deepseek-harness/docs/persistence-catalog.md

742 lines
27 KiB
Markdown
Raw Normal View History

<!-- Generated by scripts/gen-persistence-catalog.ts — do not edit by hand.
Run `pnpm run gen-persistence-catalog` to regenerate. -->
# Session Persistence Event Catalog
Every event type that can appear in a session's durable event log: the complete persisted `SessionEvent` envelope and each member of the merge-extensible `SessionEventMap` — the owning vocabulary in `@deepseek-ai/dsh-session` plus every plugin declaration merge in this repo — with source JSDoc, full payload declaration, surface badge, and declaration site. It complements [session.md](core-data-structures/session.md) (surface ordering and the `deriveMessages()` projection), [persistence.md](core-data-structures/persistence.md) (how the log is made durable), and the [cordis events catalog](cordis-catalog/events.md) (the live bus wiring — a log event is NOT a cordis event; it reaches listeners via the single `session/event` emit).
This file is GENERATED from source (`scripts/gen-persistence-catalog.ts`) and verified fresh by `pnpm run verify-persistence-catalog` (part of `doc-sync`) — do not edit it by hand. Declaration blocks retain the source declaration and nested property JSDoc, removing only the indentation imposed by a containing interface/module, and use a `ts persistence-catalog` fence (skipped by doc-typecheck because declarations reference types from their owning modules). Type names in a payload link to the page that documents them. See [the persistence-log-catalog Agent Note](../.agents/notes/archived/process/2026-07-04-persistence-log-catalog.md).
The envelope declarations below compose each event's `type`, monotonic `seq`, epoch-ms `time`, `data`, and the conditional `surfaceOp`/`sourceEventSeqs` fields. **surface** marks a `SurfaceEventType` member: it produces an LLM message and declares how it joins the surface list. **log-only** marks everything else: a durable, replayable record with no derived-history contribution. Every payload is JSON-serializable (enforced at `Session.append`), and the whole format is pinned at `SESSION_FORMAT_VERSION = 0` — pre-release, no compatibility implied ([the version stance](core-data-structures/persistence.md)). Scope: the packages in this repo; a downstream plugin can merge further event types, which are outside this catalog by construction.
## Event envelope
```ts persistence-catalog
/** The appendable event-type keys of {@link SessionEventMap}, plugin-merged extensions included. */
export type SessionEventType = keyof SessionEventMap
/**
* The subset of {@link SessionEventType} values whose events produce LLM
* messages and are eligible to appear on the ordered surface. Only these
* event types may carry {@link SurfaceOp} and {@link SessionEvent.sourceEventSeqs}.
*/
export type SurfaceEventType =
| 'user/message'
| 'assistant/message'
| 'tool/result'
/**
* How a session event entered the ordered surface. Only valid on
* {@link SurfaceEventType} events.
*
* - `'append'`: added to the tail — normal path for user/assistant/tool
* messages.
* - `{ op: 'replace', start, end }`: replaces surface nodes from `start`
* (inclusive) through `end` (inclusive) with this node. Both must exist as
* surface nodes in the current surface. `start === end` replaces a single
* node. The node's {@link SessionEvent.sourceEventSeqs} must include every
* shadowed surface node. Used by compaction and possible other manipulations.
*/
export type SurfaceOp =
| 'append'
| { op: 'replace'; start: number; end: number }
/**
* One immutable entry in the session log.
*
* A proper discriminated union over `type` (not independent `type`/`data`
* unions), so `switch (event.type)` narrows `event.data` without casts.
*
* The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional:
* they only exist on {@link SurfaceEventType} variants (`user/message`,
* `assistant/message`, `tool/result`).
* Non-surface events (boundary markers, chunks, usage, errors) never carry
* surface metadata — the compiler enforces this at `Session.append()`
* call sites.
*/
export type SessionEvent<T extends SessionEventType = SessionEventType> = {
[K in SessionEventType]: {
type: K
/** Monotonic sequence number within the session. */
seq: number
/** Unix epoch milliseconds. */
time: number
data: SessionEventMap[K]
} & (K extends SurfaceEventType ? {
/**
* Seq numbers of events that are provenance sources of this event
* (e.g. the `assistant/chunk` seqs that built an `assistant/message`,
* or the surface nodes shadowed by a compaction replace node). An
* `assistant/message` may carry a present empty array for a known empty
* provider stream; omission means unrecorded provenance.
*/
sourceEventSeqs?: number[]
/** How this event entered the surface; absent for non-surface events. */
surfaceOp?: SurfaceOp
} : object)
}[T]
```
Sources: [`packages/core/session/src/types.ts:290`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:297`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:325`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:357`](../packages/core/session/src/types.ts)
## Events
### `agent/*`
#### `agent/inbox/spliced` — log-only
```ts persistence-catalog
/**
* One normalized mutation of an agent's durable pending-message lists.
* Live dispatch precedes projection mutation, so synchronous observers may
* read the pre-splice inbox to recover the removed messages.
*/
'agent/inbox/spliced': {
target: InboxTarget
start: number
removedCount?: number
inserted: UserMessage[]
outcome?: 'canceled'
}
```
Source: [`packages/core/agent/src/types.ts:313`](../packages/core/agent/src/types.ts)
### `approval/*`
#### `approval/asked` — log-only
```ts persistence-catalog
/**
* An approval question was put to the answerer chain — log-only audit
* (like `hook/*`; NOT a surface event, carries no `surfaceOp`). `id` pairs
* it with the `approval/decided` that always follows; `toolName` is the
* tool the question is about, `callId` the exact tool call when the asker
* had one, `reason` the asker's human-readable explanation (e.g. a hook's
* permission-decision reason).
*/
'approval/asked': {
id: ApprovalRequestId
toolName: string
callId?: CallId
reason?: string
}
```
Types: [CallId](core-data-structures/core.md)
Source: [`packages/ui/user-approval/src/index.ts:44`](../packages/ui/user-approval/src/index.ts)
#### `approval/decided` — log-only
```ts persistence-catalog
/**
* The outcome of a prior `approval/asked` (same `id`) — log-only audit.
* Exactly one per ask, appended when the outcome is known: a decision, a
* cancellation, or the fail-closed `'unavailable'`.
