Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge origin/master into worktree/explicit-turn-signal

Browse Source
This commit is contained in:
Yichen Jiang
2026-07-20 21:38:49 +08:00
parent 5190e10d27 7b7d6f38e8
commit a92d2e5f34
1322 changed files with 47895 additions and 20257 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
packages/core/README.md
View File

@@ -8,12 +8,11 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co
| `session/` | Event-sourced session log + in-memory store | `ctx.sessions` |
| `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` |
| `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` |
| `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` |
| `agent-execution/` | Process-local ambient Agent identity for asynchronous driver work | `ctx.agentExecution` |
| `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` |
| `agent/` | Agent interface, live registry, process-local initiator scope, `agent/*` event vocabulary | `ctx.agents` |
| `agent-loop/` | Concrete plugin implementing the public `Agent` contract and owning the loop driver | `ctx.agentLoop` |
`scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle.
`agent-execution` is mandatory control infrastructure shared by concrete loops and deep process-local consumers. `agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop; other plugins depend on the `agent` vocabulary and execution service, never on `agent-loop` directly, so the loop stays swappable.
`agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop. It runs each driver inside `ctx.agents.withInitiator()`. Extension plugins depend on `agent`, including when they need the initiating Agent, and never on `agent-loop` directly, so the loop stays swappable.
The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + agent-execution + invariants + the local [skill family](../skill/README.md) + `tool-bash` + workspace-context + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door.
The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + the local [skill family](../skill/README.md) + `tool-bash` + workspace-context + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door.

23
packages/core/agent-execution/README.md
View File

@@ -1,23 +0,0 @@
# dsh-agent-execution
Process-local ambient Agent identity for asynchronous work initiated by a concrete agent driver. The default export, `AgentExecutionProvider`, installs the mandatory `ctx.agentExecution` service; [`dsh-agent-loop`](../agent-loop/README.md) establishes one boundary around each driver's complete lifetime.
## Service: `AgentExecutionService` (ctx key: `agentExecution`)
- `current()` returns the inherited `AgentExecution` or `undefined` outside a driver and inside an explicit clearing boundary.
- `require()` returns the inherited execution or throws `no agent execution context is active`.
- `run(execution, operation)` returns the exact synchronous value or Promise from `operation`. Passing `undefined` establishes a real boundary that hides an inherited Agent.
The store contains only `{ readonly agent: Agent }`. A Session is available through `agent.session`; turn, step, signal, cwd, sandbox, authorization, and other capability state remain with their explicit owners. Ambient presence identifies the initiator but does not prove that the Agent is live or that an operation is authorized.
## Lifetime and detached work
Provider teardown rejects new `run()` boundaries, removes the service so injected dependents drain, waits for returned Promise boundaries, then disables its `AsyncLocalStorage`. In-flight code retaining the service can call `current()` and `require()` while it drains; after disposal, all three methods throw `agent execution service is disposed`.
Async resources created inside `run()` inherit its Agent even when the operation does not await them. Agent-owned foreground work may inherit the boundary but keeps using the explicit cancellation and disposal contract of its execution seam. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)` and own an explicit stop. Queue, worker, process, and wire boundaries serialize any identity they need instead of relying on ALS propagation.
## Known Limitations and Deferred Work
- **Process-local only** — ALS does not cross workers, child processes, HTTP, durable queues, or restarts; each boundary materializes a typed identity explicitly.
- **Agent identity only** — turn, step, signal, cwd, sandbox, and authorization stay outside the frame until a concrete cross-cutting consumer justifies a separate design.
- **Ambient references may outlive liveness** — consumers still check `agent.status`, their explicit signal, and the owning capability contract before lifecycle-sensitive work.

31
packages/core/agent-execution/package.json
View File

@@ -1,31 +0,0 @@
{
"name": "@deepseek-ai/dsh-agent-execution",
"description": "Agent-scoped asynchronous execution context for the DeepSeek Harness",
"version": "0.0.1",
"private": true,
"type": "module",
"main": "lib/index.js",
"types": "lib/types/index.d.ts",
"exports": {
".": {
"types": "./lib/types/index.d.ts",
"default": "./lib/index.js"
},
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
],
"license": "BSD-3-Clause",
"peerDependencies": {
"@deepseek-ai/dsh-agent": "^0.0.1",
"cordis": "^4.0.0-rc.7"
},
"devDependencies": {
"@deepseek-ai/dsh-agent": "workspace:^",
"cordis": "^4.0.0-rc.7"
}
}

140
packages/core/agent-execution/src/index.ts
View File

@@ -1,140 +0,0 @@
/**
* Process-local Agent execution context backed by Node AsyncLocalStorage.
*
* @module @deepseek-ai/dsh-agent-execution
*/
import type { Context } from 'cordis'
import { AsyncLocalStorage } from 'node:async_hooks'
import { isPromise } from 'node:util/types'
import type { AgentExecution } from './types.ts'
export type { AgentExecution } from './types.ts'
const NO_ACTIVE_EXECUTION = 'no agent execution context is active'
const DISPOSED_SERVICE = 'agent execution service is disposed'
/** Ambient Agent identity within one process-local asynchronous chain. */
export interface AgentExecutionService {
/**
* Read the active execution without requiring one.
* @returns the inherited execution, or `undefined` outside/inside a cleared boundary.
* @throws when this service instance has been disposed.
*/
current(): AgentExecution | undefined
/**
* Read the active execution and fail when no boundary is active.
* @returns the inherited execution.
* @throws when no execution is active or this service instance has been disposed.
*/
require(): AgentExecution
/**
* Run an operation inside an execution boundary. Passing `undefined` clears
* an inherited execution; the exact synchronous value or Promise is returned.
* @param execution - execution to inherit, or `undefined` for a clearing boundary.
* @param operation - synchronous or asynchronous operation to invoke.
* @returns the exact value returned by `operation`.
* @throws when this service is closing/disposed, or when `operation` throws.
*/
run<T>(execution: AgentExecution | undefined, operation: () => T): T
}
declare module 'cordis' {
interface Context {
agentExecution: AgentExecutionService
}
}
/** One provider-owned ALS instance with quiescent shutdown. */
class DefaultAgentExecutionService implements AgentExecutionService {
private readonly storage = new AsyncLocalStorage<AgentExecution | undefined>()
private state: 'active' | 'closing' | 'disposed' = 'active'
private activeRuns = 0
private drainWaiter: PromiseWithResolvers<void> | undefined
private disposalTask: Promise<void> | undefined
current(): AgentExecution | undefined {
this.assertReadable()
return this.storage.getStore()
}
require(): AgentExecution {
const execution = this.current()
if (execution === undefined) throw new Error(NO_ACTIVE_EXECUTION)
return execution
}
run<T>(execution: AgentExecution | undefined, operation: () => T): T {
if (this.state !== 'active') throw new Error(DISPOSED_SERVICE)
this.activeRuns += 1
let result: T
try {
result = this.storage.run(execution, operation)
} catch (error: unknown) {
this.releaseRun()
throw error
}
if (isPromise(result)) {
void result.then(
() => { this.releaseRun() },
() => { this.releaseRun() },
)
} else {
this.releaseRun()
}
return result
}
/** Reject new boundaries while existing continuations remain readable. */
close(): void {
if (this.state === 'active') this.state = 'closing'
}
/** Wait for every returned Promise boundary, then invalidate retained references. */
dispose(): Promise<void> {
return (this.disposalTask ??= (async () => {
this.close()
if (this.activeRuns !== 0) {
this.drainWaiter ??= Promise.withResolvers<void>()
await this.drainWaiter.promise
}
this.state = 'disposed'
this.storage.disable()
})())
}
private assertReadable(): void {
if (this.state === 'disposed') throw new Error(DISPOSED_SERVICE)
}
private releaseRun(): void {
this.activeRuns -= 1
if (this.activeRuns !== 0) return
this.drainWaiter?.resolve()
this.drainWaiter = undefined
}
}
/** Cordis provider for the mandatory `ctx.agentExecution` service. */
export class AgentExecutionProvider {
private readonly service = new DefaultAgentExecutionService()
/**
* Install one isolated execution service and its ordered lifecycle.
* @param ctx - provider-owning Cordis context.
*/
constructor(ctx: Context) {
const service = this.service
ctx.effect(function* () {
// First yielded, disposed last: invalidate ALS only after dependents and active runs drain.
yield () => service.dispose()
yield ctx.provide('agentExecution', service)
// Last yielded, disposed first: prevent a teardown race from opening another boundary.
yield () => { service.close() }
}, 'agentExecution.lifecycle()')
}
}
export default AgentExecutionProvider

12
packages/core/agent-execution/src/types.ts
View File

@@ -1,12 +0,0 @@
/**
* Public Agent execution-context types.
*
* @module @deepseek-ai/dsh-agent-execution/types
*/
import type { Agent } from '@deepseek-ai/dsh-agent'
/** The exact live Agent associated with one asynchronous execution chain. */
export interface AgentExecution {
readonly agent: Agent
}

162
packages/core/agent-execution/tests/agent-execution.spec.ts
View File

@@ -1,162 +0,0 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import { runInNewContext } from 'node:vm'
import { AgentId, type Agent } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import type { AgentExecution, AgentExecutionService } from '@deepseek-ai/dsh-agent-execution'
function execution(id: string): AgentExecution {
return { agent: { id: AgentId(id) } as Agent }
}
async function harness(): Promise<{
ctx: Context
service: AgentExecutionService
dispose: () => Promise<void>
}> {
const ctx = new Context()
const fiber = await ctx.plugin(AgentExecutionProvider)
return {
ctx,
service: ctx.agentExecution,
dispose: fiber.dispose,
}
}
describe('AgentExecutionProvider', () => {
it('reports an absent boundary and requires an active execution', async () => {
const { service, dispose } = await harness()
expect(service.current()).toBeUndefined()
expect(() => service.require()).toThrow('no agent execution context is active')
await dispose()
})
it('preserves exact synchronous and Promise return identities across await', async () => {
const { service, dispose } = await harness()
const active = execution('identity')
const value = { result: true }
expect(service.run(active, () => {
expect(service.require()).toBe(active)
return value
})).toBe(value)
const promise = service.run(active, async () => {
expect(service.require()).toBe(active)
await Promise.resolve()
expect(service.require()).toBe(active)
return value
})
expect(service.run(active, () => promise)).toBe(promise)
await expect(promise).resolves.toBe(value)
expect(service.current()).toBeUndefined()
await dispose()
})
it('isolates overlapping executions', async () => {
const { service, dispose } = await harness()
const a = execution('a')
const b = execution('b')
const bothStarted = Promise.withResolvers<boolean>()
const release = Promise.withResolvers<boolean>()
let starts = 0
const run = (active: AgentExecution): Promise<void> => service.run(active, async () => {
expect(service.require()).toBe(active)
starts += 1
if (starts === 2) bothStarted.resolve(true)
await release.promise
expect(service.require()).toBe(active)
})
const pending = [run(a), run(b)]
await bothStarted.promise
expect(service.current()).toBeUndefined()
release.resolve(true)
await Promise.all(pending)
await dispose()
})
it('restores nested and explicitly cleared boundaries', async () => {
const { service, dispose } = await harness()
const parent = execution('parent')
const child = execution('child')
service.run(parent, () => {
expect(service.require()).toBe(parent)
service.run(child, () => { expect(service.require()).toBe(child) })
expect(service.require()).toBe(parent)
service.run(undefined, () => {
expect(service.current()).toBeUndefined()
expect(() => service.require()).toThrow('no agent execution context is active')
})
expect(service.require()).toBe(parent)
})
expect(service.current()).toBeUndefined()
await dispose()
})
it('restores context after synchronous throws and rejected operations', async () => {
const { service, dispose } = await harness()
const parent = execution('parent')
const child = execution('child')
const syncError = new Error('sync failure')
const asyncError = new Error('async failure')
service.run(parent, () => {
expect(() => service.run(child, () => { throw syncError })).toThrow(syncError)
expect(service.require()).toBe(parent)
})
await expect(service.run(child, async () => {
await Promise.resolve()
throw asyncError
})).rejects.toBe(asyncError)
expect(service.current()).toBeUndefined()
await dispose()
})
it('stops new boundaries, drains active Promises, and invalidates retained references', async () => {
const { ctx, service, dispose } = await harness()
const active = execution('draining')
const release = Promise.withResolvers<boolean>()
const pending = service.run(active, async () => {
await release.promise
expect(service.require()).toBe(active)
})
let disposed = false
const disposal = dispose().then(() => { disposed = true })
await Promise.resolve()
expect(() => service.run(active, () => 1)).toThrow('agent execution service is disposed')
expect(disposed).toBe(false)
expect(ctx.get('agentExecution')).toBeUndefined()
release.resolve(true)
await pending
await disposal
expect(() => service.current()).toThrow('agent execution service is disposed')
expect(() => service.require()).toThrow('agent execution service is disposed')
})
it('drains cross-realm Promise boundaries before disposal', async () => {
const { service, dispose } = await harness()
const active = execution('cross-realm')
const release = Promise.withResolvers<boolean>()
const operation = runInNewContext(
'(async () => { await release; inspect() })',
{
release: release.promise,
inspect: () => { expect(service.require()).toBe(active) },
},
) as () => Promise<void>
const pending = service.run(active, operation)
expect(pending).not.toBeInstanceOf(Promise)
let disposed = false
const disposal = dispose().then(() => { disposed = true })
await Promise.resolve()
expect(disposed).toBe(false)
release.resolve(true)
await pending
await disposal
expect(disposed).toBe(true)
})
})

21
packages/core/agent-execution/tsconfig.json
View File

@@ -1,21 +0,0 @@
{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib/types"
},
"include": [
"src"
],
"references": [
{
"path": "../../../vendor/cosmokit"
},
{
"path": "../../../vendor/cordis"
},
{
"path": "../../core/agent"
}
]
}

74
packages/core/agent-loop/README.md
View File

@@ -1,6 +1,6 @@
# dsh-agent-loop
Concrete `ReactLoopAgent` implementation and loop driver.
THE concrete agent plugin and loop driver. Its package-internal implementation satisfies the `Agent` interface and drives the session/turn/step lifecycle.
This is the only package in the harness that contains concrete loop logic. Everything else is an abstract service or a plugin against extension seams — new behavior goes into plugins, not here.
@@ -8,22 +8,24 @@ This is the only package in the harness that contains concrete loop logic. Every
### Public API
Creation and resume use one caller-owned transaction: compose while unpublished, enter both registries, announce lifecycle edges, then start the driver. Failure rolls back private resources; caller, handle, and provider teardown share one quiescence boundary. The interface contract and ownership order live in [`dsh-agent`](../agent/README.md) and the [agent-scope runtime RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md).
Creation and resume are one rollback-covered transaction: construct a private session, concrete agent, and scoped context; await optional setup; enter both registries; announce `session/created` then `agent/created`; emit `agent/session-start`; and only then start the driver. Setup receives the full scoped `Context` as trusted same-process composition code and must not drive the unpublished agent. Ordinary typed identity and option inputs are borrowed under their readonly contract, while seed events and session metadata are validated and snapshotted because they cross the durable session boundary. An optional `AbortSignal` cancels only load/setup/publication and is detached before the returned handle becomes visible.
Caller-chosen ids arbitrate only at final registry entry, so concurrent contenders may prepare but every loser rolls back. Entry-bound detach capabilities cannot remove a later same-id replacement. Teardown stops and drains—including idle-injection flushes—before detaching agent, session, and scope; ids become reusable at detach.
The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createAgent(ownerCtx, options)` and `resume(ownerCtx, options)` receive caller ownership explicitly, while the factory keeps its own dependency context for `sessions`/`llm`/`tools`/`systemPrompt`; this lets a caller inject only `agents` without shrinking the new agent's service surface. Caller unload, handle disposal, or provider unload converge on one memoized quiescence boundary. Provider shutdown waits both resource teardown and the public create/resume wrapper that observed deactivation, so no continuation can publish after dependencies disappear.
- `ctx.agentLoop.create(id, options?, meta?)` synchronously creates a caller-fiber-owned agent with a fresh generated session id and optional cwd. Each call starts a new session rather than applying resume-or-create policy.
Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`.
- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): Agent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-<uuid>` before calling this boundary. An app may instead supply a stable exact `sessionId`: first use creates it, while a remount with persistence already present resumes its materialized history. `resumeSessionId` requires and loads an existing persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity.
`AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface):
- `ctx.agents.create({ agentId, sessionId, meta?, seed?, agentOptions?, setup?, signal? })` validates and snapshots durable seed and metadata, awaits optional composition while unpublished, creates on the supplied session id, and returns an owned [`AgentHandle`](../agent/README.md). Its signal applies only until publication.
- `ctx.agents.resume({ agentId, resumeSessionId, agentOptions?, setup?, signal? })` loads through optional [session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md), continues stored history and turn numbering under the resumed session id, and follows the same unpublished setup and creation-only cancellation boundary. It rejects when no persistence backend is mounted.
- `ctx.agents.create({ sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise<AgentHandle>` — programmatic create under the caller-supplied shared id. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown.
- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise<AgentHandle>` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`.
The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle). For a programmatic agent, the handle holder is the only consumer-facing teardown capability; AgentLoop provider unload is the independent structural teardown edge, not another handle exposed to application code.
### Injected services
`agents`, `agentExecution`, `sessions`, `llm`, `tools`, `systemPrompt` — all six interface services. The loop cannot activate without `agentExecution`; the default bundle loads its provider before the loop.
`agents`, `sessions`, `llm`, `tools`, `systemPrompt` — all five interface services.
### Configuration (schemastery)
@@ -42,23 +44,19 @@ interface Config {
Configured agents start automatically. A model call requires both `provider` and `model`; `agent/request` may supply a missing pair before dispatch. `maxParallelToolCalls` bounds every agent's rolling pool for parallel-safe calls and defaults to `10`. `cwd` applies only to fresh sessions, while `resumeSessionId` retains persisted metadata. Configured agents use the deployment persona, and programmatic setup can shadow it per agent. This plugin supplies the per-agent `provider`, `model`, and `cwd` prompt variables; harness identity and deployment persona belong to `dsh-system-prompt`.
### Exported concrete class
### Internal concrete driver
- `ReactLoopAgent` — the concrete `Agent` implementation. Its inbox is a JavaScript native-private field, and one prepared session can be claimed by only one concrete driver. Everything observable happens through session events and the `agent/*` event taxonomy.
The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy.
`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()`, running `steer()`, and open-turn `inject()` materialize content plus resolved source once as detached, deeply frozen lossless JSON; malformed data throws before enqueue or append. An injection that arrives while the current step executes assistant tool calls stays in a FIFO until the batch settles; successful batches place it after the complete result batch, and interrupted batches drain it before the turn closes.
Each concrete `send()` materializes content plus resolved source once as a detached, deeply frozen lossless-JSON FIFO item. If claimed, it is the sole ordinary message in its turn; a successor waits for the preceding ordinary turn's checkpoint to settle, while cancellation, disposal, or a pre-start failure may drop it without a turn. Running `steer()` enters the steering FIFO: an open turn records it at the next steering checkpoint before a request or continuation decision, but policy can still stop before another step; steering left after turn close and its checkpoint becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. Open-turn `inject()` uses the same accepted-value boundary but defers in a FIFO while the current step executes assistant tool calls; successful batches place it after all results, and interrupted batches drain it before turn close. Malformed data throws before enqueue or append.
### Loop lifecycle (`loop.ts`)
The driver owns one agent for its lifetime and runs inside `ctx.agentExecution.run({ agent }, ...)`, so process-local asynchronous continuations can recover the initiating Agent. The ALS frame contains only `{ agent }`: creation, persistence load, and unpublished setup stay outside the child boundary, while turn, step, signal, and other control state remain explicit at every seam. The [execution-context package](../agent-execution/README.md) owns propagation and detached-work rules.
The loop records turn, step, request, stream, and tool boundaries in the session log; live extension events coordinate policy around those durable facts. The [architecture turn flow](../../../docs/architecture.md#turn-flow) and generated [event catalog](../../../docs/cordis-catalog/events.md) are the authoritative sequence and signatures.
The driver owns one agent for its lifetime and runs inside `ctx.agents.withInitiator(agent, ...)`. Package-private orchestration entry points recover the exact Agent, derive `agent.session` once, and let operation-local helpers capture it instead of forwarding the concrete driver or per-operation `Session` through shallow interfaces. A helper keeps an explicit `Session` when that is its actual interface, while creation, persistence load, unpublished setup, services, workers, processes, persistence, and wire protocols retain their explicit identities. The [agent service](../agent/README.md#initiating-agent-scope) owns propagation, teardown, and detached-work rules.
Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history.
Plugin failure ends the current turn, not the loop. The loop creates one private turn cancellation holder before announcing `running`, passes its single signal through prompt handling, prompt assembly, every step, model and tool execution, continuation, terminal stop, turn end, and durability flush, then discards it. A replacement prompt accepted after cancellation receives a fresh holder, while all work in the cancelled turn observes the first typed runtime cause. The durable turn outcome is only `aborted`; disposal is a separate runtime interrupt and wins classification even if cancellation reached the signal first.
Cancellation is cooperative: the loop checks for interruption between awaited boundaries but does not abandon an in-process listener, adapter, or tool Promise with `Promise.race`. `whenIdle()` and handle disposal therefore observe real quiescence. See the [explicit turn cancellation RFC](../../../docs/rfc/implemented/architecture/2026-07-16-explicit-turn-cancellation.md).
Plugin failure ends the current turn, not the loop. Only final adapter dispatch/iteration failures and terminal in-band error or aborted finishes enter `agent/request-error`; middleware, result processing, tools, and `agent/post-step` remain ordinary turn failures. Recovery observes a closed failed step, and a retry rebuilds the request from the durable log in a new numbered step. AgentLoop privately owns one cancellation holder whose explicit signal spans prompt policy, assembly, every step, model and tool work, continuation, terminal stop, turn close, and flush; the next turn gets a fresh signal. `cancel()` strictly normalizes a runtime-only `user | parent` cause, clears pending work, and cooperatively aborts the holder without leaking to the next prompt; durable `turn/end` remains coarse `aborted`, and undispatched model tool calls receive synthetic `tool/call` and aborted result pairs. Disposal wins terminal classification, and work that ignores the signal must settle before quiescence. The [explicit-cancellation decision](../../../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md) owns the lifecycle and race contract. Terminal continuation stops remain authoritative through turn close and durability flush.
Within a step, exclusive calls form barriers; parallel-safe calls use a bounded rolling pool and are reclassified before start. Only dispatch/body overlaps. Policy, durable results, and result context remain model-ordered. Abort stops new calls, drains started results, then drains accepted batch context before the turn closes through the normal abort path.
@@ -66,7 +64,7 @@ Within a step, exclusive calls form barriers; parallel-safe calls use a bounded
Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy:
- Hooks and policy: the relevant `agent/*` checkpoints plus the guarded `tools/pre-execute` → `tools/execute` → `tools/post-execute` → `tools/result` pipeline; exact signatures and modes live in the [generated event catalog](../../../docs/cordis-catalog/events.md)
- Compaction: `agent/pre-step`
- Compaction: pressure on `agent/post-step`; canonical context overflow on `agent/request-error`
- Sandbox, permission, plan mode: `tools/pre-execute` for extensible deny/ask, `tools.guard()` for monotonic owner policy, `tools/post-execute` for result decisions, and `tools/result` for final observation
- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while generic [`ctx.tasks`](../../tasks/tasks/) plus [`dsh-tool-subagent`](../../subagent/tool-subagent/) own background collection.
- Persistence: `session/event` + `session/flush`
@@ -76,19 +74,49 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p
### Complete conversation request
**What the model sees**: For each step, the loop sends the rendered per-agent system prompt, visible tool schemas, the frozen session prefix, and the session's derived messages. It supplies `model` and `cwd` variable values but no additional fixed prose.
#### What the model sees
**Token effect**: System text, schemas, and prefix are paid again on every step. Per-agent scoping chooses the initial contributions, while the authoritative assembly waterfall can alter the final request and makes its listener responsible for protocol coherence.
For each step, the loop sends the rendered per-agent system prompt, visible tool schemas, the frozen session prefix, and the session's derived messages. It supplies `model` and `cwd` variable values but no additional fixed prose.
#### Token effect
System text, schemas, and prefix are paid again on every step. Per-agent scoping chooses the initial contributions, while the authoritative assembly waterfall can alter the final request and makes its listener responsible for protocol coherence.
#### KV Cache effect
Append-only only while system text, schemas, session prefix, and earlier history remain byte-identical under the same provider and model route. A token-bearing assembly rewrite or composition change may invalidate reuse from the first altered request token.
### Retained message history
**What the model sees**: Accepted user messages, assistant messages, tool calls and results, injected context, and steering are logged and sent on later steps. Raw stream chunks, lifecycle boundaries, and other log-only events are excluded.
#### What the model sees
**Token effect**: Input grows with every surface message until a compaction replacement shadows older nodes; a multi-step tool turn resends the accumulated prefix and history each step.
Accepted user messages, assistant messages, tool calls and results, injected context, and steering are logged and sent on later steps. Raw stream chunks, lifecycle boundaries, and other log-only events are excluded.
#### Token effect
Input grows with every surface message until a compaction replacement shadows older nodes; a multi-step tool turn resends the accumulated prefix and history each step.
#### KV Cache effect
Ordinary history growth is append-only and preserves reusable entries. A surface replacement or compaction invalidates reuse from the first shadowed history token.
### Undispatched calls after cancellation
#### What the model sees
If a later request replays an aborted step, each tool call that cancellation prevented from dispatching has the error result text `Error: tool call skipped because the step was aborted before execution`.
#### Token effect
One fixed error result per skipped call remains in history until compaction shadows it.
#### KV Cache effect
Append-only; each synthetic result follows the reusable request prefix and does not invalidate existing KV-cache entries.
## Known Limitations and Deferred Work
- **Classification is unary** — calls whose safety depends on comparing siblings or resources must remain exclusive ([rationale](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)).
- **No resume-or-create policy on the config path** — config-driven `create()` starts a fresh `${id}-session-<uuid>` every run (`TODO(demo)`), and a config `resumeSessionId` whose resume fails logs a warning and creates no agent.
- **Classification is unary** — calls whose safety depends on comparing siblings or resources must remain exclusive ([rationale](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)).
- **Config labels are fresh by default** — omitting `sessionId` creates a fresh `${id}-session-<uuid>` on every startup; exact resume-or-create behavior requires an explicit stable `sessionId`, while `resumeSessionId` requires existing persisted history.
- **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options.
- **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin.

