From fbd09a70f3fb20fe1b2acc771ed4335fe921abda Mon Sep 17 00:00:00 2001 From: _Kerman Date: Mon, 10 Aug 2026 19:50:43 +0800 Subject: [PATCH] docs: document SessionRawArtifact and fix backpressure claims The persistence subsystem page gains the SessionRawArtifact section (with a type-equiv manifest entry and zh counterpart), and the README and Agent Note describe the drain-based backpressure instead of claiming the archive never accumulates. --- ...2026-08-10-web-session-log-export.i18n.yaml | 4 ++-- .../2026-08-10-web-session-log-export.md | 4 ++-- .../2026-08-10-web-session-log-export.zh.md | 4 ++-- docs/subsystems/persistence.i18n.yaml | 4 ++-- docs/subsystems/persistence.md | 18 +++++++++++++++++- docs/subsystems/persistence.zh.md | 18 +++++++++++++++++- packages/host/apiproxy/README.i18n.yaml | 4 ++-- packages/host/apiproxy/README.md | 2 +- packages/host/apiproxy/README.zh.md | 2 +- .../tool-cordis/src/api-catalog.ts | 2 +- scripts/type-equiv.manifest.json | 5 +++++ 11 files changed, 52 insertions(+), 15 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.i18n.yaml b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.i18n.yaml index 60c70d5519..0c8a3f2781 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-web-session-log-export.md -2026-08-10-web-session-log-export.md: 9d31e4deb640474230dd9b16ec02f2f36dc5ca56 -2026-08-10-web-session-log-export.zh.md: 0a2ba678b0ea56202493507165d94750761ce3d9 +2026-08-10-web-session-log-export.md: 427b6478ac44fb28030aa932630f276de7bb2edc +2026-08-10-web-session-log-export.zh.md: 63b9804a54cda7eea4ff793d78a925fe296d06cb diff --git a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.md b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.md index 9d31e4deb6..427b6478ac 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.md +++ b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.md @@ -1,4 +1,4 @@ -# Agent Note: Web session-log export via session.log + ZIP download +# Agent Note: Web session-log export as a host-streamed ZIP download Status: implemented @@ -10,7 +10,7 @@ The Trajectory view had no way to hand a debugging artifact to a human: the raw ## Decision -- **The export is a host-only download, not an RPC**: `GET /api/session.export?sessionId=…&includeDescendants=true` streams one ZIP attachment. Every file is a session's **stored artifact text verbatim**: `readRaw` on the persistence service reads the backend's own durable bytes (the JSONL backend decodes its physical zstd frames, or returns plaintext) — never a reconstruction from parsed events, so packed-chunk rows, key order, and line breaks survive byte-for-byte — under its original base name (`session.jsonl` at the root, `subagents//session.jsonl` for descendants). Compression runs on the host with fflate's streaming `Zip`/`ZipDeflate` API, each entry deflated in bounded chunks as it is produced, so the response is chunked as it is generated and the host never materializes the whole archive (at most one descendant's artifact text beyond the preloaded root). No manifest is written — every file is byte-identical to the durable artifact and self-describing through its own header line. +- **The export is a host-only download, not an RPC**: `GET /api/session.export?sessionId=…&includeDescendants=true` streams one ZIP attachment. Every file is a session's **stored artifact text verbatim**: `readRaw` on the persistence service reads the backend's own durable bytes (the JSONL backend decodes its physical zstd frames, or returns plaintext) — never a reconstruction from parsed events, so packed-chunk rows, key order, and line breaks survive byte-for-byte — under its original base name (`session.jsonl` at the root, `subagents//session.jsonl` for descendants). Compression runs on the host with fflate's streaming `Zip`/`ZipDeflate` API, each entry deflated in bounded chunks as it is produced, so the response is chunked as it is generated and the host never holds the whole archive in one buffer (at most one descendant's artifact text beyond the preloaded root), and production yields