From ccb0842cfcc23ca11a89c136761e355eb0c94741 Mon Sep 17 00:00:00 2001 From: Turtle Date: Thu, 6 Aug 2026 16:27:27 +0800 Subject: [PATCH] fix(telemetry): fail closed outside full mode --- ...feedback-gated-session-telemetry.i18n.yaml | 4 +- ...-08-05-feedback-gated-session-telemetry.md | 6 +- ...-05-feedback-gated-session-telemetry.zh.md | 6 +- docs/config-catalog.md | 2 +- .../session-telemetry-otel/README.i18n.yaml | 4 +- .../session-telemetry-otel/README.md | 2 + .../session-telemetry-otel/README.zh.md | 2 + .../session-telemetry-otel/src/index.ts | 91 +++++++++++++------ .../session-telemetry-otel/tests/otel.spec.ts | 64 ++++++++++++- 9 files changed, 139 insertions(+), 42 deletions(-) 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 index 331b2e97c6..4255886987 100644 --- 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 @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-05-feedback-gated-session-telemetry.md -2026-08-05-feedback-gated-session-telemetry.md: 00a8f23fa6bf69f10277ad0d9f2513a0df73de16 -2026-08-05-feedback-gated-session-telemetry.zh.md: 888ce48abe7a5ce2212c152730f8203f5747ef41 +2026-08-05-feedback-gated-session-telemetry.md: 7d923a7e4cf61e8d1119187564b87e4cbb2065b7 +2026-08-05-feedback-gated-session-telemetry.zh.md: 2862162c0c36e5194846c7e1c7bbc24230ce90aa 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 index 00a8f23fa6..7d923a7e4c 100644 --- 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 @@ -18,7 +18,7 @@ Session telemetry originally has one mounted behavior: every accepted record ent The generic telemetry coordinator owns `live` and `on-demand` capture. Live capture projects, clones, redacts, and hands each event to the backend on the session firehose. On-demand capture registers no continuous capture listeners; `captureSession(session, throughSeq)` reads the canonical log from the handoff cursor through an inclusive boundary, then projects, clones, redacts, and hands over that prefix. The cursor advances only for handed-over records. The [buffer-free replay decision](../simplification/2026-08-06-buffer-free-feedback-telemetry.md) owns why the on-demand path uses the canonical log instead of copied records. -The OTel feedback listener passes the feedback event's sequence to `captureSession()`. `Session.append` commits the event before publishing `session/event`, so replay includes that feedback but cannot extend past its boundary. `exporter.url` is required in `FULL` and `FEEDBACK_ONLY`; `DISABLED` does not validate or use exporter configuration. +Mode resolution is a closed, fail-before-setup check: an unknown direct-construction value fails before transport configuration is read. Only `FULL` exposes the public service's `emit()` path to the SDK pipeline. `FEEDBACK_ONLY` gives its on-demand coordinator a private backend capability; its listener passes an event to `captureSession()` only when the exact `feedback/record` object is already stored at `session.events[event.seq]`. `Session.append` commits that object before publishing `session/event`, so replay includes the feedback but cannot extend past its boundary. `DISABLED` creates neither the capability nor the SDK pipeline and does not inspect exporter configuration. ## Alternatives considered @@ -26,8 +26,10 @@ The OTel feedback listener passes the feedback event's sequence to `captureSessi **Retain capture-time redacted records until feedback.** Rejected because it duplicates an unbounded session prefix even though the canonical log already owns the events. It preserves capture-time redaction policy and operational records, but those properties do not justify the memory cost for a mode defined as uploading the session log after feedback. +**Temporarily allow public `emit()` calls during feedback replay.