*/
'approval/decided': {
id: ApprovalRequestId
outcome: ApprovalOutcome
}
```
Source: [`packages/ui/user-approval/src/index.ts:55`](../packages/ui/user-approval/src/index.ts)
#### `approval/policy` — log-only
```ts persistence-catalog
/**
* The session's approval policy was switched — log-only, durable,
* replayable, never in the model transcript (the model learns the policy
* from the runtime-context snapshot and live switch notices). The LAST
* such event is the session's override ({@link effectiveApprovalPolicy}).
subagent: seed inherited policy events at creation The parent implementation introduced sandboxMode and approvalPolicy as generic SessionHeader fields, then propagated those fields through both persistence backends, session-query indexes, collision checks, policy-specific seed-boundary folds, catalogs, and a broad test matrix. That storage plane is unnecessary: Session already accepts a validated constructor seed, and persistence captures that seed when the session is announced before committing its first batch. Capture each parent override synchronously at delegation, append source-tagged sandbox/mode and approval/policy records after the optional fork prefix, and create the child with that combined seed. Keeping header.seedLength at the original fork-prefix length preserves lineage while ordinary last-event-wins folds make the inherited records outrank stale parent history and remain subordinate to later child switches. Unswitched parents still stamp nothing, so children continue to follow deployment defaults. Remove the generic header fields and every persistence/query/schema branch built around them. Collapse the inheritance suite from ten leaking scenarios to four owned-context cases covering real filesystem confinement, stale fork precedence, delegation-time capture, and the no-override path. The assembled headless snapshot now asserts the persisted inheritance event directly. This keeps the security behavior while restoring policy ownership to the existing event log and deleting the speculative durability machinery that the original tests did not exercise.
2026-07-28 21:31:17 +08:00
* `source: 'delegation'` marks an override seeded into a child; an absent
* source is a runtime switch.
*/
subagent: seed inherited policy events at creation The parent implementation introduced sandboxMode and approvalPolicy as generic SessionHeader fields, then propagated those fields through both persistence backends, session-query indexes, collision checks, policy-specific seed-boundary folds, catalogs, and a broad test matrix. That storage plane is unnecessary: Session already accepts a validated constructor seed, and persistence captures that seed when the session is announced before committing its first batch. Capture each parent override synchronously at delegation, append source-tagged sandbox/mode and approval/policy records after the optional fork prefix, and create the child with that combined seed. Keeping header.seedLength at the original fork-prefix length preserves lineage while ordinary last-event-wins folds make the inherited records outrank stale parent history and remain subordinate to later child switches. Unswitched parents still stamp nothing, so children continue to follow deployment defaults. Remove the generic header fields and every persistence/query/schema branch built around them. Collapse the inheritance suite from ten leaking scenarios to four owned-context cases covering real filesystem confinement, stale fork precedence, delegation-time capture, and the no-override path. The assembled headless snapshot now asserts the persisted inheritance event directly. This keeps the security behavior while restoring policy ownership to the existing event log and deleting the speculative durability machinery that the original tests did not exercise.
2026-07-28 21:31:17 +08:00
'approval/policy': {
policy: ApprovalPolicy
/** Marks an override seeded into a child at delegation. */
source?: 'delegation'
}
```
Source: [`packages/ui/user-approval/src/index.ts:67`](../packages/ui/user-approval/src/index.ts)
### `assistant/*`
#### `assistant/chunk` — log-only
```ts persistence-catalog
/** Raw stream chunk — token-level replay fidelity. */
'assistant/chunk': { turn: number; step: number; chunk: StreamChunk }
```
Types: [StreamChunk](core-data-structures/llm-streaming.md)
Source: [`packages/core/session/src/types.ts:220`](../packages/core/session/src/types.ts)
#### `assistant/message` — surface
```ts persistence-catalog
/**
* Assembled assistant message for one step (derived history uses this).
* Carries the step's `usage` when the adapter reported token accounting, so
* the model output and its accounting travel together (there is no separate
* usage record). `usage` is absent when the adapter reported none.
*/
'assistant/message': { turn: number; step: number; message: AssistantMessage; usage?: TokenUsage }
```
Types: [TokenUsage](core-data-structures/llm-streaming.md)
Source: [`packages/core/session/src/types.ts:227`](../packages/core/session/src/types.ts)
### `command/*`
#### `command/done` — log-only
```ts persistence-catalog
/**
* The paired command settled. `kind`/`text` carry the handler's verbatim
* outcome (a thrown/aborted handler settles as `kind: 'error'` with the
* rendered failure); presentation stays client-computed at render time.
*/
'command/done': { commandId: CommandId; kind: 'success' | 'error'; text?: string }
```
2026-07-28 16:50:07 +08:00
Source: [`packages/ui/commands/src/index.ts:138`](../packages/ui/commands/src/index.ts)
#### `command/run` — log-only
```ts persistence-catalog
/**
* A resolved slash command entered its handler. Log-only (never model
* surface); paired with `command/done` by `commandId`, mirroring the
* `tool/call`↔`tool/result` pairing. The payload is structured — `name`
* and `args` are `parseCommand`'s own split (name and verbatim rawInput,
* separator whitespace included), so a consumer (a projection unit
* folding its own command records, a rich command card) never re-parses
* a line.
*/
'command/run': { commandId: CommandId; name: string; args: string; source: CommandSource }
```
2026-07-28 16:50:07 +08:00
Source: [`packages/ui/commands/src/index.ts:132`](../packages/ui/commands/src/index.ts)
### `compact/*`
#### `compact/end` — log-only
```ts persistence-catalog
/**
* Marks the end of a compaction — log-only, releases the lock. Its owner
* matches `compact/start`; `error` records an unsuccessful attempt.
*/
'compact/end': { turn: number | null; error?: string }
```
Source: [`packages/compact/compact/src/types.ts:54`](../packages/compact/compact/src/types.ts)
#### `compact/prune` — log-only
```ts persistence-catalog
/**
* Shadow price of one model-free prune replacement — log-only, no
* surfaceOp. The shared shadow-price protocol: a surface `replace` event
* is priced by the metering event immediately before it (`compact/summary`
* for a summarizing compaction, this event for a prune), which states the
* heuristic token price of the exact replaced range so a pure consumer
* can subtract it without retaining per-node prices. The replacement MUST
* be appended synchronously right after this event.
*/
'compact/prune': {
/** The replaced range's first and last surface-node seqs (a surface-position span, like {@link CompactionResult.shadowedRange}). */
shadowedRange: { start: number; end: number }
/** The seqs of all shadowed surface nodes, in surface order. */
shadowedSeqs: number[]
/** Heuristic price of the shadowed content under the token-meter's fixed estimator. */
shadowedTokenCount: number
}
```
Source: [`packages/compact/compact/src/types.ts:64`](../packages/compact/compact/src/types.ts)
#### `compact/start` — log-only
```ts persistence-catalog
/**
* Marks the start of a compaction — log-only, holds the lock until
* `compact/end`. A numbered owner is strictly enclosed by that open turn;
* `null` identifies a standalone manual transaction between turns.
