期还会丢弃人工规划的日期或较早 PR 记录的日期。
 
 ## 决策
 
-Issue 生命周期工作流仅在 `pull_request.opened` 时初始化 `Start date`。工作流读取 PR 的实时正文，保留每个能解析为 Issue 的同仓库引用，把 `created_at` 按配置的 Project 时区转换为日历日期，确保 Issue 是 Project item，并仅在当前值为空时写入配置的 Date 字段。
+Issue 生命周期工作流仅在 `pull_request.opened` 时初始化 `Start date`。工作流读取 PR 的实时正文，保留每个能解析为 Issue 的同仓库引用，把 `created_at` 按配置的 Project 时区转换为日历日期，确保 Issue 是 Project item，并仅在当前值为空时写入配置的组织级 Issue Date 字段。
 
-配置指定 Project 字段和时区。配置缺失会在策略模块加载时失败；字段缺失、字段不是 Date 类型、时间戳无效或 API 请求失败会让首个相关 PR 的工作流失败。
+配置指定 Project 中显示的字段和时区。该 Project 字段必须解析为组织级 Issue Date 字段；工作流读取它的 Issue 值并通过 `updateIssueFieldValue` 更新。配置缺失会在策略模块加载时失败；字段缺失、字段不是 Date 类型或是 Project 局部字段、时间戳无效或 API 请求失败会让首个相关 PR 的工作流失败。
 
 [由事件直接指定的 PR 评审状态命令](2026-08-10-event-directed-pr-review-status.zh.md)继续负责 Status 转换。日期初始化同时包含解决型和信息型 Issue 引用，对 Draft PR 和自动化 PR 同样运行，也不依赖 PR 策略检查是否生效。
 
 ## 验证
 
-[Issue 管理测试](../../../../.github/issue-management/policy.test.mjs)覆盖上海时区日期边界、仅 opened 分派、全部保留的 Issue 引用、空值写入、已有值保留、Project item 缺失、字段配置无效和 GraphQL mutation 变量。[工作流测试](../../../../scripts/ci-workflow.spec.ts)要求保留 `pull_request.opened` 订阅。
+[Issue 管理测试](../../../../.github/issue-management/policy.test.mjs)覆盖上海时区日期边界、仅 opened 分派、全部保留的 Issue 引用、Issue 字段发现、空值写入、已有值保留、Project item 缺失、字段配置无效和 `updateIssueFieldValue` 变量。[工作流测试](../../../../scripts/ci-workflow.spec.ts)要求保留 `pull_request.opened` 订阅。
 
 ## 考虑过的替代方案
 
 **使用 Project 内置工作流。** 内置工作流负责固定的 Project item 和 Status 转换；仓库工作流已经负责经过身份验证的 GraphQL mutation，并且能够提供 PR 创建日期。
 
+**使用 Project 局部 Date 字段。** Project 字段允许同一个 Issue 在不同 Project 中使用不同日期，并且不会显示在 Issue 自身。工作是针对 Issue 开始，而不是针对某次 Project 归属开始，因此由组织级 Issue 字段持有该值。
+
 **处理每个已订阅 PR 事件或运行协调器。** 后续事件可以为已有 PR 和创建后新增的引用补上日期，但这会让该字段成为修复型投影，而不是随 PR 创建的记录，并且会增加重复 Project 读取。
 
 **仅更新解决型 Issue 引用。** 信息型引用同样标识随该 PR 开始实现工作的 Issue，因此日期初始化使用现有的全部引用集合，Status 转换仍只处理解决型引用。
@@ -34,6 +37,6 @@ Issue 生命周期工作流仅在 `pull_request.opened` 时初始化 `Start date
 
 ## 后果
 
-只有工作流发布后新建的 PR 会初始化日期。创建后新增的引用和现有开放 PR 保持不变，工作流不会扫描已有 Project item 或 PR。
+只有工作流发布后新建的 PR 会初始化日期。创建后新增的引用和现有开放 PR 保持不变，工作流不会扫描已有 Project item 或 PR。日期会随 Issue 出现在组织内显示该字段的各个 Project 中。
 
-空值读取使重试在通常情况下保持幂等。ProjectV2 没有条件字段更新，因此同时引用同一个空日期 Issue 的 PR 可能都会写入；按 PR 设置的并发控制不会串行化该 Issue，最后一次 mutation 可能胜出。
+空值读取使重试在通常情况下保持幂等。Issue 字段 mutation 没有比较并设置前提，因此同时引用同一个空日期 Issue 的 PR 可能都会写入；按 PR 设置的并发控制不会串行化该 Issue，最后一次 mutation 可能胜出。

.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-14-session-persistence.md
-2026-06-14-session-persistence.md: a7e06af78c4a372be7a68f3e0f6dc18e38cbead1
-2026-06-14-session-persistence.zh.md: 6d458d4f4c31793212d674bb406204c3882a25ed
+2026-06-14-session-persistence.md: 8f6c8753007e1998f9b072974e154c5a76ef116b
+2026-06-14-session-persistence.zh.md: b6d8e16377e0c294f19c69334c0770a66add756e

.agents/notes/implemented/architecture/2026-06-14-session-persistence.md

@@ -14,12 +14,12 @@ The [event-sourced model](2026-06-11-event-sourced-sessions.md) makes the append
 
 Persistence is a **capability seam** with an abstract Service Definition ([capability seams](2026-06-13-capability-seams.md), the `dsh-shell` template), not loop or core logic:
 
-1. **Interface** (`dsh-session-persistence`, `ctx.sessionPersistence`) — an abstract `SessionPersistence` service: `create`/`open`/`stat`/`list`/`export`, with `create`/`open` returning per-session `SessionHandle`s that carry `read`/`append`/`flush`/`close` ([handle-based seam](2026-08-27-handle-based-session-persistence.md)). Its persisted unit IS the existing `SessionEvent` (`{ type, seq, time, data }`), reused verbatim — no conversion type.
-2. **Implementation** (`dsh-session-persistence-jsonl`) — an append-only logical JSONL log per session: a `SessionHeader` line followed by storage records that losslessly represent the contiguous `SessionEvent` stream. Eligible `assistant/chunk` delta runs use packed rows by default; [checksummed Zstandard frames](2026-07-19-zstandard-jsonl-session-logs.md) are the default physical encoding, with raw lines configurable.
+1. **Interface** (`dsh-session-persistence`, `ctx.sessionPersistence`) — an abstract `SessionPersistence` service: `create`/`open`/`stat`/`list`/`flush`, with `create`/`open` returning per-session `SessionHandle`s that carry `read`/`append`/`flush`/`close` ([handle-based seam](2026-08-27-handle-based-session-persistence.md)). Its persisted unit IS the existing `SessionEvent` (`{ type, seq, time, data }`), reused verbatim — no conversion type.
+2. **Implementation** (`dsh-session-persistence-jsonl`) — an append-only logical JSONL log per session: a `SessionHeader` line followed by storage records that losslessly represent the contiguous `SessionEvent` stream. Current v2 writes one event per row; frozen v0 and v1 readers retain their historical packed-delta representation. [Checksummed Zstandard frames](2026-07-19-zstandard-jsonl-session-logs.md) are the default physical encoding, with raw lines configurable.
 
 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.
+- **The canonical durable log persists every current `SessionEvent` losslessly.** In v2, one `assistant/message` or `assistant/attempt` embeds the exact timed provider stream for an attempt; `deriveMessages()` projects only the surface message. Dropping embedded stream members is tempting, but it loses replay, timing, usage, partial-failure, and diagnostic facts. Removing a complete event likewise requires dense renumbering because `seq = log.length` and `events[i].seq === i`; the [v1-to-v2 migration](2026-09-01-v2-embedded-assistant-streams.md) performs that rewrite explicitly rather than filtering 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, persistence returns its contiguous, parseable events unmodified; the reader owns balancing — resume computes risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }` (`interruptedTurnClosers`) and appends them through its write handle, while read-only observers add the same closers in memory. The synthetic results keep resumed provider transcripts valid. Only the incomplete fragment of a torn final append is discarded — complete records recovered from it are durably rewritten by the write path before its first new append; a parse error or sequence gap in the committed prefix 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 remains 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).)
@@ -27,10 +27,10 @@ Key durable, contested choices:
 
 ## Alternatives considered
 
-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.
+Each key choice above records its rejected alternative where the choice is stated: a **stream-filtered canonical log** — loses attempt evidence, while removing events without an explicit migration breaks contiguous sequence numbers; **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 compatibility promise: reads validate current v0 records only, and retired same-version shapes refuse fail-closed ([export and pre-release trims](../simplification/2026-08-27-persistence-export-and-pre-release-trims.md)). Append-only + flush is robust to partial trailing writes (tolerated during cold preparation) but not to fsync-less power loss mid-line; a DB/WAL backend is the stronger option there.
+Format versioning: the header carries a `version`; handles expose only `SESSION_FORMAT_VERSION = 2`. JSONL event-body reads compose the static v0-to-v1 and v1-to-v2 adjacent migration chain before returning a handle; the first edge owns bounded legacy normalization, while the second owns Assistant stream embedding and dense reference remapping. V0 remains at suffixless `session.jsonl[.zstd]`, while positive versions 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; a future provider or write-ahead log needs its own power-loss and recovery contract.
 
 ## Consequences
 
-The Service Definition, JSONL provider, and metadata contract in `dsh-session` (`session.header`, the `create(id?, options?)` signature) buy durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log. The reusable `runPersistenceContract` suite holds the provider and future implementations to the same append-only, contiguous-seq, lazy-materialization, logical-recovery, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every `assistant/chunk` survives exactly even when JSONL packs several into one storage row.
+The Service Definition, JSONL provider, and metadata contract in `dsh-session` (`session.header`, the `create(header, options?)` signature) buy durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log. The reusable `runPersistenceContract` suite holds the provider and future implementations to the same append-only, contiguous-seq, lazy-materialization, logical-recovery, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every Assistant attempt retains its exact compact timed stream in one durable settlement.

.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md

@@ -14,12 +14,12 @@ Status: implemented
 
 持久化是一个具有抽象 Service Definition 的**能力 seam**（[能力 seam](2026-06-13-capability-seams.zh.md)，`dsh-shell` 模板），而非循环或核心逻辑：
 
-1. **接口**（`dsh-session-persistence`，`ctx.sessionPersistence`）：一个抽象的 `SessionPersistence` 服务，提供 `create`/`open`/`stat`/`list`/`export`，其中 `create`/`open` 返回逐会话的 `SessionHandle`，句柄承载 `read`/`append`/`flush`/`close`（[基于句柄的 seam](2026-08-27-handle-based-session-persistence.zh.md)）。其持久化单元就是现有的 `SessionEvent`（`{ type, seq, time, data }`），原样复用，无转换类型。
-2. **实现**（`dsh-session-persistence-jsonl`）：每个会话一个仅追加的逻辑 JSONL 日志：先是一行 `SessionHeader`，随后是无损表示连续 `SessionEvent` 流的存储记录。符合条件的 `assistant/chunk` 增量连续段默认使用打包行；[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.zh.md)是默认物理编码，也可通过配置使用原始行。
+1. **接口**（`dsh-session-persistence`，`ctx.sessionPersistence`）：一个抽象的 `SessionPersistence` 服务，提供 `create`/`open`/`stat`/`list`/`flush`，其中 `create`/`open` 返回逐会话的 `SessionHandle`，句柄承载 `read`/`append`/`flush`/`close`（[基于句柄的 seam](2026-08-27-handle-based-session-persistence.zh.md)）。其持久化单元就是现有的 `SessionEvent`（`{ type, seq, time, data }`），原样复用，无转换类型。
+2. **实现**（`dsh-session-persistence-jsonl`）：每个会话一个仅追加的逻辑 JSONL 日志：先是一行 `SessionHeader`，随后是无损表示连续 `SessionEvent` 流的存储记录。当前 v2 每个事件写一行；冻结的 v0 与 v1 reader 保留其历史 packed-delta 表示。[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.zh.md)是默认物理编码，也可通过配置使用原始行。
 
 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。
+- **规范持久日志无损保留每个当前 `SessionEvent`。** 在 v2 中，一个 `assistant/message` 或 `assistant/attempt` 会嵌入该 attempt 的精确带时间 provider stream；`deriveMessages()` 只投影 surface message。删除嵌入 stream 成员看似诱人，但会丢失 replay、timing、usage、部分失败与诊断事实。移除完整事件同样需要密集重新编号，因为 `seq = log.length` 且 `events[i].seq === i`；[v1 到 v2 迁移](2026-09-01-v2-embedded-assistant-streams.zh.md)会显式执行该改写，而不是过滤规范日志。
 - **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，持久化会原样返回其连续、可解析的事件；配平是读方的职责——resume 会为未应答的 assistant 调用计算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`（`interruptedTurnClosers`），并通过其写句柄追加它们，而只读观察方仅在内存中添加同样的收尾事件。合成结果保证恢复后的提供方 transcript（文本记录）仍然有效。只有撕裂的最终 append 中不完整的碎片会被丢弃——从中恢复的完整记录由写路径在第一次新 append 之前持久重写；已提交前缀中的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)。）
@@ -27,10 +27,10 @@ Status: implemented
 
 ## 曾考虑的替代方案
 
-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。
+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 stream 的规范日志**会丢失 attempt 证据，而未通过显式迁移移除事件会破坏连续序号；**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`，不作兼容承诺：读取只校验当前 v0 记录，已废弃的同版本形态会以 fail-closed 方式拒绝（[导出与预发布精简](../simplification/2026-08-27-persistence-export-and-pre-release-trims.zh.md)）。仅追加 + 刷写对尾部的不完整写入具有健壮性（冷准备时可容忍），但无法抵御未使用 fsync 时在行写入中途断电；数据库/WAL 后端是该场景下更强的选项。
+格式版本控制：header 携带 `version`；句柄只暴露 `SESSION_FORMAT_VERSION = 2`。JSONL 的事件正文读取会在返回句柄前组合静态 v0-to-v1 与 v1-to-v2 相邻迁移链；第一条边负责有界 legacy normalization，第二条边负责 Assistant stream 嵌入与密集引用重映射。V0 保留无后缀的 `session.jsonl[.zstd]`，正版本则使用不可变的小写 `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 append 与 flush 能稳健处理不完整尾部写入；未来 provider 或 WAL 必须定义自己的断电与恢复约定。
 
 ## 后果
 
-Service Definition、JSONL provider 与 `dsh-session` 中的元数据约定（`session.header`，`create(id?, options?)` 签名）带来持久恢复/fork、读取/回放路径、崩溃容忍，以及基于现有事件溯源日志的宿主侧会话访问。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、逻辑恢复、整数元数据与可序列化语义约束该 provider 与未来实现。持久化完整的逻辑日志还确定了事件保真度：即使 JSONL 将多个 `assistant/chunk` 打包到一条存储行中，每个事件也会精确保留。
+Service Definition、JSONL provider 与 `dsh-session` 中的元数据约定（`session.header`，`create(header, options?)` 签名）带来持久恢复/fork、读取/replay 路径、崩溃容忍，以及基于现有事件溯源日志的宿主侧 Session 访问。可复用 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、逻辑恢复、整数元数据与可序列化语义约束该 provider 与未来实现。持久化完整逻辑日志也确定了事件保真度：每个 Assistant attempt 都在一个持久 settlement 中保留其精确紧凑带时间 stream。

.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-session-surface.md
-2026-06-18-session-surface.md: 95298da0e4bd16e822cb5960718d23ecda7a1b5c
-2026-06-18-session-surface.zh.md: 7dd05d79f635b193b2c11cb3599264ebf2424d79
+2026-06-18-session-surface.md: 0139cc4beba766e4e8b936594899649304234eaa
+2026-06-18-session-surface.zh.md: 0596d2a0425890924276265dd9cc6c32fcffb974

.agents/notes/implemented/architecture/2026-06-18-session-surface.md

@@ -16,7 +16,7 @@ Add a **surface** — a derived, cached order of event sequences (the subset of
 
 Every `SessionEvent` gains two optional fields (structural metadata, like `seq`/`time`):
 
-- **`sourceEventSeqs?: number[]`** — seq numbers of earlier events cited as sources (e.g., the `assistant/chunk` seqs that built an `assistant/message`, or the surface nodes shadowed by a compaction marker). A present `[]` is valid only on `assistant/message` and records a known empty provider stream; when the field is absent, a legacy or foreign event does not record which earlier events produced the message. Other surface events require a non-empty list when the field is present. Without these cited seqs, replay cannot validate that a replace-range operation names every event it removed.
+- **`sourceEventSeqs?: number[]`** — seq numbers of earlier events cited as sources, such as a `tool/call` cited by its result or surface nodes shadowed by a compaction marker. A present list is non-empty, unique, earlier, and known. V2 `assistant/message` embeds its provider stream and cannot carry this field. Without cited seqs, replay cannot validate that a replace-range operation names every event it removed.
 - **`surfaceOp?: SurfaceOp`** — how this event entered the surface. Absent for non-surface events.
 
 ### SurfaceOp: two operations
@@ -27,7 +27,7 @@ export type SurfaceOp =
   | { op: 'replace'; start: number; end: number }  // shadow [start, end] inclusive
 ```
 
-1. **Append** — add the new event seq to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`. The loop passes `surfaceOp: 'append'` on all such appends and records `sourceEventSeqs` where applicable: every successful `assistant/message` records its complete `assistant/chunk` source set, including `[]`, while `tool/result` records its `tool/call` source.
+1. **Append** — add the new event seq to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`. The loop passes `surfaceOp: 'append'` on all such appends and records `sourceEventSeqs` where applicable: `tool/result` records its `tool/call` source, while `assistant/message` owns its embedded stream directly.
 
 2. **Replace** — remove entries from `start` through `end` (both inclusive) and insert the new event seq in their place. Both `start` and `end` must be present in the current surface; `start === end` replaces one entry. The event's `sourceEventSeqs` must contain every shadowed surface seq. The shadowed events remain in the log but are no longer on the surface.
 
@@ -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
 
@@ -49,9 +49,9 @@ The `repair.ts` module synthesizes `tool/result` closers for orphaned tool calls
 
 ### Invariants
 
-`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.
+`Session` validates `sourceEventSeqs` and `surfaceOp` at the always-on seed/append boundary: source lists are non-empty, unique, earlier, and known; `assistant/message` carries no source list; 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
 

.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md

@@ -16,7 +16,7 @@ Status: implemented
 
 每个 `SessionEvent` 获得两个可选字段（结构性元数据，与 `seq`/`time` 同级）：
 
-- **`sourceEventSeqs?: number[]`**：被引用为数据来源的早期事件 seq 编号（例如构成 `assistant/message` 的各 `assistant/chunk` 的 seq，或被压缩标记遮蔽的 surface 节点）。出现的 `[]` 只在 `assistant/message` 上有效，表示已知为空的提供方流；旧格式或外部事件缺少该字段时，没有记录这条消息由哪些早期事件产生。其他 surface 事件一旦出现此字段，就必须是非空列表。如果没有这些引用的 seq，回放就无法验证 replace-range 操作是否列出了它移除的每个事件。
+- **`sourceEventSeqs?: number[]`**：被引用为数据来源的早期事件 seq 编号，例如 result 引用的 `tool/call`，或被 compaction marker 遮蔽的 surface 节点。出现的列表必须非空、唯一、更早且已知。V2 `assistant/message` 嵌入其 provider stream，不能携带该字段。如果没有这些引用的 seq，回放就无法验证 replace-range 操作是否列出了它移除的每个事件。
 - **`surfaceOp?: SurfaceOp`**：该事件如何进入 surface。非 surface 事件不携带此字段。
 
 ### SurfaceOp：两种操作
@@ -27,7 +27,7 @@ export type SurfaceOp =
   | { op: 'replace'; start: number; end: number }  // shadow [start, end] inclusive
 ```
 
-1. **Append**：在尾部追加新事件的 seq。`user/message`、`assistant/message`、`tool/result`、`context/message` 使用此操作。agent loop（智能体循环）在所有此类追加上传入 `surfaceOp: 'append'`，并在适用时记录 `sourceEventSeqs`：每个成功的 `assistant/message` 都记录完整的 `assistant/chunk` 来源集合（包括 `[]`），而 `tool/result` 记录其 `tool/call` 来源。
+1. **Append**：在尾部追加新事件的 seq。`user/message`、`assistant/message`、`tool/result`、`context/message` 使用此操作。agent loop（智能体循环）在所有此类追加上传入 `surfaceOp: 'append'`，并在适用时记录 `sourceEventSeqs`：`tool/result` 记录其 `tool/call` 来源，`assistant/message` 则直接拥有其嵌入式 stream。
 
 2. **Replace**：移除从 `start` 到 `end`（两端包含）的条目，并在其位置插入新事件的 seq。`start` 和 `end` 都必须存在于当前 surface；`start === end` 表示替换单个条目。该事件的 `sourceEventSeqs` 必须包含所有被遮蔽的 surface seq。被遮蔽的事件仍留在日志中，但不再出现在 surface 上。
 
@@ -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
 
@@ -49,9 +49,9 @@ export type SurfaceOp =
 
 ### 不变式
 
-`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。
+`Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`：source list 必须非空、唯一、更早且已知；`assistant/message` 不携带 source list；replacement endpoint 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 invariant service 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
 

.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md
-2026-06-21-bounded-llm-request-recovery.md: 42bf460e52133b2a5471479fa3d7647e70092b48
-2026-06-21-bounded-llm-request-recovery.zh.md: 2a13f0a740348a5f74bd3d90120a148b25f2e870
+2026-06-21-bounded-llm-request-recovery.md: 6ae3915462c00eadcc550c80165fab7247a9170c
+2026-06-21-bounded-llm-request-recovery.zh.md: 82e2e783fffaedcb5bfaabe72f56f7c4176d3784

.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md

@@ -10,7 +10,7 @@ The [per-provider request retry policy](../feature/2026-07-24-provider-retry-pol
 
 Provider adapters can fail by throwing during dispatch or iteration or by ending with `finish { kind: 'error' | 'aborted' }`. The final adapter boundary normalizes thrown values to that terminal finish protocol before `dsh-agent-loop` receives them; middleware and result-processing defects remain thrown. The loop offers a terminal model-request failure to `agent/request-error`. An unhandled failure is terminal; a handling listener repairs policy-owned state, returns `{ kind: 'retry' }`, and stops waterfall delegation. The [retry-action decision](../simplification/2026-07-27-request-error-retry-action.md) owns this return contract.
 
-That boundary is already safe for another request attempt. Raw `assistant/chunk` events carry the failed `turn` and `step`, message derivation ignores them unless a successful `assistant/message` cites them, tool calls are dispatched only after a successful terminal finish and assembly, and a retry reconstructs its next attempt from the durable log. The harness therefore does not need a second response lifecycle or tentative-output protocol to keep two attempts separate.
+That boundary is already safe for another request attempt. Each failed stream commits one log-only `assistant/attempt` with its exact compact stream, message derivation ignores it, tool calls are dispatched only after a successful terminal finish and assembled `assistant/message`, and a retry reconstructs its next attempt from the durable surface. The harness therefore does not need a second response lifecycle or tentative-output protocol to keep two attempts separate.
 
 The prior boundary left three narrower gaps.
 