2
packages/core/agent-loop/package.json
View File

@@ -22,7 +22,6 @@
"license": "BSD-3-Clause",
"peerDependencies": {
"@deepseek-ai/dsh-agent": "^0.0.1",
"@deepseek-ai/dsh-agent-execution": "^0.0.1",
"@deepseek-ai/dsh-llm": "^0.0.1",
"@deepseek-ai/dsh-scope": "^0.0.1",
"@deepseek-ai/dsh-session": "^0.0.1",
@@ -36,7 +35,6 @@
},
"devDependencies": {
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-agent-execution": "workspace:^",
"@deepseek-ai/dsh-invariants": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-scope": "workspace:^",

59
packages/core/agent-loop/src/agent.ts
View File

@@ -8,11 +8,11 @@
import type { Context } from 'cordis'
import { agentEvents, normalizeAgentCancelCause } from '@deepseek-ai/dsh-agent'
import type { AgentCancelCause, AgentId, AgentOptions, AgentStatus, HookContext, InjectOptions, SendOptions } from '@deepseek-ai/dsh-agent'
import type { AgentCancelCause, AgentOptions, AgentStatus, HookContext, InjectOptions, SendOptions } from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { deepFreeze } from '@deepseek-ai/dsh-llm'
import { deepFreeze, errorChain } from '@deepseek-ai/dsh-llm'
import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
import { snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session'
import { snapshotJsonValue, type Session, type SessionId } from '@deepseek-ai/dsh-session'
import { DISPOSED_INTERRUPT_REASON, TurnCancellation } from './cancellation.ts'
import { Inbox, type InboxMessage } from './inbox.ts'
import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts'
@@ -59,7 +59,11 @@ export interface PreparedReactLoopAgent {
* @returns the agent and closures bound only to that exact instance.
*/
export function prepareReactLoopAgent(
ctx: Context, id: AgentId, options: AgentOptions, session: Session, maxParallelToolCalls: number,
ctx: Context,
id: SessionId,
options: AgentOptions,
session: Session,
maxParallelToolCalls: number,
): PreparedReactLoopAgent {
if (claimedDriverSessions.has(session)) {
throw new Error(`session "${session.id}" already has a concrete agent driver`)
@@ -77,7 +81,6 @@ export function prepareReactLoopAgent(
},
}
}
/**
* Install the concrete agent's scope context exactly once. Construction and
* scope minting are mutually referential (the scope key is the agent), so the
@@ -93,7 +96,7 @@ export function bindReactLoopAgentContext(agent: ReactLoopAgent, ctx: Context):
/**
* The concrete {@link Agent} implementation owned by the agent-loop plugin.
*
* Owns the inbox (queued + steering FIFOs), one turn cancellation holder, and
* Owns the inbox (queued + steering FIFOs), turn cancellation, and
* the loop driver. Everything observable happens through session events and
* the agent/* event taxonomy — plugins never need this class.
*/
@@ -118,17 +121,13 @@ export class ReactLoopAgent implements Agent {
}
private _status: AgentStatus = 'idle'
/** Active turn owner, installed before the running notification and retained through flush. */
/** Active turn owner from pre-running publication through durability settlement. */
private turnCancellation: TurnCancellation | undefined
/** Whether runLoop has been installed into {@link done}. */
private driverStarted = false
/** Whether registry publication began and status disposal is externally visible. */
private published = false
/**
* Cause-less marker for queued work cancelled before the driver installs a
* turn owner. It never represents an active turn and cannot leak a cause into
* replacement work.
*/
/** Cause-less marker for queued work cancelled before the driver installs a turn owner. */
private preRunCancelled = false
private disposed: Promise<void>
private resolveDisposed!: () => void
@@ -157,7 +156,7 @@ export class ReactLoopAgent implements Agent {
constructor(
private loopCtx: Context,
public readonly id: AgentId,
public readonly id: SessionId,
public readonly options: AgentOptions,
public readonly session: Session,
maxParallelToolCalls: number,
@@ -246,7 +245,6 @@ export class ReactLoopAgent implements Agent {
const context = {
content,
source,
...options?.envelope !== undefined ? { envelope: options.envelope } : {},
...options?.meta !== undefined ? { meta: options.meta } : {},
}
if (isTurnOpen(this.session)) {
@@ -285,7 +283,7 @@ export class ReactLoopAgent implements Agent {
if (turnRecorded) {
// Through the store's flush (the carrier owner), never a raw parallel.
const flush = this.loopCtx.sessions.flush(this.session).catch((error: unknown) => {
const rendered = renderThrown(error)
const rendered = errorChain(error)
const err = error instanceof Error ? error : new Error(rendered)
this.loopCtx.logger.warn(`agent "${this.id}": flush after idle injection failed: ${rendered}`)
agentEvents(this.loopCtx, this).emit('agent/error', turn, 0, err)
@@ -327,18 +325,16 @@ export class ReactLoopAgent implements Agent {
}
cancel(cause?: AgentCancelCause): void {
// Validate before the idle no-op so misuse fails consistently in every state.
const accepted = normalizeAgentCancelCause(cause ?? { kind: 'user' })
const active = this.turnCancellation
if (active === undefined && !this.#inbox.hasQueued && !this.#inbox.hasSteering) return
if (active === undefined) this.preRunCancelled = true
// Drop all pending queued + steering work (un-started prompts never run; the
// cancelled turn's steering is not re-enqueued). Clear before abort dispatch,
// whose synchronous observers may enqueue replacement work that must survive.
// This is direct even when the loop is parked in waitForQueued — there is no
// turn to stop and nothing left for the parked loop to run, so no wake is needed.
const normalized = normalizeAgentCancelCause(cause ?? { kind: 'user' })
const cancellation = this.turnCancellation
const preRun = cancellation === undefined && (this.#inbox.hasQueued || this.#inbox.hasSteering)
if (preRun) {
this.preRunCancelled = true
}
// Clear work already present before abort observers run. A replacement
// synchronously enqueued by an observer belongs to the next turn.
this.#inbox.clear()
if (active !== undefined) active.request(accepted)
cancellation?.request(normalized)
}
/**
@@ -376,7 +372,7 @@ export class ReactLoopAgent implements Agent {
[startDriver](): void {
if (this._status === 'disposed') return
this.driverStarted = true
this.done = this.loopCtx.agentExecution.run({ agent: this }, () => runLoop(this.loopCtx, this, {
this.done = this.loopCtx.agents.withInitiator(this, () => runLoop(this.loopCtx, {
inbox: this.#inbox,
maxParallelToolCalls: this.maxParallelToolCalls,
setStatus: (status) => { this.setStatus(status) },
@@ -386,7 +382,7 @@ export class ReactLoopAgent implements Agent {
return cancellation
},
clearTurnCancellation: (cancellation) => {
/* v8 ignore else -- the internal driver clears only the exact holder returned by its latest install */
/* v8 ignore else -- the driver clears only the exact owner returned by its latest install. */
if (this.turnCancellation === cancellation) this.turnCancellation = undefined
},
disposed: this.disposed,
@@ -394,7 +390,7 @@ export class ReactLoopAgent implements Agent {
isPreRunCancelled: () => this.preRunCancelled,
clearPreRunCancel: () => { this.preRunCancelled = false },
withToolBatch: run => this.withToolBatch(run),
// Pre-run cancellation re-parks without emitting a status transition.
// Pre-run cancellation settles queued-work waiters before publishing idle.
settleIdle: () => { this.settleIdleWaiters() },
}))
}
@@ -441,8 +437,3 @@ export class ReactLoopAgent implements Agent {
}
}
}
/** Render an ordinary thrown value for the error event and log. */
function renderThrown(value: unknown): string {
return value instanceof Error ? value.message : String(value)
}

12
packages/core/agent-loop/src/inbox.ts
View File

@@ -15,7 +15,7 @@ export interface InboxMessage {
}
/**
* Per-agent inbox: a queued FIFO (drained at turn start) and a steering FIFO
* Per-agent inbox: a queued FIFO (dequeued once per turn start) and a steering FIFO
* (drained between steps of a running turn). Purely an in-memory mechanism of
* the loop — the public surface is `Agent.send()` / `Agent.steer()`.
*/
@@ -54,11 +54,11 @@ export class Inbox {
}
/**
* Drain all queued messages (turn start).
* @returns the drained messages in arrival order; the queued FIFO is left empty.
* Remove the oldest queued message for one turn start.
* @returns the oldest message, or `undefined` when the queued FIFO is empty.
*/
drainQueued(): InboxMessage[] {
return this.queuedMessages.splice(0)
dequeueQueued(): InboxMessage | undefined {
return this.queuedMessages.shift()
}
/**
@@ -72,7 +72,7 @@ export class Inbox {
/**
* Discard all pending messages (queued + steering) without delivering them —
* used by `cancel()`, which drops un-started work rather than draining it into
* a turn. Unlike `drainQueued`/`drainSteering`, the messages are thrown away.
* a turn. Unlike `dequeueQueued`/`drainSteering`, the messages are thrown away.
*/
clear(): void {
this.queuedMessages.length = 0

180
packages/core/agent-loop/src/index.ts
View File

@@ -11,17 +11,16 @@ import z from 'schemastery'
import { createScope } from '@deepseek-ai/dsh-scope'
import type { Scope } from '@deepseek-ai/dsh-scope'
import { agentEvents } from '@deepseek-ai/dsh-agent'
import type {} from '@deepseek-ai/dsh-agent-execution'
import type {
Agent,
AgentFactory,
AgentHandle,
AgentId,
AgentOptions,
CreateAgentOptions,
ResumeAgentOptions,
SessionStartSource,
} from '@deepseek-ai/dsh-agent'
import type {} from '@deepseek-ai/dsh-llm'
import { errorChain } from '@deepseek-ai/dsh-llm'
import { SessionId } from '@deepseek-ai/dsh-session'
import type { Session, SessionHeader } from '@deepseek-ai/dsh-session'
import type {} from '@deepseek-ai/dsh-system-prompt'
@@ -35,8 +34,6 @@ import {
import type { PreparedReactLoopAgent } from './agent.ts'
import { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from './constants.ts'
export { ReactLoopAgent } from './agent.ts'
/** Fiber states that cannot own or serve a new lifecycle. */
const INACTIVE_STATES: ReadonlySet<FiberState> = new Set([
FiberState.UNLOADING,
@@ -47,7 +44,9 @@ const INACTIVE_STATES: ReadonlySet<FiberState> = new Set([
/** Factory-level ownership of every preparing or live transaction. */
class FactoryOwnership {
private accepting = true
private readonly inactive = Promise.withResolvers<void>()
private transactions = new Set<AgentCreationTransaction>()
private startupTasks = new Set<Promise<void>>()
constructor(private readonly fiber: Context['fiber']) {}
@@ -60,17 +59,31 @@ class FactoryOwnership {
return () => { this.transactions.delete(transaction) }
}
/** Join config startup work that begins before an agent transaction exists. */
trackStartup(task: Promise<void>): void {
this.startupTasks.add(task)
const forget = () => { this.startupTasks.delete(task) }
void task.then(forget, forget)
}
/** Resolve `task`, or stop waiting when factory teardown begins. */
async waitWhileActive(task: Promise<void>): Promise<void> {
await Promise.race([task, this.inactive.promise])
}
async dispose(): Promise<void> {
this.accepting = false
this.inactive.resolve()
const reason = new Error('agent loop is not active')
await Promise.all(
[...this.transactions].map(transaction => transaction.disposeForFactory(reason)),
)
await Promise.all([
...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)),
...this.startupTasks,
])
}
}
/** Build the public cancellation error while preserving a caller-supplied cause. */
function signalAbortError(id: AgentId, signal: AbortSignal): Error {
function signalAbortError(id: SessionId, signal: AbortSignal): Error {
if (signal.reason instanceof Error) return signal.reason
return new Error(`agent "${id}" creation aborted`, { cause: signal.reason })
}
@@ -116,7 +129,7 @@ class AgentCreationTransaction {
private readonly loopCtx: Context,
private readonly ownerCtx: Context,
private readonly ownership: FactoryOwnership,
readonly id: AgentId,
readonly id: SessionId,
signal?: AbortSignal,
) {
ownerCtx.fiber.assertActive()
@@ -238,7 +251,7 @@ class AgentCreationTransaction {
this.publishing = true
try {
this.detachSession = agent.ctx.sessions.enter(session)
this.detachAgent = this.loopCtx.agents.enter(agent)
this.detachAgent = this.loopCtx.agents.enter(agent, this.ownerAgent)
agent.ctx.sessions.announce(session)
this.assertActive()
@@ -327,6 +340,18 @@ declare module 'cordis' {
interface Context {
agentLoop: AgentLoop
}
interface Events {
/**
* A declarative agent entry failed before it could publish a live agent.
* Consumers that buffer work for the configured identity use this
* transient signal to reject that work instead of waiting forever. Normal
* factory teardown suppresses failures from the cancelled startup attempt.
* @param sessionId - exact shared agent/session identity that failed startup.
* @param error - persistence, setup, or publication failure.
* @mode emit
*/
'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void
}
}
export { DEFAULT_MAX_PARALLEL_TOOL_CALLS }
@@ -340,8 +365,10 @@ export interface Config {
maxParallelToolCalls?: number
/** Agents created or resumed at plugin startup. */
agents: (AgentOptions & {
/** Registry identity for the live agent. */
id: AgentId
/** Stable config label used in logs and as the fresh combined-id prefix. */
id: string
/** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */
sessionId?: SessionId
/** Optional workspace for a fresh session. */
cwd?: string
/** Persisted session to resume instead of creating a fresh session. */
@@ -349,15 +376,34 @@ export interface Config {
})[]
}
/** Concrete ReactLoopAgent factory and driver service. */
/** Reject self-contained identity conflicts before any configured agent starts. */
function validateConfiguredAgents(agents: Config['agents']): void {
const exactIdentities = new Map<SessionId, string>()
for (const { id, sessionId, resumeSessionId } of agents) {
const hasResumeId = resumeSessionId !== undefined && resumeSessionId !== ''
if (sessionId !== undefined && hasResumeId) {
throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`)
}
const exactIdentity = hasResumeId ? resumeSessionId : sessionId
if (exactIdentity === undefined) continue
const firstId = exactIdentities.get(exactIdentity)
if (firstId !== undefined) {
throw new Error(`agents "${firstId}" and "${id}" use duplicate exact session identity "${exactIdentity}"`)
}
exactIdentities.set(exactIdentity, id)
}
}
/** Concrete agent factory and driver service. */
export class AgentLoop extends Service implements AgentFactory {
static inject = ['agents', 'agentExecution', 'sessions', 'llm', 'tools', 'systemPrompt']
static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt']
/** Runtime schema for declarative agents. */
static Config = z.object({
maxParallelToolCalls: z.number().step(1).min(1).default(DEFAULT_MAX_PARALLEL_TOOL_CALLS),
agents: z.array(z.object({
id: z.string().required(),
sessionId: z.string().min(1),
provider: z.string(),
model: z.string(),
cwd: z.string(),
@@ -373,6 +419,7 @@ export class AgentLoop extends Service implements AgentFactory {
constructor(ctx: Context, public config: Config) {
super(ctx, 'agentLoop')
validateConfiguredAgents(config.agents)
this.maxParallelToolCalls = resolveMaxParallelToolCalls(config.maxParallelToolCalls)
this.ownership = new FactoryOwnership(ctx.fiber)
this.runtime = { ctx }
@@ -382,19 +429,28 @@ export class AgentLoop extends Service implements AgentFactory {
ctx.systemPrompt.variable('model', context => context.agent?.options.model)
ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd)
for (const { id, cwd, resumeSessionId, ...options } of config.agents) {
for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) {
const meta = cwd === undefined ? {} : { cwd }
if (resumeSessionId === undefined || resumeSessionId === '') {
this.create(id, options, cwd === undefined ? {} : { cwd })
const configuredId = sessionId ?? SessionId(`${id}-session-${randomUUID()}`)
const persistence = sessionId === undefined ? undefined : ctx.get('sessionPersistence')
if (persistence === undefined) {
this.create(configuredId, options, meta)
} else {
const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => {
this.reportConfiguredStartupFailure(id, 'restore', configuredId, error)
})
this.ownership.trackStartup(startup)
}
continue
}
ctx.effect(() => {
const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => {
void this.resumeWith(ctx, childCtx.sessionPersistence, {
agentId: id,
resumeSessionId,
agentOptions: options,
}).catch((error: unknown) => {
ctx.logger.warn(`agent "${id}": config-driven resume of "${resumeSessionId}" failed: ${String(error)}`)
this.reportConfiguredStartupFailure(id, 'resume', resumeSessionId, error)
})
})
return fiber.dispose
@@ -402,20 +458,83 @@ export class AgentLoop extends Service implements AgentFactory {
}
}
/** Report a contained declarative-start failure to identity-bound consumers. */
private reportConfiguredStartupFailure(
configId: string,
action: 'restore' | 'resume',
sessionId: SessionId,
error: unknown,
): void {
if (!this.ownership.isActive()) return
this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${errorChain(error)}`)
const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error]
for (const callback of this.ctx.events.dispatch('emit', args)) {
try {
const returned: unknown = callback(...args)
void Promise.resolve(returned).catch((listenerError: unknown) => {
this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${errorChain(listenerError)}`)
})
} catch (listenerError: unknown) {
this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${errorChain(listenerError)}`)
}
}
}
/** Restore a materialized exact config identity on remount, or create it on first use. */
private async restoreOrCreateConfigured(
ownerCtx: Context,
persistence: SessionPersistence,
sessionId: SessionId,
agentOptions: AgentOptions,
meta: Pick<SessionHeader, 'cwd'>,
): Promise<void> {
await this.waitForDrainingConfiguredIdentity(ownerCtx, sessionId)
if (!this.ownership.isActive()) return
const exists = (await persistence.list()).some(header => header.id === sessionId)
if (!this.ownership.isActive()) return
if (exists) {
await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions })
return
}
this.create(sessionId, agentOptions, meta)
}
/** Wait for an already-disposed same-id lifecycle to finish registry teardown. */
private async waitForDrainingConfiguredIdentity(ownerCtx: Context, sessionId: SessionId): Promise<void> {
const current = ownerCtx.agents.get(sessionId)
if (current?.status !== 'disposed') return
const released = Promise.withResolvers<void>()
const checkReleased = (): void => {
if (ownerCtx.agents.get(sessionId) === undefined && ownerCtx.sessions.get(sessionId) === undefined) {
released.resolve()
}
}
const disposeAgentListener = ownerCtx.on('agent/disposed', checkReleased)
const disposeSessionListener = ownerCtx.on('session/disposed', checkReleased)
try {
checkReleased()
await this.ownership.waitWhileActive(released.promise)
} finally {
disposeAgentListener()
disposeSessionListener()
}
}
/**
* Create an agent on a fresh per-run session, owned by the accessing fiber.
* Constructor-driven config calls use the loop fiber itself.
* @param id - agent registry id.
* Create an agent and session under one caller-supplied identity, owned by
* the accessing fiber. Constructor-driven config calls mint a fresh combined
* id before entering this boundary.
* @param id - shared agent/session identity.
* @param options - concrete loop options.
* @param meta - optional fresh-session workspace metadata.
* @returns the published running agent.
*/
create(id: AgentId, options: AgentOptions = {}, meta: Pick<SessionHeader, 'cwd'> = {}): ReactLoopAgent {
create(id: SessionId, options: AgentOptions = {}, meta: Pick<SessionHeader, 'cwd'> = {}): Agent {
const loopCtx = this.runtime.ctx
const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id)
try {
const sessionId = SessionId(`${id}-session-${randomUUID()}`)
const session = loopCtx.sessions.prepare(sessionId, { meta })
const session = loopCtx.sessions.prepare(id, { meta })
const agent = transaction.prepare(options, session, this.maxParallelToolCalls)
transaction.publish('startup')
return agent
@@ -439,7 +558,7 @@ export class AgentLoop extends Service implements AgentFactory {
this.runtime.ctx,
ownerCtx,
this.ownership,
options.agentId,
options.sessionId,
options.signal,
)
try {
@@ -484,7 +603,7 @@ export class AgentLoop extends Service implements AgentFactory {
this.runtime.ctx,
ownerCtx,
this.ownership,
options.agentId,
options.resumeSessionId,
options.signal,
)
try {
@@ -492,12 +611,7 @@ export class AgentLoop extends Service implements AgentFactory {
transaction.assertActive()
const session = this.runtime.ctx.sessions.prepare(options.resumeSessionId, {
seed: loaded.events,
meta: {
createdAt: loaded.meta.createdAt,
...loaded.meta.cwd === undefined ? {} : { cwd: loaded.meta.cwd },
...loaded.meta.parentSession === undefined ? {} : { parentSession: loaded.meta.parentSession },
...loaded.meta.seedLength === undefined ? {} : { seedLength: loaded.meta.seedLength },
},
meta: loaded.meta,
})
const agent = transaction.prepare(agentOptions, session, this.maxParallelToolCalls)
await transaction.waitFor(options.setup?.(agent.ctx))

