From c836fcd416ddf0bc0c384fa24d6abbebdeb12c8d Mon Sep 17 00:00:00 2001 From: Turtle Date: Wed, 5 Aug 2026 12:43:35 +0800 Subject: [PATCH] feat(telemetry): add feedback-gated OTEL modes --- ...3-session-telemetry-otel-revival.i18n.yaml | 4 +- ...26-07-23-session-telemetry-otel-revival.md | 4 +- ...07-23-session-telemetry-otel-revival.zh.md | 4 +- .../2026-07-28-feedback-command.i18n.yaml | 4 +- .../feature/2026-07-28-feedback-command.md | 8 +- .../feature/2026-07-28-feedback-command.zh.md | 8 +- ...feedback-gated-session-telemetry.i18n.yaml | 6 + ...-08-05-feedback-gated-session-telemetry.md | 35 ++++ ...-05-feedback-gated-session-telemetry.zh.md | 35 ++++ docs/config-catalog.md | 16 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 4 +- .../tests/fixtures/telemetry-otel-driver.ts | 10 ++ .../tests/fixtures/telemetry-otel.cordis.yml | 9 + examples/package.json | 2 + packages/feedback/README.i18n.yaml | 4 +- packages/feedback/README.md | 2 +- packages/feedback/README.zh.md | 2 +- .../command-feedback/README.i18n.yaml | 4 +- packages/feedback/command-feedback/README.md | 4 +- .../feedback/command-feedback/README.zh.md | 4 +- packages/telemetry/README.i18n.yaml | 4 +- packages/telemetry/README.md | 6 +- packages/telemetry/README.zh.md | 6 +- .../session-telemetry-otel/README.i18n.yaml | 4 +- .../session-telemetry-otel/README.md | 16 +- .../session-telemetry-otel/README.zh.md | 16 +- .../session-telemetry-otel/package.json | 2 + .../session-telemetry-otel/src/index.ts | 94 +++++++---- .../session-telemetry-otel/src/invariant.ts | 7 +- .../tests/loader-composition.e2e.ts | 93 ++++++++--- .../session-telemetry-otel/tests/otel.spec.ts | 90 +++++++++- .../session-telemetry-otel/tsconfig.json | 3 + .../session-telemetry/README.i18n.yaml | 4 +- .../telemetry/session-telemetry/README.md | 11 +- .../telemetry/session-telemetry/README.zh.md | 11 +- .../session-telemetry/src/coordinator.ts | 158 ++++++++++++------ .../telemetry/session-telemetry/src/index.ts | 17 +- .../session-telemetry/tests/telemetry.spec.ts | 93 ++++++++++- pnpm-lock.yaml | 9 + 41 files changed, 635 insertions(+), 182 deletions(-) create mode 100644 .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml create mode 100644 .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md create mode 100644 .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml index cd9e4f7e9f..3f487762d6 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.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/2026-07-23-session-telemetry-otel-revival.md -2026-07-23-session-telemetry-otel-revival.md: a58598d8a956d47cb0cf6aa3e659f38314bc4b17 -2026-07-23-session-telemetry-otel-revival.zh.md: cc09717e349d5ae2ab5157bf46de30b1823c775f +2026-07-23-session-telemetry-otel-revival.md: dcbff9757cbb730b66f456535fbd7ae471b6ffd1 +2026-07-23-session-telemetry-otel-revival.zh.md: c3a098041795fa92bb4e0dd421ca09be94907cb8 diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md index a58598d8a9..dcbff9757c 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md @@ -14,7 +14,7 @@ Every deployment that wants harness sessions in an observability stack must hand - **`@deepseek-ai/dsh-session-telemetry`** — the seam. `TelemetryBackend` (`emit`/`flush?`/`shutdown`), the service-registered `Telemetry` form, and `TelemetryCoordinator` owning capture: adoption with cursor read-back, the per-append firehose (project → `structuredClone` → redact → `emit`, zero I/O), the fixed first-chunk-per-(turn, step) projection, the `agent/error` relay, and dispose-time `shutdown` records. - **The `telemetry/record` waterfall** — the delta over the branch version and the seam's redaction extension point. Every record passes it before reaching any backend; the seam ships NO rules of its own — the innermost `next()` is a pass-through, deployments mount their rules as listeners (stacking by transforming `next()`'s return value), and a throwing rule withholds the record fail-closed. Redaction applies to the exported copy only; the canonical log is never rewritten. -- **`@deepseek-ai/dsh-session-telemetry-otel`** — the reference backend: OTel JS SDK log pipeline (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter), configured verbatim through `exporter`/`processor` passthroughs. `exporter.url` is required and validated at load; unmounted or unconfigured, nothing leaves the process. +- **`@deepseek-ai/dsh-session-telemetry-otel`** — the reference backend: OTel JS SDK log pipeline (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter), configured verbatim through `exporter`/`processor` passthroughs. Its default `FULL` mode requires `exporter.url`; the later [feedback-gated telemetry decision](2026-08-05-feedback-gated-session-telemetry.md) adds `FEEDBACK_ONLY` and `DISABLED` delivery modes without moving the redaction or backend boundary. The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry, queueing, and loss policy are the reporting SDK's, configured through passthroughs — delivery is best-effort (at-most-once across a crash), which the READMEs state plainly. @@ -34,4 +34,4 @@ The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry ## Consequences -A deployment adds one `cordis.yml` entry with an OTLP endpoint and gets its session stream in any OTel-compatible stack; removing the entry is the opt-out, with no residual state. A rule-free deployment exports records exactly as captured — including any credentials embedded in file contents or command output — so a deployment crossing a trust boundary must mount `telemetry/record` listeners, and both READMEs state this plainly. Where rules are mounted, exported bodies can differ from canonical log bytes, so receivers must not treat telemetry as a byte-exact replica; the log remains the source of truth. Crash durability is explicitly out of scope until the outbox decision above is revisited. +A deployment adds one `cordis.yml` entry with an OTLP endpoint and gets its session stream in any OTel-compatible stack. `FULL` preserves that behavior by default, `FEEDBACK_ONLY` withholds records until feedback releases a prefix, and `DISABLED` constructs no reporting pipeline; removing the entry remains a silent opt-out, while the disabled mode keeps the local feedback warning. A rule-free deployment exports records exactly as captured — including any credentials embedded in file contents or command output — so a deployment crossing a trust boundary must mount `telemetry/record` listeners, and both READMEs state this plainly. Where rules are mounted, exported bodies can differ from canonical log bytes, so receivers must not treat telemetry as a byte-exact replica; the log remains the source of truth. Crash durability is explicitly out of scope until the outbox decision above is revisited. diff --git a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md index cc09717e34..c3a0980417 100644 --- a/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md +++ b/.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.zh.md @@ -14,7 +14,7 @@ Status: implemented - **`@deepseek-ai/dsh-session-telemetry`** —— seam 本体。`TelemetryBackend`（`emit`/`flush?`/`shutdown`）、服务注册形态的 `Telemetry`、以及拥有捕获侧的 `TelemetryCoordinator`：带游标回读的收养、逐 append 的 firehose（投影 → `structuredClone` → 脱敏 → `emit`，零 I/O）、固定的每 (turn, step) 首 chunk 投影、`agent/error` 转发、以及 dispose 时的 `shutdown` 记录。 - **`telemetry/record` waterfall** —— 相对分支版本的增量，也是该 seam 的脱敏扩展点。每条记录抵达任何 backend 前必经此处；seam 自身不带任何规则——最内层 `next()` 原样透传，部署方以监听器挂载自己的规则（通过变换 `next()` 的返回值堆叠），抛异常的规则将该记录 fail-closed 扣下。脱敏只作用于导出副本；canonical log 永不改写。 -- **`@deepseek-ai/dsh-session-telemetry-otel`** —— 参考 backend：OTel JS SDK 日志管线（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter），经 `exporter`/`processor` passthrough 原样配置。`exporter.url` 必填且加载时校验；未挂载或未配置时，任何数据都不会离开进程。 +- **`@deepseek-ai/dsh-session-telemetry-otel`** —— 参考 backend：OTel JS SDK 日志管线（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP exporter），经 `exporter`/`processor` passthrough 原样配置。其默认 `FULL` 模式要求 `exporter.url`；后续的[反馈门控遥测决策](2026-08-05-feedback-gated-session-telemetry.md)增加了 `FEEDBACK_ONLY` 与 `DISABLED` 投递模式，但未移动脱敏或后端边界。 边界公理保持不变：harness 的职责止于 `emit()`。批处理、重试、排队与丢失策略属于 reporting SDK，经 passthrough 配置——投递是尽力而为（崩溃时至多一次），README 对此如实陈述。 @@ -34,4 +34,4 @@ Status: implemented ## Consequences -部署方在 `cordis.yml` 加一个带 OTLP endpoint 的条目即可把会话流接入任何 OTel 兼容体系；删除条目即退出，无残留状态。未挂载规则的部署导出的记录与捕获时完全一致——包括文件内容与命令输出中内嵌的任何凭据——因此跨信任边界的部署必须挂载 `telemetry/record` 监听器，两个 README 对此如实陈述。挂载规则后，导出的 body 可能与 canonical log 字节不同，接收端不得把遥测当作字节精确副本；日志仍是唯一事实源。崩溃持久性在上述 outbox 决定重启前明确不在范围内。 +部署方在 `cordis.yml` 加一个带 OTLP endpoint 的条目即可把会话流接入任何 OTel 兼容体系。`FULL` 默认保留该行为，`FEEDBACK_ONLY` 在反馈释放前暂存记录前缀，`DISABLED` 则不构造上报流水线；删除条目仍是静默退出方式，而禁用模式会保留本地反馈警告。未挂载规则的部署导出的记录与捕获时完全一致，包括文件内容与命令输出中内嵌的任何凭据。因此，跨信任边界的部署必须挂载 `telemetry/record` 监听器，两个 README 对此如实陈述。挂载规则后，导出的 body 可能与 canonical log 字节不同，接收端不得把遥测当作字节精确副本；日志仍是真源。崩溃持久性在上述 outbox 决定重启前明确不在范围内。 diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml index 7a429953d8..be039deb2c 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.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/2026-07-28-feedback-command.md -2026-07-28-feedback-command.md: 1c093d0e37eb72dc66e3c5569bd642557dde56a1 -2026-07-28-feedback-command.zh.md: 300946a71ac7485a4bc787dd70ae5357147627f3 +2026-07-28-feedback-command.md: 963153ceb4332b74693ff5c1d248c616ff4e8de9 +2026-07-28-feedback-command.zh.md: 4dd02dcfb8d0606436c22e269db8c0d6cf163cee diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.md b/.agents/notes/implemented/feature/2026-07-28-feedback-command.md index 1c093d0e37..963153ceb4 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.md +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.md @@ -18,7 +18,7 @@ The package declares the log-only `feedback/record { text }` session event and e `dsh-commands` still writes its `command/run` / `command/done` lifecycle pair around `/feedback`, but this command sets `recordInput: false`. Its `command/run` therefore carries the command identity and source without `args`; the feedback text exists only in `feedback/record`, while `command/done` carries the acknowledgement outcome. All three records are log-only and non-surface. Their appends start persistence's ordinary eager drain; nothing forces a flush, so acknowledgement reports that the feedback is in the log rather than already on disk. -Capture is deliberately inert: nothing in this repository reads `feedback/record`. +Capture remains inert for the running agent and model. The optional OTel telemetry package later adds one infrastructure consumer: it observes `feedback/record` as a release trigger in `FEEDBACK_ONLY` mode and as the local-only warning trigger in `DISABLED` mode, without changing the feedback event or command path. See [Feedback-gated session telemetry](2026-08-05-feedback-gated-session-telemetry.md). ### Why feedback owns an event @@ -34,7 +34,7 @@ Surrounding whitespace is discarded, but nothing else is parsed. `/feedback /pla ### A new group -`packages/feedback/` is a new group because no existing one owns this. `goal/` is objective state, `session-title/` is titles, `core/` is the product spine. The group holds one package; a consumer would join it rather than forcing this one to grow. +`packages/feedback/` is a new group because no existing one owns this. `goal/` is objective state, `session-title/` is titles, `core/` is the product spine. The group holds one producer package; cross-cutting consumers stay in their owning groups rather than forcing this one to grow. ## Alternatives considered @@ -48,7 +48,7 @@ Surrounding whitespace is discarded, but nothing else is parsed. `/feedback /pla **Register the command inside an existing package** such as `packages/ui/commands`. Avoids a new group and its README pair. Rejected: `ctx.commands` is the registry, not a home for arbitrary command implementations, and the requester asked for a standalone package. -**Parse structure out of the text** (category prefixes, severity markers). Rejected as speculative: no consumer exists to use the structure, and any control-word grammar makes the corresponding literal feedback unrecordable. Verbatim text is the widest surface a future consumer can narrow; a parsed one cannot be widened after the fact. +**Parse structure out of the text** (category prefixes, severity markers). Rejected as speculative: no consumer needs that structure, and any control-word grammar makes the corresponding literal feedback unrecordable. Verbatim text is the widest surface a future consumer can narrow; a parsed one cannot be widened after the fact. **Add a model-facing tool instead of a slash command.** Rejected: feedback is a direct human observation. Routing it through the model spends a turn, lets the model paraphrase the user's words, and makes the record contingent on the model choosing to call the tool. @@ -58,6 +58,6 @@ The TUI mounts the command unconditionally — no configuration, no dependency o The package owns one independent append-only event with no cross-event or mutable-data relation for an invariant companion to check. The event follows the session log's existing replay, fork, persistence, and crash-tail behavior. -Deferred: no consumer; no structured fields; no amend or withdraw, since the log is append-only and this package adds no tombstone; and no explicit durability barrier, so an entry recorded immediately before a crash can be lost with any other unflushed tail. +Deferred: no product or model consumer; no structured fields; no amend or withdraw, since the log is append-only and this package adds no tombstone; and no explicit durability barrier, so an entry recorded immediately before a crash can be lost with any other unflushed tail. The optional telemetry consumer treats the event only as an export-policy trigger. No snapshot accompanies this change. AGENTS.md asks for a keyless snapshot through a runnable example for product-user-visible behavior; this was skipped at the requester's explicit direction. The package tests plus a real Loader composition test over a `cordis.yml` are the whole of the evidence, alongside interactive verification in the assembled TUI. diff --git a/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md b/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md index 300946a71a..4dd02dcfb8 100644 --- a/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md +++ b/.agents/notes/implemented/feature/2026-07-28-feedback-command.zh.md @@ -18,7 +18,7 @@ Status: implemented `dsh-commands` 仍会围绕 `/feedback` 写入 `command/run` / `command/done` 生命周期配对，但该命令设置了 `recordInput: false`。