Files
deepseek-harness/docs/cordis-catalog/events-and-services.md
Hypatia May d6da8ca29a fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001)
Codex round 1 CBR-001: a head-anchored compaction checkpoint was
mis-classified by the log-position step-alignment scan, so a second
auto-compaction over a checkpoint-headed surface silently failed.

Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a
`replace` op lands a checkpoint at a high log seq whose SURFACE position
is the head — its log neighbours (the open step's assistant/message) are
not its surface neighbours, so the forward scan wrongly reported mid-step.

Fix, per the agreed direction:
- Replace the two log-position predicates with one surface-anchored
  helper `isToolPairingBalanced(nodes, events, beforeSeq)` in
  `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is
  balanced when no unanswered tool-call precedes it on the surface; a
  region is collapsible iff both edges are balanced cuts. The open-tail
  and free-node cases fall out of the same counter. It also throws on a
  corrupt surface (a tool/result with no matching call).
- Move compaction off the in-step seam to a new "pre-step" seam fired
  after turn/start and before step/start, so a compaction's log-only
  compact/* records and its replacement node land cleanly OUTSIDE any
  step (the honest structure crash-safety relies on). Renamed the event
  agent/pre-request → agent/pre-step and switched its dispatch from
  parallel → serial (listeners mutate the surface as a side effect;
  serial isolates them so concurrent appends can't interleave). Extended
  the catalog generator to accept @mode serial.

Regression coverage: a real-loop test driving an auto-compaction asserts
the landed checkpoint is a balanced cut on both sides; unit tests pin the
checkpoint case, the mid-step injection case, multi-call steps, and the
corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00

28 KiB

Cordis Events & Services Catalog

An index reference to the wiring a plugin author works against: every cordis event you can listen to (exact signature + dispatch mode) and every ctx.<key> service you can call (exact public interface). It complements core-data-structures/, which catalogs the data structures these signatures move around — this page is the verbs, that page is the nouns.

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. The inherited tier at the end is the cordis-core + loader/hmr/timer surface a plugin also sees — pinned vendor source, summarized tersely.

Events

Dispatch modes: emit (fire-and-forget), waterfall (each listener gets next() and may transform or veto — see waterfall semantics), parallel (awaited fan-out, no veto), serial (awaited, in registration order, no veto). The harness declares 25 events across 6 scopes.

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:137

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:143

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:249

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, no veto), not a waterfall: a listener mutates the surface as a side effect; there is nothing to transform or veto, but the loop must wait for the mutation to complete before opening the step and deriving, and serial isolates listeners from each other (one finishes its surface append before the next runs). system/model are the assembled values a listener needs to measure pressure (system counts toward the budget) and to summarize (the model). signal cancels any in-flight work a listener starts (e.g. a summarization model call).

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

Types: Agent

Source: packages/core/agent/src/types.ts:209

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:156

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:218

agent/status — emit

Agent status changed (idle ⇄ running, 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:150

agent/steering — emit

Steering content was injected into a running turn.

'agent/steering'(agent: Agent, turn: number, content: ContentBlock[], source: MessageSource): void

Types: Agent · ContentBlock · MessageSource

Source: packages/core/agent/src/types.ts:243

agent/step-end — emit

A step ended.

'agent/step-end'(agent: Agent, turn: number, step: number): void

Types: Agent

Source: packages/core/agent/src/types.ts:180

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:224

agent/step-start — emit

A step (one model call plus its tool dispatch) began. step is 1-based within the turn; a turn runs one or more steps.

'agent/step-start'(agent: Agent, turn: number, step: number): void

Types: Agent

Source: packages/core/agent/src/types.ts:175

agent/stream-chunk — emit

A raw StreamChunk arrived from the model (token-level UI/log feed).

'agent/stream-chunk'(agent: Agent, turn: number, step: number, chunk: StreamChunk): void

Types: Agent · StreamChunk

Source: packages/core/agent/src/types.ts:238

agent/turn-continuation — waterfall

Waterfall: override the turn-continuation decision. The default (computed by the loop) is hadToolCalls || steeringInjected. Listeners can force-continue (/goal, /loop) or force-stop (budget guards).

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

Types: Agent

Source: packages/core/agent/src/types.ts:231

agent/turn-end — emit

A turn ended. reason distinguishes a clean stop from a truncated or aborted one (completed | aborted | error | disposed | max-tokens).

'agent/turn-end'(agent: Agent, turn: number, reason: TurnEndReason): void

Types: Agent · TurnEndReason

Source: packages/core/agent/src/types.ts:169

agent/turn-start — emit

A turn began. turn is the 1-based turn number within the session.

