docs(session-title): record contracts and generated catalogs
This commit is contained in:
Tianyi Cui
@@ -29,6 +29,7 @@ Packages live at `packages/<group>/<pkg>/`; groups are containers, while names r
|
||||
| [`hooks/`](hooks/README.md) | Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface |
|
||||
| [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface |
|
||||
| [`session-query/`](session-query/README.md) | Session retrieval: logical corpus, bounded reads, lineage, and event relationships | Product — stable surface |
|
||||
| [`session-title/`](session-title/README.md) | Log-backed session titles: fallback service, shared LLM policy, and opt-in providers | Product — stable surface |
|
||||
| [`sdk/`](sdk/README.md) | Project SDK tooling | Product — stable surface |
|
||||
| [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, JSON-RPC SDK server, user-approval/user-interaction seams, ask-user tool | Product — stable surface |
|
||||
| [`examples/`](examples/README.md) | Demo bundles (agent-spine + TUI/one-shot CLI/ACP/JSON-RPC bins) the leaves load | Support — example infra |
|
||||
|
||||
@@ -343,6 +343,10 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
|
||||
signature: 'listSessions(): Promise<SessionRecord[]>',
|
||||
jsDoc: '/**\n * List the complete logical corpus using live-preferred records.\n * @returns deterministic newest-first cloned session records.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'async readTitle(sessionId: SessionId): Promise<SessionTitleSnapshot | undefined>',
|
||||
jsDoc: '/**\n * Fold the latest log-backed title from one live-preferred logical session.\n * @param sessionId - live or persisted session id to read.\n * @returns latest title snapshot, or `undefined` when the log has no title event.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'async listEvents(sessionId: SessionId): Promise<SessionEventRecord[]>',
|
||||
jsDoc: '/**\n * List lightweight raw-log event records for one logical session.\n * @param sessionId - live-preferred session id to read.\n * @returns event records in ascending seq order.\n */',
|
||||
@@ -385,6 +389,10 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
|
||||
signature: 'async flush(session: Session): Promise<void>',
|
||||
jsDoc: '/**\n * Dispatch the awaited `session/flush` durability checkpoint for `session`,\n * with the carrier captured at {@link enter}. THE flush entry point: the\n * store owns the carrier, so callers (the loop\'s turn-end checkpoint, idle\n * injection, teardown drains) must come through here rather than dispatch a\n * raw `ctx.parallel(\'session/flush\', …)` — one owner, one spelling, and the\n * scoped-dispatch invariant can pin it.\n * @param session - the session whose buffered events must reach durable storage.\n * @returns resolves when every flush listener has settled; after all settle,\n * rejects with the first registered listener failure if any listener failed.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'async appendOutOfBand<T extends OutOfBandSessionEventType>( session: Session, type: T, data: SessionEventMap[T], trigger: TurnTrigger, ): Promise<SessionEvent<T>>',
|
||||
jsDoc: '/**\n * Append one plugin-declared log-only event without borrowing the agent\n * loop\'s lifecycle. An open turn receives the event directly and remains\n * responsible for its ordinary checkpoint. A closed log receives one\n * zero-step turn around the event, followed by an awaited flush.\n *\n * Once the synthetic `turn/start` commits, this method always attempts its\n * matching `turn/end` and flush, including when the target append fails.\n * Detachment requested by an event or flush listener is deferred until that\n * sequence settles, so publication cannot switch from a live scoped session\n * to an unobserved bare `Session` halfway through the update.\n *\n * @param session - exact live session that owns the target log.\n * @param type - event type opted into {@link OutOfBandSessionEventMap} by its owner.\n * @param data - typed JSON payload for the target event.\n * @param trigger - plugin-owned turn trigger used only when the log is closed.\n * @returns the accepted target event with its assigned sequence and timestamp.\n * @throws when the session is detached, another out-of-band append is active,\n * event acceptance fails, the synthetic turn cannot close, or flushing fails.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'get(id: SessionId): Session | undefined',
|
||||
jsDoc: '/**\n * Look up a live session.\n * @param id - the session id to look up.\n * @returns the session, or undefined when no live session has that id.\n */',
|
||||
@@ -399,6 +407,24 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
key: 'sessionTitle',
|
||||
summary: 'Log-backed title fold plus asynchronous fallback generation.',
|
||||
methods: [
|
||||
{
|
||||
signature: 'get(session: Session): SessionTitleSnapshot | undefined',
|
||||