@@ -38,7 +38,7 @@ interface LlmFailure {
 }
 ```
 
-`code` remains the provider-neutral machine-routing taxonomy established by `HarnessError`; the new fields are observations from the provider boundary. `ProviderRequestId` is owned and constructed by `dsh-llm`, then serializes as its provider-issued string. The payload deliberately has no `retryable`, `failover`, `partialOutput`, provider, model, phase, or route id fields. Retryability belongs to policy, provider/model are already in the durable request header, and partial output is derived from the failed step's `assistant/chunk` events.
+`code` remains the provider-neutral machine-routing taxonomy established by `HarnessError`; the new fields are observations from the provider boundary. `ProviderRequestId` is owned and constructed by `dsh-llm`, then serializes as its provider-issued string. The payload deliberately has no `retryable`, `failover`, `partialOutput`, provider, model, phase, or route id fields. Retryability belongs to policy, provider/model are already in the durable request header, and partial output is preserved by the failed attempt's embedded stream.
 
 `LlmError` carries `failure: LlmFailure` and preserves `failure.code === error.code`. `FinishReasonMap.error` and `FinishReasonMap.aborted` carry the same payload instead of parallel failure shapes. The final adapter boundary detaches those facts from adapter-thrown values and emits the appropriate terminal finish; unknown SDK exceptions receive an `UNKNOWN` payload. Exact thrown-object identity does not cross the LLM stream seam.
 
@@ -82,7 +82,7 @@ Boundary tests prove termination at both actual transports. The hand-written ada
 
 ### Keep attempts separate in the existing log
 
-A failed attempt may leave `assistant/chunk` events in its step, but it never appends `assistant/message` and never dispatches a tool. A retry continues inside the failing turn and step, reconstructs the request from the durable surface, and produces its own chunks; only the final outcome closes the turn. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed attempt or `turn/end` records failure. Web validates the complete retry payload contract, clears the failed partial at `llm/retry`, projects each producer-correlated `retryId` chain into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from `llm/retry-started` and the owning turn and step boundaries' closure. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no assistant node. Message derivation continues to ignore the failed chunks, and Web applies the same projection during history rebuild so refreshing cannot resurrect discarded partials or duplicate retry rows.
+A failed attempt appends `assistant/attempt` with its embedded stream, but never appends a surface `assistant/message` or dispatches a tool. A retry continues inside the failing turn and step, reconstructs the request from the durable surface, and produces its own settlement; only the final outcome closes the turn. UIs may render transient `assistant/live-chunk` updates while a step is open, then settle the failed attempt when `llm/retry` identifies it or `turn/end` records failure. Web validates the complete retry payload contract, projects each producer-correlated `retryId` chain into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from `llm/retry-started` and the owning turn and step boundaries' closure. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no surface Assistant node. Message derivation ignores `assistant/attempt`, and Web applies the same projection during history rebuild so refreshing cannot promote failed partials into model history or duplicate retry rows.
 
 If recovery is exhausted, the final failure is stored once on `turn/end.reason` with the structured facts. Web derives one `turn-error` node at that sequence position and renders its display-safe message and optional code inline; AUTH projections replace provider copy that may echo credential fragments with `API key is invalid`, while the raw diagnostic remains in the session log. The same fold runs for live events and history replay. While transient recovery continues, `llm/retry` is the durable home for each intermediate failure and delay; the terminal row exists only once `turn/end` records the error, and because exhausted recovery shares the failing turn, the turn's retry history never suppresses that row — the settled retry chain and the terminal error render side by side. No standalone final-error event or response-id vocabulary is added.
 

.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md

@@ -10,7 +10,7 @@ Status: implemented
 
 提供方适配器可能在分发或迭代时抛出异常，也可能以 `finish { kind: 'error' | 'aborted' }` 结束。最终适配器边界会在 `dsh-agent-loop` 接收前把抛出值规范化为该终止 finish 协议；middleware 与结果处理缺陷仍会抛出。loop 会将终止模型请求失败交给 `agent/request-error`。未被处理的失败是终态；处理失败的监听器修复策略自有状态，返回 `{ kind: 'retry' }`，并停止 waterfall（瀑布式事件）委托。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.zh.md)规定这一返回约定。
 
-该边界已能安全地再次发起请求。原始 `assistant/chunk` 事件携带失败的 `turn` 和 `step`；除非某条成功的 `assistant/message` 引用这些事件，否则消息派生会忽略它们。只有终止性 finish 成功且组装完成后，系统才会分发工具调用；重试则会从持久日志重建下一次尝试。因此，harness 无需引入第二套响应生命周期或暂定输出协议，即可分隔两次尝试。
+该边界已能安全地再次发起请求。每个失败 stream 会提交一个包含精确紧凑 stream 的仅日志 `assistant/attempt`，message derivation 会忽略它；系统只会在 terminal finish 成功并组装 `assistant/message` 后分派工具调用，重试则从持久 surface 重建下一次 attempt。因此，harness 无需引入第二套响应生命周期或暂定输出协议，即可分隔两次 attempt。
 
 此前的边界还留有三个较窄的缺口。
 
@@ -38,7 +38,7 @@ interface LlmFailure {
 }
 ```
 
-`code` 仍是 `HarnessError` 建立的提供方无关机器路由分类体系；新字段是在提供方边界观测到的事实。`ProviderRequestId` 由 `dsh-llm` 拥有并构造，序列化后为提供方发放的字符串。该载荷有意不包含 `retryable`、`failover`、`partialOutput`、提供方、模型、阶段或路由 id 字段。是否可重试属于策略，提供方／模型已位于持久请求头中，部分输出则从失败步骤的 `assistant/chunk` 事件派生。
+`code` 仍是 `HarnessError` 建立的 provider-neutral 机器路由分类；新字段是在 provider 边界观测到的事实。`ProviderRequestId` 由 `dsh-llm` 拥有并构造，序列化后是 provider 发放的字符串。该 payload 有意不包含 `retryable`、`failover`、`partialOutput`、provider、model、phase 或 route id。是否可重试属于 policy，provider/model 已位于持久 request header 中，部分输出由失败 attempt 的嵌入式 stream 保留。
 
 `LlmError` 携带 `failure: LlmFailure`，并保持 `failure.code === error.code`。`FinishReasonMap.error` 和 `FinishReasonMap.aborted` 携带同一载荷，而不是并行的失败形状。最终适配器边界会从适配器抛出值中分离这些事实，并发出相应的终止 finish；未知 SDK 异常会获得 `UNKNOWN` 载荷。精确的抛出对象身份不会跨越 LLM 流 seam。
 
@@ -82,7 +82,7 @@ agent loop（智能体循环）会将终止 finish 的 `LlmFailure` 传给 `agen
 
 ### 在现有日志中分隔尝试
 
-一次失败尝试可以在其步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试在失败的轮次与步骤内继续，从持久表层重建请求，并生成自己的分片；只有最终结果才会关闭该轮次。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败尝试，或 `turn/end` 记录失败时，UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷约定，在 `llm/retry` 到达时清除失败的部分输出，将每条生产方关联的 `retryId` 重试链投影为稳定的一行，并用最新一次尝试更新该行，再从 `llm/retry-started` 与所属轮次、步骤边界的关闭派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点，而不是使用 Host 事件时钟；它按向上取整且不低于 1 秒的秒数显示，仅在重试尚未结束时显示动画，并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点，重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片；Web 在重建历史时也会应用同一投影，因此刷新页面不会让已丢弃的部分输出重新出现，也不会生成重复的重试行。
+失败 attempt 会追加带嵌入式 stream 的 `assistant/attempt`，但绝不追加 surface `assistant/message` 或分派工具。重试在失败 turn 与 step 内继续，从持久 surface 重建请求，并产生自己的 settlement；只有最终结果才会关闭 turn。step 打开时，UI 可以渲染瞬态 `assistant/live-chunk` update；当 `llm/retry` 标识失败 attempt 或 `turn/end` 记录失败时，UI 再结算它。Web 会校验完整 retry payload contract，把每条 producer-correlated `retryId` chain 投影为稳定一行并更新到最新 attempt，再从 `llm/retry-started` 与所属 turn、step boundary 的关闭派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到 event 的时刻为计划延迟起点，而不是 Host event clock；它按向上取整且不低于 1 秒的秒数显示，只在未结算时动画，并把最新失败详情折叠在该行后。即使失败 attempt 没有 surface Assistant node，retry node 也会锚定自己的 trajectory turn。Message derivation 会忽略 `assistant/attempt`，Web 在历史重建时应用同一投影，因此刷新不会把失败 partial 提升进模型历史，也不会生成重复 retry row。
 
 如果恢复预算耗尽，最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。Web 会在该序列位置派生一个 `turn-error` 节点，并内联渲染适合展示的消息与可选错误码；AUTH 投影会把可能回显凭据片段的提供方文案替换为 `API key is invalid`，原始诊断仍保留在会话日志中。实时事件和历史回放使用同一套折叠逻辑。暂时性恢复继续期间，`llm/retry` 是每次中间失败与延迟的持久归属位置；终态错误行只在 `turn/end` 记录错误后才存在，而由于耗尽的恢复与失败共享同一轮次，该轮次的重试历史绝不会抑制这一行——定格的重试链与终态错误并列渲染。本决策不增加独立的最终错误事件或响应 id 词汇。
 

.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md
-2026-06-30-event-domain-semantics.md: 70da718b5471ce309a090c8aade3e7290cc949dc
-2026-06-30-event-domain-semantics.zh.md: c3b12a167da0a41b792914d82a675a98b3a0b860
+2026-06-30-event-domain-semantics.md: f3e4686a1e9e14c9284de5a4bff16501c50aa907
+2026-06-30-event-domain-semantics.zh.md: f4bc92111666b0c30586222e14ee1aeab49ebb3f

.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md

@@ -21,7 +21,7 @@ This vocabulary is the foundation for interception decisions, the durable `hook/
 **Three domains, one job each, with a single boundary rule.**
 
 - **`session/*` — the durable, replayable FACT log.** Owns `SessionEventMap`; every entry is JSON-only (no live objects). One `session/event` emit per append, plus the `session/flush` parallel durability checkpoint. It is also the live transcript feed: a consumer that wants to render or react to what happened subscribes here, so live rendering and replay projections share one path.
-- **`agent/*` — the LIVE runtime surface.** Always carries the live `Agent`. Interception waterfalls (`agent/pre-step`, `agent/request`, `agent/request-error`) transform, reject, or recover; awaited `agent/turn-stopping` observes the stop boundary; transient emits report lifecycle, status, inbox insertion/claim/discard, and errors. Turn and step BOUNDARIES are NOT here — they are durable session events read off `session/event`, as are the token stream (`assistant/chunk`) and mid-turn steering (a `user/message`).
+- **`agent/*` — the LIVE runtime surface.** Always carries the live `Agent`. Interception waterfalls (`agent/pre-step`, `agent/request`, `agent/request-error`) transform, reject, or recover; awaited `agent/turn-stopping` observes the stop boundary; transient emits report lifecycle, status, inbox insertion/claim/discard, errors, and process-local `agent/assistant-stream` frames. Turn and step BOUNDARIES are NOT here — they are durable session events read off `session/event`; Assistant stream evidence becomes durable only inside one `assistant/message` or `assistant/attempt` settlement, and mid-turn steering is a durable `user/message`.
 - **`tools/*` — the tool registry and execution pipeline.**
 
 **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit.

.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md

@@ -21,7 +21,7 @@ harness 通过 Cordis 事件分类体系扩展 agent loop（智能体循环）
 **三个域，各司其职，以一条边界规则统一。**
 
 - **`session/*`——持久的、可回放的事实日志。** 拥有 `SessionEventMap`；每条记录仅含 JSON（无活对象）。每次追加触发一次 `session/event` emit，加上 `session/flush` 并行持久性检查点。它同时也是实时 transcript（文本记录）源：想渲染或响应已发生事件的消费方在此订阅，因此实时渲染与回放投影共享同一路径。
-- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。拦截 waterfall（瀑布式事件）（`agent/pre-step`、`agent/request`、`agent/request-error`）负责变换、拒绝或恢复；awaited `agent/turn-stopping` 观察停止边界；瞬态 emit 报告生命周期、状态、inbox 的插入、领取和丢弃，以及错误。轮次和步骤边界不在此处——它们是持久的会话事件，从 `session/event` 读取；token 流（`assistant/chunk`）和轮次中途以 `user/message` 呈现的 steering（中途引导）同理。
+- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。拦截 waterfall（瀑布式事件）（`agent/pre-step`、`agent/request`、`agent/request-error`）负责变换、拒绝或恢复；awaited `agent/turn-stopping` 观察停止边界；瞬态 emit 报告生命周期、状态、inbox 插入、领取与丢弃、错误，以及进程本地 `agent/assistant-stream` frame。轮次和步骤边界不在此处——它们是从 `session/event` 读取的持久 Session event；Assistant stream 证据只在一个 `assistant/message` 或 `assistant/attempt` settlement 内变为持久事实，轮次中途 steering 则是持久 `user/message`。
 - **`tools/*`——工具注册表与执行流水线。**
 
 **边界规则：** 持久的、可回放的事实是 `SessionEvent`；实时拦截或瞬态/活对象信号是 `agent`/`tools` Cordis 事件。轮次或步骤边界是持久事实，因此存在于会话日志中并从 `session/event` 源读取——不会被镜像为 `agent/*` emit。

.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
-2026-07-05-reconstructable-requests.md: 3786de02d06c0b6c094297ae89ac3f84053e408d
-2026-07-05-reconstructable-requests.zh.md: 851045aca7dababd0da859f3b04b721c65382fc3
+2026-07-05-reconstructable-requests.md: bc8ba640c400b18598f18aa303f2bd1b5c5b9cdc
+2026-07-05-reconstructable-requests.zh.md: de1802aac83f1e0980172d2d541a093f2d729e4a

.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md

@@ -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.

.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md

@@ -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。

.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md
-2026-07-10-single-file-executable-sdk-runtime-distribution.md: c152345772826ec4e2dbfd238726c429418c7897
-2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: ea5e457afd761cb5071f8b584ef10fa7ffaa8210
+2026-07-10-single-file-executable-sdk-runtime-distribution.md: 558358167a5e7d37bc79c42003a183b0c4c40d17
+2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 0f7daec5b79e6f526dde7a01c5ef85b07e955707

.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-14-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

.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md

@@ -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.

.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md

@@ -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。

.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md
-2026-07-19-zstandard-jsonl-session-logs.md: 33486251a8b018cda61a2845a55218f13c38072b
-2026-07-19-zstandard-jsonl-session-logs.zh.md: 5e6b4a1ed7cf5869e1700c2884898b9899452a30
+2026-07-19-zstandard-jsonl-session-logs.md: a893a79f063842dfa93e57cb3972ea151421b05d
+2026-07-19-zstandard-jsonl-session-logs.zh.md: bdaeab701359acbd02f47a2a3d83fe4913d607e7

.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md

@@ -6,7 +6,7 @@ English | [中文](2026-07-19-zstandard-jsonl-session-logs.zh.md)
 
 ## Problem
 
-The JSONL persistence backend keeps every `SessionEvent` verbatim, including high-volume `assistant/chunk` records. Raw text makes logs inspectable but spends storage and I/O on repeated JSON keys and model text. Compression must retain the existing append/fsync commit boundary, collision-safe first materialization, crash repair, and metadata-only listing; rewriting a whole compressed file after every turn would discard those properties.
+The JSONL persistence backend keeps every `SessionEvent` verbatim, including Assistant settlements with embedded model streams. Raw text makes logs inspectable but spends storage and I/O on repeated JSON keys and model text. Compression must retain the existing append/fsync commit boundary, collision-safe first materialization, crash repair, and metadata-only listing; rewriting a whole compressed file after every turn would discard those properties.
 
 The encoding also has to remain explicit at the deployment boundary. Snapshot fixtures and external line readers require raw JSONL, while a backend cannot safely guess between compressed and raw artifacts in one root or silently migrate pre-release session data.
 
@@ -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
 

.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md

@@ -6,7 +6,7 @@ Status: implemented
 
 ## 问题
 
-JSONL 持久化后端会逐字保留每个 `SessionEvent`，其中包括数量庞大的 `assistant/chunk` 记录。原始文本便于检查，但重复的 JSON 键和模型文本会增加存储与 I/O 开销。压缩编码必须保留既有的 append/fsync 提交边界、首次物化时的无冲突发布、崩溃修复以及仅元数据列举；如果每轮都重写整个压缩文件，就会失去这些属性。
+JSONL 持久化后端会逐字保留每个 `SessionEvent`，包括嵌入模型 stream 的 Assistant settlement。原始文本便于检查，但重复的 JSON key 和模型文本会增加存储与 I/O 开销。压缩编码必须保留既有 append/fsync 提交边界、首次物化时的无冲突发布、崩溃修复与仅元数据列举；如果每轮都重写整个压缩文件，就会失去这些属性。
 
 编码还必须在部署边界上保持显式。快照 fixture（测试前置数据）与外部逐行读取器需要原始 JSONL，而后端无法在同一根目录中安全猜测压缩产物与原始产物，也不能静默迁移预发布会话数据。
 
@@ -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
 

.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md
-2026-07-29-projected-token-usage-and-request-context.md: 7c984012b7a4b387f1ff24279567fe15aa34cf77
-2026-07-29-projected-token-usage-and-request-context.zh.md: b34fb7702898f4a51524a24ad27927c48220bfad
+2026-07-29-projected-token-usage-and-request-context.md: d62f7dccd544a342da64fc35c24d32d53bf56231
+2026-07-29-projected-token-usage-and-request-context.zh.md: 6d2bb624ac11dbcdac30695913d3c16513bfdf9e

.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md

@@ -14,7 +14,7 @@ Context occupancy needs a numerator and a denominator that no existing surface c
 
 Both values are ordinary durable session-projection state. `@deepseek-ai/dsh-token-meter` registers two units when `ctx.sessionProjections` is present.
 
-`tokenUsage` folds the complete durable log into uncached input, output, cache-read, and cache-write buckets. An `assistant/chunk` usage sample survives a later failed request; an `assistant/message` usage value replaces the earlier sample from the same model attempt instead of double-counting it. A matching `llm/retry-started` boundary ends that replacement scope, so a retry with the same `(turn, step)` contributes a new attempt. Reasoning stays an output subdivision. Compaction and surface replacement do not erase earlier billing.
+`tokenUsage` folds the complete durable log into uncached input, output, cache-read, and cache-write buckets. It expands each `assistant/message` or `assistant/attempt` stream and takes the last usage sample; a message's top-level usage takes precedence over its embedded sample instead of double-counting it. `assistant/attempt` therefore preserves usage from failed requests. A matching `llm/retry-started` boundary opens a new attempt, so a retry with the same `(turn, step)` contributes separately. Reasoning stays an output subdivision. Compaction and surface replacement do not erase earlier billing.
 
 Token-meter also owns the shared pure attempt/Turn fold over durable events. It applies the same retry boundary while adding the stricter completeness and exact-total checks required by an exact per-Turn disclosure. A presentation consumer may select a complete Turn window and invoke that fold, but does not own or duplicate the accounting semantics.
 

.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.zh.md

@@ -14,7 +14,7 @@ Web 统计行原先从当前已加载的会话节点推导 token 总量。该窗
 
 这两个值都是普通的持久会话投影状态。当 `ctx.sessionProjections` 存在时，`@deepseek-ai/dsh-token-meter` 会注册两个单元。
 
-`tokenUsage` 将完整持久日志归并为未缓存输入、输出、缓存读取和缓存写入四类计数项。即使后续请求失败，`assistant/chunk` 用量样本仍会保留；`assistant/message` 用量值会替换同一次模型 attempt 的先前样本，不会重复计数。匹配的 `llm/retry-started` 边界会结束该替换作用域，因此复用同一 `(turn, step)` 的重试会贡献一次新的 attempt。推理（reasoning）仍是输出的细分项。压缩和表层替换不会抹除先前的计费用量。
+`tokenUsage` 将完整持久日志归并为未缓存输入、输出、缓存读取和缓存写入四类计数项。它会展开每个 `assistant/message` 或 `assistant/attempt` stream 并采用最后一个 usage sample；message 顶层 usage 优先于其嵌入式 sample，因此不会重复计数。`assistant/attempt` 由此保留失败请求的 usage。匹配的 `llm/retry-started` 边界会打开新 attempt，因此复用同一 `(turn, step)` 的重试会单独贡献用量。推理（reasoning）仍是输出的细分项。compaction 和 surface replacement 不会抹除先前计费。
 
 token-meter 还拥有在持久事件上运行的共享纯 attempt／Turn fold。它采用相同的重试边界，并增加精确单轮次 disclosure 所需的更严格完整性与精确总量检查。展示消费方可以选择完整 Turn 窗口并调用该 fold，但不拥有或复制记账语义。
 

.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md
-2026-07-30-session-end-seed-log-boundary.md: c6ed3911a797480804d064273922d85412664c79
-2026-07-30-session-end-seed-log-boundary.zh.md: 1e9517f9a5aed819fdaff6194ab952c322c85b82
+2026-07-30-session-end-seed-log-boundary.md: aeec2a36d0b1e498591ef509e2e9164f586ed60c
+2026-07-30-session-end-seed-log-boundary.zh.md: ceba46a474c402230dbf215a2d53a41d3c027fc2

.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md

@@ -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 that capture begins with the current lifecycle's newly appended boundary and excludes the 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.

.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md

@@ -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 的接管测试断言捕获从当前生命周期新追加的边界开始，并排除 constructor seed；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。

.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.md
-2026-08-04-configuration-source-ownership.md: 1fe5908ab77632732996bd1d5c1eed9c8ab048e6
-2026-08-04-configuration-source-ownership.zh.md: 197cb936cdff303e23425d008c7a2cb738500ae0
+2026-08-04-configuration-source-ownership.md: 29dd5fd623d38532502af8c4e4afd972236fc139
+2026-08-04-configuration-source-ownership.zh.md: e5cbf70826b9314daccb7a62e5da4603e38158de

.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.md

@@ -42,7 +42,7 @@ The launching environment wins because `DEEPSEEK_API_KEY=… dsh`, a CI secret,
 
 **The project the harness is launched in is trusted, by default and without a prompt.** A checkout may carry its own endpoint, its own ordinary variables, and its own key; the key ranks below the managed store, so a key stored through the Models page is never displaced by one a checkout happens to contain. `LaunchEnvironmentSnapshot.getFrom(name, sources)` still searches only the layers a caller names, and omitting one is a refusal rather than a demotion — the mechanism exists for decisions where a layer must be unreachable; this decision includes the project layer.
 
-**Trust does not extend to changing the harness itself.** `loadLayeredEnv` rejects, at load and before anything is materialized, any `.env` that sets a variable governing how a process launches (`PATH`, `SHELL`, `NODE_OPTIONS`, `LD_PRELOAD`), which ambient program handles an operation (`EDITOR`, `PAGER`, `BROWSER`), what code a runtime executes before the program it was asked to run (`BASH_ENV`, `PERL5OPT`, `PYTHONSTARTUP`, `RUBYOPT`, `JAVA_TOOL_OPTIONS`, the Git hook commands), where model-visible instructions load from (the whole `DSH_*` namespace, `HOME`, `XDG_*`), or how the network is reached and trusted (proxy and CA variables). Matching is case-insensitive, so `https_proxy` is not a bypass.
+**Trust does not extend to changing the harness itself.** `loadLayeredEnv` rejects, at load and before anything is materialized, any `.env` that sets a variable governing how a process launches (`PATH`, `SHELL`, `NODE_OPTIONS`, `LD_PRELOAD`), which ambient program handles an operation (`EDITOR`, `PAGER`, `BROWSER`), what code a runtime executes before the program it was asked to run (`BASH_ENV`, `PERL5OPT`, `PYTHONSTARTUP`, `RUBYOPT`, `JAVA_TOOL_OPTIONS`, the Git hook commands), where model-visible instructions load from (the whole `DSH_*` namespace, `HOME`, `XDG_*`), or how the network is reached and trusted (proxy and CA variables). Matching is case-insensitive, so `https_proxy` is not a bypass. One exemption, recorded in [the proxy policy note](2026-08-27-outbound-proxy-policy.md): the four proxy names are accepted from `$DSH_HOME/.env`, which no `.env` can relocate, and still refused from the invoking directory's file.
 
 The line is that these take effect with no user action, before any turn, outside the permission policy and the sandbox. `DSH_PERMISSION_MODE` would switch off the approvals that make trusting a project meaningful at all, and `BASH_ENV` runs a file of the project's choosing on every single `bash -c` the bash tool issues — the project's code running under the agent's policy is the deal; the project rewriting that policy is not. Enumerating these is a losing game one variable at a time, which is why the whole `DSH_*` namespace is denied rather than an audited subset, and why the list is organised by what a variable *does* rather than by which runtime owns it. There is no opt-out: an escape hatch would have to be readable from somewhere, and anything a discovered file could set is the hole itself.
 
@@ -53,7 +53,7 @@ The line is that these take effect with no user action, before any turn, outside
 ## Consequences
 
 - The web credential form now takes effect against an older key in the user's `.env`; only a key exported in the launching shell still makes it read-only, and the diagnostic says so.
-- A `.env` holding `DSH_*`, `PATH`, `BROWSER`, or a proxy variable fails the launch instead of being applied. Developers keeping switches in a repository `.env` move them to their shell — a deliberate, loud break.
+- A `.env` holding `DSH_*`, `PATH`, `BROWSER`, or — in the invoking directory — a proxy variable fails the launch instead of being applied. Developers keeping switches in a repository `.env` move them to their shell — a deliberate, loud break.
 - Composition is no longer overridable by a stale shell endpoint. It is still overridable by a user's stored `settings.yaml`, which is the settings seam's layering and not something this note changes; the product CLI offers no flag above it, so a deployment that must win against stored settings owns its own bin or loader tree.
 - Not solved: the layers are still materialized into `process.env`, so ordinary project variables continue to reach child processes under the subprocess scrub. Bootstrap variables cannot come from a file at all; the environment package records the remaining subprocess reach as a limitation.
 - Exa and Perplexity still capture their key at load time rather than through the credential seam. They no longer read raw `process.env` — they resolve through the trusted layers — but converting them to per-request credential resolution is separate work.

.agents/notes/implemented/architecture/2026-08-04-configuration-source-ownership.zh.md

@@ -43,7 +43,7 @@ inherited process environment      (read-only, wins)
 
 **harness 被启动于其中的项目默认可信，且不做询问。** 一个 checkout 可以携带自己的 endpoint、自己的普通变量和自己的密钥；密钥排在受管存储之下，因此通过 Models 页存下的密钥绝不会被 checkout 中恰好带有的那一个顶掉。`LaunchEnvironmentSnapshot.getFrom(name, sources)` 仍然只搜索调用方点名的层，省略某层仍是拒绝而不是降级——该机制供要求某一层不可达的决策使用；本决策包含项目层。
 
-**信任不延伸到改变 harness 本身。** `loadLayeredEnv` 会在加载时、且在物化任何内容之前，拒绝任何设置了下列变量的 `.env`：决定进程如何启动的（`PATH`、`SHELL`、`NODE_OPTIONS`、`LD_PRELOAD`）、决定由哪个环境程序处理一项操作的（`EDITOR`、`PAGER`、`BROWSER`）、决定运行时在执行被要求运行的程序之前先执行哪些代码的（`BASH_ENV`、`PERL5OPT`、`PYTHONSTARTUP`、`RUBYOPT`、`JAVA_TOOL_OPTIONS`、Git 的钩子命令）、决定模型可见指令从哪里加载的（整个 `DSH_*` 命名空间、`HOME`、`XDG_*`），以及决定网络如何访问以及如何建立信任的（proxy 与 CA 变量）。匹配不区分大小写，因此 `https_proxy` 不是绕过手段。
+**信任不延伸到改变 harness 本身。** `loadLayeredEnv` 会在加载时、且在物化任何内容之前，拒绝任何设置了下列变量的 `.env`：决定进程如何启动的（`PATH`、`SHELL`、`NODE_OPTIONS`、`LD_PRELOAD`）、决定由哪个环境程序处理一项操作的（`EDITOR`、`PAGER`、`BROWSER`）、决定运行时在执行被要求运行的程序之前先执行哪些代码的（`BASH_ENV`、`PERL5OPT`、`PYTHONSTARTUP`、`RUBYOPT`、`JAVA_TOOL_OPTIONS`、Git 的钩子命令）、决定模型可见指令从哪里加载的（整个 `DSH_*` 命名空间、`HOME`、`XDG_*`），以及决定网络如何访问以及如何建立信任的（proxy 与 CA 变量）。匹配不区分大小写，因此 `https_proxy` 不是绕过手段。唯一的豁免记录在[代理策略笔记](2026-08-27-outbound-proxy-policy.zh.md)中：四个代理名可从 `$DSH_HOME/.env` 接受——没有任何 `.env` 能挪动该文件——但仍拒绝来自调用目录文件的同名变量。
 
 这条界线在于：它们无需任何用户动作、在任何轮次开始之前、且在权限策略与沙箱之外就生效。`DSH_PERMISSION_MODE` 会关掉让「信任项目」根本成立的那道审批，而 `BASH_ENV` 会在 bash 工具每次发出 `bash -c` 时执行项目指定的文件——项目的代码在 agent（智能体）的策略下运行是约定，项目改写那份策略不是。一个变量一个变量地枚举是必输的游戏，所以整个 `DSH_*` 命名空间被拒绝而不是只拒绝一份经审查的子集，也所以这份清单是按变量*做什么*而不是按哪个运行时拥有它来组织的。不设逃生门：逃生门本身总得从某处读取，而任何被发现的文件能设置的东西，就是那个漏洞本身。
 
@@ -54,7 +54,7 @@ inherited process environment      (read-only, wins)
 ## Consequences
 
 - Web 凭据表单现在能压过用户 `.env` 里更旧的密钥；只有在启动 shell 里 export 的密钥才会让它变成只读，诊断信息也会这么说。
-- 含 `DSH_*`、`PATH`、`BROWSER` 或 proxy 变量的 `.env` 会导致启动失败而不是被应用。把开关放在仓库 `.env` 里的开发者需要改放到 shell——这是一次刻意且响亮的破坏。
+- 含 `DSH_*`、`PATH`、`BROWSER` 或（在调用目录中）proxy 变量的 `.env` 会导致启动失败而不是被应用。把开关放在仓库 `.env` 里的开发者需要改放到 shell——这是一次刻意且响亮的破坏。
 - composition 不再会被陈旧的 shell endpoint 覆盖。但它仍然会被用户已存的 `settings.yaml` 覆盖，这是 settings seam 的分层方式，本 Note 不改变它；产品 CLI 没有高于它的标志，因此需要压过已存 settings 的部署方要自带 bin 或 loader 配置树。
 - 未解决的：各层仍然会被物化进 `process.env`，因此普通项目变量继续按子进程清洗规则抵达子进程。bootstrap 变量完全不能来自文件；环境包将其余变量仍可抵达子进程这一点记录为一项限制。
 - Exa 与 Perplexity 仍在加载时捕获密钥，而不是经凭据 seam。它们不再读裸 `process.env`——改为经受信层解析——但把它们改造成按请求解析凭据是另一件事。

.agents/notes/implemented/architecture/2026-08-04-draft-provider-endpoint-interrogation.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-04-draft-provider-endpoint-interrogation.md
-2026-08-04-draft-provider-endpoint-interrogation.md: d4112d813ad4f5781b74639209d13952e459f7dd
-2026-08-04-draft-provider-endpoint-interrogation.zh.md: 1626a34cb3163949d70688cefeec77d328c62caa
+2026-08-04-draft-provider-endpoint-interrogation.md: a6d8d32f12711744cb1380d2ab2767dcd3dd63f6
+2026-08-04-draft-provider-endpoint-interrogation.zh.md: e162ddb30706e871a2a42b5bbe7e09a451296289

.agents/notes/implemented/architecture/2026-08-04-draft-provider-endpoint-interrogation.md

@@ -6,7 +6,7 @@ English | [中文](2026-08-04-draft-provider-endpoint-interrogation.zh.md)
 
 ## Problem
 
-Once a pi-ai route became [a declaration rather than a catalog lookup](2026-08-03-pi-ai-declared-provider-catalog.md), a person adding an OpenAI-compatible gateway had to know its model ids before they could configure it. The adapter no longer constrains them to an installed catalog, which is the point, but it also means nothing tells the user what the endpoint actually serves — and most of these endpoints do publish that list at `GET /models`.
+Once a pi-ai route became [a declaration rather than a catalog lookup](2026-08-03-pi-ai-declared-provider-catalog.md), a person adding a compatible gateway had to know its model ids before they could configure it. The adapter no longer constrains them to an installed catalog, which is the point, but it also means nothing tells the user what the endpoint actually serves — and OpenAI- and Anthropic-compatible endpoints publish that list through protocol-specific model-listing routes.
 