*/
'compact/start': { turn: number | null }
```
Source: [`packages/compact/compact/src/types.ts:19`](../packages/compact/compact/src/types.ts)
#### `compact/summary` — log-only
```ts persistence-catalog
/**
* Provenance record of a completed summarization — log-only, no surfaceOp.
* The summary content is in `data.summary`; the actual surface replacement
* is performed by the immediately following `user/message` event that
* shadows the compacted range. That adjacency is contractual — the
* shadowed pricing fields are the replacement's shadow price, so a
* consumer may pair a replacement with the metering event directly
* before it (`compact/prune` documents the shared protocol).
*/
'compact/summary': {
summary: ContentBlock[]
/** Complete provider output before the backend's safe summary projection. */
rawOutput?: ContentBlock[]
shadowedRange: { start: number; end: number }
shadowedSeqs: number[]
shadowedTokenCount: number
/** The provider route that wrote the summary. */
provider: string
/**
* The model that wrote the summary — the summarize call's envelope,
* reported by the backend that made the call, logged so the one-shot
* request is reconstructable from log + code and "which model wrote
2026-07-19 22:50:49 +08:00
* this summary" has a durable answer (the reconstructability Agent Note).
*/
model: string
/** The generation cap the summarize call sent, when one applied. */
maxTokens?: number
/** Provider-reported token usage for the summarization request, when emitted. */
usage?: TokenUsage
}
```
Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md)
Source: [`packages/compact/compact/src/types.ts:29`](../packages/compact/compact/src/types.ts)
### `goal/*`
#### `goal/change` — log-only
```ts persistence-catalog
/**
* Complete post-mutation goal state or clear tombstone.
*/
'goal/change': GoalChangeMeta
```
Source: [`packages/goal/goal/src/domain.ts:81`](../packages/goal/goal/src/domain.ts)
### `hook/*`
#### `hook/invoked` — log-only
```ts persistence-catalog
/**
* A hook command was invoked at a hook point — log-only provenance (like
* `compact/*`; NOT a {@link SurfaceEventType}, carries no `surfaceOp`).
* `dialect` is the bridge that ran it (`claude`/`codex`), `point`
* the hook point (`PreToolUse`, `Stop`, …), `matcher` the matcher-group
* pattern that selected it (absent for match-all), `handlerId` a stable id
* for the command (so an invoked/result pair correlates). `turn` is the open
* turn the invocation lives inside.
*/
'hook/invoked': {
turn: number
point: string
dialect: HookDialect
matcher?: string
handlerId: string
}
```
2026-07-12 03:36:43 +08:00
Source: [`packages/hooks/hook-protocol/src/types.ts:19`](../packages/hooks/hook-protocol/src/types.ts)
#### `hook/result` — log-only
```ts persistence-catalog
/**
* Log-only outcome paired to `hook/invoked` by `handlerId`. Decision is the
* parsed permission result, `stop` for `continue:false`, or `pass`; exit code
* may be absent, stderr is bounded, and duration is wall-clock runtime.
*/
'hook/result': {
turn: number
point: string
handlerId: string
decision: string
exitCode?: number
stderrSummary?: string
durationMs: number
}
```
Source: [`packages/hooks/hook-protocol/src/types.ts:31`](../packages/hooks/hook-protocol/src/types.ts)
### `llm/*`
#### `llm/retry` — log-only
```ts persistence-catalog
/** Durable, non-surface record of one provider-routed retry scheduled after a failed request attempt. */
'llm/retry': {
turn: number
step: number
provider: string
mode: 'normal'
policyKey: string
retry: number
maxRetries: number
delayMs: number
failure: LlmFailure
} | {
turn: number
step: number
provider: string
mode: 'always'
policyKey: string
retry: number
delayMs: number
failure: LlmFailure
}
```
Source: [`packages/llm/llm-retry/src/index.ts:17`](../packages/llm/llm-retry/src/index.ts)
feat(permission): user-facing permission presets — one Permissions select over the two knobs A preset names a bundle of the two mechanism knobs — request = workspace-write + ask, yolo = danger-full-access + never — so the editor shows ONE 'Permissions' select where the sandbox-mode and approval-policy tiers stay orthogonal capabilities (the Codex /approvals shape: presets over two dials). ctx.permission (dsh-permission) owns the config-defined table, validates the default preset's bundle against the composed knob defaults at load (fails loud), and writes a switch THROUGH: one log-only permission/preset event (the audit fact reverse-mapping cannot recover — the planned 'agent' preset shares request's knob values and differs only in composed policy) plus each knob event via its own setter, deduped — a net-zero switch appends nothing. Every knob consumer keeps reading its own fold, untouched. The current preset DERIVES from the effective knob values — the fold breaks bundle ties, a knob state outside the table is the reserved 'custom' value (a state, not an error: shown while it holds, switchable FROM, never a target), and defaultPreset disappears (zero-event state reverse-maps from the composition defaults). The ACP bridge drops the two per-knob selects for the one preset select (advertised only when ctx.permission is composed); pending/anchor/no-op semantics carry over unchanged, with the no-op echo acknowledged before vocabulary validation so a client re-pushing a derived 'custom' current never errors. The sandbox variant example composes the service with a workspace-write default; the permission-switching, escalation-approved and escalation-rejected scenarios are re-recorded under it (escalations now target an outside-workspace /tmp path under danger-full-access, self-cleaning) and config-options is re-authored on the single-select wire.
2026-07-12 21:03:41 +08:00
### `permission/*`
#### `permission/preset` — log-only
```ts persistence-catalog
/**
* Records the selected preset as durable, log-only user intent. The knob
* events follow in the same turn and control execution; this event stays
* out of the model transcript and lets {@link effectivePermissionPreset}
* preserve a selection when bundles match.
*/
feat(permission): user-facing permission presets — one Permissions select over the two knobs A preset names a bundle of the two mechanism knobs — request = workspace-write + ask, yolo = danger-full-access + never — so the editor shows ONE 'Permissions' select where the sandbox-mode and approval-policy tiers stay orthogonal capabilities (the Codex /approvals shape: presets over two dials). ctx.permission (dsh-permission) owns the config-defined table, validates the default preset's bundle against the composed knob defaults at load (fails loud), and writes a switch THROUGH: one log-only permission/preset event (the audit fact reverse-mapping cannot recover — the planned 'agent' preset shares request's knob values and differs only in composed policy) plus each knob event via its own setter, deduped — a net-zero switch appends nothing. Every knob consumer keeps reading its own fold, untouched. The current preset DERIVES from the effective knob values — the fold breaks bundle ties, a knob state outside the table is the reserved 'custom' value (a state, not an error: shown while it holds, switchable FROM, never a target), and defaultPreset disappears (zero-event state reverse-maps from the composition defaults). The ACP bridge drops the two per-knob selects for the one preset select (advertised only when ctx.permission is composed); pending/anchor/no-op semantics carry over unchanged, with the no-op echo acknowledged before vocabulary validation so a client re-pushing a derived 'custom' current never errors. The sandbox variant example composes the service with a workspace-write default; the permission-switching, escalation-approved and escalation-rejected scenarios are re-recorded under it (escalations now target an outside-workspace /tmp path under danger-full-access, self-cleaning) and config-options is re-authored on the single-select wire.