jsDoc: '/**\n * Read the latest folded title from one live or replayed session.\n * @param session - session whose log is the title source of truth.\n * @returns latest title snapshot, or `undefined` before eligible input.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'async refresh(session: Session, signal?: AbortSignal): Promise<SessionTitleSnapshot | undefined>',
|
||||
jsDoc: '/**\n * Explicitly retry the registered provider, or materialize the built-in\n * fallback when no provider is registered.\n * @param session - exact live session to refresh.\n * @param signal - optional caller cancellation.\n * @returns latest accepted title, or `undefined` when no eligible text exists.\n */',
|
||||
},
|
||||
{
|
||||
signature: 'register(provider: SessionTitleProvider): () => void',
|
||||
jsDoc: '/**\n * Register the sole optional title provider. Disposal aborts its pending and\n * active work before another provider may register.\n * @param provider - provider identity, cadence, and generation function.\n * @returns exact Cordis effect disposer for HMR-safe unregistration.\n */',
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
key: 'skills',
|
||||
summary: 'Registry of skill providers.',
|
||||
@@ -1227,6 +1253,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [
|
||||
name: 'MessageSourceMap',
|
||||
declaration: 'export interface MessageSourceMap {\n user: {\n kind: \'user\';\n };\n plugin: {\n kind: \'plugin\';\n plugin: string;\n };\n}',
|
||||
},
|
||||
{
|
||||
name: 'OutOfBandSessionEventMap',
|
||||
declaration: 'export interface OutOfBandSessionEventMap {\n}',
|
||||
},
|
||||
{
|
||||
name: 'OutOfBandSessionEventType',
|
||||
declaration: 'export type OutOfBandSessionEventType = Exclude<Extract<SessionEventType, keyof OutOfBandSessionEventMap>, SurfaceEventType>;',
|
||||
},
|
||||
{
|
||||
name: 'PresetOption',
|
||||
declaration: 'export interface PresetOption {\n value: string;\n name: string;\n description?: string;\n}',
|
||||
@@ -1351,6 +1385,46 @@ export const TYPE_API: readonly TypeApiEntry[] = [
|
||||
name: 'SessionRecord',
|
||||
declaration: 'export interface SessionRecord {\n header: SessionHeader;\n live: boolean;\n persisted: boolean;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleAutomaticMode',
|
||||
declaration: 'export type SessionTitleAutomaticMode = \'first-message\' | \'all-user-messages\';',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleEventData',
|
||||
declaration: 'export interface SessionTitleEventData {\n readonly title: string;\n readonly messageSeqs: number[];\n readonly source: SessionTitleSource;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleModelProvenance',
|
||||
declaration: 'export interface SessionTitleModelProvenance {\n readonly provider: string;\n readonly model: string;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleProvider',
|
||||
declaration: 'export interface SessionTitleProvider {\n readonly id: SessionTitleProviderId;\n readonly automatic: SessionTitleAutomaticMode;\n generate(request: SessionTitleProviderRequest): Promise<SessionTitleProviderResult>;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleProviderId',
|
||||
declaration: 'export type SessionTitleProviderId = Branded<\'SessionTitleProviderId\'>;',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleProviderRequest',
|
||||
declaration: 'export interface SessionTitleProviderRequest {\n readonly session: Session;\n readonly messages: readonly SessionTitleUserMessage[];\n readonly route?: SessionTitleModelProvenance;\n readonly signal: AbortSignal;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleProviderResult',
|
||||
declaration: 'export interface SessionTitleProviderResult {\n readonly title: string;\n readonly messageSeqs: readonly number[];\n readonly model?: SessionTitleModelProvenance;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleSnapshot',
|
||||
declaration: 'export interface SessionTitleSnapshot extends SessionTitleEventData {\n readonly eventSeq: number;\n readonly updatedAt: number;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleSource',
|
||||
declaration: 'export type SessionTitleSource = {\n readonly kind: \'fallback\';\n} | {\n readonly kind: \'provider\';\n readonly provider: SessionTitleProviderId;\n readonly model?: SessionTitleModelProvenance;\n};',
|
||||
},
|
||||
{
|
||||
name: 'SessionTitleUserMessage',
|
||||
declaration: 'export interface SessionTitleUserMessage {\n readonly seq: number;\n readonly text: string;\n}',
|
||||
},
|
||||
{
|
||||
name: 'SkillCandidate',
|
||||
declaration: 'export interface SkillCandidate extends SkillSummary {\n readonly rank: number;\n readonly locator: unknown;\n readonly path?: string;\n readonly metadata?: Readonly<Record<string, unknown>>;\n}',
|
||||
|
||||
@@ -15,4 +15,4 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co
|
||||
|
||||
`agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop. It runs each driver inside `ctx.agents.withInitiator()`. Extension plugins depend on `agent`, including when they need the initiating Agent, and never on `agent-loop` directly, so the loop stays swappable.