 The obvious answer, a dynamic runtime catalog refreshed in the background, was rejected with the layer below it: it makes a route's model list external mutable state needing a cache, an invalidation story, and an offline path, while the product need is narrower. What is needed is a *question asked once*, whose answer the user adopts into `settings.yaml` — so `settings.yaml` remains the only thing deciding what a route serves.
 
@@ -21,7 +21,7 @@ Interrogation is keyed by **settings namespace**, not by provider route:
 - `LlmDiscoveredModel` makes every field but `id` optional, because most listings disclose an id and nothing else. The reply is candidates, not a catalog: a surface adopting one still owes the capacities the adapter requires.
 - `llm.discoverModels` carries the same draft over the wire. Its `apiKey` is the third and last payload on which a secret may ride, alongside `settings.update`/`mutate` and `credentials.set`, and it is never stored or echoed back. It does ride the client's outgoing envelope like every other secret-bearing payload, where a `subscribeEnvelopes()` observer can see it; redacting that tap is a configuration-plane-wide change, not this method's to make alone. Connection authenticates the method with the complete Host API: it makes the host issue a GET to a caller-chosen URL and reports the outcome, which an anonymous caller must not receive. Every refusal folds into `model-discovery-failed`, whose message is the adapter's own text and whose details name the endpoint asked but never the credential offered.
 
-`dsh-llm-pi-ai` implements the wire path as a plain `GET {baseURL}/models`, reading `openai-completions` and `openai-responses`: their `GET /models` shape with bearer auth is the one a gateway, a self-hosted server, and the official endpoints all agree on. Profile resolution rejects names and values Fetch cannot represent, so a malformed deployment header is reported as a configuration error before interrogation. Configured profile headers are installed first; the fixed JSON accept header, a typed-or-stored bearer credential, and Harness attribution then win case-insensitive collisions in that order. Azure is excluded despite its OpenAI lineage — it authenticates with an `api-key` header and requires an `api-version` query — and Codex uses OAuth; both would have reported an authentication failure as a provider with no models. Every other protocol answers `DISCOVERY_UNSUPPORTED`, so the surface falls back to hand-entry rather than reporting a guessed response shape as an empty provider. `baseURL` is treated as a prefix rather than a URL to resolve against, so a deployment path such as `https://gateway.example/openai/v1` keeps its segments. The reply is read under a four-megabyte ceiling enforced on the bytes actually received — the endpoint is a URL the user typed, so a declared `content-length` is checked first as a courtesy but never trusted as the bound, matching `dsh-web-fetch`'s two-stage shape for its own caller-supplied URLs.
+`dsh-llm-pi-ai` applies the protocol-specific listing routes, authentication, URL normalization, response formats, and metadata rules recorded by [protocol-specific model listing discovery](2026-09-02-protocol-specific-model-listing-discovery.md). Profile resolution rejects names and values Fetch cannot represent, so a malformed deployment header is reported as a configuration error before interrogation. Configured profile headers are installed first; fixed protocol headers, a typed-or-stored protocol credential, and Harness attribution then win their case-insensitive collisions. A protocol without a documented listing contract answers `DISCOVERY_UNSUPPORTED`, so the surface falls back to hand-entry rather than reporting guessed response fields as an empty provider. `baseURL` is treated as a prefix rather than a URL to resolve against, so deployment path segments remain intact. The reply is read under a four-megabyte ceiling enforced on the bytes actually received — the endpoint is a URL the user typed, so a declared `content-length` is checked first as a courtesy but never trusted as the bound, matching `dsh-web-fetch`'s two-stage pattern for its own caller-supplied URLs.
 
 ### Why not pi-ai's own refresh machinery
 
@@ -35,16 +35,16 @@ pi-ai supplies `createProvider({ fetchModels })` plus `Models.refresh()` and a `
 
 **Have the host read the entire stored profile instead of accepting a draft.** No secret would cross the wire for an already-configured provider. But adding a provider would then require saving an unusable configuration first, and a form whose endpoint was edited but not yet saved would silently interrogate the old one. The draft remains authoritative for the endpoint and protocol. The narrow Host-side exceptions are the stored credential, which is write-only, and profile headers, which remain deployment configuration rather than Models-page fields.
 
-**Interrogate every pi-ai protocol.** Anthropic's listing happens to share OpenAI's envelope, and Google's does not. Supporting the ones that are easy would make coverage arbitrary and, worse, make a wrong guess at a response shape indistinguishable from a provider with no models. A protocol that says it cannot be interrogated sends the user to hand-entry, which is the documented fallback.
+**Interrogate every pi-ai protocol.** Coverage based on convenient response similarities would be arbitrary and would make a wrong guess indistinguishable from a provider with no models. Anthropic is included only through its documented native listing contract, as the [protocol-specific extension](2026-09-02-protocol-specific-model-listing-discovery.md) records; Google's field set and Azure's request contract differ, while Codex uses OAuth. An unsupported protocol sends the user to hand-entry, which remains the documented fallback.
 
 **Buffer the reply with `response.text()` and check its length.** Simpler, but the bound would arrive after the bytes did, and the endpoint is whatever URL the user typed.
 
 ## Consequences
 
-A person adding a gateway can ask it what it serves instead of hunting through its documentation, and the answer arrives as candidates they choose from rather than as configuration written behind their back. An already-configured enterprise gateway uses the same deployment headers for interrogation and model requests without adding a header injection field to the browser protocol. The seam gained a registry that is deliberately small: one offer per namespace, no storage, no lifecycle beyond the fiber.
+A person adding a gateway can ask it what it serves instead of hunting through its documentation, and the answer arrives as candidates they choose from rather than as configuration written behind their back. When an endpoint discloses richer metadata, adopting a candidate fills its id, name, context window, and output-token cap into the editable Web row. Search preserves hidden selections, selecting all adds the visible results, and deselecting all clears every result so a filtered picker cannot submit hidden models accidentally. An already-configured enterprise gateway uses the same deployment headers and Harness `User-Agent` for interrogation and model requests without adding a header injection field to the browser protocol. The seam gained a registry that is deliberately small: one offer per namespace, no storage, no lifecycle beyond the fiber.
 
-What it costs: the wire gained a third secret-carrying payload, so the configuration plane's write-only surface is now three methods rather than two. Discovery coverage is protocol-shaped rather than provider-shaped — an Anthropic-compatible gateway must be filled in by hand even though its listing would parse. And because nothing re-runs the question, a model list is still only as current as its last edit; that is the same trade the layer below made deliberately.
+What it costs: the wire gained a third secret-carrying payload, so the configuration plane's write-only surface is now three methods rather than two. Discovery coverage remains protocol-shaped rather than provider-shaped, and an endpoint using an unsupported request contract must be filled in by hand. Because nothing re-runs the question, a model list is still only as current as its last edit; that is the same trade the layer below made deliberately.
 
 ## Testing
 
-`packages/llm/llm/tests/topology.spec.ts` covers the registry: one offer per namespace, disposal with the fiber, normalization that drops duplicate and unusable ids without inventing capacities, the `NO_DISCOVERY`/`INVALID_DISCOVERY` refusals, and the `model-discovery-failed` Remote mapping. `packages/llm/llm-pi-ai/tests/discovery.spec.ts` drives the probe against local HTTP servers — a listing with and without disclosed capacities, a preserved deployment path, an absent credential, a configured route supplying its stored credential and headers while a typed key wins without resolving the stored one, a catalog route answering without resolving one at all, dropped rows, 401/403 versus a server fault, a non-listing and a non-JSON body, an unreachable endpoint, caller cancellation, an unsupported protocol, and the size ceiling in both its declared-length and streamed forms. `packages/llm/llm-pi-ai/tests/loader-composition.spec.ts` boots settings and credentials through the Loader and proves settings-only headers reach `GET /models` with request-owned headers winning collisions. `packages/llm/llm-pi-ai/tests/adapter.spec.ts` rejects profile headers Fetch cannot represent, and `packages/llm/llm-pi-ai/tests/dynamic-config.spec.ts` proves a settings write reports that configuration error while its last good routes keep serving. `packages/client/connection/tests/node-half.host.spec.ts` pins the `llm/discoverModels` `/api` carrier registration, while `packages/client/ui-settings-models/tests/provider-form.client.spec.tsx` verifies that the draft reaches the Remote whole, absent fields stay absent, and no settings namespace or credential is written before selection.
+`packages/llm/llm/tests/topology.spec.ts` covers the registry: one offer per namespace, disposal with the fiber, normalization that drops duplicate and unusable ids without inventing capacities, the `NO_DISCOVERY`/`INVALID_DISCOVERY` refusals, and the `model-discovery-failed` Remote mapping. `packages/llm/llm-pi-ai/tests/discovery.spec.ts` drives the probe against local HTTP servers — standard arrays and enriched objects with every accepted metadata spelling, Anthropic's native path, headers, and capacity fields, route keys that differ from nested canonical ids, name fallback, a preserved deployment path, an absent credential, a configured route supplying its stored credential and headers while a typed key wins without resolving the stored one, a catalog route answering without resolving one at all, dropped rows, 401/403 versus a server fault, a non-listing and a non-JSON body, an unreachable endpoint, caller cancellation, an unsupported protocol, and the size ceiling in both its declared-length and streamed forms. `packages/llm/llm-pi-ai/tests/loader-composition.spec.ts` boots settings and credentials through the Loader and proves settings-only headers reach `GET /models` with request-owned headers winning collisions. `packages/llm/llm-pi-ai/tests/adapter.spec.ts` rejects profile headers Fetch cannot represent, and `packages/llm/llm-pi-ai/tests/dynamic-config.spec.ts` proves a settings write reports that configuration error while its last good routes keep serving. `packages/client/connection/tests/node-half.host.spec.ts` pins the `llm/discoverModels` `/api` carrier registration, while the component and built-Web settings tests verify that the complete draft reaches the Remote, absent fields stay absent, selected metadata fills all four editable model fields, tuned rows win over rediscovery, filtered deselection clears hidden candidates, and no settings namespace or credential is written before selection.

.agents/notes/implemented/architecture/2026-08-04-draft-provider-endpoint-interrogation.zh.md

@@ -6,7 +6,7 @@ Status: implemented
 
 ## Problem
 
-当 pi-ai 路由变成[一份声明而非 catalog 查表](2026-08-03-pi-ai-declared-provider-catalog.zh.md)之后，要接入一个 OpenAI 兼容网关的人，必须先知道它的模型 id 才能完成配置。适配器不再把人限制在已安装 catalog 里——这正是那次改动的目的——但也意味着没有任何东西告诉用户该端点究竟服务什么，而这类端点大多在 `GET /models` 上公布了这份列表。
+当 pi-ai 路由变成[一份声明而非 catalog 查表](2026-08-03-pi-ai-declared-provider-catalog.zh.md)之后，要接入一个兼容网关的人，必须先知道它的模型 id 才能完成配置。适配器不再把人限制在已安装 catalog 里——这正是那次改动的目的——但也意味着没有任何东西告诉用户该端点究竟服务什么，而 OpenAI 与 Anthropic 兼容端点会通过各自协议的模型列表路由公布这份信息。
 
 显而易见的答案——后台刷新的运行时动态 catalog——已随下层一并被拒绝：它会把路由的模型列表变成需要缓存、失效语义与离线路径的外部可变状态，而产品需求要窄得多。真正需要的是*一次性询问*，其答案由用户采纳进 `settings.yaml`，从而让 `settings.yaml` 始终是决定路由服务内容的唯一真源。
 
@@ -21,7 +21,7 @@ Status: implemented
 - `LlmDiscoveredModel` 除 `id` 外每个字段都可选，因为大多数列表只公布 id。回复是候选而非 catalog：采纳其中一条的界面仍要补上适配器所需的容量。
 - `llm.discoverModels` 把同一份草稿送过协议层。它的 `apiKey` 是可承载机密的第三个、也是最后一个载荷（另两个是 `settings.update`/`mutate` 与 `credentials.set`），且绝不被存储或回显。它确实会像其他承载机密的载荷一样随客户端外发信封同行，`subscribeEnvelopes()` 观察者看得到；把那个抽头脱敏是整个配置面的改动，不该由这一个方法独自决定。Connection 用与完整 Host API 相同的会话认证该方法：它让宿主向调用方选定的 URL 发起 GET 并回报结果，匿名调用者绝不能获得这类探测能力。每一种拒绝都折叠为 `model-discovery-failed`，其消息是适配器自己的文本，details 点名被询问的端点，绝不点名所提供的凭据。
 
-`dsh-llm-pi-ai` 的实现只是一次朴素的 `GET {baseURL}/models`，且仅限 OpenAI 兼容协议。它们的列表形状是网关、自建服务与官方端点三方一致认可的那一种，而这正是该动作存在的场景。Profile 解析会拒绝 Fetch 无法表示的名称与值，因此格式错误的部署 header 会在询问前以配置错误报告。已配置的 profile headers 最先装入；固定的 JSON accept header、键入或已存的 bearer 凭据以及 Harness attribution 随后依次以大小写不敏感方式赢得冲突。其余协议一律以 `DISCOVERY_UNSUPPORTED` 回答，让界面回退到手工填写，而不是把猜错的响应形状报成一个空提供方。`baseURL` 按前缀而非待解析 URL 处理，因此 `https://gateway.example/openai/v1` 这类部署路径会保留其路径段。回复在四兆字节上限下读取，且上限落在实际收到的字节上——端点是用户自己填的 URL，因此会先看声明的 `content-length` 作为善意提示，但绝不把它当作边界；这与 `dsh-web-fetch` 面对自己的调用方提供 URL 时所用的两段式形状一致。
+`dsh-llm-pi-ai` 会应用[协议特定模型列表发现](2026-09-02-protocol-specific-model-listing-discovery.zh.md)记录的列表路由、认证、URL 归一化、响应格式与元数据规则。Profile 解析会拒绝 Fetch 无法表示的名称与值，因此格式错误的部署 header 会在询问前以配置错误报告。已配置的 profile headers 最先装入；固定协议 headers、键入或已存的协议凭据以及 Harness attribution 随后分别以大小写不敏感方式赢得相应冲突。没有文档化列表约定的协议会以 `DISCOVERY_UNSUPPORTED` 回答，让界面回退到手工填写，而不是把猜错的响应字段报成一个空提供方。`baseURL` 按前缀而非待解析 URL 处理，因此部署路径段会保持不变。回复在四兆字节上限下读取，且上限落在实际收到的字节上——端点是用户自己填的 URL，因此会先看声明的 `content-length` 作为善意提示，但绝不把它当作边界；这与 `dsh-web-fetch` 面对自己的调用方提供 URL 时所用的两段式模式一致。
 
 ### 为什么不用 pi-ai 自己的 refresh 机制
 
@@ -35,16 +35,16 @@ pi-ai 提供了 `createProvider({ fetchModels })` 加上 `Models.refresh()` 与
 
 **让 Host 读取整个已存 profile，而不是接受草稿。** 对已配置好的提供方来说，不会有机密跨越协议层。但这样一来新增提供方就必须先保存一份不可用的配置，而端点已改却尚未保存的表单会静默地去询问旧地址。草稿仍是端点和协议的权威来源。Host 侧的狭窄例外是只写的已存凭据，以及仍属部署配置、而非 Models 页面字段的 profile headers。
 
-**询问 pi-ai 的每一种协议。** Anthropic 的列表恰好与 OpenAI 共用同一层信封，而 Google 的不是。只支持容易的那几种会让覆盖范围变得任意；更糟的是，猜错的响应形状会与「该提供方没有模型」无法区分。一个明说自己无法被询问的协议，会把用户送去手工填写——那正是既定的回退路径。
+**询问每一种 pi-ai 协议。** 根据便利的响应相似性选择覆盖范围会显得武断，也会让猜错的响应与「提供方没有模型」无法区分。Anthropic 仅通过其文档化原生列表约定纳入支持，具体由[协议特定扩展](2026-09-02-protocol-specific-model-listing-discovery.zh.md)记录；Google 的字段集合与 Azure 的请求约定不同，Codex 则使用 OAuth。不支持的协议会把用户送去手工填写，这仍是既定回退路径。
 
 **用 `response.text()` 缓冲整个回复再判断长度。** 更简单，但上限会在字节已经到达之后才生效，而端点是用户随手填的任意 URL。
 
 ## Consequences
 
-接入网关的人可以直接问它服务什么，而不必去翻它的文档；答案以候选形式抵达，由用户自己挑选，而不是被背着写进配置。已配置的企业网关会为询问与模型请求使用同一组部署 headers，而无需给浏览器协议增加 header 注入字段。seam 因此多了一个刻意保持很小的注册表：每个 namespace 一份、不存储、生命周期不超出 fiber。
+接入网关的人可以直接问它服务什么，而不必去翻它的文档；答案以候选形式抵达，由用户自己挑选，而不是被背着写进配置。当端点公布了更丰富的元数据时，采纳候选会把 id、名称、上下文窗口与最大输出 token 数填进 Web 的可编辑行。搜索会保留隐藏项的勾选状态，全选会加入可见结果，而取消全选会清空全部结果，因此筛选后的选择器不会意外提交隐藏模型。已配置的企业网关会为询问与模型请求使用同一组部署 headers 和 Harness `User-Agent`，而无需给浏览器协议增加 header 注入字段。seam 因此多了一个刻意保持很小的注册表：每个 namespace 一份、不存储、生命周期不超出 fiber。
 
-代价是：协议层多了第三个承载机密的载荷，配置面的只写接口从两个方法变成三个。发现覆盖范围按协议而非按提供方划分——一个 Anthropic 兼容网关即便其列表能被解析，也仍须手工填写。而且由于没有任何环节会重跑该询问，模型列表的新鲜度依旧只到最近一次编辑为止；这与下层刻意做出的取舍是同一个。
+代价是：协议层多了第三个承载机密的载荷，配置面的只写接口从两个方法变成三个。发现覆盖范围仍按协议而非按提供方划分，使用不受支持请求约定的端点仍须手工填写。由于没有任何环节会重跑该询问，模型列表的新鲜度依旧只到最近一次编辑为止；这与下层刻意做出的取舍是同一个。
 
 ## Testing
 
-`packages/llm/llm/tests/topology.spec.ts` 覆盖注册表：每个 namespace 一份、随 fiber dispose（资源释放）、丢弃重复与不可用 id 且不凭空补容量的归一化、`NO_DISCOVERY`/`INVALID_DISCOVERY` 两种拒绝，以及 `model-discovery-failed` Remote 映射。`packages/llm/llm-pi-ai/tests/discovery.spec.ts` 针对本地 HTTP 服务器驱动探测——含与不含公布容量的列表、被保留的部署路径、无凭据、已配置路由提供自己的已存凭据与 headers 且键入的密钥无需解析已存凭据便可压过它、catalog 路由完全不解析凭据即作答、被丢弃的行、401/403 与服务器故障之别、非列表与非 JSON 响应、不可达端点、调用方取消、不支持的协议，以及尺寸上限的「声明长度」与「流式」两种形态。`packages/llm/llm-pi-ai/tests/loader-composition.spec.ts` 通过 Loader 启动 settings 与 credentials，并证明仅配置在 settings 中的 headers 会抵达 `GET /models`，且请求所持有的 headers 赢得冲突。`packages/llm/llm-pi-ai/tests/adapter.spec.ts` 拒绝 Fetch 无法表示的 profile headers，`packages/llm/llm-pi-ai/tests/dynamic-config.spec.ts` 证明 settings 写入会报告该配置错误，同时上一组可用路由仍继续服务。`packages/client/connection/tests/node-half.host.spec.ts` 固定 `llm/discoverModels` 的 `/api` 承载注册，`packages/client/ui-settings-models/tests/provider-form.client.spec.tsx` 则验证草稿完整抵达 Remote、缺席字段保持缺席，以及选择前没有 settings namespace 或凭据被写入。
+`packages/llm/llm/tests/topology.spec.ts` 覆盖注册表：每个 namespace 一份、随 fiber dispose（资源释放）、丢弃重复与不可用 id 且不凭空补容量的归一化、`NO_DISCOVERY`/`INVALID_DISCOVERY` 两种拒绝，以及 `model-discovery-failed` Remote 映射。`packages/llm/llm-pi-ai/tests/discovery.spec.ts` 针对本地 HTTP 服务器驱动探测——包括采用每种受支持元数据拼写的标准数组与富信息对象、Anthropic 原生路径、headers 与容量字段、不同于嵌套规范 id 的路由键、名称回退、被保留的部署路径、无凭据、已配置路由提供自己的已存凭据与 headers 且键入的密钥无需解析已存凭据便可压过它、catalog 路由完全不解析凭据即作答、被丢弃的行、401/403 与服务器故障之别、非列表与非 JSON 响应、不可达端点、调用方取消、不支持的协议，以及尺寸上限的「声明长度」与「流式」两种形态。`packages/llm/llm-pi-ai/tests/loader-composition.spec.ts` 通过 Loader 启动 settings 与 credentials，并证明仅配置在 settings 中的 headers 会抵达 `GET /models`，且请求所持有的 headers 赢得冲突。`packages/llm/llm-pi-ai/tests/adapter.spec.ts` 拒绝 Fetch 无法表示的 profile headers，`packages/llm/llm-pi-ai/tests/dynamic-config.spec.ts` 证明 settings 写入会报告该配置错误，同时上一组可用路由仍继续服务。`packages/client/connection/tests/node-half.host.spec.ts` 固定 `llm/discoverModels` 的 `/api` 承载注册，而设置页的组件测试和构建后 Web 测试则验证完整草稿抵达 Remote、缺席字段保持缺席、所选元数据填满四个可编辑模型字段、用户调整过的行优先于重新发现结果、筛选后的取消选择会清除隐藏候选项，以及选择前没有 settings namespace 或凭据被写入。

.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.md
-2026-08-05-large-session-jsonl-restore-pipeline.md: 309d9dc6bdb5c3160f3e6e76a8318915df58fe59
-2026-08-05-large-session-jsonl-restore-pipeline.zh.md: 28acd3ebe804dca22a0619c257ff3ad9c09500a9
+2026-08-05-large-session-jsonl-restore-pipeline.md: e87777cc407e50a0e4808b77c3a7d554659d62e7
+2026-08-05-large-session-jsonl-restore-pipeline.zh.md: 32762bd19914423ef38c6472f0a8087e3e7e45fa

.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.md

@@ -30,7 +30,7 @@ The scanner stops retaining events at the first unparsable row or sequence gap b
 
 ### Restore admission
 
-Persistence transfers freshly materialized JSON values to `Session.fromRestore`. These values are detached, acyclic trees, and packed chunk rows expand into newly allocated events, so the restore-only path validates the fixed event envelope with one `for...in` and `switch`, dispatches current-shape checks by event discriminant, and iteratively freezes the owned graph with an explicit `pending` array and no cycle-tracking set. Surface validation records one transition plan and commits that plan when the exact candidate enters the log instead of planning the same event twice.
+Persistence transfers freshly materialized current JSON values to `Session.fromRestore`. These values are detached, acyclic trees; historical packed rows and adjacent migrations have already produced newly allocated v2 settlements. The restore-only path validates the fixed event envelope with one `for...in` and `switch`, dispatches current-shape checks by event discriminant, and iteratively freezes the owned graph with an explicit `pending` array and no cycle-tracking set. Surface validation records one transition plan and commits that plan when the exact candidate enters the log instead of planning the same event twice.
 
 Borrowed seeds used by ordinary creation and fork paths still take a JSON snapshot and use the generic cycle-safe deep freeze. The specialization therefore changes only durable restoration; it does not weaken acceptance for caller-owned values.
 

