mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge origin/master into lsp
This commit is contained in:
Dudu-0223
@@ -159,7 +159,7 @@ interface CollectedOutput {
|
||||
|
||||
## File sandbox: `BashSandboxInfo`
|
||||
|
||||
A sandbox-consuming executor exposes its configured fallback through `BashExecutor.sandboxMode`. The tool layer folds each session's durable `bash/sandbox-mode` override and may replace it for one user-approved strictly wider call. The mode/enforcement vocabulary is owned by the [`@deepseek-ai/dsh-sandbox` seam](sandbox.md); modes govern file effects only.
|
||||
A sandbox-consuming executor exposes its configured fallback through `BashExecutor.sandboxMode`. The tool layer folds each session's durable `sandbox/mode` override (owned by [`@deepseek-ai/dsh-sandbox-policy`](../../packages/sandbox/sandbox-policy/README.md)) and may replace it for one user-approved strictly wider call. The mode/enforcement vocabulary is owned by the [`@deepseek-ai/dsh-sandbox` seam](sandbox.md); modes govern file effects only.
|
||||
|
||||
A sandboxed run reports its mode, conservative denial classification, and enforcement completeness. `runnerFailed` marks a sandbox runner failure before the command ran; foreground execution throws `SANDBOX_UNAVAILABLE`, while a settled background process has only its facts channel.
|
||||
|
||||
|
||||
84
docs/core-data-structures/commands.md
Normal file
84
docs/core-data-structures/commands.md
Normal file
@@ -0,0 +1,84 @@
|
||||
# Human Commands
|
||||
|
||||
The human-command seam of [`dsh-commands`](../../packages/ui/commands). TUI and ACP adapters use it to discover and directly execute plugin-owned commands for an exact agent without creating a model message. The [command Agent Note](../../.agents/notes/implemented/feature/2026-07-19-plugin-command-registration.md) owns dispatch and lifecycle rationale; the [package README](../../packages/ui/commands/README.md) owns composition and limitations.
|
||||
|
||||
Source: [`packages/ui/commands/src/index.ts`](../../packages/ui/commands/src/index.ts)
|
||||
|
||||
## Input metadata
|
||||
|
||||
ACP currently exposes one unstructured-input hint. Command availability follows plugin composition: every adapter consuming the registry sees every effective definition.
|
||||
|
||||
```ts type-equiv
|
||||
/** Immutable command input metadata compatible with ACP unstructured input. */
|
||||
interface CommandInputDescriptor {
|
||||
/** Placeholder shown before the user supplies free-form input. */
|
||||
readonly hint: string
|
||||
}
|
||||
```
|
||||
|
||||
## Definition
|
||||
|
||||
`CommandDefinition` is the plugin-authored registration. The registry validates and freezes a detached effective definition.
|
||||
|
||||
```ts type-equiv
|
||||
/** Plugin-owned command registration. */
|
||||
interface CommandDefinition {
|
||||
/** Lowercase command name without the leading slash. */
|
||||
readonly name: string
|
||||
/** Human-readable summary used in discovery UI. */
|
||||
readonly description: string
|
||||
/** Optional free-form input hint advertised to capable clients. */
|
||||
readonly input?: CommandInputDescriptor
|
||||
/** Execute against the receiving agent without sending the command to the model. */
|
||||
readonly handler: (invocation: CommandInvocation) => CommandResult | Promise<CommandResult>
|
||||
}
|
||||
```
|
||||
|
||||
## Invocation and result
|
||||
|
||||
The adapter owns cancellation and passes the exact target agent. `rawInput` begins immediately after the parsed name and retains the adapter-delivered separator and suffix. Results are direct UI outcomes, not tool results or session events.
|
||||
|
||||
```ts type-equiv
|
||||
/** Invocation passed to one registered command handler. */
|
||||
interface CommandInvocation {
|
||||
/** Exact agent whose human-facing surface received the command. */
|
||||
readonly agent: Agent
|
||||
/** Exact text following the registered command name, including separator whitespace. */
|
||||
readonly rawInput: string
|
||||
/** Cancellation signal owned by the dispatching UI request. */
|
||||
readonly signal: AbortSignal
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Expected command outcome rendered directly by the dispatching UI. */
|
||||
type CommandResult =
|
||||
| { readonly kind: 'success'; readonly text?: string }
|
||||
| { readonly kind: 'error'; readonly text: string }
|
||||
```
|
||||
|
||||
## Discovery and parsing views
|
||||
|
||||
Adapters receive handler-free immutable descriptors after scope resolution. `parseCommand()` returns `ParsedCommand` before registry resolution; syntax-valid input can still name an unavailable command.
|
||||
|
||||
```ts type-equiv
|
||||
/** Handler-free immutable command view returned to UI adapters. */
|
||||
interface CommandDescriptor {
|
||||
/** Lowercase command name without the leading slash. */
|
||||
readonly name: string
|
||||
/** Human-readable summary used in discovery UI. */
|
||||
readonly description: string
|
||||
/** Optional free-form input hint advertised to capable clients. */
|
||||
readonly input?: CommandInputDescriptor
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Syntactically valid slash command before registry resolution. */
|
||||
interface ParsedCommand {
|
||||
/** Lowercase command name without the leading slash. */
|
||||
readonly name: string
|
||||
/** Exact text following the command name. */
|
||||
readonly rawInput: string
|
||||
}
|
||||
```
|
||||
@@ -6,7 +6,7 @@ Source: [`packages/compact/compact/src/types.ts`](../../packages/compact/compact
|
||||
|
||||
## The `compact/*` session events
|
||||
|
||||
Compaction extends [`SessionEventMap`](session.md) with three event types via declaration merging. All three are **log-only** — they record the compaction lock and its provenance, and never join the surface. `SurfaceEventType` is deliberately NOT extended (only message-producing events reach the model), so the summary itself rides on a separate `user/message` with `surfaceOp: { op: 'replace', start, end }` — the only surface mutation. See the Agent Note for why reusing `user/message` is honest rather than a workaround.
|
||||
Compaction extends [`SessionEventMap`](session.md) with three event types via declaration merging. All three are **log-only** — they record the compaction lock and its provenance, and never join the surface. `SurfaceEventType` is deliberately NOT extended (only message-producing events reach the model), so the summary itself rides on a separate `user/message` with `surfaceOp: { op: 'replace', start, end }` — the only surface mutation performed by summary compaction. See the Agent Note for why reusing `user/message` is honest rather than a workaround.