|
||||
|
||||
The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + the local [skill family](../skill/README.md) + `tool-bash` + workspace-context + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door.
|
||||
The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + fallback session titles + system-prompt + tools + agents + invariants + the local [skill family](../skill/README.md) + `tool-bash` + workspace-context + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door.
|
||||
|
||||
@@ -10,6 +10,7 @@ Creates and holds event-sourced `Session` instances. Persistence is intentionall
|
||||
|
||||
- `ctx.sessions.create(id?, { seed?, meta? }?)` validates and detaches durable seed/header data, fills the version and id, defaults `createdAt` to now, publishes the session, and binds it to the calling fiber. Persisted reconstruction supplies its original `createdAt`, `seedLength`, and `delegationDepth`.
|
||||
- `ctx.sessions.flush(session)` dispatches the awaited parallel durability checkpoint through the session's captured scope. Every listener starts and the call waits for all to settle before reporting failure; unpublished, detached, and stale objects reject.
|
||||
- `ctx.sessions.appendOutOfBand(session, type, data, trigger)` accepts only plugin event types opted into `OutOfBandSessionEventMap`. It appends directly inside an open turn; otherwise it atomically opens a zero-step plugin turn, appends, closes, and flushes. A target failure still closes and flushes the synthetic turn, and detach is deferred until the sequence settles.
|
||||
- `ctx.sessions.fork(source, boundary?, childSessionId?): Session` — Resolve a live session object or id, select a seed through the inclusive `boundary` event seq (default: current last event), require that boundary to be `turn/end`, and create a live child session with lineage metadata.
|
||||
- `ctx.sessions.get(id: SessionId): Session | undefined`
|
||||
- `ctx.sessions.list(): Session[]`
|
||||
@@ -62,7 +63,7 @@ Durable values need one accepted representation, not a check followed by a secon
|
||||
|
||||
The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog.md). Token accounting reads per-step `assistant/chunk { type: 'usage' }` records and treats `assistant/message.usage` as the committed-step fallback when no usage chunk exists; failed model-request attempts have no assistant message. Provider/model/replay provenance rides on `assistant/message`; an operational error's step is on `turn/end.reason` for `kind: 'error'`, with structured provider facts for a final model-request failure.
|
||||
|
||||
Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own types (the compaction seam's `compact/*`, bounded recovery's non-surface `llm/retry`, the hook bridges' `hook/*`); merged members appear in the same catalog.
|
||||
Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own types (the compaction seam's `compact/*`, bounded recovery's non-surface `llm/retry`, the hook bridges' `hook/*`); merged members appear in the same catalog. `OutOfBandSessionEventMap` is a separate empty-by-default marker map: an event owner must merge the same key there before `appendOutOfBand()` accepts that log-only type, while surface and lifecycle types remain excluded.
|
||||
|
||||
Also defines `TurnTriggerMap` and `TurnEndReasonMap` (merge-extensible sum types for typed turn boundaries — `kind`-tagged instead of strings). A final model-request error retains one structured `LlmFailure`; other turn errors retain message/code, and both identify the failed step.
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ Pre-composed plugin bundles a thin leaf `cordis.yml` loads instead of assembling
|
||||
|
||||
| Package | npm name | Role |
|
||||
|---|---|---|
|
||||
| `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + system-prompt + tools + skills + agents + invariants + `tool-bash` + workspace-context + `tool-skill` + `agent-loop`) |
|
||||
| `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + fallback titles + system-prompt + tools + skills + agents + invariants + `tool-bash` + workspace-context + `tool-skill` + `agent-loop`) |
|
||||
| `tui-demo/` | `@deepseek-ai/dsh-tui-demo` | Full-screen terminal app: the spine + JSONL persistence + `dsh-tui` + a pre-created `main` agent, with a boot `bin` |
|
||||
| `cli-demo/` | `@deepseek-ai/dsh-cli-demo` | Headless one-shot app: the spine + JSONL persistence + a pre-created `main` agent, with text and DSH-native JSON output |
|
||||
| `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` |
|
||||
|
||||
@@ -12,6 +12,7 @@ Read this package for the whole plugin tree and its composition order.