442
packages/core/agent-loop/src/loop.ts
View File

@@ -1,16 +1,16 @@
/**
* Drives one agent across queued durable turns. Turn failures are contained so
* later work can run; the session log, not this driver, owns conversation state.
* See docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md.
* See .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md.
* @module dsh-agent-loop/loop
*/
import type { Context } from 'cordis'
import { isDeepStrictEqual } from 'node:util'
import type { ContentBlock, FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm'
import { assertNever, BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm'
import { isDeepStrictEqual } from 'node:util'
import { BlockAssembler, HarnessError, assertNever, deepFreeze, errorChain, isLlmAdapterFailure } from '@deepseek-ai/dsh-llm'
import { agentEvents, agentInterruptReasonOf, assembleContextFor } from '@deepseek-ai/dsh-agent'
import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent'
import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision, RequestError, RequestErrorDecision } from '@deepseek-ai/dsh-agent'
import { canonicalHeader } from '@deepseek-ai/dsh-session'
import type { Session, TurnEndReason, TurnTrigger } from '@deepseek-ai/dsh-session'
import { createTransmissionLog, recordRequestHeader } from './request-log.ts'
@@ -19,28 +19,32 @@ import { renderPrompt } from '@deepseek-ai/dsh-system-prompt'
import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt'
import type {} from '@deepseek-ai/dsh-tools'
import { executeToolCalls } from './tool-calls.ts'
import type { ReactLoopAgent } from './agent.ts'
import type { Inbox } from './inbox.ts'
import type { TurnCancellation } from './cancellation.ts'
/** An Error with an optional machine-readable code (e.g., from LlmError or a throwing plugin). */
type CodedError = Error & { code?: string }
/** Normalize thrown values while preserving an existing error code. */
function toError(error: unknown): CodedError {
function toError(error: unknown): RequestError {
return error instanceof Error ? error : new HarnessError(String(error), 'UNKNOWN', { cause: error })
}
/** Distinguishes final model-request failures from failures in later step processing. */
class TerminalModelRequestFailure extends Error {
constructor(readonly requestError: RequestError) {
super(requestError.message, { cause: requestError })
this.name = 'TerminalModelRequestFailure'
}
}
/** Convert terminal failure finishes into step errors; unknown extensible finishes remain successful. */
function finishError(finish: FinishReason): CodedError | undefined {
function finishError(finish: FinishReason): RequestError | undefined {
switch (finish.kind) {
case 'error': {
const error: CodedError = new Error(finish.message)
const error: RequestError = new Error(finish.message)
if (finish.code !== undefined) error.code = finish.code
return error
}
case 'aborted': {
const error: CodedError = new Error('model stream aborted')
const error: RequestError = new Error('model stream aborted')
error.code = 'ABORTED'
return error
}
@@ -53,9 +57,12 @@ function finishError(finish: FinishReason): CodedError | undefined {
/**
* Build the `{ message, code? }` part of an error payload, omitting the
* `code` key entirely when absent (exactOptionalPropertyTypes-correct).
* The durable message renders the full cause chain: `turn/end` is the single
* durable record of an in-turn failure, so a wrapper message alone (e.g.
* `fetch failed`) would lose the diagnosis the session log exists to keep.
*/
function errorData(err: CodedError): { message: string; code?: string } {
return { message: err.message, ...typeof err.code === 'string' ? { code: err.code } : {} }
function errorData(err: RequestError): { message: string; code?: string } {
return { message: errorChain(err), ...typeof err.code === 'string' ? { code: err.code } : {} }
}
/** Map a successful max-token finish onto the turn reason; other successful finishes add nothing. */
@@ -88,10 +95,10 @@ function interruptionTurnEndReason(handle: LoopHandle, signal: AbortSignal): Tur
case 'user':
case 'parent':
return { kind: 'aborted' }
/* v8 ignore next 2 -- the private holder requests disposed only after lifecycle state flips, which returns above */
/* v8 ignore next 2 -- the private holder requests disposed only after lifecycle state flips, which returns above. */
case 'disposed':
return { kind: 'disposed' }
/* v8 ignore next 2 -- AgentInterruptReason is closed and the public helper filters unsupported reasons */
/* v8 ignore next 2 -- AgentInterruptReason is closed and the public helper filters unsupported reasons. */
default:
return assertNever(reason, 'AgentInterruptReason')
}
@@ -115,20 +122,25 @@ export interface LoopHandle {
isPreRunCancelled(): boolean
/** Clear the cause-less pre-run marker without affecting replacement work. */
clearPreRunCancel(): void
/** Settle idle waiters when pre-running cancellation skips a turn, without emitting `agent/status`. */
/** Settle idle waiters before pre-running cancellation publishes idle. */
settleIdle(): void
/** Run an active tool-call batch, accepting post-tool context into the FIFO drained before settlement. */
readonly withToolBatch: <T>(run: (acceptContext: (context: HookContext) => void) => Promise<T>) => Promise<T>
}
/**
* Drive queued batches as durable turns until disposal. Plugin failures end the
* current turn without terminating the driver.
* @param ctx - the plugin context the loop reaches events (agent/…, session/flush) and services (systemPrompt, llm, tools) through.
* @param agent - the agent this invocation drives for its whole lifetime (its inbox, session, and options).
* Drive queued messages as independent durable turns until disposal. Plugin
* failures end the current turn without terminating the driver. The caller
* establishes the `ctx.agents.withInitiator()` boundary before entry; package-private
* orchestration recovers that exact Agent and captures its Session locally.
* @param ctx - the plugin context the loop reaches its initiating Agent,
* events (agent/…, session/flush), and services (systemPrompt, llm, tools)
* through.
* @param handle - the bridge to status, turn cancellation ownership, disposal, and pre-run cancellation state.
* @throws when no initiating Agent is active.
*/
export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopHandle): Promise<void> {
export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
const agent = ctx.agents.requireInitiator()
// Per-instance prefix and request-header state; conversation history remains in the session log.
const transmission = createTransmissionLog()
@@ -137,29 +149,42 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH
const events = agentEvents(ctx, agent)
while (!handle.isDisposed()) {
await handle.inbox.waitForQueued(handle.disposed)
if (handle.isDisposed()) break
// Cancellation between wake and `running` skips only the cancelled work;
// a replacement prompt still runs and owns the eventual idle transition.
// An idle listener can enqueue and cancel replacement work before the next
// wait is installed. Consume that empty marker before parking the driver.
if (handle.isPreRunCancelled()) {
handle.clearPreRunCancel()
if (!handle.inbox.hasQueued) {
handle.settleIdle()
handle.setStatus('idle')
continue
}
}
await handle.inbox.waitForQueued(handle.disposed)
if (handle.isDisposed()) break
// Cancellation between wake and `running` skips only the cancelled work;
// a replacement prompt still runs before the eventual idle transition.
if (handle.isPreRunCancelled()) {
handle.clearPreRunCancel()
if (!handle.inbox.hasQueued) {
// Settle before publishing idle: the already-idle path has no status
// transition, while an idle listener can register waiters for new work.
handle.settleIdle()
handle.setStatus('idle')
continue
}
}
let cancellation = handle.installTurnCancellation()
handle.setStatus('running')
if (handle.isDisposed()) {
handle.clearTurnCancellation(cancellation)
break
}
// A synchronous running listener may cancel old work and enqueue a
// replacement. The replacement receives a fresh, non-aborted turn owner.
// A synchronous `running` listener can cancel before `runTurn`; balance the
// status only when no replacement prompt was queued by that listener.
if (cancellation.signal.aborted) {
handle.clearTurnCancellation(cancellation)
if (!handle.inbox.hasQueued) {
@@ -173,11 +198,11 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH
const turn = lastTurnNumber(session) + 1
let terminalStopped = false
try {
terminalStopped = await runTurn(ctx, events, agent, handle, turn, transmission, cancellation.signal)
terminalStopped = await runTurn(ctx, events, handle, turn, transmission, cancellation.signal)
} catch (error: unknown) {
// Pre-turn failure has no durable boundary to close; report it without appending outside a turn.
const err = toError(error)
ctx.logger.warn(`agent "${agent.id}": turn ${turn} failed before it started: ${err.message}`)
ctx.logger.warn(`agent "${agent.id}": turn ${turn} failed before it started: ${errorChain(err)}`)
try {
events.emit('agent/error', turn, 0, err)
} catch { /* contained: a throwing agent/error listener must not kill the driver */ }
@@ -195,20 +220,28 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH
}
async function runTurn(
ctx: Context, events: AgentEventDispatch, agent: ReactLoopAgent, handle: LoopHandle, turn: number, transmission: TransmissionLog,
ctx: Context, events: AgentEventDispatch, handle: LoopHandle, turn: number, transmission: TransmissionLog,
signal: AbortSignal,
): Promise<boolean> {
const agent = ctx.agents.requireInitiator()
const { session } = agent
const drainSteering = (): boolean => {
const messages = handle.inbox.drainSteering()
for (const message of messages) {
session.append('steering/message', { turn, content: message.content, source: message.source }, { surfaceOp: 'append' })
}
return messages.length > 0
}
// Drain before opening the turn, but append only after `turn/start`.
const queued = handle.inbox.drainQueued()
const first = queued[0]
// Claim one queued message before opening its turn, but append it only after `turn/start`.
const message = handle.inbox.dequeueQueued()
/* v8 ignore next 3 -- invariant guard: runLoop only calls runTurn when hasQueued */
if (!first) throw new Error('runTurn invariant violated: no queued message at turn start')
const trigger: TurnTrigger = { kind: 'message', source: first.source }
if (!message) throw new Error('runTurn invariant violated: no queued message at turn start')
const trigger: TurnTrigger = { kind: 'message', source: message.source }
let reason: TurnEndReason = { kind: 'completed' }
let step = 0
let requestRetryAttempt = 0
let stepOpen = false
let errorReported = false
let terminalStopped = false
@@ -221,7 +254,7 @@ async function runTurn(
}
// Record the durable turn failure once and contain the live error notification.
const failTurn = (err: CodedError): void => {
const failTurn = (err: RequestError): void => {
if (errorReported) return
errorReported = true
reason = { kind: 'error', step, ...errorData(err) }
@@ -244,71 +277,51 @@ async function runTurn(
// veto leaves no turn/start in the log and therefore owes no turn/end.
session.append('turn/start', { turn, trigger })
interruptionCheckpoint(signal)
// Each drained queued message runs the `agent/prompt-submit` waterfall before
// it becomes a `user/message` — a hook can rewrite the prompt or block it.
// The claimed message runs the `agent/prompt-submit` waterfall before it
// becomes a `user/message` — a hook can rewrite the prompt or block it.
// Recorded INSIDE the turn (after turn/start) so every event is turn-enclosed;
// turn/end is now owed, so a throwing prompt-submit listener (the waterfall
// throws) is caught below and the turn still closes.
let anyAllowed = false
// Seeded with a floor (only observable if the batch were empty, which
// runTurn never allows — it is called with ≥1 queued message); each `block`
// decision carries a required `reason` and overwrites it, so a fully-blocked
// batch always reports the last vetoing reason.
let lastBlockReason = 'prompt blocked by hook'
for (const message of queued) {
const decision = await events.waterfall(
'agent/prompt-submit', message.content, message.source, signal,
() => Promise.resolve<PromptDecision>({ kind: 'allow' }),
)
interruptionCheckpoint(signal)
if (decision.kind === 'block') {
lastBlockReason = decision.reason
// Record the veto durably: `PromptDecision.reason` is the durable record
// of why a prompt was blocked, but a fully-blocked batch's `rejected`
// turn/end only preserves the LAST reason, and a MIXED batch (this prompt
// blocked, another allowed) does not end `rejected` at all — so without
// this append a blocked prompt would vanish from the log whenever any
// sibling prompt is allowed. `prompt/blocked` sits in the open turn in
// place of the `user/message` this prompt would have become.
session.append('prompt/blocked', { content: message.content, source: message.source, reason: decision.reason })
continue
}
anyAllowed = true
const promptDecision = await events.waterfall(
'agent/prompt-submit', message.content, message.source, signal,
() => Promise.resolve<PromptDecision>({ kind: 'allow' }),
)
interruptionCheckpoint(signal)
if (promptDecision.kind === 'block') {
session.append('prompt/blocked', { content: message.content, source: message.source, reason: promptDecision.reason })
reason = { kind: 'rejected', reason: promptDecision.reason }
} else {
// `allow.content` REPLACES the prompt bytes (a rewrite); absent keeps them.
const content = decision.content ?? message.content
const content = promptDecision.content ?? message.content
session.append('user/message', { content, source: message.source }, { surfaceOp: 'append' })
// Every `allow.additionalContexts` entry is a separate context/message the
// next request also sees. The turn is open, so inject() appends each one
// into THIS turn without flattening provenance, framing, or metadata.
for (const context of decision.additionalContexts ?? []) {
// into THIS turn without flattening provenance or metadata.
for (const context of promptDecision.additionalContexts ?? []) {
agent.inject(context.content, {
source: context.source,
...context.envelope !== undefined ? { envelope: context.envelope } : {},
...context.meta !== undefined ? { meta: context.meta } : {},
})
}
}
while (true) {
// A fully blocked batch closes its zero-step turn as rejected.
if (!anyAllowed) {
reason = { kind: 'rejected', reason: lastBlockReason }
break
}
// A blocked prompt closes its zero-step turn as rejected.
if (promptDecision.kind === 'block') break
step += 1
// Steering from the previous round's continuation listeners joins before
// the request.
drainSteering(agent, handle.inbox, turn)
drainSteering()
// Assemble once before pre-step so pressure checks and the request share the same prompt.
// Assemble once before pre-step so listener work and the request share one prompt value.
const assembly = await ctx.systemPrompt.assemble(assembleContextFor(agent, signal))
interruptionCheckpoint(signal)
const fullSystemPrompt = renderPrompt(assembly)
// Compose the request-only prefix once per loop instance before pressure
// checks. It precedes all derived history and is recorded only in the
// request header, not as session history.
// Compose the request-only prefix once per loop instance before the first
// request boundary. It precedes all derived history and is recorded only
// in the request header, not as session history.
if (transmission.sessionPrefix === undefined) {
const emptyPrefix: Message[] = deepFreeze([])
const composed = await events.waterfall(
@@ -320,8 +333,8 @@ async function runTurn(
transmission.sessionPrefix = deepFreeze(structuredClone(composed))
}
// Await surface mutations outside the step; pressure checks receive the pending prefix.
await events.serial('agent/pre-step', turn, step, fullSystemPrompt, transmission.sessionPrefix, signal)
// Await surface mutations outside the step before snapshotting history.
await events.serial('agent/pre-step', turn, step, signal)
interruptionCheckpoint(signal)
// Snapshot the exact log prefix before step/start: the reconstruction
@@ -333,15 +346,67 @@ async function runTurn(
// pre-commit veto throws before this assignment; post-commit observers
// are contained inside Session.append().
stepOpen = true
// A synchronous step/start observer can cancel after the step opened.
interruptionCheckpoint(signal)
let stepOutcome: { hadToolCalls: boolean; finish: FinishReason } | { error: Error }
let stepOutcome:
| { hadToolCalls: boolean; finish: FinishReason }
| { requestError: RequestError }
| { error: RequestError }
try {
stepOutcome = await runStep(
ctx, events, agent, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, signal)
ctx, events, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, signal)
} catch (error: unknown) {
stepOutcome = { error: toError(error) }
if (error instanceof TerminalModelRequestFailure) {
stepOutcome = { requestError: error.requestError }
} else {
stepOutcome = { error: toError(error) }
}
}
if ('requestError' in stepOutcome) {
// Recovery observes a balanced failed step and the original provider
// error while the failed step's signal remains the active owner.
closeStep()
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted !== undefined) {
reason = interrupted
break
}
const defaultDecision: RequestErrorDecision = { action: 'fail' }
let recoveryDecision: RequestErrorDecision = defaultDecision
try {
recoveryDecision = await events.waterfall(
'agent/request-error', turn, step, stepOutcome.requestError,
requestRetryAttempt, signal,
() => Promise.resolve(defaultDecision),
)
} catch (recoveryError: unknown) {
ctx.logger.warn(
`agent "${agent.id}": request recovery failed at turn ${turn}, step ${step}: ${errorChain(recoveryError)}`,
)
}
// Cancellation and disposal always win over either a recovery decision
// or a recovery-listener failure.
const recoveryInterrupted = interruptionTurnEndReason(handle, signal)
if (recoveryInterrupted !== undefined) {
reason = recoveryInterrupted
break
}
switch (recoveryDecision.action) {
case 'retry':
requestRetryAttempt += 1
continue
case 'fail':
failTurn(stepOutcome.requestError)
break
/* v8 ignore next -- closed-union exhaustiveness guard */
default:
assertNever(recoveryDecision, 'agent request-error decision')
}
break
}
if ('error' in stepOutcome) {
@@ -350,21 +415,43 @@ async function runTurn(
// starts a fresh turn instead of being silently consumed.
closeStep()
const { error } = stepOutcome
const interruption = interruptionTurnEndReason(handle, signal)
if (interruption === undefined) failTurn(error)
else reason = interruption
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(error)
else reason = interrupted
break
}
requestRetryAttempt = 0
// Preserve max-token completion unless a later disposal, abort, or error wins.
const stepReason = stepFinishReason(stepOutcome.finish)
if (stepReason) reason = stepReason
// Steering that arrived during streaming/tool execution.
const steered = drainSteering(agent, handle.inbox, turn)
const steered = drainSteering()
try {
await events.serial('agent/post-step', turn, step, signal)
} catch (error: unknown) {
stepOutcome = { error: toError(error) }
}
if ('error' in stepOutcome) {
closeStep()
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(stepOutcome.error)
else reason = interrupted
break
}
const postStepInterrupted = interruptionTurnEndReason(handle, signal)
if (postStepInterrupted !== undefined) {
reason = postStepInterrupted
closeStep()
break
}
closeStep()
interruptionCheckpoint(signal)
const defaultDecision: ContinuationDecision = { action: stepOutcome.hadToolCalls || steered ? 'continue' : 'stop' }
let decision: ContinuationDecision
@@ -375,9 +462,9 @@ async function runTurn(
)
interruptionCheckpoint(signal)
} catch (error: unknown) {
const interruption = interruptionTurnEndReason(handle, signal)
if (interruption === undefined) failTurn(toError(error))
else reason = interruption
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(toError(error))
else reason = interrupted
break
}
@@ -397,9 +484,11 @@ async function runTurn(
interruptionCheckpoint(signal)
terminalStop = stop !== undefined
} catch (error: unknown) {
const interruption = interruptionTurnEndReason(handle, signal)
if (interruption === undefined) failTurn(toError(error))
else reason = interruption
// A broken terminal policy is an ordinary continuation failure: fail
// this turn closed while leaving the driver alive for later turns.
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(toError(error))
else reason = interrupted
break
}
if (terminalStop) {
@@ -409,11 +498,7 @@ async function runTurn(
shouldContinue = false
}
if (!shouldContinue || handle.isDisposed()) {
/* v8 ignore next -- disposal during continuation-decision window is a narrow race; error-path disposal is covered elsewhere */
if (handle.isDisposed()) reason = { kind: 'disposed' }
break
}
if (!shouldContinue) break
}
// Normal / inline-error loop exit: close the turn.
@@ -423,9 +508,9 @@ async function runTurn(
const turnStartLogged = session.events.some(e => e.type === 'turn/start' && e.data.turn === turn)
if (!turnStartLogged) throw error
closeStep()
const interruption = interruptionTurnEndReason(handle, signal)
if (interruption === undefined) failTurn(toError(error))
else reason = interruption
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(toError(error))
else reason = interrupted
closeTurn()
}
@@ -435,7 +520,7 @@ async function runTurn(
} catch (error: unknown) {
// The turn is closed, so report the failed flush live rather than append outside a turn.
const err = toError(error)
ctx.logger.warn(`agent "${agent.id}": session/flush failed at turn ${turn}: ${err.message}`)
ctx.logger.warn(`agent "${agent.id}": session/flush failed at turn ${turn}: ${errorChain(err)}`)
try {
events.emit('agent/error', turn, step, err)
} catch {
@@ -445,15 +530,6 @@ async function runTurn(
return terminalStopped
}
/** Drain the steering queue into the session. Returns whether any arrived. */
function drainSteering(agent: ReactLoopAgent, inbox: Inbox, turn: number): boolean {
const messages = inbox.drainSteering()
for (const message of messages) {
agent.session.append('steering/message', { turn, content: message.content, source: message.source }, { surfaceOp: 'append' })
}
return messages.length > 0
}
/**
* Run one committed step: transform call config, log the request header, build
* the request from the cached prefix plus the step-boundary snapshot, stream and
@@ -463,7 +539,6 @@ function drainSteering(agent: ReactLoopAgent, inbox: Inbox, turn: number): boole
async function runStep(
ctx: Context,
events: AgentEventDispatch,
agent: ReactLoopAgent,
handle: LoopHandle,
turn: number,
step: number,
@@ -473,6 +548,7 @@ async function runStep(
transmission: TransmissionLog,
signal: AbortSignal,
): Promise<{ hadToolCalls: boolean; finish: FinishReason }> {
const agent = ctx.agents.requireInitiator()
const { session, options } = agent
// Seed the first request from agent options and later requests from the logged header;
@@ -483,7 +559,9 @@ async function runStep(
: { provider: options.provider ?? '', model: options.model ?? '' }))
// Listener replacements are recorded in the request header before dispatch.
const config = await events.waterfall('agent/request', turn, step, seedConfig, signal, () => Promise.resolve(seedConfig))
const config = await events.waterfall(
'agent/request', turn, step, seedConfig, signal, () => Promise.resolve(seedConfig),
)
interruptionCheckpoint(signal)
if (!config.provider || !config.model) {
throw new Error(`agent "${agent.id}" has no provider/model: set AgentOptions.provider and AgentOptions.model or supply both via the agent/request waterfall`)
@@ -518,27 +596,67 @@ async function runStep(
// --- Model call (streaming-first; raw chunks are the replay record) ---
const assembler = new BlockAssembler()
const chunkSeqs: number[] = []
for await (const chunk of ctx.llm.stream(request)) {
interruptionCheckpoint(signal)
const chunkEvent = session.append('assistant/chunk', { turn, step, chunk })
chunkSeqs.push(chunkEvent.seq)
assembler.push(chunk)
const stream = ctx.llm.stream(request)
try {
for await (const chunk of stream) {
interruptionCheckpoint(signal)
const chunkEvent = session.append('assistant/chunk', { turn, step, chunk })
chunkSeqs.push(chunkEvent.seq)
assembler.push(chunk)
}
} catch (error: unknown) {
if (isLlmAdapterFailure(stream, error)) throw new TerminalModelRequestFailure(error)
throw error
}
interruptionCheckpoint(signal)
// Normalize failure finish chunks into the same path as thrown stream errors.
const stepError = finishError(assembler.finish)
if (stepError) throw stepError
if (stepError) throw new TerminalModelRequestFailure(stepError)
const recordAssistantMessage = (
assembledContent: ContentBlock[],
message: Message,
preserveReplayState = true,
): void => {
session.append(
'assistant/message',
{
turn,
step,
content: message.content,
provenance: assistantProvenance(
header.config,
assembler.replayState,
preserveReplayState && isDeepStrictEqual(message.content, assembledContent),
),
...assembler.usage === undefined ? {} : { usage: assembler.usage },
},
{ surfaceOp: 'append', sourceEventSeqs: chunkSeqs },
)
}
// A rejected result still records the successful provider call without retaining rejected output.
const processStepResult = async (assembledContent: ContentBlock[], message: Message): Promise<Message> => {
try {
const processed = await events.waterfall(
'agent/step-result', turn, step, message, signal, () => Promise.resolve(message),
)
interruptionCheckpoint(signal)
return processed
} catch (error: unknown) {
recordAssistantMessage(assembledContent, { ...message, content: [] }, false)
throw error
}
}
if (assembler.finish.kind === 'max-tokens') {
const assembled = assembler.message()
const assembledContent = structuredClone(assembled.content)
let message: Message = withoutToolCalls(assembled)
message = withoutToolCalls(await processStepResult(
events, session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs, signal,
))
message = withoutToolCalls(await processStepResult(assembledContent, message))
// Preserve usage even when max-token truncation produced no content.
recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs)
recordAssistantMessage(assembledContent, message)
return { hadToolCalls: false, finish: assembler.finish }
}
@@ -546,89 +664,23 @@ async function runStep(
const assembled = assembler.message()
const assembledContent = structuredClone(assembled.content)
let message: Message = assembled
message = await processStepResult(
events, session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs, signal,
)
message = await processStepResult(assembledContent, message)
// Every successful call records its completion anchor, including explicit
// empty chunk provenance for a contentless, usage-less provider response.
recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs)
recordAssistantMessage(assembledContent, message)
// Dispatch may overlap; policy, durable results, and result context stay model-ordered.
const toolCalls = message.content.filter(block => block.type === 'tool-call')
if (toolCalls.length === 0) return { hadToolCalls: false, finish: assembler.finish }
return handle.withToolBatch(async (acceptContext) => {
await executeToolCalls(
ctx, agent, turn, step, toolCalls, signal, handle.maxParallelToolCalls, acceptContext,
ctx, turn, step, toolCalls, signal, handle.maxParallelToolCalls, acceptContext,
)
return { hadToolCalls: true, finish: assembler.finish }
})
}
/** Preserve successful-call accounting without retaining output that result processing rejected. */
async function processStepResult(
events: AgentEventDispatch,
session: Session,
turn: number,
step: number,
config: LlmCallConfig,
assembledContent: ContentBlock[],
message: Message,
assembler: BlockAssembler,
chunkSeqs: number[],
signal: AbortSignal,
): Promise<Message> {
try {
const processed = await events.waterfall(
'agent/step-result', turn, step, message, signal, () => Promise.resolve(message),
)
interruptionCheckpoint(signal)
return processed
} catch (error: unknown) {
recordAssistantMessage(
session,
turn,
step,
config,
assembledContent,
{ ...message, content: [] },
assembler,
chunkSeqs,
false,
)
throw error
}
}
/** Record one content-or-usage assistant message with replay-safe provenance. */
function recordAssistantMessage(
session: Session,
turn: number,
step: number,
config: LlmCallConfig,
assembledContent: ContentBlock[],
message: Message,
assembler: BlockAssembler,
chunkSeqs: number[],
preserveReplayState = true,
): void {
session.append(
'assistant/message',
{
turn,
step,
content: message.content,
provenance: assistantProvenance(
config,
assembler.replayState,
preserveReplayState && isDeepStrictEqual(message.content, assembledContent),
),
...assembler.usage === undefined ? {} : { usage: assembler.usage },
},
{ surfaceOp: 'append', sourceEventSeqs: chunkSeqs },
)
}
/** Build durable assistant provenance, dropping replay state after any content rewrite. */
function assistantProvenance(config: LlmCallConfig, replayState: unknown, contentUnchanged: boolean): NonNullable<Message['provenance']> {
return {

63
packages/core/agent-loop/src/tool-calls.ts
View File

@@ -4,8 +4,8 @@
* Dispatch may overlap, while policy, results, and result context remain
* model-ordered. Abort stops replenishment and drains started calls.
*
* Each started call records `tool/call`; `tool/result` commits in model order,
* preserving derived history when audit events interleave with earlier results.
* Each advertised call records a balanced `tool/call`/`tool/result` pair. Calls
* skipped after abort receive synthetic error results so replay stays valid.
* @module dsh-agent-loop/tool-calls
*/
@@ -14,7 +14,6 @@ import { assertNever, type ToolCallBlock } from '@deepseek-ai/dsh-llm'
import type { HookContext } from '@deepseek-ai/dsh-agent'
import type { Session } from '@deepseek-ai/dsh-session'
import { TOOL_REGISTRY_SCHEDULER, type ToolExecutionInput, type ToolExecutionMode, type ToolExecutionResult, type ToolRunContext } from '@deepseek-ai/dsh-tools'
import type { ReactLoopAgent } from './agent.ts'
/** One tool call after argument parsing, ready to schedule. */
interface PlannedCall {
@@ -29,21 +28,21 @@ interface Slot {
needsPost: boolean
}
/** Control-flow sentinel; turn classification reads only the explicit signal. */
const TOOL_CALLS_INTERRUPTED = new Error('tool calls interrupted')
/** Stop scheduling at a cooperative boundary without exposing the runtime reason. */
function interruptionCheckpoint(signal: AbortSignal): void {
if (signal.aborted) throw TOOL_CALLS_INTERRUPTED
/** One scheduler group outcome, including a drained cancellation. */
interface GroupOutcome {
consumed: number
aborted: boolean
}
/**
* Schedule one assistant step's tool calls by their live concurrency mode.
* Started calls receive ordered results. Abort drains them and rethrows after
* accepting their context into the batch FIFO owned by the caller.
* Started calls receive ordered results. Abort drains them, records synthetic
* results for unstarted calls, and returns with the signal still aborted after
* accepting started-call context into the batch FIFO owned by the caller.
* The committed step's AgentLoop driver boundary supplies the initiating Agent
* that becomes each explicit {@link ToolExecutionInput.agent}.
*
* @param ctx - loop context that owns the tool registry.
* @param agent - agent and session receiving the call lifecycle.
* @param ctx - loop context that owns the tool registry and carries the initiating Agent.
* @param turn - current turn number.
* @param step - current step number.
* @param toolCalls - assistant calls in model order.
@@ -53,7 +52,6 @@ function interruptionCheckpoint(signal: AbortSignal): void {
*/
export async function executeToolCalls(
ctx: Context,
agent: ReactLoopAgent,
turn: number,
step: number,
toolCalls: ToolCallBlock[],
@@ -61,6 +59,7 @@ export async function executeToolCalls(
maxParallel: number,
acceptContext: (context: HookContext) => void,
): Promise<void> {
const agent = ctx.agents.requireInitiator()
const { session } = agent
// Inputs are distinct because tools/execute wrappers may replace `exec.signal`.
@@ -82,7 +81,14 @@ export async function executeToolCalls(
const first = planned[next]!
const mode = ctx.tools.executionMode(first.exec).kind
const group = mode === 'parallel' ? planned.slice(next) : [first]
next += await runGroup(ctx, session, turn, step, group, mode, signal, maxParallel, acceptContext)
const outcome = await runGroup(
ctx, turn, step, group, mode, signal, maxParallel, acceptContext,
)
next += outcome.consumed
if (outcome.aborted) {
for (const call of planned.slice(next)) appendSkippedToolCall(session, turn, step, call.block)
return
}
}
}
@@ -100,11 +106,11 @@ function parseArguments(raw: string): unknown {
* before start; an exclusive reclassification waits for the current pool to
* drain and remains for the caller's next barrier. Results and contexts commit
* in model order. Abort stops starts, drains and commits started calls, accepts
* their contexts into the owning batch, and throws.
* their contexts into the owning batch, records results for skipped calls, and
* returns an aborted outcome.
*/
async function runGroup(
ctx: Context,
session: Session,
turn: number,
step: number,
group: PlannedCall[],
@@ -112,8 +118,8 @@ async function runGroup(
signal: AbortSignal,
maxParallel: number,
acceptContext: (context: HookContext) => void,
): Promise<number> {
interruptionCheckpoint(signal)
): Promise<GroupOutcome> {
const { session } = ctx.agents.requireInitiator()
const slots: (Slot | undefined)[] = group.map(() => undefined)
// Started slots retain their tool/call seq for result provenance.
const callSeqs: number[] = group.map(() => -1)
@@ -191,17 +197,30 @@ async function runGroup(
inFlight.delete(settledIndex)
await commitReady()
// Abort may arrive while a tool or ordered commit awaits.
if (signal.aborted) aborted = true
await fillPool()
}
if (aborted) {
// Started calls and accepted context settle before the turn records the abort.
throw TOOL_CALLS_INTERRUPTED
// Started calls and accepted context settle first; every remaining model
// call then receives an ordered synthetic result before the turn aborts.
for (const call of group.slice(started)) appendSkippedToolCall(session, turn, step, call.block)
return { consumed: group.length, aborted: true }
}
/* v8 ignore next -- unreachable: a non-aborted group commits every started call */
if (committed !== started) throw new Error('tool-call scheduler: uncommitted settled calls')
return started
return { consumed: started, aborted: false }
}
/** Append the durable call/result pair for a model call skipped after cancellation. */
function appendSkippedToolCall(session: Session, turn: number, step: number, block: ToolCallBlock): void {
const callSeq = appendToolCall(session, turn, step, block)
appendToolResult(session, turn, step, block, {
content: [{ type: 'text', text: 'Error: tool call skipped because the step was aborted before execution' }],
isError: true,
error: { name: 'AbortError', code: 'ABORTED' },
}, callSeq)
}
/** Append a started call and return its provenance sequence. */