.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.zh.md

@@ -30,7 +30,7 @@ Zstandard 结构扫描器会在解码前识别完整帧范围。系统单独解
 
 ### 恢复准入
 
-持久化层把刚物化的 JSON 值转移给 `Session.fromRestore`。这些值是已分离且无环的树，打包的分片行也会展开成新分配的事件。因此，恢复专用路径使用一次 `for...in` 与 `switch` 校验固定事件信封，按事件判别字段执行当前数据形状检查，并通过显式 `pending` 数组迭代冻结所拥有的对象图，不使用循环跟踪集合。`surface` 校验会记录一次转换计划；当同一个候选事件进入日志时，系统直接提交该计划，不再对同一事件规划两次。
+持久化把刚物化的当前 JSON 值转移给 `Session.fromRestore`。这些值是已分离且无环的 tree；历史 packed row 与相邻 migration 已经生成新分配的 v2 settlement。restore-only path 使用一次 `for...in` 与 `switch` 校验固定 event envelope，按 event discriminant 执行当前表示检查，并通过显式 `pending` array 迭代冻结 owned object graph，不使用 cycle-tracking set。`surface` 校验记录一次 transition plan，并在同一个 candidate event 进入 log 时提交该 plan。
 
 普通创建与 fork 路径使用的借用 `seed` 仍会创建 JSON 快照，并使用支持循环检测的通用深度冻结。因此，这项特化仅改变持久恢复，不会放宽调用方所有值的准入要求。
 

.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.md
-2026-08-08-bounded-session-persistence-write-batching.md: 6fb44e494fc17bde08eb3132afe42ce73b5a4e47
-2026-08-08-bounded-session-persistence-write-batching.zh.md: 576764583dd8c465ae45866f62ef15773735961e
+2026-08-08-bounded-session-persistence-write-batching.md: 350a4dd7a4af64156b6d68939fbc10ea8f06b7b1
+2026-08-08-bounded-session-persistence-write-batching.zh.md: 495d7a7824fb2c622e37b5e233e4cb8fe45755de

.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.md

@@ -6,13 +6,13 @@ English | [中文](2026-08-08-bounded-session-persistence-write-batching.zh.md)
 
 ## Problem
 
-Streaming responses can emit many `assistant/chunk` events in a short interval. The persistence coordinator previously scheduled a provider append as soon as an idle queue received one event. Events arriving while that append was active shared a follow-up batch, but a fast provider could still produce many small durable appends. Each JSONL append creates and syncs a Zstandard frame or raw suffix.
+One agent step can emit several durable events in a short interval: request metadata, one Assistant settlement, tool lifecycles, plugin facts, and execution boundaries. Scheduling a provider append as soon as an idle queue receives one event can therefore produce many small durable appends. Each JSONL append creates and syncs a Zstandard frame or raw suffix.
 
-Dropping chunk events or replacing them with assembled messages would reduce logical storage, but it would also change the event log, replay, sequence numbers, timestamps, and the chunk seqs cited by assistant messages. The write-amplification problem does not require that larger semantic change.
+Assistant stream embedding reduces one high-volume event family, but write cadence remains a provider-neutral lifecycle concern for every other burst and for historical generations. The batching decision does not change event semantics or storage encoding.
 
 ### Quantified baseline
 
-Repository fixtures make the logical volume concrete. Decoding the current packed rows in [`goal-multi-turn-actions`](../../../../snapshots/web/goal-multi-turn-actions/session.jsonl) yields 2,098 events: 2,017 chunks (96.1%). Their unpacked JSONL lines occupy 332,647 of 379,225 event bytes (87.7%), while chunk packing reduces the committed file to 89,176 bytes and 182 storage rows, including 23 packed chunk rows. [`permission-policy-context`](../../../../snapshots/web/permission-policy-context/session.jsonl) yields 813 events: 746 chunks (91.8%) and 118,935 of 184,821 unpacked event bytes (64.4%); its packed file is 84,917 bytes and 123 storage rows, including 14 packed rows. These are tracked deterministic fixtures, not a production workload distribution, but they demonstrate why deleting chunks would reduce logical volume and why the existing packed-row layout already removes much of their JSON envelope cost.
+Released-v1 repository fixtures established the original logical volume. Decoding the packed `goal-multi-turn-actions` generation yielded 2,098 events, including 2,017 chunks (96.1%); unpacked chunk lines occupied 332,647 of 379,225 event bytes, while the packed file used 89,176 bytes and 182 rows. The packed `permission-policy-context` generation yielded 813 events, including 746 chunks (91.8%); unpacked chunk lines occupied 118,935 of 184,821 event bytes, while the packed file used 84,917 bytes and 123 rows. These deterministic historical measurements explain why v2 embeds streams, but they are not a production workload distribution or a current-format size claim.
 
 JSONL writes one Zstandard frame and fsync per durable append batch. Runtime files do not record former append boundaries, so fixture row counts cannot honestly be presented as fsync counts.
 
@@ -28,7 +28,7 @@ The window bounds only the controller's intentional batching wait. Event-loop sc
 
 `session/flush` cancels any remaining wait and becomes a shared quiescence barrier. It drains the active attempt and every event admitted while the barrier is running before it resolves. Session retirement (`session/disposed`), the handle's close, and backend teardown's close sweep use that same barrier, so lifecycle teardown never waits for the batching timer. The checkpoint policy continues to place mandatory barriers before model requests and top-level tool side effects.
 
-Every event remains durable in its original order and shape. The controller copies each event on admission; no `assistant/chunk`, `seq`, `time`, surface metadata, or storage record is removed or rewritten. JSONL can therefore encode more events in one append frame without changing its on-disk format.
+Every admitted event remains durable in its original order and representation. The controller copies each event on admission; batching removes or rewrites no sequence, timestamp, surface metadata, embedded Assistant stream, or storage record. JSONL can therefore encode more events in one append frame without changing the Session format.
 
 A failed background drain retains its complete batch in order ahead of newer pending events, reports the failure once, and pauses the automatic timer. The next explicit drain — a `session/flush` barrier, service-level `flush()`, or close — retries immediately and surfaces a repeated failure to its caller. This avoids a timer-driven failure loop while preserving the existing recoverable flush boundary.
 
@@ -36,7 +36,7 @@ This decision supersedes only the immediate scheduling cadence in [Collapse live
 
 ## Alternatives considered
 
-**Do not persist streaming chunk events.** Rejected here: it changes the event-sourced authority and recovery semantics rather than only physical write cadence. The existing [assembled-message rejection](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.md) remains the guardrail until a no-information-loss replacement defines replay, fork, cited source-event links, sequence, and crash behavior independently. The [packed-row decision](2026-07-26-packed-chunk-rows-by-default.md) remains the complementary JSONL storage-size optimization.
+**Use one settlement per Assistant attempt instead of batching writes.** The [v2 Assistant stream decision](2026-09-01-v2-embedded-assistant-streams.md) provides that no-information-loss event model and reduces Assistant event cardinality. It does not replace bounded batching for other adjacent events, historical-generation publication, or providers with the same append interface.
 
 **Write only at semantic checkpoints.** Rejected: it maximizes batching but makes the ordinary crash-loss window depend on a separately mounted policy. Bounded background writes preserve progress between checkpoints while mandatory flushes keep their stronger ordering contract.
 
@@ -50,10 +50,10 @@ The shared live-write contract suite (`runLiveWritePathContract`) uses a fake cl
 
 ## Consequences
 
-High-frequency event bursts normally produce fewer durable append operations while preserving the exact logical event count. The reduction depends on arrival rate and backend latency: a burst inside one 200 ms window becomes one batch, while mandatory flushes and sparse events can still produce small batches.
+High-frequency event bursts normally produce fewer durable append operations while preserving the exact admitted event sequence. The reduction depends on arrival rate and backend latency: a burst inside one 200 ms window becomes one batch, while mandatory flushes and sparse events can still produce small batches.
 
 This decision does not cap pending event count or bytes behind a slow provider, and it does not reduce the decoded logical log. A demonstrated memory bound or logical-retention policy would require its own failure and replay contract rather than another hidden timer rule.
 
 An admitted event can remain only in memory during the fixed window, and then while scheduling or backend work is outstanding. Explicit durability boundaries remain unchanged and bypass the wait.
 
-The handle gives the timer, active drain, pending prefix, retry pause, and barrier one owner; the backend's listeners own routing and lifecycle-driven drains. `SESSION_FORMAT_VERSION` remains unchanged.
+The handle gives the timer, active drain, pending prefix, retry pause, and barrier one owner; the backend's listeners own routing and lifecycle-driven drains. Batching itself never changes `SESSION_FORMAT_VERSION`.

.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.zh.md

@@ -6,13 +6,13 @@ Status: implemented
 
 ## 问题
 
-流式响应可能会在短时间内发出大量 `assistant/chunk` 事件。此前，只要空闲队列收到一个事件，持久化协调器就会立即调度一次 provider 追加。该追加仍在进行时到达的事件会共用一个后续批次，但如果 provider 速度很快，仍可能产生大量小规模的持久化追加。每次 JSONL 追加都会创建并同步一个 Zstandard 帧或原始格式后缀。
+一个 agent 步骤可以在短时间内发出多个持久事件：请求元数据、一个 Assistant settlement、工具生命周期、插件事实与执行边界。只要空闲队列收到一个事件就立即调度 provider 追加，仍可能产生大量小规模的持久化追加。每次 JSONL 追加都会创建并同步一个 Zstandard 帧或原始格式后缀。
 
-丢弃分片事件或用组装后的消息替代它们可以减少逻辑存储量，但也会改变事件日志、回放、序列号、时间戳，以及助手消息引用的分片 seq。写放大问题不要求采取这项语义变化更大的方案。
+Assistant stream 嵌入会减少一个高频事件 family，但对于其他事件突发与历史 generation，写入节奏仍是 provider-neutral 生命周期问题。批处理决策不会改变事件语义或存储编码。
 
 ### 量化基线
 
-仓库 fixture（测试前置数据）让逻辑数据量有了具体依据。对当前 [`goal-multi-turn-actions`](../../../../snapshots/web/goal-multi-turn-actions/session.jsonl) 中的打包行进行解码，可得到 2,098 个事件，其中 2,017 个是分片（96.1%）。这些分片解包后的 JSONL 行共 332,647 字节，占全部事件 379,225 字节的 87.7%；分片打包则把仓库中的已提交文件缩小到 89,176 字节和 182 个存储行，其中包括 23 个打包分片行。[`permission-policy-context`](../../../../snapshots/web/permission-policy-context/session.jsonl) 可得到 813 个事件，其中 746 个是分片（91.8%）；这些分片解包后的 JSONL 行共 118,935 字节，占全部事件 184,821 字节的 64.4%。其打包文件为 84,917 字节，共 123 个存储行，其中包括 14 个打包行。这些是纳入版本控制的确定性 fixture，不代表生产工作负载分布；但它们说明了删除分片为何会降低逻辑数据量，也说明现有打包行布局已经消除了大量 JSON 包装开销。
+已发布 v1 仓库 fixture 建立了原始逻辑数据量。解码 packed `goal-multi-turn-actions` generation 得到 2,098 个事件，其中 2,017 个是 chunk（96.1%）；解包的 chunk 行占 379,225 个事件字节中的 332,647 字节，而 packed 文件使用 89,176 字节与 182 行。packed `permission-policy-context` generation 得到 813 个事件，其中 746 个是 chunk（91.8%）；解包的 chunk 行占 184,821 个事件字节中的 118,935 字节，而 packed 文件使用 84,917 字节与 123 行。这些确定性历史测量解释了 v2 为何嵌入 stream，但不代表生产工作负载分布或当前格式大小。
 
 JSONL 每个持久化追加批次会写入一个 Zstandard 帧并执行一次 fsync。运行时文件不记录原有追加边界，因此不能把 fixture 的存储行数当作 fsync 次数。
 
@@ -28,7 +28,7 @@ JSONL 每个持久化追加批次会写入一个 Zstandard 帧并执行一次 fs
 
 `session/flush` 会取消剩余等待，并充当共享的完全停稳屏障。它会在完成前等待活跃写入尝试，并排空屏障运行期间接纳的每个事件。会话退役（`session/disposed`）、句柄的 close 与后端 teardown 的关闭清扫共用该屏障，因此生命周期 teardown 绝不会等待批处理计时器。检查点策略仍会在模型请求与顶层工具副作用之前设置强制屏障。
 
-每个事件仍会按原有顺序和形态持久化。控制器会在接纳时复制每个事件；任何 `assistant/chunk`、`seq`、`time`、surface 元数据或存储记录都不会被删除或重写。因此，JSONL 可以在一个追加帧中编码更多事件，而无需改变其磁盘格式。
+每个已接纳事件仍会按原有顺序和表示持久化。控制器会在接纳时复制每个事件；批处理不会删除或改写任何序号、时间戳、surface 元数据、嵌入式 Assistant stream 或存储记录。因此，JSONL 可以在一个追加 frame 中编码更多事件，而无需改变 Session 格式。
 
 后台排空失败后，其完整批次会按顺序保留在所有较新的待处理事件之前，该失败被报告一次，自动计时器随之暂停。下一次显式排空——`session/flush` 屏障、服务级 `flush()` 或 close——会立即重试，如果故障再次发生，则会向调用方暴露该故障。这可以避免计时器驱动的失败循环，同时保留现有可恢复的 flush 边界。
 
@@ -36,7 +36,7 @@ JSONL 每个持久化追加批次会写入一个 Zstandard 帧并执行一次 fs
 
 ## 备选方案
 
-**不持久化流式分片事件。** 这里不采纳：这会改变事件溯源的权威地位及恢复语义，而不只是改变物理写入节奏。在无信息损失的替代方案独立定义回放、fork、引用源事件的关联、序列和崩溃行为之前，现有的[拒绝仅保留组装消息的决策](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.zh.md)仍是防护规则。[打包行决策](2026-07-26-packed-chunk-rows-by-default.zh.md)仍是配套的 JSONL 存储体积优化。
+**使用每个 Assistant attempt 一个 settlement 代替批处理写入。** [v2 Assistant stream 决策](2026-09-01-v2-embedded-assistant-streams.zh.md)提供该无信息损失事件模型，并减少 Assistant 事件基数。它不能替代其他相邻事件、历史 generation 发布或使用同一 append 接口的 provider 所需的有界批处理。
 
 **仅在语义检查点写入。** 不采纳：此方案会最大化批处理，却让普通的崩溃丢失窗口取决于另行挂载的策略。有界后台写入会在检查点之间持久化进度，而强制 flush 继续提供更强的顺序约定。
 
@@ -50,10 +50,10 @@ JSONL 每个持久化追加批次会写入一个 Zstandard 帧并执行一次 fs
 
 ## 后果
 
-高频事件突发通常会减少持久化追加操作，同时保持逻辑事件数量完全不变。减少幅度取决于事件到达速率和后端延迟：位于同一 200 ms 窗口内的突发事件会成为一个批次，而强制 flush 与稀疏事件仍可能产生小批次。
+高频事件突发通常会减少持久化追加操作，同时保持已接纳事件序列完全不变。减少幅度取决于事件到达速率和后端延迟：位于同一 200 ms 窗口内的突发事件会成为一个批次，而强制 flush 与稀疏事件仍可能产生小批次。
 
 本决策不会限制因 provider 缓慢而积压的待处理事件数量或字节数，也不会减少解码后的逻辑日志。若要建立经过验证的内存上界或逻辑保留策略，就必须为其另行定义失败与回放约定，而不是再引入一条隐式计时器规则。
 
 接纳后的事件在固定窗口内可能只存在于内存中，此后在等待调度或后端工作完成期间也可能如此。显式持久性边界保持不变，并会绕过等待。
 
-句柄统一负责计时器、活跃排空、待处理前缀、重试暂停和屏障；后端的监听器负责路由和生命周期驱动的排空。`SESSION_FORMAT_VERSION` 保持不变。
+句柄统一负责计时器、活跃排空、待处理前缀、重试暂停和屏障；后端的监听器负责路由和生命周期驱动的排空。批处理本身绝不改变 `SESSION_FORMAT_VERSION`。

.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.md
-2026-08-09-client-conversation-node-assembly.md: 0aac5056e2cbe22359f8064b1bf4aa0b015a35c8
-2026-08-09-client-conversation-node-assembly.zh.md: b06a92113f91e6297da986866dce097b11bab45f
+2026-08-09-client-conversation-node-assembly.md: 425975944f7b23575c4f716dee8754dc6b3ab54c
+2026-08-09-client-conversation-node-assembly.zh.md: 96439fa951cdc1d6abe397ee37661291c0f954a7

.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.md

@@ -51,7 +51,7 @@ Each `(kind, id)` has at most one start Match. A second start fails immediately;
 
 #### `match(event)`
 
-`match(event)` reads only the current `SessionEventLike` and returns `{ id, role: 'start' | 'update' }` or `null`. It cannot access a Context, history, a Reader, a Location, or the view envelope. A `chunkrow/*` event can only be an update; the Assembler rejects it as a start, and `start()` receives a `ConversationStartMatch` containing a standard `SessionEvent`.
+`match(event)` reads only the current `SessionEventLike` and returns `{ id, role: 'start' | 'update' }` or `null`. It cannot access a Context, history, a Reader, a Location, or the view envelope. A Client-only `assistant/live-chunk` event can only be an update; the Assembler rejects every transient start, and `start()` receives a `ConversationStartMatch` containing a durable `SessionEvent`.
 
 This restriction makes one scalar event or packed run's routing cost depend only on the number of registered Definitions. The Assembler never scans a Definition's historical Contexts to decide which one owns an update.
 
@@ -110,7 +110,7 @@ Dependencies point strictly from earlier starts to later starts, so transitive r
 
 #### `update(context, match)`
 
-`update()` handles a post-start scalar or packed Match that `match()` has already routed exactly to the current `(kind, id)`. It does not decide which Context owns the input. A Definition that consumes Assistant deltas folds each matching `chunkrow/*` value as one batch without constructing member events.
+`update()` handles a post-start durable or transient Match that `match()` has already routed exactly to the current `(kind, id)`. It does not decide which Context owns the input. An Assistant Definition folds each `assistant/live-chunk` update directly and expands an embedded `assistant/message` or `assistant/attempt` stream during history replay.
 
 The Assembler invokes `update()` in ascending `seq` order. A live tail update can apply incrementally; any non-tail insertion, newly loaded start, or invalidated dependency causes a complete replay from `start()`.
 
@@ -262,7 +262,7 @@ Page size, record packing, the number of history loads, and RAF coalescing affec
 | Next-step Inbox / `inbox-next-step` | Splice Event seq | Each `agent/inbox/spliced` targeting next-step | None | Append message IDs to persistent splice state; materialize once per claim and expose the shared current claimed batch to Message |
 | Message / `input-message` | Message ID | Append-surface `user/message` | None | Use source for a context message, or read the nearest next-step Inbox to distinguish user from steering |
 | Request Prompt / `request-prompt` | Header Event seq | Each `request/header` | None | Read the preceding Request Prompt through Reader, retain the full prompt state, and classify system/tool changes |
-| Assistant / `assistant-step` | `turn:step` | `step/start` | Scalar or packed `assistant/chunk`, final `assistant/message`, and same-step Retry | Aggregate blocks, usage, first-token time, final evidence, and retry-hidden state, then publish same-key Step data |
+| Assistant / `assistant-step` | `turn:step` | `step/start` | Live `assistant/live-chunk`, durable `assistant/message` or `assistant/attempt`, and same-step Retry | Aggregate blocks, usage, first-token time, settlement evidence, and retry-hidden state, then publish same-key Step data |
 | Tool / `tool-call` | Root call ID | Root `tool/call` | Root result and Code Dispatch start/result | Aggregate the root, children, and parent Map; Dispatch Events route exactly through `rootCallId` |
 | Command / `command` | Command ID | `command/run` | `command/done` and compact lifecycle/checkpoint Events carrying a source command ID | Aggregate command outcome and manual-compaction evidence |
 | Automatic Compaction / `compaction` | Compaction ID | `compaction/start` without a source command ID | Summary, end, and replacement checkpoint | Aggregate summary/checkpoint; sufficient checkpoint evidence supports fallback without a start |
@@ -382,7 +382,7 @@ History-path tests cover complete replace, non-overlapping prepend, complete-ran
 
 **Define a reverse State fold for backward history scanning.** Rejected: every business would maintain two inverse algorithms, and deletion, non-invertible aggregation, and cross-Context dependencies would be difficult to keep equivalent. Ordered Matches followed by forward replay from start preserve one business meaning.
 
-**Add a separate chunk-run matcher and update lifecycle.** Rejected: a second Definition path would duplicate dispatch, replay, publication, and Context types. `ChunkRowEvent` uses the existing `match(event)` and `update(context, match)` lifecycle while making packed handling explicit through its `chunkrow/*` discriminant.
+**Add a separate live-stream matcher and update lifecycle.** Rejected: a second Definition path would duplicate dispatch, replay, publication, and Context types. Client-only `assistant/live-chunk` and durable settlements use the existing `match(event)` and `update(context, match)` lifecycle; only the event discriminator and stream expansion differ.
 
 **Make Inbox a first-class engine concept or one window-wide Context.** Rejected: Inbox is ordinary business State and does not belong in the generic engine. Per-splice instantaneous State plus a strictly backward Reader supports prepend, append, and Message lookup together.
 

.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.zh.md

@@ -51,7 +51,7 @@ Assembler 使用 `conversationContextKey(kind, id)` 组合无碰撞 key；不同
 
 #### `match(event)`
 
-`match(event)` 只读取当前 `SessionEventLike`，返回 `{ id, role: 'start' | 'update' }` 或 `null`。它拿不到 Context、历史、Reader、Location 或 view envelope。`chunkrow/*` event 只能作为 update；Assembler 会拒绝 packed start，`start()` 接收的 `ConversationStartMatch` 只包含标准 `SessionEvent`。
+`match(event)` 只读取当前 `SessionEventLike`，返回 `{ id, role: 'start' | 'update' }` 或 `null`。它拿不到 Context、history、Reader、Location 或 view envelope。Client-only `assistant/live-chunk` event 只能作为 update；Assembler 会拒绝每个 transient start，`start()` 接收的 `ConversationStartMatch` 只包含持久 `SessionEvent`。
 
 这项限制使单条 scalar event 或 packed run 的路由成本只随已注册 Definition 数量增长。Assembler 不会为了判断一条 update 属于谁而遍历该 Definition 的历史 Context。
 
@@ -110,7 +110,7 @@ Reader 每次查询都记录 `{ key, revision, windowGap }` 依赖。命中前
 
 #### `update(context, match)`
 
-`update()` 只处理已经由 `match()` 精确路由到当前 `(kind, id)` 的 post-start scalar 或 packed Match。它不判断 input 属于哪个 Context。消费 Assistant delta 的 Definition 会把每个匹配的 `chunkrow/*` 值作为一个 batch fold，而不构造成员 event。
+`update()` 只处理已由 `match()` 精确路由到当前 `(kind, id)` 的 post-start durable 或 transient Match。它不判断 input 属于哪个 Context。Assistant Definition 会直接 fold 每个 `assistant/live-chunk` update，并在 history replay 期间展开嵌入式 `assistant/message` 或 `assistant/attempt` stream。
 
 Assembler 按 `seq` 升序调用 `update()`。实时尾部 update 可以直接增量应用；任何非尾部证据插入、start 补齐或依赖失效都会从 `start()` 完整 replay。
 
@@ -262,7 +262,7 @@ Chat `order` 的结构性变化仍可能重排当前可见 key；纯 data 更新
 | Next-step Inbox / `inbox-next-step` | splice Event seq | 每条目标为 next-step 的 `agent/inbox/spliced` | 无 | 把消息 ID 追加到持久 splice state；每次 claim 只 materialize 一次，并向 Message 暴露共享的当前 claimed batch |
 | Message / `input-message` | message ID | append-surface `user/message` | 无 | 根据 source 生成 context message，或读取最近 next-step Inbox 判断 user/steering |
 | Request Prompt / `request-prompt` | header Event seq | 每条 `request/header` | 无 | 通过 Reader 读取前一条 Request Prompt，保留完整 prompt 状态，并判定 system/tool 变化 |
-| Assistant / `assistant-step` | `turn:step` | `step/start` | scalar 或 packed `assistant/chunk`、final `assistant/message`、同 step Retry | 聚合 blocks、usage、首 token 时间、final 和 retry 隐藏状态，并发布同 key Step data |
+| Assistant / `assistant-step` | `turn:step` | `step/start` | Live `assistant/live-chunk`、持久 `assistant/message` 或 `assistant/attempt`、同 step Retry | 聚合 block、usage、首 token 时间、settlement 证据与 retry-hidden state，再发布同 key Step data |
 | Tool / `tool-call` | root call ID | root `tool/call` | root result、Code Dispatch start/result | 聚合 root、children 和 parent Map；Dispatch Event 用 `rootCallId` 精确路由 |
 | Command / `command` | command ID | `command/run` | `command/done`、带 source command ID 的 compact lifecycle/checkpoint | 聚合 command outcome 和手动压缩证据 |
 | Automatic Compaction / `compaction` | compaction ID | 无 source command ID 的 `compaction/start` | summary、end、replacement checkpoint | 聚合 summary/checkpoint；checkpoint 足够时可在缺 start 下 fallback |
@@ -382,7 +382,7 @@ Assembled Web snapshot、GUI 和浏览器场景覆盖真实 plugin graph。浏
 
 **为历史反扫定义逆向 State fold。** 拒绝：每个业务都要维护互为逆运算的两套逻辑，删除、非可逆聚合和跨 Context 依赖很难保持一致。统一 Matches 后从 start 正序 replay 只有一套业务语义。
 
-**增加独立的 chunk-run matcher 与 update lifecycle。** 拒绝：第二条 Definition 路径会重复 dispatch、replay、publication 与 Context 类型。`ChunkRowEvent` 使用既有 `match(event)` 与 `update(context, match)` lifecycle，并通过 `chunkrow/*` discriminator 明确标记 packed 处理。
+**增加独立 live-stream matcher 与 update lifecycle。** 拒绝：第二条 Definition path 会重复 dispatch、replay、publication 与 Context type。Client-only `assistant/live-chunk` 与持久 settlement 使用既有 `match(event)` 和 `update(context, match)` lifecycle；只有 event discriminator 与 stream expansion 不同。
 
 **把 Inbox 做成引擎一级公民或一个窗口级 Context。** 拒绝：Inbox 是普通业务状态，不应污染通用引擎；逐 splice 瞬间态加严格前序 Reader 同时支持 prepend、append 和 Message 查询。
 

.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md
-2026-08-10-cancelled-stream-prefix-finalize.md: fd397a02663908f5984b4e1798d1b1759b140c79
-2026-08-10-cancelled-stream-prefix-finalize.zh.md: 44adb2ff4163cd1904a9a93895c99519bae2f234
+2026-08-10-cancelled-stream-prefix-finalize.md: 1e6fe59bcc1b323941b69d0e9232f0bcf9e56f53
+2026-08-10-cancelled-stream-prefix-finalize.zh.md: 7aa81f179b80925ef47a8820f8a80c1ef37ec5ea

.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md

@@ -6,23 +6,23 @@ English | [中文](2026-08-10-cancelled-stream-prefix-finalize.zh.md)
 
 ## Problem
 
-A cancelled stream can leave `assistant/chunk` events that clients continue rendering while `deriveMessages()` excludes them because no `assistant/message` records the delivered prefix. A follow-up such as "expand on your second point" then lacks text the user read, and a fork at the cancelled turn inherits the same gap.
+A cancelled stream can leave transient chunks that clients have rendered while `deriveMessages()` excludes them because no `assistant/message` records the delivered prefix. A follow-up such as "expand on your second point" then lacks text the user read, and a fork at the cancelled turn inherits the same gap.
 