|
||||
@cordisjs/plugin-timer timer service (writes nothing to stdout)
|
||||
@deepseek-ai/dsh-llm abstract LLM service + content-block vocabulary
|
||||
@deepseek-ai/dsh-session event-sourced session log + store
|
||||
@deepseek-ai/dsh-session-title log-backed title service + deterministic fallback
|
||||
@deepseek-ai/dsh-system-prompt prompt-section + tool-schema assembly
|
||||
@deepseek-ai/dsh-tools registry + guarded pre/around/post/final-result pipeline
|
||||
@deepseek-ai/dsh-skill skill provider registry
|
||||
@@ -33,6 +34,7 @@ Read this package for the whole plugin tree and its composition order.
|
||||
The spine is everything COMMON to every front door. The swappable and front-door-coupled pieces stay out, picked by whatever loads the bundle:
|
||||
|
||||
- **the LLM adapter** — the bundle ships the abstract `llm` service; the leaf registers a concrete adapter on `ctx.llm` (`llm-deepseek`, `llm-pi-ai`, `llm-replay`).
|
||||
- **model-backed session-title providers** — the bundle mounts the fallback service with fixed example limits (5 words, 40 fallback bytes, 80 accepted-title bytes); a leaf may opt into exactly one first-message or all-messages LLM provider.
|
||||
- **the bash executor** — the bundle ships `tool-bash` (the consumer schema); the leaf provides `ctx.bash` (`bash-local` or a sandboxed impl).
|
||||
- **non-local skill providers** — the bundle ships the skill registry, the local filesystem provider, and the `skill` tool; deployments can add other providers such as embedded or remote catalogs as siblings.
|
||||
- **presentation + per-app infra** — the terminal TUI or ACP front door and `hmr`. These form the coupled front-door cluster that the app packages ([`dsh-tui-demo`](../tui-demo/README.md), [`dsh-acp-demo`](../acp-demo/README.md)) bake in. `timer` is in the spine because it is common and stdout-silent; front doors own stdout and remain outside.
|
||||
@@ -47,7 +49,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-spine-demo'
|
||||
// workspaceContext requires { maxBytes } or false; the other owner schemas supply defaults.
|
||||
```
|
||||
|
||||
The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — TUI and headless apps pre-create `main`, while the ACP app creates agents on demand at `session/new`; `llmRetry` to the bounded retry policy; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. Set `skills.enabled: false` to omit both the local provider and model-facing skill tool, and set `toolTasks: false` to retain the task service for foreground producers without exposing `task_output` / `task_list` / `task_kill`. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and enabled local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
|
||||
The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — TUI and headless apps pre-create `main`, while the ACP app creates agents on demand at `session/new`; `llmRetry` to the bounded retry policy; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. The session-title fallback limits are fixed example composition policy rather than bundle config. Set `skills.enabled: false` to omit both the local provider and model-facing skill tool, and set `toolTasks: false` to retain the task service for foreground producers without exposing `task_output` / `task_list` / `task_kill`. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and enabled local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
|
||||
|
||||
## Why a code bundle, not a shared YAML include
|
||||
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
# session-query/ — session retrieval capability family
|
||||
|
||||
Trusted exact reads and relationship traces over live and durable session logs. The family contains one interface package that owns `ctx.sessionQuery`, logical-corpus precedence, surface classification, bounded event reads, lineage, and direct event relationships.
|
||||
Trusted exact reads and relationship traces over live and durable session logs. The family contains one interface package that owns `ctx.sessionQuery`, logical-corpus precedence, title folding, surface classification, bounded event reads, lineage, and direct event relationships.
|
||||
|
||||
| Package | Role | ctx key |
|
||||
|---|---|---|
|
||||
| [`session-query/`](session-query/README.md) | Logical-corpus exact-read and relationship-tracing service | `ctx.sessionQuery` |
|
||||
| [`session-query/`](session-query/README.md) | Logical-corpus title, event, lineage, and relationship reads | `ctx.sessionQuery` |
|
||||
|
||||
The family is independent of compaction: it reads canonical lineage, surface operations, and logged provenance but does not participate in compaction policy or execution. Full-text search remains a proposed SQLite package rather than a speculative provider seam in this interface package.
