Files
deepseek-harness/docs/cordis-catalog/events.md
2026-07-05 19:07:34 +08:00

20 KiB

Cordis Events Catalog

Every cordis event a plugin can listen to: exact signature, dispatch mode, and the declaration's JSDoc. This is one axis of the wiring reference a plugin author works against — the callable ctx.<key> surface is the sibling services catalog, and core-data-structures/ catalogs the data structures these signatures move around.

This file is GENERATED from source (scripts/gen-cordis-catalog.ts) and verified fresh by pnpm run verify-cordis-catalog (part of doc-sync) — do not edit it by hand. Signature blocks use a ts cordis-catalog fence (skipped by doc-typecheck, since a bare signature is not standalone-compilable). Type names in a signature link to the page that documents them.

The harness tier below (the @deepseek-ai/dsh-* packages) is the vocabulary this repo owns, grouped by scope. The inherited tier at the end is the cordis-core + loader/hmr/timer event surface a plugin also sees — pinned vendor source, summarized tersely.

Dispatch modes: emit (fire-and-forget), waterfall (each listener gets next() and may transform or veto — see waterfall semantics), parallel (awaited fan-out; all listeners run), serial (awaited in registration order until one returns a bail value — anything other than null, false, or undefined).

agent/*

agent/created — emit

An agent was registered in the AgentRegistry and is ready to receive messages.

'agent/created'(agent: Agent): void

Types: Agent

Source: packages/core/agent/src/types.ts:234

agent/disposed — emit

An agent was disposed and removed from the registry; its fiber and any in-flight turn have been torn down.

'agent/disposed'(agent: Agent): void

Types: Agent

Source: packages/core/agent/src/types.ts:241

agent/error — emit

A step or turn errored. The loop reports a failure here (plus the logger) even when the error has no in-turn position for a session error event.

'agent/error'(agent: Agent, turn: number, step: number, error: Error): void

Types: Agent

Source: packages/core/agent/src/types.ts:380

agent/pre-step — serial

Awaited pre-step surface-mutation checkpoint, fired once per step AFTER turn/start (and after the prior step closed) but BEFORE this step's step/start — so anything a listener appends lands OUTSIDE the step, between turn/start/step/end and the upcoming step/start. step is the number of the step about to start. The loop awaits ctx.serial('agent/pre-step', …) after assembling the system prompt, then opens the step and derives the request history ONCE from whatever the surface now holds. This is where compaction belongs: it mutates the session surface in place (shadowing an older range with a summary node) with its log-only compact/* records cleanly outside any step, and the single subsequent derive reflects the mutation — so there is no double-derive and no listener can see (or be expected to act on) an assembled messages array that does not exist yet.

Serial (awaited in registration order), not a waterfall: a listener mutates the surface as a side effect; there is nothing to transform, but the loop must wait for the mutation to complete before opening the step and deriving. Cordis serial bails early if a listener returns a bail value; this event is typed and documented as void, so listeners must not return a semantic veto value. fullSystemPrompt is the assembled prompt a listener needs to measure pressure (the system prompt counts toward the budget). signal cancels any in-flight work a listener starts (e.g. a summarization model call).

'agent/pre-step'(agent: Agent, turn: number, step: number, fullSystemPrompt: string, signal: AbortSignal): Promise<void> | void

Types: Agent

Source: packages/core/agent/src/types.ts:319

agent/prompt-submit — waterfall

Waterfall: decide what happens to ONE drained queued message before it becomes a user/message — allow (optionally rewriting the prompt bytes or attaching additionalContext) or block it. Fires inside the already-open turn, per drained message. Maps onto Claude Code's UserPromptSubmit hook. Call next() to delegate to the default (allow unchanged), or return a PromptDecision without calling next() to short-circuit.

'agent/prompt-submit'(agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise<PromptDecision>): Promise<PromptDecision>

Types: Agent · ContentBlock · MessageSource

Source: packages/core/agent/src/types.ts:332

agent/queued — emit

A message entered the agent's inbox (queued or steering). source is the resolved source (defaults applied), not the caller's raw options.