 The model history must contain assistant content that remains visible to the user after cancellation.
 
 ## Decision
 
-`ReactLoopAgent.step()` catches cancellation while consuming a model stream, when its `BlockAssembler`, logged chunk seqs, and provider route identify the delivered prefix. It appends that prefix as the step's `assistant/message` with `interrupted: true`, `surfaceOp: 'append'`, and `sourceEventSeqs` containing exactly the logged chunks. The append precedes `step/end` and the aborted `turn/end`.
+`ReactLoopAgent.step()` catches cancellation while consuming a model stream, when its `BlockAssembler`, compact stream accumulator, and provider route identify the delivered prefix. It appends that prefix as the step's `assistant/message` with `interrupted: true`, `surfaceOp: 'append'`, and the exact embedded timed stream. The append precedes the committed `agent/assistant-stream` end frame, `step/end`, and the aborted `turn/end`.
 
-`BlockAssembler.interruptedBlocks()` returns closed and open `text` and `reasoning` blocks with non-whitespace content in stream order. It omits tool calls because interruption precedes dispatch and no real result exists; it also omits empty blocks and open unknown block types. An empty result appends no assistant message. Provider `error` and `aborted` finishes leave the stream-consumption scope before `agent/request-error`, so provider failures and cancellation during recovery commit no content from the failed request.
+`BlockAssembler.interruptedBlocks()` returns closed and open `text` and `reasoning` blocks with non-whitespace content in stream order. It omits tool calls because interruption precedes dispatch and no real result exists; it also omits empty blocks and open unknown block types. An empty result appends `assistant/attempt` instead of a surface message. Provider `error` and `aborted` finishes also commit `assistant/attempt` before `agent/request-error`, so their streams remain durable without contributing failed-request content to model history.
 
-Chat and Trajectory Conversation Definitions read `interrupted` from the durable message. Chat renders the Stopped marker, while Trajectory keeps the provider request in the error lifecycle after `step/end` and retains the durable result seq and provenance. Cancellation during tool execution follows the tool scheduler contract because the assistant message has already committed: started calls produce real results, and undispatched calls receive `ABORTED_BEFORE_DISPATCH` results.
+Chat and Trajectory Conversation Definitions read `interrupted` from the durable message. Chat renders the Stopped marker, while Trajectory keeps the provider request in the error lifecycle after `step/end` and retains the durable result seq and provider information. Cancellation during tool execution follows the tool scheduler contract because the assistant message has already committed: started calls produce real results, and undispatched calls receive `ABORTED_BEFORE_DISPATCH` results.
 
 ## Alternatives considered
 
 **Always discard the prefix.** This avoids a new durable marker but makes every cancel-then-follow-up and fork omit assistant content that remains visible to the user.
 
-**Assemble the prefix from chunks during projection.** `deriveMessages()` and client Conversation Definitions would each need interruption assembly rules, and the log would have no authoritative assistant message for the prefix. This also expands model history beyond the three `SurfaceEventType` events.
+**Assemble the prefix from the embedded attempt during projection.** `deriveMessages()` and Client Conversation Definitions would each need interruption assembly rules, and the log would have no authoritative surface message for the prefix. This also expands model history beyond the three `SurfaceEventType` events.
 
 **Retain complete tool calls with synthetic aborted results.** These calls never dispatched, so synthetic results would claim an execution outcome that did not occur and add content the user did not receive as a tool result.
 
@@ -32,8 +32,8 @@ Chat and Trajectory Conversation Definitions read `interrupted` from the durable
 
 Post-cancel follow-ups and forks include the delivered prefix. The ACP bridge drains ordered assistant output before settling the prompt, so the final `agent_message_chunk` update precedes the cancelled stop reason.
 
-Terminal provider errors still discard their streamed prefix. That asymmetry remains because an error turn ends without the user's cancellation decision and requires its own retention policy.
+Terminal provider errors retain their stream in `assistant/attempt` but keep its content out of model history. Only the user's cancellation decision turns visible delivered text into an interrupted surface message.
 
 ## Testing
 
-`packages/core/agent-loop/tests/cancel.spec.ts` covers content, cited seqs, event order, next-request parity, reasoning-only output, tool-call omission, recovery cancellation, and the empty-prefix case. `packages/llm/llm/tests/assembler.spec.ts` covers `interruptedBlocks()`. `packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts` and `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` cover both client projections. The keyless `cancel` ACP snapshot and `goal-round-driver` goal snapshot cover assembled applications.
+`packages/core/agent-loop/tests/cancel.spec.ts` covers content, embedded streams, event order, next-request parity, reasoning-only output, tool-call omission, recovery cancellation, and the empty-prefix attempt. `packages/llm/llm/tests/assembler.spec.ts` covers `interruptedBlocks()`. `packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts` and `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` cover both Client projections. The keyless `cancel` ACP snapshot and `goal-round-driver` goal snapshot cover assembled applications.

.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.zh.md

@@ -6,23 +6,23 @@ Status: implemented
 
 ## Problem
 
-被取消的流可能留下客户端继续渲染的 `assistant/chunk` 事件，但如果没有 `assistant/message` 记录已送达前缀，`deriveMessages()` 就会排除这部分内容。后续的「第二点展开讲讲」之类追问会缺少用户已读到的文本，在该轮次上创建的分支也会继承这个缺口。
+被取消的流可能留下 Client 已经渲染的瞬态 chunk，但如果没有 `assistant/message` 记录已送达前缀，`deriveMessages()` 就会排除这部分内容。后续的「第二点展开讲讲」之类追问会缺少用户已读到的文本，在该轮次上创建的分支也会继承这个缺口。
 
 模型历史必须包含取消后仍对用户可见的 assistant 内容。
 
 ## Decision
 
-`ReactLoopAgent.step()` 在消费模型流期间捕捉取消，此时 `BlockAssembler`、已记录的分片 seq 和提供方路由可以确定已送达前缀。循环把该前缀追加为 step 的 `assistant/message`，并设置 `interrupted: true`、`surfaceOp: 'append'` 以及恰好包含已记录分片的 `sourceEventSeqs`。该追加先于 `step/end` 和记录 aborted 的 `turn/end`。
+`ReactLoopAgent.step()` 在消费模型 stream 期间捕捉取消，此时 `BlockAssembler`、紧凑 stream accumulator 与 provider route 可以确定已送达前缀。loop 把该前缀追加为 step 的 `assistant/message`，并设置 `interrupted: true`、`surfaceOp: 'append'` 与精确嵌入式带时间 stream。该追加先于 committed `agent/assistant-stream` end frame、`step/end` 和记录 aborted 的 `turn/end`。
 
-`BlockAssembler.interruptedBlocks()` 按流顺序返回内容非空白的已闭合和未闭合 `text` 与 `reasoning` 块。打断先于分派，没有真实工具结果，因此它会省略工具调用，也会省略空块和未闭合的未知块类型。返回结果为空时不追加 assistant 消息。提供方的 `error` 和 `aborted` finish 会在 `agent/request-error` 前离开流消费范围，因此提供方故障和恢复期间的取消都不会提交失败请求的内容。
+`BlockAssembler.interruptedBlocks()` 按 stream 顺序返回内容非空白的已闭合和未闭合 `text` 与 `reasoning` block。打断先于分派，没有真实工具结果，因此它会省略工具调用，也会省略空 block 和未闭合的未知 block 类型。返回结果为空时追加 `assistant/attempt`，而不是 surface message。Provider `error` 与 `aborted` finish 也会在 `agent/request-error` 前提交 `assistant/attempt`，因此其 stream 保持持久，但失败请求内容不会进入模型历史。
 
-Chat 和 Trajectory Conversation Definition 从持久消息读取 `interrupted`。Chat 渲染 Stopped 标记，Trajectory 则在 `step/end` 后把提供方请求保持在 error 生命周期，并保留持久结果 seq 和提供方信息。工具执行期间的取消遵循工具调度器约定，因为 assistant 消息已提交：已启动的调用生成真实结果，未分派的调用获得 `ABORTED_BEFORE_DISPATCH` 结果。
+Chat 和 Trajectory Conversation Definition 从持久 message 读取 `interrupted`。Chat 渲染 Stopped marker，Trajectory 则在 `step/end` 后把 provider request 保持在 error 生命周期，并保留持久 result seq 与 provider 信息。工具执行期间的取消遵循工具调度器约定，因为 assistant message 已提交：已启动的调用生成真实结果，未分派的调用获得 `ABORTED_BEFORE_DISPATCH` 结果。
 
 ## Alternatives considered
 
 **始终丢弃前缀。** 这能避免新增持久标记，但每次取消后的追问和分支都会缺少仍对用户可见的 assistant 内容。
 
-**在投影时从分片组装前缀。** `deriveMessages()` 和客户端 Conversation Definition 都需要实现打断组装规则，日志中也没有该前缀的权威 assistant 消息。这还会让模型历史超出三类 `SurfaceEventType` 事件。
+**在投影时从嵌入式 attempt 组装前缀。** `deriveMessages()` 与 Client Conversation Definition 都需要实现打断组装规则，日志中也没有该前缀的权威 surface message。这还会让模型历史超出三类 `SurfaceEventType` 事件。
 
 **保留完整工具调用并合成 aborted 结果。** 这些调用从未分派，合成结果会声称一个并未发生的执行结果，还会增加用户未收到的工具结果内容。
 
@@ -32,8 +32,8 @@ Chat 和 Trajectory Conversation Definition 从持久消息读取 `interrupted`
 
 取消后的追问和分支会包含已送达前缀。ACP 桥会在结算 prompt 前排空按序传送的 assistant 输出，因此最后一条 `agent_message_chunk` 更新先于 cancelled stop reason。
 
-终局提供方错误仍会丢弃已流出前缀。该不对称保留，因为 error 轮次的结束不来自用户的取消决定，需要独立的保留策略。
+终局 provider error 会在 `assistant/attempt` 中保留其 stream，但不让内容进入模型历史。只有用户的取消决策会把可见的已送达文本变成 interrupted surface message。
 
 ## Testing
 
-`packages/core/agent-loop/tests/cancel.spec.ts` 覆盖内容、引用的 seq、事件顺序、下一请求的一致性、仅 reasoning 的输出、工具调用省略、恢复期间的取消和空前缀情形。`packages/llm/llm/tests/assembler.spec.ts` 覆盖 `interruptedBlocks()`。`packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts` 和 `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` 覆盖两种客户端投影。keyless 的 `cancel` ACP 快照和 `goal-round-driver` goal 快照覆盖完整应用。
+`packages/core/agent-loop/tests/cancel.spec.ts` 覆盖 content、嵌入式 stream、事件顺序、下一请求的一致性、仅 reasoning 的输出、工具调用省略、恢复期间的取消和空前缀 attempt。`packages/llm/llm/tests/assembler.spec.ts` 覆盖 `interruptedBlocks()`。`packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts` 与 `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` 覆盖两种 Client 投影。keyless `cancel` ACP snapshot 与 `goal-round-driver` goal snapshot 覆盖组装应用。

.agents/notes/implemented/architecture/2026-08-10-session-log-version-mechanism.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-10-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: 98eb220e49457d3a2783edefce13d053c9b94025
+2026-08-10-session-log-version-mechanism.zh.md: 8853e6ed9a1a1ed43193cfe0949fffdbb9b4a26f

.agents/notes/implemented/architecture/2026-08-10-session-log-version-mechanism.md

@@ -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). V2 keeps the physical codec neutral to ordinary event vocabulary and payload additions: the adjacent edge freezes its released source and target inventories, while equal-version restoration applies the installed known-event set and current payload semantics. 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.

.agents/notes/implemented/architecture/2026-08-10-session-log-version-mechanism.zh.md

@@ -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。V2 让物理 codec 对普通事件词汇与 payload 新增项保持中立：相邻迁移边冻结 released source 与 target 清单，同版本恢复则应用已安装的 known-event set 与当前 payload 语义。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。

.agents/notes/implemented/architecture/2026-08-19-projection-cache-per-session-files.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-19-projection-cache-per-session-files.md
-2026-08-19-projection-cache-per-session-files.md: 9e102e786a6c06d82d1a0f45cc2f96a50c8abcd8
-2026-08-19-projection-cache-per-session-files.zh.md: d875c3f57800936f66fbf65233637df9bf300e2d
+2026-08-19-projection-cache-per-session-files.md: 0792ed6cac23d1ae09767f608c74f82430db68e9
+2026-08-19-projection-cache-per-session-files.zh.md: 201146ce8568b66eebf6793fcdc489929a3e4cdb

.agents/notes/implemented/architecture/2026-08-19-projection-cache-per-session-files.md

@@ -20,8 +20,9 @@ Reads and writes share ONE coherent state: every read (`cachedSnapshot`) is a sy
 - Listing is a synchronous in-memory read; a session without a record document simply lacks the projection column.
 - ACP, headless, SDK, and Web sessions publish cache rows for later consumers. The log-leading durability barrier may flush a covered prefix at the cache cadence and split otherwise coalesced physical JSONL runs; recorded profile snapshots re-pack the logical event stream so cache timing does not define fixture layout.
 - The per-record contract scopes failure: a malformed or stale-version document reads as an absent record at open, so one bad file never bricks the cache, and a checkpoint schema bump discards stale sessions per record instead of rejecting the whole domain.
-- The json backend bootstraps the per-record tree from the legacy whole-unit cache only when enumeration finds no new-layout document path. Any new document path, including an unreadable or stale file, suppresses the bootstrap for the whole unit; missing session rows refold from the log. The legacy file remains untouched.
-- The cache record is bound to the same log lifecycle as before: the stored `{createdAt, cwd}` identity guards against a recreated id.
+- The json backend bootstraps the per-record tree from the legacy whole-unit cache only when enumeration finds no new-layout document path, the legacy unit name matches, and its version is current or declared compatible. A version outside that accepted set remains untouched and the new domain opens empty; storage never relabels a version the domain owner did not approve. Any new document path, including an unreadable or stale file, suppresses the bootstrap for the whole unit; missing session rows refold from the log. The [cross-version read-compatibility decision](2026-09-02-projcache-cross-version-read-compat.md) owns the version policy.
+- The `session_projcache` domain uses version 7 and declares versions 3 through 6 structurally compatible. Predecessor identities lack the Session `formatVersion`, so they cannot seed current projections and refold cold; a current checkpoint rewrites them with the complete identity. Once the format matches, absent lineage fields normalize to an unseeded identity, and a seeded caller rejects that identity and refolds cold. A record that still fails schema validation is backed up and skipped; every subsequent write stamps version 7.
+- The cache record is bound to the same log lifecycle as before: the stored `{createdAt, cwd, isSeeded, inheritedEventCount}` identity guards against a recreated id or a mismatched inherited prefix.
 
 ## Alternatives considered
 
@@ -29,3 +30,4 @@ Reads and writes share ONE coherent state: every read (`cachedSnapshot`) is a sy
 - **Cache-owned per-session files** (`<root>/<session-id>/projection_cache.json`, the first revision of this change). Tried and reverted in review: the cache hand-rolled the medium — paths, per-path write chains, in-flight tracking, owner-only file modes, and a sqlite no-path special case — and its listing read hit the disk directly on every call while writes were throttled, so reads and writes were never consistent.
 - **Resolve the path through `sessionPersistence.locate(meta)`** (the file beside the session log). Rejected: the cache would have to guess "beside the log" from a log artifact path (`dirname` + fixed filename), coupling the cache to the persistence service and to a backend's layout.
 - **Make `per-record` a mode of the existing unit instead of a separate unit class.** Rejected: the two layouts have genuinely different state models — `single` is memory-authoritative with whole-file publish, `per-record` is stateless (the directory is the state; `loadAll` re-reads the tree) — so they are separate small classes behind one backend, with record keys validated path-safe instead of encoded.
+- **Copy legacy values across undeclared unit versions.** Rejected: the json backend does not know a domain's record schema and cannot derive session-lineage fields. It copies an older record only when the domain explicitly lists that version in `compatibleVersions` and its current schema accepts the value; otherwise the record stays untouched and reads as absent.

.agents/notes/implemented/architecture/2026-08-19-projection-cache-per-session-files.zh.md

@@ -20,8 +20,9 @@ Status: implemented
 - 列表读取是同步内存读；没有记录文档的会话只是缺少投影列。
 - ACP、headless、SDK 与 Web 会话都会发布缓存行，供后续消费方使用。确保日志领先的持久性屏障可能按缓存节奏 flush 已覆盖的前缀，并拆分原本会合并的物理 JSONL 行；各 profile 的录制快照会重新 pack 逻辑事件流，因此缓存时序不会决定 fixture 布局。
 - per-record 契约把故障范围缩小到单记录：畸形或过期版本的文档在打开时读作"无此记录"，单个坏文件不会拖垮整个缓存；检查点 schema 升级按会话丢弃过期行，而不是拒绝整个域。
-- json 后端仅在枚举时没有发现任何新布局文档路径，才从旧整单元缓存引导 per-record 目录树。只要存在任意新文档路径，即使文件不可读或版本陈旧，也会对整个单元禁用引导；缺失的会话行从日志重折叠。旧文件保持不变。
-- 缓存记录仍绑定同一日志生命周期：存储的 `{createdAt, cwd}` 身份防止被重建的 id 误导。
+- json 后端仅在枚举时没有发现任何新布局文档路径、旧单元名称匹配，且其版本为当前版本或已声明兼容版本时，才从旧整单元缓存引导 per-record 目录树。接受集合之外的版本保持不变，新域为空；存储绝不把域 owner 未批准的版本改标为当前版本。只要存在任意新文档路径，即使文件不可读或版本陈旧，也会对整个单元禁用引导；缺失的会话行从日志重折叠。[跨版本读兼容决策](2026-09-02-projcache-cross-version-read-compat.zh.md)是版本策略的权威说明。
+- `session_projcache` 域使用版本 7，并声明版本 3 至 6 在结构上兼容。前代 identity 缺少 Session `formatVersion`，因此不能播种当前投影并会回落冷折叠；当前检查点会用完整 identity 重写它们。格式匹配后，缺失的 lineage 字段归一化为 unseeded 身份，seeded 调用方会拒绝该身份并回落冷折叠。仍然通不过 schema 校验的记录会被备份并跳过；后续每次写入都使用版本 7。
+- 缓存记录仍绑定同一日志生命周期：存储的 `{createdAt, cwd, isSeeded, inheritedEventCount}` 身份防止被重建的 id 或不匹配的继承前缀误导。
 
 ## Alternatives considered
 
@@ -29,3 +30,4 @@ Status: implemented
 - **缓存自持的每会话文件**（`<root>/<session-id>/projection_cache.json`，本改动的第一版）。试过并在评审中回退：缓存手搓了介质——路径、按路径的写链、在途跟踪、仅属主文件权限，以及 sqlite 无路径特判——而且它的列表读每次调用都直读磁盘、写却在节流，读写永不一致。
 - **经 `sessionPersistence.locate(meta)` 解析路径**（文件放在会话日志旁）。未采用：缓存得从日志 artifact 路径"猜"日志旁边（`dirname` + 固定文件名），把缓存耦合到持久化服务与后端的布局。
 - **把 `per-record` 做成既有单元的一种模式而非独立单元类。** 未采用：两种布局的状态模型本质不同——`single` 内存权威、整文件发布；`per-record` 无状态（目录即状态，`loadAll` 重扫目录树）——所以它们是同一后端下的两个小型独立类，记录键做路径安全校验而非编码。
+- **跨未声明单元版本复制旧值。** 未采用：json 后端不知道域的记录 schema，也无法推导会话 lineage 字段。只有当域在 `compatibleVersions` 中明确列出旧版本，且当前 schema 接受该值时，后端才复制旧记录；否则记录保持不变并读作不存在。

.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.md
-2026-08-21-deepseek-llm-api-request-extensions.md: 018b93115f5376affd86a4da3c76f0f367ba9ed0
-2026-08-21-deepseek-llm-api-request-extensions.zh.md: 4bc0f0c992445c5897069b68efa47fdba46dfdb4
+2026-08-21-deepseek-llm-api-request-extensions.md: eadbe2a5f17de446c345120f9a6aeeeb531c43b4
+2026-08-21-deepseek-llm-api-request-extensions.zh.md: f45210adbc075c30484754ce7f8c2b65b515be6c

.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.md

@@ -73,7 +73,7 @@ The receiver would also need to traverse the tagged tree, resolve paths into the
 
 ### Why not omit assistant chunks or overlapping event data?
 
-About 98% of the measured real-session events were `assistant/chunk`. Omitting chunks after reference encoding reduced the complete identity JSON by another 84.79% for late enable and 6.49% for steady state, but it prevents lossless canonical-log reconstruction and leaves `assistant/message.sourceEventSeqs` pointing to absent events. Fuzzy or normalized substitutions have the same reconstruction defect.
+About 98% of the measured v1 real-session events were `assistant/chunk`. Omitting them after reference encoding reduced the complete identity JSON by another 84.79% for late enable and 6.49% for steady state, but prevented lossless reconstruction and left message provenance dangling. V2 embeds compact streams in attempt settlements; `dsh_session_log` still sends every current canonical event whole and does not omit those embedded records. Fuzzy or normalized substitutions have the same reconstruction defect.
 
 **Keep the upload cursor only in memory.** Rejected because a normal process restart would resend the entire Session. A canonical acceptance event makes restart recovery best-effort durable without another storage backend; the remaining crash window produces allowed duplicates.
 

.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.zh.md

@@ -73,7 +73,7 @@ Status: implemented
 
 ### 为什么不省略 assistant 分片或重叠事件数据？
 
-实测真实会话事件中约 98% 为 `assistant/chunk`。在引用编码后省略分片，会让完整未压缩 JSON 在延迟启用场景进一步减少 84.79%，在稳态场景进一步减少 6.49%，但这会阻止权威日志的无损重建，并让 `assistant/message.sourceEventSeqs` 指向缺失事件。模糊替换或规范化替换也存在同一重建缺陷。
+实测 v1 真实 Session event 中约 98% 为 `assistant/chunk`。在引用编码后省略它们，会让完整 identity JSON 在延迟启用场景进一步减少 84.79%，在稳态场景进一步减少 6.49%，但会阻止无损重建并让 message provenance 悬空。V2 把紧凑 stream 嵌入 attempt settlement；`dsh_session_log` 仍会完整发送每个当前规范 event，且不会省略这些嵌入式 record。模糊或规范化替换也有相同重建缺陷。
 
 **只在内存中保留上传游标。** 已否决，因为普通进程重启会重发完整会话。权威接受事件让重启恢复获得尽力而为的持久性，无需另一存储后端；剩余崩溃窗口只会产生允许的重复。
 

.agents/notes/implemented/architecture/2026-08-22-single-dsh-application-launcher.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-22-single-dsh-application-launcher.md
-2026-08-22-single-dsh-application-launcher.md: feac31b3eafced8158a8d79a0e5967a8de5e2f87
-2026-08-22-single-dsh-application-launcher.zh.md: 88fe4ef4d4e0436ecb450e3f5319be7acee6882b
+2026-08-22-single-dsh-application-launcher.md: 068c59c1695ac41216e4df7012eaeb9f80e1e5a6
+2026-08-22-single-dsh-application-launcher.zh.md: 1e082a3d6de391c70a38031caafc44781bc2c7e4

.agents/notes/implemented/architecture/2026-08-22-single-dsh-application-launcher.md

@@ -48,7 +48,7 @@ Direct SDK use follows normal Harness-home resolution: explicit `dshHome`, inher
 
 The Python runtime wheel packages the ordinary `@deepseek-ai/dsh` CLI from `node_modules/@deepseek-ai/dsh/lib/bin.js` through the private `dsh-python-runtime-closure` deploy manifest. The Python client selects `dsh --profile sdk` by default, ordered patch files, and an explicit Harness home; the runnable example under `python/sdk/examples` selects `sdk-minimal`. The installed `dsh` console command exposes the same profile grammar and the separately packaged `web` application.
 
-The executable family is `deepseek-harness-sdk-runtime-<platform>-<arch>`. The SDK wire, wheel and import distribution names, sidecar names, and wire identity `deepseek-harness-sdk-runtime` remain stable. The SDK package family is `@deepseek-ai/dsh-sdk-client`, `@deepseek-ai/dsh-sdk-protocol`, and `@deepseek-ai/dsh-sdk-jsonrpc-server`; `@deepseek-ai/dsh-acp` remains the ACP protocol plugin. There is no Python-specific Node application, checked-in complete config, compatibility package, forwarding executable, fallback parser, or SDK/ACP launcher alias. The [Python profile-runtime decision](2026-08-23-python-sdk-dsh-profile-runtime.md) owns this launch, and the [Windows x64 runtime decision](2026-08-23-python-sdk-windows-x64-runtime.md) owns the fourth carrier.
+The executable family is `deepseek-harness-sdk-runtime-<platform>-<arch>`. The SDK wire, wheel and import distribution names, sidecar names, and wire identity `deepseek-harness-sdk-runtime` remain stable. The SDK package family is `@deepseek-ai/dsh-sdk-client`, `@deepseek-ai/dsh-sdk-protocol`, and `@deepseek-ai/dsh-sdk-jsonrpc-server`; `@deepseek-ai/dsh-acp` remains the ACP protocol plugin. There is no Python-specific Node application, checked-in complete config, compatibility package, forwarding executable, fallback parser, or SDK/ACP launcher alias. The [Python profile-runtime decision](2026-08-23-python-sdk-dsh-profile-runtime.md) owns this launch, and the [Windows x64 runtime decision](2026-08-23-python-sdk-windows-x64-runtime.md) owns the Windows carrier.
 