whenever the response queue fills, so a slow consumer bounds the accumulation (fflate's callback is synchronous — the drain point is the only backpressure). No manifest is written — every file is byte-identical to the durable artifact and self-describing through its own header line. - **Error vocabulary is HTTP-native**: missing services → 500, missing root session → 404 (both decided before any byte streams), a descendant without a stored artifact → the stream errors (fail-loud, never silent under-export). The carrier (`toFetchHandler`) already applies the `/api` trust fence; the GET branch sits beside the existing SSE GET routes, and `ApiProxy.downloads.sessionLog` (host-only, no wire envelope, absent from `IApiClient`) implements it. - **The UI just downloads**: the 导出 button fetches the endpoint and saves the response; the `session.log` RPC that an earlier iteration shipped was removed — the download endpoint is its only consumer, and the repo rule is no public interface without a current owner. The client bundle no longer carries fflate (the earlier browser-entry-alias pitfall is moot). - The 导出 button lives in the Trajectory toolbar; the plugin exposes `exportLog` through the view's inject face (components never touch ctx) and resolves the view tab label through the locale service (`轨迹` in Chinese, `Trajectory` in English). In-flight state disables the button; a failure surfaces in a visible alert bar under the toolbar. diff --git a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.zh.md b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.zh.md index 0a2ba678b0..63b9804a54 100644 --- a/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.zh.md +++ b/.agents/notes/implemented/feature/2026-08-10-web-session-log-export.zh.md @@ -1,4 +1,4 @@ -# Agent Note：Web 会话日志导出——session.log RPC + ZIP 下载 +# Agent Note：Web 会话日志导出——宿主流式 ZIP 下载 状态：implemented @@ -10,7 +10,7 @@ Trajectory 视图没有任何方式把调试工件交到人手里：原始会话 ## 决策 -- **导出是宿主侧的下载面，不是 RPC**：`GET /api/session.export?sessionId=…&includeDescendants=true` 流式返回一个 ZIP 附件。每个文件都是会话**存储工件的逐字原文**：持久化服务新增的 `readRaw` 读取后端自己的持久化字节（jsonl 后端解码其物理 zstd 帧，或直接返回明文）——绝非从解析后事件重建，因此 chunk 打包、键序、换行全部逐字节保留——放在其原始基础文件名下（根为 `session.jsonl`，子代理为 `subagents//session.jsonl`）。压缩在宿主侧用 fflate 的流式 `Zip`/`ZipDeflate` API 完成，每个条目按有界分块边产出边压缩，响应随生成分块写出，宿主从不把整个归档放进内存（除预载的根外，最多同时持有一条后代的工件文本）。不写清单——每个文件都与持久化工件逐字节一致，并通过自身 header 行自描述。 +- **导出是宿主侧的下载面，不是 RPC**：`GET /api/session.export?sessionId=…&includeDescendants=true` 流式返回一个 ZIP 附件。每个文件都是会话**存储工件的逐字原文**：持久化服务新增的 `readRaw` 读取后端自己的持久化字节（jsonl 后端解码其物理 zstd 帧，或直接返回明文）——绝非从解析后事件重建，因此 chunk 打包、键序、换行全部逐字节保留——放在其原始基础文件名下（根为 `session.jsonl`，子代理为 `subagents//session.jsonl`）。压缩在宿主侧用 fflate 的流式 `Zip`/`ZipDeflate` API 完成，每个条目按有界分块边产出边压缩，响应随生成分块写出，宿主从不把整个归档放进单个缓冲区（除预载的根外，最多同时持有一条后代的工件文本），且每当响应队列填满时生产会让出，慢消费者因此只产生有界的积压（fflate 的回调是同步的——让出点是唯一的背压手段）。不写清单——每个文件都与持久化工件逐字节一致，并通过自身 header 行自描述。 - **错误词汇是 HTTP 原生的**：服务缺失 → 500，根会话缺失 → 404（两者都在任何字节流出前判定），后代缺少存储工件 → 流失败（fail-loud，绝不静默少导出）。载体（`toFetchHandler`）已对 `/api` 应用信任围栏；GET 分支与既有 SSE GET 路由并列，由 `ApiProxy.downloads.sessionLog`（host-only、无 wire 信封、不在 `IApiClient` 上）实现。 - **UI 只负责下载**：「导出」按钮 fetch 该端点并保存响应；早先迭代发布的 `session.log` RPC 已删除——下载端点是它唯一的消费者，仓库规则是不留无当前所有者的公共接口。客户端 bundle 不再携带 fflate（早先的浏览器入口别名坑随之消失）。 - 「导出」按钮位于 Trajectory 工具栏；插件通过视图的 inject face 暴露 `exportLog`（组件从不接触 ctx），并通过 locale 服务解析视图标签页标题（中文「轨迹」、英文 "Trajectory"）。进行中状态会禁用按钮；失败会在工具栏下方的可见警示条中显示。 diff --git a/docs/subsystems/persistence.i18n.yaml b/docs/subsystems/persistence.i18n.yaml index fa128a80d0..602ec01ec9 100644 --- a/docs/subsystems/persistence.i18n.yaml +++ b/docs/subsystems/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 docs/subsystems/persistence.md -persistence.md: 25541139de02d2bd3ea743fe530e47a628002695 -persistence.zh.md: d76ff93f5564e7612fd7107cd74e3138c03542d8 +persistence.md: 363d28034b58d007d1440afcb8fb9137b0048091 +persistence.zh.md: e208720eae1902ad429fa358c112fe9188f8d8dd diff --git a/docs/subsystems/persistence.md b/docs/subsystems/persistence.md index 25541139de..363d28034b 100644 --- a/docs/subsystems/persistence.md +++ b/docs/subsystems/persistence.md @@ -118,6 +118,22 @@ interface CreateSessionOptions { Replay/fork is therefore `ctx.sessions.create(id, { seed: seedEvents })`; resuming a *persisted* session into a live agent is `ctx.agents.resume({ resumeSessionId })`. +## `SessionRawArtifact` — verbatim stored artifact text + +A backend's own artifact text for one session, byte-identical to what it durably wrote (decoded from its physical encoding). `readRaw` returns it without reconstructing from parsed events, so backend-specific serialization (chunk packing, key order, line breaks) survives; backends without a per-session artifact, such as SQLite, inherit the `undefined` default. + +```ts type-equiv +/** A backend's own raw artifact text for one session, verbatim. */ +interface SessionRawArtifact { + /** The session header parsed from the artifact's own first line. */ + readonly meta: SessionHeader + /** The artifact's base filename on disk, without any physical encoding suffix. */ + readonly filename: string + /** The artifact's full text content, decoded from the backend's physical encoding. */ + readonly content: string +} +``` + ## Preparation and restoration ownership `SessionStore.prepare()` accepts ordinary creation options or fresh persistence graphs transferred through `RestoredSessionOptions`. The restoration branch validates and freezes the transferred header and events in place, so callers must retain no mutable aliases. `SessionPreparation` then owns the exact unpublished Session until publication or rollback; disposal is synchronous and idempotent. Persistence inspection exposes only `SessionInspection`, an immutable logical view borrowed from the same prepared Session. @@ -250,7 +266,7 @@ abstract locate(meta: SessionHeader): SessionLocation | undefined * @returns the raw artifact plus its parsed header, or `undefined` when the * session is absent or the backend owns no per-session artifact. */ -readRaw(_id: SessionId, signal?: AbortSignal): Promise +async readRaw(_id: SessionId, signal?: AbortSignal): Promise /** * Register a new session's metadata. A backend MAY defer the physical write diff --git a/docs/subsystems/persistence.zh.md b/docs/subsystems/persistence.zh.md index d76ff93f55..e208720eae 100644 --- a/docs/subsystems/persistence.zh.md +++ b/docs/subsystems/persistence.zh.md @@ -118,6 +118,22 @@ interface CreateSessionOptions { 因此，回放/fork 的调用方式为 `ctx.sessions.create(id, { seed: seedEvents })`；将一个*持久化*会话恢复为活跃 agent 的调用方式为 `ctx.agents.resume({ resumeSessionId })`。 +## `SessionRawArtifact`——逐字存储工件文本 + +后端为单个会话自持的工件文本，与其持久化写入的字节逐字一致（按物理编码解码）。`readRaw` 返回它而不从解析后事件重建，因此后端特定的序列化（chunk 打包、键序、换行）得以保留；没有每会话工件的后端（如 SQLite）继承 `undefined` 默认。 + +```ts type-equiv +/** A backend's own raw artifact text for one session, verbatim. */ +interface SessionRawArtifact { + /** The session header parsed from the artifact's own first line. */ + readonly meta: SessionHeader + /** The artifact's base filename on disk, without any physical encoding suffix. */ + readonly filename: string + /** The artifact's full text content, decoded from the backend's physical encoding. */ + readonly content: string +} +``` + ## 准备与恢复所有权 `SessionStore.prepare()` 接收普通创建选项，或通过 `RestoredSessionOptions` 转移所有权的新鲜持久化对象图。恢复分支会直接验证并冻结转移来的 header 与事件，因此调用方不得保留可变别名。`SessionPreparation` 随后持有该精确的未发布 Session，直至发布或回滚；dispose 是同步且幂等的。持久化检查只暴露 `SessionInspection`，即从同一个已准备 Session 借用的不可变逻辑视图。 @@ -250,7 +266,7 @@ abstract locate(meta: SessionHeader): SessionLocation | undefined * @returns the raw artifact plus its parsed header, or `undefined` when the * session is absent or the backend owns no per-session artifact. */ -readRaw(_id: SessionId, signal?: AbortSignal): Promise +async readRaw(_id: SessionId, signal?: AbortSignal): Promise /** * Register a new session's metadata. A backend MAY defer the physical write diff --git a/packages/host/apiproxy/README.i18n.yaml b/packages/host/apiproxy/README.i18n.yaml index 6a7abf8bdc..4a6976a6d6 100644 --- a/packages/host/apiproxy/README.i18n.yaml +++ b/packages/host/apiproxy/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/host/apiproxy/README.md -README.md: 452e157ed93ca4ace07a8c958bad04b15d598b31 -README.zh.md: f0509276ef690874e788a3a1e312d35ec37034f0 +README.md: 7d48fd9eaa5ce65a9b5ad22942fe82c2292bd710 +README.zh.md: 245ee6ed62231c9e4381405a8dd3c04428307061 diff --git a/packages/host/apiproxy/README.md b/packages/host/apiproxy/README.md index 452e157ed9..7d48fd9eaa 100644 --- a/packages/host/apiproxy/README.md +++ b/packages/host/apiproxy/README.md @@ -28,7 +28,7 @@ Question responses are validated against their pending request before the first `session.history`'s tail page (`beforeSeq` absent) additionally carries an optional `projections` block — the watermark snapshot of every unit registered on `ctx.sessionProjections` (`@deepseek-ai/dsh-session-projection`), with `asOfSeq` = the last event seq the values reflect (`-1` on an empty log). The gateway also subscribes to the registry's change feed and mints a `session/projection` mux frame per changed unit (`{sessionId, key, value, seq}` — live push state, never logged; clients hold one generic per-session value store under higher-seq-wins). The carrier holds zero domain knowledge (each value passed its unit's own schema inside the registry; the wire schemas keep `values`/`value` wide); loadOlder pages never carry the block, and a composition without the registry serves histories without either surface. -Session-log export is a host-only download surface, not an RPC: `GET /api/session.export?sessionId=…&includeDescendants=true` streams a ZIP whose files are each session's stored artifact text verbatim (the persistence backend's `readRaw` — exact durable bytes decoded from the physical encoding, never a reconstruction from parsed events), root under its original base name plus each subagent descendant under `subagents//`. Compression runs on the host with fflate's streaming Zip API, so the response is chunked as it is produced and the host never materializes the whole archive. It requires both the persistence and session-query services: a deployment without either answers 500, a missing root session 404, and a descendant without a stored artifact fails the stream (fail-loud, never silent under-export). The carrier mounts the endpoint; `ApiProxy.downloads.sessionLog` implements it. +Session-log export is a host-only download surface, not an RPC: `GET /api/session.export?sessionId=…&includeDescendants=true` streams a ZIP whose files are each session's stored artifact text verbatim (the persistence backend's `readRaw` — exact durable bytes decoded from the physical encoding, never a reconstruction from parsed events), root under its original base name plus each subagent descendant under `subagents//`. Compression runs on the host with fflate's streaming Zip API, so the response is chunked as it is produced and the host never holds the whole archive in one buffer, and production yields whenever the response queue fills, so a slow consumer bounds the accumulation (fflate's callback is synchronous — the drain point is the only backpressure). It requires both the persistence and session-query services: a deployment without either answers 500, a missing root session 404, and a descendant without a stored artifact fails the stream (fail-loud, never silent under-export). The carrier mounts the endpoint; `ApiProxy.downloads.sessionLog` implements it. Session titles ride the generic projection pair like every other domain — the history-tail `projections` block plus `session/projection` frames under the `title` key. Titles do not join `session.list`; cold sessions remain metadata-only there until opening or resuming attaches their logs. `session.rename` accepts an explicit user title (resuming a cold session first), delegating to `ctx.sessionTitle.rename` — the accepted `session/title` event pins the title against automatic regeneration — and returns the normalized title plus its event seq so a client settles its `title` projection cell ahead of the push frame; a title that normalizes to empty returns `title-invalid`. diff --git a/packages/host/apiproxy/README.zh.md b/packages/host/apiproxy/README.zh.md index f0509276ef..245ee6ed62 100644 --- a/packages/host/apiproxy/README.zh.md +++ b/packages/host/apiproxy/README.zh.md @@ -28,7 +28,7 @@ Settings 分节中的 `reasoningEffort` 在 agent-default-model 插件配置中 `session.history` 的尾页（不带 `beforeSeq`）额外携带一个可选的 `projections` 块——`ctx.sessionProjections`（`@deepseek-ai/dsh-session-projection`）上每个已注册单元的水位线快照，`asOfSeq` = 这些值共同反映到的最后一个事件 seq（空日志为 `-1`）。