135
packages/core/agent-loop/tests/agent-execution.spec.ts → packages/core/agent-loop/tests/agent-initiator.spec.ts
View File

@@ -1,9 +1,7 @@
import { describe, expect, it } from 'vitest'
import { Context, FiberState, type Fiber } from 'cordis'
import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import type { AgentExecutionService } from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { Context, type Fiber } from 'cordis'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
@@ -13,7 +11,7 @@ import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
interface Harness {
ctx: Context
providerFiber: Fiber
agentsFiber: Fiber
loopFiber: Fiber
}
@@ -23,14 +21,13 @@ async function harness(adapter: LlmAdapter): Promise<Harness> {
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
const providerFiber = await ctx.plugin(AgentExecutionProvider)
const agentsFiber = await ctx.plugin(AgentRegistry)
const loopFiber = await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return { ctx, providerFiber, loopFiber }
return { ctx, agentsFiber, loopFiber }
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent | Agent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -56,12 +53,12 @@ class OverlapAdapter extends LlmAdapter {
}
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
const before = this.ctx.agentExecution.require().agent
const before = this.ctx.agents.requireInitiator()
this.starts += 1
if (this.starts === 2) this.bothStarted.resolve(true)
await this.bothStarted.promise
await Promise.resolve()
const after = this.ctx.agentExecution.require().agent
const after = this.ctx.agents.requireInitiator()
this.observations.push({ sessionId: options.sessionId, before, after })
yield* textResponse('done')
}
@@ -71,12 +68,12 @@ class OverlapAdapter extends LlmAdapter {
class TestCapabilityTransport {
readonly requests: { path: string; headers: Record<string, string> }[] = []
constructor(private readonly execution: AgentExecutionService) {}
constructor(private readonly agents: AgentRegistry) {}
async request(path: string): Promise<Record<string, string>> {
await Promise.resolve()
const headers = {
'X-Harness-Session-Id': this.execution.require().agent.session.id,
'X-Harness-Session-Id': this.agents.requireInitiator().session.id,
}
this.requests.push({ path, headers })
return headers
@@ -89,11 +86,11 @@ class ReloadAdapter extends LlmAdapter {
firstAgentDuringAbort: Agent | undefined
laterAgent: Agent | undefined
calls = 0
execution: AgentExecutionService | undefined
agents: AgentRegistry | undefined
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
const execution = this.execution
if (execution === undefined) throw new Error('execution service missing')
const agents = this.agents
if (agents === undefined) throw new Error('agent service missing')
this.calls += 1
if (this.calls === 1) {
this.firstStarted.resolve(true)
@@ -105,18 +102,18 @@ class ReloadAdapter extends LlmAdapter {
})
} catch (error: unknown) {
await Promise.resolve()
this.firstAgentDuringAbort = execution.require().agent
this.firstAgentDuringAbort = agents.requireInitiator()
throw error
}
return
}
await Promise.resolve()
this.laterAgent = execution.require().agent
this.laterAgent = agents.requireInitiator()
yield* textResponse('reloaded')
}
}
describe('AgentLoop execution context', () => {
describe('AgentLoop initiator scope', () => {
it('keeps overlapping driver continuations bound to their exact Agents', async () => {
const ctx = new Context()
const adapter = new OverlapAdapter(ctx)
@@ -125,12 +122,11 @@ describe('AgentLoop execution context', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
const a = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' })
const b = ctx.agentLoop.create(AgentId('b'), { provider: 'mock', model: 'mock' })
const a = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
const b = ctx.agentLoop.create(SessionId('b'), { provider: 'mock', model: 'mock' })
const idleA = waitForIdle(ctx, a)
const idleB = waitForIdle(ctx, b)
send(a, 'a')
@@ -142,24 +138,22 @@ describe('AgentLoop execution context', () => {
{ sessionId: a.session.id, before: a, after: a },
{ sessionId: b.session.id, before: b, after: b },
]))
expect(ctx.agentExecution.current()).toBeUndefined()
expect(ctx.agents.currentInitiator()).toBeUndefined()
await ctx.fiber.dispose()
})
it('keeps ALS identity minimal while one explicit signal spans each turn seam', async () => {
it('keeps initiator identity minimal while one explicit signal spans each turn seam', async () => {
const adapter = new MockAdapter([
toolCallResponse('observe-call', 'observe', {}),
textResponse('first done'),
textResponse('second done'),
])
const { ctx } = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('signal-owner'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('signal-owner'), { provider: 'mock', model: 'mock' })
let signals: AbortSignal[] = []
const capture = (signal: AbortSignal | undefined): void => {
if (signal === undefined) throw new Error('turn seam omitted its explicit signal')
const execution = ctx.agentExecution.require()
expect(Object.keys(execution)).toEqual(['agent'])
expect(execution.agent).toBe(agent)
expect(ctx.agents.requireInitiator()).toBe(agent)
signals.push(signal)
}
@@ -175,7 +169,7 @@ describe('AgentLoop execution context', () => {
if (subject === agent) capture(signal)
return next()
})
ctx.on('agent/pre-step', (subject, _turn, _step, _system, _prefix, signal) => {
ctx.on('agent/pre-step', (subject, _turn, _step, signal) => {
if (subject === agent) capture(signal)
})
ctx.on('agent/request', async (subject, _turn, _step, _config, signal, next) => {
@@ -218,11 +212,11 @@ describe('AgentLoop execution context', () => {
expect(secondSignal).toBeDefined()
expect(new Set([...signals, adapter.requests[2]!.signal!])).toEqual(new Set([secondSignal]))
expect(secondSignal).not.toBe(firstSignal)
expect(ctx.agentExecution.current()).toBeUndefined()
expect(ctx.agents.currentInitiator()).toBeUndefined()
await ctx.fiber.dispose()
})
it('keeps child setup under the parent boundary, switches for the child driver, then restores the parent', async () => {
it('keeps child setup under the parent boundary and restores the parent while the child driver remains active', async () => {
const adapter = new MockAdapter([
toolCallResponse('spawn', 'spawn-child', {}),
toolCallResponse('observe', 'observe-child', {}),
@@ -233,7 +227,7 @@ describe('AgentLoop execution context', () => {
let parentDuringSetup: Agent | undefined
let explicitChild: Agent | undefined
let childDuringDriver: Agent | undefined
let parentAfterChild: Agent | undefined
let parentWhileChildDriverActive: Agent | undefined
let child: Agent | undefined
ctx.tools.register(defineTool({
@@ -243,11 +237,10 @@ describe('AgentLoop execution context', () => {
execute: async (_args, exec) => {
if (exec.agent === undefined) throw new Error('parent agent missing')
const handle = await exec.agent.ctx.agents.create({
agentId: AgentId('child'),
sessionId: SessionId('child-session'),
agentOptions: { provider: 'mock', model: 'mock' },
setup: (agentCtx) => {
parentDuringSetup = ctx.agentExecution.require().agent
parentDuringSetup = ctx.agents.requireInitiator()
explicitChild = agentCtx.agent
agentCtx.tools.register(defineTool({
name: 'observe-child',
@@ -255,23 +248,22 @@ describe('AgentLoop execution context', () => {
parameters: {},
execute: async () => {
await Promise.resolve()
childDuringDriver = ctx.agentExecution.require().agent
childDuringDriver = ctx.agents.requireInitiator()
return [{ type: 'text', text: 'observed' }]
},
}))
},
})
child = handle.agent
parentWhileChildDriverActive = ctx.agents.requireInitiator()
send(handle.agent, 'run child')
await handle.agent.whenIdle()
parentAfterChild = ctx.agentExecution.require().agent
await handle.dispose()
return [{ type: 'text', text: 'child completed' }]
},
}))
const parentHandle = await ctx.agents.create({
agentId: AgentId('parent'),
sessionId: SessionId('parent-session'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -282,8 +274,8 @@ describe('AgentLoop execution context', () => {
expect(parentDuringSetup).toBe(parentHandle.agent)
expect(explicitChild).toBe(child)
expect(childDuringDriver).toBe(child)
expect(parentAfterChild).toBe(parentHandle.agent)
expect(ctx.agentExecution.current()).toBeUndefined()
expect(parentWhileChildDriverActive).toBe(parentHandle.agent)
expect(ctx.agents.currentInitiator()).toBeUndefined()
await parentHandle.dispose()
await ctx.fiber.dispose()
})
@@ -294,7 +286,7 @@ describe('AgentLoop execution context', () => {
textResponse('done'),
])
const { ctx } = await harness(adapter)
const transport = new TestCapabilityTransport(ctx.agentExecution)
const transport = new TestCapabilityTransport(ctx.agents)
let directAmbient: Agent | undefined
let captured: Agent | undefined
@@ -304,7 +296,7 @@ describe('AgentLoop execution context', () => {
parameters: {},
execute: async () => {
await Promise.resolve()
directAmbient = ctx.agentExecution.current()?.agent
directAmbient = ctx.agents.currentInitiator()
return [{ type: 'text', text: 'ok' }]
},
}))
@@ -313,7 +305,7 @@ describe('AgentLoop execution context', () => {
description: 'call the test capability transport',
parameters: { path: { type: 'string' } },
execute: async (args) => {
captured = ctx.agentExecution.require().agent
captured = ctx.agents.requireInitiator()
const path = (args as { path: string }).path
const headers = await transport.request(path)
return [{ type: 'text', text: JSON.stringify(headers) }]
@@ -329,7 +321,6 @@ describe('AgentLoop execution context', () => {
expect(directAmbient).toBeUndefined()
const handle = await ctx.agents.create({
agentId: AgentId('transport'),
sessionId: SessionId('transport-session'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -350,45 +341,16 @@ describe('AgentLoop execution context', () => {
await handle.dispose()
expect(captured?.status).toBe('disposed')
expect(ctx.agentExecution.current()).toBeUndefined()
expect(ctx.agents.currentInitiator()).toBeUndefined()
await ctx.fiber.dispose()
})
it('keeps AgentLoop inactive until the mandatory provider appears', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
const loopFiber = ctx.plugin(AgentLoop, { agents: [] })
await Promise.resolve()
expect(loopFiber.state).toBe(FiberState.PENDING)
await ctx.plugin(AgentExecutionProvider)
await loopFiber
expect(loopFiber.state).toBe(FiberState.ACTIVE)
await ctx.fiber.dispose()
})
it('drains the old driver before disabling ALS during provider restart', async () => {
const ctx = new Context()
it('drains the old driver before disabling ALS during agent-service restart', async () => {
const adapter = new ReloadAdapter()
const { providerFiber, loopFiber } = await (async (): Promise<Harness> => {
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
const mountedProvider = await ctx.plugin(AgentExecutionProvider)
const mountedLoop = await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return { ctx, providerFiber: mountedProvider, loopFiber: mountedLoop }
})()
const oldService = ctx.agentExecution
adapter.execution = oldService
const { ctx, agentsFiber, loopFiber } = await harness(adapter)
const oldService = ctx.agents
adapter.agents = oldService
const oldHandle = await ctx.agents.create({
agentId: AgentId('before-restart'),
sessionId: SessionId('before-restart-session'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -396,17 +358,16 @@ describe('AgentLoop execution context', () => {
send(oldAgent, 'block')
await adapter.firstStarted.promise
await providerFiber.restart()
await agentsFiber.restart()
await loopFiber.await()
expect(adapter.firstAgentDuringAbort?.id).toBe(oldAgent.id)
expect(adapter.firstAgentDuringAbort?.session).toBe(oldAgent.session)
expect(oldAgent.status).toBe('disposed')
expect(() => oldService.current()).toThrow('agent execution service is disposed')
expect(ctx.agentExecution).not.toBe(oldService)
adapter.execution = ctx.agentExecution
expect(() => oldService.currentInitiator()).toThrow('agent initiator scope is disposed')
expect(ctx.agents).not.toBe(oldService)
adapter.agents = ctx.agents
const newHandle = await ctx.agents.create({
agentId: AgentId('after-restart'),
sessionId: SessionId('after-restart-session'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -427,13 +388,11 @@ describe('AgentLoop execution context', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
const service = ctx.agentExecution
adapter.execution = service
const service = ctx.agents
adapter.agents = service
const handle = await ctx.agents.create({
agentId: AgentId('root-dispose'),
sessionId: SessionId('root-dispose-session'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -445,6 +404,6 @@ describe('AgentLoop execution context', () => {
expect(adapter.firstAgentDuringAbort?.id).toBe(agent.id)
expect(adapter.firstAgentDuringAbort?.session).toBe(agent.session)
expect(agent.status).toBe('disposed')
expect(() => service.current()).toThrow('agent execution service is disposed')
expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed')
})
})

129
packages/core/agent-loop/tests/agent.spec.ts
View File

@@ -1,16 +1,18 @@
import { describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from '@deepseek-ai/dsh-agent-loop'
import { bindReactLoopAgentContext, prepareReactLoopAgent, type ReactLoopAgent } from '../src/agent.ts'
import { MockAdapter, textResponse } from './mock-adapter.ts'
function driverDone(agent: Agent): Promise<void> {
return (agent as Agent & { done: Promise<void> }).done
}
async function harness(adapter: MockAdapter) {
const ctx = new Context()
await ctx.plugin(LlmService)
@@ -18,13 +20,12 @@ async function harness(adapter: MockAdapter) {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -35,7 +36,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
})
}
function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopAgent['status']): Promise<void> {
function waitForStatus(ctx: Context, agent: Agent, expected: Agent['status']): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === expected) {
@@ -46,23 +47,22 @@ function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopA
})
}
function send(agent: ReactLoopAgent, text: string) {
function send(agent: Agent, text: string) {
agent.send([{ type: 'text', text }])
}
describe('ReactLoopAgent', () => {
describe('Agent', () => {
it('rejects access before context binding and a second driver for one session', async () => {
const ctx = new Context()
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(SessionStore)
const session = ctx.sessions.create(SessionId('exclusive-driver'))
const prepared = prepareReactLoopAgent(
ctx, AgentId('first-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
ctx, SessionId('first-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
)
expect(() => prepared.agent.ctx).toThrow('context is not bound')
expect(() => prepareReactLoopAgent(
ctx, AgentId('second-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
ctx, SessionId('second-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
))
.toThrow('already has a concrete agent driver')
@@ -73,12 +73,12 @@ describe('ReactLoopAgent', () => {
it('borrows caller options and binds its scoped context exactly once', async () => {
const ctx = await harness(new MockAdapter([textResponse('unused')]))
const options = { provider: 'mock', model: 'mock' }
const agent = ctx.agentLoop.create(AgentId('owned-bindings'), options)
const agent = ctx.agentLoop.create(SessionId('owned-bindings'), options)
expect(agent.options).toBe(options)
expect(agent.id).toBe('owned-bindings')
expect(agent.session.id).toMatch(/^owned-bindings-session-/)
expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/)
expect(agent.session.id).toBe(agent.id)
expect(() => { bindReactLoopAgentContext(agent as ReactLoopAgent, new Context()) }).toThrow(/context is already bound/)
await ctx.fiber.dispose()
})
@@ -86,14 +86,14 @@ describe('ReactLoopAgent', () => {
it('send() throws after disposal', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
await fiber.dispose()
await agent.done
await driverDone(agent)
expect(() => { agent.send([{ type: 'text', text: 'too late' }]) }).toThrow('disposed')
})
@@ -101,14 +101,14 @@ describe('ReactLoopAgent', () => {
it('steer() throws after disposal', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
await fiber.dispose()
await agent.done
await driverDone(agent)
expect(() => { agent.steer([{ type: 'text', text: 'too late' }]) }).toThrow('disposed')
})
@@ -116,14 +116,14 @@ describe('ReactLoopAgent', () => {
it('inject() throws after disposal', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
await fiber.dispose()
await agent.done
await driverDone(agent)
expect(() => { agent.inject([{ type: 'text', text: 'too late' }]) }).toThrow('disposed')
})
@@ -131,7 +131,7 @@ describe('ReactLoopAgent', () => {
it('inject() decides enclosure from the LOG (open turn), not agent status', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// Simulate an OPEN turn in the log while the agent is idle (status is not a
// reliable open-turn signal). inject must append into that open turn, NOT
@@ -157,7 +157,7 @@ describe('ReactLoopAgent', () => {
// A persistence-like listener whose flush rejects.
ctx.on('session/flush', () => { throw new Error('disk gone') })
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// inject() is synchronous and fires a fire-and-forget flush; a rejecting
// flush must be contained (logged), never thrown into the caller.
@@ -170,12 +170,14 @@ describe('ReactLoopAgent', () => {
it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let flushes = 0
ctx.on('session/flush', () => { flushes += 1 })
// Invalid injected content throws after turn/start. `finally` must still append turn/end and
// flush the balanced in-memory turn so a crash cannot lose it before the next checkpoint.
// Non-serializable injected content makes Session.append throw AFTER
// turn/start was recorded. The turn/end must still be appended (finally),
// AND the durability checkpoint must still fire — the balanced turn is in
// memory and a crash before the next turn/dispose would otherwise lose it.
expect(() => {
agent.inject([{ type: 'text', text: 'x', bad: 1n } as never], { source: { kind: 'plugin', plugin: 'p' } })
}).toThrow(/non-JSON-serializable/)
@@ -188,7 +190,7 @@ describe('ReactLoopAgent', () => {
it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let flushes = 0
ctx.on('session/flush', () => { flushes += 1 })
// Session contains a throwing post-commit turn/end observer. The accepted
@@ -211,7 +213,7 @@ describe('ReactLoopAgent', () => {
// A non-Error rejection exercises the String() normalization branch.
ctx.on('session/flush', () => { throw 'disk gone' })
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const errors: { turn: number; step: number; message: string }[] = []
ctx.on('agent/error', (_a, turn, step, error) => void errors.push({ turn, step, message: error.message }))
@@ -230,7 +232,7 @@ describe('ReactLoopAgent', () => {
it('idle inject() with a non-serializable source opens no turn (nothing to close)', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// A non-serializable source makes the turn/start append throw BEFORE the
// event is pushed (Session.append validates before push), so NO turn opens.
@@ -245,7 +247,7 @@ describe('ReactLoopAgent', () => {
it('steer() when idle falls through to send() and starts a turn', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// steer while idle delegates to send
agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } })
@@ -257,23 +259,29 @@ describe('ReactLoopAgent', () => {
})
it('disposer is idempotent (double-stop)', async () => {
// The internal start seam exposes one idle driver's disposer for repeated invocation.
// Create a bare Agent and start it through the package-internal
// test seam. Then call its disposer twice — the second call hits the
// early-return branch.
const ctx = new Context()
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(SessionStore)
await ctx.plugin(AgentRegistry)
const session = ctx.sessions.create(SessionId('test'))
const prepared = prepareReactLoopAgent(
ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
ctx, SessionId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
)
const { agent } = prepared
// Start the loop to get the disposer; the agent waits for messages
// (idle, never-resolving cancel), so it will stay idle.
prepared.markPublished()
const dispose = prepared.startDriver()
// First dispose
const firstDisposal = dispose()
expect(agent.status).toBe('disposed')
await firstDisposal
// Second dispose — idempotent, no throw
await expect(dispose()).resolves.toBeUndefined()
expect(agent.status).toBe('disposed')
})
@@ -283,7 +291,7 @@ describe('ReactLoopAgent', () => {
await ctx.plugin(SessionStore)
const session = ctx.sessions.create(SessionId('pre-start-dispose'))
const prepared = prepareReactLoopAgent(
ctx, AgentId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
ctx, SessionId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
)
await prepared.dispose()
@@ -298,7 +306,7 @@ describe('ReactLoopAgent', () => {
it('setting the same status does not emit agent/status again', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const statuses: string[] = []
ctx.on('agent/status', (subject, status) => {
@@ -317,7 +325,7 @@ describe('ReactLoopAgent', () => {
it('whenIdle() resolves immediately when the agent is not running', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// Fresh agent is idle — whenIdle() takes the not-running fast path and
// resolves without subscribing. await must not hang.
@@ -328,7 +336,7 @@ describe('ReactLoopAgent', () => {
it('whenIdle() waits for queued work that has not flipped status yet', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'queued')
let settled = false
@@ -346,8 +354,8 @@ describe('ReactLoopAgent', () => {
it('whenIdle() awaits the running→idle transition, ignoring other subjects/running events', async () => {
const adapter = new MockAdapter([textResponse('ok'), textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const other = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const other = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' })
// Drive `agent` into `running`, then await whenIdle() — it subscribes to
// agent/status and resolves on the first transition out of running.
@@ -370,10 +378,11 @@ describe('ReactLoopAgent', () => {
})
it('whenIdle() subscribed while running resolves via done when the agent is then disposed', async () => {
// Queue the internal waiter while running, then dispose the bare driver. Its disposed branch
// must chain the loop's `done` promise rather than resolve before exit.
// Covers the waiter's disposed arm: whenIdle() queues an internal waiter
// while running (not the fast path), then the disposer settles it and chains
// `done` (loop exit), not an eager resolve. A bare Agent + direct
// internal driver disposer keeps the emit synchronous.
const ctx = new Context()
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
@@ -383,7 +392,7 @@ describe('ReactLoopAgent', () => {
ctx.llm.registerAdapter(['mock'], adapter)
const session = ctx.sessions.create(SessionId('bare'))
const prepared = prepareReactLoopAgent(
ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
ctx, SessionId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
)
const { agent } = prepared
prepared.markPublished()
@@ -400,13 +409,15 @@ describe('ReactLoopAgent', () => {
})
it('whenIdle() subscribed while running survives a FIBER dispose (no hung promise)', async () => {
// The waiter is agent-owned state, not an effect-scoped listener that owner disposal would
// remove before the disposed transition. Fiber teardown must still settle it.
// The waiter is internal agent state, NOT an effect-scoped ctx.on listener:
// disposing the OWNING fiber runs the agent's listener disposers, which would
// have dropped a ctx.on-based waiter before the 'disposed' transition and
// hung the promise. With internal waiters, the fiber disposer still settles it.
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
@@ -419,19 +430,21 @@ describe('ReactLoopAgent', () => {
})
it('whenIdle() on a disposed agent awaits the loop exit (done), not just the status flip', async () => {
// Disposed status is emitted before the driver unwinds. `whenIdle()` must chain `done` so it
// resolves only after true loop exit.
// The disposer emits agent/status('disposed') BEFORE the driver loop
// unwinds, so whenIdle() must chain `done` (true quiescence) on the
// disposed path. Dispose a running agent, then assert whenIdle() resolves
// only after `done` — i.e. the loop has actually exited.
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
let doneResolved = false
void agent.done.then(() => { doneResolved = true })
void driverDone(agent).then(() => { doneResolved = true })
await fiber.dispose() // sets status disposed, aborts, drains the loop
expect(agent.status).toBe('disposed')
@@ -446,7 +459,7 @@ describe('ReactLoopAgent', () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/status', (_subject, status) => {
if (status === 'running') throw new Error('bad running listener')
})
@@ -464,7 +477,7 @@ describe('ReactLoopAgent', () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/status', (_subject, status) => {
if (status === 'idle') throw new Error('bad idle listener')
})