 ### Enforcement
 

.agents/notes/implemented/architecture/2026-08-22-single-dsh-application-launcher.zh.md

@@ -48,7 +48,7 @@ SDK 用户通过 profile 自定义插件。`dsh plugin --profile <name> ...` 管
 
 Python 运行时 wheel 通过私有 `dsh-python-runtime-closure` 部署 manifest，打包来自 `node_modules/@deepseek-ai/dsh/lib/bin.js` 的普通 `@deepseek-ai/dsh` CLI。Python 客户端默认选择 `dsh --profile sdk`、有序 patch 文件与显式 Harness home；`python/sdk/examples` 下的可运行示例选择 `sdk-minimal`。安装的 `dsh` 控制台命令暴露相同 profile 语法与单独打包的 `web` 应用。
 
-可执行文件族是 `deepseek-harness-sdk-runtime-<platform>-<arch>`。SDK 协议格式、wheel 与 import 分发名称、伴随文件名称，以及协议 identity `deepseek-harness-sdk-runtime` 保持稳定。SDK 包族是 `@deepseek-ai/dsh-sdk-client`、`@deepseek-ai/dsh-sdk-protocol` 与 `@deepseek-ai/dsh-sdk-jsonrpc-server`；`@deepseek-ai/dsh-acp` 继续作为 ACP 协议插件。仓库不保留 Python 专用 Node 应用、检入的完整配置、兼容包、转发可执行文件、后备解析器或 SDK／ACP 启动别名。[Python profile 运行时决策](2026-08-23-python-sdk-dsh-profile-runtime.zh.md)负责该启动方式，[Windows x64 运行时决策](2026-08-23-python-sdk-windows-x64-runtime.zh.md)负责第四个载体。
+可执行文件族是 `deepseek-harness-sdk-runtime-<platform>-<arch>`。SDK 协议格式、wheel 与 import 分发名称、伴随文件名称，以及协议 identity `deepseek-harness-sdk-runtime` 保持稳定。SDK 包族是 `@deepseek-ai/dsh-sdk-client`、`@deepseek-ai/dsh-sdk-protocol` 与 `@deepseek-ai/dsh-sdk-jsonrpc-server`；`@deepseek-ai/dsh-acp` 继续作为 ACP 协议插件。仓库不保留 Python 专用 Node 应用、检入的完整配置、兼容包、转发可执行文件、后备解析器或 SDK／ACP 启动别名。[Python profile 运行时决策](2026-08-23-python-sdk-dsh-profile-runtime.zh.md)负责该启动方式，[Windows x64 运行时决策](2026-08-23-python-sdk-windows-x64-runtime.zh.md)负责 Windows 载体。
 
 ### 强制校验
 

.agents/notes/implemented/architecture/2026-08-23-python-sdk-dsh-profile-runtime.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-23-python-sdk-dsh-profile-runtime.md
-2026-08-23-python-sdk-dsh-profile-runtime.md: 4af7812db6818b65c754a43ec1a7f973d1cbcbf9
-2026-08-23-python-sdk-dsh-profile-runtime.zh.md: 155e7d2ae0b0ba3e4163dd85a31de90bef9d588a
+2026-08-23-python-sdk-dsh-profile-runtime.md: 07e3bd522b1952a8e6257f79eb292fa0ef18e5ef
+2026-08-23-python-sdk-dsh-profile-runtime.zh.md: 1b68c50d93e0fd6d2555115891772b00f95bb7d4

.agents/notes/implemented/architecture/2026-08-23-python-sdk-dsh-profile-runtime.md

@@ -34,7 +34,7 @@ The zero-code deployment manifest is `dsh-python-runtime-closure`. It packages `
 
 Plain Node profiles use symlinks in `$DSH_HOME/profiles/node_modules` to share installation packages with external plugins. An operating-system symlink cannot traverse pkg's `/snapshot` filesystem, so the packaged CLI writes small real ESM proxy packages instead. Each proxy resolves the source package's explicit ESM export map directly under Node import conditions, exposes targets that exist in the installation, and re-exports their virtual module URLs. Export rows without an ESM runtime target and executable-only or declaration-only packages produce no unusable proxy entry; malformed export maps fail startup. A complete matching generation returns without acquiring the cross-process writer lock. A missing or stale entry acquires the lock, rechecks the generation, and repairs it without exposing partial proxies; either carrier can replace the other carrier's managed entry. Loader rows and external plugin peers therefore resolve through the normal profile parent walk while retaining one Cordis and one instance of each bundled module.
 
-The published target set is Linux x64, Linux arm64, macOS arm64, and Windows x64. Installed-wheel black-box CI owns artifact provenance, default and patched profiles, external bundle installation, native tools, MCP, direct JSON-RPC, snapshots, and trusted real-provider turns on every target. The [Windows x64 runtime decision](2026-08-23-python-sdk-windows-x64-runtime.md) owns the fourth artifact and its platform-specific shell surface.
+The published target set is Linux x64, Linux arm64, macOS arm64, macOS x64, and Windows x64. Installed-wheel black-box CI owns artifact provenance, default and patched profiles, external bundle installation, native tools, MCP, direct JSON-RPC, snapshots, and trusted real-provider turns on every target. The [Windows x64 runtime decision](2026-08-23-python-sdk-windows-x64-runtime.md) owns the Windows artifact and its platform-specific shell surface.
 
 ## Existing decisions and supersession
 

.agents/notes/implemented/architecture/2026-08-23-python-sdk-dsh-profile-runtime.zh.md

@@ -34,7 +34,7 @@ Python SDK 分发一个私有 Node 应用，直接启动完整外部 `cordis.yml
 
 普通 Node profile 在 `$DSH_HOME/profiles/node_modules` 中使用符号链接，让外部插件共享安装包。操作系统符号链接无法进入 pkg 的 `/snapshot` 文件系统，因此打包 CLI 改为写入小型真实 ESM 代理包。每个代理直接按 Node import 条件解析源包的显式 ESM exports map，公开安装中实际存在的目标，并重新导出其虚拟模块 URL。没有 ESM 运行时目标的 export 项以及仅含可执行入口或类型声明入口的包不会产生不可用的代理条目；格式错误的 exports map 会导致启动失败。完整且匹配的 generation 不会获取跨进程写入锁。缺失或过期的配置项会获取该锁、重新检查 generation，并在不暴露半成品代理的前提下修复；任一载体都可以替换另一载体留下的受管配置项。Loader 配置项和外部插件 peer 因而可以通过普通 profile 逐级向上查找解析，同时保留一个 Cordis 和每个内置模块的单一实例。
 
-已发布目标集合是 Linux x64、Linux arm64、macOS arm64 与 Windows x64。Installed-wheel 黑盒 CI 在每个目标上负责产物来源、默认及 patched profile、外部 bundle 安装、原生工具、MCP、直接 JSON-RPC、快照，以及可信真实提供方轮次。[Windows x64 运行时决策](2026-08-23-python-sdk-windows-x64-runtime.zh.md)负责第四个产物及其平台专属 shell surface。
+已发布目标集合是 Linux x64、Linux arm64、macOS arm64、macOS x64 与 Windows x64。Installed-wheel 黑盒 CI 在每个目标上负责产物来源、默认及 patched profile、外部 bundle 安装、原生工具、MCP、直接 JSON-RPC、快照，以及可信真实提供方轮次。[Windows x64 运行时决策](2026-08-23-python-sdk-windows-x64-runtime.zh.md)负责 Windows 产物及其平台专属 shell surface。
 
 ## 既有决策与取代关系
 

.agents/notes/implemented/architecture/2026-08-23-python-sdk-windows-x64-runtime.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-23-python-sdk-windows-x64-runtime.md
-2026-08-23-python-sdk-windows-x64-runtime.md: 59a46d99f9e7ed411aeffbb541bbe3bb0c752078
-2026-08-23-python-sdk-windows-x64-runtime.zh.md: 3ab972aabb8135c8bc6285d129ba7bc9335eb11f
+2026-08-23-python-sdk-windows-x64-runtime.md: 1b59dec47036e7351b212b408a31847a1a1c9639
+2026-08-23-python-sdk-windows-x64-runtime.zh.md: 75cea660c3e5cc8e0222e72dc2d07a0c802aeecd

.agents/notes/implemented/architecture/2026-08-23-python-sdk-windows-x64-runtime.md

@@ -20,7 +20,7 @@ The Python process still launches the ordinary `dsh --profile sdk` application a
 
 The executable builder accepts `win` as a pkg platform only with x64, requires the Windows build to run under x64 Node on a Windows host, preserves `.exe` names, and copies `@vscode/ripgrep-win32-x64` as the conventional `-rg.exe` sidecar. Pnpm subprocesses use a caller-supplied JavaScript entry through `process.execPath`. When the caller exposes a `.cmd` shim, the builder resolves the installed `pnpm.mjs` or `pnpm.cjs` through `PNPM_HOME`; it fails if no JavaScript entry exists instead of spawning the shim or enabling a command shell.
 
-The required GitHub matrix builds `node24-win-x64` on `windows-2025` beside the three existing targets. The public GitHub release and GitLab tag pipeline each publish the same four runtime wheels plus the pure SDK wheel. Windows arm64 is absent from target parsing, manifests, matrices, release contents, and documentation.
+The required GitHub matrix builds `node24-win-x64` on `windows-2025` beside Linux x64, Linux arm64, macOS arm64, and macOS x64. The public GitHub release and GitLab tag pipeline each publish the same five runtime wheels plus the pure SDK wheel. Windows arm64 is absent from target parsing, manifests, matrices, release contents, and documentation.
 
 ### Installed-wheel behavior
 
@@ -48,4 +48,4 @@ This decision partially supersedes the Windows non-goal in the [single-file runt
 
 ## Consequences
 
-Python installation now selects a Node-free Windows x64 runtime with the same explicit-home and profile customization model as Linux and macOS. Every pull request pays for a fourth executable, runtime wheel, full keyless blackbox, and—on trusted heads—real provider task. Release validation retains five wheels instead of four. Windows arm64 users receive an explicit unsupported-platform failure until a separate native product decision supplies and proves that carrier.
+Python installation selects a Node-free Windows x64 runtime with the same explicit-home and profile customization model as Linux and macOS. Every pull request builds the Windows executable and runtime wheel as one of five native targets, runs the full keyless blackbox, and—on trusted heads—runs the real-provider task. Release validation retains six wheels. Windows arm64 users receive an explicit unsupported-platform failure until a separate native product decision supplies and proves that carrier.

.agents/notes/implemented/architecture/2026-08-23-python-sdk-windows-x64-runtime.zh.md

@@ -20,7 +20,7 @@ Python 进程仍按 [Python profile 运行时决策](2026-08-23-python-sdk-dsh-p
 
 可执行文件构建器仅允许 x64 使用 pkg 的 `win` 平台，并要求 Windows 构建在 Windows 宿主的 x64 Node 下运行；构建器保留 `.exe` 文件名，并把 `@vscode/ripgrep-win32-x64` 复制为常规 `-rg.exe` sidecar。Pnpm 子进程通过 `process.execPath` 执行调用方提供的 JavaScript 入口。当调用方暴露 `.cmd` shim 时，构建器会通过 `PNPM_HOME` 解析已安装的 `pnpm.mjs` 或 `pnpm.cjs`；如果不存在 JavaScript 入口，构建会失败，而不会启动 shim 或启用命令 shell。
 
-必需 GitHub 矩阵会在 `windows-2025` 上构建 `node24-win-x64`，与现有三个目标并列。公开 GitHub 发布与 GitLab 标签流水线都会发布同一组四个运行时 wheel 加纯 SDK wheel。目标解析、manifest、矩阵、发布内容与文档均不包含 Windows arm64。
+必需 GitHub 矩阵会在 `windows-2025` 上构建 `node24-win-x64`，与 Linux x64、Linux arm64、macOS arm64 和 macOS x64 并列。公开 GitHub 发布与 GitLab 标签流水线都会发布同一组五个运行时 wheel 加纯 SDK wheel。目标解析、manifest、矩阵、发布内容与文档均不包含 Windows arm64。
 
 ### Installed-wheel 行为
 
@@ -48,4 +48,4 @@ Windows lane 会创建干净的 Windows 虚拟环境，安装版本精确匹配
 
 ## Consequences
 
-Python 安装现在会选择无需 Node 的 Windows x64 运行时，并与 Linux、macOS 使用同一套显式 home 与 profile 自定义模型。每个拉取请求都要承担第四个可执行文件、运行时 wheel 与完整 keyless 黑盒测试；可信 head 还要承担真实提供方任务。候选发行版验证会保留五个而不是四个 wheel。Windows arm64 用户会收到明确的不支持平台错误，直到另一项原生产品决策提供并证明该载体。
+Python 安装会选择无需 Node 的 Windows x64 运行时，并与 Linux、macOS 使用同一套显式 home 与 profile 自定义模型。每个拉取请求都会把 Windows 可执行文件和运行时 wheel 作为五个原生目标之一进行构建，运行完整 keyless 黑盒测试，并在可信 head 上运行真实提供方任务。候选发行版验证会保留六个 wheel。Windows arm64 用户会收到明确的不支持平台错误，直到另一项原生产品决策提供并证明该载体。

.agents/notes/implemented/architecture/2026-08-25-rename-code-mode-to-ptc.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-25-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

.agents/notes/implemented/architecture/2026-08-25-rename-code-mode-to-ptc.md

@@ -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).

.agents/notes/implemented/architecture/2026-08-25-rename-code-mode-to-ptc.zh.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)。

.agents/notes/implemented/architecture/2026-08-27-handle-based-session-persistence.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-27-handle-based-session-persistence.md
-2026-08-27-handle-based-session-persistence.md: ced7a78178d3036fd5fa9a09ca49f8c751c3a169
-2026-08-27-handle-based-session-persistence.zh.md: e13b5b0e9e7286411b6d38f3b9dc0e86fa742a3d
+2026-08-27-handle-based-session-persistence.md: d3fbbe8137c8ac4a1b6897914db26c010036faa8
+2026-08-27-handle-based-session-persistence.zh.md: f8846f4b54cd6b8bb654cb29bbf49d0ee99ccfa8

.agents/notes/implemented/architecture/2026-08-27-handle-based-session-persistence.md

@@ -18,7 +18,7 @@ The previous persistence seam owned far more than storage. A shared coordinator
 
 **Visibility and freshness are explicit.** A created session is observable in-process from `create`; physical materialization may be deferred (a pure optimization) until the first append or flush, other processes see only materialized sessions, and a crash before materialization means the session never existed. Once an append or flush resolves, reads started afterwards on the same backend instance observe at least that prefix — the guarantee `message-feedback`'s durable-target check rides on.
 
-**Revision simplifies to a per-instance change token.** Equal tokens may be treated as an unchanged log; ownership churn never changes one. JSONL derives a best-effort token and `sizeBytes` from one `fs.stat`; a backend whose medium can count events cheaply may supply the `eventCount` hint instead. The session-list cold blank probe returns on this metadata (`coldBlankProbeMaxEvents`/`coldBlankProbeMaxBytes`), restoring the capability removed with the path query.
+**Revision simplifies to a per-instance change token.** Equal tokens may be treated as an unchanged log; ownership churn never changes one. JSONL derives a best-effort token and `sizeBytes` from one `fs.stat`; a backend whose medium can count events cheaply may supply the `eventCount` hint instead. Session listing remains a zero-body-read metadata/cache operation: it trusts a cached nonblank projection, keeps a cached blank value only when the current cache identity matches, and otherwise reports `blank: false` as the visible unknown fallback. No cold blank probe or probe-limit configuration remains.
 
 ## Alternatives considered
 
@@ -37,6 +37,6 @@ Resume, fork, subagent, ACP, webhook, and SDK sessions all persist through one e
 ## Related
 
 - [Session persistence as an abstract service](2026-06-14-session-persistence.md) — the seam this reshapes; its interface list reflects the handle API.
-- [Persistence export() and pre-release trims](../simplification/2026-08-27-persistence-export-and-pre-release-trims.md) — the preparatory removals, including the blank probe this note's metadata restores.
+- [Persistence export() and pre-release trims](../simplification/2026-08-27-persistence-export-and-pre-release-trims.md) — the preparatory removals, including the retired cold blank probe.
 - [Retain ignorable external session events](2026-08-30-retain-ignorable-external-session-events.md) — the read-side refusal contract, now shared through `storage-contract` helpers.
 - [Bounded session-persistence write batching](2026-08-08-bounded-session-persistence-write-batching.md) — the batching semantics the routed write path preserves as internal scheduling policy.

.agents/notes/implemented/architecture/2026-08-27-handle-based-session-persistence.zh.md

@@ -18,7 +18,7 @@ Status: implemented
 
 **可见性与新鲜度是显式的。**已创建的会话自 `create` 起即可在进程内被观察到；物理实体化（纯粹的优化）可以推迟到第一次 append 或 flush，其他进程只能看到已实体化的会话，实体化之前崩溃意味着该会话从未存在。一旦某次 append 或 flush 完成，其后在同一后端实例上开始的读取至少能观察到该前缀——这正是 `message-feedback` 持久目标检查所依赖的保证。
 
-**revision 简化为逐实例变更令牌。**令牌相等可视为日志未变；所有权变动绝不会改变令牌。JSONL 通过一次 `fs.stat` 派生尽力而为的令牌与 `sizeBytes`；存储介质能够廉价统计事件数的后端可以改为提供 `eventCount` 提示。会话列表的冷空白探测回归到这些元数据之上（`coldBlankProbeMaxEvents`/`coldBlankProbeMaxBytes`），恢复了随路径查询一起移除的能力。
+**revision 简化为逐实例变更令牌。**令牌相等可视为日志未变；所有权变动绝不会改变令牌。JSONL 通过一次 `fs.stat` 派生尽力而为的令牌与 `sizeBytes`；存储介质能够廉价统计事件数的后端可以改为提供 `eventCount` 提示。Session listing 保持零正文读取的 metadata/cache 操作：它信任缓存的非空 projection，只在当前 cache identity 匹配时保留缓存的空值，否则用 `blank: false` 表示可见的未知回退。冷空白探测及其探测限制配置均不再存在。
 
 ## 考虑过的替代方案
 
@@ -37,6 +37,6 @@ Status: implemented
 ## 相关
 
 - [作为抽象服务的会话持久化](2026-06-14-session-persistence.zh.md)——本 Note 重塑的 seam；其接口列表已反映句柄 API。
-- [持久化 export() 与预发布读取路径精简](../simplification/2026-08-27-persistence-export-and-pre-release-trims.zh.md)——预备性的移除，包括本 Note 的元数据所恢复的空白探测。
+- [持久化 export() 与预发布读取路径精简](../simplification/2026-08-27-persistence-export-and-pre-release-trims.zh.md)——预备性的移除，包括已退役的冷空白探测。
 - [保留可忽略的外部会话事件](2026-08-30-retain-ignorable-external-session-events.zh.md)——读取侧的拒绝约定，现经由 `storage-contract` 辅助函数共享。
 - [为会话持久化写入批处理设定上界](2026-08-08-bounded-session-persistence-write-batching.zh.md)——被路由写路径作为内部调度策略保留的批处理语义。

.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.i18n.yaml → .agents/notes/implemented/architecture/2026-08-27-outbound-proxy-policy.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md
-2026-08-15-packed-session-history-transport.md: 01e36509b7ad2c878ae4ea04c3a10f029e1b8f3d
-2026-08-15-packed-session-history-transport.zh.md: 6ef847a14da1b4ec1bd59e5aaad9093162b42d84
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-27-outbound-proxy-policy.md
+2026-08-27-outbound-proxy-policy.md: 67927a9d1404e0b14c6e420cc5bea462be5c87ad
+2026-08-27-outbound-proxy-policy.zh.md: cf0b203a061522450a2a1b0c337a060b0c387684