因此，它的 `command/run` 携带命令标识与来源，但不携带 `args`；反馈文本只存在于 `feedback/record` 中，而 `command/done` 携带确认结果。三个记录都仅写入日志且非 surface。它们的追加会启动持久化的常规即时排空；没有任何环节强制 flush，因此确认文本报告的是反馈已进入日志，而非已经落盘。 -采集刻意不产生后续动作：本仓库中没有任何代码读取 `feedback/record`。 +采集对正在运行的 agent 与模型仍不产生后续动作。可选的 OTel 遥测包后续增加了一个基础设施消费方：它在 `FEEDBACK_ONLY` 模式下将 `feedback/record` 作为释放触发器，在 `DISABLED` 模式下将其作为本地警告触发器，且不改变反馈事件或命令路径。见[反馈门控的会话遥测](2026-08-05-feedback-gated-session-telemetry.md)。 ### 为何反馈拥有自己的事件 @@ -34,7 +34,7 @@ Status: implemented ### 一个新的分组 -`packages/feedback/` 是新分组，因为现有分组都不拥有此职责：`goal/` 负责目标状态，`session-title/` 负责标题，`core/` 是产品主干。该分组目前只有一个包；未来的消费方应加入该分组，而不是迫使这个包不断膨胀。 +`packages/feedback/` 是新分组，因为现有分组都不拥有此职责：`goal/` 负责目标状态，`session-title/` 负责标题，`core/` 是产品主干。该分组只包含一个生产方包；跨领域的消费方留在各自所属的分组，而不是迫使这个包不断膨胀。 ## 考虑过的替代方案 @@ -48,7 +48,7 @@ Status: implemented **在现有包中注册该命令**，例如 `packages/ui/commands`。可省去新分组及其双语 README。已否决：`ctx.commands` 是注册表，而不是任意命令实现的归属地；且请求者明确要求独立的包。 -**从文本中解析结构**（类别前缀、严重程度标记）。已否决，属于投机设计：目前没有消费方使用该结构，而任何控制词语法都会让对应的字面反馈无法记录。原样文本是未来消费方可以收窄的最宽接口；而已被解析的接口无法事后放宽。 +**从文本中解析结构**（类别前缀、严重程度标记）。已否决，属于投机设计：没有消费方需要该结构，而任何控制词语法都会让对应的字面反馈无法记录。原样文本是未来消费方可以收窄的最宽接口；而已被解析的接口无法事后放宽。 **改为提供面向模型的工具。** 已否决：反馈是人类的直接观察。经由模型会消耗一个轮次、让模型改写用户的原话，并使记录取决于模型是否选择调用该工具。 @@ -58,6 +58,6 @@ TUI 无条件挂载该命令：没有配置，也不依赖 goal 栈。无头 CLI 本包拥有一个独立的仅追加事件，不存在跨事件关系或可变数据关系可供不变式伴生插件检查。该事件遵循会话日志现有的回放、fork、持久化和崩溃尾部行为。 -延期事项：没有消费方；没有结构化字段；不支持修改或撤回，因为日志仅追加且本包不新增 tombstone；且没有显式持久化屏障，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。 +延期事项：没有产品或模型消费方；没有结构化字段；不支持修改或撤回，因为日志仅追加且本包不新增 tombstone；且没有显式持久化屏障，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。可选的遥测消费方只将该事件作为导出策略触发器。 本次变更不附带 snapshot。AGENTS.md 要求面向产品用户的可见行为变更通过可运行示例附带无密钥 snapshot；此项按请求者的明确指示跳过。包测试连同一个基于真实 `cordis.yml` 的 Loader 组合测试即为全部证据，此外还有在组装后 TUI 中的交互验证。 diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml new file mode 100644 index 0000000000..d12ad78728 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md +2026-08-05-feedback-gated-session-telemetry.md: 21a9028c603f3faaec39b2ddb8ef14644d6c84d4 +2026-08-05-feedback-gated-session-telemetry.zh.md: ea94c743b962a93a5fc64bdc2e4ed103aadecc99 diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md new file mode 100644 index 0000000000..21a9028c60 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md @@ -0,0 +1,35 @@ +# Agent Note: Feedback-gated session telemetry + +Status: implemented + +English | [中文](2026-08-05-feedback-gated-session-telemetry.zh.md) + +## Problem + +Session telemetry originally has one mounted behavior: every accepted record enters the reporting backend immediately. Deployments need two stricter policies without replacing the plugin: hold a session's telemetry unless its user records feedback, or disable reporting while still explaining what happens to feedback. The policy must preserve the existing full-export default and the telemetry seam's redaction-before-backend boundary. + +## Decision + +`@deepseek-ai/dsh-session-telemetry-otel` exposes three uppercase `mode` values: + +- `FULL` is the default and preserves immediate delivery to the configured OTel pipeline. +- `FEEDBACK_ONLY` captures redacted copies in memory and releases the pending session prefix when `feedback/record` is appended. The released prefix includes the feedback event itself. Records appended after that event form another withheld prefix until another feedback event releases them. +- `DISABLED` constructs no exporter, processor, or logger provider. A `feedback/record` listener prints that nothing is shared and the feedback remains local. + +The generic telemetry coordinator owns the delivery distinction as `immediate` or `held`. Both paths project, clone, and run `telemetry/record` listeners at capture time. Immediate delivery sends the accepted record to the backend and advances the session's handoff cursor. Held delivery retains the accepted record per session without moving that cursor. `release(session)` submits the retained records in order, contains each backend failure independently, advances the cursor only for submitted records, and removes the released prefix. + +The OTel feedback listener is registered after the coordinator's session listener. Cordis therefore gives the coordinator the feedback append first, then the OTel listener releases a prefix that already contains that event. `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`; `DISABLED` does not validate or use exporter configuration. + +## Alternatives considered + +**Open a session permanently after its first feedback.** Rejected because later work would be shared without another feedback act and the plugin would need additional open-session state. Releasing one pending prefix per feedback has the smaller state machine and the narrower sharing boundary. + +**Buffer after `TelemetryCoordinator.emit()` in the OTel backend.** Rejected because the coordinator would advance its handoff cursor before a record became eligible for upload. A plugin rebuild would then lose the only retained copy and incorrectly treat the prefix as handed off. + +**Replay the canonical session log when feedback arrives.** Rejected because replay would repeat projection and redaction, exclude telemetry operation records that are not session events, and require more lifecycle state to distinguish previously released prefixes. + +**Use an unmounted plugin as the disabled state.** That remains the silent opt-out, but it cannot warn when feedback is recorded. The explicit disabled mode lets a deployment keep one configuration shape and communicate that the local feedback did not leave the process. + +## Consequences + +`FULL` remains source- and wire-compatible with the original default. `FEEDBACK_ONLY` retains deep-copied, already-redacted records in process memory until feedback or session collection; a crash before release uploads nothing from that prefix. A clean shutdown after the last feedback is part of the new withheld suffix, so feedback-only streams do not carry a reliable shutdown or crash signal. Each later feedback releases the suffix accumulated since the previous one. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log. diff --git a/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md new file mode 100644 index 0000000000..ea94c743b9 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.zh.md @@ -0,0 +1,35 @@ +# Agent Note：反馈门控的会话遥测 + +Status: implemented + +[English](2026-08-05-feedback-gated-session-telemetry.md) | 中文 + +## 问题 + +会话遥测原本只有一种已挂载行为：每条已接受记录都立即进入上报后端。部署方需要两种更严格的策略，且不替换插件：只有用户记录反馈时才释放该会话的遥测，或禁用上报并仍向用户说明反馈的去向。该策略必须保留现有的全量导出默认值，以及遥测 seam 在记录抵达后端之前脱敏的边界。 + +## 决策 + +`@deepseek-ai/dsh-session-telemetry-otel` 公开三个大写的 `mode` 值： + +- `FULL` 是默认值，保留向已配置 OTel 流水线的即时投递。 +- `FEEDBACK_ONLY` 在内存中捕获已脱敏副本，并在追加 `feedback/record` 时释放待处理的会话前缀。已释放前缀包含反馈事件本身。在该事件之后追加的记录会形成另一个暂存前缀，直到下一个反馈事件将其释放。 +- `DISABLED` 不构造导出器、处理器或日志提供方。`feedback/record` 监听器会输出警告，说明什么都不会共享，且反馈仍留在本地。 + +通用遥测协调器以 `immediate` 或 `held` 的形式拥有这两种投递方式。两条路径都会在捕获时进行投影、深拷贝，并运行 `telemetry/record` 监听器。即时投递把已接受记录发送到后端，并推进会话的 handoff 游标。暂存投递按会话保留已接受记录，且不移动该游标。`release(session)` 按顺序提交保留的记录，独立隔离每个后端失败，仅为已提交的记录推进游标，并移除已释放前缀。 + +OTel 反馈监听器在协调器的会话监听器之后注册。因此，Cordis 先将反馈追加交给协调器，再由 OTel 监听器释放已包含该事件的前缀。`exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填；`DISABLED` 不校验也不使用导出器配置。 + +## 考虑过的替代方案 + +**会话在首次反馈后永久开放。** 已否决，因为后续工作会在用户未再次提交反馈的情况下被共享，而且插件需要额外的会话开放状态。每次反馈只释放一个待处理前缀，状态机更小，共享边界也更窄。 + +**在 OTel 后端的 `TelemetryCoordinator.emit()` 之后缓冲。** 已否决，因为协调器会在记录具备上传资格前推进 handoff 游标。插件重建后，唯一保留的副本会丢失，而协调器会错误地将该前缀视为已交接。 + +**反馈到达时回放权威会话日志。** 已否决，因为回放会重复执行投影与脱敏，排除不属于会话事件的遥测运维记录，且需要更多生命周期状态才能区分已释放前缀。 + +**以不挂载插件表示禁用状态。** 这仍然是静默退出方式，但无法在记录反馈时输出警告。显式禁用模式让部署方可以保持同一种配置形态，并说明本地反馈未离开进程。 + +## 后果 + +`FULL` 与原有默认值保持源码及协议兼容。`FEEDBACK_ONLY` 会在进程内存中保留已深拷贝且已脱敏的记录，直到收到反馈或会话被回收；释放前发生崩溃时，该前缀不上传任何内容。上次反馈之后的干净关闭属于新的暂存后缀，因此仅反馈的流不携带可靠的关闭或崩溃信号。每个后续反馈都会释放从上一个反馈开始累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index f552e6ab63..0c4fb632c1 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1159,12 +1159,13 @@ Requires: `sessions` ```ts config-catalog /** - * Plugin configuration: two verbatim SDK option shapes plus nothing else. - * `exporter.url` is the one field this package validates itself — required, - * no default, must parse as an `http(s)` URL — because a missing endpoint - * must fail at plugin load, not at first export. + * Plugin configuration: one sharing policy plus two verbatim SDK option + * shapes. `exporter.url` is required for modes that upload and unused for + * `DISABLED`. */ export interface Config { + /** Sharing policy; defaults to immediate `FULL` delivery. */ + mode?: TelemetryMode /** * Passed verbatim to the SDK's OTLP/HTTP log exporter — the complete * `OTLPExporterNodeConfigBase` shape (`headers`, `timeoutMillis`, @@ -1172,7 +1173,7 @@ export interface Config { * is the one field this package requires and validates itself. */ exporter?: OTLPExporterNodeConfigBase & { - /** Full logs endpoint (e.g. `https://collector.example.com/v1/logs`). Required; validated at plugin load. */ + /** Full logs endpoint (e.g. `https://collector.example.com/v1/logs`). Required outside `DISABLED`; validated at load. */ url?: string } /** @@ -1181,11 +1182,14 @@ export interface Config { */ processor?: Omit } + +/** Session-sharing policy selected by {@link Config.mode}. */ +export type TelemetryMode = typeof TELEMETRY_MODES[number] ``` Depends on: `BatchLogRecordProcessorOptions` (`@opentelemetry/sdk-logs`) · `OTLPExporterNodeConfigBase` (`@opentelemetry/otlp-exporter-base`) -Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:40`](../packages/telemetry/session-telemetry-otel/src/index.ts) +Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:54`](../packages/telemetry/session-telemetry-otel/src/index.ts) ## `@deepseek-ai/dsh-session-title` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 54291934fd..d159fa0a53 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -853,7 +853,7 @@ Transform one outbound record before it reaches the backend. This waterfall is t 'telemetry/record'(record: TelemetryRecord, next: () => TelemetryRecord): TelemetryRecord ``` -Source: [`packages/telemetry/session-telemetry/src/index.ts:41`](../../packages/telemetry/session-telemetry/src/index.ts) +Source: [`packages/telemetry/session-telemetry/src/index.ts:42`](../../packages/telemetry/session-telemetry/src/index.ts) ## `tools/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 395d0850e1..e051463877 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -1996,7 +1996,7 @@ flush?(): void abstract shutdown(): Promise ``` -Source: [`packages/telemetry/session-telemetry/src/index.ts:135`](../../packages/telemetry/session-telemetry/src/index.ts) +Source: [`packages/telemetry/session-telemetry/src/index.ts:140`](../../packages/telemetry/session-telemetry/src/index.ts) ## `ctx.tokenMeter` — `TokenMeterService` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index fabd16bbdd..4ccc19f305 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -33,7 +33,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:58`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`llm-replay`](../packages/support/llm-replay), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-title`](../packages/session-title/session-title) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:71`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | `apiproxy`, [`compact`](../packages/compact/compact), [`goal`](../packages/goal/goal), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`llm-retry`](../packages/llm/llm-retry), [`plan-mode`](../packages/plan/plan-mode), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-telemetry`](../packages/telemetry/session-telemetry), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:81`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), `apiproxy`, [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection-cache`](../packages/session-projection/session-projection-cache), [`session-telemetry`](../packages/telemetry/session-telemetry), [`session-title`](../packages/session-title/session-title) | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:93`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/acp/acp), `apiproxy`, [`cli-demo`](../packages/examples/cli-demo), [`compact`](../packages/compact/compact), [`compact-basic`](../packages/compact/compact-basic), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection`](../packages/session-projection/session-projection), [`session-projection-cache`](../packages/session-projection/session-projection-cache), [`session-telemetry`](../packages/telemetry/session-telemetry), [`session-title`](../packages/session-title/session-title), [`token-meter`](../packages/llm/token-meter), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-approval`](../packages/ui/user-approval), [`workspace-context`](../packages/context/workspace-context) | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:93`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/acp/acp), `apiproxy`, [`cli-demo`](../packages/examples/cli-demo), [`compact`](../packages/compact/compact), [`compact-basic`](../packages/compact/compact-basic), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-projection`](../packages/session-projection/session-projection), [`session-projection-cache`](../packages/session-projection/session-projection-cache), [`session-telemetry`](../packages/telemetry/session-telemetry), [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel), [`session-title`](../packages/session-title/session-title), [`token-meter`](../packages/llm/token-meter), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-approval`](../packages/ui/user-approval), [`workspace-context`](../packages/context/workspace-context) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:103`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence), [`session-telemetry`](../packages/telemetry/session-telemetry) | | `slash/input-begin-command` | `bail` | [`packages/client/ui-slash/src/types.ts:230`](../packages/client/ui-slash/src/types.ts) | - | `ui-conversation` | | `slash/input-consume-token` | `bail` | [`packages/client/ui-slash/src/types.ts:244`](../packages/client/ui-slash/src/types.ts) | - | `ui-conversation` | @@ -45,7 +45,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:131`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`subagent`](../packages/subagent/subagent) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:29`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:35`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | -| `telemetry/record` | `waterfall` | [`packages/telemetry/session-telemetry/src/index.ts:41`](../packages/telemetry/session-telemetry/src/index.ts) | [`session-telemetry`](../packages/telemetry/session-telemetry) (`waterfall`) | - | +| `telemetry/record` | `waterfall` | [`packages/telemetry/session-telemetry/src/index.ts:42`](../packages/telemetry/session-telemetry/src/index.ts) | [`session-telemetry`](../packages/telemetry/session-telemetry) (`waterfall`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:156`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | | `tools/code-dispatch-log` | `waterfall` | [`packages/core/tools/src/index.ts:138`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`spill-policy`](../packages/spill/spill-policy) | | `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:113`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`timeout-policy`](../packages/timeout/timeout-policy) | diff --git a/examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts b/examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts index 02be1a9011..72305f0724 100644 --- a/examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts +++ b/examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts @@ -11,6 +11,7 @@ import { createServer } from 'node:http' import { once } from 'node:events' import { boot, resolveConfigPath } from '@deepseek-ai/dsh-app-boot' import { runOneShot } from '@deepseek-ai/dsh-cli-demo/src/cli.ts' +import { recordFeedback } from '@deepseek-ai/dsh-command-feedback' const configPath = process.argv[2] if (configPath === undefined) throw new Error('telemetry-otel driver requires a config path') @@ -35,6 +36,15 @@ try { // The fixture credential rides the model-visible user message; the exported // copy must scrub it while the canonical log keeps the original bytes. await runOneShot(ctx, { task: 'prove telemetry with key sk-e2efixture1234567890' }) + const mode = process.env.DSH_TELEMETRY_E2E_MODE ?? 'FULL' + if (mode !== 'FULL') { + const [agent] = ctx.get('agents')?.roots() ?? [] + if (agent === undefined) throw new Error('telemetry-otel driver requires one root agent') + recordFeedback(agent.session, 'fixture feedback') + if (mode === 'FEEDBACK_ONLY') { + await runOneShot(ctx, { task: 'post-feedback private suffix' }) + } + } } finally { await ctx.fiber.dispose() } diff --git a/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml b/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml index 34e23b828e..1433173768 100644 --- a/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml +++ b/examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml @@ -2,6 +2,14 @@ # path, exporting to the mock OTLP collector the driver starts (url via env). # The redact-rule entry models a deployment mounting its own scrub rule on the # telemetry/record waterfall — the seam itself ships no rules. +- id: logger-console + name: '@cordisjs/plugin-logger-console' + config: + colors: false + levels: + default: 3 + showTime: '' + - id: cli-mock-llm name: './cli-mock-llm.ts' @@ -14,6 +22,7 @@ - id: telemetry-otel name: '@deepseek-ai/dsh-session-telemetry-otel' config: + mode: !!js process.env.DSH_TELEMETRY_E2E_MODE || 'FULL' exporter: url: !!js process.env.DSH_TELEMETRY_E2E_URL diff --git a/examples/package.json b/examples/package.json index 51fc48b8fa..0298685693 100644 --- a/examples/package.json +++ b/examples/package.json @@ -7,6 +7,7 @@ "dependencies": { "@cordisjs/plugin-hmr": "workspace:*", "@cordisjs/plugin-include": "workspace:*", + "@cordisjs/plugin-logger-console": "workspace:*", "@deepseek-ai/dsh-acp-demo": "workspace:*", "@deepseek-ai/dsh-agent-spine-demo": "workspace:*", "@deepseek-ai/dsh-app-boot": "workspace:*", @@ -14,6 +15,7 @@ "@deepseek-ai/dsh-bash-sandbox": "workspace:*", "@deepseek-ai/dsh-cli-demo": "workspace:*", "@deepseek-ai/dsh-code-runtime-worker": "workspace:*", + "@deepseek-ai/dsh-command-feedback": "workspace:*", "@deepseek-ai/dsh-compact-basic": "workspace:*", "@deepseek-ai/dsh-compact-tool-result-prune": "workspace:*", "@deepseek-ai/dsh-fs-local": "workspace:*", diff --git a/packages/feedback/README.i18n.yaml b/packages/feedback/README.i18n.yaml index 31ed2d25e8..4ad5a93fb5 100644 --- a/packages/feedback/README.i18n.yaml +++ b/packages/feedback/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/feedback/README.md -README.md: 7962a16ee9bc7d8a969a466591d761829cd55d7f -README.zh.md: aad8f4d797ff16a5ef9be4c968fb28d708bad13e +README.md: d2a4a5a27e1c661d2f62b328578fd890a0c622ee +README.zh.md: 2fa42e3bb5f05dfc425356f302f44e497b100f24 diff --git a/packages/feedback/README.md b/packages/feedback/README.md index 7962a16ee9..d2a4a5a27e 100644 --- a/packages/feedback/README.md +++ b/packages/feedback/README.md @@ -8,4 +8,4 @@ The feedback family lets a human record a remark about the session without actin |---|---|---| | `command-feedback/` | Trigger-independent `feedback/record` event plus the human-facing `/feedback` producer | — | -A recorded remark is log-only: it never enters the model surface or derived history, and no shipped plugin consumes it. A future consumer reads `feedback/record` events from the session log rather than changing how they are captured. +A recorded remark is log-only: it never enters the model surface or derived history. When mounted, [`dsh-session-telemetry-otel`](../telemetry/session-telemetry-otel/) observes `feedback/record` to release a pending telemetry prefix or warn that disabled telemetry leaves the feedback local; capture itself remains independent of that policy. diff --git a/packages/feedback/README.zh.md b/packages/feedback/README.zh.md index aad8f4d797..2fa42e3bb5 100644 --- a/packages/feedback/README.zh.md +++ b/packages/feedback/README.zh.md @@ -8,4 +8,4 @@ feedback 家族让人类记录对会话的评价，但不据此采取任何动 |---|---|---| | `command-feedback/` | 与触发方式无关的 `feedback/record` 事件，以及面向用户的 `/feedback` 生产方 | 无 | -被记录的评价仅写入日志：它绝不会进入模型 surface 或派生历史，随附插件也不会消费它。未来的消费方从会话日志中读取 `feedback/record` 事件，而不是改变它们的采集方式。 +被记录的评价仅写入日志：它绝不会进入模型 surface 或派生历史。挂载后，[`dsh-session-telemetry-otel`](../telemetry/session-telemetry-otel/) 会观察 `feedback/record`，以释放待处理的遥测前缀，或在遥测已禁用时警告反馈将留在本地；采集本身与该策略相互独立。 diff --git a/packages/feedback/command-feedback/README.i18n.yaml b/packages/feedback/command-feedback/README.i18n.yaml index 47c169ec3f..ea439ce2fe 100644 --- a/packages/feedback/command-feedback/README.i18n.yaml +++ b/packages/feedback/command-feedback/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/feedback/command-feedback/README.md -README.md: c9650d6a2c595550545b3dbf07f62e6aa65f39b9 -README.zh.md: ba24276ba1bd71a4eb68c7fdb48a3760bdbec8fc +README.md: e3b0e58f1746c7bcd1c74ac0990a872a1f24d7d7 +README.zh.md: 40ec871caff6f90b0b1c685e833c874e32a48d16 diff --git a/packages/feedback/command-feedback/README.md b/packages/feedback/command-feedback/README.md index c9650d6a2c..e3b0e58f17 100644 --- a/packages/feedback/command-feedback/README.md +++ b/packages/feedback/command-feedback/README.md @@ -15,7 +15,7 @@ Surrounding whitespace is discarded, but feedback is otherwise unparsed: no trun ## What this plugin does and does not do -`recordFeedback(session, text)` is the command-independent write path. It rejects empty normalized text and appends `feedback/record { text }`; a different UI, hook, or host integration can call it without constructing a slash command. The `/feedback` handler uses that producer, starts no model work, and no plugin in this repository reads the event. +`recordFeedback(session, text)` is the command-independent write path. It rejects empty normalized text and appends `feedback/record { text }`; a different UI, hook, or host integration can call it without constructing a slash command. The `/feedback` handler uses that producer and starts no model work. The optional [`dsh-session-telemetry-otel`](../../telemetry/session-telemetry-otel/) consumer observes the event without changing its capture contract. The feedback text appears in exactly one durable payload: `feedback/record`. [`dsh-commands`](../../ui/commands/README.md) still appends its generic `command/run` / `command/done` pairing, but this definition sets `recordInput: false`, so `command/run` omits `args`; the paired `command/done` carries only the outcome. All three events are log-only and absent from the ordered surface, `deriveMessages()`, and model requests. These appends start persistence's ordinary eager drain, but neither producer forces `session/flush`, so acknowledgement means the feedback is in the log, not that it has reached disk. Rejected empty input leaves only the command pairing settled as `kind: 'error'`, with no `feedback/record`. @@ -52,7 +52,7 @@ Independent of the model request path. Recording appends to the session log only ## Known Limitations and Deferred Work -- **Nothing consumes the recorded feedback** — capture is deliberately inert. There is no retrieval, aggregation, export, or reporting surface, and no model-facing tool reads `feedback/record`; a consumer is a separate package. +- **No feedback retrieval or management surface** — the optional OTel plugin uses the event only as a sharing trigger. There is no retrieval, aggregation, categorization, or model-facing tool for `feedback/record`. - **No structured fields** — an entry is one free-text string with no category, severity, or referenced-event link, so feedback cannot be filtered by subject without re-reading its text. - **No amend or withdraw** — the session log is append-only and this package adds no tombstone, so a mistaken entry stays recorded and can only be superseded by a later one. - **No explicit durability barrier** — the acknowledgement follows the append, not a flush, so an entry recorded immediately before a crash can be lost with any other unflushed tail. Feedback is not worth forcing a synchronous disk write for; a consumer that needs one awaits `ctx.sessions.flush(session)`. diff --git a/packages/feedback/command-feedback/README.zh.md b/packages/feedback/command-feedback/README.zh.md index ba24276ba1..40ec871caf 100644 --- a/packages/feedback/command-feedback/README.zh.md +++ b/packages/feedback/command-feedback/README.zh.md @@ -15,7 +15,7 @@ ## 本插件做什么、不做什么 -`recordFeedback(session, text)` 是不依赖命令的写入路径。它拒绝规范化后为空的文本，并追加 `feedback/record { text }`；其他 UI、钩子或 host 集成无需构造斜杠命令即可调用它。`/feedback` 处理器通过该生产方写入，不启动任何模型工作；本仓库中也没有任何插件读取该事件。 +`recordFeedback(session, text)` 是不依赖命令的写入路径。它拒绝规范化后为空的文本，并追加 `feedback/record { text }`；其他 UI、钩子或 host 集成无需构造斜杠命令即可调用它。`/feedback` 处理器通过该生产方写入，且不启动任何模型工作。可选的 [`dsh-session-telemetry-otel`](../../telemetry/session-telemetry-otel/) 消费方会观察该事件，但不改变它的采集契约。 反馈文本只出现在一个持久载荷中：`feedback/record`。[`dsh-commands`](../../ui/commands/README.md) 仍会追加通用的 `command/run` / `command/done` 配对，但此定义设置了 `recordInput: false`，因此 `command/run` 会省略 `args`；配对的 `command/done` 只携带结果。三个事件都仅写入日志，不出现在有序 surface、`deriveMessages()` 以及模型请求中。这些追加会启动持久化的常规即时排空，但两个生产方都不会强制 `session/flush`，因此确认文本表示反馈已进入日志，而不表示它已经落盘。被拒绝的空输入只会留下以 `kind: 'error'` 结算的命令配对，不会产生 `feedback/record`。 @@ -52,7 +52,7 @@ TUI 应用无条件挂载此命令；它没有配置，也不依赖持久 goal ## 已知限制与暂缓工作 -- **没有任何消费方读取被记录的反馈**：采集刻意不产生任何后续动作。这里没有检索、聚合、导出或报告 surface，也没有面向模型的工具读取 `feedback/record`；消费方是另一个独立包。 +- **没有反馈检索或管理 surface**：可选的 OTel 插件仅将该事件用作共享触发器。本包不为 `feedback/record` 提供检索、聚合、分类或面向模型的工具。 - **没有结构化字段**：一条条目就是一个自由文本字符串，没有类别、严重程度或关联事件链接，因此无法在不重读文本的情况下按主题过滤反馈。 - **不支持修改或撤回**：会话日志是仅追加的，本包也不新增 tombstone，因此错误的条目会一直保留在记录中，只能由后续条目取代。 - **没有显式持久化屏障**：确认文本紧随追加而非 flush，因此紧临崩溃前记录的条目可能与其他未 flush 的尾部一同丢失。为反馈强制同步写盘并不值得；需要该保证的消费方可自行等待 `ctx.sessions.flush(session)`。 diff --git a/packages/telemetry/README.i18n.yaml b/packages/telemetry/README.i18n.yaml index 41f1bd956f..cd3be8d155 100644 --- a/packages/telemetry/README.i18n.yaml +++ b/packages/telemetry/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/telemetry/README.md -README.md: 944cb3f9bac6169feddf8b49bc481cfbe7c6fa9d -README.zh.md: 795b20abb47e1bf791730cc7f3ebb0522549a271 +README.md: 0adf140a19bd6ab19c4d4139d4ebdae941c0d1b0 +README.zh.md: 57988732e36d105ebcc48adcdab9344a6cccb525 diff --git a/packages/telemetry/README.md b/packages/telemetry/README.md index 944cb3f9ba..0adf140a19 100644 --- a/packages/telemetry/README.md +++ b/packages/telemetry/README.md @@ -2,9 +2,9 @@ English | [中文](README.zh.md) -Outbound session reporting: the telemetry seam plus its OpenTelemetry backend. The design — the boundary axiom (the harness's aspect ends at `emit()`; delivery is the reporting SDK's), the `telemetry/record` waterfall (deployment-mounted redaction rules; the seam ships none), the fixed chunk projection, the handoff cursor, and the operational-record channel — is pinned in [the revival Agent Note](../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md). +Outbound session reporting: the telemetry seam plus its OpenTelemetry backend. The boundary axiom, redaction waterfall, fixed chunk projection, handoff cursor, and operational-record channel are pinned in [the revival Agent Note](../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md); immediate, feedback-gated, and disabled delivery are owned by [the mode decision](../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md). | Package | Role | |---|---| -| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | The seam: capture points, projection, redaction, handoff cursor, ops signals, and the minimal backend contract (`emit`/`flush?`/`shutdown`). | -| [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | The backend a deployment loads: the OTel JS SDK's log pipeline (`LoggerProvider` + `BatchLogRecordProcessor` + OTLP/HTTP exporter), configured verbatim through passthroughs. | +| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | The seam: capture points, projection, redaction, immediate or held handoff, cursor, ops signals, and the minimal backend contract (`emit`/`flush?