|
||||
|
||||
| Event | Payload | Role |
|
||||
|---|---|---|
|
||||
@@ -60,6 +60,36 @@ type CompactionTrigger = 'pressure' | 'context-overflow'
|
||||
|
||||
`CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration.
|
||||
|
||||
Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Failed-request recovery runs through `agent/request-error` after the failed step closes, and authorizes a fresh numbered-step retry only when the surface replacement generation advances. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling.
|
||||
Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Once pressure or canonical overflow qualifies, compact-basic invokes optional [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md) before range selection, remeasures through `ctx.tokenMeter`, and can advance the surface without a summary. Failed-request recovery runs through `agent/request-error` after the failed step closes and authorizes a fresh numbered-step retry only when the surface replacement generation advances, even if later summary work throws after pruning; cancellation still wins. Region boundaries preserve tool-call/result pairing but not whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling.
|
||||
|
||||
The seam exports `toolPairingBalancedBefore(session, seq)` and `toolPairingBalancedAfter(session, seq)` for those edge checks. Both validate current surface membership and reject missing seqs and orphan results; the [package contract](../../packages/compact/compact/README.md#tool-pairing-boundaries) owns their cache semantics.
|
||||
|
||||
## Tool-result pruning outcomes
|
||||
|
||||
The optional tool-result pruning service reports each durable content replacement and the aggregate Unicode-code-point reduction. Its public result types live in [`compact-tool-result-prune/src/types.ts`](../../packages/compact/compact-tool-result-prune/src/types.ts).
|
||||
|
||||
```ts type-equiv
|
||||
/** Provenance and size accounting for one landed surface replacement. */
|
||||
interface PrunedEntry {
|
||||
/** Full-fidelity tool-result event shadowed by the replacement. */
|
||||
readonly originalSeq: number
|
||||
/** Newly appended pruned tool-result event. */
|
||||
readonly replacementSeq: number
|
||||
/** Tool call shared by the original and replacement. */
|
||||
readonly callId: CallId
|
||||
/** Original text size in Unicode code points. */
|
||||
readonly charsBefore: number
|
||||
/** Replacement text size in Unicode code points. */
|
||||
readonly charsAfter: number
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Aggregate outcome of one stable-surface pruning pass. */
|
||||
interface PruneResult {
|
||||
/** Replacements in the snapshotted surface order. */
|
||||
readonly pruned: readonly PrunedEntry[]
|
||||
/** Total Unicode code points removed across replacements. */
|
||||
readonly charsRemoved: number
|
||||
}
|
||||
```
|
||||
|
||||
@@ -18,6 +18,8 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t
|
||||
| [llm-streaming.md](llm-streaming.md) | the `StreamChunk` wire protocol + adapter contract, `BlockAssembler`, the `LlmAdapter` seam |
|
||||
| [token-meter.md](token-meter.md) | immutable scalar and positional replay measurements with consumed-log revisions |
|
||||
| [scope.md](scope.md) | scoped registration identity, dispatch carriers, and the owned `Scope` context |
|
||||
| [goal.md](goal.md) | persisted goal identity, lifecycle snapshots, activation, change records, and round attribution |
|
||||
| [commands.md](commands.md) | the human-command seam: definitions, adapter discovery, direct invocation, results, and parsing views |
|
||||
| [session.md](session.md) | the full `SessionEventMap` variant catalog, `TurnTrigger`/`TurnEndReason`, `deriveMessages()`, the turn-enclosure invariant |
|
||||
| [persistence.md](persistence.md) | the durability seam: `SessionPersistence`, JSONL + SQLite backends, `session/flush`, crash recovery, `SessionHeader` |
|
||||
| [session-query.md](session-query.md) | logical records, bounded exact-event reads, and relationship traces |
|
||||
@@ -225,7 +227,7 @@ interface GenerateOptions {
|
||||
}
|
||||
```
|
||||
|
||||
Why a model response stopped is a merge-extensible reason:
|
||||
Why a model response stopped is a merge-extensible reason. Terminal provider failures carry the streaming contract's [`LlmFailure`](llm-streaming.md#llmfailure):
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -236,8 +238,8 @@ interface FinishReasonMap {
|
||||
'stop': { kind: 'stop' }
|
||||
'tool-calls': { kind: 'tool-calls' }
|
||||
'max-tokens': { kind: 'max-tokens' }
|
||||
'aborted': { kind: 'aborted' }
|
||||
'error': { kind: 'error'; message: string; code?: string }
|
||||
'aborted': { kind: 'aborted'; failure: LlmFailure }
|
||||
'error': { kind: 'error'; failure: LlmFailure }
|
||||
}
|
||||
```
|
||||
|
||||
@@ -339,13 +341,11 @@ The fourteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`,
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
`InjectOptions` extends ordinary message attribution with context-only framing and durable model-hidden JSON metadata:
|
||||
`InjectOptions` extends ordinary message attribution with durable model-hidden JSON metadata:
|
||||
|
||||
```ts type-equiv
|
||||
/** Options specific to durable synthetic context injection. */
|
||||
interface InjectOptions extends SendOptions {
|
||||
/** Keep the canonical context tag, or send caller-owned framing verbatim. */
|
||||
envelope?: ContextEnvelope
|
||||
/** Opaque JSON state retained in the session event but hidden from the model. */
|
||||
meta?: JsonValue
|
||||
}
|
||||
@@ -363,15 +363,20 @@ interface Agent {
|
||||
readonly ctx: Context
|
||||
|
||||
/**
|
||||
* Queue detached, frozen lossless-JSON input; starts a turn when idle.
|
||||
* Queue one detached, frozen lossless-JSON item. If claimed, it is the sole
|
||||
* ordinary message in its FIFO-ordered turn; the next claimed item waits for
|
||||
* that turn's checkpoint.
|
||||
* Invalid input throws synchronously before notification or enqueue.
|
||||
*/
|
||||
send(content: ContentBlock[], options?: SendOptions): void
|
||||
|
||||
/**
|
||||
* Steer a running turn: content is injected between steps of the current
|
||||
* turn. Uses the same owned-value and synchronous-validation boundary as
|
||||
* {@link send}; when idle, behaves exactly like that method.