1040
packages/core/agent-loop/tests/cancel.spec.ts
View File

File diff suppressed because it is too large Load Diff

316
packages/core/agent-loop/tests/config-session-id.spec.ts
View File

@@ -7,16 +7,16 @@ import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse } from './mock-adapter.ts'
const dirs: string[] = []
afterEach(async () => { for (const d of dirs.splice(0)) await rm(d, { recursive: true, force: true }) })
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') { dispose(); resolve() }
@@ -24,7 +24,281 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
})
}
async function makeCoreContext(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
return ctx
}
describe('config-driven session id', () => {
it('rejects an empty exact id before publishing an agent', async () => {
const ctx = await makeCoreContext()
await expect(ctx.plugin(AgentLoop, {
agents: [{ id: 'main', sessionId: SessionId(''), model: 'mock' }],
})).rejects.toThrow('expected string length >= 1')
expect(ctx.agents.get(SessionId(''))).toBeUndefined()
await ctx.fiber.dispose()
})
it('accepts one exact fresh id and rejects it alongside a resume id', async () => {
const exact = await makeCoreContext()
await exact.plugin(AgentLoop, {
agents: [{ id: 'main', sessionId: SessionId('config-exact'), model: 'mock' }],
})
expect(exact.agents.get(SessionId('config-exact'))?.session.id).toBe('config-exact')
await exact.fiber.dispose()
const conflicting = await makeCoreContext()
await expect(conflicting.plugin(AgentLoop, {
agents: [{
id: 'main',
sessionId: SessionId('fresh'),
resumeSessionId: SessionId('persisted'),
model: 'mock',
}],
})).rejects.toThrow('sessionId and resumeSessionId are mutually exclusive')
await conflicting.fiber.dispose()
})
it('rejects duplicate exact ids before asynchronous configured startup', async () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-duplicate-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
const outcome = await ctx.plugin(AgentLoop, {
agents: [
{ id: 'first', sessionId: SessionId('shared'), model: 'mock' },
{ id: 'second', sessionId: SessionId('shared'), model: 'mock' },
],
}).then(() => undefined, (error: unknown) => error)
const published = ctx.agents.get(SessionId('shared'))
await ctx.fiber.dispose()
expect(outcome).toEqual(new Error('agents "first" and "second" use duplicate exact session identity "shared"'))
expect(published).toBeUndefined()
})
it('restores a materialized exact id across an AgentLoop-only reload', async () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first'), textResponse('second')]))
const config = { agents: [{ id: 'main', sessionId: SessionId('config-exact-reload'), model: 'mock' }] }
const firstLoop = await ctx.plugin(AgentLoop, config)
let first: Agent | undefined
for (let i = 0; i < 50 && first === undefined; i++) {
await new Promise(resolve => setTimeout(resolve, 5))
first = ctx.agents.get(SessionId('config-exact-reload'))
}
expect(first).toBeDefined()
first!.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } })
await waitForIdle(ctx, first!)
await firstLoop.dispose()
const secondLoop = await ctx.plugin(AgentLoop, config)
let second: Agent | undefined
for (let i = 0; i < 50 && second === undefined; i++) {
await new Promise(resolve => setTimeout(resolve, 5))
second = ctx.agents.get(SessionId('config-exact-reload'))
}
expect(second).toBeDefined()
expect(JSON.stringify(second!.session.deriveMessages())).toContain('remember me')
second!.send([{ type: 'text', text: 'continue' }], { source: { kind: 'user' } })
await waitForIdle(ctx, second!)
await ctx.sessions.flush(second!.session)
const loaded = await ctx.sessionPersistence.load(SessionId('config-exact-reload'))
expect(loaded.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
await secondLoop.dispose()
await ctx.fiber.dispose()
})
it('waits for a draining exact-id lifecycle during an overlapping reload', async () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-overlap-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
const sessionId = SessionId('config-exact-overlap')
const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] }
const firstLoop = await ctx.plugin(AgentLoop, config)
await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined()
const first = ctx.agents.get(sessionId) as Agent
const flushGate = Promise.withResolvers<undefined>()
let flushStarted = false
ctx.on('session/flush', (session) => {
if (session !== first.session) return
flushStarted = true
return flushGate.promise
})
first.inject([{ type: 'text', text: 'persist before replacement' }], {
source: { kind: 'plugin', plugin: 'test' },
})
expect(flushStarted).toBe(true)
const firstDisposal = firstLoop.dispose()
await expect.poll(() => first.status).toBe('disposed')
const failures: unknown[] = []
ctx.on('agent-loop/config-start-failed', (_id, error) => { failures.push(error) })
const secondLoop = await ctx.plugin(AgentLoop, config)
await new Promise(resolve => setTimeout(resolve, 0))
expect(ctx.agents.get(sessionId)).toBe(first)
expect(failures).toEqual([])
flushGate.resolve(undefined)
await firstDisposal
await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined()
const second = ctx.agents.get(sessionId) as Agent
expect(second).not.toBe(first)
expect(JSON.stringify(second.session.deriveMessages())).toContain('persist before replacement')
expect(failures).toEqual([])
await secondLoop.dispose()
await ctx.fiber.dispose()
})
it('cancels an exact-id reload while the prior lifecycle is still draining', async () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-cancel-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
const sessionId = SessionId('config-exact-cancel')
const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] }
const firstLoop = await ctx.plugin(AgentLoop, config)
await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined()
const first = ctx.agents.get(sessionId) as Agent
const flushGate = Promise.withResolvers<undefined>()
ctx.on('session/flush', (session) => {
if (session === first.session) return flushGate.promise
})
first.inject([{ type: 'text', text: 'persist before cancellation' }], {
source: { kind: 'plugin', plugin: 'test' },
})
const firstDisposal = firstLoop.dispose()
await expect.poll(() => first.status).toBe('disposed')
const secondLoop = await ctx.plugin(AgentLoop, config)
await secondLoop.dispose()
expect(ctx.agents.get(sessionId)).toBe(first)
flushGate.resolve(undefined)
await firstDisposal
expect(ctx.agents.get(sessionId)).toBeUndefined()
await ctx.fiber.dispose()
})
it('contains an exact-id persistence lookup failure', async () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
const failure = new Error('persistence index failed')
const listenerFailure = new Error('failure observer failed')
const asyncListenerFailure = new Error('async failure observer failed')
const failures: { sessionId: SessionId; error: unknown }[] = []
ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure })
ctx.on('agent-loop/config-start-failed', () => Promise.reject(asyncListenerFailure) as never)
ctx.on('agent-loop/config-start-failed', (sessionId, error) => {
failures.push({ sessionId, error })
})
vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure)
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
await ctx.plugin(AgentLoop, {
agents: [{ id: 'main', sessionId: SessionId('config-exact-failure'), model: 'mock' }],
})
await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining(
'config-driven restore of "config-exact-failure" failed: persistence index failed',
))
expect(failures).toEqual([{ sessionId: SessionId('config-exact-failure'), error: failure }])
expect(warn).toHaveBeenCalledWith(
'agent "main": config-start-failed listener threw: failure observer failed',
)
await expect.poll(() => warn).toHaveBeenCalledWith(
'agent "main": config-start-failed listener rejected: async failure observer failed',
)
expect(ctx.agents.get(SessionId('config-exact-failure'))).toBeUndefined()
warn.mockRestore()
await ctx.fiber.dispose()
})
it('contains startup and observer failures whose string coercion throws', async () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-unrenderable-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
const unrenderable = {
[Symbol.toPrimitive](): never {
throw new Error('coercion escaped')
},
}
const failures: unknown[] = []
ctx.on('agent-loop/config-start-failed', () => { throw unrenderable })
// Deliberately violate the normal Error-only rejection rule to exercise the unknown boundary.
// eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors
ctx.on('agent-loop/config-start-failed', () => Promise.reject(unrenderable) as never)
ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) })
vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(unrenderable)
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
await ctx.plugin(AgentLoop, {
agents: [{ id: 'main', sessionId: SessionId('config-exact-unrenderable'), model: 'mock' }],
})
await expect.poll(() => failures).toEqual([unrenderable])
expect(warn).toHaveBeenCalledWith(
'agent "main": config-driven restore of "config-exact-unrenderable" failed: <unrenderable value>',
)
expect(warn).toHaveBeenCalledWith(
'agent "main": config-start-failed listener threw: <unrenderable value>',
)
await expect.poll(() => warn).toHaveBeenCalledWith(
'agent "main": config-start-failed listener rejected: <unrenderable value>',
)
await ctx.fiber.dispose()
})
it.each(['resolve', 'reject'] as const)(
'joins an exact-id persistence lookup that will %s before AgentLoop disposal completes',
async (outcome) => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
const listing = Promise.withResolvers<Awaited<ReturnType<typeof ctx.sessionPersistence.list>>>()
vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise)
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
const failures: unknown[] = []
ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) })
const loop = await ctx.plugin(AgentLoop, {
agents: [{ id: 'main', sessionId: SessionId('config-exact-dispose'), model: 'mock' }],
})
let disposed = false
const disposal = loop.dispose().then(() => { disposed = true })
await Promise.resolve()
expect(disposed).toBe(false)
if (outcome === 'resolve') listing.resolve([])
else listing.reject(new Error('startup cancelled by teardown'))
await disposal
expect(ctx.agents.get(SessionId('config-exact-dispose'))).toBeUndefined()
expect(failures).toEqual([])
expect(warn).not.toHaveBeenCalled()
warn.mockRestore()
await ctx.fiber.dispose()
},
)
it('identity-nests the deferred resume fiber under its labeled owner effect', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
@@ -32,9 +306,8 @@ describe('config-driven session id', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
const loopFiber = await ctx.plugin(AgentLoop, {
agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }],
agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }],
})
const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)')
@@ -55,12 +328,13 @@ describe('config-driven session id', () => {
await ctx1.plugin(SystemPrompt)
await ctx1.plugin(ToolRegistry)
await ctx1.plugin(AgentRegistry)
await ctx1.plugin(AgentExecutionProvider)
await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), provider: 'mock', model: 'mock' }] })
await ctx1.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', model: 'mock' }] })
await ctx1.plugin(SessionPersistenceJsonl, { root })
ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')]))
const a1 = ctx1.agents.get(AgentId('cfg')) as ReactLoopAgent
const a1 = ctx1.agents.list()[0] as Agent
expect(a1.id).toBe(a1.session.id)
expect(a1.session.id).toMatch(idPattern)
expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined()
a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
await waitForIdle(ctx1, a1)
await ctx1.fiber.dispose()
@@ -73,11 +347,11 @@ describe('config-driven session id', () => {
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentExecutionProvider)
await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), provider: 'mock', model: 'mock' }] })
await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', model: 'mock' }] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')]))
const a2 = ctx2.agents.get(AgentId('cfg')) as ReactLoopAgent
const a2 = ctx2.agents.list()[0] as Agent
expect(a2.id).toBe(a2.session.id)
expect(a2.session.id).toMatch(idPattern)
expect(a2.session.id).not.toBe(a1.session.id)
a2.send([{ type: 'text', text: 'q2' }], { source: { kind: 'user' } })
@@ -97,11 +371,10 @@ describe('config-driven session id', () => {
await ctx1.plugin(SystemPrompt)
await ctx1.plugin(ToolRegistry)
await ctx1.plugin(AgentRegistry)
await ctx1.plugin(AgentExecutionProvider)
await ctx1.plugin(AgentLoop, { agents: [] })
await ctx1.plugin(SessionPersistenceJsonl, { root })
ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')]))
const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent
const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent
a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } })
await waitForIdle(ctx1, a1)
await ctx1.fiber.dispose()
@@ -114,20 +387,20 @@ describe('config-driven session id', () => {
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentExecutionProvider)
await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] })
await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')]))
// The deferred resume runs on a microtask after the backend is available.
let resumed: ReactLoopAgent | undefined
let resumed: Agent | undefined
for (let i = 0; i < 50 && !resumed; i++) {
await new Promise(r => setTimeout(r, 5))
resumed = ctx2.agents.get(AgentId('main')) as ReactLoopAgent | undefined
resumed = ctx2.agents.get(SessionId('sticky-1'))
}
expect(resumed).toBeDefined()
// The live session id IS the resumed id (NOT a fresh ${id}-session-<uuid>),
// and the prior turn's user message is in the derived history.
expect(resumed!.id).toBe(SessionId('sticky-1'))
expect(resumed!.session.id).toBe('sticky-1')
const derived = resumed!.session.deriveMessages()
expect(JSON.stringify(derived)).toContain('remember me')
@@ -143,17 +416,16 @@ describe('config-driven session id', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] })
await ctx.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] })
const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn')
.mockImplementation(() => undefined)
await ctx.plugin(SessionPersistenceJsonl, { root })
ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('x')]))
// The deferred resume fails (no such session on disk). It must be contained:
// a warning is logged, no 'main' agent is registered, and the app stays up.
// a warning is logged, no agent is registered, and the app stays up.
await new Promise(r => setTimeout(r, 200))
expect(ctx.agents.get(AgentId('main'))).toBeUndefined()
expect(ctx.agents.list()).toEqual([])
expect(warn).toHaveBeenCalledWith(expect.stringContaining('config-driven resume of "does-not-exist" failed'))
warn.mockRestore()
await ctx.fiber.dispose()

283
packages/core/agent-loop/tests/contract-regressions.spec.ts
View File

@@ -4,13 +4,16 @@ import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@d
import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool, type PostToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent, type ContinuationDecision } from '@deepseek-ai/dsh-agent'
import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from '@deepseek-ai/dsh-agent-loop'
import { prepareReactLoopAgent } from '../src/agent.ts'
import * as Invariants from '@deepseek-ai/dsh-invariants'
import { maxTokensResponse, MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
function driverDone(agent: Agent): Promise<void> {
return (agent as Agent & { done: Promise<void> }).done
}
/** Regression tests for agent-loop boundary, identity, and lifecycle contracts. */
async function harness(adapter: MockAdapter) {
@@ -20,13 +23,12 @@ async function harness(adapter: MockAdapter) {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -37,7 +39,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
})
}
function send(agent: ReactLoopAgent, text: string) {
function send(agent: Agent, text: string) {
agent.send([{ type: 'text', text }])
}
@@ -57,7 +59,7 @@ describe('session log records what agent/step-result actually produced', () => {
return [{ type: 'text', text: 'ran' }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// Plugin rewrites the message: replaces the text AND adds a tool call.
let rewritten = false
@@ -99,7 +101,7 @@ describe('session log records what agent/step-result actually produced', () => {
response[response.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState }
const adapter = new MockAdapter([response])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('replay-state'), { provider: 'mock', model: 'next-model' })
const agent = ctx.agentLoop.create(SessionId('replay-state'), { provider: 'mock', model: 'next-model' })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -123,7 +125,7 @@ describe('session log records what agent/step-result actually produced', () => {
if (block?.type === 'text') block.text = 'mutated'
return message
})
const agent = ctx.agentLoop.create(AgentId('mutated-replay-state'), { provider: 'mock', model: 'next-model' })
const agent = ctx.agentLoop.create(SessionId('mutated-replay-state'), { provider: 'mock', model: 'next-model' })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -143,7 +145,7 @@ describe('successful provider completion survives agent/step-result failure', ()
const adapter = new MockAdapter([response])
const ctx = await harness(adapter)
await ctx.plugin(Invariants)
const agent = ctx.agentLoop.create(AgentId(id), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId(id), { provider: 'mock', model: 'mock' })
const failure = new Error(`${id} result processing failed`)
const reported: Error[] = []
@@ -202,7 +204,7 @@ describe('successful provider completion survives agent/step-result failure', ()
})
describe('abort during tool execution ends the turn', () => {
it('cancelling the active turn inside a tool prevents both remaining tools and the next model step', async () => {
it('balances a cancelled tool batch through context and post-step before closing', async () => {
const adapter = new MockAdapter([
// model asks for two tool calls in one step
[
@@ -216,17 +218,28 @@ describe('abort during tool execution ends the turn', () => {
])
const ctx = await harness(adapter)
const executed: string[] = []
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.tools.register(defineTool({
name: 'aborter',
description: '',
parameters: {},
async execute() {
async execute(_args, exec) {
executed.push('aborter')
exec.agent?.steer(
[{ type: 'text', text: 'steering before abort' }],
{ source: { kind: 'plugin', plugin: 'abort-test' } },
)
agent.cancel({ kind: 'user' })
return [{ type: 'text', text: 'done' }]
},
}))
ctx.on('tools/post-execute', async exec => ({
kind: 'accept',
additionalContexts: [{
content: [{ type: 'text', text: `context for ${exec.callId}` }],
source: { kind: 'plugin', plugin: 'abort-test' },
}],
}))
ctx.tools.register(defineTool({
name: 'second',
description: '',
@@ -238,20 +251,69 @@ describe('abort during tool execution ends the turn', () => {
}))
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
const order: string[] = []
ctx.on('session/event', (session, event) => {
if (session !== agent.session) return
switch (event.type) {
case 'assistant/message': order.push('assistant/message'); break
case 'tool/call': order.push(`tool/call:${event.data.callId}`); break
case 'tool/result': {
const outcome = event.data.error?.code === 'ABORTED' ? 'synthetic-aborted' : 'real'
order.push(`tool/result:${event.data.callId}:${outcome}`)
break
}
case 'context/message': order.push('context/message'); break
case 'steering/message': order.push('steering/message'); break
case 'step/end': order.push('step/end'); break
case 'turn/end': {
reasons.push(event.data.reason)
order.push(`turn/end:${event.data.reason.kind}`)
break
}
}
})
let postSteps = 0
ctx.on('agent/post-step', (subject, turn, step, signal) => {
if (subject !== agent) return
postSteps += 1
expect({ turn, step, aborted: signal.aborted }).toEqual({ turn: 1, step: 1, aborted: true })
order.push('agent/post-step')
})
send(agent, 'go')
await waitForIdle(ctx, agent)
expect(executed).toEqual(['aborter']) // second tool never ran
expect(adapter.requests).toHaveLength(1) // no follow-up model call
expect(executed).toEqual(['aborter'])
expect(adapter.requests).toHaveLength(1)
expect(postSteps).toBe(1)
expect(order).toEqual([
'assistant/message',
'tool/call:c1',
'tool/result:c1:real',
'tool/call:c2',
'tool/result:c2:synthetic-aborted',
'context/message',
'agent/post-step',
'step/end',
'turn/end:aborted',
])
expect(reasons).toEqual([{ kind: 'aborted' }])
const calls = agent.session.events.filter(event => event.type === 'tool/call')
const results = agent.session.events.filter(event => event.type === 'tool/result')
expect(calls.map(event => event.data.callId)).toEqual([CallId('c1'), CallId('c2')])
expect(results).toHaveLength(2)
expect(results[0]!.data).toMatchObject({ callId: CallId('c1'), isError: false })
expect(results[1]!.data).toMatchObject({
callId: CallId('c2'),
isError: true,
error: { name: 'AbortError', code: 'ABORTED' },
})
})
it('records context accepted before a tool-step abort in the same turn', async () => {
const adapter = new MockAdapter([toolCallResponse('c1', 'aborter', {})])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-abort-injection'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-abort-injection'), { provider: 'mock', model: 'mock' })
ctx.tools.register(defineTool({
name: 'aborter',
description: '',
@@ -297,7 +359,7 @@ describe('abort during tool execution ends the turn', () => {
{ type: 'finish', reason: { kind: 'tool-calls' } },
] satisfies StreamChunk[]])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-later-abort-context'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-later-abort-context'), { provider: 'mock', model: 'mock' })
ctx.tools.register(defineTool({
name: 'first',
description: '',
@@ -343,9 +405,9 @@ describe('abort during tool execution ends the turn', () => {
const adapter = new MockAdapter([toolCallResponse('c1', 'waiter', {})])
const ctx = await harness(adapter)
const started = Promise.withResolvers<undefined>()
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-dispose-injection'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('a-dispose-injection'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
ctx.tools.register(defineTool({
name: 'waiter',
@@ -398,7 +460,7 @@ describe('abort during tool execution ends the turn', () => {
textResponse('later turn'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-historical-tool-pair'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-historical-tool-pair'), { provider: 'mock', model: 'mock' })
ctx.tools.register(defineTool({
name: 'aborter',
description: '',
@@ -440,7 +502,7 @@ describe('steering from late extension points is never stranded', () => {
textResponse('continued because of steering'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let steeredOnce = false
ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, _signal, next) => {
@@ -466,7 +528,7 @@ describe('steering from late extension points is never stranded', () => {
textResponse('after goal reminder'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let steeredOnce = false
ctx.on('session/event', (subject, event) => {
@@ -494,7 +556,7 @@ describe('steering from late extension points is never stranded', () => {
it('steer() from a turn/end session-event listener becomes a queued message for the next turn', async () => {
const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const turns: number[] = []
let steeredOnce = false
@@ -517,27 +579,13 @@ describe('steering from late extension points is never stranded', () => {
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('too late for this turn')
})
it('steering queued before turn cancellation is discarded with the cancelled work', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
agent.steer([{ type: 'text', text: 'redirect' }])
agent.cancel({ kind: 'user' })
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1)
expect(JSON.stringify(agent.session.events)).not.toContain('redirect')
})
})
describe('plugin exceptions are contained', () => {
it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let threwOnce = false
ctx.on('agent/turn-continuation', async (): Promise<ContinuationDecision> => {
@@ -562,15 +610,20 @@ describe('plugin exceptions are contained', () => {
expect(agent.status).toBe('idle')
})
it('a rejecting session/flush listener is reported but does not kill the agent', async () => {
it('a rejecting first-turn flush settles before the queued tail starts', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let rejectedOnce = false
ctx.on('session/flush', async () => {
if (!rejectedOnce) {
rejectedOnce = true
const firstFlush = Promise.withResolvers<undefined>()
const releaseFirstFlush = Promise.withResolvers<undefined>()
let flushes = 0
ctx.on('session/flush', async (session) => {
if (session !== agent.session) return
flushes += 1
if (flushes === 1) {
firstFlush.resolve(undefined)
await releaseFirstFlush.promise
throw new Error('disk full')
}
})
@@ -578,24 +631,31 @@ describe('plugin exceptions are contained', () => {
const errors: Error[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
const idle = waitForIdle(ctx, agent)
send(agent, 'first')
await waitForIdle(ctx, agent)
expect(errors.map(e => e.message)).toEqual(['disk full'])
send(agent, 'second')
await waitForIdle(ctx, agent)
await firstFlush.promise
expect(adapter.requests).toHaveLength(1)
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
releaseFirstFlush.resolve(undefined)
await idle
expect(errors.map(e => e.message)).toEqual(['disk full'])
expect(adapter.requests).toHaveLength(2)
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
})
})
describe('disposed status is part of the agent/status contract', () => {
it('disposing the fiber emits agent/status(disposed) and ends the turn with reason disposed', async () => {
it('disposing the fiber ends the active turn and never starts its queued tail', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
const statuses: string[] = []
@@ -605,20 +665,28 @@ describe('disposed status is part of the agent/status contract', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
send(agent, 'queued tail')
await fiber.dispose()
await agent.done
await driverDone(agent)
expect(statuses).toEqual(['running', 'disposed'])
expect(reasons).toEqual([{ kind: 'disposed' }])
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
const messages = agent.session.events
.filter(event => event.type === 'user/message')
.flatMap(event => event.data.content)
.flatMap(block => block.type === 'text' ? [block.text] : [])
expect(messages).toEqual(['go'])
expect(adapter.requests).toHaveLength(1)
})
it('a throwing agent/status listener cannot break disposal or leak the registry entry', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
ctx.on('agent/status', (_agent, status) => {
@@ -628,10 +696,10 @@ describe('disposed status is part of the agent/status contract', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
await fiber.dispose()
await agent.done // must not hang
await driverDone(agent) // must not hang
expect(agent.status).toBe('disposed')
expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() // unregistered despite the throw
expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw
})
})
@@ -650,7 +718,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => {
const adapter = new MockAdapter([textResponse('never')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model
const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model
const errors: Error[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
@@ -665,9 +733,9 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
it('the agent/request waterfall can supply the model for a model-less agent', async () => {
const adapter = new MockAdapter([textResponse('routed')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model — router plugin decides
const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model — router plugin decides
ctx.on('agent/request', async (_agent, _turn, _step, config, _signal, _next) => {
ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => {
return { ...config, provider: 'mock', model: 'mock' }
})
@@ -680,7 +748,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
it('agent/queued carries the resolved source; steering/message records its source', async () => {
const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.tools.register(defineTool({
name: 'noop',
description: '',
@@ -708,7 +776,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
it('send() owns content and source before notification and delivery', async () => {
const adapter = new MockAdapter([textResponse('done')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('owned-send'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('owned-send'), { provider: 'mock', model: 'mock' })
const content = [{ type: 'text' as const, text: 'accepted-send' }]
const source = { kind: 'plugin' as const, plugin: 'accepted-source' }
let notifiedContent: ContentBlock[] | undefined
@@ -744,7 +812,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
it('running steer() owns content and source before notification and delivery', async () => {
const adapter = new MockAdapter([toolCallResponse('c1', 'gate', {}), textResponse('done')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('owned-steer'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('owned-steer'), { provider: 'mock', model: 'mock' })
const entered = Promise.withResolvers<undefined>()
const release = Promise.withResolvers<undefined>()
ctx.tools.register(defineTool({
@@ -798,7 +866,7 @@ describe('turn numbering continues across seeded sessions', () => {
it('a forked agent continues turn numbers after the seed log', async () => {
const first = new MockAdapter([textResponse('turn one')])
const ctx = await harness(first)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'first')
await waitForIdle(ctx, agent)
@@ -810,13 +878,12 @@ describe('turn numbering continues across seeded sessions', () => {
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentExecutionProvider)
await ctx2.plugin(AgentLoop, { agents: [] })
ctx2.llm.registerAdapter(['mock'], second)
const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] })
const prepared = prepareReactLoopAgent(
ctx2, AgentId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
ctx2, SessionId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
)
const forked = prepared.agent
prepared.markPublished()
@@ -861,7 +928,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', ()
]
const adapter = new MockAdapter([errorStream])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-finish-error'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -886,7 +953,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', ()
]
const adapter = new MockAdapter([abortedStream])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-finish-aborted'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -904,7 +971,7 @@ describe('a finish-error stream chunk ends the turn as error, not completed', ()
]
const adapter = new MockAdapter([errorStream])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-finish-error-nocode'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -920,7 +987,7 @@ describe('step boundary publication order', () => {
it('the step/start event is in session.events when its session/event listener fires', async () => {
const adapter = new MockAdapter([textResponse('done')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-step-order'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-step-order'), { provider: 'mock', model: 'mock' })
// Append commits before observers run.
const observed: { turn: number; step: number; lastEventType: string | undefined; sawStepStart: boolean }[] = []
@@ -953,7 +1020,6 @@ describe('turn and step boundary recovery', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants)
ctx.llm.registerAdapter(['mock'], adapter)
@@ -961,7 +1027,7 @@ describe('turn and step boundary recovery', () => {
}
/** Count turn/step boundary events for balance assertions. */
function boundaryCounts(agent: ReactLoopAgent) {
function boundaryCounts(agent: Agent) {
const e = [...agent.session.events]
return {
turnStart: e.filter(x => x.type === 'turn/start').length,
@@ -976,7 +1042,7 @@ describe('turn and step boundary recovery', () => {
it('a throwing step/start observer cannot change a successful turn', async () => {
const adapter = new MockAdapter([textResponse('request completed')])
const ctx = await balancedHarness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-stepstart'), { provider: 'mock', model: 'mock' })
// Session owns post-commit containment. The loop sees a successful append,
// runs the request, and balances the ordinary step and turn boundaries.
@@ -1005,7 +1071,7 @@ describe('turn and step boundary recovery', () => {
it('a pre-commit step/start validation failure does not invent a step boundary', async () => {
const adapter = new MockAdapter([textResponse('never reached')])
const ctx = await balancedHarness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-stepstart-veto'), { provider: 'mock', model: 'mock' })
let rejected = false
ctx.on('internal/dispatch', (_mode, name, args) => {
if (name !== 'session/event') return
@@ -1036,7 +1102,7 @@ describe('turn and step boundary recovery', () => {
const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider failed' } }]
const adapter = new MockAdapter([errorStream])
const ctx = await balancedHarness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-turnend-veto'), { provider: 'mock', model: 'mock' })
let rejected = false
ctx.on('internal/dispatch', (_mode, name, args) => {
if (name !== 'session/event') return
@@ -1070,7 +1136,7 @@ describe('turn and step boundary recovery', () => {
it('a one-shot step/end validation failure keeps the step open until retry succeeds', async () => {
const adapter = new MockAdapter([textResponse('completed before close validation')])
const ctx = await balancedHarness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-stepend-veto'), { provider: 'mock', model: 'mock' })
let rejected = false
ctx.on('internal/dispatch', (_mode, name, args) => {
if (name !== 'session/event') return
@@ -1102,7 +1168,7 @@ describe('turn and step boundary recovery', () => {
const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }]
const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')])
const ctx = await balancedHarness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-errorlistener'), { provider: 'mock', model: 'mock' })
let threw = false
ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } })
@@ -1129,13 +1195,13 @@ describe('turn and step boundary recovery', () => {
it('disposal during a running turn ends the turn with reason disposed (balanced)', async () => {
// The 'hang' adapter blocks in stream() until the signal aborts; disposing
// the agent's fiber mid-turn aborts the active turn. The turn must close
// the agent's fiber mid-turn aborts the in-flight step. The turn must close
// balanced with reason disposed (no error event for a disposal).
const adapter = new MockAdapter(['hang'])
const ctx = await balancedHarness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-dispose'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('a-dispose'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
@@ -1144,7 +1210,7 @@ describe('turn and step boundary recovery', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
await fiber.dispose() // dispose during the hanging step
await agent.done
await driverDone(agent)
const e = [...agent.session.events]
const turnStarts = e.filter(x => x.type === 'turn/start').length
@@ -1160,9 +1226,9 @@ describe('turn and step boundary recovery', () => {
// Disposal remains authoritative when the listener also throws.
const adapter = new MockAdapter([textResponse('never reached')])
const ctx = await balancedHarness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
let threw = false
@@ -1176,7 +1242,7 @@ describe('turn and step boundary recovery', () => {
ctx.on('agent/error', (_a, _t, _s, error) => void errorEmits.push(error))
send(agent, 'go')
await agent.done
await driverDone(agent)
const e = [...agent.session.events]
// Balanced: one turn/start, one turn/end carrying disposed (NOT error).
@@ -1193,7 +1259,7 @@ describe('turn and step boundary recovery', () => {
it('a throwing turn/start observer cannot starve the loop or later turns', async () => {
const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-preturn'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-preturn'), { provider: 'mock', model: 'mock' })
let threw = false
ctx.on('session/event', (_session, event) => {
@@ -1224,7 +1290,7 @@ describe('turn and step boundary recovery', () => {
it('a throwing step/end observer cannot rewrite the turn outcome', async () => {
const adapter = new MockAdapter([textResponse('all good'), textResponse('turn 2 ok')])
const ctx = await balancedHarness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-stepend-throw'), { provider: 'mock', model: 'mock' })
let threw = false
ctx.on('session/event', (_s, event) => {
@@ -1263,7 +1329,7 @@ describe('turn and step boundary recovery', () => {
const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }]
const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-stependthrow'), { provider: 'mock', model: 'mock' })
let threw = false
ctx.on('session/event', (_s, event) => {
@@ -1293,7 +1359,7 @@ describe('turn and step boundary recovery', () => {
// boundary stays authoritative and the loop continues normally.
const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-turnendappend'), { provider: 'mock', model: 'mock' })
let threw = false
ctx.on('session/event', (_s, event) => {
@@ -1339,7 +1405,7 @@ describe('tool result call identity', () => {
return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] })
}, { prepend: true })
const agent = ctx.agentLoop.create(AgentId('a-callid'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-callid'), { provider: 'mock', model: 'mock' })
send(agent, 'use tool')
await waitForIdle(ctx, agent)
@@ -1370,9 +1436,9 @@ describe('surface: assistant/message records exact empty provenance when no chun
const adapter = new MockAdapter([[]])
const ctx = await harness(adapter)
await ctx.plugin(Invariants)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _signal, _next) => ({
ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({
role: 'assistant' as const,
content: [{ type: 'text' as const, text: 'injected' }],
}))
@@ -1405,7 +1471,6 @@ describe('disposal and cancellation during pre-step assembly', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants)
ctx.llm.registerAdapter(['mock'], adapter)
@@ -1416,9 +1481,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
return next()
})
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
@@ -1433,7 +1498,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
releaseAssemble()
await disposalDone
await agent.done
await driverDone(agent)
unlisten()
// Turn boundaries are durable rows; there is no `agent/*` mirror to assert.
@@ -1457,7 +1522,6 @@ describe('disposal and cancellation during pre-step assembly', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants)
ctx.llm.registerAdapter(['mock'], adapter)
@@ -1467,9 +1531,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
return next()
})
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
@@ -1482,7 +1546,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
releaseAssemble()
await waitForIdle(ctx, agent)
await fiber.dispose()
await agent.done
await driverDone(agent)
unlisten()
const e = [...agent.session.events]
@@ -1510,7 +1574,6 @@ describe('disposal and cancellation during pre-step assembly', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants)
ctx.llm.registerAdapter(['mock'], adapter)
@@ -1519,9 +1582,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
await blocker
})
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
@@ -1534,7 +1597,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
const disposalDone = fiber.dispose()
releasePreStep()
await disposalDone
await agent.done
await driverDone(agent)
// After the pre-step seam finishes, the post-seam cancel/dispose check
// catches disposal. The step was never opened, no LLM call was made.
@@ -1562,7 +1625,6 @@ describe('disposal and cancellation during pre-step assembly', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants)
ctx.llm.registerAdapter(['mock'], adapter)
@@ -1571,9 +1633,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
await blocker
})
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
@@ -1586,7 +1648,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
releasePreStep()
await waitForIdle(ctx, agent)
await fiber.dispose()
await agent.done
await driverDone(agent)
const e = [...agent.session.events]
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
@@ -1612,7 +1674,6 @@ describe('disposal and cancellation during pre-step assembly', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(Invariants)
ctx.llm.registerAdapter(['mock'], adapter)
@@ -1622,9 +1683,9 @@ describe('disposal and cancellation during pre-step assembly', () => {
return next()
})
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
send(agent, 'go')
@@ -1633,7 +1694,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
const disposalDone = fiber.dispose()
releaseAssemble()
await disposalDone
await agent.done
await driverDone(agent)
const e = [...agent.session.events]
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)