`/`shutdown`). | +| [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | The backend a deployment loads: `FULL`, `FEEDBACK_ONLY`, or `DISABLED` policy around the OTel JS SDK log pipeline. | diff --git a/packages/telemetry/README.zh.md b/packages/telemetry/README.zh.md index 795b20abb4..57988732e3 100644 --- a/packages/telemetry/README.zh.md +++ b/packages/telemetry/README.zh.md @@ -2,9 +2,9 @@ [English](README.md) | 中文 -面向外部的会话上报：遥测（telemetry）seam 及其 OpenTelemetry 后端。整套设计固定在[复活 Agent Note（agent 决策记录）](../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)中：边界公理（harness 的职责止于 `emit()`，投递由上报 SDK 负责）、`telemetry/record` waterfall（瀑布式事件；脱敏规则由部署方挂载，seam 自身不带任何规则）、固定分片投影、handoff 游标，以及运维记录通道。 +面向外部的会话上报：遥测（telemetry）seam 及其 OpenTelemetry 后端。边界公理、脱敏 waterfall（瀑布式事件）、固定分片投影、handoff 游标及运维记录通道的决定见[复活 Agent Note（agent 决策记录）](../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)；即时、反馈门控及禁用投递由[模式决策](../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md)统一规定。 | 包（package） | 职责 | |---|---| -| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | seam 本体：捕获点、投影、脱敏、handoff 游标、运维信号，以及最小后端契约（`emit`/`flush?`/`shutdown`）。 | -| [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | 部署方要加载的后端：OTel JS SDK 的日志流水线（`LoggerProvider` + `BatchLogRecordProcessor` + OTLP/HTTP 导出器），经透传（passthrough）原样配置。 | +| [`@deepseek-ai/dsh-session-telemetry`](session-telemetry/) | seam 本体：捕获点、投影、脱敏、即时或暂存交接、游标、运维信号，以及最小后端契约（`emit`/`flush?`/`shutdown`）。 | +| [`@deepseek-ai/dsh-session-telemetry-otel`](session-telemetry-otel/) | 部署方要加载的后端：围绕 OTel JS SDK 日志流水线实施 `FULL`、`FEEDBACK_ONLY` 或 `DISABLED` 策略。 | diff --git a/packages/telemetry/session-telemetry-otel/README.i18n.yaml b/packages/telemetry/session-telemetry-otel/README.i18n.yaml index b1a2052a3f..6557557b8c 100644 --- a/packages/telemetry/session-telemetry-otel/README.i18n.yaml +++ b/packages/telemetry/session-telemetry-otel/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/telemetry/session-telemetry-otel/README.md -README.md: 9b208e291e77bee50d9d4fd14808268dca75f2db -README.zh.md: 76de1bf1ad58a0239907f3b63c672177874c7966 +README.md: fab2461477b2174bded42ed6f05ae55c7c5f697c +README.zh.md: ab0191188836e03434adbce527d31b62ead848a3 diff --git a/packages/telemetry/session-telemetry-otel/README.md b/packages/telemetry/session-telemetry-otel/README.md index 9b208e291e..fab2461477 100644 --- a/packages/telemetry/session-telemetry-otel/README.md +++ b/packages/telemetry/session-telemetry-otel/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — the only entry a deployment loads. It composes the OTel JS SDK as-is (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP log exporter) and maps each record the seam hands over onto `logger.emit()`, under two instrumentation scopes: ledger records on `@deepseek-ai/dsh-session-telemetry-otel`, operational records on `@deepseek-ai/dsh-session-telemetry-otel/ops`. Resource identity (`service.name`/`service.version`) comes from `dsh-llm`'s `APP_IDENTITY`, the same source the attribution headers use. +The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — the only entry a deployment loads. Its `mode` decides whether the seam hands records over immediately, releases them only at recorded feedback, or keeps telemetry local. Uploading modes compose the OTel JS SDK as-is (`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP log exporter) and map each handed-over record onto `logger.emit()`, under two instrumentation scopes: ledger records on `@deepseek-ai/dsh-session-telemetry-otel`, operational records on `@deepseek-ai/dsh-session-telemetry-otel/ops`. Resource identity (`service.name`/`service.version`) comes from `dsh-llm`'s `APP_IDENTITY`, the same source the attribution headers use. ## Config @@ -10,6 +10,7 @@ The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — th - id: telemetry-otel name: '@deepseek-ai/dsh-session-telemetry-otel' config: + mode: FULL # FULL (default), FEEDBACK_ONLY, or DISABLED exporter: # passed verbatim to the SDK's OTLP/HTTP log exporter url: https://collector.example.com/v1/logs headers: @@ -17,15 +18,21 @@ The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — th processor: {} # optional; passed verbatim to BatchLogRecordProcessor ``` -`exporter.url` is the one field this package validates itself — required, no default, must parse as `http(s)` — so a missing endpoint fails at plugin load (as does a non-positive-integer `processor.maxExportBatchSize`, which the SDK accepts but then hangs on at shutdown). Everything else is the SDK's option shape, owned and documented by the SDK, and both blocks pass through whole: every `OTLPExporterNodeConfigBase` field (`headers`, `timeoutMillis`, `compression`, `keepAlive`, …) reaches the exporter, and batching, export cadence (`scheduledDelayMillis`), retry, queue bounds, and loss policy under sustained failure are the SDK's documented behavior, tuned through the `processor` passthrough. The backend deliberately implements no `flush()`: the batch processor is the only flusher in the process, which is what makes `shutdown()`'s drain complete. Removing this block from `cordis.yml` is the opt-out: no residual state, no `enabled` flag. +| `mode` | Behavior | +|---|---| +| `FULL` | Default. Each projected record, including lifecycle ops records, is handed to the OTel SDK immediately. | +| `FEEDBACK_ONLY` | Each `feedback/record` releases the redacted, projected session prefix through that event. Later records wait for another feedback event and remain local if none arrives. | +| `DISABLED` | No coordinator, provider, processor, or exporter is constructed. No telemetry record leaves the process. A `feedback/record` logs `session telemetry is DISABLED; nothing will be shared and this feedback remains local`; the event remains in the local session log. | + +`exporter.url` is required in `FULL` and `FEEDBACK_ONLY`, has no default, and must parse as `http(s)`; it is optional and unused in `DISABLED`. Uploading modes also reject a non-positive-integer `processor.maxExportBatchSize`, which the SDK accepts but then hangs on at shutdown. Everything else is the SDK's option shape, owned and documented by the SDK, and both blocks pass through whole: every `OTLPExporterNodeConfigBase` field (`headers`, `timeoutMillis`, `compression`, `keepAlive`, …) reaches the exporter, and batching, export cadence (`scheduledDelayMillis`), retry, queue bounds, and loss policy under sustained failure are the SDK's documented behavior, tuned through the `processor` passthrough. The backend deliberately implements no `flush()`: the batch processor is the only flusher in the process, which is what makes `shutdown()`'s drain complete. ## What leaves the machine -Records carry the complete `event.data` as the seam's `telemetry/record` waterfall returns it — user and assistant message content, tool arguments and results (command output, file contents), the full system prompt and tool schemas (`request/header`), todo text, compaction summaries, hook `stderrSummary`, and the session `cwd` (a local path). The seam ships no redaction rules: with no `telemetry/record` listener mounted, that is the raw captured copy, so a deployment exporting beyond a trusted boundary mounts its own rules (see [the seam README](../session-telemetry/README.md#the-redact-waterfall)). Provider credentials never appear regardless: adapter API keys are constructor parameters, not session events, so they are structurally absent from the log and therefore from telemetry. +In uploading modes, records carry the complete `event.data` as the seam's `telemetry/record` waterfall returns it — user and assistant message content, tool arguments and results (command output, file contents), the full system prompt and tool schemas (`request/header`), todo text, compaction summaries, hook `stderrSummary`, feedback text, and the session `cwd` (a local path). The seam ships no redaction rules: with no `telemetry/record` listener mounted, that is the raw captured copy, so a deployment exporting beyond a trusted boundary mounts its own rules (see [the seam README](../session-telemetry/README.md#the-redact-waterfall)). Provider credentials never appear regardless: adapter API keys are constructor parameters, not session events, so they are structurally absent from the log and therefore from telemetry. `DISABLED` does not construct the SDK pipeline or hand any capture to a backend. ## Field mapping -Seam record → SDK log record: `time` → `timestamp`/`observedTimestamp`; `severity` → `severityNumber`/`severityText` (INFO 9 / WARN 13 / ERROR 17); `body` → the structured log body; `attributes` verbatim. Receivers dedupe on `(session.id, event.seq)`, alert on severity, and detect crashes by `shutdown`-record absence (a session with activity, no `shutdown` ops record, gone stale ended uncleanly). The marker means telemetry stopped observing the session cleanly — emitted at the session's own disposal, or at application teardown for sessions still running then; a marker followed by more of that session's events is a telemetry reload, not a session restart. Streams are not self-contained across lineage: a resumed session continues its own id's stream from where the previous process left off, and a forked session's stream starts at its inherited boundary — its prefix lives in the parent's stream, stitched via `session.parent_id` + `session.seed_length`. One consequence of continuing rather than replaying: a turn left open mid-stream and never closed marks the previous process dying inside it. The local log is repaired with synthetic closers at resume, but those repairs are never exported — the wire stream stays faithful to what the crashed process actually shipped, and a later clean `shutdown` marker attests only to the resumed process's own exit. +Seam record → SDK log record: `time` → `timestamp`/`observedTimestamp`; `severity` → `severityNumber`/`severityText` (INFO 9 / WARN 13 / ERROR 17); `body` → the structured log body; `attributes` verbatim. Receivers dedupe on `(session.id, event.seq)` and alert on severity. In `FULL`, they may also detect crashes by `shutdown`-record absence: the marker is emitted at the session's own disposal or application teardown, and a marker followed by more events is a telemetry reload. In `FEEDBACK_ONLY`, a released prefix normally has no later `shutdown` marker, so its absence is not a crash signal. Streams are not self-contained across lineage: a resumed session continues its own id's stream from where the previous process left off, and a forked session's stream starts at its inherited boundary — its prefix lives in the parent's stream, stitched via `session.parent_id` + `session.seed_length`. A resumed local log may contain synthetic closers that were never exported; the wire stream stays faithful to records actually handed to the SDK. ## Model Experience @@ -39,3 +46,4 @@ None; this package neither assembles nor sends a provider request. - **Upstream experimental tree** — `@opentelemetry/sdk-logs` is still published from the upstream experimental tree; SDK API churn lands here and only here — the seam contract does not move. - **No live-collector coverage** — every test exports to a local mock collector; the keyless Loader-composition e2e (`tests/loader-composition.e2e.ts`) covers the wire shape on every run, and behavior against a real OTLP deployment (auth, TLS, throttling) is the SDK exporter's documented territory. +- **Feedback-only memory** — each session retains deep-copied, redacted projected records in memory until feedback releases them or the session becomes unreachable. There is no durable pre-feedback spool; a crash before feedback uploads nothing. diff --git a/packages/telemetry/session-telemetry-otel/README.zh.md b/packages/telemetry/session-telemetry-otel/README.zh.md index 76de1bf1ad..ab01911888 100644 --- a/packages/telemetry/session-telemetry-otel/README.zh.md +++ b/packages/telemetry/session-telemetry-otel/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -[遥测（telemetry）seam](../session-telemetry/) 的 OpenTelemetry 后端，也是部署方唯一要加载的条目。它原样组合 OTel JS SDK（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP 日志导出器），把 seam 交接过来的每条记录映射到 `logger.emit()`，并使用两个插桩作用域（instrumentation scope）：ledger 记录挂在 `@deepseek-ai/dsh-session-telemetry-otel` 下，运维记录挂在 `@deepseek-ai/dsh-session-telemetry-otel/ops` 下。资源身份（`service.name`/`service.version`）来自 `dsh-llm` 的 `APP_IDENTITY`，与归因标头同源。 +[遥测（telemetry）seam](../session-telemetry/) 的 OpenTelemetry 后端，也是部署方唯一要加载的条目。其 `mode` 决定 seam 是立即交接记录、仅在记录反馈时释放记录，还是将遥测留在本地。上传模式会原样组合 OTel JS SDK（`LoggerProvider` → `BatchLogRecordProcessor` → OTLP/HTTP 日志导出器），把每条已交接记录映射到 `logger.emit()`，并使用两个插桩作用域（instrumentation scope）：ledger 记录挂在 `@deepseek-ai/dsh-session-telemetry-otel` 下，运维记录挂在 `@deepseek-ai/dsh-session-telemetry-otel/ops` 下。资源身份（`service.name`/`service.version`）来自 `dsh-llm` 的 `APP_IDENTITY`，与归因标头同源。 ## 配置 @@ -10,6 +10,7 @@ - id: telemetry-otel name: '@deepseek-ai/dsh-session-telemetry-otel' config: + mode: FULL # FULL (default), FEEDBACK_ONLY, or DISABLED exporter: # passed verbatim to the SDK's OTLP/HTTP log exporter url: https://collector.example.com/v1/logs headers: @@ -17,15 +18,21 @@ processor: {} # optional; passed verbatim to BatchLogRecordProcessor ``` -`exporter.url` 是本包（package）唯一自行校验的字段：必填、无默认值、必须能解析为 `http(s)`，因此缺失端点会在插件加载时失败（`processor.maxExportBatchSize` 不是正整数时同样如此：SDK 会接受该值，随后却在关闭时因它挂起）。其余全部是 SDK 自己的选项形态，由 SDK 拥有并在 SDK 文档中说明，两个配置块都整体透传（passthrough）：`OTLPExporterNodeConfigBase` 的每个字段（`headers`、`timeoutMillis`、`compression`、`keepAlive` 等）都会到达导出器；批处理、导出节奏（`scheduledDelayMillis`）、重试、队列上限，以及持续失败下的丢失策略，都是 SDK 的文档化行为，经 `processor` 透传调优。该后端刻意不实现 `flush()`：批处理器是进程内唯一执行 flush 的组件，`shutdown()` 的排空正因如此才是完整的。从 `cordis.yml` 中删除该配置块即为退出方式：无残留状态，也没有 `enabled` 开关。 +| `mode` | 行为 | +|---|---| +| `FULL` | 默认值。每条已投影记录都立即交给 OTel SDK，包括生命周期运维记录。 | +| `FEEDBACK_ONLY` | 每个 `feedback/record` 都会释放截至该事件的已脱敏、已投影会话前缀。后续记录等待下一个反馈事件；如果没有后续反馈，则留在本地。 | +| `DISABLED` | 不构造协调器、提供方、处理器或导出器。没有遥测记录会离开进程。`feedback/record` 会记录 `session telemetry is DISABLED; nothing will be shared and this feedback remains local`；该事件留在本地会话日志中。 | + +`exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填，无默认值，且必须能解析为 `http(s)`；在 `DISABLED` 中可省略且不使用。