2026-07-12 21:03:41 +08:00
'permission/preset': { preset: string }
```
Source: [`packages/ui/permission/src/index.ts:50`](../packages/ui/permission/src/index.ts)
feat(permission): user-facing permission presets — one Permissions select over the two knobs A preset names a bundle of the two mechanism knobs — request = workspace-write + ask, yolo = danger-full-access + never — so the editor shows ONE 'Permissions' select where the sandbox-mode and approval-policy tiers stay orthogonal capabilities (the Codex /approvals shape: presets over two dials). ctx.permission (dsh-permission) owns the config-defined table, validates the default preset's bundle against the composed knob defaults at load (fails loud), and writes a switch THROUGH: one log-only permission/preset event (the audit fact reverse-mapping cannot recover — the planned 'agent' preset shares request's knob values and differs only in composed policy) plus each knob event via its own setter, deduped — a net-zero switch appends nothing. Every knob consumer keeps reading its own fold, untouched. The current preset DERIVES from the effective knob values — the fold breaks bundle ties, a knob state outside the table is the reserved 'custom' value (a state, not an error: shown while it holds, switchable FROM, never a target), and defaultPreset disappears (zero-event state reverse-maps from the composition defaults). The ACP bridge drops the two per-knob selects for the one preset select (advertised only when ctx.permission is composed); pending/anchor/no-op semantics carry over unchanged, with the no-op echo acknowledged before vocabulary validation so a client re-pushing a derived 'custom' current never errors. The sandbox variant example composes the service with a workspace-write default; the permission-switching, escalation-approved and escalation-rejected scenarios are re-recorded under it (escalations now target an outside-workspace /tmp path under danger-full-access, self-cleaning) and config-options is re-authored on the single-select wire.
2026-07-12 21:03:41 +08:00
### `plan/*`
#### `plan/mode` — log-only
```ts persistence-catalog
/**
* Whether plan mode is in force from this point on: log-only, non-surface,
* whole-value replace. The last `plan/mode` wins; a log with none folds to
* inactive through {@link foldPlanMode}.
*/
'plan/mode': { active: boolean }
```
Source: [`packages/plan/plan-mode/src/index.ts:52`](../packages/plan/plan-mode/src/index.ts)
### `request/*`
#### `request/context` — log-only
```ts persistence-catalog
/**
* Route metadata for the next request, logged only when the route or capacity
* changes. It does not participate in request reconstruction or header equality.
*/
'request/context': RequestContext
```
Source: [`packages/core/session/src/types.ts:263`](../packages/core/session/src/types.ts)
#### `request/header` — log-only
```ts persistence-catalog
/**
* Full header for the next request, appended inside its step before dispatch.
* It is log-only; the latest snapshot reconstructs the request header.
*/
'request/header': { header: EpochHeader; reason: RequestHeaderReason }
```
Source: [`packages/core/session/src/types.ts:258`](../packages/core/session/src/types.ts)
feat(sandbox): cross-family file sandbox — one policy home, sandboxed fs provider, fs escalation parity Extend SandboxMode enforcement from bash to the filesystem tools, the sandbox RFC's deferred cross-family phase. - dsh-sandbox-policy (new, ctx.sandboxPolicy): the single home for the deployment default mode + workspaceRoot and the per-session override event, renamed bash/sandbox-mode -> sandbox/mode and moved here with its fold/setter. Decouples the bash seam from dsh-session. - dsh-fs-sandbox (new): SandboxedFileSystem extends LocalFileSystem and fences write/edit by the per-call mode (read-only denies, workspace-write contains to the workspace + temp roots via the shared writableRoots, danger passes through); reads pass through. Structured FS_SANDBOX_DENIED; in-lock parent re-canonicalization. A policy fence in trusted code, not a kernel boundary. - dsh-sandbox: the shared escalation kit (writableRoots, the strictly-wider ladder, denial/hint markers, approveEscalation) both tool families use; approveEscalation takes a structural approver so dsh-sandbox gains no approval/agent dependency, and both tools stay duplication-free. - tool-fs: write/edit advertise sandbox_permissions/justification under a confining ctx.fs, map FS_SANDBOX_DENIED to the shared [sandbox: ...] marker, and resolve the same one-approved-wider retry. - examples/acp-agent: composes sandbox-policy + fs-sandbox, drops the gating that disabled the fs stack under confined modes. RFC docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md; the old sandbox RFC's In-process/deferred/FAQ sections updated to shipped fact.
2026-07-14 20:05:57 +08:00
### `sandbox/*`
#### `sandbox/mode` — log-only
```ts persistence-catalog
Merge remote-tracking branch 'origin/master' into cross-family-fs-sandbox # Conflicts: # .agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.i18n.yaml # .agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md # .agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.zh.md # docs/capability-seams.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/module-graph.md # docs/persistence-catalog.md # docs/rfc/INDEX.md # examples/acp-agent/README.md # examples/acp-agent/fs.cordis.snapshot.yml # examples/acp-agent/fs.cordis.yml # examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl # examples/acp-agent/tests/snapshots/permission-switching/session.jsonl # examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md # examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json # examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md # examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json # packages/bash/bash/src/index.ts # packages/bash/tool-bash/package.json # packages/bash/tool-bash/src/index.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/fs/README.md # packages/fs/tool-fs/src/edit.ts # packages/fs/tool-fs/src/write.ts # packages/sandbox/README.md # pnpm-lock.yaml
2026-07-20 11:40:29 +08:00
/**
* The session's sandbox mode was switched — log-only (like `approval/*`;
* NOT a surface event, carries no `surfaceOp`): durable and replayable,
* never in the model transcript. The LAST such event is the session's
subagent: seed inherited policy events at creation The parent implementation introduced sandboxMode and approvalPolicy as generic SessionHeader fields, then propagated those fields through both persistence backends, session-query indexes, collision checks, policy-specific seed-boundary folds, catalogs, and a broad test matrix. That storage plane is unnecessary: Session already accepts a validated constructor seed, and persistence captures that seed when the session is announced before committing its first batch. Capture each parent override synchronously at delegation, append source-tagged sandbox/mode and approval/policy records after the optional fork prefix, and create the child with that combined seed. Keeping header.seedLength at the original fork-prefix length preserves lineage while ordinary last-event-wins folds make the inherited records outrank stale parent history and remain subordinate to later child switches. Unswitched parents still stamp nothing, so children continue to follow deployment defaults. Remove the generic header fields and every persistence/query/schema branch built around them. Collapse the inheritance suite from ten leaking scenarios to four owned-context cases covering real filesystem confinement, stale fork precedence, delegation-time capture, and the no-override path. The assembled headless snapshot now asserts the persisted inheritance event directly. This keeps the security behavior while restoring policy ownership to the existing event log and deleting the speculative durability machinery that the original tests did not exercise.