|
||||
|
||||
@@ -5,12 +5,13 @@ Exact session-history retrieval and relationship tracing through `ctx.sessionQue
|
||||
## Reads
|
||||
|
||||
- `listSessions()` reads current persistence metadata, merges live records with live precedence, and returns cloned records in deterministic newest-first order.
|
||||
- `readTitle(sessionId)` loads one live-preferred or persisted log and folds its latest `session/title` event into a `SessionTitleSnapshot`; it returns `undefined` when the known session has no title.
|
||||
- `listEvents(sessionId)` loads the live-preferred raw log and classifies each event as `current`, `shadowed`, or `log-only` with the shared `dsh-session` surface fold.
|
||||
- `readEvent(request)` returns a cloned header, the full target event, and a bounded raw-seq window. `before` and `after` default to zero and may not exceed `readWindowMax`.
|
||||
- `traceSession(sessionId)` reads the corpus once and returns immediate-to-outward ancestors plus deterministic recursive descendant trees. `complete: false` identifies the first missing parent; a target-connected cycle fails with `SESSION_QUERY_INVALID_LINEAGE`.
|
||||
- `traceEvent(request)` loads the logical log once and returns direct positional replacements and direct logged provenance. `replacementChain` follows positional replacers to the final replacement; provenance links remain non-transitive.
|
||||
|
||||
Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. An event read or trace targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory history unreadable. Persisted event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations.
|
||||
Persistence is optional and may mount or unmount dynamically. Cross-corpus listing and lineage tracing fail with `SESSION_QUERY_PERSISTENCE_FAILED` while mounted persistence is unreadable. A title, event read, or trace targeting a known live session does not consult persistence, so durable backend health cannot make current in-memory state unreadable. Persisted title and event operations list before loading and reject a metadata mismatch rather than combining inconsistent observations. `listSessions()` remains lightweight and does not load logs or index titles.
|
||||
|
||||
`listEvents()` and `traceEvent()` run the same one-pass `dsh-session` surface fold. A loaded log is valid only when event seqs are zero-based and contiguous, surface markers obey event-type eligibility, provenance arrays are nonempty and duplicate-free, references name earlier events, and each positional replacement names and cites every surface node it removes; every violation fails with `SESSION_QUERY_INVALID_SURFACE`.
|
||||
|
||||
|
||||
@@ -6,8 +6,8 @@ Four layers, importable separately:
|
||||
|
||||
- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit, inherited stdio closure, and ACP parser exhaustion before resolving or propagating a child error, so captures are complete and callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy.
|
||||
- **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the expected-output and purity checks, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). Startup failures preserve captured agent stderr in the rejected diagnostic.
|
||||
- **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header Agent Note](../../../.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
|
||||
- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario expected-output and re-persisted-log comparisons, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.expected.md` plus `tool-schemas.expected.json`) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session.<n>.jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time.
|
||||
- **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; `session_info_update.updatedAt` → `{{updatedAt}}`; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header Agent Note](../../../.agents/notes/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
|
||||
- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario expected-output and re-persisted-log comparisons, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.expected.md` plus `tool-schemas.expected.json`) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Refresh preserves existing volatile fields by event position and gives a newly inserted `session/title` its preceding event's time, so feature-driven insertions do not churn the remainder of a fixture. Each scenario directory's `session.jsonl` plus contiguous `session.<n>.jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time.
