refactor(telemetry): drop dead live-collector smoke and the compact/end severity probe

tests/otel.e2e.ts self-skipped on $DSH_OTLP_E2E_ENDPOINT, which nothing in the repo sets — it never ran; the mock-collector wire spec and the keyless Loader-composition e2e already cover the pipeline both ways. The severityOf compact/end probe parsed another package's merged event shape by string comparison — an untyped cross-package contract that breaks silently — and its only consumer was the test's own stand-in declaration. Unknown event types now uniformly fall through as info; outcome semantics stay with the owning package.
2026-07-23 17:49:17 +08:00
parent 70febffe1a
commit b5523b0b48
7 changed files with 14 additions and 50 deletions
@@ -1554,7 +1554,7 @@ flush?(): void
 abstract shutdown(): Promise<void>
 ```

-Source: [`packages/telemetry/session-telemetry/src/index.ts:124`](../../packages/telemetry/session-telemetry/src/index.ts)
+Source: [`packages/telemetry/session-telemetry/src/index.ts:125`](../../packages/telemetry/session-telemetry/src/index.ts)

 ## `ctx.tokenMeter` — `TokenMeterService`

@@ -36,4 +36,4 @@ None; this package neither assembles nor sends a provider request.
 ## Known Limitations and Deferred Work

 - **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.
- **Live-collector smoke is opt-in** — the e2e smoke (`tests/otel.e2e.ts`) self-skips without `$DSH_OTLP_E2E_ENDPOINT`; the keyless Loader-composition e2e (`tests/loader-composition.e2e.ts`) covers the wire shape against a mock collector on every run.
+- **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.
@@ -1,25 +0,0 @@
-/**
- * Keyless-self-skipping smoke: ship one real session's records to a live
- * OTLP collector named by $DSH_OTLP_E2E_ENDPOINT and require the SDK's
- * shutdown (flush-and-quiesce) to resolve. Skipped without the endpoint so
- * secretless CI stays green — a CI accommodation, not a cost signal.
- */
-
-import { describe, expect, it } from 'vitest'
-import { Context } from 'cordis'
-import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
-import TelemetryOtel from '../src/index.ts'
-
-describe.skipIf(!process.env.DSH_OTLP_E2E_ENDPOINT)('telemetry-otel e2e (live collector)', () => {
-  it('exports a session and quiesces cleanly', async () => {
-    const ctx = new Context()
-    await ctx.plugin(SessionStore)
-    const fiber = await ctx.plugin(TelemetryOtel, {
-      exporter: { url: process.env.DSH_OTLP_E2E_ENDPOINT! },
-    })
-    const session = ctx.sessions.create(SessionId(`e2e-${Date.now()}`), { meta: {} })
-    session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
-    session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
-    await expect(fiber.dispose()).resolves.not.toThrow()
-  })
-})
@@ -24,7 +24,7 @@ Only the first `assistant/chunk` of each `(turn, step)` ships; the rest are drop

 ## The logical record

-`TelemetryRecord`: `channel` (`ledger` | `ops`), `time` (epoch ms), `severity` (pre-mapped: ERROR for `tool/result.isError`, `turn/end` error reasons, `compact/end` errors; WARN for `prompt/blocked`; INFO otherwise), identity-only `attributes` (`session.id`, `event.type`, `event.seq`, plus `session.cwd`/`session.parent_id` when the header has them), and the complete deep-copied `event.data` as `body` — post-redaction. Operational records carry `telemetry.op` (`agent-error` | `shutdown`) and `session.id`, and deliberately NO `event.seq`/`event.type` — signals to alert on, not entries to sum. Delivery downstream of the handoff is the backend SDK's; duplicates remain possible (cursor-less re-adoption, SDK retries), so receivers dedupe on `(session.id, event.seq)`.