|
||||
* Submit steering while the agent is `running`. An open turn records it at
|
||||
* the next steering checkpoint before a request or continuation decision;
|
||||
* policy may stop before another step. After turn close and its checkpoint,
|
||||
* any remainder is queued for a later turn; terminal `agent/turn-stop`,
|
||||
* cancellation, or disposal may discard it. Uses the same synchronous
|
||||
* snapshot-and-validation boundary as {@link send}; when idle, delegates to it.
|
||||
*/
|
||||
steer(content: ContentBlock[], options?: SendOptions): void
|
||||
|
||||
@@ -385,8 +390,9 @@ interface Agent {
|
||||
inject(content: ContentBlock[], options?: InjectOptions): void
|
||||
|
||||
/**
|
||||
* Clear queued and steering work, including work waiting to start, and abort
|
||||
* the active step. The supplied reason is preserved across pre-step and active
|
||||
* Clear all queued and steering work, including items waiting to start, and
|
||||
* abort the active step. An effective call first emits `agent/cancel-requested`
|
||||
* with the resolved reason. That reason is preserved across pre-step and active
|
||||
* cancellation windows, and `whenIdle()` resolves after cancellation reaches
|
||||
* quiescence. Idle cancellation is a no-op and does not arm a later cancel.
|
||||
*/
|
||||
@@ -398,7 +404,7 @@ interface Agent {
|
||||
}
|
||||
```
|
||||
|
||||
`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `SessionId` is branded. `AgentOptions` is merge-extensible and currently includes `provider?` and `model?`; dispatch requires both after `agent/request`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default.
|
||||
`AgentStatus` is `'idle' | 'running' | 'disposed'`, and `SessionId` is branded. `running` describes the driver-wide drain interval, which can span turn close, its durability checkpoint, and consecutive queued turns; it does not prove a turn is still open. `AgentOptions` is merge-extensible and currently includes `provider?` and `model?`; dispatch requires both after `agent/request`. Persona belongs to `dsh-system-prompt`: an agent-scoped `deployment:persona` may shadow the global default.
|
||||
|
||||
The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits.
|
||||
|
||||
@@ -408,7 +414,7 @@ The process-local initiator carried by `ctx.agents` is the exact `Agent` above,
|
||||
|
||||
## Interception decisions
|
||||
|
||||
Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. Prompt and post-tool decisions share one model-facing context shape, `HookContext`, which is `inject()`ed as a `context/message` and therefore carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt). Its optional `envelope` selects the canonical context tag or caller-owned raw framing, while JSON `meta` persists plugin state without exposing it to the model. Both decisions carry `additionalContexts[]` so every entry preserves its own provenance, framing, and metadata. Continuation reasons are steering messages instead and deliberately use the narrower content/source shape.
|
||||
Each `agent/*` interception waterfall returns a small, seam-specific typed union — the unified Decision idiom (the tool seams' `PreToolDecision`/`PostToolDecision` in [tools.md](tools.md) follow the same shape). A CC/Codex hook bridge maps its `permissionDecision`/`decision`/`continue`/`additionalContext` fields onto these; a native plugin returns them directly. Prompt and post-tool decisions share one model-facing context shape, `HookContext`, which is `inject()`ed as a `context/message` and therefore carries a REQUIRED `source` (a missing source would default to `{kind:'user'}` and mislabel plugin context as a user prompt). Its `content` reaches the model verbatim as a user-role message, while JSON `meta` persists plugin state without exposing it to the model. Both decisions carry `additionalContexts[]` so every entry preserves its own provenance and metadata. Continuation reasons are steering messages instead and deliberately use the narrower content/source shape.
|
||||
|
||||
Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts)
|
||||
|
||||
@@ -417,27 +423,26 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types
|
||||
interface HookContext {
|
||||
content: ContentBlock[]
|
||||
source: MessageSource
|
||||
/** Keep the canonical context tag, or use caller-owned framing verbatim. */
|
||||
envelope?: ContextEnvelope
|
||||
/** Opaque JSON state retained in the session event but hidden from the model. */
|
||||
meta?: JsonValue
|
||||
}
|
||||
```
|
||||
|
||||
`agent/prompt-submit` returns a `PromptDecision` (allow a drained queued message — optionally rewriting its `content` or attaching `additionalContexts` — or block it; a batch whose every prompt is blocked opens a zero-step turn that ends `rejected`):
|
||||
`agent/prompt-submit` returns a `PromptDecision` (allow the turn's claimed queued message — optionally rewriting its `content` or attaching `additionalContexts` — or record `prompt/blocked` and end that zero-step turn as `rejected`):
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
* Prompt interception result. `allow.content` replaces the prompt and each
|
||||
* `additionalContexts` entry becomes a separate context message. `block` records a
|
||||
* durable `prompt/blocked`; an all-blocked batch ends a zero-step rejected turn.
|
||||
* `additionalContexts` entry becomes a separate context message. `block`
|
||||
* records a durable `prompt/blocked` and ends the claimed prompt's zero-step
|
||||
* turn as rejected.
|
||||
*/
|
||||
type PromptDecision =
|
||||
| { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: HookContext[] }
|
||||
| { kind: 'block'; reason: string }
|
||||
```
|
||||
|
||||
`agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn and therefore carries no context envelope or metadata — the typed `/goal` pattern):
|
||||
`agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn and therefore carries no context metadata — the typed `/goal` pattern):
|
||||
|
||||
```ts type-equiv
|
||||
/** Turn continuation override; a continue reason is recorded as next-step steering in the same turn. */
|
||||
@@ -446,14 +451,14 @@ type ContinuationDecision =
|
||||
| { action: 'continue'; reason?: { content: ContentBlock[]; source: MessageSource } }
|
||||
```
|
||||
|
||||
`agent/request-error` receives the original `RequestError`, whose optional provider-neutral `code` supports stable routing without message parsing:
|
||||
`agent/request-error` receives the exact original `RequestError` beside its immutable `LlmFailure`, an immutable list of failures that already authorized another request in the consecutive sequence, the turn signal, and `next()`. Recovery plugins route on `failure.code`, not the live error's message; each policy counts only its own codes, and a successful request clears the history:
|
||||
|
||||
```ts type-equiv
|
||||
/** Model-request failure with an optional machine-routable provider code. */
|
||||
type RequestError = Error & { code?: string }
|
||||
```
|
||||
|
||||
It returns a `RequestErrorDecision`; `retry` opens a new numbered step after the recovery listener's durable mutation, while `fail` preserves that error:
|
||||
It returns a `RequestErrorDecision`; `retry` opens a new numbered step after the recovery listener's durable mutation, while `fail` retains the structured failure on `turn/end`:
|
||||
|
||||
```ts type-equiv
|
||||
/** Failed-request recovery decision; `retry` opens another numbered step while listeners delegate by calling `next()`. */
|
||||
|
||||
@@ -241,6 +241,7 @@ type FsErrorCode =
|
||||
| 'FS_NOT_TEXT'
|
||||
| 'FS_NOT_REGULAR_FILE'
|
||||
| 'FS_PERMISSION_DENIED'
|
||||
| 'FS_SANDBOX_DENIED'
|
||||
| 'FS_IO_ERROR'
|
||||
| 'FS_STALE_VERSION'
|
||||
| 'FS_NOT_OBSERVED'
|
||||
@@ -249,7 +250,7 @@ type FsErrorCode =
|
||||
| 'FS_ABORTED'
|
||||
```
|
||||
|
||||
`FS_NOT_DIRECTORY`, `FS_PERMISSION_DENIED`, and `FS_IO_ERROR` are used by directory listing to distinguish an existing non-directory target, a denied listing, and an unexpected backend I/O failure. `FS_NOT_OBSERVED` means the policy plugin has no prior-observation record for this owner (or a `createIfAbsent` hit an existing file). `FS_STALE_VERSION` means the backend version no longer matches the observed one (or an edit hit a missing target). Freshness authorization has no partial/full distinction, so there is no `FS_PARTIAL_OBSERVATION`.