55
packages/core/agent-loop/tests/coverage-edges.spec.ts
View File

@@ -1,15 +1,19 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService, { CallId, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { TurnEndReason } from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
function driverDone(agent: Agent): Promise<void> {
return (agent as Agent & { done: Promise<void> }).done
}
async function harness(adapter: MockAdapter) {
const ctx = new Context()
await ctx.plugin(LlmService)
@@ -17,13 +21,12 @@ async function harness(adapter: MockAdapter) {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -34,7 +37,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
})
}
function send(agent: ReactLoopAgent, text: string) {
function send(agent: Agent, text: string) {
agent.send([{ type: 'text', text }])
}
@@ -42,7 +45,7 @@ describe('inbox acceptance', () => {
it('rejects non-serializable content or source synchronously before notification or enqueue', async () => {
const adapter = new MockAdapter([textResponse('turn 1')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let queued = 0
ctx.on('agent/queued', () => { queued += 1 })
@@ -82,7 +85,7 @@ describe('tool JSON parse', () => {
return [{ type: 'text', text: typeof args === 'string' ? `raw: ${args}` : JSON.stringify(args) }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'use tool')
await waitForIdle(ctx, agent)
@@ -115,7 +118,7 @@ describe('tool JSON parse', () => {
return [{ type: 'text', text: 'ran with empty args' }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'use tool')
await waitForIdle(ctx, agent)
@@ -128,7 +131,7 @@ describe('toError normalization', () => {
it('normalizes non-Error throws from pre-commit dispatch validation via the runLoop backstop', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let threwOnce = false
ctx.on('internal/dispatch', (_mode, name, args) => {
@@ -143,18 +146,28 @@ describe('toError normalization', () => {
const errors: Error[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
send(agent, 'go')
send(agent, 'fails before turn start')
send(agent, 'survives as the next item')
await waitForIdle(ctx, agent)
expect(errors).toHaveLength(1)
expect(errors[0]).toMatchObject({ message: 'naked string error', code: 'UNKNOWN' })
expect(adapter.requests).toEqual([])
expect(agent.session.events.some(event => event.type === 'turn/start' || event.type === 'turn/end')).toBe(false)
expect(adapter.requests).toHaveLength(1)
const starts = agent.session.events.filter(event => event.type === 'turn/start')
const ends = agent.session.events.filter(event => event.type === 'turn/end')
const messages = agent.session.events.filter(event => event.type === 'user/message')
expect(starts).toHaveLength(1)
expect(starts[0]?.type === 'turn/start' && starts[0].data.turn).toBe(1)
expect(ends).toHaveLength(1)
expect(messages).toHaveLength(1)
expect(messages[0]?.type === 'user/message' && messages[0].data.content).toEqual([
{ type: 'text', text: 'survives as the next item' },
])
})
it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => {
const adapter = new MockAdapter([textResponse('irrelevant')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let threwOnce = false
ctx.on('agent/request', async (_agent, _turn, _step, _options, _signal, _next) => {
@@ -182,7 +195,7 @@ describe('coded error data emission', () => {
it('errorData includes code when a coded error (LlmError) is thrown from a plugin', async () => {
const adapter = new MockAdapter([textResponse('turn 1')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let threwOnce = false
ctx.on('agent/request', async (_agent, _turn, _step, _options, _signal, next) => {
@@ -214,9 +227,9 @@ describe('disposed vs aborted branching', () => {
it('handles dispose during model streaming producing reason "disposed"', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
const reasons: TurnEndReason[] = []
@@ -225,14 +238,14 @@ describe('disposed vs aborted branching', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
await fiber.dispose() // dispose during hang
await agent.done
await driverDone(agent)
// Disposal wins abort classification because the error path checks it first.
expect(reasons).toContainEqual({ kind: 'disposed' })
})
})
describe('structured tool error propagation (the runtime-validation RFC, part 2)', () => {
describe('structured tool error propagation (the runtime-validation Agent Note, part 2)', () => {
it('forwards a tool HarnessError onto the tool/result session event', async () => {
const { HarnessError } = await import('@deepseek-ai/dsh-llm')
// First model turn calls the tool; second turn (after the tool result is
@@ -242,7 +255,7 @@ describe('structured tool error propagation (the runtime-validation RFC, part 2)
textResponse('done'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.tools.register(defineTool({
name: 'boom',
description: 'always fails',

10
packages/core/agent-loop/tests/inbox.spec.ts
View File

@@ -8,17 +8,17 @@ function resolverPair() {
}
describe('Inbox', () => {
it('enqueues and drains queued messages in FIFO order', () => {
it('dequeues one queued message at a time in FIFO order', () => {
const inbox = new Inbox()
inbox.enqueue({ content: [{ type: 'text', text: 'first' }], source: { kind: 'user' } })
inbox.enqueue({ content: [{ type: 'text', text: 'second' }], source: { kind: 'user' } })
expect(inbox.hasQueued).toBe(true)
const drained = inbox.drainQueued()
expect(drained).toHaveLength(2)
expect(drained[0]!.content[0]).toMatchObject({ text: 'first' })
expect(drained[1]!.content[0]).toMatchObject({ text: 'second' })
expect(inbox.dequeueQueued()?.content[0]).toMatchObject({ text: 'first' })
expect(inbox.hasQueued).toBe(true)
expect(inbox.dequeueQueued()?.content[0]).toMatchObject({ text: 'second' })
expect(inbox.hasQueued).toBe(false)
expect(inbox.dequeueQueued()).toBeUndefined()
})
it('pushes and drains steering messages separately from queued', () => {

149
packages/core/agent-loop/tests/interception.spec.ts
View File

@@ -1,17 +1,12 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm'
import SessionStore, { type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry, {
AgentId,
type ContinuationDecision,
type PromptDecision,
type SessionStartSource,
} from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent, type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
/**
@@ -30,13 +25,12 @@ async function harness(adapter: MockAdapter) {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -47,11 +41,11 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
})
}
function send(agent: ReactLoopAgent, text: string) {
function send(agent: Agent, text: string) {
agent.send([{ type: 'text', text }])
}
function events(agent: ReactLoopAgent): SessionEvent[] {
function events(agent: Agent): SessionEvent[] {
return [...agent.session.events]
}
@@ -59,7 +53,7 @@ describe('agent/prompt-submit', () => {
it('allow (default via next) records the user/message unchanged', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const seen: string[] = []
ctx.on('agent/prompt-submit', async (_agent, content, _source, _signal, next) => {
@@ -78,7 +72,7 @@ describe('agent/prompt-submit', () => {
it('allow with content REWRITES the prompt before it is recorded', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
({ kind: 'allow', content: [{ type: 'text', text: 'REWRITTEN' }] }))
@@ -96,7 +90,7 @@ describe('agent/prompt-submit', () => {
it('allow with additionalContexts injects separate context/message events into the turn', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const meta = { kind: 'prompt-context', version: 1 }
ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
@@ -105,7 +99,6 @@ describe('agent/prompt-submit', () => {
additionalContexts: [{
content: [{ type: 'text', text: '<system-reminder>extra ctx</system-reminder>' }],
source: { kind: 'plugin', plugin: 'test' },
envelope: 'raw',
meta,
}],
}))
@@ -119,19 +112,15 @@ describe('agent/prompt-submit', () => {
expect(userMsg).toBeDefined()
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.content).toEqual([{ type: 'text', text: '<system-reminder>extra ctx</system-reminder>' }])
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'test' })
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.envelope).toBe('raw')
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.meta).toEqual(meta)
// both the prompt and the injected context reach the model
const sent = JSON.stringify(adapter.requests[0]!.messages)
expect(sent).toContain('extra ctx')
})
it('a prompt-submit rewrite + additionalContexts is VISIBLE to the agent/pre-step seam (merged ordering)', async () => {
// Prompt rewrites and injected context land before `agent/pre-step`, so a
// compaction listener measures the current surface before the single derive.
it('runs pre-step after prompt rewrites and injected context become durable', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
({
@@ -140,8 +129,6 @@ describe('agent/prompt-submit', () => {
additionalContexts: [{ content: [{ type: 'text', text: 'injected ctx' }], source: { kind: 'plugin', plugin: 'test' } }],
}))
// The pre-step seam (where compaction lives) derives the surface it would act
// on. Capture what it sees on the first step.
let preStepDerived: string | undefined
ctx.on('agent/pre-step', (subject, _turn, step) => {
if (subject === agent && step === 1) preStepDerived = JSON.stringify(subject.session.deriveMessages())
@@ -150,8 +137,6 @@ describe('agent/prompt-submit', () => {
send(agent, 'ORIGINAL prompt')
await waitForIdle(ctx, agent)
// The pre-step seam ran and saw BOTH the rewrite (not the original) and the
// injected context — i.e. the prompt-submit effects landed before it.
expect(preStepDerived).toBeDefined()
expect(preStepDerived).toContain('REWRITTEN prompt')
expect(preStepDerived).toContain('injected ctx')
@@ -161,7 +146,7 @@ describe('agent/prompt-submit', () => {
it('block drops the (only) prompt → zero-step turn ends rejected, model never called', async () => {
const adapter = new MockAdapter([textResponse('should not run')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/prompt-submit', async (): Promise<PromptDecision> =>
({ kind: 'block', reason: 'blocked by policy' }))
@@ -192,12 +177,10 @@ describe('agent/prompt-submit', () => {
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'rejected', reason: 'blocked by policy' })
})
it('a mixed batch records a prompt/blocked for the vetoed prompt while the allowed one runs', async () => {
// Blocking one prompt in a mixed batch must persist its reason even though
// the allowed prompt keeps the turn from ending rejected.
it('adjacent blocked and allowed prompts keep independent turn outcomes', async () => {
const adapter = new MockAdapter([textResponse('ran once')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/prompt-submit', async (_agent, content, _source, _signal, next): Promise<PromptDecision> => {
const text = content.map(b => (b.type === 'text' ? b.text : '')).join('')
@@ -207,13 +190,13 @@ describe('agent/prompt-submit', () => {
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
// both sends land before the loop drains → one batched turn
// Both sends land before the driver wakes, but each remains its own turn.
send(agent, 'secret')
send(agent, 'safe')
await waitForIdle(ctx, agent)
const log = events(agent)
// the allowed prompt became a user/message and drove exactly one model call
// The allowed prompt became a user/message and drove exactly one model call.
const userMsgs = log.filter(e => e.type === 'user/message')
expect(userMsgs).toHaveLength(1)
expect(userMsgs[0]?.type === 'user/message' && userMsgs[0].data.content).toEqual([{ type: 'text', text: 'safe' }])
@@ -225,15 +208,17 @@ describe('agent/prompt-submit', () => {
content: [{ type: 'text', text: 'secret' }],
reason: 'policy: no secrets',
})
// the turn did NOT reject — a sibling was allowed — so the boundary reason
// alone would not have preserved the block
expect(reasons.some(r => r.kind === 'rejected')).toBe(false)
expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2)
expect(reasons).toEqual([
{ kind: 'rejected', reason: 'policy: no secrets' },
{ kind: 'completed' },
])
})
it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => {
it('a throwing prompt-submit listener ends its turn balanced while an adjacent message survives', async () => {
const adapter = new MockAdapter([textResponse('after')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let threw = false
ctx.on('agent/prompt-submit', async () => {
@@ -241,20 +226,31 @@ describe('agent/prompt-submit', () => {
return { kind: 'allow' as const }
})
const errors: Error[] = []
const reasons: TurnEndReason[] = []
const statuses: string[] = []
ctx.on('agent/error', (_a, _t, _s, error) => void errors.push(error))
ctx.on('agent/status', (subject, status) => { if (subject === agent) statuses.push(status) })
ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'turn/end') reasons.push(event.data.reason)
})
const idle = waitForIdle(ctx, agent)
send(agent, 'first')
await waitForIdle(ctx, agent)
expect(errors.map(e => e.message)).toEqual(['prompt hook broke'])
// turn balanced
const log = events(agent)
expect(log.filter(e => e.type === 'turn/start')).toHaveLength(1)
expect(log.filter(e => e.type === 'turn/end')).toHaveLength(1)
// loop survives: a second prompt runs normally
send(agent, 'second')
await waitForIdle(ctx, agent)
expect(adapter.requests.length).toBeGreaterThanOrEqual(1)
await idle
expect(errors.map(e => e.message)).toEqual(['prompt hook broke'])
// The failed prompt forms one balanced error turn; the adjacent prompt forms
// the following normal turn without an intermediate idle transition.
const log = events(agent)
expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2)
expect(log.filter(e => e.type === 'turn/end')).toHaveLength(2)
expect(reasons).toEqual([
{ kind: 'error', step: 0, message: 'prompt hook broke' },
{ kind: 'completed' },
])
expect(statuses).toEqual(['running', 'idle'])
expect(adapter.requests).toHaveLength(1)
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('second')
})
})
@@ -266,7 +262,7 @@ describe('agent/session-start', () => {
const sources: SessionStartSource[] = []
ctx.on('agent/session-start', (_agent, source) => void sources.push(source))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// fires synchronously at create, before any turn
expect(sources).toEqual(['startup'])
expect(events(agent).some(e => e.type === 'turn/start')).toBe(false)
@@ -285,7 +281,7 @@ describe('agent/session-start', () => {
agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } })
})
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -303,8 +299,8 @@ describe('agent/session-start', () => {
ctx.on('agent/session-start', () => { throw new Error('session-start hook broke') })
// create must not throw — the listener error is contained/logged
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
expect(agent.id).toBe(AgentId('a1'))
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
expect(agent.id).toBe(SessionId('a1'))
// and the agent still runs
send(agent, 'go')
@@ -317,8 +313,8 @@ describe('agent/session-prefix', () => {
it('dispatches to global and matching agent-scope listeners only', async () => {
const adapter = new MockAdapter([textResponse('a done'), textResponse('b done')])
const ctx = await harness(adapter)
const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { provider: 'mock', model: 'mock' })
const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { provider: 'mock', model: 'mock' })
const agentA = ctx.agentLoop.create(SessionId('prefix-a'), { provider: 'mock', model: 'mock' })
const agentB = ctx.agentLoop.create(SessionId('prefix-b'), { provider: 'mock', model: 'mock' })
const seen: string[] = []
ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => {
seen.push(`global:${agent.id}`)
@@ -355,7 +351,7 @@ describe('agent/session-prefix', () => {
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const reminder: Message = { role: 'user', content: [{ type: 'text', text: '<system-reminder>catalog</system-reminder>' }] }
let composed = 0
@@ -385,10 +381,10 @@ describe('agent/session-prefix', () => {
expect(agent.session.deriveMessages()[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'go' }] })
})
it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => {
it('composes before the first pre-step and records the prefix on the request header', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] }
const order: string[] = []
@@ -396,26 +392,21 @@ describe('agent/session-prefix', () => {
order.push('compose')
return [reminder, ...await next()]
})
const seen: (readonly Message[])[] = []
ctx.on('agent/pre-step', (_agent, _turn, _step, _system, sessionPrefix) => {
ctx.on('agent/pre-step', () => {
order.push('pre-step')
seen.push(sessionPrefix)
})
send(agent, 'hi')
await waitForIdle(ctx, agent)
// Composition precedes the pre-step seam, and the seam receives THIS
// instance's composed prefix — a token-pressure gate (compaction) counts
// what the request will actually carry, never a stale logged prefix.
expect(order).toEqual(['compose', 'pre-step'])
expect(seen[0]).toEqual([reminder])
expect(agent.session.requestHeader()?.messagePrefix).toEqual([reminder])
})
it('the canonical prepend pattern composes contributions in registration order', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// Both listeners use the canonical `[mine, ...await next()]` prepend: the
// waterfall unwinds innermost-first (the second listener's array is built
@@ -437,7 +428,7 @@ describe('agent/session-prefix', () => {
it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// A listener that delegates without contributing — the canonical no-op.
ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next())
@@ -453,7 +444,7 @@ describe('agent/session-prefix', () => {
it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let mutationError: unknown
ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise<Message[]> => {
@@ -482,7 +473,7 @@ describe('agent/session-prefix', () => {
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] }
ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => [...await next(), held])
@@ -503,7 +494,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => {
it('a continue decision with a reason records next-step steering in the same turn', async () => {
const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let forced = false
ctx.on('agent/turn-continuation', async (_agent, _turn, _default, _signal, next): Promise<ContinuationDecision> => {
@@ -535,7 +526,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => {
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/turn-continuation', async (): Promise<ContinuationDecision> => ({ action: 'stop' }))
@@ -565,7 +556,7 @@ describe('tool additionalContexts buffering across a step', () => {
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// Each call attaches one context naming itself.
ctx.on('tools/post-execute', async (exec, _result): Promise<PostToolDecision> =>
@@ -574,7 +565,6 @@ describe('tool additionalContexts buffering across a step', () => {
additionalContexts: [{
content: [{ type: 'text', text: `ctx-${exec.callId}` }],
source: { kind: 'plugin', plugin: 'p' },
envelope: 'raw',
meta: { callId: exec.callId },
}],
}))
@@ -598,7 +588,6 @@ describe('tool additionalContexts buffering across a step', () => {
.map(b => (b.type === 'text' ? b.text : ''))
expect(ctxTexts).toEqual(['ctx-c1', 'ctx-c2'])
const contextEvents = events(agent).filter(e => e.type === 'context/message')
expect(contextEvents.map(e => e.type === 'context/message' && e.data.envelope)).toEqual(['raw', 'raw'])
expect(contextEvents.map(e => e.type === 'context/message' && e.data.meta)).toEqual([{ callId: 'c1' }, { callId: 'c2' }])
})
@@ -609,11 +598,11 @@ describe('tool additionalContexts buffering across a step', () => {
name: 'composite', description: 'composite', parameters: {},
async execute(_args, exec) {
exec.deferContext({ content: [{ type: 'text', text: 'nested-a' }], source: { kind: 'plugin', plugin: 'a' }, meta: { order: 1 } })
exec.deferContext({ content: [{ type: 'text', text: 'nested-b' }], source: { kind: 'plugin', plugin: 'b' }, envelope: 'raw', meta: { order: 2 } })
exec.deferContext({ content: [{ type: 'text', text: 'nested-b' }], source: { kind: 'plugin', plugin: 'b' }, meta: { order: 2 } })
return [{ type: 'text', text: 'outer result' }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -640,7 +629,7 @@ describe('tools/pre-execute gate (native-plugin permission pattern, end-to-end t
name: 'danger', description: 'danger', parameters: {},
async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' }
@@ -702,7 +691,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se
name: 'echo', description: 'echo', parameters: { text: { type: 'string' } },
async execute(args) { return [{ type: 'text', text: String(args.text) }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'please echo hi')
await waitForIdle(ctx, agent)
@@ -725,7 +714,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se
const adapter = new MockAdapter([textResponse('should not run')])
const ctx = await harness(adapter)
await ctx.plugin(NativeGuard)
const agent = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -744,7 +733,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se
await fiber.dispose()
// After disposal, a destructive prompt is NOT blocked (the listener is gone).
const agent = ctx.agentLoop.create(AgentId('a3'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a3'), { provider: 'mock', model: 'mock' })
send(agent, 'run rm -rf /')
await waitForIdle(ctx, agent)
// the prompt ran (not rejected) — proving the prompt-submit listener was disposed