上传模式也会拒绝不是正整数的 `processor.maxExportBatchSize`，SDK 虽会接受该值，但随后会在关闭时挂起。其余全部是 SDK 自己的选项形态，由 SDK 拥有并在 SDK 文档中说明，两个配置块都整体透传（passthrough）：`OTLPExporterNodeConfigBase` 的每个字段（`headers`、`timeoutMillis`、`compression`、`keepAlive` 等）都会到达导出器；批处理、导出节奏（`scheduledDelayMillis`）、重试、队列上限，以及持续失败下的丢失策略，都是 SDK 的文档化行为，经 `processor` 透传调优。该后端刻意不实现 `flush()`：批处理器是进程内唯一执行 flush 的组件，`shutdown()` 的排空正因如此才是完整的。 ## 哪些数据会离开本机 -记录携带完整的 `event.data`，内容以 seam 的 `telemetry/record` waterfall（瀑布式事件）返回的结果为准：用户与 assistant 消息内容、工具参数与工具结果（命令输出、文件内容）、完整的系统提示词与工具 schema（`request/header`）、todo 文本、压缩（compaction）摘要、钩子的 `stderrSummary`，以及会话 `cwd`（一个本地路径）。seam 不带任何脱敏规则：未挂载 `telemetry/record` 监听器时，导出的就是捕获原样的副本，因此向可信边界之外导出的部署方要挂载自己的规则（见 [seam README](../session-telemetry/README.md#the-redact-waterfall)）。无论如何，提供方凭据都不会出现：适配器的 API key 是构造函数参数而非会话事件，因此它们在结构上就不存在于日志中，也就不存在于遥测中。 +在上传模式中，记录携带完整的 `event.data`，内容以 seam 的 `telemetry/record` waterfall（瀑布式事件）返回的结果为准：用户与 assistant 消息内容、工具参数与工具结果（命令输出、文件内容）、完整的系统提示词与工具 schema（`request/header`）、todo 文本、压缩（compaction）摘要、钩子的 `stderrSummary`、反馈文本，以及会话 `cwd`（一个本地路径）。seam 不带任何脱敏规则：未挂载 `telemetry/record` 监听器时，导出的就是捕获原样的副本，因此向可信边界之外导出的部署方要挂载自己的规则（见 [seam README](../session-telemetry/README.md#the-redact-waterfall)）。无论如何，提供方凭据都不会出现：适配器的 API key 是构造函数参数而非会话事件，因此它们在结构上就不存在于日志中，也就不存在于遥测中。`DISABLED` 不会构造 SDK 流水线，也不会将任何捕获内容交给后端。 ## 字段映射 -seam 记录 → SDK 日志记录：`time` → `timestamp`/`observedTimestamp`；`severity` → `severityNumber`/`severityText`（INFO 9 / WARN 13 / ERROR 17）；`body` → 结构化日志 body；`attributes` 原样照搬。接收端基于 `(session.id, event.seq)` 去重、按严重级别告警，并通过 `shutdown` 记录的缺失检测崩溃（一个曾有活动、没有 `shutdown` 运维记录、且已然陈旧的会话，就是未干净结束的会话）。该标记的含义是遥测干净地停止了对该会话的观察：它在会话自身 dispose（资源释放）时发出，对于届时仍在运行的会话，则在应用关闭时发出；标记之后又出现该会话的更多事件，说明发生的是遥测重载，而不是会话重启。跨谱系（lineage）的流并不自足：恢复的会话在其自身 id 的流上从上一个进程停止之处继续；fork 出的会话，其流从继承边界开始，前缀位于父会话的流中，由接收端基于 `session.parent_id` + `session.seed_length` 拼接。继续而非回放的一个后果：流中一个开启后再未关闭的轮次，标志着上一个进程死在了该轮次之内。恢复时本地日志会以合成的关闭事件修复，但这些修复绝不导出：导出的流忠实于崩溃进程实际发出的内容，其后干净的 `shutdown` 标记也只证明恢复后进程自身的退出。 +seam 记录 → SDK 日志记录：`time` → `timestamp`/`observedTimestamp`；`severity` → `severityNumber`/`severityText`（INFO 9 / WARN 13 / ERROR 17）；`body` → 结构化日志 body；`attributes` 原样照搬。接收端基于 `(session.id, event.seq)` 去重，并按严重级别告警。在 `FULL` 中，接收端还可通过缺少 `shutdown` 记录检测崩溃：该标记在会话自身 dispose（资源释放）或应用关闭时发出；标记之后出现更多事件，说明遥测发生了重载。在 `FEEDBACK_ONLY` 中，已释放的前缀通常不包含随后的 `shutdown` 标记，因此缺少该标记不是崩溃信号。跨谱系（lineage）的流并不自足：恢复的会话在其自身 id 的流上从上一个进程停止之处继续；fork 出的会话的流从继承边界开始，其前缀位于父会话的流中，由接收端基于 `session.parent_id` + `session.seed_length` 拼接。恢复后的本地日志可能包含从未导出的合成关闭事件；协议流忠实于实际交给 SDK 的记录。 ## 模型体验 @@ -39,3 +46,4 @@ seam 记录 → SDK 日志记录：`time` → `timestamp`/`observedTimestamp`； - **上游实验性源码树**：`@opentelemetry/sdk-logs` 仍从上游实验性（experimental）源码树发布；SDK API 的变动只会落在本包，也仅落在本包；seam 契约不动。 - **无真实 collector 覆盖**：所有测试都导出到本地 mock collector；无密钥的 Loader 组合 e2e（`tests/loader-composition.e2e.ts`）在每次运行中都覆盖协议格式（wire format）形态，而面对真实 OTLP 部署的行为（认证、TLS、限流）属于 SDK 导出器文档的职责范围。 +- **仅反馈模式的内存占用**：每个会话都会在内存中保留已深拷贝、已脱敏的投影记录，直到反馈将其释放或会话变得不可达。反馈前不存在持久化 spool；如果在反馈前崩溃，则什么都不上传。 diff --git a/packages/telemetry/session-telemetry-otel/package.json b/packages/telemetry/session-telemetry-otel/package.json index 7be8c04ce4..4037cfe28a 100644 --- a/packages/telemetry/session-telemetry-otel/package.json +++ b/packages/telemetry/session-telemetry-otel/package.json @@ -36,6 +36,7 @@ "schemastery": "^3.18.0" }, "peerDependencies": { + "@deepseek-ai/dsh-command-feedback": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -44,6 +45,7 @@ }, "devDependencies": { "@cordisjs/plugin-loader": "workspace:^", + "@deepseek-ai/dsh-command-feedback": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/telemetry/session-telemetry-otel/src/index.ts b/packages/telemetry/session-telemetry-otel/src/index.ts index 85dd75f275..cb0ee71fc7 100644 --- a/packages/telemetry/session-telemetry-otel/src/index.ts +++ b/packages/telemetry/session-telemetry-otel/src/index.ts @@ -6,8 +6,8 @@ * record handed over by the seam onto `logger.emit()`. Per the seam's * boundary axiom, everything downstream of that call (batching, retry, * queueing, loss policy) is the SDK's documented behavior, configured - * verbatim through the `exporter`/`processor` passthroughs; this package - * adds no knobs of its own on top of them. + * verbatim through the `exporter`/`processor` passthroughs. This package owns + * only whether capture is immediate, feedback-released, or disabled. * * @module @deepseek-ai/dsh-session-telemetry-otel */ @@ -15,7 +15,14 @@ import { createRequire } from 'node:module' import z from 'schemastery' import type { Context } from 'cordis' -import { Telemetry, TelemetryCoordinator, type TelemetryRecord, type TelemetrySeverity } from '@deepseek-ai/dsh-session-telemetry' +import type {} from '@deepseek-ai/dsh-command-feedback' +import { + Telemetry, + TelemetryCoordinator, + type TelemetryDelivery, + type TelemetryRecord, + type TelemetrySeverity, +} from '@deepseek-ai/dsh-session-telemetry' import { APP_IDENTITY } from '@deepseek-ai/dsh-llm' import { BatchLogRecordProcessor, @@ -31,13 +38,22 @@ import { resourceFromAttributes } from '@opentelemetry/resources' // version (same pattern as dsh-llm's attribution identity). const { version } = createRequire(import.meta.url)('../package.json') as { version: string } +/** Supported session-sharing policies for the OTel backend. */ +export const TELEMETRY_MODES = ['FULL', 'FEEDBACK_ONLY', 'DISABLED'] as const + +/** Session-sharing policy selected by {@link Config.mode}. */ +export type TelemetryMode = typeof TELEMETRY_MODES[number] + +const DISABLED_FEEDBACK_WARNING = 'session telemetry is DISABLED; nothing will be shared and this feedback remains local' + /** - * Plugin configuration: two verbatim SDK option shapes plus nothing else. - * `exporter.url` is the one field this package validates itself — required, - * no default, must parse as an `http(s)` URL — because a missing endpoint - * must fail at plugin load, not at first export. + * Plugin configuration: one sharing policy plus two verbatim SDK option + * shapes. `exporter.url` is required for modes that upload and unused for + * `DISABLED`. */ export interface Config { + /** Sharing policy; defaults to immediate `FULL` delivery. */ + mode?: TelemetryMode /** * Passed verbatim to the SDK's OTLP/HTTP log exporter — the complete * `OTLPExporterNodeConfigBase` shape (`headers`, `timeoutMillis`, @@ -45,7 +61,7 @@ export interface Config { * is the one field this package requires and validates itself. */ exporter?: OTLPExporterNodeConfigBase & { - /** Full logs endpoint (e.g. `https://collector.example.com/v1/logs`). Required; validated at plugin load. */ + /** Full logs endpoint (e.g. `https://collector.example.com/v1/logs`). Required outside `DISABLED`; validated at load. */ url?: string } /** @@ -57,13 +73,14 @@ export interface Config { /** * Schemastery validator for {@link Config}; cordis runs it before the plugin - * starts. Shape-level only — the load-bearing `exporter.url` check lives in - * the constructor so its error message names the field. Both slots are opaque - * passthroughs: the SDK owns their shapes and validates its own options; - * re-declaring them field-by-field here would violate the boundary axiom - * (and silently drop every field not re-declared). + * starts. Shape-level only — the mode-dependent `exporter.url` check lives in + * the constructor so its error message names the field. Both SDK slots are + * opaque passthroughs: the SDK owns their shapes and validates its own + * options; re-declaring them field-by-field here would violate the boundary + * axiom (and silently drop every field not re-declared). */ export const Config: z = z.object({ + mode: z.union(TELEMETRY_MODES).default('FULL'), exporter: z.any(), processor: z.any(), }) @@ -76,22 +93,32 @@ const SEVERITY: Record { + if (event.type === 'feedback/record') ctx.logger.warn(DISABLED_FEEDBACK_WARNING) + }) + return + } + const url = config.exporter?.url if (url === undefined || url.length === 0) { throw new Error('session-telemetry-otel: exporter.url is required (the full OTLP logs endpoint)') @@ -134,16 +161,26 @@ export class TelemetryOtel extends Telemetry { }) this.ledger = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel', version) this.ops = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel/ops', version) - new TelemetryCoordinator(ctx, this) + const delivery: TelemetryDelivery = mode === 'FULL' ? 'immediate' : 'held' + const coordinator = new TelemetryCoordinator(ctx, this, delivery) + if (mode === 'FEEDBACK_ONLY') { + // The coordinator listener is registered first, so a feedback event + // enters the held prefix before this listener releases that exact prefix. + ctx.on('session/event', (session, event) => { + if (event.type === 'feedback/record') coordinator.release(session) + }) + } } /** * Map one seam record onto the SDK logger for its channel — a synchronous - * enqueue into the batch processor's queue. + * enqueue into the batch processor's queue. Direct calls are no-ops in + * `DISABLED`, where no coordinator or SDK pipeline exists. * @param record - the logical record handed over by the coordinator. */ emit(record: TelemetryRecord): void { const logger = record.channel === 'ops' ? this.ops : this.ledger + if (logger === undefined) return logger.emit({ timestamp: record.time, observedTimestamp: record.time, @@ -167,14 +204,15 @@ export class TelemetryOtel extends Telemetry { /** * Delegate disposal to the SDK's shutdown contract: drain the queue and * quiesce. With no concurrent `forceFlush()` in the process (see above), - * shutdown's internal drain is complete — everything emitted before this - * call, including the coordinator's dispose-time `shutdown` markers, is - * exported before the exporter closes. Awaited (and error-contained) by - * the coordinator's disposer. + * shutdown's internal drain is complete — everything handed to the SDK + * before this call is exported before the exporter closes. In `FULL`, that + * includes dispose-time `shutdown` markers; held suffixes never reach the + * SDK. Awaited (and error-contained) by the coordinator's disposer. A + * disabled backend resolves immediately. * @returns resolves when the SDK pipeline has quiesced. */ shutdown(): Promise { - return this.provider.shutdown() + return this.provider === undefined ? Promise.resolve() : this.provider.shutdown() } } diff --git a/packages/telemetry/session-telemetry-otel/src/invariant.ts b/packages/telemetry/session-telemetry-otel/src/invariant.ts index 075e5cc193..030b7ce670 100644 --- a/packages/telemetry/session-telemetry-otel/src/invariant.ts +++ b/packages/telemetry/session-telemetry-otel/src/invariant.ts @@ -15,10 +15,9 @@ export const name = 'session-telemetry-otel-invariant' export const inject = ['invariants'] /** - * No runtime invariant: the backend forwards seam records into the OTel SDK's - * in-process pipeline and appends nothing to any session; its only observable - * effects (batching, export) happen inside the SDK past the seam's boundary - * axiom, out of reach of an independent companion. + * No runtime invariant: mode selection changes capture handoff, SDK setup, and + * local diagnostics without mutating session or service state an independent + * companion can compare. Export remains inside the SDK past the seam boundary. */ const install: InvariantInstaller = () => {} diff --git a/packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts b/packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts index 8f16662614..e07e05fed9 100644 --- a/packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts +++ b/packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts @@ -40,6 +40,11 @@ interface OtlpCapture { }[] } +interface FixtureOutput { + captures: OtlpCapture[] + logContent: string +} + async function jsonlFiles(dir: string): Promise { const entries = await readdir(dir, { withFileTypes: true }) const paths = await Promise.all(entries.map(async (entry) => { @@ -50,10 +55,29 @@ async function jsonlFiles(dir: string): Promise { return paths.flat() } +async function readFixtureOutput(cwd: string): Promise { + const captures = JSON.parse(await readFile(join(cwd, 'otlp-captures.json'), 'utf8')) as OtlpCapture[] + const logs = await jsonlFiles(join(cwd, '.sessions')) + expect(logs).toHaveLength(1) + return { captures, logContent: await readFile(logs[0] as string, 'utf8') } +} + +function allRecords(captures: OtlpCapture[]) { + return captures.flatMap(capture => capture.resourceLogs.flatMap(resource => + resource.scopeLogs.flatMap(scoped => scoped.logRecords.map(record => ({ scope: scoped.scope.name, record }))))) +} + +function eventTypes(captures: OtlpCapture[]): string[] { + return allRecords(captures).flatMap(({ record }) => + record.attributes?.flatMap(attribute => + attribute.key === 'event.type' && typeof attribute.value['stringValue'] === 'string' + ? [attribute.value['stringValue']] + : []) ?? []) +} + describe('session-telemetry-otel through a real headless cordis.yml', () => { it('exports redacted ledger records to the collector while the canonical log keeps the secret', async () => { - let captures: OtlpCapture[] = [] - let logContent = '' + let output!: FixtureOutput const { stderr } = await runLoaderSmoke({ label: 'session-telemetry-otel loader smoke', tempDirPrefix: 'telemetry-otel-e2e-', @@ -61,39 +85,70 @@ describe('session-telemetry-otel through a real headless cordis.yml', () => { libBinScript: driver, configPath, tsconfigPath: repoTsconfig, - inspect: async (cwd) => { - captures = JSON.parse(await readFile(join(cwd, 'otlp-captures.json'), 'utf8')) as OtlpCapture[] - const logs = await jsonlFiles(join(cwd, '.sessions')) - expect(logs).toHaveLength(1) - logContent = await readFile(logs[0] as string, 'utf8') - }, + inspect: async (cwd) => { output = await readFixtureOutput(cwd) }, }) expect(stderr).not.toContain('UNHANDLED') - const records = captures.flatMap(capture => capture.resourceLogs.flatMap(resource => - resource.scopeLogs.flatMap(scoped => scoped.logRecords.map(record => ({ scope: scoped.scope.name, record }))))) + const records = allRecords(output.captures) expect(records.length).toBeGreaterThan(0) - const eventTypes = records.flatMap(({ record }) => - record.attributes?.flatMap(attribute => - attribute.key === 'event.type' && typeof