'agent/queued'(agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void

Types: Agent · ContentBlock · MessageSource

Source: packages/core/agent/src/types.ts:259

agent/request — waterfall

Waterfall: mutate the fully-assembled GenerateOptions before the model call (hooks, model switching, tool filtering, …). Call next() to delegate, or return without it to short-circuit. For surface mutation that must precede history derivation (compaction), use agent/pre-step instead — by the time this fires, options.messages is already derived.

'agent/request'(agent: Agent, turn: number, step: number, options: GenerateOptions, next: () => Promise<GenerateOptions>): Promise<GenerateOptions>

Types: Agent · GenerateOptions

Source: packages/core/agent/src/types.ts:345

agent/session-start — emit

The agent's session lifecycle began, fired once before its first turn. source says why (SessionStartSource: fresh startup, a resumed persisted session, …). A pure NOTIFICATION (emit, not waterfall): it carries no veto — a session-start listener that wants to seed context does so via agent.inject() (a context/message the first request sees), not by returning a decision. Cannot block the session from starting; that gap is deliberate (a bridge logs/injects, it does not gate startup).

'agent/session-start'(agent: Agent, source: SessionStartSource): void

Types: Agent

Source: packages/core/agent/src/types.ts:274

agent/status — emit

Agent status changed (idlerunning, or → disposed). Drive lifecycle off this transition, never off a status you just requested — send() does not flip status to running before it returns.

'agent/status'(agent: Agent, status: AgentStatus): void

Types: Agent

Source: packages/core/agent/src/types.ts:250

agent/step-result — waterfall

Waterfall: post-process the assembled assistant Message before tool dispatch (validation, content rewriting, …).

'agent/step-result'(agent: Agent, turn: number, step: number, message: Message, next: () => Promise<Message>): Promise<Message>

Types: Agent · Message

Source: packages/core/agent/src/types.ts:355

agent/turn-continuation — waterfall

Waterfall: override the turn-continuation decision via a typed ContinuationDecision. The loop's defaultDecision is continue when the step had tool calls or steering was injected, else stop. Listeners force-continue (/goal, /loop — optionally attaching a reason recorded as next-step steering) or force-stop (budget guards). Call next() to delegate to the default, or return a decision to override.

'agent/turn-continuation'(agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise<ContinuationDecision>): Promise<ContinuationDecision>

Types: Agent

Source: packages/core/agent/src/types.ts:368

fs/*

fs/edit-intent — waterfall

Single-slot decision: produce the optional version guard for the next FileSystem.editText. The tool dispatches this as an unbound waterfall and supplies a default thunk returning undefined (unconditional edit of the current content — the bare provider; no stat). The @deepseek-ai/dsh-fs-policy policy listener returns { version: vObserved }, or throws FS_NOT_OBSERVED if the actor is unset or has not observed the target. Does NOT call next(): one decision, first-wins (see Events.'fs/write-intent').

'fs/edit-intent'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined>

Types: FsTarget · FsVersion

Source: packages/fs/fs/src/index.ts:123

fs/observed — emit

Record that an actor observed a target at a version, after a successful read/write/edit. Fire-and-forget (plain emit). A listener MUST be a synchronous, side-effect-only recorder (@deepseek-ai/dsh-fs-policy's is a WeakMap.set): the tool does not guard the emit, so a listener that throws surfaces as the tool's isError result, and cordis emit does not await listener promises — async or fallible audit/telemetry does not belong here. No listener ⇒ nothing recorded. actor is the opaque tool-execution context.

'fs/observed'(target: FsTarget, version: FsVersion, actor: object | undefined): void

Types: FsTarget · FsVersion

Source: packages/fs/fs/src/index.ts:138

fs/write-intent — waterfall

Single-slot decision: produce the write intent for the next FileSystem.writeText. The tool dispatches this as an unbound waterfall (no this) and supplies a default thunk returning undefined (unconditional create-or-overwrite — the bare provider). The @deepseek-ai/dsh-fs-policy policy listener returns createIfAbsent (unobserved actor) or { kind: 'replaceIfVersion', version: vObserved } (observed) and does NOT call next() — one decision, not a composable chain. The slot is first-wins: the first non-next() decider (registration order, or prepend) occupies it; a second decider is a misconfiguration, not layering. actor is the opaque tool-execution context, never read here.