** Rejected because a redaction listener or another reentrant caller could enqueue an unrelated record while the flag was open. A private backend capability makes authorization structural and keeps the public service closed throughout replay. + **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` adds no telemetry-owned per-event buffer before feedback; a crash before feedback uploads nothing from that prefix. Replay applies the redaction policy mounted when feedback is recorded and excludes operational records that do not exist in the canonical log. Feedback-only streams therefore carry neither `agent-error` nor `shutdown` records, and shutdown absence is not a crash signal. Each later feedback captures the suffix accumulated since the previous boundary. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log. +`FULL` remains source- and wire-compatible with the original default. `FEEDBACK_ONLY` adds no telemetry-owned per-event buffer before feedback; direct service calls and non-canonical feedback events upload nothing, and a crash before feedback uploads nothing from that prefix. Replay applies the redaction policy mounted when feedback is recorded and excludes operational records that do not exist in the canonical log. Feedback-only streams therefore carry neither `agent-error` nor `shutdown` records, and shutdown absence is not a crash signal. Each later feedback captures the suffix accumulated since the previous boundary. `DISABLED` can omit `exporter.url`, does no reporting work, and keeps feedback only in the canonical session log. 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 index 888ce48abe..2862162c0c 100644 --- 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 @@ -18,7 +18,7 @@ Status: implemented 通用遥测协调器拥有 `live` 与 `on-demand` 捕获。实时捕获在会话 firehose 上投影、深拷贝、脱敏每个事件，并将其交给后端。按需捕获不注册持续捕获监听器；`captureSession(session, throughSeq)` 从 handoff 游标起读取权威日志，直至含边界的指定序列号，然后投影、深拷贝、脱敏并交接该前缀。游标只为已交接记录推进。[无缓冲回放决策](../simplification/2026-08-06-buffer-free-feedback-telemetry.md)说明了按需路径为何使用权威日志而非记录副本。 -OTel 反馈监听器把反馈事件的序列号传给 `captureSession()`。`Session.append` 在发布 `session/event` 前已提交该事件，因此回放会包含该反馈，但不会超过其边界。`exporter.url` 在 `FULL` 与 `FEEDBACK_ONLY` 中必填；`DISABLED` 不校验也不使用导出器配置。 +模式解析采用封闭式检查，并在设置前失败：通过直接构造传入未知值时，会在读取传输配置前失败。只有 `FULL` 向 SDK 流水线开放公共服务的 `emit()` 路径。`FEEDBACK_ONLY` 向其按需协调器提供私有后端能力；其监听器向 `captureSession()` 传递事件的唯一条件，是该事件与那个 `feedback/record` 对象身份完全相同，且该对象已存储于 `session.events[event.seq]`。`Session.append` 在发布 `session/event` 前已提交该对象，因此回放包含该反馈，但不会越过其边界。`DISABLED` 既不创建该能力，也不创建 SDK 流水线，并且不检查导出器配置。 ## 考虑过的替代方案 @@ -26,8 +26,10 @@ OTel 反馈监听器把反馈事件的序列号传给 `captureSession()`。`Sess **反馈前保留捕获时已脱敏记录。** 已否决，因为权威日志已拥有这些事件，该方案仍会复制无上限的会话前缀。它能保留捕获时的脱敏策略与运维记录，但对于一个定义为「反馈后上传会话日志」的模式，这些性质不足以证明该内存成本合理。 +**在反馈回放期间临时允许公开 `emit()` 调用。** 已否决，因为在标志开启期间，脱敏监听器或另一个可重入调用方可能将无关记录入队。私有后端能力使授权成为结构性保证，并确保公共服务在整个回放过程中保持关闭。 + **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` 在反馈前不增加遥测自有的逐事件缓冲；反馈前发生崩溃时，该前缀不上传任何内容。回放使用记录反馈时挂载的脱敏策略，并排除权威日志中不存在的运维记录。因此，仅反馈的流既不携带 `agent-error` 记录，也不携带 `shutdown` 记录，而缺少 shutdown 不是崩溃信号。每个后续反馈都会捕获从上一个边界起累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。 +`FULL` 与原有默认值保持源码及协议兼容。`FEEDBACK_ONLY` 在反馈前不增加遥测自有的逐事件缓冲；直接服务调用与非权威反馈事件均不上传任何内容，且反馈前发生崩溃时，该前缀也不上传任何内容。回放使用记录反馈时挂载的脱敏策略，并排除权威日志中不存在的运维记录。因此，仅反馈的流既不携带 `agent-error` 记录，也不携带 `shutdown` 记录，而缺少 shutdown 不是崩溃信号。每个后续反馈都会捕获从上一个边界起累积的后缀。`DISABLED` 可省略 `exporter.url`，不执行任何上报工作，并仅在权威会话日志中保留反馈。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a2f82d2bec..c386ee4e6b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1193,7 +1193,7 @@ export enum TelemetryMode { Depends on: `BatchLogRecordProcessorOptions` (`@opentelemetry/sdk-logs`) · `OTLPExporterNodeConfigBase` (`@opentelemetry/otlp-exporter-base`) -Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:63`](../packages/telemetry/session-telemetry-otel/src/index.ts) +Source: [`packages/telemetry/session-telemetry-otel/src/index.ts:83`](../packages/telemetry/session-telemetry-otel/src/index.ts) ## `@deepseek-ai/dsh-session-title` diff --git a/packages/telemetry/session-telemetry-otel/README.i18n.yaml b/packages/telemetry/session-telemetry-otel/README.i18n.yaml