|
||||
`FS_NOT_DIRECTORY`, `FS_PERMISSION_DENIED`, and `FS_IO_ERROR` are used by directory listing to distinguish an existing non-directory target, a denied listing, and an unexpected backend I/O failure. `FS_SANDBOX_DENIED` is a POLICY refusal from a sandbox-enforcing backend (`dsh-fs-sandbox`) — the mode fence denied a write/edit — distinct from `FS_PERMISSION_DENIED` (the host kernel refusing). `FS_NOT_OBSERVED` means the policy plugin has no prior-observation record for this owner (or a `createIfAbsent` hit an existing file). `FS_STALE_VERSION` means the backend version no longer matches the observed one (or an edit hit a missing target). Freshness authorization has no partial/full distinction, so there is no `FS_PARTIAL_OBSERVATION`.
|
||||
|
||||
## The service and the plugin
|
||||
|
||||
|
||||
143
docs/core-data-structures/goal.md
Normal file
143
docs/core-data-structures/goal.md
Normal file
@@ -0,0 +1,143 @@
|
||||
# Same-session goals
|
||||
|
||||
Types shared by the event-sourced goal domain and its policy consumers. The [goal-domain Agent Note](../../.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.md) owns the persistence and activation decisions; this page records the literal shapes from [`packages/goal/goal/src/types.ts`](../../packages/goal/goal/src/types.ts).
|
||||
|
||||
## Identity and lifecycle
|
||||
|
||||
`GoalId` is a [branded id](core.md#branded-ids). A caller mutates one exact revision through `GoalRef`; every accepted durable mutation increments the revision.
|
||||
|
||||
```ts type-equiv
|
||||
/** Compare-and-set identity for one exact goal revision. */
|
||||
interface GoalRef {
|
||||
/** Stable goal identity. */
|
||||
readonly id: GoalId
|
||||
/** Positive revision; every durable mutation increments it. */
|
||||
readonly revision: number
|
||||
}
|
||||
```
|
||||
|
||||
The durable phase answers what happened to the objective. Process-local activation separately answers whether a continuation consumer may start another round.
|
||||
|
||||
```ts type-equiv
|
||||
/** Durable continuation phase. Activation is process-local and separate. */
|
||||
type GoalPhase =
|
||||
| 'active'
|
||||
| 'paused'
|
||||
| 'blocked'
|
||||
| 'complete'
|
||||
```
|
||||
|
||||
Blocking is the single durable stopped-by-a-problem state. Its policy-owned reason carries a stable lower-kebab-case code for routing and a free-form explanation for humans and models.
|
||||
|
||||
```ts type-equiv
|
||||
/** Machine-routable and human-readable explanation for a blocked goal. */
|
||||
interface GoalBlockReason {
|
||||
/** Stable lower-kebab-case classification chosen by the blocking policy. */
|
||||
readonly code: string
|
||||
/** Non-empty explanation shown to humans and models. */
|
||||
readonly message: string
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Full durable state written by every non-clear goal mutation. */
|
||||
interface GoalSnapshot extends GoalRef {
|
||||
/** Human-requested completion objective. */
|
||||
readonly objective: string
|
||||
/** Durable lifecycle phase. */
|
||||
readonly phase: GoalPhase
|
||||
/** Present exactly while `phase` is `blocked`. */
|
||||
readonly blockedReason?: GoalBlockReason
|
||||
/** Total admitted goal-round cap. */
|
||||
readonly maxGoalRounds: number
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Current goal projection, including values derived from the session log. */
|
||||
interface GoalView extends GoalSnapshot {
|
||||
/** Highest admitted round number for this goal. */
|
||||
readonly roundsStarted: number
|
||||
/** Epoch milliseconds of the create mutation. */
|
||||
readonly createdAt: number
|
||||
/** Epoch milliseconds of the latest mutation. */
|
||||
readonly updatedAt: number
|
||||
/** Process-local continuation eligibility; never persisted. */
|
||||
readonly activation: GoalActivation
|
||||
}
|
||||
```
|
||||
|
||||
## Durable changes
|
||||
|
||||
Every mutation is a `context/message` whose metadata is either a complete snapshot or a clear tombstone. The version, metadata, goal source, and verbatim rendered content form one replay invariant.
|
||||
|
||||
```ts type-equiv
|
||||
/** Full-snapshot goal mutation retained in a model-visible context event. */
|
||||
interface GoalSnapshotChangeMeta {
|
||||
readonly kind: 'goal/change'
|
||||
readonly version: 1
|
||||
readonly operation: Exclude<GoalOperation, 'clear'>
|
||||
readonly goal: GoalSnapshot
|
||||
readonly roundsStarted: number
|
||||
readonly createdAt: number
|
||||
readonly updatedAt: number
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Tombstone retained when the current goal is cleared. */
|
||||
interface GoalClearChangeMeta {
|
||||
readonly kind: 'goal/change'
|
||||
readonly version: 1
|
||||
readonly operation: 'clear'
|
||||
readonly cleared: GoalRef
|
||||
readonly clearedAt: number
|
||||
}
|
||||
```
|
||||
|
||||
Goal state changes use round `0`. A continuation consumer attributes each admitted user-message turn with a positive, sequential round number and the current revision; replay rejects gaps, stale revisions, stopped phases, and cap overflow.