.agents/notes/implemented/architecture/2026-08-27-outbound-proxy-policy.md

@@ -0,0 +1,99 @@
+# Agent Note: One outbound proxy policy, installed before anything can request
+
+Status: implemented
+
+English | [中文](2026-08-27-outbound-proxy-policy.zh.md)
+
+## Problem
+
+Node's built-in `fetch` ignores `HTTP_PROXY` and `HTTPS_PROXY`. Every other tool a developer runs — curl, git, npm, pip — honours them, so a user behind a proxy exports the variables once and expects everything to follow. The harness did not: `setGlobalDispatcher`, `ProxyAgent`, and `EnvHttpProxyAgent` appeared zero times across `packages/` and `apps/`, so the model request, every web search, `web_fetch`, MCP over HTTP, the OTLP exporter, and the E2B SDK all connected directly, silently, with no diagnostic anywhere.
+
+The repository had briefly had an answer and lost it without noticing. PR #971 set `NODE_USE_ENV_PROXY=1` in `bin/dsh`; eleven days later `bbb1b1cc38 cleanup: remove managed source installer` deleted that launcher wholesale, taking the flag with it. What survived was one sentence in `apps/cli/reference/README.md` telling the reader to set a variable that nothing consumed any more.
+
+That sentence could not have worked anyway, for three measured reasons. `NODE_USE_ENV_PROXY` samples the environment at process start, while `loadLayeredEnv()` merges the `.env` layers afterwards, so a proxy declared in `$DSH_HOME/.env` is invisible to it. It reaches Node 24.0+ and, on the 22 line, only 22.21+ — while `engines` admits `^22.19.0`, where the variable does not exist and setting it warns about nothing. And it does not reach `web-fetch-http` at all: that provider passes its own `dispatcher` to `fetch`, and an explicit dispatcher overrides the global one whatever the flag says.
+
+## Decision
+
+**One policy, resolved once from the launch environment, installed as the global dispatcher.** `packages/util/http-proxy` resolves a `ProxyPolicy` and installs it in `runProfile` immediately after the environment snapshot is provided and before any entry mounts. Node's `fetch` resolves undici's global dispatcher, so every plain `fetch()` and every SDK that reaches `globalThis.fetch` is covered without touching its code — nine call sites at the time of writing, and every future one for free. `loadLayeredEnv` has exactly one caller and `apps/web` ships no bin, so this single site covers every profile including `sdk-minimal`, which does not layer over `base`.
+
+Resolution reads the launcher's snapshot rather than `process.env`, which is what makes a proxy in `$DSH_HOME/.env` work — the capability the environment-variable approach cannot have. Only that file: `loadLayeredEnv` refuses a proxy name in the project `.env` exactly as it refuses `PATH` or `NODE_OPTIONS` there, because that file arrives with a clone and must not choose the harness's route. The home file is exempt for the four proxy names alone, and `DSH_HOME` is itself bootstrap-only, so no `.env` can point the exemption at a directory a repository controls.
+
+**A library in `util/`, not a plugin.** Transport policy has one answer per process: nothing to swap, and no scope narrower than the process to give one. The package exports functions and mounts nothing — `boot`, `web`, `subprocess`, and `workflow` all consume it, and `util/` is the group every other group may depend on.
+
+An earlier revision put it in a new `net/` package group, reasoning that depending on `undici` disqualified it from a "zero-dependency" group. That reading was wrong: [dependencies over hand-rolling](../process/2026-07-26-dependencies-over-hand-rolling.md) records that the charter governs *harness* dependencies — util stays free of them so any group can depend on util — and does not ban external packages. What did need removing was the dependency on `dsh-launch-environment`: resolution needs one method from it, so it names a structural `EnvLookup` instead and the launcher passes its snapshot unchanged.
+
+The plugin that revision shipped is gone with it. It let a composition declare the policy in `cordis.yml`, but no shipped bundle mounted it, so the launcher's path was the only reachable one — and its `Config` was the sole supplier of a configuration branch nothing else could reach.
+
+**Four functions, because the call sites converged rather than the package growing an export each.** An earlier revision exported six: a dispatcher factory, a `node:http` agent factory, a proxy-URL lookup, a policy accessor, an installer, and a child-environment builder. Each existed for one SDK's transport, which is how a transport-policy package turns into a catalogue of other packages' constraints. Review asked whether the call sites could converge instead; they could, and each removal took a whole shape with it. Telemetry stopped being routed at all, retiring the `node:http` factory. `web-fetch-http` builds its own pinning agent under an annotated exemption, retiring the dispatcher factory. E2B reads `route.proxy`, retiring the proxy-URL lookup.
+
+What remains is `installProxyFromEnvironment`, `proxyRouteFor`, `proxyEnvironmentForChild`, and `clearedProxyEnv` — one per way a caller can need the policy, none per SDK. Installation absorbed resolution and diagnostic reporting, which no caller needed apart: a resolved policy that is not installed routes nothing.
+
+`proxyRouteFor` also closes a defect the old accessor made expressible. `web-fetch-http` read the policy to decide whether to pin, then read it again to build a transport; an unmount between the two returned a direct, unpinned agent for a URL the first read had cleared as proxied. A route carries both, so the branch and the request cannot disagree. Its dispatcher is the process-wide one, closed rather than destroyed on disposal, so a request already in flight when a policy is unmounted still finishes.
+
+**The installed dispatcher routes by the policy, not by an environment it re-parses.** Installation builds an `Agent` whose per-origin `factory` asks `proxyForUrl` where that origin goes, and returns a `ProxyAgent` or undici's own default client for it. undici's `EnvHttpProxyAgent` was the first choice and is wrong for this policy: when no `HTTPS_PROXY` is present it sets its HTTPS agent to the HTTP one, so a scheme this package keeps direct after refusing a SOCKS or malformed URL would still be tunnelled while the diagnostic said otherwise. Routing through the one predicate removes that class of divergence by construction rather than by test. Publishing the policy into the environment remains, but now serves one reader only: a spawned child, which has no policy object to consult.
+
+This keeps `proxyForUrl()` and the dispatcher answering from one set of values. They must agree: if they disagreed about a URL, `web-fetch-http` would pin a connection the dispatcher meant to tunnel.
+
+**Resolution supplies what neither Node nor undici does.** `ALL_PROXY` backs both schemes; a blank value counts as unset, because undici's `??` chain lets an empty lowercase name shadow a populated uppercase one; loopback is always bypassed, since the Web UI, the Connection transport, and every local test server would otherwise route through the proxy and loop. The bypass list carries `::1` *and* `[::1]`: undici's own matcher reads a bare `::1` as host `:` port `1` and never exempts it.
+
+**Rejection is quiet, and never reroutes the refused scheme.** A slot the user filled and this package refused keeps that scheme direct rather than falling through to `ALL_PROXY` or the HTTP proxy, so the diagnostic and the route agree. A SOCKS URL, an unparseable string, or an unsupported scheme is reported on stderr and skipped — the variable may have been exported for other tools, and a typo in it must not stop the agent from starting. The environment is the only source, so no configuration surface exists where `AGENTS.md`'s fail-loud rule would apply instead.
+
+**Through a proxy, `web_fetch` stops resolving and pinning.** The provider validates a public address set and pins the connection to it. Through a proxy there is nothing to pin — the proxy performs the origin's DNS — and a pinned direct connection would bypass the proxy entirely. So a proxied hop skips resolution, and configuring a proxy is a statement that the proxy is trusted with destination selection. A hop the policy bypasses, which includes every loopback and every `NO_PROXY` entry, takes the resolved-and-pinned path unchanged. Kimi Code and Claude Code reached this same conclusion independently.
+
+The URL-level policy is untouched: `http(s)` only, no embedded credentials, the length cap, and the cross-origin redirect refusal all still apply on every hop.
+
+**A spawned child gets the policy through its environment; a model-executing worker gets nothing.** `proxyEnvironmentForChild()` merges into `scrubbedParentEnv()`, the one function every spawner already shares. The workflow worker does NOT receive it: it executes the model-authored script body, and a proxy URL may carry `user:password`. That is the same containment the code runtime keeps and `docs/defensive-patterns.md` requires, so a workflow's own requests go direct.
+
+The child keeps the user's own values, and that is what once broke it. Node parses `HTTP_PROXY` and `HTTPS_PROXY` under `NODE_USE_ENV_PROXY` before running the program and exits on any scheme other than `http:` or `https:`; a `socks4://` kept for `curl` therefore ended every Node child — MCP servers, subagent CLIs, `npm` — before its first line, while this process had reported only that the scheme stayed direct. Measured on Node 24.17: `socks4://`, `ftp://`, and a malformed value all exit 1; `socks5://` happens to be accepted there. The flag is now withheld whenever a value the child receives is one this package refused, so such a child connects directly and `curl` still reads the value it was kept for. Handing the child the resolved value instead would have kept Node proxied at the price of silently rewriting what the user set for another tool.
+
+This accepts a documented seam. Such a context matches bypass entries by Node's rules, which differ from this package's in separators and IPv4-range support, and the flag exists only on Node 22.21+ and 24+.
+
+**Two SDKs do not reach `globalThis.fetch`, and reading their code said otherwise.** The audit first classified the OTLP exporter and the E2B SDK as covered, on a grep that found `globalThis.fetch` in `@opentelemetry/otlp-exporter-base`. That match is the *browser* transport; on Node the delegate selects `http-exporter-transport`, which posts through `node:http` — where a global dispatcher does not reach. E2B is a second shape again: it builds its own undici `Agent`/`ProxyAgent` and takes a `proxy` URL that it never reads from the environment. Both were measured direct. E2B is handed `route.proxy` from `proxyRouteFor`, the same call `web-fetch-http` makes. Telemetry is deliberately left direct, and that exclusion is the more interesting half.
+
+**Telemetry stays direct on purpose.** Routing it needs one of two things, and both cost more than the channel is worth. An `http.Agent` reads the environment through `proxyEnv`, which arrived in Node 22.21 and 24.5 — inside the engines range, so 22.19, 22.20, and 24.0–24.4 would stay direct regardless, and the proxy package would have to keep a `createNodeHttpAgent` export for a path that works on some runtimes. Replacing the transport with the SDK's `fetch` delegate covers every runtime, but that delegate has no compression, and the shipped `base` bundle enables gzip: a realistic OTLP batch measures 6.4x smaller with it. An attempt that refused `exporter.compression` instead broke every test that boots the shipped bundle, and one that gzipped at the serializer worked but put transport code in a telemetry plugin to keep it working.
+
+Weighed against that, telemetry is the one outbound channel whose loss costs the user nothing: no tool, no model request, and no session depends on it, and an export that cannot connect is already dropped silently. A user behind a mandatory proxy is left exactly where they were before this change rather than regressed. `egress.spec.ts` now asserts the exclusion — an SDK upgrade that moved the exporter onto `fetch` would start routing telemetry through a proxy silently, and that case is what makes it visible.
+
+**Every call site carries an egress test, because reading the code was not enough.** `egress.spec.ts` in each owning package drives that site's real code path at an unresolvable `.invalid` host through a fake proxy and asserts the proxy saw the request. Nine of them cover the search backends, pi-ai discovery, MCP over HTTP, E2B, a spawned child Node, a worker thread, and telemetry's exclusion. The gate below cannot see inside a dependency; these can, and they are what turns "an SDK changed its transport" from a silent regression into a failing test.
+
+**A gate keeps the defect from returning.** `verify-no-bare-dispatcher` parses the TypeScript AST — `scripts/AGENTS.md` requires syntax-aware discovery, and a line-wise regex missed both the `{ dispatcher }` shorthand this repository already uses and a `new Alias(...)` behind a renamed import. It rejects an undici agent construction and an explicit `dispatcher` option outside the owning package. `proxyRouteFor(url)` is the sanctioned replacement, and the one call site that genuinely owns its transport — `web-fetch-http`, pinning a request to addresses it validated — says so with a `proxy-exempt:` comment. The rule exists because `web-fetch-http`'s original `new Agent` was entirely reasonable when it was written — proxying simply did not exist yet, and nothing would have caught it.
+
+## Alternatives considered
+
+**Document `NODE_USE_ENV_PROXY=1` and stop.** Rejected on three measurements, above: invisible to `$DSH_HOME/.env`, absent on the lowest supported Node, and bypassed by `web-fetch-http` regardless. It is also what the repository already claimed to do.
+
+**Thread a policy value to every call site.** DeepSeek-Reasonix does this across 98 sites, buying a per-provider opt-out. Rejected: that opt-out exists for a need this harness does not have, and nine sites changed by hand means the tenth is forgotten — Pi's changelog records OAuth and Bedrock as two separate after-the-fact fixes of exactly that kind. The isolation argument for it is real, and is answered instead by handling worker threads explicitly and by proving disposal restores the previous dispatcher.
+
+**`http.setGlobalProxyFromEnv()`.** Node's own programmatic switch covers `fetch` and `node:http` together and returns a restore function — the shape `ctx.effect()` wants. Unusable: `added: v24.14.0`, with nothing on the 22 line. Worth revisiting if `engines` ever rises past it.
+
+**Patch `globalThis.fetch` via `undici.install()`.** Pi does, to keep fetch and the dispatcher on one undici when a newer Node's bundled fetch mishandles compressed responses through a userland dispatcher. Rejected as speculative here: this repository's `engines` ceiling has not reached that runtime.
+
+**Make this a capability seam.** Rejected. Service Definition / Provider / Consumer is for swappable backends; this has one implementation and one answer per process. If operating-system proxy or PAC support ever lands, `resolveProxyPolicy` is the extension point.
+
+**Read the operating system's proxy settings.** Rejected for this change. Only Codex and Reasonix among six surveyed products do it, and Codex keeps it behind a default-off flag. Measured on the author's machine, it would have found nothing: the proxy application had written the setting to the Wi-Fi service while the primary interface was a USB ethernet adapter with no proxy, so `scutil --proxy` reported none while the exported variables worked. It also needs its own bypass matcher, because an operating system list carries CIDR entries that neither undici nor Node matches.
+
+**Give the `code-runtime` worker the proxy too.** Rejected. Model-authored programs run there with no ambient environment at all — a stronger containment than the scrubbed environment spawned commands get — and a proxy URL may carry credentials. Handing model code a credentialed URL to reach the network is the wrong trade; the exclusion is recorded in that package's limitations.
+
+## Consequences
+
+A user who exports `HTTPS_PROXY`, or writes it into `$DSH_HOME/.env`, is proxied everywhere the harness makes a request, with no flag and no configuration. The launcher installs it exactly once, before the first plugin mounts.
+
+Because the operating system's settings are not read, the user-facing documentation is now load-bearing rather than supplementary: a user who only toggled "system proxy" in a proxy application gets nothing and no diagnostic. `docs/user/guide/network-proxy.md` therefore states which variables to export and why a browser is proxied when a terminal is not — the three-mechanism confusion is the single most common report, and it is not specific to this harness.
+
+`web_fetch`'s safety story now has two shapes, and its README says so: direct hops keep address validation and pinning, proxied hops delegate destination selection to a proxy the operator configured. This is the one outward-facing security promise the change alters.
+
+Reaching Node's built-in `fetch` from a userland undici depends on both writing the legacy `Symbol.for('undici.globalDispatcher.1')` slot. That is an implicit cross-version coupling rather than a contract — corepack#834 records it breaking — so `tests/install.spec.ts` drives a real request through a loopback proxy. A version bump that breaks the coupling fails there instead of in the field.
+
+The suite is hermetic against the developer's own environment: every Vitest configuration runs `scripts/test-proxy-environment.ts`, which clears all eight proxy names in both casings before any test, and `install.spec.ts` restores the machine's values around each case that sets its own. It has to. An exported lowercase `all_proxy` decided a test's outcome during development, because resolution reads lowercase first.
+
+## Testing
+
+`packages/util/http-proxy` holds 84 tests at 100% per-file coverage. Resolution covers precedence, the `ALL_PROXY` fallback, blank-shadowing, the SOCKS and malformed diagnostics, and the HTTPS-only environment that leaves `http:` direct; routing covers the whole loopback range structurally, and bypass matching covers suffixes, ports, both IPv6 spellings, and the CIDR entry that deliberately does not match. Installation drives a real loopback proxy and asserts the absolute-form request arrives, that a bypassed target does not, and that disposal restores the dispatcher, the policy, and the environment. Every case installs through `installProxyFromEnvironment`, so no test can assert a policy object a real launch could not produce.
+
+`packages/web/web-fetch-http/tests/proxy.spec.ts` asserts the decision that matters most: under a proxy the public-address resolver is never called, while a bypassed hop still calls it exactly once, and the cross-origin redirect refusal survives on the proxied path.
+
+`verify-no-bare-dispatcher.spec.ts` proves the gate rejects the exact shape this package was introduced to fix, accepts `proxyRouteFor`, accepts an annotated exemption, and passes on the current tree.
+
+The egress suite carries telemetry's case in the negative: the shipped backend exports under an installed policy and the fake proxy sees nothing, so the deliberate exclusion is asserted rather than merely documented. A parity suite checks `proxyForUrl` against where a real `fetch` actually went for every form in the documented `NO_PROXY` vocabulary; since the dispatcher routes by that same predicate, what it now catches is a form `bypassesProxy` reads differently from how the vocabulary documents it, and any future dispatcher that reintroduces a second matcher.
+
+No recorded-session snapshot changes: nothing here alters a model-visible input or product-user-visible transcript output.

.agents/notes/implemented/architecture/2026-08-27-outbound-proxy-policy.zh.md

@@ -0,0 +1,99 @@
+# Agent Note: 一份出站代理策略，在任何请求发生之前装好
+
+Status: implemented
+
+[English](2026-08-27-outbound-proxy-policy.md) | 中文
+
+## Problem
+
+Node 内置的 `fetch` 会忽略 `HTTP_PROXY` 与 `HTTPS_PROXY`。开发者运行的其他工具——curl、git、npm、pip——都遵循它们，所以代理后面的用户导出一次变量就期待一切随之生效。Harness 并没有：`setGlobalDispatcher`、`ProxyAgent` 与 `EnvHttpProxyAgent` 在 `packages/` 与 `apps/` 中出现次数为零，因此模型请求、每次 web 搜索、`web_fetch`、走 HTTP 的 MCP、OTLP 导出器与 E2B SDK 全部直连，且是静默的，任何地方都没有诊断。
+
+仓库曾短暂拥有过答案，又在无人察觉时弄丢了。PR #971 在 `bin/dsh` 里设置了 `NODE_USE_ENV_PROXY=1`；十一天后 `bbb1b1cc38 cleanup: remove managed source installer` 整体删除了那个启动器，把该标志一并带走。留下的只有 `apps/cli/reference/README.md` 里的一句话，让读者去设置一个已经无人消费的变量。
+
+即便照做，那句话也不可能生效，原因有三条且都经过实测。`NODE_USE_ENV_PROXY` 在进程启动时对环境取快照，而 `loadLayeredEnv()` 是在之后才合并 `.env` 层，因此写在 `$DSH_HOME/.env` 中的代理对它不可见。它只覆盖 Node 24.0+，在 22 线上只覆盖 22.21+——而 `engines` 允许 `^22.19.0`，那里根本没有这个变量，设置了也不会有任何警告。它也完全触及不到 `web-fetch-http`：该提供方向 `fetch` 传入自己的 `dispatcher`，而显式 dispatcher 无论标志如何都会覆盖全局的那个。
+
+## Decision
+
+**一份策略，从启动环境解析一次，装为全局 dispatcher。** `packages/util/http-proxy` 解析出 `ProxyPolicy`，并在 `runProfile` 中于环境快照提供之后、任何 entry 挂载之前完成安装。Node 的 `fetch` 解析的正是 undici 的全局 dispatcher，因此每一处普通 `fetch()` 以及每一个最终落到 `globalThis.fetch` 的 SDK 都无需改动即被覆盖——撰写时是九个调用点，未来新增的也自动覆盖。`loadLayeredEnv` 只有一个调用方，且 `apps/web` 不提供 bin，因此这一处即覆盖全部 profile，包括不叠加 `base` 的 `sdk-minimal`。
+
+解析读取的是启动器的快照而非 `process.env`，这正是让 `$DSH_HOME/.env` 中的代理生效的原因——也是环境变量方案不可能具备的能力。仅限该文件：`loadLayeredEnv` 拒绝项目 `.env` 里的代理名，正如它在那里拒绝 `PATH` 或 `NODE_OPTIONS`，因为那个文件随 clone 一起到来，不得替 Harness 选择路由。home 文件仅对这四个代理名豁免，而 `DSH_HOME` 本身是 bootstrap-only，因此没有任何 `.env` 能把这份豁免指向仓库控制的目录。
+
+**放在 `util/` 的库，而非插件。** 传输策略每个进程只有一个答案：没有可替换的实现，也没有比进程更窄的作用域可赋予。因此本包只导出函数、不挂载任何东西——`boot`、`web`、`subprocess` 与 `workflow` 都消费它，而 `util/` 正是其他所有组都可以依赖的那一组。
+
+早先的修订把它放进新建的 `net/` 包组，理由是依赖 `undici` 使它不符合“零依赖”组。那个理解是错的：[优先使用依赖而非手写](../process/2026-07-26-dependencies-over-hand-rolling.zh.md) 记录了该章程约束的是 *harness* 依赖——util 不依赖它们，任何组才都能依赖 util——并不禁止外部包。真正需要去掉的是对 `dsh-launch-environment` 的依赖：解析只用到它的一个方法，于是改为声明结构化的 `EnvLookup`，启动器原样传入自己的快照即可。
+
+那次修订一并引入的插件也随之删除。它让某个组合可以把策略写进 `cordis.yml`，但没有任何随附 bundle 挂载它，因此启动器那条路径是唯一可达的——而它的 `Config` 是那条配置分支唯一的供给方，别处无从到达。
+
+**四个函数——收敛的是调用方，而不是让本包为每个 SDK 各加一个导出。** 早先一版导出六个：dispatcher 工厂、`node:http` agent 工厂、代理 URL 查询、策略访问器、安装器与子进程环境构造器。每一个都为某个 SDK 的传输而存在，而这正是一个传输策略包退化成「别的包的约束目录」的过程。Review 问能不能反过来让调用方收敛；能，而且每删掉一个导出都带走了一整种写法。遥测不再被路由，`node:http` agent 工厂随之退场。`web-fetch-http` 在带注释的豁免下自建 pin agent，dispatcher 工厂随之退场。E2B 读 `route.proxy`，代理 URL 查询随之退场。
+
+剩下的是 `installProxyFromEnvironment`、`proxyRouteFor`、`proxyEnvironmentForChild` 与 `clearedProxyEnv`——按「调用方需要策略的方式」各一个，而不是按 SDK 各一个。安装吸收了解析与诊断上报，因为没有调用方需要把它们分开：解析出来却不安装的策略什么也路由不了。
+
+`proxyRouteFor` 还堵掉了旧访问器让人写得出来的一个缺陷。`web-fetch-http` 先读策略决定是否 pin，再读一次去构造传输；两次读取之间发生卸载，就会为第一次读取已判定走代理的 URL 返回一个直连且未 pin 的 agent。路由把两者一起交出，分支与请求便无从分歧。它携带的是进程级 dispatcher，dispose 时是 close 而非 destroy，因此策略被卸载时已经发出的请求仍会跑完。
+
+**已安装的 dispatcher 按策略路由，而不是重新解析一遍环境。** 安装过程构造一个 `Agent`，其按 origin 调用的 `factory` 会询问 `proxyForUrl` 该 origin 的去向，并据此返回 `ProxyAgent` 或 undici 自带的默认客户端。undici 的 `EnvHttpProxyAgent` 曾是首选，但对这套策略是错的：没有 `HTTPS_PROXY` 时它会把 HTTPS agent 设为 HTTP agent，于是本包在拒绝某个 SOCKS 或畸形 URL 后本应保持直连的 scheme 仍会被隧道转发，而诊断却声称直连。让路由走同一个谓词，从构造上而非靠测试消除了这一类分歧。把策略发布到环境中的做法保留下来，但如今只服务一类读者：派生的子进程——它没有策略对象可查。
+
+这样 `proxyForUrl()` 与 dispatcher 就从同一组值给出答案。两者必须一致：一旦对某个 URL 产生分歧，`web-fetch-http` 就会把 dispatcher 本打算隧道转发的连接固定到某个地址上。
+
+**解析补上 Node 与 undici 都不提供的部分。** `ALL_PROXY` 为两种协议兜底；空值视为未设置，因为 undici 的 `??` 链会让空的小写名遮住有值的大写名；loopback 始终绕过，否则 Web UI、Connection 传输以及每一个本地测试服务器都会经由代理并形成回环。绕过列表同时携带 `::1` **与** `[::1]`：undici 自带的匹配器会把裸写的 `::1` 读成主机 `:` 端口 `1`，从而永不豁免它。
+
+**拒绝是静默的，且绝不为被拒协议改道。** 用户填写而被本包拒绝的槽位，会让该协议保持直连，而不是继续回退到 `ALL_PROXY` 或 HTTP 代理，从而让诊断与实际路由一致。SOCKS URL、无法解析的字符串或不受支持的协议，会在 stderr 上报告并跳过——该变量可能是为其他工具导出的，它的笔误不应阻止 agent 启动。环境是唯一来源，因此不存在一个本应适用 `AGENTS.md` 「配置错误必须响」规则的配置面。
+
+**经由代理时，`web_fetch` 不再解析与固定地址。** 该提供方会校验一组公网地址并把连接固定到其上。经由代理时没有可固定的对象——origin 的 DNS 由代理执行——而固定后的直连会彻底绕开代理。因此代理转发的一跳跳过解析，配置代理即表示信任该代理进行目的地选择。被策略绕过的一跳，包括每一个 loopback 与每一条 `NO_PROXY` 条目，仍走原有的解析并固定路径。Kimi Code 与 Claude Code 各自独立得出了同一结论。
+
+URL 层策略未受影响：仅 `http(s)`、禁止内嵌凭据、长度上限与跨域重定向拒绝在每一跳上依然生效。
+
+**派生的子进程通过环境获得策略；执行模型代码的 worker 什么也不获得。** `proxyEnvironmentForChild()` 并入 `scrubbedParentEnv()`——每个 spawner 本就共享的那一个函数。workflow worker **不**接收它：它执行的是模型编写的脚本体，而代理 URL 可能携带 `user:password`。这与 code runtime 保持的隔离相同，也是 `docs/defensive-patterns.md` 的要求，因此 workflow 自身的请求直连。
+
+子进程拿到的是用户自己的值，而这恰恰曾把它弄坏。Node 在 `NODE_USE_ENV_PROXY` 下会在运行程序之前先解析 `HTTP_PROXY` 与 `HTTPS_PROXY`，遇到 `http:`/`https:` 之外的协议直接退出；于是一个为 `curl` 保留的 `socks4://` 会让每个 Node 子进程——MCP server、subagent CLI、`npm`——在第一行之前就终结，而本进程此前只报告过该协议保持直连。在 Node 24.17 上实测：`socks4://`、`ftp://` 与畸形值均以 1 退出；`socks5://` 恰好在该版本被接受。现在只要子进程收到的某个值是本包拒绝过的，就扣下该标志，这样的子进程直连，`curl` 仍读到为它保留的值。若改为把解析后的值交给子进程，Node 固然能继续走代理，代价却是悄悄改写用户为另一工具设置的值。
+
+这接受了一处已记录的接缝。此类上下文按 Node 自己的规则匹配绕过条目，其分隔符与 IPv4 区间支持与本包不同，且该标志仅存在于 Node 22.21+ 与 24+。
+
+**有两个 SDK 并不落到 `globalThis.fetch`，而读代码给出的答案是相反的。** 审计最初把 OTLP 导出器与 E2B SDK 判为已覆盖，依据是在 `@opentelemetry/otlp-exporter-base` 里 grep 到了 `globalThis.fetch`。那处命中属于**浏览器**传输；在 Node 上 delegate 选择的是 `http-exporter-transport`，它通过 `node:http` 投递——那里全局 dispatcher 触及不到。E2B 又是另一种形态：它自建 undici `Agent`／`ProxyAgent`，并接受一个自己从不从环境读取的 `proxy` URL。两者都实测为直连。E2B 接收 `proxyRouteFor` 给出的 `route.proxy`，与 `web-fetch-http` 调的是同一个函数。遥测则被有意保留为直连，而这个排除项才是更值得说的一半。
+
+**遥测的直连是有意为之。** 要让它走代理只有两条路，代价都超过这条通道本身的价值。`http.Agent` 通过 `proxyEnv` 读取环境，而该选项自 Node 22.21 与 24.5 才有——落在 engines 范围之内，因此 22.19、22.20 与 24.0–24.4 无论如何仍是直连，而代理包还得为一条只在部分运行时生效的路径保留 `createNodeHttpAgent` 导出。改用 SDK 的 `fetch` delegate 替换传输可以覆盖所有运行时，但该 delegate 没有压缩能力，而随附的 `base` bundle 启用了 gzip：实测一批真实规模的 OTLP 数据启用后体积只有 1/6.4。曾有一版转而在加载期拒绝 `exporter.compression`，结果凡是启动随附 bundle 的测试全部失败；另一版在 serializer 处 gzip 确实能跑通，但代价是把传输层代码塞进了遥测插件。
+
+与之相比，遥测是唯一一条丢失了对用户毫无代价的出网通道：没有任何工具、模型请求或会话依赖它，而连不上的导出本就被静默丢弃。处在强制代理后的用户，只是停留在本次改动之前的状态，而不是被弄坏。`egress.spec.ts` 现在断言这一排除——若某次 SDK 升级把导出器挪到 `fetch` 上，遥测就会开始静默走代理，而该用例正是让这件事暴露出来的东西。
+
+**每个出网点都配一份出网测试，因为读代码不够。** 各所属包中的 `egress.spec.ts` 驱动该点的真实代码路径，目标是无法解析的 `.invalid` 主机，穿过一个假代理，并断言代理确实收到了请求。九份测试覆盖搜索后端、pi-ai 发现、走 HTTP 的 MCP、E2B、派生的子 Node、worker 线程，以及遥测的排除。下面那条门禁看不进依赖内部；这些能，它们把「某个 SDK 换了传输」从静默回归变成失败的测试。
+
+**用门禁防止该缺陷复现。** `verify-no-bare-dispatcher` 解析 TypeScript AST——`scripts/AGENTS.md` 要求 source-ownership 门禁使用语法感知发现，而逐行正则漏掉了本仓库已在使用的 `{ dispatcher }` 简写，以及重命名导入后的 `new Alias(...)`。它在所属包之外拒绝 undici agent 构造与显式 `dispatcher` 选项。`proxyRouteFor(url)` 是受支持的替代；唯一一处确实自有传输的调用点——`web-fetch-http`，它把请求钉在已校验的地址上——用 `proxy-exempt:` 注释说明。这条规则之所以存在，是因为 `web-fetch-http` 里原本那行 `new Agent` 在写下时完全合理——那时根本还没有代理这回事，也没有任何机制会拦下它。
+
+## Alternatives considered
+
+**只写文档，让用户设 `NODE_USE_ENV_PROXY=1`。** 基于上文三条实测被否决：对 `$DSH_HOME/.env` 不可见、在最低支持的 Node 上不存在、且无论如何被 `web-fetch-http` 绕过。而这恰恰是仓库此前声称的做法。
+
+**把策略值传递到每一个调用点。** DeepSeek-Reasonix 在 98 处这样做，换来每提供方的 opt-out。被否决：该能力服务于本 Harness 并不具备的需求，而手工改九处意味着第十处会被遗忘——Pi 的变更日志正记录了 OAuth 与 Bedrock 两次事后补漏。它关于隔离性的论点确实成立，本方案改为显式处理 worker 线程、并以「dispose 后还原前一个 dispatcher」的断言来回应。
+
+**`http.setGlobalProxyFromEnv()`。** Node 自带的程序化开关同时覆盖 `fetch` 与 `node:http`，并返回还原函数——正是 `ctx.effect()` 想要的形态。不可用：`added: v24.14.0`，22 线上完全没有。若 `engines` 日后升过该版本，值得回头替换。
+
+**用 `undici.install()` patch `globalThis.fetch`。** Pi 这样做，是为了让 fetch 与 dispatcher 处于同一个 undici——较新 Node 的内置 fetch 经 userland dispatcher 处理压缩响应时会出错。此处被否决为投机性复杂度：本仓库 `engines` 的上限尚未触及该运行时。
+
+**做成能力接缝。** 被否决。Service Definition／Provider／Consumer 用于可替换后端；这里每个进程只有一种实现、一个答案。若日后要支持操作系统代理或 PAC，`resolveProxyPolicy` 就是扩展点。
+
+**读取操作系统的代理设置。** 本次变更中被否决。所调研的六个产品中只有 Codex 与 Reasonix 这样做，且 Codex 把它放在默认关闭的开关之后。在作者机器上实测，它什么也读不到：代理软件把设置写在了 Wi-Fi 服务上，而主接口是一块没有代理的 USB 以太网卡，因此 `scutil --proxy` 报告无代理，而导出的环境变量却工作正常。它还需要自带的绕过匹配器，因为操作系统的列表含有 undici 与 Node 都不匹配的 CIDR 条目。
+
+**也把代理给 `code-runtime` worker。** 被否决。模型编写的程序在那里运行时完全没有环境变量——这比派生命令得到的 scrubbed 环境更严——而代理 URL 可能携带凭据。把带凭据的 URL 交给模型代码去访问网络是错误的取舍；该排除已记入那个包的限制清单。
+
+## Consequences
+
+导出了 `HTTPS_PROXY`、或把它写进 `$DSH_HOME/.env` 的用户，在 Harness 发起请求的每一处都会走代理，无需任何标志与配置。启动器在第一个插件挂载之前恰好安装一次。
+
+由于不读取操作系统设置，面向用户的文档从补充材料变成了承重件：仅在代理软件里拨了「系统代理」开关的用户什么也得不到，且没有诊断。因此 `docs/user/guide/network-proxy.md` 说明了要导出哪些变量，以及为什么浏览器走代理而终端不走——这个「三套机制」的困惑是最常见的报障，且并非本 Harness 特有。
+
+`web_fetch` 的安全叙述现在有两种形态，其 README 已如实说明：直连的一跳保留地址校验与固定，代理转发的一跳把目的地选择交给运维方配置的代理。这是本次变更唯一改动的对外安全承诺。
+
+userland undici 能触及 Node 内置的 `fetch`，依赖于两者都会写入 legacy 的 `Symbol.for('undici.globalDispatcher.1')` 槽位。那是跨版本的隐式耦合而非约定——corepack#834 记录了它失效的实例——因此 `tests/install.spec.ts` 会驱动一次真实请求穿过 loopback 代理。破坏该耦合的版本升级会在那里失败，而不是流到线上。
+
+测试套件对开发者自身的环境免疫：每份 Vitest 配置都会先运行 `scripts/test-proxy-environment.ts`，在任何测试之前清除全部八个代理变量名的两种大小写形式；`install.spec.ts` 则在每个自行设值的用例前后还原本机的值。这是必需的。开发过程中，一个已导出的小写 `all_proxy` 曾决定了某个测试的结果，因为解析优先读取小写。
+
+## Testing
+
+`packages/util/http-proxy` 有 84 个测试，per-file 覆盖率 100%。解析覆盖优先级、`ALL_PROXY` 兜底、空值遮蔽、SOCKS 与畸形值诊断，以及只设 https 变量时 `http:` 保持直连；路由以结构化方式覆盖整个 loopback 网段，绕过匹配覆盖后缀、端口、两种 IPv6 写法，以及刻意不匹配的 CIDR 条目。安装驱动一个真实的 loopback 代理，断言绝对形式的请求确实抵达、被绕过的目标不抵达，且 dispose 会还原 dispatcher、策略与环境。所有用例一律经 `installProxyFromEnvironment` 安装，因此没有测试能断言一次真实启动无法产生的策略对象。
+
+`packages/web/web-fetch-http/tests/proxy.spec.ts` 断言了最关键的那个决定：经由代理时公网地址解析器完全不被调用，而被绕过的一跳仍恰好调用一次，且跨域重定向拒绝在代理路径上依然成立。
+
+`verify-no-bare-dispatcher.spec.ts` 证明该门禁能拒掉本包所要修复的那种写法、接受 `proxyRouteFor`、接受带注释的豁免，并在当前代码树上通过。
+
+出网测试以负向形式承载遥测这一项：随附后端在已安装策略下执行导出，而假代理什么也没收到——这个有意的排除因此是被断言的，而不只是被记录的。另有一组一致性测试，对文档所述 `NO_PROXY` 词汇中的每种形态，把 `proxyForUrl` 的判断与真实 `fetch` 的实际去向相互核对；由于 dispatcher 正是按同一谓词路由，它现在能抓住的是 `bypassesProxy` 对某种形态的读法与词汇文档不一致，以及未来任何重新引入第二个匹配器的 dispatcher。
+
+无录制会话快照变更：本次改动不影响任何模型可见输入或产品用户可见的 transcript 输出。

