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.
This commit is contained in:
145
packages/telemetry/session-telemetry/src/index.ts
Normal file
145
packages/telemetry/session-telemetry/src/index.ts
Normal file
@@ -0,0 +1,145 @@
|
||||
/**
|
||||
* Telemetry seam for the DeepSeek Harness.
|
||||
*
|
||||
* 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
|
||||
* {@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
|
||||
* .agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-session-telemetry
|
||||
*/
|
||||
|
||||
import { Context, Service } from 'cordis'
|
||||
|
||||
declare module 'cordis' {
|
||||
interface Context {
|
||||
telemetry: Telemetry
|
||||
}
|
||||
|
||||
interface Events {
|
||||
/**
|
||||
* Redact one outbound record before it reaches the backend. The innermost
|
||||
* `next()` applies the seam's conservative default rule set
|
||||
* (credential-shape scrubbing); listeners stack stricter rules by
|
||||
* transforming its return value, and returning without `next()` replaces
|
||||
* the default — the exported record is then only as clean as the
|
||||
* replacing rule. Dispatched synchronously on the capture hot path inside
|
||||
* the coordinator's containment: a throwing listener withholds that one
|
||||
* record (fail-closed) and never reaches the agent loop. Redaction
|
||||
* applies to the exported copy only; the canonical session log is never
|
||||
* rewritten.
|
||||
* @param record - the candidate record, already the coordinator's own deep
|
||||
* copy; listeners return a (possibly new) record and must not mutate it.
|
||||
* @mode waterfall
|
||||
*/
|
||||
'telemetry/redact'(record: TelemetryRecord, next: () => TelemetryRecord): TelemetryRecord
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 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.
|
||||
*/
|
||||
export type TelemetrySeverity = 'info' | 'warn' | 'error'
|
||||
|
||||
/**
|
||||
* One logical record handed to a backend — the seam's whole outbound
|
||||
* vocabulary. Ledger records mirror session-log events one-to-one;
|
||||
* operational records (`channel: 'ops'`) carry the two signals with no log
|
||||
* home (`agent-error`, `shutdown`) and deliberately omit `event.seq`-style
|
||||
* identity so they can never be mistaken for ledger rows.
|
||||
*/
|
||||
export interface TelemetryRecord {
|
||||
/** Ledger (session-log mirror) or ops (operational signal) channel; backends keep the two under separate instrumentation scopes. */
|
||||
channel: 'ledger' | 'ops'
|
||||
/** Unix epoch milliseconds — the source event's append time for ledger records, the emission time for ops records. */
|
||||
time: number
|
||||
/** Pre-mapped alerting severity; see {@link TelemetrySeverity}. */
|
||||
severity: TelemetrySeverity
|
||||
/**
|
||||
* Identity attributes, deliberately minimal: ledger records carry
|
||||
* `session.id`, `event.type`, `event.seq`, plus `session.cwd` /
|
||||
* `session.parent_id` when the header has them; ops records carry
|
||||
* `telemetry.op`, `session.id`, and (for `agent-error`) `agent.id`,
|
||||
* `turn`, `step`, `error.name`. Anything recoverable from the body is
|
||||
* intentionally NOT duplicated here.
|
||||
*/
|
||||
attributes: Record<string, string | number>
|
||||
/**
|
||||
* The complete payload: a deep copy of the session event's `data` for
|
||||
* ledger records (JSON-serializable by `Session.append`'s own
|
||||
* validation), or the op payload for ops records. Never mutated after
|
||||
* handoff.
|
||||
*/
|
||||
body: unknown
|
||||
}
|
||||
|
||||
/**
|
||||
* The backend contract the coordinator hands records to — the minimum any
|
||||
* reporting SDK satisfies with zero bending. {@link Telemetry} is its
|
||||
* service-registered form; tests compose the coordinator with a bare
|
||||
* implementation of this interface.
|
||||
*/
|
||||
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.
|
||||
* @param record - the logical record to report; owned by the backend after the call.
|
||||
*/
|
||||
emit(record: TelemetryRecord): void
|
||||
/**
|
||||
* Optional hint that a natural boundary (turn end) passed — a backend may
|
||||
* forward it to its SDK's flush so records land at turn boundaries. Called
|
||||
* fire-and-forget; implementations must not block and must not throw
|
||||
* meaningfully (the coordinator contains exceptions).
|
||||
*/
|
||||
flush?(): void
|
||||
/**
|
||||
* Forward the fiber's disposal to the SDK: flush whatever is queued and
|
||||
* reach quiescence, per the SDK's own shutdown contract. Awaited by the
|
||||
* coordinator's dispose; a rejection is logged as a warning and never
|
||||
* fails application teardown.
|
||||
* @returns resolves when the backend's pipeline has quiesced.
|
||||
*/
|
||||
shutdown(): Promise<void>
|
||||
}
|
||||
|
||||
/**
|
||||
* The backend contract in its loadable form: one implementation per context —
|
||||
* the cordis `Service` registration under the `telemetry` key throws on a
|
||||
* duplicate, cordis' standard behavior. A backend composes a
|
||||
* {@link TelemetryCoordinator} in its constructor to install the capture side.
|
||||
*/
|
||||
export abstract class Telemetry extends Service implements TelemetryBackend {
|
||||
constructor(ctx: Context) {
|
||||
super(ctx, 'telemetry')
|
||||
}
|
||||
|
||||
/**
|
||||
* See {@link TelemetryBackend.emit} — the seam declaration is the contract's one home.
|
||||
* @param record - the logical record to report; owned by the backend after the call.
|
||||
*/
|
||||
abstract emit(record: TelemetryRecord): void
|
||||
|
||||
/** See {@link TelemetryBackend.flush}. */
|
||||
flush?(): void
|
||||
|
||||
/**
|
||||
* See {@link TelemetryBackend.shutdown}.
|
||||
* @returns resolves when the backend's pipeline has quiesced.
|
||||
*/
|
||||
abstract shutdown(): Promise<void>
|
||||
}
|
||||
|
||||
export { TelemetryCoordinator } from './coordinator.ts'
|
||||
export { applyDefaultRedaction, REDACTION_PLACEHOLDER } from './redact.ts'
|
||||
Reference in New Issue
Block a user