333
packages/core/agent-loop/tests/loop.spec.ts
View File

@@ -4,11 +4,15 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts'
function driverDone(agent: Agent): Promise<void> {
return (agent as Agent & { done: Promise<void> }).done
}
async function harness(adapter: MockAdapter, persona = '') {
const ctx = new Context()
await ctx.plugin(LlmService)
@@ -16,7 +20,6 @@ async function harness(adapter: MockAdapter, persona = '') {
await ctx.plugin(SystemPrompt, { persona })
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
@@ -27,7 +30,7 @@ async function harness(adapter: MockAdapter, persona = '') {
* invoke this right after send(), when the loop hasn't woken yet (status is
* still 'idle' synchronously), so polling the current status would lie.
*/
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -38,7 +41,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
})
}
function send(agent: ReactLoopAgent, text: string) {
function send(agent: Agent, text: string) {
agent.send([{ type: 'text', text }])
}
@@ -46,7 +49,7 @@ describe('agent loop', () => {
it('runs a simple turn: queued message → model → idle, with ordered events', async () => {
const adapter = new MockAdapter([textResponse('hello there')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
// All boundaries — turn and step — are durable session events on the
// session/event feed (no agent/* mirror). Record them in fire order to
@@ -94,7 +97,7 @@ describe('agent loop', () => {
return [{ type: 'text', text: `echo: ${args.text}` }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'use the tool')
await waitForIdle(ctx, agent)
@@ -133,7 +136,7 @@ describe('agent loop', () => {
return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } }
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'use the tool')
await waitForIdle(ctx, agent)
@@ -157,7 +160,7 @@ describe('agent loop', () => {
return []
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'hi')
await waitForIdle(ctx, agent)
@@ -171,13 +174,12 @@ describe('agent loop', () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter, 'Working in {{cwd}}.')
const handle = await ctx.agents.create({
agentId: AgentId('a-cwd'),
sessionId: SessionId('s-cwd'),
meta: { cwd: '/work/space' },
agentOptions: { provider: 'mock', model: 'mock' },
})
const agent = handle.agent as ReactLoopAgent
const agent = handle.agent
send(agent, 'hi')
await waitForIdle(ctx, agent)
@@ -190,7 +192,7 @@ describe('agent loop', () => {
const ctx = await harness(adapter, 'In {{cwd}}.')
const errors: Error[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'hi')
await waitForIdle(ctx, agent)
@@ -232,7 +234,7 @@ describe('agent loop', () => {
ctx.on('agent/request', async (_agent, _turn, _step, config, _signal, _next) => {
return { ...config, provider: 'mock', model: 'mock' }
})
const agent = ctx.agentLoop.create(AgentId('a-late-model'), {})
const agent = ctx.agentLoop.create(SessionId('a-late-model'), {})
send(agent, 'hi')
await waitForIdle(ctx, agent)
@@ -258,7 +260,7 @@ describe('agent loop', () => {
parameters: {},
execute: () => Promise.resolve({ content: [{ type: 'text' as const, text: 'apparent success' }], meta }),
}))
const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('bad-meta-agent'), { provider: 'mock', model: 'mock' })
send(agent, 'use the tool')
await waitForIdle(ctx, agent)
@@ -287,7 +289,7 @@ describe('agent loop', () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} }))
const agent = ctx.agentLoop.create(AgentId('a-no-system'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a-no-system'), { provider: 'mock', model: 'mock' })
send(agent, 'hi')
await waitForIdle(ctx, agent)
@@ -299,7 +301,7 @@ describe('agent loop', () => {
it('records raw chunks for replay as assistant/chunk session events', async () => {
const adapter = new MockAdapter([textResponse('abc')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'hi')
await waitForIdle(ctx, agent)
@@ -323,7 +325,7 @@ describe('agent loop', () => {
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.tools.register(defineTool({
name: 'slow',
description: '',
@@ -352,20 +354,30 @@ describe('agent loop', () => {
expect(flat).toContain('change of plans')
})
it('steering while idle behaves like send (starts a turn)', async () => {
const adapter = new MockAdapter([textResponse('ok')])
it('same-tick idle steering inherits one-send-one-turn FIFO behavior', async () => {
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.steer([{ type: 'text', text: 'hello' }])
await waitForIdle(ctx, agent)
expect(agent.session.events.some(e => e.type === 'user/message')).toBe(true)
const idle = waitForIdle(ctx, agent)
agent.steer([{ type: 'text', text: 'first idle steer' }])
agent.steer([{ type: 'text', text: 'second idle steer' }])
await idle
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
expect(agent.session.events
.filter(event => event.type === 'user/message')
.map(event => event.data.content)).toEqual([
[{ type: 'text', text: 'first idle steer' }],
[{ type: 'text', text: 'second idle steer' }],
])
expect(adapter.requests).toHaveLength(2)
})
it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } })
// The idle inject records a self-contained turn (turn/start → context/message
@@ -383,13 +395,13 @@ describe('agent loop', () => {
await waitForIdle(ctx, agent)
const flat = JSON.stringify(adapter.requests[0]!.messages)
expect(flat).toContain('file changed: a.ts')
expect(flat).toContain('<context source=\\"plugin\\">')
expect(flat).not.toContain('<context source=')
})
it('inject() can persist raw structured context without the generic context envelope', async () => {
it('inject() persists structured context content verbatim with durable hidden meta', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('raw-context'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('raw-context'), { provider: 'mock', model: 'mock' })
const text = '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>'
const meta = {
kind: 'workspace-instructions',
@@ -399,14 +411,13 @@ describe('agent loop', () => {
agent.inject([{ type: 'text', text }], {
source: { kind: 'plugin', plugin: 'workspace-context' },
envelope: 'raw',
meta,
})
send(agent, 'go')
await waitForIdle(ctx, agent)
const contextEvent = agent.session.events.find(event => event.type === 'context/message')
expect(contextEvent?.type === 'context/message' && contextEvent.data).toMatchObject({ envelope: 'raw', meta })
expect(contextEvent?.type === 'context/message' && contextEvent.data).toMatchObject({ meta })
const requestText = JSON.stringify(adapter.requests[0]!.messages)
expect(requestText).toContain('Additional instructions from: pkg/AGENTS.md')
expect(requestText).not.toContain('<context source=')
@@ -418,7 +429,7 @@ describe('agent loop', () => {
textResponse('done'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let visibleDuringTool = false
const meta = { kind: 'deferred-test', version: 1 }
ctx.tools.register(defineTool({
@@ -430,7 +441,6 @@ describe('agent loop', () => {
const first = { type: 'text' as const, text: 'mid-turn notice' }
agent.inject([first], {
source: { kind: 'plugin', plugin: 'x' },
envelope: 'raw',
meta,
})
first.text = 'mutated after inject'
@@ -456,7 +466,6 @@ describe('agent loop', () => {
expect(contexts).toHaveLength(2)
expect(result.seq).toBeLessThan(contexts[0]!.seq)
expect(contexts[0]?.type === 'context/message' && contexts[0].data).toMatchObject({
envelope: 'raw',
meta,
})
expect(contexts.flatMap(event => event.type === 'context/message' ? event.data.content : []))
@@ -484,7 +493,7 @@ describe('agent loop', () => {
textResponse('done'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('invalid-context'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('invalid-context'), { provider: 'mock', model: 'mock' })
ctx.tools.register(defineTool({
name: 'invalid-injector',
description: 'attempts an invalid context injection',
@@ -514,7 +523,7 @@ describe('agent loop', () => {
textResponse('step 3'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let steps = 0
ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ })
@@ -540,7 +549,7 @@ describe('agent loop', () => {
return [{ type: 'text', text: String(args.text) }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const)
@@ -555,7 +564,7 @@ describe('agent loop', () => {
it('agent/request waterfall switches models by returning a replacement config; the switch is logged', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/request', async (_agent, _turn, _step, config, _signal, _next) => {
// The seed is frozen — config is not a mutable per-call knob; a switch
@@ -575,10 +584,6 @@ describe('agent loop', () => {
})
it('agent/pre-step fires once per step before the step is opened', async () => {
// Two steps (a tool call, then a final text turn) → two model calls → two
// pre-step fires, each carrying the assembled full system prompt, BEFORE
// the step is opened and its request is derived (the request the adapter
// sees reflects any surface state at fire time).
const adapter = new MockAdapter([
toolCallResponse('c1', 'echo', {}, 'calling echo'),
textResponse('done'),
@@ -588,23 +593,21 @@ describe('agent loop', () => {
name: 'echo', description: 'echo', parameters: {},
async execute() { return [{ type: 'text', text: 'echoed' }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const fires: { turn: number; step: number; fullSystemPrompt: string }[] = []
ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => {
if (subject === agent) fires.push({ turn, step, fullSystemPrompt })
const fires: { turn: number; step: number; signal: AbortSignal }[] = []
ctx.on('agent/pre-step', (subject, turn, step, signal) => {
if (subject === agent) fires.push({ turn, step, signal })
})
send(agent, 'go')
await waitForIdle(ctx, agent)
// One fire per step, in order, each with the assembled system prompt
// (here just the loop's own harness-identity section — no persona set).
const HARNESS = 'You are an AI agent powered by the DeepSeek Harness SDK.'
expect(fires).toEqual([
{ turn: 1, step: 1, fullSystemPrompt: HARNESS },
{ turn: 1, step: 2, fullSystemPrompt: HARNESS },
expect(fires.map(({ turn, step }) => ({ turn, step }))).toEqual([
{ turn: 1, step: 1 },
{ turn: 1, step: 2 },
])
expect(fires.every(({ signal }) => signal instanceof AbortSignal)).toBe(true)
})
it('agent/pre-step fires BEFORE the step it precedes opens (events land outside the step)', async () => {
@@ -612,7 +615,7 @@ describe('agent loop', () => {
// same step's request must include it.
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let injected = false
ctx.on('agent/pre-step', (subject) => {
@@ -646,7 +649,7 @@ describe('agent loop', () => {
// closing, the turn records error, and the loop remains available.
const adapter = new MockAdapter([textResponse('second turn ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let throwOnce = true
ctx.on('agent/pre-step', () => {
@@ -680,7 +683,7 @@ describe('agent loop', () => {
it('cancel() mid-stream ends the turn with reason aborted', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -700,7 +703,7 @@ describe('agent loop', () => {
// turn stops by default and ends max-tokens, not completed.
const adapter = new MockAdapter([maxTokensResponse('truncat')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -723,7 +726,7 @@ describe('agent loop', () => {
textResponse('second half'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let steps = 0
ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ })
@@ -754,7 +757,7 @@ describe('agent loop', () => {
// stop. The per-turn reason must be independent — turn 2 ends completed.
const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -787,7 +790,7 @@ describe('agent loop', () => {
return [{ type: 'text', text: 'should not run' }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -824,7 +827,7 @@ describe('agent loop', () => {
parameters: { text: { type: 'string' } },
async execute() { return [{ type: 'text', text: 'should not run' }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -849,7 +852,7 @@ describe('agent loop', () => {
// a durable successful-call boundary for replay consumers.
const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
@@ -886,7 +889,7 @@ describe('agent loop', () => {
expect(message.content).toEqual([{ type: 'text', text: 'partial text' }])
return next()
})
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -913,7 +916,7 @@ describe('agent loop', () => {
return [{ type: 'text', text: String(args.text) }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let threw = false
// Post-commit session observers cannot control the loop. The tool call still
// drives the second model request, and the turn completes normally.
@@ -929,10 +932,152 @@ describe('agent loop', () => {
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('completed')
})
it('chains queued messages into consecutive turns', async () => {
it('keeps same-tick sends in separate turns and checkpoints before the next starts', async () => {
const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const firstFlush = Promise.withResolvers<undefined>()
const releaseFirstFlush = Promise.withResolvers<undefined>()
let flushes = 0
ctx.on('session/flush', async (session) => {
if (session !== agent.session) return
flushes += 1
if (flushes === 1) {
firstFlush.resolve(undefined)
await releaseFirstFlush.promise
}
})
const turns: number[] = []
ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'turn/start') turns.push(event.data.turn)
})
const idle = waitForIdle(ctx, agent)
send(agent, 'first message')
send(agent, 'second message')
await firstFlush.promise
expect(turns).toEqual([1])
expect(adapter.requests).toHaveLength(1)
releaseFirstFlush.resolve(undefined)
await idle
expect(turns).toEqual([1, 2])
expect(flushes).toBe(2)
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first answer')
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message')
})
it('holds a turn-end listener send behind the closing turn checkpoint', async () => {
const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const firstFlush = Promise.withResolvers<undefined>()
const releaseFirstFlush = Promise.withResolvers<undefined>()
let flushes = 0
ctx.on('session/flush', async (session) => {
if (session !== agent.session) return
flushes += 1
if (flushes === 1) {
firstFlush.resolve(undefined)
await releaseFirstFlush.promise
}
})
const turns: number[] = []
const statuses: string[] = []
ctx.on('agent/status', (subject, status) => {
if (subject === agent) statuses.push(status)
})
ctx.on('session/event', (session, event) => {
if (session !== agent.session) return
if (event.type === 'turn/start') turns.push(event.data.turn)
if (event.type === 'turn/end' && event.data.turn === 1) send(agent, 'turn-end listener message')
})
const idle = waitForIdle(ctx, agent)
send(agent, 'first message')
await firstFlush.promise
expect(turns).toEqual([1])
expect(adapter.requests).toHaveLength(1)
releaseFirstFlush.resolve(undefined)
await idle
expect(turns).toEqual([1, 2])
expect(statuses).toEqual(['running', 'idle'])
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first answer')
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('turn-end listener message')
})
it('keeps a reentrant agent/queued send as the next independent turn', async () => {
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let nested = false
ctx.on('agent/queued', (subject) => {
if (subject !== agent || nested) return
nested = true
send(agent, 'queued listener message')
})
const idle = waitForIdle(ctx, agent)
send(agent, 'outer message')
await idle
const turns = agent.session.events.filter(event => event.type === 'turn/start')
const messages = agent.session.events
.filter(event => event.type === 'user/message')
.map(event => event.data.content)
expect(turns).toHaveLength(2)
expect(messages).toEqual([
[{ type: 'text', text: 'outer message' }],
[{ type: 'text', text: 'queued listener message' }],
])
})
it('preserves independent turn sources across an adjacent microtask send', async () => {
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const idle = waitForIdle(ctx, agent)
agent.send([{ type: 'text', text: 'user message' }])
await Promise.resolve()
agent.send(
[{ type: 'text', text: 'plugin message' }],
{ source: { kind: 'plugin', plugin: 'test' } },
)
await idle
const triggers = agent.session.events
.filter(event => event.type === 'turn/start')
.map(event => event.data.trigger)
const sources = agent.session.events
.filter(event => event.type === 'user/message')
.map(event => event.data.source)
expect(triggers).toEqual([
{ kind: 'message', source: { kind: 'user' } },
{ kind: 'message', source: { kind: 'plugin', plugin: 'test' } },
])
expect(sources).toEqual([
{ kind: 'user' },
{ kind: 'plugin', plugin: 'test' },
])
})
it('keeps a session-listener send after dequeue in the following turn', async () => {
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const turns: number[] = []
ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) })
@@ -952,12 +1097,43 @@ describe('agent loop', () => {
expect(turns).toEqual([1, 2])
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first')
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message')
})
it('keeps a model-adapter callback send in the following turn', async () => {
const agentRef: { current?: Agent } = {}
const adapter = new MockAdapter([
() => {
const agent = agentRef.current
if (agent === undefined) throw new Error('model callback ran before agent setup')
send(agent, 'model callback message')
return textResponse('first')
},
textResponse('second'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agentRef.current = agent
const idle = waitForIdle(ctx, agent)
send(agent, 'outer message')
await idle
const messages = agent.session.events
.filter(event => event.type === 'user/message')
.map(event => event.data.content)
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
expect(messages).toEqual([
[{ type: 'text', text: 'outer message' }],
[{ type: 'text', text: 'model callback message' }],
])
})
it('awaits session/flush at turn end (persistence checkpoint)', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let flushed = 0
let flushedBeforeIdle = false
@@ -977,7 +1153,7 @@ describe('agent loop', () => {
it('errors from the model surface as agent/error and end the turn', async () => {
const adapter = new MockAdapter([]) // script exhausted → throws
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const errors: Error[] = []
const reasons: TurnEndReason[] = []
@@ -1000,21 +1176,21 @@ describe('agent loop', () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
let agent!: ReactLoopAgent
let agent!: Agent
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' })
agent = inner.agentLoop.create(SessionId('scoped'), { provider: 'mock', model: 'mock' })
}, { inject: ['agentLoop'] }))
expect(ctx.agents.get(AgentId('scoped'))).toBe(agent)
expect(ctx.agents.get(SessionId('scoped'))).toBe(agent)
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
expect(agent.status).toBe('running')
await fiber.dispose()
await agent.done
await driverDone(agent)
expect(agent.status).toBe('disposed')
expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined()
expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined()
expect(() => { send(agent, 'too late') }).toThrow('disposed')
})
@@ -1026,15 +1202,15 @@ describe('agent loop', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, {
agents: [{ id: AgentId('config-agent'), provider: 'mock', model: 'mock' }],
agents: [{ id: SessionId('config-agent'), provider: 'mock', model: 'mock' }],
})
ctx.llm.registerAdapter(['mock'], adapter)
const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent
const agent = ctx.agents.list()[0]!
expect(agent).toBeDefined()
expect(agent.id).toBe('config-agent')
expect(agent.id).toBe(agent.session.id)
expect(agent.id).toMatch(/^config-agent-session-/)
expect(agent.options.model).toBe('mock')
// the agent is alive: send triggers a turn
@@ -1050,12 +1226,11 @@ describe('agent loop', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, {
agents: [{ id: AgentId('config-agent'), provider: 'mock', model: 'mock', cwd: '/work/project' }],
agents: [{ id: SessionId('config-agent'), provider: 'mock', model: 'mock', cwd: '/work/project' }],
})
const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent
const agent = ctx.agents.list()[0]!
expect(agent.session.header.cwd).toBe('/work/project')
})
@@ -1073,7 +1248,7 @@ describe('agent loop', () => {
return [{ type: 'text', text: String(args.text) }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'run')
await waitForIdle(ctx, agent)

75
packages/core/agent-loop/tests/properties.spec.ts
View File

@@ -1,7 +1,12 @@
/**
* Deterministic property tests for inbox scheduling: every sent message logs
* once, turn numbers increase, and status follows idle→running→idle/disposed.
* Schedules advance on status events rather than wall-clock sleeps.
* Property-based tests for the agent loop's inbox/turn scheduling (the
* property-testing Agent Note). Deterministic by construction: schedules are driven
* through the `agent/status` settle signal (no wall-clock sleeps), so a flake
* is a finding, not timing noise.
*
* Invariants: every sent message appears exactly once in the log (none lost);
* turn numbers strictly increase; status transitions follow the legal machine
* idle→running→idle (and →disposed at teardown).
*/
import { describe, expect, it } from 'vitest'
@@ -9,12 +14,12 @@ import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
import { LlmAdapter } from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import fc from 'fast-check'
/** A never-exhausting adapter: every model call returns the same short reply. */
@@ -37,14 +42,13 @@ async function harness() {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], new EchoAdapter())
return ctx
}
/** Resolve on the agent's next transition to idle (event-based, not polled). */
function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function nextIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -57,7 +61,7 @@ function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
/** Record every status transition for the legal-machine assertion. Returns
* the seen list plus a disposer for the listener (per the registry convention). */
function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; dispose: () => void } {
function recordStatus(ctx: Context, agent: Agent): { seen: string[]; dispose: () => void } {
const seen: string[] = []
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent) seen.push(status)
@@ -65,18 +69,33 @@ function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; di
return { seen, dispose }
}
function userMessageTexts(agent: ReactLoopAgent): string[] {
function userMessageTexts(agent: Agent): string[] {
return agent.session.events
.filter(e => e.type === 'user/message')
.map(e => (e.data as { content: { type: string; text?: string }[] }).content.map(b => b.text ?? '').join(''))
}
function turnNumbers(agent: ReactLoopAgent): number[] {
function turnNumbers(agent: Agent): number[] {
return agent.session.events
.filter(e => e.type === 'turn/start')
.map(e => (e.data as { turn: number }).turn)
}
function turnEndNumbers(agent: Agent): number[] {
return agent.session.events
.filter(e => e.type === 'turn/end')
.map(e => (e.data as { turn: number }).turn)
}
function userMessageCountsByTurn(agent: Agent): number[] {
const counts: number[] = []
for (const event of agent.session.events) {
if (event.type === 'turn/start') counts.push(0)
if (event.type === 'user/message') counts[counts.length - 1]! += 1
}
return counts
}
/** Assert a status trace is a legal run: idle/running alternating, ending idle. */
function assertLegalStatusTrace(trace: string[]): void {
for (let i = 1; i < trace.length; i++) {
@@ -86,13 +105,13 @@ function assertLegalStatusTrace(trace: string[]): void {
}
describe('agent loop scheduling properties', () => {
it('a synchronous burst loses no message and uses strictly increasing turns', async () => {
it('a synchronous burst gives every message its own strictly increasing turn', async () => {
await fc.assert(fc.asyncProperty(
fc.array(fc.string({ minLength: 1 }), { minLength: 1, maxLength: 6 }),
async (texts) => {
const ctx = await harness()
try {
const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
const { seen: trace } = recordStatus(ctx, agent)
const idle = nextIdle(ctx, agent)
// Send all in one synchronous tick: they queue before the loop wakes.
@@ -101,8 +120,11 @@ describe('agent loop scheduling properties', () => {
// No message lost: every send appears as a user/message, in order.
expect(userMessageTexts(agent)).toEqual(texts)
// A synchronous burst batches into exactly one turn.
expect(turnNumbers(agent)).toEqual([1])
// This failure-free fixture maps every item to an independent turn.
expect(turnNumbers(agent)).toEqual(texts.map((_, i) => i + 1))
expect(turnEndNumbers(agent)).toEqual(texts.map((_, i) => i + 1))
expect(userMessageCountsByTurn(agent)).toEqual(texts.map(() => 1))
expect(trace).toEqual(['running', 'idle'])
assertLegalStatusTrace(trace)
} finally {
await ctx.fiber.dispose()
@@ -117,7 +139,7 @@ describe('agent loop scheduling properties', () => {
async (texts) => {
const ctx = await harness()
try {
const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
for (const text of texts) {
const idle = nextIdle(ctx, agent)
agent.send([{ type: 'text', text }])
@@ -133,16 +155,16 @@ describe('agent loop scheduling properties', () => {
), { numRuns: 20, timeout: 2000 })
})
it('mixed schedule (send, optionally settle) loses no message and orders turns', async () => {
// Each step is a (text, settle?) pair: settle=true awaits idle before the
// next send (own turn); settle=false sends in the same tick (batches).
it('mixed settled and same-tick sends preserve one turn per message', async () => {
// Each step optionally waits for idle before the next send; that scheduling
// choice must not change the ordinary message-to-turn mapping.
const stepArb = fc.record({ text: fc.string({ minLength: 1 }), settle: fc.boolean() })
await fc.assert(fc.asyncProperty(
fc.array(stepArb, { minLength: 1, maxLength: 6 }),
async (steps) => {
const ctx = await harness()
try {
const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
// Capture before each send; the last waiter covers the final turn, and
// awaiting an already-settled earlier waiter is harmless.
let lastIdle: Promise<void> | undefined
@@ -154,14 +176,13 @@ describe('agent loop scheduling properties', () => {
}
await lastIdle
// No message lost or reordered, regardless of batching.
// No message is lost or reordered, regardless of driver timing.
expect(userMessageTexts(agent)).toEqual(steps.map(s => s.text))
// Turn numbers are a strictly increasing 1..N prefix (N = turn count).
// Every item forms one FIFO-ordered turn containing only that message.
const turns = turnNumbers(agent)
expect(turns).toEqual(turns.map((_, i) => i + 1))
// Every message landed in some turn; turns never exceed messages.
expect(turns.length).toBeLessThanOrEqual(steps.length)
expect(turns.length).toBeGreaterThanOrEqual(1)
expect(turns).toEqual(steps.map((_, i) => i + 1))
expect(turnEndNumbers(agent)).toEqual(turns)
expect(userMessageCountsByTurn(agent)).toEqual(steps.map(() => 1))
} finally {
await ctx.fiber.dispose()
}

11
packages/core/agent-loop/tests/request-cache.e2e.ts
View File

@@ -1,11 +1,11 @@
import { afterEach, describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
@@ -14,7 +14,7 @@ import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
* multi-step tool turn (plus a follow-up turn) against the live DeepSeek API must report
* `cacheReadTokens > 0` on every request after the first — the adapter maps the provider's
* `prompt_cache_hit_tokens`, and the per-step usage recorded on `assistant/message` events is
* the production observable for cache behavior (the reconstructability RFC's measurement
* the production observable for cache behavior (the reconstructability Agent Note's measurement
* layer: prefix stability is corollary #1). Mocks establish append-extension;
* this key-gated test establishes a real provider cache hit.
*/
@@ -43,7 +43,6 @@ async function loopHarness(): Promise<Context> {
await created.plugin(SystemPrompt, { persona: SYSTEM })
await created.plugin(ToolRegistry)
await created.plugin(AgentRegistry)
await created.plugin(AgentExecutionProvider)
await created.plugin(AgentLoop, { agents: [] })
await created.plugin(LlmDeepSeek)
created.tools.register(defineTool({
@@ -71,7 +70,7 @@ function waitForIdle(context: Context, agent: Agent): Promise<void> {
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => {
it('every request after the first hits the provider prefix cache', async () => {
ctx = await loopHarness()
const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
// Turn 1: forces a tool call → at least two steps (two model requests).
agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }])

32
packages/core/agent-loop/tests/request-reconstruction.spec.ts
View File

@@ -12,9 +12,9 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm'
import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
async function harness(adapter: MockAdapter, persona = 'stable base') {
@@ -24,13 +24,12 @@ async function harness(adapter: MockAdapter, persona = 'stable base') {
await ctx.plugin(SystemPrompt, { persona })
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -41,7 +40,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
})
}
function send(agent: ReactLoopAgent, text: string) {
function send(agent: Agent, text: string) {
agent.send([{ type: 'text', text }])
}
@@ -73,7 +72,7 @@ describe('request stability across the loop', () => {
])
const ctx = await harness(adapter)
registerEcho(ctx)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'go')
await waitForIdle(ctx, agent)
@@ -94,7 +93,7 @@ describe('request stability across the loop', () => {
it('a later turn append-extends the previous turn (one conversation, one log)', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'first')
await waitForIdle(ctx, agent)
@@ -108,7 +107,7 @@ describe('request stability across the loop', () => {
it('a compaction replace rewrites the resend, and the log explains it', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'first')
await waitForIdle(ctx, agent)
@@ -141,7 +140,7 @@ describe('request stability across the loop', () => {
it('a real system-prompt change is a full changed-header snapshot; a stable prompt logs nothing', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'first')
await waitForIdle(ctx, agent)
@@ -165,7 +164,7 @@ describe('request stability across the loop', () => {
it('an inject() during the agent/request waterfall joins the NEXT request (the step/start boundary)', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let injected = false
ctx.on('agent/request', async (_agent, _turn, _step, _config, _signal, next) => {
@@ -193,7 +192,7 @@ describe('request stability across the loop', () => {
it('a mutation attempt on the frozen request content throws into the step (loud, not silent)', async () => {
const adapter = new MockAdapter([textResponse('one')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const errors: Error[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
@@ -214,7 +213,7 @@ describe('request stability across the loop', () => {
it('a fresh loop instance over a seeded log anchors with a resume snapshot and stays cache-aligned', async () => {
const adapter = new MockAdapter([textResponse('one')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('gen1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('gen1'), { provider: 'mock', model: 'mock' })
send(agent, 'first')
await waitForIdle(ctx, agent)
@@ -223,12 +222,11 @@ describe('request stability across the loop', () => {
const adapter2 = new MockAdapter([textResponse('two')])
const ctx2 = await harness(adapter2)
const handle = await ctx2.agents.create({
agentId: AgentId('gen2'),
sessionId: SessionId('gen2-session'),
seed: [...agent.session.events],
agentOptions: { provider: 'mock', model: 'mock' },
})
const agent2 = handle.agent as ReactLoopAgent
const agent2 = handle.agent
send(agent2, 'second')
await waitForIdle(ctx2, agent2)
@@ -243,7 +241,7 @@ describe('request stability across the loop', () => {
it('a delegating listener cannot mutate the seed through next() — the fold stays log-true', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/request', async (_agent, _turn, _step, _config, _signal, next) => {
const config = await next()
@@ -277,7 +275,7 @@ describe('request stability across the loop', () => {
])
const ctx = await harness(adapter)
registerEcho(ctx)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'go')
await waitForIdle(ctx, agent)