'fs/write-intent'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise<FsWriteIntent | undefined>): Promise<FsWriteIntent | undefined>

Types: FsTarget · FsWriteIntent

Source: packages/fs/fs/src/index.ts:109

llm/*

llm/stream — waterfall

Waterfall around every streaming model call (retry, caching, routing). Bound to the LlmService; call next() to reach the resolved adapter's stream, or yield your own chunks to short-circuit.

'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable<StreamChunk>): AsyncIterable<StreamChunk>

Types: GenerateOptions · StreamChunk

Source: packages/llm/llm/src/index.ts:33

session/*

session/created — emit

A session was created in the store.

'session/created'(session: Session): void

Source: packages/core/session/src/index.ts:36

session/event — emit

An event was appended to a session log (sync, fire-and-forget). This is the per-append feed a UI or invariant plugin tails.

'session/event'(session: Session, event: SessionEvent): void

Types: SessionEvent

Source: packages/core/session/src/index.ts:44

session/flush — parallel

Awaited durability checkpoint. The agent loop awaits ctx.parallel('session/flush', session) at every turn end; persistence plugins (JSONL, SQLite) drain their write-behind buffers here and on fiber dispose. Awaited (parallel), not a waterfall: every listener runs and the loop waits for all of them, but none can veto.

'session/flush'(session: Session): Promise<void> | void

Source: packages/core/session/src/index.ts:54

subagent/*

subagent/end — emit

A subagent run settled — emitted when SubagentRun.result resolves (any stop reason). Paired with Events['subagent/start'].

'subagent/end'(info: SubagentRunEndInfo): void

Source: packages/subagent/subagent/src/index.ts:77

subagent/start — emit

A subagent run started — emitted after the provider is resolved and its capabilities validated, as the child run begins. Paired with Events['subagent/end'].

'subagent/start'(info: SubagentRunInfo): void

Source: packages/subagent/subagent/src/index.ts:70

system-prompt/*

system-prompt/assemble — waterfall

Waterfall around prompt assembly — mutate or extend the PromptAssembly (sections + tool schemas) before it is rendered. Bound to the SystemPrompt service; call next() to delegate.

'system-prompt/assemble'(this: SystemPrompt, assembly: PromptAssembly, next: () => Promise<PromptAssembly>): Promise<PromptAssembly>

Source: packages/core/system-prompt/src/index.ts:26

system-prompt/change — emit

A section or tool provider was registered or unregistered (the assembly inputs changed).

'system-prompt/change'(): void

Source: packages/core/system-prompt/src/index.ts:32

tools/*

tools/change — emit

A tool was registered or unregistered (the available tool set changed).

'tools/change'(): void

Source: packages/core/tools/src/index.ts:87

tools/post-execute — waterfall

Waterfall AFTER a tool runs — where hook plugins inspect the result and accept it (optionally REPLACING the model-facing content, and/or attaching additionalContext for the next request) or block it with corrective feedback (Claude Code's PostToolUse). Listeners receive (exec, result, next): call next() to delegate to the default (accept unchanged), or return a PostToolDecision to override. The core tool dispatch sits between the two waterfalls as plain code, all inside execute's outer try/catch (and the tool body keeps its own inner try/catch, so a thrown tool still reaches post-execute as an isError result).

'tools/post-execute'(this: ToolRegistry, exec: ToolExecution, result: ToolExecutionResult, next: () => Promise<PostToolDecision>): Promise<PostToolDecision>

Types: ToolExecution · ToolExecutionResult

Source: packages/core/tools/src/index.ts:82

tools/pre-execute — waterfall

Waterfall BEFORE a tool runs — the gate where sandbox, permission, and hook plugins allow or deny a call (Claude Code's PreToolUse). Listeners receive (exec, next): call next() to delegate to the default (allow), or return a PreToolDecision without calling next() to short-circuit. A deny skips dispatch and yields an isError result; the tool body never runs. Input rewrite is deliberately NOT offered here (see PreToolDecision); ask degrades to deny until the permission system lands (FIXME(permissions)).

'tools/pre-execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>

Types: ToolExecution

Source: packages/core/tools/src/index.ts:66

Inherited events (cordis core + loader/hmr/timer)

The framework events every plugin also sees, beyond the harness vocabulary above. This is pinned vendor source (vendoring policy); it is summarized here so the page is a complete picture of the event bus, without elevating framework internals to the harness tier's prominence.