2026-07-28 21:31:17 +08:00
* override ({@link effectiveSandboxMode}). `source: 'delegation'` marks
* an override seeded into a child; an absent source is a runtime switch.
Merge remote-tracking branch 'origin/master' into cross-family-fs-sandbox # Conflicts: # .agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.i18n.yaml # .agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md # .agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.zh.md # docs/capability-seams.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/module-graph.md # docs/persistence-catalog.md # docs/rfc/INDEX.md # examples/acp-agent/README.md # examples/acp-agent/fs.cordis.snapshot.yml # examples/acp-agent/fs.cordis.yml # examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl # examples/acp-agent/tests/snapshots/permission-switching/session.jsonl # examples/acp-agent/tests/snapshots/workspace-context/system-prompt.expected.md # examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json # examples/acp-agent/tests/snapshots/workspace-edit/system-prompt.expected.md # examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.expected.json # packages/bash/bash/src/index.ts # packages/bash/tool-bash/package.json # packages/bash/tool-bash/src/index.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/fs/README.md # packages/fs/tool-fs/src/edit.ts # packages/fs/tool-fs/src/write.ts # packages/sandbox/README.md # pnpm-lock.yaml
2026-07-20 11:40:29 +08:00
*/
subagent: seed inherited policy events at creation The parent implementation introduced sandboxMode and approvalPolicy as generic SessionHeader fields, then propagated those fields through both persistence backends, session-query indexes, collision checks, policy-specific seed-boundary folds, catalogs, and a broad test matrix. That storage plane is unnecessary: Session already accepts a validated constructor seed, and persistence captures that seed when the session is announced before committing its first batch. Capture each parent override synchronously at delegation, append source-tagged sandbox/mode and approval/policy records after the optional fork prefix, and create the child with that combined seed. Keeping header.seedLength at the original fork-prefix length preserves lineage while ordinary last-event-wins folds make the inherited records outrank stale parent history and remain subordinate to later child switches. Unswitched parents still stamp nothing, so children continue to follow deployment defaults. Remove the generic header fields and every persistence/query/schema branch built around them. Collapse the inheritance suite from ten leaking scenarios to four owned-context cases covering real filesystem confinement, stale fork precedence, delegation-time capture, and the no-override path. The assembled headless snapshot now asserts the persisted inheritance event directly. This keeps the security behavior while restoring policy ownership to the existing event log and deleting the speculative durability machinery that the original tests did not exercise.
2026-07-28 21:31:17 +08:00
'sandbox/mode': {
mode: SandboxMode
/** Marks an override seeded into a child at delegation. */
source?: 'delegation'
}
feat(sandbox): cross-family file sandbox — one policy home, sandboxed fs provider, fs escalation parity Extend SandboxMode enforcement from bash to the filesystem tools, the sandbox RFC's deferred cross-family phase. - dsh-sandbox-policy (new, ctx.sandboxPolicy): the single home for the deployment default mode + workspaceRoot and the per-session override event, renamed bash/sandbox-mode -> sandbox/mode and moved here with its fold/setter. Decouples the bash seam from dsh-session. - dsh-fs-sandbox (new): SandboxedFileSystem extends LocalFileSystem and fences write/edit by the per-call mode (read-only denies, workspace-write contains to the workspace + temp roots via the shared writableRoots, danger passes through); reads pass through. Structured FS_SANDBOX_DENIED; in-lock parent re-canonicalization. A policy fence in trusted code, not a kernel boundary. - dsh-sandbox: the shared escalation kit (writableRoots, the strictly-wider ladder, denial/hint markers, approveEscalation) both tool families use; approveEscalation takes a structural approver so dsh-sandbox gains no approval/agent dependency, and both tools stay duplication-free. - tool-fs: write/edit advertise sandbox_permissions/justification under a confining ctx.fs, map FS_SANDBOX_DENIED to the shared [sandbox: ...] marker, and resolve the same one-approved-wider retry. - examples/acp-agent: composes sandbox-policy + fs-sandbox, drops the gating that disabled the fs stack under confined modes. RFC docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md; the old sandbox RFC's In-process/deferred/FAQ sections updated to shipped fact.
2026-07-14 20:05:57 +08:00
```
subagent: seed inherited policy events at creation The parent implementation introduced sandboxMode and approvalPolicy as generic SessionHeader fields, then propagated those fields through both persistence backends, session-query indexes, collision checks, policy-specific seed-boundary folds, catalogs, and a broad test matrix. That storage plane is unnecessary: Session already accepts a validated constructor seed, and persistence captures that seed when the session is announced before committing its first batch. Capture each parent override synchronously at delegation, append source-tagged sandbox/mode and approval/policy records after the optional fork prefix, and create the child with that combined seed. Keeping header.seedLength at the original fork-prefix length preserves lineage while ordinary last-event-wins folds make the inherited records outrank stale parent history and remain subordinate to later child switches. Unswitched parents still stamp nothing, so children continue to follow deployment defaults. Remove the generic header fields and every persistence/query/schema branch built around them. Collapse the inheritance suite from ten leaking scenarios to four owned-context cases covering real filesystem confinement, stale fork precedence, delegation-time capture, and the no-override path. The assembled headless snapshot now asserts the persisted inheritance event directly. This keeps the security behavior while restoring policy ownership to the existing event log and deleting the speculative durability machinery that the original tests did not exercise.
2026-07-28 21:31:17 +08:00
Source: [`packages/sandbox/sandbox-policy/src/session-mode.ts:33`](../packages/sandbox/sandbox-policy/src/session-mode.ts)
### `session/*`
#### `session/end-seed` — log-only
```ts persistence-catalog
/**
* Marks the end of a constructor seed. Events before it have smaller seq
* values and came from the seed (resume, fork, or replay); this lifecycle
* produced none of them. This log-only event is the durable projection of
* {@link Session.firstLiveSeq}. Its payload is empty — position and `time`
* carry the meaning.