|
||||
|
||||
```ts type-equiv
|
||||
/** Message attribution for durable goal state and continuation rounds. */
|
||||
interface GoalMessageSource {
|
||||
readonly kind: 'goal'
|
||||
readonly goalId: GoalId
|
||||
readonly revision: number
|
||||
/** Zero for state changes; positive for admitted continuation rounds. */
|
||||
readonly round: number
|
||||
}
|
||||
```
|
||||
|
||||
## Requests and notifications
|
||||
|
||||
Creation separates caller omission from the deployment choice, which `create()` resolves internally. An edit is a partial replacement whose runtime validator requires at least one field. Every mutation notification carries the accepted operation and exact revision; clear omits `goal`.
|
||||
|
||||
```ts type-equiv
|
||||
/** Input whose omitted round cap is resolved by the service configuration. */
|
||||
interface CreateGoalRequest {
|
||||
readonly objective: string
|
||||
readonly maxGoalRounds?: number
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Fields changed by an edit; at least one must be present. */
|
||||
interface EditGoalRequest {
|
||||
readonly objective?: string
|
||||
readonly maxGoalRounds?: number
|
||||
}
|
||||
```
|
||||
|
||||
```ts type-equiv
|
||||
/** Live notification after one goal mutation has been accepted for logging. */
|
||||
interface GoalChanged {
|
||||
readonly operation: GoalOperation
|
||||
readonly ref: GoalRef
|
||||
/** Absent for a clear tombstone. */
|
||||
readonly goal?: GoalView
|
||||
}
|
||||
```
|
||||
|
||||
## Service behavior
|
||||
|
||||
[`GoalService`](../../packages/goal/goal/src/index.ts) resolves creation defaults, folds strict replay, enforces exact-live-agent identity and compare-and-set mutations, overlays deferred injections, and emits contained `goal/changed` notifications. The package [README](../../packages/goal/goal/README.md) owns the callable and model-visible contract.
|
||||
@@ -31,18 +31,40 @@ type StreamChunk =
|
||||
}
|
||||
```
|
||||
|
||||
## `LlmFailure`
|
||||
|
||||
Every thrown or in-band final-adapter failure normalizes to one serializable provider-neutral payload. `providerRetryAfterMs` is a validated positive delay requested by the provider, not a retry decision; `ProviderRequestId` is an opaque branded string for diagnostics.
|
||||
|
||||
```ts type-equiv
|
||||
/** Serializable provider-boundary facts; policy decides whether they are retryable. */
|
||||
interface LlmFailure {
|
||||
/** Human-readable provider or transport failure. */
|
||||
readonly message: string
|
||||
/** Stable provider-neutral machine-routing code. */
|
||||
readonly code: string
|
||||
/** HTTP status observed at the provider boundary, when available. */
|
||||
readonly status?: number
|
||||
/** Provider-requested delay in milliseconds, when valid and available. */
|
||||
readonly providerRetryAfterMs?: number
|
||||
/** Opaque provider-issued request identifier for diagnostics. */
|
||||
readonly requestId?: ProviderRequestId
|
||||
}
|
||||
```
|
||||
|
||||
## The adapter contract
|
||||
|
||||
Every adapter MUST obey these, and every consumer may rely on them:
|
||||
|
||||
- **`usage` before `finish`, nothing after `finish`.** Defer both to the provider's end-of-stream marker so a trailing usage-only chunk can't violate the ordering.
|
||||
- **Tool-call `arguments` stay raw JSON strings end-to-end.** Partial fragments stream via `argumentsDelta`; a provider that hands back parsed objects re-stringifies at `block-end`.
|
||||
- **Two sanctioned error paths.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted'}` (provider in-band errors, for adapters that can't throw mid-stream). Consumers must handle *both*. The agent loop closes the failed step and offers either form to `agent/request-error`; absent recovery it becomes a turn error, and no normal completed assistant message is logged for that request.
|
||||
- **Two sanctioned error paths, one fact shape.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted', failure}` (provider in-band errors, for adapters that can't throw mid-stream). `LlmError.failure` carries the same `LlmFailure`. The final adapter boundary preserves the exact thrown `Error` object and associates immutable facts with that call; the agent loop closes the failed step and offers the error, facts, and immutable prior-retried facts to `agent/request-error`. Absent recovery the structured failure becomes the turn error, and no normal assistant message or tool side effect is committed for that attempt.
|
||||
- **One adapter call is one provider attempt.** Adapters disable library retries. Agent-level recovery opens another durable numbered step; direct `ctx.llm.stream()` callers remain single-attempt.
|
||||
- **Provider stalls are bounded at the transport.** Both shipping remote adapters expose positive finite `streamIdleTimeoutMs` with a five-minute default. The watchdog arms only while iterator `next()` is outstanding, uses one stable signal for the whole request, maps its own expiry to `TIMEOUT`, and keeps an earlier caller abort as `ABORTED`.
|
||||
- **Context overflow has one canonical code.** Both DeepSeek adapters classify explicit provider detail through `isContextWindowExceededError()` and surface `CONTEXT_WINDOW_EXCEEDED`, whether the failure arrives as a thrown HTTP `LlmError` or an in-band finish error. Consumers route on the code, never provider text.
|
||||
- **Every provider HTTP request carries the app-attribution header.** Adapters send `attributionHeaders()` (below) - the `User-Agent` baseline - and prove it with a wire-level test (mock server asserting the received header, or the library's header hook for a library-backed adapter).
|
||||
- **Replay state is adapter-owned.** A successful `finish` may carry lossless-JSON state needed to reconstruct a native provider response. The loop stores it with the assembled assistant message unless an `agent/step-result` listener rewrote the content. On a later request, `LlmService` passes the state only when the historical provider and target provider are currently registered to the exact same adapter instance. That adapter validates the state and owns any cross-model or cross-provider conversion; other adapters receive the provider-neutral content and provenance without the private state.
|
||||
|
||||
This contract was pinned down by two deliberately independent implementations: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (a generic multi-provider adapter through `@earendil-works/pi-ai`). The library-backed adapter cannot throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not.