index 5a6bd9bc9d..ec7fddf6b4 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: 01d803236329afbe65e2d92960928441aaff301c -README.zh.md: 8adf4a3c11b95dc302f8afd0dc79e99433e50f22 +README.md: af177dc86bc30a7b17e34e3c8c3592326b9026f2 +README.zh.md: 9a3ad628bb7d480a1c4cd8346669ad8ebbd6258f diff --git a/packages/telemetry/session-telemetry-otel/README.md b/packages/telemetry/session-telemetry-otel/README.md index 01d8032363..af177dc86b 100644 --- a/packages/telemetry/session-telemetry-otel/README.md +++ b/packages/telemetry/session-telemetry-otel/README.md @@ -26,6 +26,8 @@ The OpenTelemetry backend for [the telemetry seam](../session-telemetry/) — th Programmatic TypeScript configuration uses the exported `TelemetryMode` enum (`TelemetryMode.FULL`, `TelemetryMode.FEEDBACK_ONLY`, or `TelemetryMode.DISABLED`); raw string literals are not assignable. Serialized Cordis configuration continues to use the string values shown above. +Upload authorization is positive and fail-closed. An unknown direct-construction mode fails before transport configuration is read. Only `FULL` accepts direct `ctx.telemetry.emit()` calls. `FEEDBACK_ONLY` gives its on-demand coordinator a private backend capability and treats only the exact `feedback/record` object already stored at `session.events[event.seq]` as consent; an independently emitted bus value is ignored. `DISABLED` never constructs the SDK pipeline, even when exporter options are present. + `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 diff --git a/packages/telemetry/session-telemetry-otel/README.zh.md b/packages/telemetry/session-telemetry-otel/README.zh.md index 8adf4a3c11..9a3ad628bb 100644 --- a/packages/telemetry/session-telemetry-otel/README.zh.md +++ b/packages/telemetry/session-telemetry-otel/README.zh.md @@ -26,6 +26,8 @@ 程序化 TypeScript 配置使用导出的 `TelemetryMode` 枚举（`TelemetryMode.FULL`、`TelemetryMode.FEEDBACK_ONLY` 或 `TelemetryMode.DISABLED`）；原始字符串字面量不可赋值。序列化后的 Cordis 配置继续使用上表所示的字符串值。 +上传授权采用显式许可，且为 fail-closed。通过直接构造传入未知模式时，会在读取传输配置前失败。只有 `FULL` 接受对 `ctx.telemetry.emit()` 的直接调用。`FEEDBACK_ONLY` 向其按需协调器提供私有后端能力，并且仅在 `feedback/record` 对象已经存储于 `session.events[event.seq]` 且对象身份完全相同时，才将其视为同意；独立发出的总线值会被忽略。即使存在导出器选项，`DISABLED` 也绝不会构造 SDK 流水线。 + `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 diff --git a/packages/telemetry/session-telemetry-otel/src/index.ts b/packages/telemetry/session-telemetry-otel/src/index.ts index 95991cb932..f380d97549 100644 --- a/packages/telemetry/session-telemetry-otel/src/index.ts +++ b/packages/telemetry/session-telemetry-otel/src/index.ts @@ -20,7 +20,7 @@ import type {} from '@deepseek-ai/dsh-command-feedback' import { Telemetry, TelemetryCoordinator, - type TelemetryCapture, + type TelemetryBackend, type TelemetryRecord, type TelemetrySeverity, } from '@deepseek-ai/dsh-session-telemetry' @@ -54,6 +54,26 @@ export const TELEMETRY_MODES = [ ] as const const DISABLED_FEEDBACK_WARNING = 'session telemetry is DISABLED; nothing will be shared and this feedback remains local' +const NON_CANONICAL_FEEDBACK_WARNING = 'session telemetry ignored a feedback event absent from the canonical session log' +const DROP_RECORD: TelemetryBackend['emit'] = () => {} + +/** Resolve the default and reject unknown runtime values before transport setup. */ +function resolveMode(mode: TelemetryMode | undefined): TelemetryMode { + const resolved = mode ?? TelemetryMode.FULL + switch (resolved) { + case TelemetryMode.FULL: + case TelemetryMode.FEEDBACK_ONLY: + case TelemetryMode.DISABLED: + return resolved + default: + return assertNever(resolved) + } +} + +/** Fail closed when direct construction bypasses the runtime config schema. */ +function assertNever(value: never): never { + throw new Error(`session-telemetry-otel: unsupported mode ${JSON.stringify(value)}`) +} /** * Plugin configuration: one sharing policy plus two verbatim SDK option @@ -111,17 +131,15 @@ export class TelemetryOtel extends