'agent/turn-start'(agent: Agent, turn: number): void

Types: Agent

Source: packages/core/agent/src/types.ts:163

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:31

session/*

session/created — emit

A session was created in the store.

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

Source: packages/core/session/src/index.ts:34

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:40

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:49

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:65

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:59

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:24

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:30

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:48

tools/execute — waterfall

Waterfall around every tool execution — the single seam where sandbox, permission, hook, and plan-mode plugins wrap or veto a call. Listeners receive (exec, next): call next() to proceed (possibly around your own logic), or return a ToolExecutionResult without calling next() to short-circuit (veto).

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

Types: ToolExecution · ToolExecutionResult

Source: packages/core/tools/src/index.ts:43

Services

The 10 ctx.<key> services the harness provides. An abstract seam (e.g. ctx.bash) is implemented by a separate package; the interface is what consumers code against.

ctx.agentLoop — AgentLoop

The agent-loop plugin (ctx.agentLoop): creates ReactLoopAgents, runs their loops, and registers them in ctx.agents. Also implements the AgentFactory seam, so plugins create/resume agents through ctx.agents (the interface) without depending on this concrete package.

The loop itself is deliberately thin — every behavior beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy declared in @deepseek-ai/dsh-agent.

create(id: AgentId, options: AgentOptions = {}): ReactLoopAgent
createAgent(options: CreateAgentOptions): AgentHandle
async resume(options: ResumeAgentOptions): Promise<AgentHandle>

Source: packages/core/agent-loop/src/index.ts:63

ctx.agents — AgentRegistry

Agent registry (ctx.agents): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package. Agent creation is provided by whichever plugin implements the AgentFactory (phase 1: @deepseek-ai/dsh-agent-loop), registered via setFactory.

setFactory(factory: AgentFactory): () => void
create(options: CreateAgentOptions): AgentHandle
async resume(options: ResumeAgentOptions): Promise<AgentHandle>
register(agent: Agent): () => void
get(id: AgentId): Agent | undefined
list(): Agent[]

Types: Agent

Source: packages/core/agent/src/index.ts:117

ctx.bash — BashExecutor (abstract seam)

Abstract bash execution service. Subclass, implement the abstract methods, and load the subclass as a plugin — it registers as ctx.bash (one implementation per context; loading a second throws, which is cordis' standard duplicate-service behavior).

Semantics every implementation must honor:

  • run REJECTS only for infrastructure failures (unusable workdir, missing shell, pre-aborted signal). Nonzero exits, timeout kills, and abort kills RESOLVE with a descriptive BashRunResult — reporting a failed command is the tool layer's job, not an exception.
  • start returns immediately; no timeout applies to background tasks (callers stop them via kill or the spec's AbortSignal). Completion must fire the onTaskDone listeners exactly once per task, and must NOT fire after the service is disposed.
  • readOutput is incremental: consecutive reads never re-deliver output. Implementations bound their buffers; reads that lost data flag lossy and point at full-stream spill files when available.
  • Disposal kills every running task and awaits their exit (no orphan processes survive fiber.dispose()).
abstract resolve(request: BashExecRequest): BashExecSpec
abstract run(spec: BashExecSpec): Promise<BashRunResult>
abstract start(spec: BashExecSpec): BashTask
abstract get(id: BashTaskId): BashTask | undefined
abstract ownerOf(id: BashTaskId): OwnerToken | undefined
abstract list(): BashTask[]
abstract readOutput(id: BashTaskId): BashTaskRead
abstract kill(id: BashTaskId): boolean
onTaskDone(listener: BashTaskListener): () => void

Types: BashExecRequest · BashExecSpec · BashRunResult · BashTask · BashTaskRead

Source: packages/bash/bash/src/index.ts:59

ctx.compact — CompactService (abstract seam)

Abstract compaction service. Subclass implement the two abstract methods, and load the subclass as a plugin — it registers as ctx.compact (one implementation per context; loading a second throws, which is cordis' standard duplicate-service behavior).

Both core methods are abstract: the contract states WHAT compaction does, while the entire strategy — token estimation, retention policy, event sequencing, summarization — is a HOW decision owned by the implementation.

Implementations MUST honor:

  • Surface contract: a successful compaction shadows the compacted surface nodes with a SINGLE replacement node carrying the summary. Because SurfaceEventType is a closed union, that node is a user/message with surfaceOp: { op:'replace', start, end }; the compact/* events are log-only (lock + provenance).
  • Blocking: no compaction begins while another is in progress for the same session. The recommended mechanism is the log-recorded lock — append compact/start before the slow work and compact/end after (even on failure) — so the lock is visible to replay and crash recovery.
abstract compactIfNeeded( session: Session, system: string, model: string, signal: AbortSignal, ): Promise<CompactionResult | null>
abstract compactRegion( session: Session, start: number, end: number, model: string, signal?: AbortSignal, ): Promise<CompactionResult>

Source: packages/compact/compact/src/index.ts:57

ctx.llm — LlmService

The abstract llm service: an adapter registry plus a streaming model-call surface, interceptable via the llm/stream waterfall.

registerAdapter(models: string[], adapter: LlmAdapter): () => void
models(): string[]
stream(options: GenerateOptions): AsyncIterable<StreamChunk>

Types: GenerateOptions · StreamChunk

Source: packages/llm/llm/src/index.ts:69

ctx.sessionPersistence — SessionPersistence (abstract seam)

Abstract durable session-persistence service. Subclass, implement the abstract methods, and load the subclass as a plugin — it registers as ctx.sessionPersistence (one implementation per context; loading a second throws, cordis' standard duplicate-service behavior).

Contracts every implementation MUST honor (a DB backend asserts them inside a transaction; a file backend appends at EOF):

  • Append-only; a crashed turn is closed, not truncated. Committed events — those at or below a flushed turn/end — are never rewritten. A crash can leave an unclosed final turn whose events are real (and possibly large); load preserves them and closes the orphaned turn with synthetic boundary events (see load). Only a never-fully-written torn tail fragment is discarded.
  • Contiguous seq. A persisted log is contiguous: events[i].seq === i. load rejects a parse error or a seq gap in the COMMITTED region (unloadable); append's first event seq MUST equal the backend's stored next-seq (after load has balanced any interrupted turn).
  • JSON-serializable data. SessionEventMap is merge-extensible and event.data is typed only as SessionEventMap[K], so append REJECTS non-JSON-serializable data with an error naming the offending event type. A backend snapshots (serializes/clones) each event when it buffers, since session.events hands out the live mutable object.
  • Durability. append returns only once the batch is durable (the file backend fsyncs; a DB commits). create MAY defer the physical write until the first append (lazy materialization).
abstract create(meta: SessionHeader): Promise<void>
abstract append(id: SessionId, events: readonly SessionEvent[]): Promise<void>
abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>
abstract list(): Promise<SessionHeader[]>

Types: SessionEvent

Source: packages/session-persistence/session-persistence/src/index.ts:98

ctx.sessions — SessionStore

In-memory session store (ctx.sessions).

Persistence is intentionally not implemented here — persistence plugins subscribe to session/event and flush on session/flush / dispose.

create(id?: SessionId, options?: CreateSessionOptions): Session
prepare(id?: SessionId, options?: CreateSessionOptions): Session
enter(session: Session): () => void
announce(session: Session): void
get(id: SessionId): Session | undefined
list(): Session[]

Source: packages/core/session/src/index.ts:322

ctx.subagents — SubagentService

The subagents service: a registry of named SubagentProviders and a capability-checked start surface.

registerProvider(provider: SubagentProvider): () => void
getProvider(name: string): SubagentProvider | undefined
list(): string[]
start(name: string, request: SubagentStartRequest): SubagentRun

Source: packages/subagent/subagent/src/index.ts:103

ctx.systemPrompt — SystemPrompt

Registry service (ctx.systemPrompt): plugins contribute ordered text sections and tool-schema providers; the agent loop calls assemble() once per step.

section(section: PromptSection): () => void
tools(provider: () => ToolSchema[]): () => void
assemble(): Promise<PromptAssembly>

Source: packages/core/system-prompt/src/index.ts:71

ctx.tools — ToolRegistry

Tool registry (ctx.tools): tool plugins register definitions; the agent loop executes calls through the tools/execute waterfall. The registry contributes its schemas into the system-prompt assembly.

register(definition: ToolDefinition): () => void
get(name: string): ToolDefinition | undefined
schemas(): ToolSchema[]
async execute(exec: ToolExecution): Promise<ToolExecutionResult>

Types: ToolDefinition · ToolExecution · ToolExecutionResult

Source: packages/core/tools/src/index.ts:277

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

The framework surface every plugin inherits, beyond the harness vocabulary above. This is pinned vendor source (vendoring policy); it is summarized here so the catalog is a complete picture of what ctx and the event bus offer, without elevating framework internals to the harness tier's prominence.

Inherited events

Inherited ctx members