Files
deepseek-harness/packages/session/README.md
T

67 lines
5.7 KiB
Markdown

# dsh-session
Event-sourced session log and in-memory store. A `Session` is the append-only source of truth for an agent's whole interaction history — the LLM message history is *derived* from it. A **surface** layer (a linked list of message-producing events) is maintained on top of the raw log for efficient derivation and compaction.
## Service: `SessionStore` (ctx key: `sessions`)
Creates and holds event-sourced `Session` instances. Persistence is intentionally not implemented here — plugins subscribe to `session/event` and flush on `session/flush`.
### Public API
- `ctx.sessions.create(id?: string, options?: { seed?: SessionEvent[]; meta?: { cwd?: string; parentSession?: SessionId; createdAt?: number } }): Session` — Create a session. `options.seed` replays/forks an existing event log; `options.meta` attaches creation metadata (validated absolute `cwd`, `parentSession` lineage) as the immutable `SessionHeader`. The store fills `version`/`id` and defaults `createdAt` to now; a caller reconstructing a persisted session passes the original `createdAt` to preserve it. Disposed with the calling fiber.
- `ctx.sessions.get(id: string): Session | undefined`
- `ctx.sessions.list(): Session[]`
### Events
| Event | Mode | Purpose |
|---|---|---|
| `session/created` | emit | A session was created |
| `session/event` | emit | An event was appended (sync, fire-and-forget) |
| `session/flush` | parallel | Awaited durability checkpoint (persistence plugins drain buffers here) |
### Class: `Session`
Plain class (not a Cordis Service). Create via `ctx.sessions.create()`.
- `session.append(type, data, opts?): SessionEvent` — synchronous, never blocks on I/O. **Throws** if `data` is not losslessly JSON-serializable (BigInt, function, symbol, undefined, non-finite number, circular ref, or an exotic object like Map/Set/Date) — the event log is the durable source of truth, so this invariant is enforced at the source (exported as `isJsonValue` for backends to reuse on their replay/fork entry points). An optional third parameter `opts: SurfaceAppendOpts` carries surface metadata: `surfaceOp` controls how the event enters the surface linked list, and `sourceEventSeqs` records provenance (the seq numbers of events this one derives from).
- `session.deriveMessages(): Message[]` — derive the LLM message history. If any event in the log carries `surfaceOp`, derivation walks the surface linked list (skipping non-surface events). Otherwise, falls back to a linear scan of the raw log (legacy sessions without surface markers).
- `session.surface: SurfaceManager` — the derived surface, lazily rebuilt from `surfaceOp` markers in the log. Processes only new events (delta) on each access — the log is append-only, so prior events never change.
- `session.events`, `session.seq`, `session.id`
- `session.header: SessionHeader` — immutable creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`). Kept out of the event log (a storage concern, not replayable state); a minimal v1 header is synthesized for bare `Session` construction.
### Surface types
- `SurfaceOp` — how a surface node entered the linked list: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace nodes from `start` through `end` inclusive — both must be valid surface node seqs; `start === end` replaces a single node). Used by compaction to shadow old nodes without deleting them.
- `SurfaceAppendOpts``{ surfaceOp?: SurfaceOp; sourceEventSeqs?: number[] }`, the optional third parameter to `session.append()`.
- `SurfaceNode``{ seq: number; prev: number | null; next: number | null }`, one node in the surface linked list.
### Session event vocabulary (`types.ts`)
The append-only log: `turn/start`, `turn/end`, `step/start`, `step/end`, `user/message`, `assistant/message`, `assistant/chunk`, `tool/call`, `tool/result`, `steering/message`, `context/message`, `usage`, `error`.
Merge-extensible via `SessionEventMap` — a compaction plugin adds `compaction/marker`, etc.
Also defines `TurnTriggerMap` and `TurnEndReasonMap` (merge-extensible sum types for typed turn boundaries — `kind`-tagged instead of strings).
Every `SessionEvent` carries two optional top-level fields (structural metadata):
- `sourceEventSeqs?: number[]` — seq numbers of provenance sources (e.g., the `assistant/chunk` seqs behind an `assistant/message`, or the shadowed nodes behind a compaction marker).
- `surfaceOp?: SurfaceOp` — how this event entered the surface. Absent for non-surface events (boundaries, chunks, usage, errors).
### Metadata types (`types.ts`)
- `SessionHeader` — immutable, written once: `{ version, id, createdAt, cwd?, parentSession? }`.
- `SessionSummary` — mutable, updateable without touching the log: `{ updatedAt, title?, firstPrompt? }`.
- `SessionMeta = SessionHeader & SessionSummary` — owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export these rather than own them (which would force a package cycle).
### Extension points
- Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`/`SessionSummary`/`SessionMeta`, `session.header`) is what such a backend stores beside the log.
- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events.
- Compaction: a future plugin appends a new event with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes.
### What is NOT here (TODO)
- **Session branching/tree** (pi-style entry tree) — deferred unless needed beyond seed-based forking.