+`TelemetryRecord`: `channel` (`ledger` | `ops`), `time` (epoch ms), `severity` (pre-mapped: ERROR for `tool/result.isError` and `turn/end` error reasons; WARN for `prompt/blocked`; INFO otherwise, including plugin-merged event types whose outcome semantics stay with their owners), identity-only `attributes` (`session.id`, `event.type`, `event.seq`, plus `session.cwd`/`session.parent_id` when the header has them), and the complete deep-copied `event.data` as `body` — post-redaction. Operational records carry `telemetry.op` (`agent-error` | `shutdown`) and `session.id`, and deliberately NO `event.seq`/`event.type` — signals to alert on, not entries to sum. Delivery downstream of the handoff is the backend SDK's; duplicates remain possible (cursor-less re-adoption, SDK retries), so receivers dedupe on `(session.id, event.seq)`.

 ## Model Experience

@@ -218,15 +218,11 @@ function severityOf(event: SessionEvent): TelemetrySeverity {
      return event.data.reason.kind === 'error' ? 'error' : 'info'
    case 'prompt/blocked':
      return 'warn'
-    default: {
-      // Merge-extensible fall-through (no assertNever): types this seam does
-      // not depend on still get their RFC-pinned severity via a widened
-      // probe — `compact/end` is declared by dsh-compact, which the seam
-      // deliberately does not import.
-      const type: string = event.type
-      if (type === 'compact/end' && (event.data as { error?: unknown }).error !== undefined) return 'error'
+    default:
+      // Merge-extensible fall-through (no assertNever): event types this seam
+      // does not depend on — including plugin-merged ones it never heard of —
+      // pass through as info; their owners' outcome semantics stay theirs.
      return 'info'
-    }
  }
 }

@@ -44,9 +44,10 @@ declare module 'cordis' {
 /**
 * Severity of a telemetry record, pre-mapped at capture so a receiver can
 * alert with zero configuration: `error` for events whose own outcome flag
- * says so (`tool/result.isError`, `turn/end` error reasons, `compact/end`
- * errors) and for `agent-error` operational records, `warn` for
- * `prompt/blocked`, `info` for everything else.
+ * says so (`tool/result.isError`, `turn/end` error reasons) and for
+ * `agent-error` operational records, `warn` for `prompt/blocked`, `info`
+ * for everything else — including event types merged by other packages,
+ * whose outcome semantics stay with their owners.
 */
 export type TelemetrySeverity = 'info' | 'warn' | 'error'

@@ -19,12 +19,6 @@ declare module '@deepseek-ai/dsh-session' {
     * @param payload - opaque test payload
     */
    'telemetry-test/opaque': { payload: { nested: string[] } }
-    /**
-     * Test-only stand-in for dsh-compact's merge, exercising the widened severity probe.
-     * @mode emit
-     * @param error - failure text when the compaction failed
-     */
-    'compact/end': { turn: number; error?: string }
  }
 }

@@ -104,15 +98,14 @@ describe('TelemetryCoordinator capture', () => {
    }
  })

-  it('maps outcome flags to severity, including the widened merge-extensible probe', async () => {
+  it('maps outcome flags to severity, unknown types falling through as info', async () => {
    const { ctx, backend } = await setup()
    const session = liveSession(ctx)
    session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
    session.append('tool/result', { turn: 1, step: 1, callId: 'c1' as never, content: [], isError: true }, { surfaceOp: 'append' })
    session.append('tool/result', { turn: 1, step: 1, callId: 'c2' as never, content: [], isError: false }, { surfaceOp: 'append' })
    session.append('prompt/blocked', { content: [], source: { kind: 'user' }, reason: 'vetoed' })
-    session.append('compact/end', { turn: 1, error: 'summarizer died' })
-    session.append('compact/end', { turn: 1 })
+    session.append('telemetry-test/opaque', { payload: { nested: [] } })
    session.append('turn/end', { turn: 1, reason: { kind: 'error', step: 1, message: 'boom' } })
    const severities = backend.ledger().map(r => [r.attributes['event.type'], r.severity])
    expect(severities).toEqual([
@@ -120,8 +113,7 @@ describe('TelemetryCoordinator capture', () => {
      ['tool/result', 'error'],
      ['tool/result', 'info'],
      ['prompt/blocked', 'warn'],
-      ['compact/end', 'error'],
-      ['compact/end', 'info'],
+      ['telemetry-test/opaque', 'info'],
      ['turn/end', 'error'],
    ])
  })