|
||||
|
||||
A consuming `*.snapshot.ts` is the scenario table plus one factory call:
|
||||
|
||||
|
||||
@@ -4,12 +4,12 @@ Integrations that expose the agent to an external editor or client. These are **
|
||||
|
||||
| Package | Role | ctx key |
|
||||
|---|---|---|
|
||||
| `acp/` | Agent Client Protocol bridge: serves the agent to an ACP editor (Zed) over JSON-RPC stdio | (drives `ctx.agents`/`ctx.sessions`) |
|
||||
| `acp/` | Agent Client Protocol bridge: serves agents and live/replayed title updates to an ACP editor over JSON-RPC stdio | (drives `ctx.agents`/`ctx.sessions`) |
|
||||
| `user-approval/` | One-shot user-approval mechanism, closed outcome vocabulary, audit events, and per-session approval policy | `ctx.approval` |
|
||||
| `permission/` | User-facing permission presets (`workspace-write`/`danger-full-access`): one product-level select bundling the sandbox-mode and approval-policy knobs, written through to their session events | `ctx.permission` |
|
||||
| `user-interaction/` | Abstract human question/answer seam used by UI-backed confirmation tools | `ctx.userInteraction` |
|
||||
| `tool-ask-user/` | Model-facing `ask_user_question` tool over `ctx.userInteraction` | (registers on `ctx.tools`) |
|
||||
| `tui/` | Interactive pi-tui terminal channel for TTY sessions; renders `session/event`, tool presentation intents, and answers `ctx.userInteraction` | (drives `ctx.agents`) |
|
||||
| `tui/` | Interactive pi-tui terminal channel; renders session titles/events and tool intents, and answers `ctx.userInteraction` | (drives `ctx.agents`) |
|
||||
| `jsonrpc/` | Stdio JSON-RPC server for out-of-process SDK clients | (drives `ctx.agents`) |
|
||||
| `app-boot/` | Shared boot glue for the app bins: `.env` loading, fail-loud Loader guards, snapshot-aware config resolution, the settle-the-tree boot sequence | (library for the bins) |
|
||||
|
||||
|
||||
@@ -27,10 +27,10 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name:
|
||||
|---|---|---|
|
||||
| `initialize` | static | negotiate `protocolVersion`; advertise baseline prompt capabilities (`text`, plus `resource_link` rendered as text) and `loadSession: true` |
|
||||
| `session/new` | `ctx.agents.create({ sessionId, meta:{cwd} })` | creates a new session/agent; N concurrent sessions are allowed, keyed by id; `cwd` must be absolute (it becomes the session's workspace — see Per-session cwd); non-empty `additionalDirectories` and `mcpServers` rejected |
|
||||
| `session/load` | `ctx.agents.resume(...)` | reserves the id, verifies the persisted cwd, resumes, and replays user, assistant, and tool events |
|
||||
| `session/load` | `ctx.agents.resume(...)` | reserves the id, verifies the persisted cwd, resumes, and replays user, assistant, tool, and title events |
|
||||
| `session/prompt` | `agent.send()` | supports ACP `text` and `resource_link` blocks; rejects image/audio/embedded resource and empty prompts; one in-flight prompt PER session (independent); settles on the OWNING turn's end (a turn that ends in `error` rejects the RPC) |
|
||||
| `session/cancel` | `agent.cancel()` | the queue-aware cancel: aborts a running step, clears queued + steering work, and drops a turn about to start, then settles the prompt `cancelled` — for ONLY that session (a cancel never touches another session's stream or prompt) |
|
||||
| `session/update` | `session/event` | streams user replay, assistant text/reasoning, retry/failure attempt markers, and tool render intents |
|
||||
| `session/update` | `session/event` | streams user replay, assistant text/reasoning, retry/failure attempt markers, tool render intents, and `session_info_update` title revisions |
|
||||
| `elicitation/create` | `ctx.userInteraction.ask()` | maps `ask_user_question` questions to ACP form elicitations; option descriptions are shown in enum titles, `multi_select` uses ACP array enums, optionless requests use a required `custom` field, and a non-empty custom answer overrides any selected choice |
|
||||
| `session/request_permission` | `approval/request` listener | answers one-shot allow/reject requests for bridge-owned calls; foreign or call-less requests delegate and fail closed if unanswered — see "Permission prompts" |
|
||||
| `session/set_config_option` | agent-scoped request target / `ctx.permission.set()` | per-session provider+model and permission-preset switching over [session config options](https://agentclientprotocol.com/protocol/session-config-options) — see "Session config options" |
|
||||
@@ -49,6 +49,8 @@ The shared [`ctx.tasks` runtime](../../tasks/tasks/) fences access to predictabl
|
||||
|
||||
ACP updates are append-only, so `llm/retry` emits a visible separator that marks preceding partial model output discarded before the next attempt streams. A terminal model-request failure emits the same discarded-output warning; replay derives both markers from the durable events.
|
||||
|
||||
A log-only `session/title` event maps to ACP `session_info_update` with `title` and the event timestamp as `updatedAt`. The same mapping runs for live events and `session/load` replay, so an asynchronously generated late title and a restored persisted title have one wire representation without entering model history.
|
||||
|
||||
## Per-session cwd
|
||||
|
||||
`session/new` records the request's absolute cwd in the session header. Before constructing an agent, `session/load` uses persisted metadata to require an absolute request cwd that matches the stored one. Bash defaults to that workspace; an explicit relative workdir resolves against it, and multiple sessions may use different workspaces. `additionalDirectories` remains unsupported.