Telemetry { static inject = ['sessions'] static Config = Config + private readonly directEmit: TelemetryBackend['emit'] private readonly provider: LoggerProvider | undefined - private readonly ledger: Logger | undefined - private readonly ops: Logger | undefined constructor(ctx: Context, config: Config) { + const mode = resolveMode(config.mode) super(ctx) - const mode = config.mode ?? TelemetryMode.FULL if (mode === TelemetryMode.DISABLED) { + this.directEmit = DROP_RECORD this.provider = undefined - this.ledger = undefined - this.ops = undefined ctx.on('session/event', (_session, event) => { if (event.type === 'feedback/record') ctx.logger.warn(DISABLED_FEEDBACK_WARNING) }) @@ -168,37 +186,50 @@ 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) - const capture: TelemetryCapture = mode === TelemetryMode.FULL ? 'live' : 'on-demand' - const coordinator = new TelemetryCoordinator(ctx, this, capture) - if (mode === TelemetryMode.FEEDBACK_ONLY) { - // Session.append commits before publishing `session/event`, so the - // canonical log already includes this feedback record when replay begins. - ctx.on('session/event', (session, event) => { - if (event.type === 'feedback/record') coordinator.captureSession(session, event.seq) + const ledger = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel', version) + const ops = this.provider.getLogger('@deepseek-ai/dsh-session-telemetry-otel/ops', version) + const enqueue: TelemetryBackend['emit'] = (record) => { + const logger: Logger = record.channel === 'ops' ? ops : ledger + logger.emit({ + timestamp: record.time, + observedTimestamp: record.time, + ...SEVERITY[record.severity], + // JSON-serializable by the seam's contract (validated at Session.append), + // which is exactly the AnyValue subset. + body: record.body as AnyValue, + attributes: record.attributes, }) } + const backend: TelemetryBackend = { + emit: enqueue, + shutdown: () => this.shutdown(), + } + if (mode === TelemetryMode.FULL) { + this.directEmit = enqueue + new TelemetryCoordinator(ctx, backend, 'live') + return + } + this.directEmit = DROP_RECORD + const coordinator = new TelemetryCoordinator(ctx, backend, 'on-demand') + ctx.on('session/event', (session, event) => { + if (event.type !== 'feedback/record') return + // Consent is the committed record, not an independently emitted bus value. + if (session.events[event.seq] !== event) { + ctx.logger.warn(NON_CANONICAL_FEEDBACK_WARNING) + return + } + coordinator.captureSession(session, event.seq) + }) } /** - * Map one seam record onto the SDK logger for its channel — a synchronous - * 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. + * Hand a direct service record to the SDK only in `FULL`. Direct calls are + * no-ops in `FEEDBACK_ONLY` and `DISABLED`; feedback replay uses a private + * backend capability created only for the canonical feedback listener. + * @param record - the logical record offered directly to the service. */ 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, - ...SEVERITY[record.severity], - // JSON-serializable by the seam's contract (validated at Session.append), - // which is exactly the AnyValue subset. - body: record.body as AnyValue, - attributes: record.attributes, - }) + this.directEmit(record) } // The seam's optional flush() hint is deliberately NOT implemented. The diff --git a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts index 26118e4672..f7b3a007c9 100644 --- a/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts +++ b/packages/telemetry/session-telemetry-otel/tests/otel.spec.ts @@ -105,6 +105,13 @@ describe('TelemetryOtel wire', () => { const session = ctx.sessions.create(SessionId('wire'), { meta: { cwd: '/tmp/w' } }) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('turn/end', { turn: 1, reason: { kind: 'error', step: 1, message: 'boom' } }) + ctx.telemetry.emit({ + channel: 'ledger', + time: Date.now(), + severity: 'info', + attributes: { 'session.id': 