*
* Locate the LAST one in stored history. A seed already ending in one is not
* re-marked, so reopening an untouched session does not grow its log per
* pickup and the event need not be at the current `firstLiveSeq`.
fix(session): close the review gaps the boundary opened - `SessionSummary.updatedAt`'s wire doc still said "Persisted file mtime", which stopped being true for attached sessions. - The core invariant let `session/inherited` fall through the merge-extensible default. It is core-owned, so it gets an explicit case; an unbalanced seed legally places it inside an open turn, which the relation permits. - The Agent Note claimed the boundary reaches disk via `live.pending`/ `scheduleDrain`. Verified false: the constructor append precedes `enter()`, so it never publishes on `session/event` and rides the creation seed instead. Attaching is therefore a write where none happened before — recorded, since only `load()` stays a pure read. - The deferred-index proposal asserted this change documented the cold-mtime skew on `dsh-host-apiproxy`. It did not; the README entry now exists. - `firstLiveSeq`'s firehose gap runs through its own seq, not below it. - The boundary is not always at `firstLiveSeq` (the idempotence guard), so consumers scan for the last one. - `lastActivityTime` excludes by type, so a pickup time still leaks onto a synthetic closer when a boundary ends an open turn. Documented. - Pin the fork claim end-to-end: a child inherits a still-running parent's open bracket below its own boundary, while the parent has none. Fails if the write moves back to the load path. - Fix the telemetry title that contradicted its own assertions. The `/status` call site cannot be pinned the way the other two are: the command appends its own `command/run` before rendering, so the boundary is never the log tail there. Its fixture now at least renders over a boundary-bearing log.
2026-07-30 13:59:08 +08:00
*
* `Session`'s constructor is the only legitimate writer. The invariant
* companion deliberately constrains nothing here, so a plugin appending one
* would silently classify every live bracket before it as seed history.
*
* An owner of a standalone open/close bracket (`compact/start` …
* `compact/end`) reads it because seed history and live work are otherwise
* byte-identical: an unmatched opening marker before this event belongs to
* an ended lifecycle, whatever ended it. NOT a liveness signal about other
* writers — a concurrently live session holds its own boundary elsewhere,
* so tolerating concurrent writers needs a signal beyond the log.
*/
'session/end-seed': Record<string, never>
```
Source: [`packages/core/session/src/types.ts:286`](../packages/core/session/src/types.ts)
#### `session/title` — log-only
```ts persistence-catalog
/**
* Latest-wins session title snapshot. Log-only: it never enters the model
* surface or derived history.
*/
'session/title': SessionTitleEventData
```
Types: [SessionTitleEventData](core-data-structures/session-title.md)
Source: [`packages/session-title/session-title/src/index.ts:100`](../packages/session-title/session-title/src/index.ts)
#### `session/title-llm-request` — log-only
```ts persistence-catalog
/** Log-only pre-dispatch record of one session-title model request. */
'session/title-llm-request': SessionTitleLlmRequestEventData
```
Types: [SessionTitleLlmRequestEventData](core-data-structures/session-title.md)
Source: [`packages/session-title/session-title-llm/src/index.ts:43`](../packages/session-title/session-title-llm/src/index.ts)
### `step/*`
#### `step/end` — log-only
```ts persistence-catalog
/** Closes step `step` of turn `turn`. */
'step/end': { turn: number; step: number }
```
Source: [`packages/core/session/src/types.ts:210`](../packages/core/session/src/types.ts)
#### `step/start` — log-only
```ts persistence-catalog
/** Opens step `step` of turn `turn` — one model call plus the tool executions it requested. */
'step/start': { turn: number; step: number }
```
Source: [`packages/core/session/src/types.ts:208`](../packages/core/session/src/types.ts)
### `subagent/*`
#### `subagent/descriptor` — log-only
```ts persistence-catalog
/**
* Durable identity and lifecycle mode of a session-backed subagent child,
* appended once by the establishing provider inside the child's initial
* turn, before its first request. Continuable records also carry their
* resumable composition. Log-only: it carries no `surfaceOp`, never enters
* model history, and survives compaction.
*/
'subagent/descriptor': SubagentDescriptorData
```
Source: [`packages/subagent/subagent/src/descriptor.ts:37`](../packages/subagent/subagent/src/descriptor.ts)
### `todo/*`
#### `todo/write` — log-only
```ts persistence-catalog
/** Whole-list snapshot; latest write wins on replay. Log-only UI state; never derived history. */
'todo/write': { todos: TodoItem[] }
```
Types: [TodoItem](core-data-structures/session.md)
Source: [`packages/core/session/src/types.ts:253`](../packages/core/session/src/types.ts)
### `tool/*`
#### `tool/call` — log-only
```ts persistence-catalog
/**
* The model requested one tool invocation: `name` with the raw `arguments`
* JSON string exactly as the model produced it (unparsed). `callId` pairs the
* call with its `tool/result`.
*/
'tool/call': { turn: number; step: number; callId: CallId; name: string; arguments: string }
```
Types: [CallId](core-data-structures/core.md)
Source: [`packages/core/session/src/types.ts:233`](../packages/core/session/src/types.ts)
feat: Code Mode — the registry's mode config, the SDK codegen, and the run_code bridge The dsh-tools half of the Code Mode RFC (its fourth, final change): the registry gains its first config — mode: native | code | both — and OWNS how its tools reach the model. 'code' contributes exactly one wire tool, run_code, plus a lazy tools:sdk prompt section declaring every other tool as a generated TypeScript API (jsonSchemaToTs: total over the defineTool subset, unknown degradation, lexicographic byte-identical rendering); 'both' ships both representations; 'native' is byte-for-byte the old behavior. Non-native modes fail every assembly loudly without a typescript-language ctx.codeRuntime. run_code's dispatch bridge: JSON-normalizes each binding argument before dispatch (what dispatches is what the tool/code-dispatch event logs — the append can never fail on payload shape; BigInt/circulars reject that one call), serializes all program tool calls through a per-run queue (even Promise.all — no concurrency-safety metadata yet), routes every sub-call through tools/pre-execute → tools/post-execute (a deny rejects the program-side promise), drops sub-call additionalContext (no safe outlet mid-run; pinned), owns a run-scoped abort that follows the outer signal in and fires on settlement (in-flight sub-dispatch aborted, queued abandoned, queue drained before returning), and converts a failed run into CodeRunFailedError → a structured isError carrying kind + captured logs. tool/code-dispatch joins SessionEventMap by declaration merging (log-only; deriveMessages ignores it). The composed surface: the tools config forwards through agent-core and both app packages; examples/code-agent + demo:code run the worker runtime under mode code (keyless boot smoke + a with-key e2e proving the collapsed [run_code] header, the dispatch events, and the file the program wrote); two new snapshot scenarios (code-mode-turn, both-mode-turn) record the SDK section, collapsed header, dispatch events, and result card — each its own header-pinning class (the harness gains per-scenario config overlays and per-class pins). Catalogs, graphs, cookbook, hooks-bridge notes, and the RFC (moved to implemented/, restructured to decision-era headings) updated in the same change.