attribute.value['stringValue'] === 'string' - ? [attribute.value['stringValue']] - : []) ?? []) + const types = eventTypes(output.captures) for (const expected of ['turn/start', 'user/message', 'tool/call', 'tool/result', 'assistant/message', 'turn/end']) { - expect(eventTypes, expected).toContain(expected) + expect(types, expected).toContain(expected) } expect(records.some(({ scope }) => scope.endsWith('/ops'))).toBe(true) // The deployment-mounted rule on the wire: the fixture credential never // leaves the process, its surrounding prose does, and the placeholder // marks the spot — the seam itself ships no rules. - const wire = JSON.stringify(captures) + const wire = JSON.stringify(output.captures) expect(wire).not.toContain(FIXTURE_SECRET) expect(wire).toContain(FIXTURE_PLACEHOLDER) expect(wire).toContain('prove telemetry with key') // The canonical session log is never rewritten. - expect(logContent).toContain(FIXTURE_SECRET) - expect(logContent).not.toContain(FIXTURE_PLACEHOLDER) + expect(output.logContent).toContain(FIXTURE_SECRET) + expect(output.logContent).not.toContain(FIXTURE_PLACEHOLDER) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + + it('exports only prefixes ending in feedback under feedback-only mode', async () => { + let output!: FixtureOutput + const { stderr } = await runLoaderSmoke({ + label: 'session-telemetry-otel feedback-only loader smoke', + tempDirPrefix: 'telemetry-otel-feedback-e2e-', + binScript: driver, + libBinScript: driver, + configPath, + tsconfigPath: repoTsconfig, + env: { DSH_TELEMETRY_E2E_MODE: 'FEEDBACK_ONLY' }, + inspect: async (cwd) => { output = await readFixtureOutput(cwd) }, + }) + expect(stderr).not.toContain('UNHANDLED') + + const wire = JSON.stringify(output.captures) + expect(eventTypes(output.captures)).toContain('feedback/record') + expect(wire).toContain('fixture feedback') + expect(wire).toContain('prove telemetry with key') + expect(wire).not.toContain('post-feedback private suffix') + expect(output.logContent).toContain('post-feedback private suffix') + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + + it('keeps disabled feedback local and prints the stable warning', async () => { + let output!: FixtureOutput + const { stdout } = await runLoaderSmoke({ + label: 'session-telemetry-otel disabled loader smoke', + tempDirPrefix: 'telemetry-otel-disabled-e2e-', + binScript: driver, + libBinScript: driver, + configPath, + tsconfigPath: repoTsconfig, + env: { DSH_TELEMETRY_E2E_MODE: 'DISABLED' }, + inspect: async (cwd) => { output = await readFixtureOutput(cwd) }, + }) + + expect(output.captures).toEqual([]) + expect(output.logContent).toContain('fixture feedback') + expect(stdout.match(/session telemetry is DISABLED; nothing will be shared and this feedback remains local/)?.[0]) + .toMatchInlineSnapshot('"session telemetry is DISABLED; nothing will be shared and this feedback remains local"') }, LOADER_SMOKE_TEST_TIMEOUT_MS) }) diff --git a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts index cccb90ed43..18c466f7aa 100644 --- a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts +++ b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts @@ -5,12 +5,13 @@ * for the default-exported Service class. */ -import { afterEach, describe, expect, it } from 'vitest' +import { afterEach, describe, expect, it, vi } from 'vitest' import { createServer, type Server } from 'node:http' import { once } from 'node:events' import { gunzipSync } from 'node:zlib' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' +import { recordFeedback } from '@deepseek-ai/dsh-command-feedback' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import TelemetryOtel, { Config } from '../src/index.ts' @@ -30,6 +31,7 @@ interface OtlpLogsRequest { severityNumber: number severityText: string attributes?: { key: string; value: Record }[] + body?: unknown }[] }[] }[] @@ -88,6 +90,14 @@ function allRecords(captures: Capture[]) { s.logRecords.map(record => ({ scope: s.scope.name, record }))))) } +function eventTypes(captures: Capture[]): string[] { + return allRecords(captures).flatMap(({ record }) => + record.attributes?.flatMap(attribute => + attribute.key === 'event.type' && typeof attribute.value['stringValue'] === 'string' + ? [attribute.value['stringValue']] + : []) ?? []) +} + describe('TelemetryOtel wire', () => { it('ships session records and the ops shutdown marker through the real SDK pipeline', async () => { const { url, captures } = await mockCollector() @@ -195,6 +205,82 @@ describe('TelemetryOtel wire', () => { r.record.attributes?.some(a => a.key === 'event.type' && a.value.stringValue === 'turn/start')) expect(start?.record.severityNumber).toBe(13) }) + + it('holds each session suffix until the next feedback event', async () => { + const { url, captures } = await mockCollector() + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(TelemetryOtel, { + mode: 'FEEDBACK_ONLY', + exporter: { url }, + }) + const session = ctx.sessions.create(SessionId('feedback-only'), { meta: {} }) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + recordFeedback(session, 'first report') + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + recordFeedback(session, 'second report') + session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) + await fiber.dispose() + + const types = allRecords(captures).flatMap(({ record }) => + record.attributes?.flatMap(attribute => + attribute.key === 'event.type' ? [attribute.value.stringValue] : []) ?? []) + expect(types).toEqual(['turn/start', 'feedback/record', 'turn/end', 'feedback/record']) + expect(JSON.stringify(captures)).toContain('first report') + expect(JSON.stringify(captures)).toContain('second report') + expect(allRecords(captures).some(({ scope }) => scope.endsWith('/ops'))).toBe(false) + }) + + it('sends no request when feedback-only mode ends without feedback', async () => { + const { url, captures } = await mockCollector() + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(TelemetryOtel, { + mode: 'FEEDBACK_ONLY', + exporter: { url }, + }) + const session = ctx.sessions.create(SessionId('no-feedback'), { meta: {} }) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await fiber.dispose() + expect(captures).toEqual([]) + }) + + it('boots disabled without exporter config and warns when feedback stays local', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) + const fiber = await ctx.plugin(TelemetryOtel, { mode: 'DISABLED' }) + const session = ctx.sessions.create(SessionId('disabled'), { meta: {} }) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + recordFeedback(session, 'local report') + + expect(warn).toHaveBeenCalledWith( + 'session telemetry is DISABLED; nothing will be shared and this feedback remains local', + ) + ctx.telemetry.emit({ + channel: 'ledger', + time: 0, + severity: 'info', + attributes: {}, + body: null, + }) + await ctx.telemetry.shutdown() + await fiber.dispose() + recordFeedback(session, 'after disposal') + expect(warn).toHaveBeenCalledTimes(1) + }) + + it('defaults direct construction to full delivery', async () => { + const { url, captures } = await mockCollector() + const ctx = new Context() + await ctx.plugin(SessionStore) + new TelemetryOtel(ctx, { exporter: { url } }) + const session = ctx.sessions.create(SessionId('direct-default'), { meta: {} }) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await ctx.fiber.dispose() + + expect(eventTypes(captures)).toContain('turn/start') + }) }) describe('TelemetryOtel config fails loud', () => { @@ -203,6 +289,8 @@ describe('TelemetryOtel config fails loud', () => { [{ exporter: { url: '' } }, /exporter\.url is required/], [{ exporter: { url: 'not a url' } }, /not a valid URL/], [{ exporter: { url: 'ftp://collector' } }, /must be http\(s\)/], + [{ mode: 'FEEDBACK_ONLY' }, /exporter\.url is required/], + [{ mode: 'INVALID' }, /INVALID/], // The SDK accepts a non-positive batch size but its shutdown drain then // splices empty batches forever — dispose would hang, so reject at load. [{ exporter: { url: 'http://c/v1/logs' }, processor: { maxExportBatchSize: 0 } }, /maxExportBatchSize/], diff --git a/packages/telemetry/session-telemetry-otel/tsconfig.json b/packages/telemetry/session-telemetry-otel/tsconfig.json index 9512133cf7..4ba93f9eb1 100644 --- a/packages/telemetry/session-telemetry-otel/tsconfig.json +++ b/packages/telemetry/session-telemetry-otel/tsconfig.json @@ -20,6 +20,9 @@ { "path": "../../core/session" }, + { + "path": "../../feedback/command-feedback" + }, { "path": "../../llm/llm" }, diff --git a/packages/telemetry/session-telemetry/README.i18n.yaml b/packages/telemetry/session-telemetry/README.i18n.yaml index 18f6751424..da3a62e2fd 100644 --- a/packages/telemetry/session-telemetry/README.i18n.yaml +++ b/packages/telemetry/session-telemetry/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/telemetry/session-telemetry/README.md -README.md: 272c9abe78849be3d2bba2c54cd7e25bcbe2d4c2 -README.zh.md: e6f077c1d12d00e746147908560d05381fde11c3 +README.md: d38433a728c699c7fb3cc0512bb6a2d977dd4cc6 +README.zh.md: 3a86b01321fc7dfd33d39530ee7fa38a6ee1f2dc diff --git a/packages/telemetry/session-telemetry/README.md b/packages/telemetry/session-telemetry/README.md index 272c9abe78..d38433a728 100644 --- a/packages/telemetry/session-telemetry/README.md +++ b/packages/telemetry/session-telemetry/README.md @@ -2,23 +2,23 @@ English | [中文](README.zh.md) -The telemetry seam: the CAPTURE side of session-event reporting, behind a backend contract any reporting SDK satisfies with zero bending. The boundary axiom that shapes everything here: **this package's aspect ends at `emit()`** — batching, retry, queueing, and loss policy belong to the backend's SDK and are neither specified nor wrapped. Rationale and rejected alternatives: [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md). +The telemetry seam: the capture side of session-event reporting, behind a backend contract any reporting SDK satisfies with zero bending. Capture can hand each redacted record over immediately or hold a per-session prefix for an explicit release. The boundary axiom that shapes everything here: **this package's aspect ends at `emit()`** — batching, retry, queueing, and loss policy belong to the backend's SDK and are neither specified nor wrapped. Rationale and rejected alternatives: [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md) and [feedback-gated delivery](../../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md). ## The backend contract -`TelemetryBackend` is three members: `emit(record)` (MUST be a non-blocking enqueue — it runs synchronously on the `session/event` hot path), optional `flush()` (a turn-boundary hint, fire-and-forget; most backends leave it unimplemented and let their SDK's batching cadence govern export timing — an implementer owns the interaction between concurrent flushes and `shutdown()`'s drain), and `shutdown()` (the lifecycle forward: drain-and-quiesce, awaited at dispose). `Telemetry` is its service-registered form under the `telemetry` context key — one implementation per context, duplicate load throws. A backend composes `TelemetryCoordinator` in its constructor. +`TelemetryBackend` is three members: `emit(record)` (MUST be a non-blocking enqueue — it runs synchronously on the `session/event` hot path, either at capture or held-prefix release), optional `flush()` (a turn-boundary hint, fire-and-forget; most backends leave it unimplemented and let their SDK's batching cadence govern export timing — an implementer owns the interaction between concurrent flushes and `shutdown()`'s drain), and `shutdown()` (the lifecycle forward: drain-and-quiesce, awaited at dispose). `Telemetry` is its service-registered form under the `telemetry` context key — one implementation per context, duplicate load throws. A backend composes `TelemetryCoordinator` with `immediate` delivery or `held` delivery and calls `release(session)` at its owning trigger. ## Capture points -The coordinator registers, all through the composing fiber's effects: `session/created` (adopt: record the header, read the log back through the projection from the construction boundary — constructor seeds from fork/resume never re-emit on the firehose and never re-export), `session/event` (project, deep-copy, redact, hand off; zero I/O), `session/flush` (forward the optional `flush()` hint and return void — the loop's awaited parallel must never wait on telemetry), `session/disposed` (emit the session's `shutdown` operational record at its own termination edge — where receivers key crash detection — then retire it, so a long-lived backend neither retains closed sessions nor re-marks them at unload), `agent/error` (the one live-bus relay; the session event vocabulary intentionally has no operational-error record), a dispose effect (mark each session still alive at teardown, then await the backend's `shutdown()`; failures warn instead of throwing), and an adoption sweep of `ctx.sessions.list()` (a hot reload does not replay `session/created`). +The coordinator registers, all through the composing fiber's effects: `session/created` (adopt: record the header, read the log back through the projection from the construction boundary — constructor seeds from fork/resume never re-emit on the firehose and never re-export), `session/event` (project, deep-copy, redact, then hand off or hold; zero I/O), `session/flush` (forward the optional `flush()` hint and return void — the loop's awaited parallel must never wait on telemetry), `session/disposed` (capture the session's `shutdown` operational record at its termination edge, then retire it), `agent/error` (the one live-bus relay; the session event vocabulary intentionally has no operational-error record), a dispose effect (capture shutdown for each still-live session, then await the backend's `shutdown()`; failures warn instead of throwing), and an adoption sweep of `ctx.sessions.list()` (a hot reload does not replay `session/created`). Immediate delivery hands lifecycle records over; held delivery leaves any suffix after the last release local, including its later shutdown marker. ## The redact waterfall -Every record passes the `telemetry/record` waterfall between projection and `emit()` — the