.agents/notes/implemented/architecture/2026-08-30-retain-ignorable-external-session-events.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-30-retain-ignorable-external-session-events.md
-2026-08-30-retain-ignorable-external-session-events.md: e79713cf16c627706939f33f6748eaa4821de870
-2026-08-30-retain-ignorable-external-session-events.zh.md: 8fddbfdd7e60716b0a78ef6b33de09935e9bd4d7
+2026-08-30-retain-ignorable-external-session-events.md: 1fe3a6d99a16daa6ad88f6717baa18f18e8c7355
+2026-08-30-retain-ignorable-external-session-events.zh.md: 632b7b418252c2b299162f3e00a4d41169169509

.agents/notes/implemented/architecture/2026-08-30-retain-ignorable-external-session-events.md

@@ -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.

.agents/notes/implemented/architecture/2026-08-30-retain-ignorable-external-session-events.zh.md

@@ -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。

.agents/notes/implemented/architecture/2026-08-31-alpha-historical-unknown-event-refusal.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-31-alpha-historical-unknown-event-refusal.md
+2026-08-31-alpha-historical-unknown-event-refusal.md: 58690e30281c1f5e10f85726c1f1e50fd4664fe9
+2026-08-31-alpha-historical-unknown-event-refusal.zh.md: 73ab2ca47ab3f68b11e71ffec09287253215aa53

.agents/notes/implemented/architecture/2026-08-31-alpha-historical-unknown-event-refusal.md

@@ -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. Merge-extensible nested discriminants remain part of that explicit policy: unknown content-block types, message-source kinds, assistant finish-reason kinds, and turn-ending reason kinds are preserved as owner-opaque JSON, while known arms receive structural validation. 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.

.agents/notes/implemented/architecture/2026-08-31-alpha-historical-unknown-event-refusal.zh.md

@@ -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。可合并扩展的嵌套判别字段同样属于这项显式策略：未知 content-block type、message-source kind、assistant finish-reason kind 与 turn-ending reason kind 会作为 owner 不透明 JSON 保留，已知分支则接受结构校验。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。

.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml → .agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md
-2026-07-26-packed-chunk-rows-by-default.md: bd4b3b9f773afbf6aa7e88d51b6e842d6634c222
-2026-07-26-packed-chunk-rows-by-default.zh.md: eafe6632150aadd74395f4d0f09d064fb703a03d
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.md
+2026-08-31-live-assistant-stream-frames.md: 25d86d152714baeca1df18c353f40bc0052bdeee
+2026-08-31-live-assistant-stream-frames.zh.md: 924649932b29520ad3effa88f18267a3ae20ac02

.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.md

@@ -0,0 +1,24 @@
+# Agent Note: Live assistant stream frames remain separate from the session log
+
+Status: implemented
+
+English | [中文](2026-08-31-live-assistant-stream-frames.zh.md)
+
+## Problem
+
+The v2 session log keeps one `assistant/message` or `assistant/attempt` settlement with the complete compact timed stream, so replay, cold reads, telemetry, and request reconstruction observe one durable history. A live consumer also needs prompt frame-by-frame presentation while a request runs. Treating a transient presentation update as another durable event would restore token-level event cardinality and make a process-lifetime concern survive restart.
+
+## Decision
+
+`dsh-agent-loop` emits scoped `agent/assistant-stream` frames for each model attempt. `start`, `chunk`, and `end` carry a branded `LlmAttemptId` unique within one Agent lifecycle; every frame advances one revision local to that lifecycle. The start frame names the attempt's turn and step, chunk indexes are dense from zero, chunk timestamps are reused by the compact stream, and `end.index` equals the next chunk position. Stream acquisition and its final cancellation check occur before `start`; a failure there emits no frame. Every started attempt emits one terminal end: the loop appends the final `assistant/message` or `assistant/attempt` before a committed end names that event and seq, while assembly or settlement failure emits an abandoned end without a durable target. Authenticated Session-follow accepts an explicit Web opt-in, opens with a cached active-attempt compact baseline, and carries durable events and cursorless frames in one FIFO. Each follower captures a local arrival ordinal with the opening baseline and drops buffered frames at or before that cut; frame revisions can restart at one with a replacement Agent, so they do not define the opening cut. A settlement arriving after an active opening is owned by that attempt only when its seq follows `startedAfterSeq` and its Turn and Step match; it remains staged until the matching end index, type, and seq arrive, while an earlier retry at the same Turn and Step remains visible. Revision, dense-index, or settlement gaps for a known attempt reopen follow and replace the baseline; unknown-attempt frames fall back to the durable settlement. The TypeScript and Python SDK protocols do not expose these frames. Durable settlements remain the source of replay and model history; the [v2 stream decision](2026-09-01-v2-embedded-assistant-streams.md) owns their representation.
+
+## Alternatives considered
+
+- **Keep only the live stream** — rejected because cold reads, replay, telemetry, usage accounting, and failed-attempt diagnostics require the durable embedded stream.
+- **Persist each live frame as its own event** — rejected because process-local attempt ids, revisions, and reconnect presentation do not survive restart or affect model reconstruction; one settlement owns the durable stream.
+- **Use an unbranded request string as the attempt key** — rejected because consumers need an opaque identity that cannot be confused with provider request IDs or durable Session IDs.
+- **Let UI Chat subscribe to a second live source** — rejected because the Session object owns stream reconciliation and UI Conversation is the sole event-source subscriber; a second source would make settlement order target-dependent.
+
+## Consequences
+
+The Web client renders in-memory chunks before the attempt settles while retaining one durable v2 history. A process restart has no active Assistant frames; reconnect can restore only the baseline held by the current process, while cold replay expands durable settlements. Cursorless notifications never advance the journal cursor, and notifications observed during durable gap repair wait for the replacement page. That page has no Assistant baseline, so the Client clears transient attempts and lets the held notification reopen follow once for a paired page and baseline. The frame declaration remains agent-scoped, so a listener observes only its owning Agent unless it explicitly registers globally.

.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.zh.md

@@ -0,0 +1,24 @@
+# Agent Note: 实时 assistant 流帧与 Session log 保持分离
+
+Status: implemented
+
+[English](2026-08-31-live-assistant-stream-frames.md) | 中文
+
+## 问题
+
+v2 Session log 通过一个 `assistant/message` 或 `assistant/attempt` settlement 保留完整紧凑带时间 stream，因此 replay、冷读、遥测与请求重建都能观察同一份持久历史。实时消费方还需要在请求运行时逐帧呈现。把瞬态呈现 update 当作另一种持久事件，会恢复 token 粒度事件基数，并让只属于进程生命周期的事实跨重启保留。
+
+## 决定
+
+`dsh-agent-loop` 为每次模型 attempt 发出作用域内的 `agent/assistant-stream` frame。`start`、`chunk` 和 `end` 带有在单个 Agent lifecycle 内唯一的 branded `LlmAttemptId`；每个 frame 都会推进一次该 lifecycle 本地 revision。start frame 给出该 attempt 的 turn 与 step，chunk index 从零开始密集递增，chunk 时间戳会被紧凑 stream 复用，`end.index` 等于下一个 chunk 位置。loop 会先取得 stream 并执行最终取消检查，再发出 `start`；这些步骤失败时不发出任何 frame。每个已开始 attempt 都会发出一个终态 end：loop 会在 committed end 命名事件与 seq 前追加最终 `assistant/message` 或 `assistant/attempt`，而 assembly 或 settlement failure 会发出不命名持久目标的 abandoned end。已认证 Session-follow 接受显式 Web opt-in，以缓存的活跃 attempt 紧凑 baseline 打开，并在一个 FIFO 中携带持久事件和无 cursor frame。每个 follower 会随 opening baseline 捕获本地到达序号，并丢弃该 cut 及之前的 buffered frame；replacement Agent 的 frame revision 可以从一重新开始，因此 revision 不定义 opening cut。活跃 opening 之后到达的 settlement 只有在其 seq 晚于 `startedAfterSeq` 且 Turn 与 Step 匹配时才属于该 attempt；它会保持暂存，直到匹配的 end index、type 与 seq 到达，而同一 Turn 和 Step 中更早的 retry 仍保持可见。已知 attempt 的 revision、密集 index 或 settlement 缺口会重新打开 follow 并替换 baseline；unknown-attempt frame 回退到持久 settlement。TypeScript 和 Python SDK 协议不公开这些 frame。持久 settlement 仍是 replay 与模型历史的真源；其表示由 [v2 stream 决策](2026-09-01-v2-embedded-assistant-streams.zh.md)负责。
+
+## 曾考虑的替代方案
+
+- **只保留 live stream**：不采用，因为冷读、replay、遥测、usage 记账与失败 attempt 诊断需要持久嵌入式 stream。
+- **把每个 live frame 作为独立事件持久化**：不采用，因为进程本地 attempt id、revision 与重连呈现不会跨重启保留或影响模型重建；一个 settlement 拥有持久 stream。
+- **用未加品牌的请求字符串作为尝试键**：不采用，因为消费方需要一个不透明身份，不能把它与 provider request ID 或持久 Session ID 混淆。
+- **让 UI Chat 订阅第二个实时 source**：不采用，因为 Session 对象拥有 stream 对账，UI Conversation 是唯一的 event-source 订阅方；第二个 source 会使结算顺序依赖 target。
+
+## 影响
+
+Web client 可以在 attempt settlement 前渲染内存 chunk，同时保留一份持久 v2 历史。进程重启后没有活跃 Assistant frame；重连只能恢复当前进程持有的 baseline，冷 replay 则展开持久 settlement。无 cursor 通知绝不推进 journal cursor，在持久缺口修复期间观察到的通知会等待 replacement page。该 page 不携带 Assistant baseline，因此 Client 会清空瞬态 attempt，并让 held notification 重新打开 follow 一次，以取得配对的 page 与 baseline。frame 声明保持 agent 作用域，因此监听器只观察所属 Agent，除非它显式全局注册。

.agents/notes/implemented/architecture/2026-08-31-released-session-format-migrations.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-31-released-session-format-migrations.md
+2026-08-31-released-session-format-migrations.md: 2c75d0b57a0b513c218b6a67b8c2b31c7cae4d0f
+2026-08-31-released-session-format-migrations.zh.md: d88c643cbfaf7f3d4f52ca6e5fa244a26917eb99

.agents/notes/implemented/architecture/2026-08-31-released-session-format-migrations.md

@@ -0,0 +1,57 @@
+# 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. Stored event bodies reach consumers through read or write `SessionHandle` instances used by resume, query, export, fork, and continuation paths. Migrating only one consumer 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.
+
+The JSONL provider completes ensure-current work before `open` returns a handle for a stored Session. It selects the highest canonical generation, migrates a supported historical body, and decodes the current result from one physical snapshot; the public `SessionPersistence` and `SessionHandle` interfaces contain no migration operations. Header-only `stat` and `list` rescan Session directories, translate supported historical headers in memory, and never publish a successor. `create` checks canonical filenames independently of header readability, so every existing generation reserves its Session id.
+
+Cancellation belongs to the `open`, `stat`, or `list` call that supplied it. Discovery, stable reads, decoding, and pre-publication checks observe that signal; once an immutable successor is published and its directory entry is synced, later cancellation does not delete the committed generation.
+
+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, 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 current validation before returning a handle. The source never moves or changes; only disposable temporary stages may be moved, linked, or removed. Migration does not synthesize interrupted-turn events: agent-loop appends those repairs through the write handle, while read-only query paths balance them in memory.
+
+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`. `dsh-session-format` owns the raw basename rule (`sessionFormatLogFilename`, `parseSessionFormatLogFilename`); the JSONL provider, the session-log export archive, and recorded-session fixtures append only the compression suffix. 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. The decoded log enters the existing bounded revision-keyed memo for an immediate observe-to-resume handoff, while `stat` and `list` deliberately rescan. Multiple edges leave the original generation unchanged and publish only the final target; intermediate versions exist only in memory. A source fingerprint recheck restarts migration when content changes, and exclusive target publication accepts a racing winner only when its bytes match exactly. Cross-process append 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.
+
+Projection-cache records bind their fold to the Session header's `formatVersion`. The `session_projcache` v7 reader may load predecessor domain records structurally, but a record without the format generation cannot seed a current Session; the authoritative log refolds it and the next checkpoint writes the complete current identity. This prevents a cache row produced before a bounded normalizer or cardinality-changing edge from bypassing that migration.
+
+## 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 runs the committed Session-format corpus gate over every versioned persisted-or-projected `session*.jsonl` fixture 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; every fixture reaches 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. Record and refresh preserve every completed generation, including generations of a child role absent from a later run. Malformed historical fixtures are repaired at their source rather than admitted through path-dependent replay policy. The continuing gate discovers the corpus dynamically and fails every restoration refusal; separate assembled JSONL tests own exact physical-byte migration.
+
+Handle-integration verification runs the pure format, catalog, persistence-seam, and JSONL provider suites together: 420 tests cover both encodings, immutable publication races, header-only observation, read and write handles, migration refusal, append after migration, cancellation, and crash-tail behavior with per-file 100% statement, branch, function, and line coverage. Repository typecheck and lint, 113 keyless recorded-session replays with two declared skips, and 28 owner-local expected-output cases also pass on the merged master checkpoint.
+
+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, revision-keyed parsed-log reuse, 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.

.agents/notes/implemented/architecture/2026-08-31-released-session-format-migrations.zh.md

@@ -0,0 +1,57 @@
+# 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。已存储事件正文通过读或写 `SessionHandle` 到达恢复、查询、导出、分叉与继续路径。只迁移一个消费方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。
+
+JSONL provider 在 `open` 为已存储 Session 返回句柄前完成 ensure-current 工作。它选择最高规范 generation、迁移受支持的历史正文，并从同一物理快照解码当前结果；公开 `SessionPersistence` 与 `SessionHandle` 接口不包含迁移操作。仅 header 的 `stat` 与 `list` 会重新扫描 Session 目录，在内存中转换受支持的历史 header，且绝不发布后继。`create` 独立于 header 可读性检查规范文件名，因此每个现有 generation 都会占用其 Session id。
+
+取消属于提供信号的 `open`、`stat` 或 `list` 调用。发现、稳定读取、解码与发布前检查都会观察该信号；不可变后继一旦发布且其目录项已经同步，后续取消不会删除已提交 generation。
+
+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，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，并在返回句柄前通过当前格式校验重新打开。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。迁移不会合成中断轮次事件：agent-loop 通过写句柄追加这些修复，而只读查询路径在内存中补齐它们。
+
+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`。`dsh-session-format` 拥有原始 basename 规则（`sessionFormatLogFilename`、`parseSessionFormatLogFilename`）；JSONL provider、session-log 导出归档与 recorded-session fixture 只追加压缩后缀。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。解码日志进入现有按 revision 为键的有界 memo，供紧接的观察到恢复交接复用，而 `stat` 与 `list` 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。源 fingerprint 重新检查会在内容变化时重启迁移，排他目标发布只在竞争胜者字节完全相同时接受它。跨进程 append 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。
+
+投影缓存记录把自己的折叠结果绑定到 Session header 的 `formatVersion`。`session_projcache` v7 reader 可以在结构上载入前代 domain 记录，但缺少格式代的记录不能播种当前 Session；权威日志会重新折叠它，下一次检查点写入完整的当前 identity。这样，任何在有界规范化或基数变化边之前产生的缓存行都不能绕过该迁移。
+
+## 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/` 下每个带版本、来自持久化或投影的 `session*.jsonl` fixture 运行已提交 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；每个 fixture 都会通过当前格式 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`。Record 与 refresh 会保留每个已完成 generation，包括后续运行不再产生的 child role generation。Malformed 历史 fixture 在来源处修复，不通过依赖路径的 replay 策略准入。持续运行的门禁会动态发现语料，并拒绝每个 restore failure；独立组装式 JSONL 测试负责精确物理字节迁移。
+
+句柄集成验证会一起运行纯格式、catalog、持久化 seam 与 JSONL provider 测试套件：420 个测试覆盖两种编码、不可变发布竞态、仅 header 观察、读写句柄、迁移拒绝、迁移后 append、取消与崩溃尾部行为，并达到逐文件 100% statement、branch、function 与 line coverage。仓库 typecheck 与 lint、含两个已声明 skip 的 113 个无密钥 recorded-session replay，以及 28 个 owner-local expected-output case 也都在合并 master 的 checkpoint 上通过。
+
+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、按 revision 复用已解析日志、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。

.agents/notes/implemented/architecture/2026-09-01-streamed-tool-call-identity.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-09-01-streamed-tool-call-identity.md
+2026-09-01-streamed-tool-call-identity.md: c52f39b735199270d65ed30a388333a217003237
+2026-09-01-streamed-tool-call-identity.zh.md: 9a7ffb6343870a08e06507408e007ad94fbad178

.agents/notes/implemented/architecture/2026-09-01-streamed-tool-call-identity.md

@@ -0,0 +1,33 @@
+# Agent Note: Streamed tool-call identity survives empty continuation deltas
+
+Status: implemented
+
+English | [中文](2026-09-01-streamed-tool-call-identity.zh.md)
+
+## Problem
+
+The DeepSeek SSE translator assigned `id` and `name` on every tool-call delta that carried the field, so a continuation delta repeating either as an empty string erased the identity established by the call's first delta. The assembled block reached the loop with an empty name, which the tool registry refuses as `unknown tool ""`, leaving the affected models unable to run any tool. Gateways that fill those fields with `null` erased the identity the same way, and `WireToolCallDelta` declared both as `string | undefined`, keeping the observed `null` out of the compiler's reach.
+
+The empty identity outlived the turn. `appendToolCall` and `appendToolResult` write the block's id verbatim and no write path validates it, while `adoptSessionEvent` refuses a `tool/result` whose `callId` is empty, so the persistence coordinator wrapped that refusal in `SessionPersistenceCorruptionError`. A session that recorded one such call was writable and no longer loadable.
+
+## Decision
+
+`acceptIdentity` accepts only a non-empty string for a tool call's `id` and `name`; `undefined`, `null`, `''`, and any non-string leave the established value in place. The assignment set only narrows, so no input reaches a worse outcome than before. `WireToolCallDelta` widens `id`, `function.name`, and `function.arguments` to admit `null`, putting the values gateways actually send into the type system and making the runtime guard load-bearing rather than speculative.
+
+## Alternatives considered
+
+**Concatenate `id` and `name` across deltas.** Rejected: they are identity, not accumulation. Concatenation produces `Globnull` against a gateway that sends `null`, and a doubled name against one that repeats a non-empty value.
+
+**Refuse a conflicting non-empty identity mid-stream.** Deferred: a gateway that fragments a long tool name would be refused for it, and no observed provider re-sends a different non-empty identity within one call index.
+
+**Refuse a response whose tool call never receives an identity.** Deferred. It requires a new failure code, a change to the default retryable set, and a `[DONE]` gate that must not override the finish reason a provider already sent — cost and risk that the reported defect does not carry. The lenient wire it guards against is hypothetical: no report describes a stream that omits identity entirely.
+
+**Relax the session reader's empty-`callId` refusal.** Rejected: an empty `callId` cannot be paired back to the provider on the next request, so accepting it moves the failure into the model request. That refusal is the durable-boundary gate; the producer was the defect.
+
+## Consequences
+
+A continuation delta repeating identity empty or null is inert, so a call keeps the identity its first delta established, and the reported path to `unknown tool ""` and an unreadable session is closed. A stream that never carries identity at all still assembles an empty one, exactly as before; that path and the recovery of sessions already holding an empty `callId` are outside this change.
+
+## Testing
+
+`translate.spec.ts` covers empty and null continuation deltas, a repeated identical identity, and parallel calls holding separate identities under empty continuations. The existing cases for a wire that omits identity entirely keep their recorded empty-identity output.

.agents/notes/implemented/architecture/2026-09-01-streamed-tool-call-identity.zh.md

@@ -0,0 +1,33 @@
+# Agent Note：流式工具调用身份不被空续传分片抹除
+
+Status: implemented
+
+[English](2026-09-01-streamed-tool-call-identity.md) | 中文
+
+## 问题
+
+DeepSeek SSE 翻译器对每个携带该字段的工具调用分片都直接赋值 `id` 与 `name`，因此续传分片把其中任一字段重复发送为空串时，会抹掉该调用首个分片已建立的身份。组装出的块带着空名字进入循环，工具注册表以 `unknown tool ""` 拒绝它，受影响的模型上任何工具都跑不起来。把这些字段填成 `null` 的网关会造成同样的抹除，而 `WireToolCallDelta` 把两者都声明为 `string | undefined`，让实际观察到的 `null` 落在编译器视野之外。
+
+空身份还会活过本轮。`appendToolCall` 与 `appendToolResult` 原样写入块的 id 且没有任何写入路径校验它，而 `adoptSessionEvent` 拒绝 `callId` 为空的 `tool/result`，持久化协调器于是把该拒绝包装成 `SessionPersistenceCorruptionError`。记录过一次这种调用的会话可写但不再可读。
+
+## 决定
+
+`acceptIdentity` 对工具调用的 `id` 与 `name` 只接受非空字符串；`undefined`、`null`、`''` 以及任何非字符串都保留已建立的值。会触发赋值的输入集合只减不增，因此没有任何输入会比改动前更差。`WireToolCallDelta` 把 `id`、`function.name` 与 `function.arguments` 放宽到允许 `null`，使网关实际发送的值进入类型系统，运行时守卫因此是承重的而非臆测的。
+
+## 考虑过的替代方案
+
+**跨分片拼接 `id` 与 `name`。** 否决：它们是身份而非累积。面对发送 `null` 的网关，拼接产生 `Globnull`；面对重复发送非空值的网关，产生重复的名字。
+
+**流中途拒绝冲突的非空身份。** 推迟：分片发送长工具名的网关会因此被拒，且没有观察到任何提供方在同一个调用 index 内改发不同的非空身份。
+
+**拒绝始终未获得身份的响应。** 推迟。它需要新增失败 code、改动默认可重试集，还需要一个不得覆盖提供方已给出终止原因的 `[DONE]` 闸门——这些代价与风险，已报告的缺陷并不需要承担。它所防的宽松线上格式是假想的：没有任何报告描述过完全不发送身份的流。
+
+**放宽会话读取端对空 `callId` 的拒绝。** 否决：空 `callId` 无法在下一次请求中与提供方配对，接受它只是把失败推进模型请求。该拒绝是持久化边界的闸门；缺陷在生产方。
+
+## 后果
+
+重复发送空或 null 身份的续传分片不产生作用，调用因此保有其首个分片建立的身份，通往 `unknown tool ""` 与不可读会话的已报告路径就此切断。完全不携带身份的流仍会组装出空身份，与改动前一致；该路径以及已经写入空 `callId` 的会话恢复都不在本次改动范围内。
+
+## 测试
+
+`translate.spec.ts` 覆盖空与 null 续传分片、重复的相同身份，以及空续传下并行调用各自保有身份。原有那些描述完全不发送身份的线上格式的用例，保留其记录的空身份输出。