2026-07-08 12:58:23 +08:00
#### `tool/code-dispatch` — log-only
```ts persistence-catalog
/**
* One bridged sub-dispatch SETTLING: the pairing ids (matching the
* `tool/code-dispatch-start` with the same `subCallId`), the tool `name`
* with the same JSON-normalized `arguments`, and the sub-call's complete
* model-facing outcome in `tool/result`'s own vocabulary
* (`content` + `isError`), so UIs render a sub-call through the exact
* code path that renders a native call. Every started sub-call settles
* with exactly one of these (abort included: the aborted pipeline result
* is an `isError` outcome).
* Log-only: `deriveMessages()` ignores it, so sub-calls never re-enter
* model context; persistence and UIs get every call. Appended inside the
* parent `run_code`'s execution (the bridge drains in-flight dispatches
* before returning), so its execution-enclosure relation holds by
* construction.
*/
'tool/code-dispatch': { parentCallId: CallId; subCallId: CallId; name: string; arguments: unknown; isError: boolean; content: ContentBlock[] }
feat: Code Mode — the registry's mode config, the SDK codegen, and the run_code bridge The dsh-tools half of the Code Mode RFC (its fourth, final change): the registry gains its first config — mode: native | code | both — and OWNS how its tools reach the model. 'code' contributes exactly one wire tool, run_code, plus a lazy tools:sdk prompt section declaring every other tool as a generated TypeScript API (jsonSchemaToTs: total over the defineTool subset, unknown degradation, lexicographic byte-identical rendering); 'both' ships both representations; 'native' is byte-for-byte the old behavior. Non-native modes fail every assembly loudly without a typescript-language ctx.codeRuntime. run_code's dispatch bridge: JSON-normalizes each binding argument before dispatch (what dispatches is what the tool/code-dispatch event logs — the append can never fail on payload shape; BigInt/circulars reject that one call), serializes all program tool calls through a per-run queue (even Promise.all — no concurrency-safety metadata yet), routes every sub-call through tools/pre-execute → tools/post-execute (a deny rejects the program-side promise), drops sub-call additionalContext (no safe outlet mid-run; pinned), owns a run-scoped abort that follows the outer signal in and fires on settlement (in-flight sub-dispatch aborted, queued abandoned, queue drained before returning), and converts a failed run into CodeRunFailedError → a structured isError carrying kind + captured logs. tool/code-dispatch joins SessionEventMap by declaration merging (log-only; deriveMessages ignores it). The composed surface: the tools config forwards through agent-core and both app packages; examples/code-agent + demo:code run the worker runtime under mode code (keyless boot smoke + a with-key e2e proving the collapsed [run_code] header, the dispatch events, and the file the program wrote); two new snapshot scenarios (code-mode-turn, both-mode-turn) record the SDK section, collapsed header, dispatch events, and result card — each its own header-pinning class (the harness gains per-scenario config overlays and per-class pins). Catalogs, graphs, cookbook, hooks-bridge notes, and the RFC (moved to implemented/, restructured to decision-era headings) updated in the same change.
2026-07-08 12:58:23 +08:00
```
Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md)
feat: Code Mode — the registry's mode config, the SDK codegen, and the run_code bridge The dsh-tools half of the Code Mode RFC (its fourth, final change): the registry gains its first config — mode: native | code | both — and OWNS how its tools reach the model. 'code' contributes exactly one wire tool, run_code, plus a lazy tools:sdk prompt section declaring every other tool as a generated TypeScript API (jsonSchemaToTs: total over the defineTool subset, unknown degradation, lexicographic byte-identical rendering); 'both' ships both representations; 'native' is byte-for-byte the old behavior. Non-native modes fail every assembly loudly without a typescript-language ctx.codeRuntime. run_code's dispatch bridge: JSON-normalizes each binding argument before dispatch (what dispatches is what the tool/code-dispatch event logs — the append can never fail on payload shape; BigInt/circulars reject that one call), serializes all program tool calls through a per-run queue (even Promise.all — no concurrency-safety metadata yet), routes every sub-call through tools/pre-execute → tools/post-execute (a deny rejects the program-side promise), drops sub-call additionalContext (no safe outlet mid-run; pinned), owns a run-scoped abort that follows the outer signal in and fires on settlement (in-flight sub-dispatch aborted, queued abandoned, queue drained before returning), and converts a failed run into CodeRunFailedError → a structured isError carrying kind + captured logs. tool/code-dispatch joins SessionEventMap by declaration merging (log-only; deriveMessages ignores it). The composed surface: the tools config forwards through agent-core and both app packages; examples/code-agent + demo:code run the worker runtime under mode code (keyless boot smoke + a with-key e2e proving the collapsed [run_code] header, the dispatch events, and the file the program wrote); two new snapshot scenarios (code-mode-turn, both-mode-turn) record the SDK section, collapsed header, dispatch events, and result card — each its own header-pinning class (the harness gains per-scenario config overlays and per-class pins). Catalogs, graphs, cookbook, hooks-bridge notes, and the RFC (moved to implemented/, restructured to decision-era headings) updated in the same change.
2026-07-08 12:58:23 +08:00
Source: [`packages/core/tools/src/code-mode.ts:49`](../packages/core/tools/src/code-mode.ts)
#### `tool/code-dispatch-start` — log-only
```ts persistence-catalog
/**
* One sub-dispatch STARTING inside a `run_code` program: the parent
* `run_code` call id, the deterministic sub-call id (`<parent>:code:<n>`,
* numbered in submission order), and the tool `name` with its
* JSON-normalized `arguments` — the exact value dispatched, normalized
* BEFORE dispatch, so this append can never fail on payload shape.
* Appended when the scheduler actually starts the call (not at
* submission), so a start means the tool body pipeline was entered; a
* call abandoned in the queue logs nothing. Log-only: `deriveMessages()`
* ignores it; UIs use it for live per-sub-call running state and pair it
* with `tool/code-dispatch` by `subCallId` (timing = the two events'
* `time` fields).
*/
'tool/code-dispatch-start': { parentCallId: CallId; subCallId: CallId; name: string; arguments: unknown }
feat: Code Mode — the registry's mode config, the SDK codegen, and the run_code bridge The dsh-tools half of the Code Mode RFC (its fourth, final change): the registry gains its first config — mode: native | code | both — and OWNS how its tools reach the model. 'code' contributes exactly one wire tool, run_code, plus a lazy tools:sdk prompt section declaring every other tool as a generated TypeScript API (jsonSchemaToTs: total over the defineTool subset, unknown degradation, lexicographic byte-identical rendering); 'both' ships both representations; 'native' is byte-for-byte the old behavior. Non-native modes fail every assembly loudly without a typescript-language ctx.codeRuntime. run_code's dispatch bridge: JSON-normalizes each binding argument before dispatch (what dispatches is what the tool/code-dispatch event logs — the append can never fail on payload shape; BigInt/circulars reject that one call), serializes all program tool calls through a per-run queue (even Promise.all — no concurrency-safety metadata yet), routes every sub-call through tools/pre-execute → tools/post-execute (a deny rejects the program-side promise), drops sub-call additionalContext (no safe outlet mid-run; pinned), owns a run-scoped abort that follows the outer signal in and fires on settlement (in-flight sub-dispatch aborted, queued abandoned, queue drained before returning), and converts a failed run into CodeRunFailedError → a structured isError carrying kind + captured logs. tool/code-dispatch joins SessionEventMap by declaration merging (log-only; deriveMessages ignores it). The composed surface: the tools config forwards through agent-core and both app packages; examples/code-agent + demo:code run the worker runtime under mode code (keyless boot smoke + a with-key e2e proving the collapsed [run_code] header, the dispatch events, and the file the program wrote); two new snapshot scenarios (code-mode-turn, both-mode-turn) record the SDK section, collapsed header, dispatch events, and result card — each its own header-pinning class (the harness gains per-scenario config overlays and per-class pins). Catalogs, graphs, cookbook, hooks-bridge notes, and the RFC (moved to implemented/, restructured to decision-era headings) updated in the same change.
2026-07-08 12:58:23 +08:00
```
Types: [CallId](core-data-structures/core.md)
Source: [`packages/core/tools/src/code-mode.ts:33`](../packages/core/tools/src/code-mode.ts)
feat: Code Mode — the registry's mode config, the SDK codegen, and the run_code bridge The dsh-tools half of the Code Mode RFC (its fourth, final change): the registry gains its first config — mode: native | code | both — and OWNS how its tools reach the model. 'code' contributes exactly one wire tool, run_code, plus a lazy tools:sdk prompt section declaring every other tool as a generated TypeScript API (jsonSchemaToTs: total over the defineTool subset, unknown degradation, lexicographic byte-identical rendering); 'both' ships both representations; 'native' is byte-for-byte the old behavior. Non-native modes fail every assembly loudly without a typescript-language ctx.codeRuntime. run_code's dispatch bridge: JSON-normalizes each binding argument before dispatch (what dispatches is what the tool/code-dispatch event logs — the append can never fail on payload shape; BigInt/circulars reject that one call), serializes all program tool calls through a per-run queue (even Promise.all — no concurrency-safety metadata yet), routes every sub-call through tools/pre-execute → tools/post-execute (a deny rejects the program-side promise), drops sub-call additionalContext (no safe outlet mid-run; pinned), owns a run-scoped abort that follows the outer signal in and fires on settlement (in-flight sub-dispatch aborted, queued abandoned, queue drained before returning), and converts a failed run into CodeRunFailedError → a structured isError carrying kind + captured logs. tool/code-dispatch joins SessionEventMap by declaration merging (log-only; deriveMessages ignores it). The composed surface: the tools config forwards through agent-core and both app packages; examples/code-agent + demo:code run the worker runtime under mode code (keyless boot smoke + a with-key e2e proving the collapsed [run_code] header, the dispatch events, and the file the program wrote); two new snapshot scenarios (code-mode-turn, both-mode-turn) record the SDK section, collapsed header, dispatch events, and result card — each its own header-pinning class (the harness gains per-scenario config overlays and per-class pins). Catalogs, graphs, cookbook, hooks-bridge notes, and the RFC (moved to implemented/, restructured to decision-era headings) updated in the same change.
2026-07-08 12:58:23 +08:00
#### `tool/result` — surface
```ts persistence-catalog
/**
* A completed tool call's model-facing result, optional internal failure
* identity, and optional tool-private `meta` presentation payload. `meta` is
* opaque to the core (the producing tool owns its shape and reads it back in
* `presentResult`) but MUST be JSON-serializable: `Session.append`
* runtime-validates all event data with `isJsonValue`, so a non-serializable
* `meta` is rejected at the source, and the durable log reproduces the
* identical card on replay. Absent
2026-07-21 03:08:35 +08:00
* unless the tool attaches one (e.g. `dsh-tool-fs` carries its result-time
* contextual diff here).
*/
2026-07-21 03:08:35 +08:00
'tool/result': {
turn: number
step: number
message: ToolResultMessage
error?: { name: string; code: string }
2026-07-21 03:08:35 +08:00
meta?: JsonValue
}
```
Source: [`packages/core/session/src/types.ts:245`](../packages/core/session/src/types.ts)
### `turn/*`
#### `turn/end` — log-only
```ts persistence-catalog
/**
* Closes turn `turn` with the {@link TurnEndReason} that ended it. A turn
* with no entered step has no `step/start` or `step/end`. The loop does not await a
* flush at turn boundaries: `dsh-session-checkpoint-policy` owns the
* per-request durability checkpoint, and consumers that read storage after
* `whenIdle()` flush themselves. Success commits the turn; rejection is
* reported live and does not prevent later work.
*/
'turn/end': { turn: number; reason: TurnEndReason }
```
Types: [TurnEndReason](core-data-structures/session.md)
Source: [`packages/core/session/src/types.ts:206`](../packages/core/session/src/types.ts)
#### `turn/start` — log-only
```ts persistence-catalog
/**
* Opens turn `turn` before the loop claims queued input or runs pre-step.
* Rejection, empty input, cancellation, or failure may close it with no
* step; otherwise the following identified `user/message` event or batch
* records the messages entering the step.
*/
'turn/start': { turn: number }
```
Source: [`packages/core/session/src/types.ts:197`](../packages/core/session/src/types.ts)
### `user/*`
#### `user/message` — surface
```ts persistence-catalog
/**
* A user-role message on the model-visible surface: a direct human prompt
* (the queued message claimed for this turn), a synthetic `agent.inject()`
* context (file-change notices, subdir AGENTS.md, skill content, cron
* notifications, …), or an entered goal continuation round. All three
* project their `content` verbatim; `source` tells them apart.
*/
'user/message': UserMessage
```
Source: [`packages/core/session/src/types.ts:218`](../packages/core/session/src/types.ts)
### `web/*`
#### `web/deepseek-search-llm-request` — log-only
```ts persistence-catalog
/** Secret-free auxiliary DeepSeek search request recorded before dispatch. */
'web/deepseek-search-llm-request': DeepSeekSearchLlmRequest
```
Source: [`packages/web/web-search-deepseek/src/provider.ts:83`](../packages/web/web-search-deepseek/src/provider.ts)