|
||||
This contract is pinned down by two deliberately independent implementations: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (a generic multi-provider adapter through `@earendil-works/pi-ai`). The library-backed adapter exercises the finish-chunk error path, while transport-boundary tests prove each idle watchdog stops its actual request.
|
||||
|
||||
## `AppIdentity` — app attribution
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ The seam is a textbook [capability seam](../../.agents/notes/implemented/archite
|
||||
|
||||
## The flush checkpoint
|
||||
|
||||
`session/event` is a *synchronous* notification; persistence plugins buffer it (write-behind) and drain at the awaited `session/flush` checkpoint the loop fires at every turn end. Flush is `ctx.parallel` (awaited): a turn's events are durably committed before the next turn starts, and the turn boundary is the commit boundary. A rejecting flush is reported via `agent/error` and the logger — never as a session event (it would land past the commit boundary), so the backend keeps its buffered events for the next flush.
|
||||
`session/event` is a *synchronous* notification; persistence plugins buffer it (write-behind) until `session/flush`. The loop awaits an ordinary turn's checkpoint before claiming the next queue item; synchronous idle `inject()` schedules its checkpoint without blocking `send()`, and disposal still drains it. A successful flush durably commits the closed turn as one unit; a rejecting flush is reported through `agent/error` and the logger — never as a session event past the closed turn — while the backend keeps its buffered events for the next flush.
|
||||
|
||||
## Crash recovery preserves an interrupted turn
|
||||
|
||||
@@ -60,12 +60,18 @@ interface SessionHeader {
|
||||
* boundary lets resume and replay distinguish parent history from child work.
|
||||
*/
|
||||
readonly seedLength?: number
|
||||
/**
|
||||
* Delegation depth: absent (zero) for a top-level session, parent depth + 1
|
||||
* for a subagent child. Persisted so a recursion budget survives restart and
|
||||
* resume — a runtime-only depth would reset a resumed child to top-level.
|
||||
*/
|
||||
readonly delegationDepth?: number
|
||||
}
|
||||
```
|
||||
|
||||
## `CreateSessionOptions` — seeding and metadata
|
||||
|
||||
Creating a `Session` through the store takes a `seed` (replay/fork an existing event log) and `meta` (the storage-level fields the store folds into a `SessionHeader`). The store fills in `version`/`id` and defaults `createdAt`; the caller supplies the validated absolute `cwd`, the `parentSession` lineage, the `seedLength` seed boundary, and — only when reconstructing a persisted session — the original `createdAt` to preserve it.
|
||||
Creating a `Session` through the store takes a `seed` (replay/fork an existing event log) and `meta` (the storage-level fields the store folds into a `SessionHeader`). The store fills in `version`/`id` and defaults `createdAt`; the caller supplies the validated absolute `cwd`, the `parentSession` lineage, the `seedLength` seed boundary, the `delegationDepth`, and — only when reconstructing a persisted session — the original `createdAt` to preserve it.
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -85,6 +91,7 @@ interface CreateSessionOptions {
|
||||
readonly parentSession?: SessionId
|
||||
readonly createdAt?: number
|
||||
readonly seedLength?: number
|
||||
readonly delegationDepth?: number
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -95,7 +102,7 @@ Replay/fork is therefore `ctx.sessions.create(id, { seed: seedEvents })`; resumi
|
||||
|
||||
Both implement the same abstract `SessionPersistence` (locate/create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic:
|
||||
|
||||
- **[dsh-session-persistence-jsonl](../../packages/session-persistence/session-persistence-jsonl)** — an append-only JSONL log per session with crash-safe atomic writes, the interrupted-turn crash recovery above, and a read/replay path.
|
||||
- **[dsh-session-persistence-jsonl](../../packages/session-persistence/session-persistence-jsonl)** — an append-only logical JSONL log per session, stored as checksummed concatenated Zstandard frames by default or raw lines by configuration, with crash-safe atomic writes, interrupted-turn recovery, and a read/replay path.
|
||||
- **[dsh-session-persistence-sqlite](../../packages/session-persistence/session-persistence-sqlite)** — `node:sqlite`, one row per `SessionEvent`. The row shape `(session_id, seq, type, time, data, source_event_seqs, surface_op)` maps 1:1 onto the event, including optional surface metadata, so there is no parallel persisted schema to keep in sync.
|
||||
|
||||
Multiple backends sharing one on-disk session coordinate writes through the [shared persistence write-coordinator](../../.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md).
|
||||
|
||||
@@ -4,15 +4,6 @@ The in-memory, event-sourced model of [dsh-session](../../packages/core/session)
|
||||
|
||||
Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts)
|
||||
|
||||
## Context framing
|
||||
|
||||
`ContextEnvelope` selects the standard tagged projection or preserves a producer-owned complete frame. The latter changes framing only; the event remains a user-role `context/message` in chronological history.
|
||||
|
||||
```ts type-equiv
|
||||
/** Canonical context-tag framing, or caller-owned framing rendered verbatim. */
|
||||
type ContextEnvelope = 'context' | 'raw'
|
||||
```
|
||||
|
||||
## `SessionEventMap` — the event vocabulary
|
||||
|
||||
The append-only event types. Merge-extensible: a plugin declares extra event types via declaration merging — e.g. the [compaction seam](compaction.md) adds `compact/start` / `compact/summary` / `compact/end`, and `@deepseek-ai/dsh-hook-protocol` adds log-only `hook/invoked` / `hook/result` provenance for a hook bridge. Like `compact/*`, these are NOT `SurfaceEventType`s (no `surfaceOp`). The generated [persistence log event catalog](../persistence-catalog.md) enumerates every member — core and merged — with its payload, surface badge, and declaration site.
|
||||
@@ -26,40 +17,44 @@ The append-only event types. Merge-extensible: a plugin declares extra event typ
|
||||
*/
|
||||
interface SessionEventMap {
|
||||
/**
|
||||
* Opens turn `turn`. `trigger` records what started it — a drained message
|
||||
* batch or an idle-time injection. The turn is the durability/replay
|
||||
* Opens turn `turn`. `trigger` records what started it — one claimed queued
|
||||
* message or an idle-time injection. The turn is the durability/replay
|
||||
* boundary: every event sits between a `turn/start` and its matching
|
||||
* `turn/end` (the turn-enclosure invariant).