seam's scrubbing extension point. The seam ships NO rules of its own: the innermost `next()` passes the record through unchanged, so with no listener mounted records reach the backend exactly as captured, and exported data is precisely as clean as the rules a deployment mounts. Listeners stack by transforming `next()`'s return value; returning without `next()` replaces everything beneath, and a throwing listener withholds that one record fail-closed inside the coordinator's containment. Redaction applies to the exported copy only; the canonical session log is never rewritten. +Every record passes the `telemetry/record` waterfall immediately after projection — the seam's scrubbing extension point. The seam ships NO rules of its own: the innermost `next()` passes the record through unchanged, so with no listener mounted records reach the backend exactly as captured, and exported data is precisely as clean as the rules a deployment mounts. Listeners stack by transforming `next()`'s return value; returning without `next()` replaces everything beneath, and a throwing listener withholds that one record fail-closed inside the coordinator's containment. Held delivery stores only the waterfall result, so later policy removal cannot expose the original capture. Redaction applies to the outbound copy only; the canonical session log is never rewritten. ## The handoff cursor -A module-scope `WeakMap` marks the highest seq HANDED OFF (not delivered) per session, advanced at emit time. It survives reloads that do not re-evaluate this module — config re-applies and backend source reloads, which is where iteration happens; that asymmetry is why the cursor lives in the seam. On re-adoption the coordinator re-hands only events past the cursor (events at or below it still rebuild the chunk-projection state); a missing cursor safely degrades to a re-hand from the session's construction boundary (`Session.firstLiveSeq` — seq 0 for a session born in this process), absorbed by receiver-side dedupe on `(session.id, event.seq)`. Constructor seeds never re-export: a resumed session's history shipped from the previous process under the same id, and a fork's inherited prefix lives in the parent's stream (receivers stitch on `session.parent_id` + `session.seed_length`). The accepted cost, consistent with at-most-once delivery: a resume does not backfill records a previous process failed to deliver — a deployment with a backfill requirement needs the deferred outbox, not replay. This is a deliberate, narrow exception to the registrations-are-effects discipline: entries die with their sessions, the value is a monotonic watermark, and losing it is never an error. +A module-scope `WeakMap` marks the highest seq HANDED OFF (not delivered) per session. Immediate delivery advances it at capture; held delivery advances it only when `release(session)` hands that record to the backend. An unreleased prefix therefore survives a coordinator reload through deterministic re-adoption instead of disappearing with its in-memory copy. On re-adoption the coordinator re-hands only events past the cursor (events at or below it still rebuild the chunk-projection state); a missing cursor safely degrades to a re-hand from the session's construction boundary (`Session.firstLiveSeq` — seq 0 for a session born in this process), absorbed by receiver-side dedupe on `(session.id, event.seq)`. Constructor seeds never re-export: a resumed session's history shipped from the previous process under the same id, and a fork's inherited prefix lives in the parent's stream (receivers stitch on `session.parent_id` + `session.seed_length`). The accepted cost, consistent with at-most-once delivery: a resume does not backfill records a previous process failed to deliver — a deployment with a backfill requirement needs the deferred outbox, not replay. This is a deliberate, narrow exception to the registrations-are-effects discipline: entries die with their sessions, the value is a monotonic watermark, and losing it is never an error. ## The fixed chunk projection @@ -40,3 +40,4 @@ None; this package neither assembles nor sends a provider request. - **Best-effort delivery** — the cursor marks handed-off, not delivered; a session torn down inside a reload window cannot be re-adopted; whatever sits in a backend queue at crash time is lost. A durable outbox (spool, per-sink cursors, at-least-once) is deferred until a deployment states a crash-loss requirement — see [the revival Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md). - **No built-in redaction rules** — with no `telemetry/record` listener mounted, records leave the process exactly as captured, including any credentials embedded in file contents or command output; a deployment exporting to a shared collector owns its rule set. +- **Held prefixes duplicate memory** — held delivery retains one deep-copied, redacted record per projected event until release or session collection. It adds no durable outbox and intentionally trades memory for a simple no-upload-before-trigger boundary. diff --git a/packages/telemetry/session-telemetry/README.zh.md b/packages/telemetry/session-telemetry/README.zh.md index e6f077c1d1..3a86b01321 100644 --- a/packages/telemetry/session-telemetry/README.zh.md +++ b/packages/telemetry/session-telemetry/README.zh.md @@ -2,23 +2,23 @@ [English](README.md) | 中文 -遥测（telemetry）seam：会话事件上报的捕获侧，隔在一个后端契约之后，任何上报 SDK 都无需变形即可满足该契约。塑造本包（package）一切设计的边界公理：**本包的职责止于 `emit()`**。批处理、重试、排队与丢失策略都属于后端自身的 SDK，本包既不为其立规，也不做包装。设计依据与被否决的替代方案见[复活 Agent Note（agent 决策记录）](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)。 +遥测（telemetry）seam：会话事件上报的捕获侧，隔在一个后端契约之后，任何上报 SDK 都无需变形即可满足该契约。捕获侧可立即交接每条已脱敏记录，也可按会话暂存一个前缀，等待显式释放。塑造本包（package）一切设计的边界公理：**本包的职责止于 `emit()`**。批处理、重试、排队与丢失策略都属于后端自身的 SDK，本包既不为其立规，也不做包装。设计依据与被否决的替代方案见[复活 Agent Note（agent 决策记录）](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)与[反馈门控投递](../../../.agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md)。 ## 后端契约 -`TelemetryBackend` 只有三个成员：`emit(record)`（必须是非阻塞入队；它在 `session/event` 热路径上同步执行）、可选的 `flush()`（轮次边界提示，触发后不等待结果；多数后端不实现它，而由其 SDK 的批处理节奏决定导出时机；并发 flush 与 `shutdown()` 的排空之间的交互由实现方自行负责）、以及 `shutdown()`（生命周期转发点：排空并完全停稳，在 dispose（资源释放）时被等待）。`Telemetry` 是它注册在 `telemetry` 上下文键下的服务形态：每个上下文只允许一个实现，重复加载会抛出异常。后端在其构造函数中组合 `TelemetryCoordinator`。 +`TelemetryBackend` 只有三个成员：`emit(record)`（必须是非阻塞入队；它会在捕获或暂存前缀释放时，于 `session/event` 热路径上同步执行）、可选的 `flush()`（轮次边界提示，触发后不等待结果；多数后端不实现它，而由其 SDK 的批处理节奏决定导出时机；并发 flush 与 `shutdown()` 的排空之间的交互由实现方自行负责）、以及 `shutdown()`（生命周期转发点：排空并完全停稳，在 dispose（资源释放）时被等待）。`Telemetry` 是它注册在 `telemetry` 上下文键下的服务形态：每个上下文只允许一个实现，重复加载会抛出异常。后端以 `immediate` 或 `held` 投递模式组合 `TelemetryCoordinator`，并在自身所属的触发器中调用 `release(session)`。 ## 捕获点 -协调器的全部注册都经由组合方 fiber 的 effect 完成：`session/created`（收养：记录 header，并经投影从构造边界起回读日志；来自 fork 或恢复的构造函数种子绝不会在 firehose 上再次发出，也绝不会再次导出）、`session/event`（投影、深拷贝、脱敏、交接；零 I/O）、`session/flush`（转发可选的 `flush()` 提示并返回 void；循环所等待的并行任务绝不能等待遥测）、`session/disposed`（在会话自身的终止边缘发出该会话的 `shutdown` 运维记录，接收端正是在这个边缘锚定崩溃检测；随后将该会话退役，因此长生命周期的后端既不会保留已关闭的会话，也不会在卸载时再次标记它们）、`agent/error`（唯一的实时总线转发；会话事件词汇有意不包含运维错误记录）、一个 dispose effect（拆卸时先标记每个仍存活的会话，再等待后端的 `shutdown()`；失败只发出警告而不抛出），以及对 `ctx.sessions.list()` 的收养扫描（热重载不会重放 `session/created`）。 +协调器的全部注册都经由组合方 fiber 的 effect 完成：`session/created`（收养：记录 header，并经投影从构造边界起回读日志；来自 fork 或恢复的构造函数种子绝不会在 firehose 上再次发出，也绝不会再次导出）、`session/event`（投影、深拷贝、脱敏，再交接或暂存；零 I/O）、`session/flush`（转发可选的 `flush()` 提示并返回 void；循环所等待的并行任务绝不能等待遥测）、`session/disposed`（在会话自身的终止边缘捕获该会话的 `shutdown` 运维记录，然后将其退役）、`agent/error`（唯一的实时总线转发；会话事件词汇有意不包含运维错误记录）、一个 dispose effect（捕获每个仍存活会话的 shutdown，再等待后端的 `shutdown()`；失败只发出警告而不抛出），以及对 `ctx.sessions.list()` 的收养扫描（热重载不会重放 `session/created`）。即时投递会交接生命周期记录；暂存投递会将上次释放后的任何后缀留在本地，包括随后的 shutdown 标记。 ## 脱敏 waterfall（瀑布式事件） -每条记录在投影与 `emit()` 之间都要经过 `telemetry/record` waterfall，这是该 seam 的脱敏扩展点。seam 自身不带任何规则：最内层的 `next()` 原样透传记录，因此未挂载监听器时，记录以捕获时的原样到达后端；导出数据能干净到什么程度，恰恰取决于部署方挂载了什么规则。监听器通过变换 `next()` 的返回值来堆叠；不调用 `next()` 就返回，即替换其下方的全部逻辑；抛出异常的监听器会在协调器的隔离范围内以 fail-closed 方式拦下这一条记录。脱敏只作用于导出副本；权威会话日志永不改写。 +每条记录在投影后立即经过 `telemetry/record` waterfall，这是该 seam 的脱敏扩展点。seam 自身不带任何规则：最内层的 `next()` 原样透传记录，因此未挂载监听器时，记录以捕获时的原样到达后端；导出数据能干净到什么程度，恰恰取决于部署方挂载了什么规则。监听器通过变换 `next()` 的返回值来堆叠；不调用 `next()` 就返回，即替换其下方的全部逻辑；抛出异常的监听器会在协调器的隔离范围内以 fail-closed 方式拦下这一条记录。暂存投递只保留 waterfall 的结果，因此后续移除策略也无法暴露捕获时的原始内容。脱敏只作用于外发副本；权威会话日志永不改写。 ## handoff 游标 -一个模块作用域的 `WeakMap` 记录每个会话已交接（而非已投递）的最高 seq，在 emit 时推进。游标在不重新求值本模块的重载（配置重新应用、后端源码重载）中存活，而迭代恰恰发生在这类重载中；这种不对称正是游标放在 seam 一侧的原因。重新收养时，协调器只重新交接游标之后的事件（游标及其之前的事件仍用于重建分片投影状态）；游标缺失时安全退化为从会话构造边界起的重新交接（`Session.firstLiveSeq`，对在本进程中诞生的会话即 seq 0），由接收端基于 `(session.id, event.seq)` 的去重吸收。构造函数种子绝不会再次导出：恢复会话的历史已由上一个进程以同一 id 发出，fork 继承的前缀则位于父会话的流中（接收端基于 `session.parent_id` + `session.seed_length` 拼接）。由此接受的代价与至多一次（at-most-once）投递一致：恢复不会回填上一个进程未能投递的记录；有回填要求的部署需要的是已推迟的 outbox，而不是回放。这是对「注册即 effect」纪律的一次有意且范围极窄的例外：条目随其会话消亡，值是单调水位线，丢失它绝不是错误。 +一个模块作用域的 `WeakMap` 记录每个会话已交接（而非已投递）的最高 seq。即时投递在捕获时推进游标；暂存投递只有在 `release(session)` 将记录交给后端时才推进游标。因此，重建协调器后会通过确定性重新收养恢复未释放的前缀，而不会随其内存副本一同消失。重新收养时，协调器只重新交接游标之后的事件（游标及其之前的事件仍用于重建分片投影状态）；游标缺失时安全退化为从会话构造边界起的重新交接（`Session.firstLiveSeq`，对在本进程中诞生的会话即 seq 0），由接收端基于 `(session.id, event.seq)` 的去重吸收。构造函数种子绝不会再次导出：恢复会话的历史已由上一个进程以同一 id 发出，fork 继承的前缀则位于父会话的流中（接收端基于 `session.parent_id` + `session.seed_length` 拼接）。由此接受的代价与至多一次（at-most-once）投递一致：恢复不会回填上一个进程未能投递的记录；有回填要求的部署需要的是已推迟的 outbox，而不是回放。这是对「注册即 effect」纪律的一次有意且范围极窄的例外：条目随其会话消亡，值是单调水位线，丢失它绝不是错误。 ## 固定分片投影 @@ -40,3 +40,4 @@ - **尽力而为的投递**：游标标记的是已交接而非已投递；在重载窗口内被拆除的会话无法重新收养；崩溃时留在后端队列中的内容会丢失。持久化 outbox（spool、每 sink 游标、at-least-once）推迟到有部署方提出明确的崩溃丢失要求时再实现；见[复活 Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md)。 - **不内置脱敏规则**：未挂载 `telemetry/record` 监听器时，记录以捕获时的原样离开进程，包括文件内容或命令输出中内嵌的任何凭据；向共享 collector 导出的部署方自行负责其规则集。 +- **暂存前缀会重复占用内存**：暂存投递会为每个已投影事件保留一份深拷贝且已脱敏的记录，直到释放或回收会话。它不增加持久化 outbox，而是有意以内存换取简单的「触发前不上传」边界。 diff --git a/packages/telemetry/session-telemetry/src/coordinator.ts b/packages/telemetry/session-telemetry/src/coordinator.ts index 0bebbcc561..710e9b81f9 100644 --- a/packages/telemetry/session-telemetry/src/coordinator.ts +++ b/packages/telemetry/session-telemetry/src/coordinator.ts @@ -3,10 +3,11 @@ * firehose plus the one live-bus relay (`agent/error`), applies the fixed * chunk projection, builds logical records, runs each through the * `telemetry/record` waterfall (deployment-mounted redaction rules; - * pass-through when none), and hands the result to the backend — synchronously, with every - * handler self-contained so a failing backend can never starve other - * subscribers (cordis `emit` is stop-on-throw) or touch the agent loop. - * Composed by a backend in its constructor. + * pass-through when none), then hands the result to the backend immediately + * or holds it for explicit release. Every synchronous handler is + * self-contained so a failing backend can never starve other subscribers + * (cordis `emit` is stop-on-throw) or touch the agent loop. Composed by a + * backend in its constructor. * * @module @deepseek-ai/dsh-session-telemetry/coordinator */ @@ -16,6 +17,16 @@ import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import type { Agent } from '@deepseek-ai/dsh-agent' import type { TelemetryBackend, TelemetryRecord, TelemetrySeverity } from './index.ts' +/** Whether capture hands records over immediately or holds them for an explicit release. */ +export type TelemetryDelivery = 'immediate' | 'held' + +/** One redacted record waiting at the capture boundary. */ +interface PendingRecord { + readonly record: TelemetryRecord + /** Ledger cursor advanced only after the backend accepts this record. */ + readonly seq?: number +} + /** * The handoff cursor: per session, the highest `seq` handed to a backend. * Deliberately MODULE-scope ambient state — a narrow, documented exception @@ -35,14 +46,13 @@ const handoffCursor = new WeakMap() * Registers the persistence-coordinator listener set plus the `agent/error` * relay, all through `ctx.effect()`/`ctx.on()` on the composing fiber, and * sweeps already-live sessions (a hot reload does not replay - * `session/created`). A `session/disposed` emits the session's `shutdown` - * operational record — the marker rides the session's own termination edge, - * where receivers key crash detection — and retires it from the adopted set, - * so a long-lived backend neither retains closed sessions (and their frozen - * event logs) nor re-marks them at unload. Disposal marks the sessions still - * alive at teardown (their own edge would fire unobserved) and then awaits - * the backend's `shutdown()`; a failure there warns instead of throwing — - * best-effort reporting must not fail application teardown. + * `session/created`). A `session/disposed` captures the session's `shutdown` + * operational record at its own termination edge and retires it from the + * adopted set. Immediate delivery hands that marker over; held delivery keeps + * it local without another explicit release. Disposal captures the same + * marker for sessions still alive, then awaits the backend's `shutdown()`; a + * failure there warns instead of throwing — best-effort reporting must not + * fail application teardown. */ export class TelemetryCoordinator { /** @@ -53,28 +63,30 @@ export class TelemetryCoordinator { private readonly adopted = new Set() /** Per session, the `turn:step` keys whose first chunk already shipped; rebuilt from the log on re-adoption. */ private readonly chunkSeen = new WeakMap>() + /** Redacted records retained until {@link release}; weak keys do not extend session lifetime. */ + private readonly held = new WeakMap() /** * @param ctx - the composing backend's context; listeners bind to its fiber. * @param backend - the backend receiving records; owned elsewhere, never disposed here beyond `shutdown()` forwarding. + * @param delivery - immediate handoff, or held delivery released explicitly per session. */ constructor( private readonly ctx: Context, private readonly backend: TelemetryBackend, + private readonly delivery: TelemetryDelivery = 'immediate', ) { ctx.on('session/created', (session) => { this.adopt(session) }) - // The session's own termination edge: emit the shutdown marker HERE — - // receivers classify a session with activity and no marker as crashed, - // so