网关还订阅注册表的变更流，为每个状态发生变化的单元生成一个 `session/projection` mux 帧（`{sessionId, key, value, seq}`——实时推送状态，绝不入日志；客户端按 seq 高者胜维护一个按会话的通用值仓）。载体不持有任何领域知识（每个值在注册表内部已过其单元自己的 schema；协议 schema 对 `values`/`value` 保持宽松）；loadOlder 页永不携带该块，未装注册表的组合则两个面都不提供。 -会话日志导出是宿主侧的下载面，不是 RPC：`GET /api/session.export?sessionId=…&includeDescendants=true` 流式返回一个 ZIP，其中每个文件都是会话存储工件的逐字原文（持久化后端的 `readRaw`——按物理编码解码的确切持久化字节，绝非从解析后事件重建），根会话放在其原始基础文件名下，每个子代理后代放在 `subagents//` 下。压缩在宿主侧用 fflate 的流式 Zip API 完成，响应边生成边分块写出，宿主从不把整个归档放进内存。它要求同时挂载持久化与 session-query 服务：任一缺失应答 500，根会话缺失应答 404，后代缺少存储工件则整个流失败（fail-loud，绝不静默少导出）。端点由传输层挂载，`ApiProxy.downloads.sessionLog` 实现它。 +会话日志导出是宿主侧的下载面，不是 RPC：`GET /api/session.export?sessionId=…&includeDescendants=true` 流式返回一个 ZIP，其中每个文件都是会话存储工件的逐字原文（持久化后端的 `readRaw`——按物理编码解码的确切持久化字节，绝非从解析后事件重建），根会话放在其原始基础文件名下，每个子代理后代放在 `subagents//` 下。压缩在宿主侧用 fflate 的流式 Zip API 完成，响应边生成边分块写出，宿主从不把整个归档放进单个缓冲区，且每当响应队列填满时生产会让出，慢消费者因此只产生有界的积压（fflate 的回调是同步的——让出点是唯一的背压手段）。它要求同时挂载持久化与 session-query 服务：任一缺失应答 500，根会话缺失应答 404，后代缺少存储工件则整个流失败（fail-loud，绝不静默少导出）。端点由传输层挂载，`ApiProxy.downloads.sessionLog` 实现它。 会话标题与其他所有领域一样搭乘这对通用投影机制——历史尾页的 `projections` 块外加 `title` 键下的 `session/projection` 帧。标题不会加入 `session.list`；冷会话在其中仍只有元数据，直到打开或恢复操作附加其日志。`session.rename` 接受用户显式标题（冷会话先恢复），委托给 `ctx.sessionTitle.rename`——被接受的 `session/title` 事件将标题钉住、不再被自动生成覆盖——并返回规范化后的标题及其事件 seq，让 client 在推送帧到达前就结算自己的 `title` 投影格；规范化后为空的标题返回 `title-invalid`。 diff --git a/packages/self-modification/tool-cordis/src/api-catalog.ts b/packages/self-modification/tool-cordis/src/api-catalog.ts index 5f4d9a124b..6f9abb64da 100644 --- a/packages/self-modification/tool-cordis/src/api-catalog.ts +++ b/packages/self-modification/tool-cordis/src/api-catalog.ts @@ -689,7 +689,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ jsDoc: '/**\n * Resolve this backend\'s independent local artifact for a session without\n * reading, creating, flushing, or otherwise materializing it. Backends such\n * as SQLite that do not own one artifact per session return `undefined`.\n * @param meta - the immutable session header whose artifact is requested.\n * @returns the backend-specific absolute location, when one exists.\n */', }, { - signature: 'readRaw(_id: SessionId, signal?: AbortSignal): Promise', + signature: 'async readRaw(_id: SessionId, signal?: AbortSignal): Promise', jsDoc: '/**\n * Read a session\'s backend-owned artifact text verbatim — the exact durable\n * bytes the backend wrote (decoded from its physical encoding, e.g. a\n * decompressed JSONL). The returned `content` is the raw text, not a\n * reconstruction from parsed events, so it preserves backend-specific\n * serialization (chunk packing, key order, line breaks). Backends without a\n * per-session artifact (SQLite) inherit the `undefined` default.\n * @param _id - the persisted session to read (unused by the default: no\n * per-session artifact).\n * @param signal - optional cancellation for backend read work.\n * @returns the raw artifact plus its parsed header, or `undefined` when the\n * session is absent or the backend owns no per-session artifact.\n */', }, { diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 1a9d998029..ef44631f07 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -440,6 +440,11 @@ "symbol": "SessionLocation", "source": "packages/session/session-persistence/src/index.ts" }, + { + "doc": "docs/subsystems/persistence.md", + "symbol": "SessionRawArtifact", + "source": "packages/session/session-persistence/src/index.ts" + }, { "doc": "docs/subsystems/session-query.md", "symbol": "SessionEventSurface",