|
||||
*/
|
||||
'turn/start': { turn: number; trigger: TurnTrigger }
|
||||
/**
|
||||
* Closes turn `turn` with the {@link TurnEndReason} that ended it. The loop
|
||||
* fires the awaited `session/flush` checkpoint at every turn end, so the turn
|
||||
* boundary is also the durable-commit boundary.
|
||||
* awaits `session/flush` after an ordinary turn ends before claiming the next
|
||||
* queued item. Success commits the turn; rejection is reported live and does
|
||||
* not prevent later work.
|
||||
*/
|
||||
'turn/end': { turn: number; reason: TurnEndReason }
|
||||
/** Opens step `step` of turn `turn` — one model call plus the tool executions it requested. */
|
||||
'step/start': { turn: number; step: number }
|
||||
/** Closes step `step` of turn `turn`. */
|
||||
'step/end': { turn: number; step: number }
|
||||
/** A user-visible prompt (queued message drained at turn start). */
|
||||
/** A user-visible prompt (the queued message claimed for this turn). */
|
||||
'user/message': { content: ContentBlock[]; source: MessageSource }
|
||||
/**
|
||||
* Durable record of a prompt veto and its reason. It is log-only: the blocked
|
||||
* prompt never enters the model-visible surface, including in a mixed batch.
|
||||
* prompt never enters the model-visible surface, and its turn runs zero steps.
|
||||
*/
|
||||
'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string }
|
||||
/**
|
||||
* In-session context injection (file-change notices, subdir AGENTS.md,
|
||||
* skill content, cron notifications, …). Rendered into the derived history
|
||||
* as synthetic context — NOT a user prompt. `envelope: 'raw'` lets a caller
|
||||
* own the complete model-facing frame; `meta` is durable JSON state omitted
|
||||
* from the model projection.
|
||||
* as a synthetic user-role message carrying `content` verbatim — NOT a
|
||||
* user prompt. `meta` is durable JSON state omitted from the model
|
||||
* projection; it is also the intended channel for any future framing
|
||||
* directive (a producer declares the frame, a dedicated renderer applies it —
|
||||
* see the deferred note in
|
||||
* ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md),
|
||||
* so the surface keeps projecting `content` verbatim rather than wrapping it.
|
||||
*/
|
||||
'context/message': {
|
||||
content: ContentBlock[]
|
||||
source: MessageSource
|
||||
envelope?: ContextEnvelope
|
||||
meta?: JsonValue
|
||||
}
|
||||
/** Raw stream chunk — token-level replay fidelity. */
|
||||
@@ -432,10 +427,10 @@ declare class Session {
|
||||
- `user/message` → a user message.
|
||||
- `assistant/message` → an assistant message with the event's provider/model provenance and optional adapter-private replay state. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its usage/provenance, but a content-less assistant turn must not enter the provider transcript.
|
||||
- `tool/result` → a user message carrying a `tool-result` block.
|
||||
- `context/message` → a user-role message at its chronological position. The default `envelope` is `context`, which wraps content as `<context source="…">…</context>`; `envelope: 'raw'` uses caller-owned framing verbatim. Optional JSON `meta` remains in the event log and is never rendered.
|
||||
- `steering/message` → a user-role message wrapped in `<steering source="…">…</steering>` at its chronological position.
|
||||
- `context/message` → a user-role message carrying its `content` verbatim at its chronological position. Optional JSON `meta` remains in the event log and is never rendered.
|
||||
- `steering/message` → a user-role message carrying its content verbatim at its chronological position.
|
||||
|
||||
Everything else (`turn/*`, `step/*`) is structural and does not project into a message. Token usage is observed on `assistant/message.usage` (the step that produced it); an operational error's step number is on `turn/end.reason` for `kind: 'error'`. Because this unreleased format intentionally has no compatibility promise, seed/load validation rejects request headers without provider+model and assistant messages without provider/model provenance instead of guessing a route for historical data.
|
||||
Everything else (`turn/*`, `step/*`, plugin-owned `llm/retry`) is structural and does not project into a message. 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, so their usage chunk is the durable accounting record. An operational error's step number is on `turn/end.reason` for `kind: 'error'`, with normalized `LlmFailure` facts for a final model-request failure and message/code for other live errors. Because this unreleased format intentionally has no compatibility promise, seed/load validation rejects request headers without provider+model and assistant messages without provider/model provenance instead of guessing a route for historical data.
|
||||
|
||||
## Live-session fork API
|
||||
|
||||
@@ -479,15 +474,19 @@ interface TurnEndReasonMap {
|
||||
* The turn failed: a step threw or the model reported a failure. `step` is the
|
||||
* step number the failure occurred on (the operational error's location — the
|
||||
* single durable record of an in-turn failure; live diagnostics also fire via
|
||||
* `agent/error`). `code` is the error's code when one was attached.
|
||||
* `agent/error`). Final model-request failures retain their normalized facts
|
||||
* as one `failure`; other turn failures retain their live Error message/code.
|
||||
*/
|
||||
error: { kind: 'error'; step: number; message: string; code?: string }
|
||||
error: { kind: 'error'; step: number } & (
|
||||
| { failure: LlmFailure; message?: never; code?: never }
|
||||
| { message: string; code?: string; failure?: never }
|
||||
)
|
||||
disposed: { kind: 'disposed' }
|
||||
/** At least one step reached its output-token ceiling, even if a plugin continued the turn. */
|
||||
'max-tokens': { kind: 'max-tokens' }
|
||||
/**
|
||||
* Policy blocked every prompt before the first step. The zero-step turn still
|
||||
* records a balanced durable boundary and the veto reason.
|
||||
* Policy blocked the turn's claimed prompt before the first step. The
|
||||
* zero-step turn still records a balanced durable boundary and veto reason.
|
||||
*/
|
||||
rejected: { kind: 'rejected'; reason: string }
|
||||
/**
|
||||
@@ -498,7 +497,7 @@ interface TurnEndReasonMap {
|
||||
}
|
||||
```
|
||||
|
||||
`max-tokens` mirrors the model-call `FinishReason` of the same name: any `max-tokens` step in a turn makes the whole turn end `max-tokens` rather than `completed` (the cut-short fact wins over a later continuation), so a consumer can tell a clean stop from a truncated one — but only over `completed`: the `disposed`/`aborted`/`error` outcomes take precedence. `rejected` is a zero-step turn whose whole prompt batch an `agent/prompt-submit` hook blocked (the ACP bridge maps it to `cancelled`). `interrupted` is the one reason no loop emits — it is synthesized by crash recovery (see [persistence.md](persistence.md)). Both maps are merge-extensible.
|
||||
`max-tokens` mirrors the model-call `FinishReason` of the same name: any `max-tokens` step in a turn makes the whole turn end `max-tokens` rather than `completed` (the cut-short fact wins over a later continuation), so a consumer can tell a clean stop from a truncated one — but only over `completed`: the `disposed`/`aborted`/`error` outcomes take precedence. `rejected` is a zero-step turn whose claimed prompt an `agent/prompt-submit` hook blocked (the ACP bridge maps it to `cancelled`). `interrupted` is the one reason no loop emits — it is synthesized by crash recovery (see [persistence.md](persistence.md)). Both maps are merge-extensible.
|
||||
|
||||
## The turn-enclosure invariant
|
||||
|
||||
|
||||
@@ -237,5 +237,5 @@ interface SubagentProvider {
|
||||
|
||||
The spawn and fork backends create an ordinary agent through `parent.ctx`, pass cancellation into core creation, and dispose through `AgentHandle`. Provider removal blocks new starts without revoking accepted runs. Each child gets a new flat scope rather than inheriting parent registrations. Depth and fork seeding reuse existing agent and session vocabulary:
|
||||
|
||||
- **Delegation depth** is a merge-extensible `AgentOptions.subagentDepth` field (`0` for a top-level agent, parent + 1 for a child). Only `undefined` means top level; every stored present value must be a non-negative safe integer. The seam owns it — the loop neither sets nor reads it — so a nested spawn validates its parent's stored depth, rejects a derived child depth outside the safe-integer domain, and applies a defined absolute `request.maxDepth` cap to that child.
|
||||
- **Delegation depth** is durable `SessionHeader.delegationDepth` plus the merge-extensible runtime field `AgentOptions.subagentDepth`; absence means top-level depth zero, and the greater present value is authoritative. The seam owns both fields — the loop neither sets nor reads them — so an in-process child persists parent depth + 1, resume cannot lower it, and every start rejects a derived depth outside the safe-integer domain or above a defined absolute `request.maxDepth` cap.
|
||||
- **Fork seeding** uses `CreateAgentOptions.seed` (a `SessionEvent[]` prefix threaded through `AgentLoop.createAgent` → `ctx.sessions.prepare({ seed })`, the same primitive `resume` uses). The fork backend passes a *balanced completed-turn prefix* of the parent's log — the parent's events up to and including its last `turn/end` — so the seed is contiguous-from-0 and the [invariants](../../packages/support/invariants) replay accepts it (the in-flight, unbalanced turn is excluded).
|
||||
|
||||
@@ -180,8 +180,8 @@ A tool body receives the runtime extension. `deferContext()` is the composite-to
|
||||
interface ToolRunContext extends ToolExecution {
|
||||
/**
|
||||
* Defer one nested-dispatch context until this tool's final result reaches
|
||||
* the agent loop. Contexts retain their individual source, envelope, and
|
||||
* metadata and are emitted in call order.
|
||||
* the agent loop. Contexts retain their individual source and metadata and
|
||||
* are emitted in call order.
|
||||
*/
|
||||
deferContext(context: HookContext): void
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# User Interaction
|
||||
|
||||
The user-interaction seam of [dsh-user-interaction](../../packages/ui/user-interaction). It is the provider-neutral vocabulary a tool or permission plugin uses when it needs the human to answer before the agent can continue. UI surfaces provide the active `UserInteractionProvider`: `dsh-stdio-demo` selects keyboard-driven `dsh-tui` overlays or `dsh-stdio` readline prompts, and `dsh-acp` maps questions to ACP form elicitations.
|
||||
The user-interaction seam of [dsh-user-interaction](../../packages/ui/user-interaction). It is the provider-neutral vocabulary a tool or permission plugin uses when it needs the human to answer before the agent can continue. UI surfaces provide the active `UserInteractionProvider`: `dsh-tui` uses keyboard-driven overlays, and `dsh-acp` maps questions to ACP form elicitations.
|
||||
|
||||
Source: [`packages/ui/user-interaction/src/index.ts`](../../packages/ui/user-interaction/src/index.ts)
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ Source: [`packages/workflow/workflow/src/types.ts`](../../packages/workflow/work
|
||||
|
||||
## The start request
|
||||
|
||||
What a caller asks for when starting a run. The tool layer builds this from the model's `{ script, meta, args }` call plus the calling agent; `meta` and `args` are plain JSON DATA (the engine shape-validates `meta` and rejects loud BEFORE anything runs — no script text is ever evaluated to obtain it). `parent` is REQUIRED — every child the script spawns is attributed to it (cwd, lineage, and depth flow through the [subagent seam](subagent.md)).
|
||||
What a caller asks for when starting a run. The ordinary workflow tool builds this from the model's `{ script, meta, args }` call plus the calling agent; specialized consumers may also select one engine-wide `subagentProvider` and lower `maxTotalAgents` for the run, but the script cannot observe or replace either policy. `meta` and `args` are plain JSON DATA (the engine shape-validates `meta` and rejects loud BEFORE anything runs — no script text is ever evaluated to obtain it). `parent` is REQUIRED — every child the script spawns is attributed to it (cwd, lineage, and depth flow through the [subagent seam](subagent.md)).
|
||||
|
||||
```ts type-equiv
|
||||
/**
|
||||
@@ -26,6 +26,17 @@ interface WorkflowStartRequest {
|
||||
meta: WorkflowMeta
|
||||
/** Optional input exposed verbatim to the script as the `args` global. */
|
||||
args?: unknown
|
||||
/**
|
||||
* Optional engine-wide child-provider override for this run. The workflow
|
||||
* script cannot observe or replace it; omission uses the engine's configured
|
||||
* provider.
|
||||
*/
|
||||
subagentProvider?: string
|
||||
/**
|
||||
* Optional per-run total-child ceiling. Implementations reject values above
|
||||
* their deployment ceiling before publishing the run.
|
||||
*/
|
||||
maxTotalAgents?: number
|
||||
/** The agent on whose behalf the run executes (parent of every child). */
|
||||
parent: Agent
|
||||
/** Cancels the run when aborted (the tool's `exec.signal`). */
|
||||
|
||||
Reference in New Issue
Block a user