'wire', 'event.type': 'manual', 'event.seq': 99 }, + body: { direct: true }, + }) await fiber.dispose() expect(captures.length).toBeGreaterThan(0) @@ -128,6 +135,7 @@ describe('TelemetryOtel wire', () => { const end = ledger.find(r => r.record.attributes?.some(a => a.key === 'event.type' && a.value.stringValue === 'turn/end')) expect(end?.record.severityNumber).toBe(17) expect(end?.record.severityText).toBe('ERROR') + expect(eventTypes(captures)).toContain('manual') expect(ops).toHaveLength(1) expect(ops[0]!.record.attributes).toContainEqual({ key: 'telemetry.op', value: { stringValue: 'shutdown' } }) @@ -214,6 +222,16 @@ describe('TelemetryOtel wire', () => { mode: TelemetryMode.FEEDBACK_ONLY, exporter: { url }, }) + ctx.on('telemetry/record', (_record, next) => { + ctx.telemetry.emit({ + channel: 'ledger', + time: Date.now(), + severity: 'info', + attributes: { 'session.id': 'feedback-only', 'event.type': 'direct-bypass', 'event.seq': 99 }, + body: { mustStayLocal: true }, + }) + return next() + }) 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') @@ -231,25 +249,48 @@ describe('TelemetryOtel wire', () => { expect(allRecords(captures).some(({ scope }) => scope.endsWith('/ops'))).toBe(false) }) - it('sends no request when feedback-only mode ends without feedback', async () => { + it('ignores direct emits and non-canonical feedback in feedback-only mode', async () => { const { url, captures } = await mockCollector() const ctx = new Context() await ctx.plugin(SessionStore) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) const fiber = await ctx.plugin(TelemetryOtel, { mode: TelemetryMode.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' } } }) + ctx.telemetry.emit({ + channel: 'ledger', + time: Date.now(), + severity: 'info', + attributes: { 'session.id': 'no-feedback', 'event.type': 'direct', 'event.seq': 99 }, + body: { mustStayLocal: true }, + }) + ctx.emit('session/event', session, { + type: 'feedback/record', + seq: session.events.length, + time: Date.now(), + data: { text: 'not committed' }, + }) await fiber.dispose() + + expect(warn).toHaveBeenCalledWith( + 'session telemetry ignored a feedback event absent from the canonical session log', + ) expect(captures).toEqual([]) }) - it('boots disabled without exporter config and warns when feedback stays local', async () => { + it('constructs no disabled transport even when exporter options are present', async () => { + const { url, captures } = await mockCollector() const ctx = new Context() await ctx.plugin(SessionStore) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) - const fiber = await ctx.plugin(TelemetryOtel, { mode: TelemetryMode.DISABLED }) + const fiber = await ctx.plugin(TelemetryOtel, { + mode: TelemetryMode.DISABLED, + exporter: { url }, + processor: { maxExportBatchSize: 0 }, + }) const session = ctx.sessions.create(SessionId('disabled'), { meta: {} }) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) recordFeedback(session, 'local report') @@ -268,6 +309,7 @@ describe('TelemetryOtel wire', () => { await fiber.dispose() recordFeedback(session, 'after disposal') expect(warn).toHaveBeenCalledTimes(1) + expect(captures).toEqual([]) }) it('defaults direct construction to full delivery', async () => { @@ -306,6 +348,22 @@ describe('TelemetryOtel config fails loud', () => { await ctx.plugin(SessionStore) await expect(ctx.plugin(TelemetryOtel, config as Config)).rejects.toThrow(message) }) + + it('rejects an unknown direct mode before reading transport config', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + let exporterRead = false + const config = { + mode: 'INVALID', + get exporter() { + exporterRead = true + throw new Error('transport config was read') + }, + } as unknown as Config + + expect(() => new TelemetryOtel(ctx, config)).toThrow(/unsupported mode "INVALID"/) + expect(exporterRead).toBe(false) + }) }) describe('dsh-session-telemetry-otel real-load-path guard', () => {