a normally closed session in a long-running host must get its - // marker at disposal, not never. Then retire: the projection/cursor - // WeakMaps die with the Session object; only the strong adopted set - // needs the explicit release. + // Capture the shutdown marker at the session's own termination edge. + // Immediate delivery preserves crash classification; held delivery does + // not let a later lifecycle edge extend a user-released prefix. Then + // retire the only strong reference owned by this coordinator. ctx.on('session/disposed', (session) => { this.contain(() => { if (!this.adopted.delete(session)) return - this.handOff(shutdownRecord(session)) + this.submit(session, { record: this.redact(shutdownRecord(session)) }) }) }) ctx.on('session/event', (session, event) => { @@ -95,13 +107,12 @@ export class TelemetryCoordinator { }) }) ctx.effect(() => async () => { - // Sessions still adopted here are alive through a whole-application - // teardown (their own disposal edge will fire after telemetry is gone, - // unobserved) — mark them now so the receiver sees a clean stop of - // observation rather than a crash-shaped silence. + // Sessions still adopted here are alive through whole-application + // teardown, so capture the marker before the backend quiesces. Held + // delivery intentionally leaves it local without another release. for (const session of this.adopted) { this.contain(() => { - this.handOff(shutdownRecord(session)) + this.submit(session, { record: this.redact(shutdownRecord(session)) }) }) } try { @@ -115,6 +126,23 @@ export class TelemetryCoordinator { } } + /** + * Hand the records currently held for one session to the backend in capture order. + * Records captured after this call form a new held prefix. Backend failures remain + * contained per record and do not starve later records in the same release. + * @param session - session whose pending capture prefix may leave the process. + */ + release(session: Session): void { + const pending = this.held.get(session) + if (pending === undefined) return + this.held.delete(session) + for (const record of pending) { + this.contain(() => { + this.deliver(session, record) + }) + } + } + /** * Adopt a session: replay its log THROUGH the projection from the handoff * cursor, then rely on the firehose for everything after. When no cursor @@ -153,7 +181,7 @@ export class TelemetryCoordinator { } } - /** Project one event and hand it to the backend, advancing the cursor on handoff. */ + /** Project and redact one event, then submit it under the delivery policy. */ private capture(session: Session, event: SessionEvent): void { if (event.type === 'assistant/chunk') { const key = `${event.data.turn}:${event.data.step}` @@ -165,27 +193,47 @@ export class TelemetryCoordinator { if (seen.has(key)) return seen.add(key) } - this.handOff({ - channel: 'ledger', - time: event.time, - severity: severityOf(event), - attributes: identityOf(session, event), - // The live event object is mutable and the backend serializes later; - // append-time validation guarantees this clone cannot throw. - body: structuredClone(event.data), + this.submit(session, { + record: this.redact({ + channel: 'ledger', + time: event.time, + severity: severityOf(event), + attributes: identityOf(session, event), + // The live event object is mutable and the backend serializes later; + // append-time validation guarantees this clone cannot throw. + body: structuredClone(event.data), + }), + seq: event.seq, }) - handoffCursor.set(session, event.seq) } /** - * Run the `telemetry/record` waterfall over one record and hand the result - * to the backend. The innermost `next` passes the record through unchanged - * — the seam ships no rules; exported data is as clean as the listeners a - * deployment mounts. Callers run inside {@link contain}, so a throwing - * rule withholds the record instead of reaching the loop (fail-closed). + * Run the `telemetry/record` waterfall at capture time. The innermost `next` + * passes the record through unchanged — the seam ships no rules; exported + * data is as clean as the listeners a deployment mounts. Callers run inside + * {@link contain}, so a throwing rule withholds the record instead of + * reaching the loop (fail-closed). Held delivery stores only this result, so + * a later policy reload cannot expose the pre-redaction capture. */ - private handOff(record: TelemetryRecord): void { - this.backend.emit(this.ctx.waterfall('telemetry/record', record, () => record)) + private redact(record: TelemetryRecord): TelemetryRecord { + return this.ctx.waterfall('telemetry/record', record, () => record) + } + + /** Hold one redacted record or deliver it immediately under the configured policy. */ + private submit(session: Session, pending: PendingRecord): void { + if (this.delivery === 'held') { + let records = this.held.get(session) + if (records === undefined) this.held.set(session, records = []) + records.push(pending) + return + } + this.deliver(session, pending) + } + + /** Hand one redacted record to the backend, then advance its ledger cursor. */ + private deliver(session: Session, pending: PendingRecord): void { + this.backend.emit(pending.record) + if (pending.seq !== undefined) handoffCursor.set(session, pending.seq) } /** Forward the turn-end boundary to the backend's optional flush hint. */ @@ -196,19 +244,21 @@ export class TelemetryCoordinator { /** Relay one `agent/error` bus emission as an `agent-error` operational record. */ private relayAgentError(agent: Agent, turn: number, step: number, error: unknown): void { const detail = errorDetail(error) - this.handOff({ - channel: 'ops', - time: Date.now(), - severity: 'error', - attributes: { - 'telemetry.op': 'agent-error', - 'session.id': String(agent.session.id), - 'agent.id': agent.id, - 'error.name': detail.name, - turn, - step, - }, - body: detail, + this.submit(agent.session, { + record: this.redact({ + channel: 'ops', + time: Date.now(), + severity: 'error', + attributes: { + 'telemetry.op': 'agent-error', + 'session.id': String(agent.session.id), + 'agent.id': agent.id, + 'error.name': detail.name, + turn, + step, + }, + body: detail, + }), }) } diff --git a/packages/telemetry/session-telemetry/src/index.ts b/packages/telemetry/session-telemetry/src/index.ts index e7340eedd5..914ef96a95 100644 --- a/packages/telemetry/session-telemetry/src/index.ts +++ b/packages/telemetry/session-telemetry/src/index.ts @@ -3,8 +3,9 @@ * * The seam owns the CAPTURE side of session-event reporting — which records * exist (the chunk projection), what they carry (the logical record), when - * they are handed over (adoption, the per-append firehose, lifecycle - * forwarding), and the HMR handoff cursor. Everything downstream of + * they are captured (adoption, the per-append firehose, lifecycle + * forwarding), immediate versus explicitly released handoff, and the HMR + * cursor. Everything downstream of * {@link Telemetry.emit} — batching, retry, queueing, loss policy — is the * reporting SDK's territory and is deliberately not modelled here. The * design and its trade-offs are pinned in @@ -94,9 +95,10 @@ export interface TelemetryBackend { /** * Hand one record to the backend's pipeline. MUST be a non-blocking * enqueue — the coordinator calls this synchronously from the - * `session/event` hot path, so anything slower than a queue push would tax - * the agent loop. Errors thrown here are contained by the coordinator and - * logged; they never reach the loop. + * `session/event` hot path, either at capture or while releasing a held + * prefix, so anything slower than a queue push would tax the agent loop. + * Errors thrown here are contained by the coordinator and logged; they + * never reach the loop. * @param record - the logical record to report; owned by the backend after the call. */ emit(record: TelemetryRecord): void @@ -121,6 +123,9 @@ export interface TelemetryBackend { * coordinator emits its dispose-time `shutdown` markers immediately before * calling this). Awaited by the coordinator's dispose; a rejection is * logged as a warning and never fails application teardown. + * The coordinator captures dispose-time shutdown markers immediately + * before this call; immediate delivery enqueues them, while held delivery + * leaves an unreleased suffix local. * @returns resolves when the backend's pipeline has quiesced. */ shutdown(): Promise @@ -153,4 +158,4 @@ export abstract class Telemetry extends Service implements TelemetryBackend { abstract shutdown(): Promise } -export { TelemetryCoordinator } from './coordinator.ts' +export { TelemetryCoordinator, type TelemetryDelivery } from './coordinator.ts' diff --git a/packages/telemetry/session-telemetry/tests/telemetry.spec.ts b/packages/telemetry/session-telemetry/tests/telemetry.spec.ts index a449a4053d..d913e6a742 100644 --- a/packages/telemetry/session-telemetry/tests/telemetry.spec.ts +++ b/packages/telemetry/session-telemetry/tests/telemetry.spec.ts @@ -10,7 +10,12 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import SessionStore, { SessionId, type Session, type SessionEvent } from '@deepseek-ai/dsh-session' import type { Agent } from '@deepseek-ai/dsh-agent' -import { TelemetryCoordinator, type TelemetryBackend, type TelemetryRecord } from '../src/index.ts' +import { + TelemetryCoordinator, + type TelemetryBackend, + type TelemetryDelivery, + type TelemetryRecord, +} from '../src/index.ts' declare module '@deepseek-ai/dsh-session' { interface SessionEventMap { @@ -54,15 +59,21 @@ class FakeBackend implements TelemetryBackend { } } -async function setup(backend: FakeBackend = new FakeBackend()) { +async function setup( + backend: FakeBackend = new FakeBackend(), + delivery: TelemetryDelivery = 'immediate', +) { const ctx = new Context() await ctx.plugin(SessionStore) + let coordinator!: TelemetryCoordinator const fiber = await ctx.plugin({ name: 'fake-telemetry', inject: ['sessions'], - apply: (inner: Context) => void new TelemetryCoordinator(inner, backend), + apply: (inner: Context) => { + coordinator = new TelemetryCoordinator(inner, backend, delivery) + }, }) - return { ctx, backend, fiber } + return { ctx, backend, coordinator, fiber } } function liveSession(ctx: Context, id = `s-${Math.random().toString(36).slice(2)}`): Session { @@ -167,6 +178,80 @@ describe('TelemetryCoordinator capture', () => { }) }) +describe('TelemetryCoordinator held delivery', () => { + it('releases one pending prefix at a time without handing later records over early', async () => { + const { ctx, backend, coordinator } = await setup(new FakeBackend(), 'held') + const session = liveSession(ctx, 'held-prefix') + appendTurn(session) + expect(backend.records).toEqual([]) + + coordinator.release(session) + expect(backend.ledger().map(record => record.attributes['event.type'])).toEqual([ + 'turn/start', + 'user/message', + ]) + + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + expect(backend.ledger()).toHaveLength(2) + coordinator.release(session) + coordinator.release(session) + expect(backend.ledger().map(record => record.attributes['event.type'])).toEqual([ + 'turn/start', + 'user/message', + 'turn/end', + ]) + }) + + it('stores the capture-time redacted copy rather than re-running policy at release', async () => { + const { ctx, backend, coordinator } = await setup(new FakeBackend(), 'held') + const disposeRule = ctx.on('telemetry/record', (_record, next) => ({ + ...next(), + body: { scrubbed: true }, + })) + const session = liveSession(ctx, 'held-redacted') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + disposeRule() + + coordinator.release(session) + expect(backend.ledger()[0]!.body).toEqual({ scrubbed: true }) + }) + + it('contains each backend failure independently while releasing a batch', async () => { + const backend = new FakeBackend() + backend.rejectSeq = 1 + const { ctx, coordinator } = await setup(backend, 'held') + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) + const session = liveSession(ctx, 'held-failure') + appendTurn(session) + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + + coordinator.release(session) + expect(backend.ledger().map(record => record.attributes['event.seq'])).toEqual([0, 2]) + expect(warn).toHaveBeenCalled() + }) + + it('rebuilds an unreleased prefix after coordinator reload', async () => { + const first = new FakeBackend() + const { ctx, fiber } = await setup(first, 'held') + const session = liveSession(ctx, 'held-reload') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await fiber.dispose() + expect(first.records).toEqual([]) + + const second = new FakeBackend() + let coordinator!: TelemetryCoordinator + await ctx.plugin({ + name: 'fake-telemetry-after-held-reload', + inject: ['sessions'], + apply: (inner: Context) => { + coordinator = new TelemetryCoordinator(inner, second, 'held') + }, + }) + coordinator.release(session) + expect(second.ledger().map(record => record.attributes['event.seq'])).toEqual([0]) + }) +}) + describe('TelemetryCoordinator adoption', () => { it('exports an unpublished suffix without re-exporting constructor history', async () => { const backend = new FakeBackend() diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 2ecfd0e869..882d42c8d8 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -445,6 +445,9 @@ importers: '@cordisjs/plugin-include': specifier: workspace:* version: link:../vendor/include + '@cordisjs/plugin-logger-console': + specifier: workspace:* + version: link:../vendor/logger-console '@deepseek-ai/dsh-acp-demo': specifier: workspace:* version: link:../packages/examples/acp-demo @@ -466,6 +469,9 @@ importers: '@deepseek-ai/dsh-code-runtime-worker': specifier: workspace:* version: link:../packages/code-runtime/code-runtime-worker + '@deepseek-ai/dsh-command-feedback': + specifier: workspace:* + version: link:../packages/feedback/command-feedback '@deepseek-ai/dsh-compact-basic': specifier: workspace:* version: link:../packages/compact/compact-basic @@ -4810,6 +4816,9 @@ importers: '@cordisjs/plugin-loader': specifier: workspace:^ version: link:../../../vendor/loader + '@deepseek-ai/dsh-command-feedback': + specifier: workspace:^ + version: link:../../feedback/command-feedback '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants