feat(telemetry): session-telemetry seam with mandatory redaction + OTel backend

Revive the reviewed session-telemetry packages from the closed
session-telemetry-otlp-rfc branch (PR #222/#231) on current master, renamed
to @deepseek-ai/dsh-session-telemetry{,-otel} (the SDK component-telemetry
package holds the dsh-telemetry name).

Delta over the branch version: every record now passes a telemetry/redact
waterfall between projection and emit() — the innermost next() applies a
non-configurable conservative credential-shape rule set, listeners stack
stricter rules, a throwing rule withholds the record fail-closed, and the
canonical log is never rewritten. This answers the export-side concern that
closed PR #222; the boundary axiom (our aspect ends at emit(); delivery is
the reporting SDK's) is unchanged, and the runtime-telemetry RFC's outbox /
readCommitted lane is recorded as deferred in the Agent Note.

Covered by seam/redact/OTel-wire unit tiers (100% per-file) and a keyless
Loader-composition e2e that boots the examples fixture against a mock OTLP
collector and pins redaction on the wire plus the untouched canonical log.

packages/telemetry/session-telemetry-otel/tests/loader-composition.e2e.ts

@@ -0,0 +1,98 @@
+/**
+ * REAL-composition tier: boot the examples-owned telemetry Loader fixture as
+ * a subprocess (per testing policy, through the same app/boot path a
+ * deployment uses), run one mocked-model turn with a real bash round trip,
+ * and assert against what the mock OTLP collector actually received on the
+ * wire: ledger mirroring, default redaction, ops markers, and the untouched
+ * canonical log.
+ */
+
+import { readFile, readdir } from 'node:fs/promises'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { describe, expect, it } from 'vitest'
+import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
+import { REDACTION_PLACEHOLDER } from '@deepseek-ai/dsh-session-telemetry'
+
+const driver = fileURLToPath(new URL(
+  '../../../../examples/headless-agent/tests/fixtures/telemetry-otel-driver.ts',
+  import.meta.url,
+))
+const configPath = fileURLToPath(new URL(
+  '../../../../examples/headless-agent/tests/fixtures/telemetry-otel.cordis.yml',
+  import.meta.url,
+))
+const repoTsconfig = fileURLToPath(new URL('../../../../tsconfig.json', import.meta.url))
+
+const FIXTURE_SECRET = 'sk-e2efixture1234567890'
+
+interface OtlpLogRecord {
+  attributes?: { key: string; value: Record<string, unknown> }[]
+  body?: unknown
+}
+
+interface OtlpCapture {
+  resourceLogs: {
+    scopeLogs: {
+      scope: { name: string }
+      logRecords: OtlpLogRecord[]
+    }[]
+  }[]
+}
+
+async function jsonlFiles(dir: string): Promise<string[]> {
+  const entries = await readdir(dir, { withFileTypes: true })
+  const paths = await Promise.all(entries.map(async (entry) => {
+    const path = join(dir, entry.name)
+    if (entry.isDirectory()) return jsonlFiles(path)
+    return entry.isFile() && entry.name.endsWith('.jsonl') ? [path] : []
+  }))
+  return paths.flat()
+}
+
+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 = ''
+    const { stderr } = await runLoaderSmoke({
+      label: 'session-telemetry-otel loader smoke',
+      tempDirPrefix: 'telemetry-otel-e2e-',
+      binScript: driver,
+      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')
+      },
+    })
+    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 })))))
+    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']]
+          : []) ?? [])
+    for (const expected of ['turn/start', 'user/message', 'tool/call', 'tool/result', 'assistant/message', 'turn/end']) {
+      expect(eventTypes, expected).toContain(expected)
+    }
+    expect(records.some(({ scope }) => scope.endsWith('/ops'))).toBe(true)
+
+    // Default redaction on the wire: the fixture credential never leaves the
+    // process, its surrounding prose does, and the placeholder marks the spot.
+    const wire = JSON.stringify(captures)
+    expect(wire).not.toContain(FIXTURE_SECRET)
+    expect(wire).toContain(REDACTION_PLACEHOLDER)
+    expect(wire).toContain('prove telemetry with key')
+
+    // The canonical session log is never rewritten.
+    expect(logContent).toContain(FIXTURE_SECRET)
+    expect(logContent).not.toContain(REDACTION_PLACEHOLDER)
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+})

packages/telemetry/session-telemetry-otel/tests/otel.e2e.ts

@@ -0,0 +1,25 @@
+/**
+ * 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()
+  })
+})

packages/telemetry/session-telemetry-otel/tests/otel.spec.ts

@@ -0,0 +1,166 @@
+/**
+ * OTel backend unit tier: wire assertions against a scripted `node:http`
+ * mock collector through the SDK's REAL pipeline (BatchLogRecordProcessor →
+ * OTLP/HTTP JSON), config fail-loud cases, and the real-Loader-path guard
+ * for the default-exported Service class.
+ */
+
+import { afterEach, describe, expect, it } from 'vitest'
+import { createServer, type Server } from 'node:http'
+import { once } from 'node:events'
+import { Context } from 'cordis'
+import Loader from '@cordisjs/plugin-loader'
+import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
+import TelemetryOtel, { Config } from '../src/index.ts'
+
+interface Capture {
+  headers: import('node:http').IncomingHttpHeaders
+  body: OtlpLogsRequest
+}
+
+/** Just the slice of ExportLogsServiceRequest JSON these assertions touch. */
+interface OtlpLogsRequest {
+  resourceLogs: {
+    resource: { attributes: { key: string; value: { stringValue?: string } }[] }
+    scopeLogs: {
+      scope: { name: string }
+      logRecords: {
+        timeUnixNano: string
+        severityNumber: number
+        severityText: string
+        attributes?: { key: string; value: Record<string, unknown> }[]
+      }[]
+    }[]
+  }[]
+}
+
+const servers: Server[] = []
+
+afterEach(async () => {
+  for (const server of servers.splice(0)) {
+    server.close()
+    server.closeAllConnections()
+  }
+})
+
+async function mockCollector(): Promise<{ url: string; captures: Capture[] }> {
+  const captures: Capture[] = []
+  const server = createServer((request, response) => {
+    const chunks: Buffer[] = []
+    request.on('data', chunk => chunks.push(chunk as Buffer))
+    request.on('end', () => {
+      captures.push({
+        headers: request.headers,
+        body: JSON.parse(Buffer.concat(chunks).toString()) as OtlpLogsRequest,
+      })
+      response.writeHead(200, { 'content-type': 'application/json' }).end('{}')
+    })
+  })
+  servers.push(server)
+  server.listen(0, '127.0.0.1')
+  await once(server, 'listening')
+  const address = server.address()
+  if (address === null || typeof address === 'string') throw new Error('no port')
+  return { url: `http://127.0.0.1:${address.port}/v1/logs`, captures }
+}
+
+async function boot(url: string) {
+  const ctx = new Context()
+  await ctx.plugin(SessionStore)
+  const fiber = await ctx.plugin(TelemetryOtel, {
+    exporter: { url, headers: { authorization: 'Bearer test-token' } },
+  })
+  return { ctx, fiber }
+}
+
+function allRecords(captures: Capture[]) {
+  return captures.flatMap(c => c.body.resourceLogs.flatMap(r => r.scopeLogs.flatMap(s =>
+    s.logRecords.map(record => ({ scope: s.scope.name, record })))))
+}
+
+describe('TelemetryOtel wire', () => {
+  it('ships session records and the ops shutdown marker through the real SDK pipeline', async () => {
+    const { url, captures } = await mockCollector()
+    const { ctx, fiber } = await boot(url)
+    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' } })
+    await fiber.dispose()
+
+    expect(captures.length).toBeGreaterThan(0)
+    const first = captures[0]!
+    const authorization: string | undefined = first.headers.authorization
+    expect(authorization).toBe('Bearer test-token')
+
+    const resource = first.body.resourceLogs[0]!.resource.attributes
+    expect(resource).toContainEqual({ key: 'service.name', value: { stringValue: 'deepseek-harness' } })
+
+    const records = allRecords(captures)
+    const ledger = records.filter(r => r.scope === '@deepseek-ai/dsh-session-telemetry-otel')
+    const ops = records.filter(r => r.scope === '@deepseek-ai/dsh-session-telemetry-otel/ops')
+
+    const start = ledger.find(r => r.record.attributes?.some(a => a.key === 'event.type' && a.value.stringValue === 'turn/start'))
+    expect(start).toBeDefined()
+    expect(start?.record.severityNumber).toBe(9)
+    expect(BigInt(start!.record.timeUnixNano)).toBe(BigInt(session.events[0]!.time) * 1_000_000n)
+    expect(start?.record.attributes).toContainEqual({ key: 'session.cwd', value: { stringValue: '/tmp/w' } })
+
+    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(ops).toHaveLength(1)
+    expect(ops[0]!.record.attributes).toContainEqual({ key: 'telemetry.op', value: { stringValue: 'shutdown' } })
+  })
+
+  it('maps the warn severity and forwards the flush hint to the SDK', async () => {
+    const { url, captures } = await mockCollector()
+    const { ctx, fiber } = await boot(url)
+    const session = ctx.sessions.create(SessionId('warn'), { meta: {} })
+    session.append('prompt/blocked', { content: [], source: { kind: 'user' }, reason: 'vetoed' })
+    // The turn-boundary hint: safe, non-blocking, and enough to push the batch out.
+    expect(() => {
+      ctx.telemetry.flush!()
+    }).not.toThrow()
+    await fiber.dispose()
+    const blocked = allRecords(captures).find(r =>
+      r.record.attributes?.some(a => a.key === 'event.type' && a.value.stringValue === 'prompt/blocked'))
+    expect(blocked?.record.severityNumber).toBe(13)
+  })
+})
+
+describe('TelemetryOtel config fails loud', () => {
+  it.each([
+    [{}, /exporter\.url is required/],
+    [{ exporter: { url: '' } }, /exporter\.url is required/],
+    [{ exporter: { url: 'not a url' } }, /not a valid URL/],
+    [{ exporter: { url: 'ftp://collector' } }, /must be http\(s\)/],
+  ])('rejects %j at plugin load', async (config, message) => {
+    const ctx = new Context()
+    await ctx.plugin(SessionStore)
+    await expect(ctx.plugin(TelemetryOtel, config as Config)).rejects.toThrow(message)
+  })
+})
+
+describe('dsh-session-telemetry-otel real-load-path guard', () => {
+  it('keeps the Service class with inject/Config through unwrapExports', async () => {
+    const module = await import('../src/index.ts')
+    const loader = Object.create(Loader.prototype) as Loader
+    const unwrapped = loader.unwrapExports(module) as typeof TelemetryOtel
+    expect(unwrapped).toBe(TelemetryOtel)
+    expect(unwrapped.inject).toEqual(['sessions'])
+    expect(typeof unwrapped.Config).toBe('function')
+  })
+
+  it('boots through the unwrapped class and registers ctx.telemetry', async () => {
+    const { url } = await mockCollector()
+    const module = await import('../src/index.ts')
+    const loader = Object.create(Loader.prototype) as Loader
+    const unwrapped = loader.unwrapExports(module) as Parameters<Context['plugin']>[0]
+    const ctx = new Context()
+    await ctx.plugin(SessionStore)
+    const fiber = await ctx.plugin(unwrapped, { exporter: { url } })
+    expect(ctx.telemetry).toBeInstanceOf(TelemetryOtel)
+    await fiber.dispose()
+  })
+})