|
||||
@@ -112,7 +114,7 @@ Append-only; newly visible content follows the reusable request prefix and does
|
||||
|
||||
#### What the model sees
|
||||
|
||||
When optional consumers are loaded, ACP form answers become the exact JSON shape documented by `dsh-tool-ask-user`. Failures become `Error: ACP user questions must come from an agent-owned request`, `Error: ACP user question has no matching session`, `Error: ACP elicitation request failed`, `Error: ask_user_question was cancelled by the user`, `Error: ask_user_question returned no answer`, or `Error: ask_user_question was aborted before the user answered`. Permission decisions control whether another tool yields success or denial. ACP tool cards, terminal output, diffs, and streamed session updates are UI-only.
|
||||
When optional consumers are loaded, ACP form answers become the exact JSON shape documented by `dsh-tool-ask-user`. Failures become `Error: ACP user questions must come from an agent-owned request`, `Error: ACP user question has no matching session`, `Error: ACP elicitation request failed`, `Error: ask_user_question was cancelled by the user`, `Error: ask_user_question returned no answer`, or `Error: ask_user_question was aborted before the user answered`. Permission decisions control whether another tool yields success or denial. ACP tool cards, terminal output, diffs, title updates, and other streamed session updates are UI-only.
|
||||
|
||||
#### Token effect
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ Interactive terminals on macOS, Linux, and Windows are supported. Windows uses p
|
||||
|
||||
This package owns interactive terminal presentation and input only. It injects `agents`, `tools`, and `userInteraction`, then drives an agent created or resumed by app or developer code. Agent lifecycle, persistence, and the model-facing [`ask_user_question`](../tool-ask-user/README.md) tool remain separate composition entries.
|
||||
|
||||
The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions as keyboard-driven overlays. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Surface replacement events rebuild the transcript so compacted history does not reappear.
|
||||
The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions as keyboard-driven overlays. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Surface replacement events rebuild the transcript so compacted history does not reappear.
|
||||
|
||||
Before model output, session events, tool presenters, questions, configuration, or diagnostics reach pi-tui's ANSI-aware renderers or the terminal title, the TUI renders C0 and C1 controls other than line feeds as visible `\xNN` text. Those sources cannot add terminal control sequences; the TUI and pi-tui retain ownership of terminal rendering and styling.
|
||||
|
||||
@@ -18,7 +18,7 @@ While the agent is running, editor submissions call `agent.steer()`; otherwise t
|
||||
|
||||
| Key | Default | Meaning |
|
||||
|---|---|---|
|
||||
| `welcome` | `ready.` | Header subtitle |
|
||||
| `welcome` | `ready.` | Header subtitle until the session has a logged title. |
|
||||
| `sessionId` | `main` | Exact shared agent/session identity driven by the terminal |
|
||||
| `showReasoning` | `true` | Render reasoning blocks |
|
||||
| `maxToolOutputLines` | `12` | Collapsed tool-card output limit |
|
||||
@@ -27,7 +27,7 @@ While the agent is running, editor submissions call `agent.steer()`; otherwise t
|
||||
| `questionDialogMaxHeight` | `20` | Question-overlay maximum rows |
|
||||
| `showHardwareCursor` | `false` | Show the hardware cursor at pi-tui's IME marker |
|
||||
| `color` | `true` | Apply the built-in ANSI palette (see [Color](#color)) |
|
||||
| `title` | `DeepSeek Harness` | Terminal window title |
|
||||
| `title` | `DeepSeek Harness` | Product suffix for the terminal window title. |
|
||||
|
||||
```yaml
|
||||
- id: terminal
|
||||
@@ -55,7 +55,7 @@ Each non-empty editor submission becomes one text block, sent with `agent.send()
|
||||
|
||||
#### Token effect
|
||||
|
||||
Submitted text is retained under the agent loop's normal session-history and compaction rules. Headers, cards, Markdown rendering, status lines, plans, and help text add no tokens.
|
||||
Submitted text is retained under the agent loop's normal session-history and compaction rules. Headers, the logged title, cards, Markdown rendering, status lines, plans, and help text add no tokens.
|
||||
|
||||
#### KV Cache effect
|
||||
|
||||
|
||||
Reference in New Issue
Block a user