7.5 KiB
Agent Note: Session persistence as an abstract service over the existing SessionEvent
Status: implemented
English | 中文
Problem
Sessions lived only in memory. The example session-jsonl.ts plugin (duplicated byte-for-byte in both examples) was write-only telemetry: it buffered session/event and appended JSON lines, with no read/replay path, no crash-safety (no fsync, no atomic write, a fire-and-forget dispose drain), no listing, and no format versioning. Nothing could rehydrate a past session from disk into a live agent, so durable resume, durable forking, and host-side session browsing were all impossible.
The event-sourced model makes the append-only log the single source of truth and derives LLM history from it. Persistence had to stay faithful to that: persist the existing SessionEvent directly, with no parallel "persisted message" type that the log is converted to and from. The backend also had to be swappable — a file store now, a database store later — behind one interface.
Decision
Persistence is a capability seam with an abstract Service Definition (capability seams, the dsh-shell template), not loop or core logic:
- Interface (
dsh-session-persistence,ctx.sessionPersistence) — an abstractSessionPersistenceservice:locate/create/append/prepare/load/inspect/readFrom/list/listSnapshots. Its persisted unit IS the existingSessionEvent({ type, seq, time, data }), reused verbatim — no conversion type. - Implementation (
dsh-session-persistence-jsonl) — an append-only logical JSONL log per session: aSessionHeaderline followed by storage records that losslessly represent the contiguousSessionEventstream. Eligibleassistant/chunkdelta runs use packed rows by default; checksummed Zstandard frames are the default physical encoding, with raw lines configurable.
Key durable, contested choices:
- The canonical durable log persists every
SessionEventlosslessly, includingassistant/chunk. JSONL storage may encode a consecutive delta run as one packed row, but logical readers reconstruct the exact event boundaries, sequence numbers, and timestamps.deriveMessages()skips chunks, and a chunk-filtered rollout (Codex'spolicy.rs) is tempting — butseq = log.lengthand validation ofevents[i].seq === irequire a contiguous logical log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log. - Append-only; a crashed turn is closed, never truncated. Flushed events are never rewritten. The semantic checkpoint policy drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, cold inspection preserves its contiguous, parseable events and adds risk-classified error results for unanswered assistant calls, a missing
step/end, andturn/endwith{ kind: 'interrupted' }to the in-memory logical view.prepareorloadcommits those closers before returning a recoverable view; the synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded during committed repair; a parse error or sequence gap at or before the last realturn/endis corruption and makes the session unloadable. - The file backend is canonical while the service remains extensible.
dsh-session-persistence-jsonlis the sole first-party provider and passesrunPersistenceContract; the abstract service and coordinator remain available to out-of-tree providers. The JSONL-only persistence decision owns removal of the first-party database provider and its deliberate compatibility cut. - Metadata is out-of-log. Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a
SessionHeaderowned bydsh-sessionand attached to aSessionvia a new readonlysession.header— never inSessionEventMap, never reachingderiveMessages().createdAtis non-negative safe-integer Unix epoch milliseconds: live creation and persistence registration reject fractional values, and JSONL validates the decoded header. The alternative (a merge-extensiblesession/metaevent as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header boundary is the cleaner cost. (The header was originally split into an immutableSessionHeaderplus a mutableSessionSummarywhose union wasSessionMeta; the mutable summary was later removed as dead state — see Drop the mutable session summary.) ctx.agents.create()andctx.agents.resume()are async factories; resume additionally crosses the persistence boundary.ctx.agents.resume({ resumeSessionId })obtains the exact unpublished Session throughctx.sessionPersistence.prepare(), publishes it under the persisted id, and continues its projections. The Session preparation decision owns reuse between history inspection and resume. The agent-loop does NOT hard-injectsessionPersistence(that would pend non-persistent demos forever);resumerejects with a clear error when it is absent.
Alternatives considered
Each key choice above records its rejected alternative where the choice is stated: a chunk-filtered canonical log (Codex's policy.rs shape) — breaks the contiguous-seq contract; truncating a crashed turn — silently destroys a long autonomous run's real work; an in-log session/meta event as log line 0 — metadata is not replayable state; finite fractional createdAt values — have no producer and diverge from integer Unix-millisecond storage; hard-injecting sessionPersistence into the loop — would pend non-persistent demos forever.
Format versioning: the header carries a version; cold reads reject any non-current version. The pre-release session format stays pinned at SESSION_FORMAT_VERSION = 0 and carries no broad compatibility promise, while the coordinator may own an explicit narrow import upgrade when persisted user data requires it (pre-identity message recovery). Append-only + flush is robust to partial trailing writes tolerated during cold preparation; a future provider or write-ahead log needs its own power-loss and recovery contract.
Consequences
The Service Definition, JSONL provider, and metadata contract in dsh-session (session.header, the create(id?, options?) signature) buy durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log. The reusable runPersistenceContract suite holds the provider and future implementations to the same append-only, contiguous-seq, lazy-materialization, logical-recovery, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every assistant/chunk survives exactly even when JSONL packs several into one storage row.