516
packages/core/agent-loop/tests/request-recovery.spec.ts Normal file
View File

@@ -0,0 +1,516 @@
import { describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import LlmService, {
CallId,
CONTEXT_WINDOW_EXCEEDED_CODE,
LlmAdapter,
LlmError,
} from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import type { PostToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts'
class FailureScriptAdapter extends LlmAdapter {
requests: GenerateOptions[] = []
constructor(private readonly entries: (Error | StreamChunk[])[]) {
super()
}
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
this.requests.push(options)
const entry = this.entries.shift()
if (entry === undefined) throw new Error('failure script exhausted')
if (entry instanceof Error) throw entry
yield* entry
}
}
class IteratorConstructionFailureAdapter extends LlmAdapter {
stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
return {
[Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
throw new LlmError('iterator construction failed', 'ITERATOR_CONSTRUCTION')
},
}
}
}
class SynchronousDispatchFailureAdapter extends LlmAdapter {
constructor(private readonly error: Error) {
super()
}
stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
throw this.error
}
}
class IteratorResultGetterFailureAdapter extends LlmAdapter {
constructor(
private readonly field: 'done' | 'value',
private readonly error: Error,
) {
super()
}
stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
const result = this.field === 'done' ? {} : { done: false }
Object.defineProperty(result, this.field, { get: () => { throw this.error } })
return {
[Symbol.asyncIterator](): AsyncIterator<StreamChunk> {
return { next: () => Promise.resolve(result as unknown as IteratorResult<StreamChunk>) }
},
}
}
}
const streamListenerFailureCases: readonly [string, (ctx: Context) => void][] = [
['synchronous listener throw', (ctx) => {
ctx.on('llm/stream', () => { throw new Error('synchronous stream listener failed') })
}],
['invalid listener iterable', (ctx) => {
ctx.on('llm/stream', () => ({}) as AsyncIterable<StreamChunk>)
}],
['listener wrapper iteration failure', (ctx) => {
ctx.on('llm/stream', (_options, next) => (async function * () {
for await (const chunk of next()) {
yield chunk
throw new Error('stream listener wrapper failed')
}
})())
}],
]
async function harness(adapter?: LlmAdapter): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
if (adapter) ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
dispose()
resolve()
}
})
})
}
function send(agent: Agent): void {
agent.send([{ type: 'text', text: 'go' }])
}
function contextError(message = 'context too large'): LlmError {
return new LlmError(message, CONTEXT_WINDOW_EXCEEDED_CODE)
}
describe('agent post-step and request-error lifecycle', () => {
it('fires post-step after results, buffered context, and steering but before step/end', async () => {
const twoCalls: StreamChunk[] = [
{ type: 'block-start', index: 0, blockType: 'tool-call' },
{ type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('call-1'), name: 'work', arguments: '{}' } },
{ type: 'block-start', index: 1, blockType: 'tool-call' },
{ type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('call-2'), name: 'work', arguments: '{}' } },
{ type: 'usage', usage: { inputTokens: 10, outputTokens: 5 } },
{ type: 'finish', reason: { kind: 'tool-calls' } },
]
const adapter = new FailureScriptAdapter([twoCalls, textResponse('done')])
const ctx = await harness(adapter)
ctx.tools.register(defineTool({
name: 'work',
description: 'do work',
parameters: {},
async execute(_args, exec) {
if (exec.callId === CallId('call-2')) {
exec.agent?.steer([{ type: 'text', text: 'steered' }], { source: { kind: 'plugin', plugin: 'test' } })
}
return [{ type: 'text', text: 'worked' }]
},
}))
ctx.on('tools/post-execute', async (exec, _result): Promise<PostToolDecision> => ({
kind: 'accept',
additionalContexts: [{
content: [{ type: 'text', text: `context for ${exec.callId}` }],
source: { kind: 'plugin', plugin: 'test' },
}],
}))
const agent = ctx.agentLoop.create(SessionId('post-step-order'), { provider: 'mock', model: 'mock' })
const order: string[] = []
ctx.on('session/event', (_session, event) => {
if (
event.type === 'assistant/message' || event.type === 'tool/call'
|| event.type === 'tool/result' || event.type === 'context/message'
|| event.type === 'steering/message' || event.type === 'step/end'
) {
if (!('step' in event.data) || event.data.step === 1) order.push(event.type)
}
})
ctx.on('agent/post-step', (subject, turn, step, signal) => {
if (subject !== agent || step !== 1) return
expect({ turn, step, aborted: signal.aborted }).toEqual({ turn: 1, step: 1, aborted: false })
subject.inject([{ type: 'text', text: 'listener mutation' }], { source: { kind: 'plugin', plugin: 'post-step' } })
order.push('agent/post-step')
})
send(agent)
await waitForIdle(ctx, agent)
expect(order).toEqual([
'assistant/message',
'tool/call',
'tool/result',
'tool/call',
'tool/result',
'context/message',
'context/message',
'steering/message',
'context/message',
'agent/post-step',
'step/end',
])
})
it('fires post-step for max-tokens and lets cancellation override that success', async () => {
const adapter = new FailureScriptAdapter([maxTokensResponse('partial')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('cancel-post-step-max-tokens'), { provider: 'mock', model: 'mock' })
let entered!: () => void
const postStepEntered = new Promise<void>((resolve) => { entered = resolve })
ctx.on('agent/post-step', async (_agent, turn, step, signal) => {
expect({ turn, step }).toEqual({ turn: 1, step: 1 })
entered()
await new Promise<void>((resolve) => {
signal.addEventListener('abort', () => { resolve() }, { once: true })
})
})
send(agent)
const idle = waitForIdle(ctx, agent)
await postStepEntered
agent.cancel({ kind: 'user' })
await idle
expect(agent.session.events.find(event => event.type === 'assistant/message')).toMatchObject({
data: { usage: { inputTokens: 10, outputTokens: 7 } },
})
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'aborted' } },
})
})
it('closes the successful step as disposed when disposal lands during post-step', async () => {
const adapter = new FailureScriptAdapter([
toolCallResponse('dispose-call', 'work', {}),
textResponse('must not continue'),
])
const ctx = await harness(adapter)
ctx.tools.register(defineTool({
name: 'work',
description: 'do work',
parameters: {},
async execute() { return [{ type: 'text', text: 'worked' }] },
}))
const agent = ctx.agentLoop.create(SessionId('dispose-post-step'), { provider: 'mock', model: 'mock' })
let entered!: () => void
const postStepEntered = new Promise<void>((resolve) => { entered = resolve })
ctx.on('agent/post-step', async (_agent, turn, step, signal) => {
expect({ turn, step }).toEqual({ turn: 1, step: 1 })
entered()
await new Promise<void>((resolve) => {
signal.addEventListener('abort', () => { resolve() }, { once: true })
})
})
send(agent)
await postStepEntered
await ctx.fiber.dispose()
expect(adapter.requests).toHaveLength(1)
const boundaries = agent.session.events.filter(event =>
event.type === 'step/start' || event.type === 'step/end',
)
expect(boundaries.map(event => event.type)).toEqual(['step/start', 'step/end'])
expect(boundaries.map(event => event.data)).toEqual([
{ turn: 1, step: 1 },
{ turn: 1, step: 1 },
])
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'disposed' } },
})
})
it.each([
['thrown', contextError()],
['in-band', [{ type: 'finish', reason: { kind: 'error', message: 'too large', code: CONTEXT_WINDOW_EXCEEDED_CODE } }] satisfies StreamChunk[]],
] as const)('recovers a %s request failure in a new reconstructable step', async (_style, failure) => {
const adapter = new FailureScriptAdapter([failure, textResponse('recovered')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId(`recover-${_style}`), { provider: 'mock', model: 'mock' })
const attempts: number[] = []
ctx.on('agent/request-error', async (subject, turn, step, error, attempt) => {
expect(subject).toBe(agent)
expect({ turn, step, code: error.code }).toEqual({ turn: 1, step: 1, code: CONTEXT_WINDOW_EXCEEDED_CODE })
attempts.push(attempt)
subject.session.append('context/message', {
content: [{ type: 'text', text: 'RECOVERY SURFACE MUTATION' }],
source: { kind: 'plugin', plugin: 'test-recovery' },
}, { surfaceOp: 'append' })
return { action: 'retry' }
})
send(agent)
await waitForIdle(ctx, agent)
expect(attempts).toEqual([0])
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('RECOVERY SURFACE MUTATION')
const starts = agent.session.events.filter(event => event.type === 'step/start')
const ends = agent.session.events.filter(event => event.type === 'step/end')
expect(starts.map(event => event.data.step)).toEqual([1, 2])
expect(ends.map(event => event.data.step)).toEqual([1, 2])
const recovery = agent.session.events.find(event => event.type === 'context/message')!
expect(ends[0]!.seq).toBeLessThan(recovery.seq)
expect(recovery.seq).toBeLessThan(starts[1]!.seq)
})
it.each(streamListenerFailureCases)('does not offer %s to request recovery', async (_name, install) => {
const ctx = await harness(new FailureScriptAdapter([textResponse('unused')]))
const agent = ctx.agentLoop.create(SessionId(`stream-plugin-${_name.replaceAll(' ', '-')}`), { provider: 'mock', model: 'mock' })
let recoveries = 0
install(ctx)
ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => {
recoveries += 1
return next()
})
send(agent)
await waitForIdle(ctx, agent)
expect(recoveries).toBe(0)
expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } })
})
it('does not offer a nested model-call failure as the outer request failure', async () => {
const outer = new FailureScriptAdapter([textResponse('outer adapter must not run')])
const nested = new FailureScriptAdapter([contextError('nested overflow')])
const ctx = await harness(outer)
ctx.llm.registerAdapter(['nested'], nested)
ctx.on('llm/stream', (options, next) => {
if (options.provider !== 'mock') return next()
return (async function* () {
yield* ctx.llm.stream({
provider: 'nested',
model: 'nested',
messages: [],
...options.signal === undefined ? {} : { signal: options.signal },
})
yield* next()
})()
})
const agent = ctx.agentLoop.create(SessionId('nested-stream-not-recoverable'), { provider: 'mock', model: 'mock' })
let recoveries = 0
ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => {
recoveries += 1
return next()
})
send(agent)
await waitForIdle(ctx, agent)
expect(nested.requests).toHaveLength(1)
expect(outer.requests).toHaveLength(0)
expect(recoveries).toBe(0)
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'error', message: 'nested overflow', code: CONTEXT_WINDOW_EXCEEDED_CODE } },
})
})
it.each(['prompt-submit', 'prompt-assembly', 'pre-step', 'request'] as const)(
'does not offer %s middleware failures to request recovery',
async (boundary) => {
const adapter = new FailureScriptAdapter([textResponse('unused')])
const ctx = await harness(adapter)
if (boundary === 'prompt-submit') {
ctx.on('agent/prompt-submit', () => { throw new Error('prompt submit failed') })
} else if (boundary === 'prompt-assembly') {
ctx.on('system-prompt/assemble', () => { throw new Error('prompt assembly failed') })
} else if (boundary === 'pre-step') {
ctx.on('agent/pre-step', () => { throw new Error('pre-step failed') })
} else {
ctx.on('agent/request', () => { throw new Error('request middleware failed') })
}
const agent = ctx.agentLoop.create(SessionId(`${boundary}-not-recoverable`), { provider: 'mock', model: 'mock' })
let recoveries = 0
ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => {
recoveries += 1
return next()
})
send(agent)
await waitForIdle(ctx, agent)
expect(recoveries).toBe(0)
expect(adapter.requests).toHaveLength(0)
expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } })
},
)
it('does not offer result, tool, or post-step plugin failures to request recovery', async () => {
for (const failure of ['result', 'tool', 'post-step'] as const) {
const adapter = new FailureScriptAdapter([
failure === 'tool' ? toolCallResponse(`call-${failure}`, 'work', {}) : textResponse('done'),
...(failure === 'tool' ? [textResponse('done')] : []),
])
const ctx = await harness(adapter)
if (failure === 'result') ctx.on('agent/step-result', () => { throw new Error('result failed') })
if (failure === 'post-step') ctx.on('agent/post-step', () => { throw new Error('post-step failed') })
if (failure === 'tool') {
vi.spyOn(ctx.tools, 'execute').mockRejectedValue(new Error('tool service failed'))
}
const agent = ctx.agentLoop.create(SessionId(`${failure}-not-recoverable`), { provider: 'mock', model: 'mock' })
let recoveries = 0
ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => {
recoveries += 1
return next()
})
send(agent)
await waitForIdle(ctx, agent)
expect(recoveries, failure).toBe(0)
}
})
it.each([
['synchronous dispatch', (error: Error) => new SynchronousDispatchFailureAdapter(error)],
['done getter', (error: Error) => new IteratorResultGetterFailureAdapter('done', error)],
['value getter', (error: Error) => new IteratorResultGetterFailureAdapter('value', error)],
] as const)('preserves original Error identity for adapter %s', async (_name, makeAdapter) => {
const original = contextError(`${_name} overflow`)
const ctx = await harness(makeAdapter(original))
const agent = ctx.agentLoop.create(SessionId(`identity-${_name.replaceAll(' ', '-')}`), { provider: 'mock', model: 'mock' })
let seen: Error | undefined
ctx.on('agent/request-error', async (_agent, _turn, _step, error, _attempt, _signal, next) => {
seen = error
return next()
})
send(agent)
await waitForIdle(ctx, agent)
expect(seen).toBe(original)
})
it('classifies iterator construction and explicit NO_ADAPTER as model-request failures', async () => {
for (const scenario of ['iterator', 'no-adapter'] as const) {
const ctx = scenario === 'iterator' ? await harness(new IteratorConstructionFailureAdapter()) : await harness()
const agent = ctx.agentLoop.create(SessionId(`request-boundary-${scenario}`), { provider: 'mock', model: 'mock' })
let seen = ''
ctx.on('agent/request-error', async (_agent, _turn, _step, error, _attempt, _signal, next) => {
seen = error.code ?? ''
return next()
})
send(agent)
await waitForIdle(ctx, agent)
expect(seen).toBe(scenario === 'iterator' ? 'ITERATOR_CONSTRUCTION' : 'NO_ADAPTER')
}
})
it('tracks consecutive retry attempts and resets after a successful request', async () => {
const capped = new FailureScriptAdapter([contextError('first overflow'), contextError('second overflow')])
const cappedCtx = await harness(capped)
const cappedAgent = cappedCtx.agentLoop.create(SessionId('retry-cap'), { provider: 'mock', model: 'mock' })
const cappedAttempts: number[] = []
cappedCtx.on('agent/request-error', async (_agent, _turn, _step, _error, attempt, _signal, next) => {
cappedAttempts.push(attempt)
return attempt < 1 ? { action: 'retry' } : next()
})
send(cappedAgent)
await waitForIdle(cappedCtx, cappedAgent)
expect(cappedAttempts).toEqual([0, 1])
const reset = new FailureScriptAdapter([
contextError('first overflow'),
toolCallResponse('retry-reset-call', 'work', {}),
contextError('later overflow'),
])
const resetCtx = await harness(reset)
resetCtx.tools.register(defineTool({
name: 'work',
description: 'continue',
parameters: {},
async execute() { return [{ type: 'text', text: 'worked' }] },
}))
const resetAgent = resetCtx.agentLoop.create(SessionId('retry-reset'), { provider: 'mock', model: 'mock' })
const resetAttempts: { step: number; attempt: number }[] = []
resetCtx.on('agent/request-error', async (_agent, _turn, step, _error, attempt, _signal, next) => {
resetAttempts.push({ step, attempt })
return resetAttempts.length === 1 ? { action: 'retry' } : next()
})
send(resetAgent)
await waitForIdle(resetCtx, resetAgent)
expect(resetAttempts).toEqual([{ step: 1, attempt: 0 }, { step: 3, attempt: 0 }])
})
it('preserves the original provider error when recovery throws', async () => {
const adapter = new FailureScriptAdapter([contextError('original overflow')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('recovery-throws'), { provider: 'mock', model: 'mock' })
ctx.on('agent/request-error', () => { throw new Error('recovery exploded') })
send(agent)
await waitForIdle(ctx, agent)
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'error', message: 'original overflow', code: CONTEXT_WINDOW_EXCEEDED_CODE } },
})
})
it.each(['cancel', 'dispose'] as const)('keeps %s live through request recovery', async (action) => {
const adapter = new FailureScriptAdapter([contextError()])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId(`${action}-recovery`), { provider: 'mock', model: 'mock' })
let entered!: () => void
const recoveryEntered = new Promise<void>((resolve) => { entered = resolve })
ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, signal) => {
entered()
await new Promise<void>((resolve) => {
signal.addEventListener('abort', () => { resolve() }, { once: true })
})
return { action: 'retry' }
})
send(agent)
const idle = waitForIdle(ctx, agent)
await recoveryEntered
if (action === 'cancel') {
agent.cancel({ kind: 'user' })
await idle
} else {
await ctx.fiber.dispose()
}
expect(adapter.requests).toHaveLength(1)
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: action === 'cancel' ? { kind: 'aborted' } : { kind: 'disposed' } },
})
})
})

103
packages/core/agent-loop/tests/resume.spec.ts
View File

@@ -8,10 +8,10 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse } from './mock-adapter.ts'
const dirs: string[] = []
@@ -30,7 +30,6 @@ async function mountPersistentHarness(root: string, adapter: MockAdapter): Promi
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(SessionPersistenceJsonl, { root })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -52,7 +51,7 @@ async function persistSession(sessionId: SessionId): Promise<string> {
return root
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') { dispose(); resolve() }
@@ -76,7 +75,7 @@ function throwUnknown(value: unknown): never {
throw value
}
describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
describe('the session-persistence Agent Note: AgentLoop factory create/resume', () => {
it('normalizes a non-Error resume publication failure for rollback and rethrows it', async () => {
const sessionId = SessionId('unknown-resume-failure-s')
const root = await persistSession(sessionId)
@@ -85,11 +84,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
ctx.on('session/created', () => throwUnknown(failure))
await expect(ctx.agents.resume({
agentId: AgentId('unknown-resume-failure'),
resumeSessionId: sessionId,
})).rejects.toBe(failure)
expect(ctx.agents.get(AgentId('unknown-resume-failure'))).toBeUndefined()
expect(ctx.agents.get(SessionId('unknown-resume-failure'))).toBeUndefined()
expect(ctx.sessions.get(sessionId)).toBeUndefined()
await ctx.fiber.dispose()
})
@@ -97,27 +95,26 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
it('createAgent uses the caller-supplied sessionId (not ${id}-session)', async () => {
const adapter = new MockAdapter([textResponse('hi')])
const { ctx } = await persistentHarness(adapter)
const { agent } = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('custom-session'), meta: { cwd: '/w' } })
const { agent } = await ctx.agents.create({ sessionId: SessionId('custom-session'), meta: { cwd: '/w' } })
expect(agent.session.id).toBe('custom-session')
expect(agent.session.header.cwd).toBe('/w')
await ctx.fiber.dispose()
})
it('createAgent rejects a duplicate agent id BEFORE creating the session (no orphan)', async () => {
it('createAgent rejects a duplicate identity without orphaning a session', async () => {
const adapter = new MockAdapter([textResponse('hi')])
const { ctx } = await persistentHarness(adapter)
await ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-a') })
// A second create with the SAME agent id but a fresh session id must reject
// up front — and must NOT leave an orphaned 'sess-b' session behind.
await expect(ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-b') })).rejects.toThrow(/already registered/)
expect(ctx.sessions.get(SessionId('sess-b'))).toBeUndefined()
const sessionId = SessionId('sess-a')
await ctx.agents.create({ sessionId })
await expect(ctx.agents.create({ sessionId })).rejects.toThrow(/already exists/)
expect(ctx.sessions.list()).toHaveLength(1)
await ctx.fiber.dispose()
})
it('createAgent works without meta (no cwd)', async () => {
const adapter = new MockAdapter([textResponse('hi')])
const { ctx } = await persistentHarness(adapter)
const { agent } = await ctx.agents.create({ agentId: AgentId('a-nometa'), sessionId: SessionId('nometa-session') })
const { agent } = await ctx.agents.create({ sessionId: SessionId('nometa-session') })
expect(agent.session.id).toBe('nometa-session')
expect(agent.session.header.cwd).toBeUndefined()
await ctx.fiber.dispose()
@@ -127,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
// Lifecycle 1: create a no-cwd session and run a turn.
const adapter1 = new MockAdapter([textResponse('a')])
const { ctx: ctx1, root } = await persistentHarness(adapter1)
const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent
const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent
a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
await waitForIdle(ctx1, a1)
await ctx1.fiber.dispose()
@@ -140,11 +137,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentExecutionProvider)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent
const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent
expect(a2.session.header.cwd).toBeUndefined()
await ctx2.fiber.dispose()
})
@@ -155,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
const { ctx: ctx1, root } = await persistentHarness(adapter1)
const sources1: string[] = []
ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source))
const a1 = (await ctx1.agents.create({ agentId: AgentId('s'), sessionId: SessionId('start-sess') })).agent as ReactLoopAgent
const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent
expect(sources1).toEqual(['startup'])
a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
await waitForIdle(ctx1, a1)
@@ -169,13 +165,12 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentExecutionProvider)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const sources2: string[] = []
ctx2.on('agent/session-start', (_agent, source) => void sources2.push(source))
await ctx2.agents.resume({ agentId: AgentId('s'), resumeSessionId: SessionId('start-sess') })
await ctx2.agents.resume({ resumeSessionId: SessionId('start-sess') })
expect(sources2).toEqual(['resume'])
await ctx2.fiber.dispose()
})
@@ -190,7 +185,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
ctx.on('session/created', (session) => {
expect(ctx.sessions.get(session.id)).toBe(session)
expect(ctx.agents.get(AgentId('resumed-atomic'))?.session).toBe(session)
expect(ctx.agents.get(sessionId)?.session).toBe(session)
order.push('session/created')
})
ctx.on('agent/created', (agent) => {
@@ -203,11 +198,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
})
const resuming = ctx.agents.resume({
agentId: AgentId('resumed-atomic'),
resumeSessionId: sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
setup: async (agentCtx) => {
expect(agentCtx.agent?.id).toBe(AgentId('resumed-atomic'))
expect(agentCtx.agent?.id).toBe(sessionId)
expect(agentCtx.agent?.session.events).toHaveLength(2)
agentCtx.on('session/created', () => void order.push('setup-listener:session/created'))
agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created'))
@@ -219,7 +213,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
})
await setupStarted.promise
expect(ctx.agents.get(AgentId('resumed-atomic'))).toBeUndefined()
expect(ctx.agents.get(sessionId)).toBeUndefined()
expect(ctx.sessions.get(sessionId)).toBeUndefined()
expect(order).toEqual(['setup:start'])
@@ -240,17 +234,15 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
it('successful resume disposal retires its caller-owned transaction effects', async () => {
const sessionId = SessionId('resume-retired-effects-s')
const agentId = AgentId('resume-retired-effects')
const root = await persistSession(sessionId)
const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')]))
const handle = await ctx.agents.resume({
agentId,
resumeSessionId: sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
})
const transactionLabels = [
`agentLoop.owner(${agentId})`,
`agentLoop.lifecycle(${agentId})`,
`agentLoop.owner(${sessionId})`,
`agentLoop.lifecycle(${sessionId})`,
]
expect(ctx.fiber.getEffects().map(effect => effect.label)).toEqual(expect.arrayContaining(transactionLabels))
@@ -259,7 +251,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx.fiber.dispose()
})
it('resume setup rejection publishes nothing, unwinds, and releases both identities', async () => {
it('resume setup rejection publishes nothing, unwinds, and releases the identity', async () => {
const sessionId = SessionId('resume-setup-reject')
const root = await persistSession(sessionId)
const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')]))
@@ -269,7 +261,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
ctx.on('agent/session-start', () => void published.push('agent/session-start'))
await expect(ctx.agents.resume({
agentId: AgentId('resume-reject'),
resumeSessionId: sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
setup: async () => {
@@ -279,10 +270,9 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
})).rejects.toThrow('resume setup failed')
expect(published).toEqual([])
expect(ctx.agents.get(AgentId('resume-reject'))).toBeUndefined()
expect(ctx.agents.get(sessionId)).toBeUndefined()
expect(ctx.sessions.get(sessionId)).toBeUndefined()
const retry = await ctx.agents.resume({
agentId: AgentId('resume-reject'),
resumeSessionId: sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -303,7 +293,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
let resuming!: ReturnType<typeof ctx.agents.resume>
const owner = await ctx.plugin(Object.assign((inner: Context) => {
resuming = inner.agents.resume({
agentId: AgentId('resume-owner-race'),
resumeSessionId: sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
setup: async () => {
@@ -317,7 +306,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await owner.dispose()
await expect(resuming).rejects.toThrow(/owner disposed during setup/)
expect(published).toEqual([])
expect(ctx.agents.get(AgentId('resume-owner-race'))).toBeUndefined()
expect(ctx.agents.get(sessionId)).toBeUndefined()
expect(ctx.sessions.get(sessionId)).toBeUndefined()
gate.resolve(undefined)
@@ -326,9 +315,8 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx.fiber.dispose()
})
it('owner unload aborts a never-settling persistence load, releases identities, and blocks late publication', async () => {
it('owner unload aborts a never-settling persistence load, releases the identity, and blocks late publication', async () => {
const sessionId = SessionId('resume-load-owner-unload')
const agentId = AgentId('resume-load-race')
const root = await persistSession(sessionId)
const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')]))
const snapshot = await ctx.sessionPersistence.load(sessionId)
@@ -352,19 +340,19 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
let resuming!: ReturnType<typeof ctx.agents.resume>
const owner = await ctx.plugin(Object.assign((inner: Context) => {
resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
resuming = inner.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
}, { inject: ['agents'] }))
await loadStarted.promise
const rejection = expect(promptly(resuming)).rejects.toThrow(/owner disposed during setup/)
await promptly(owner.dispose())
expect(published).toEqual([])
expect(ctx.agents.get(agentId)).toBeUndefined()
expect(ctx.agents.get(sessionId)).toBeUndefined()
expect(ctx.sessions.get(sessionId)).toBeUndefined()
// owner.dispose() awaited transaction settlement, so the same identities
// can be reused before awaiting the public rejection.
const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } }))
const retry = await promptly(ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } }))
await rejection
expect(loads).toBe(2)
expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start'])
@@ -374,7 +362,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
lateLoad.resolve(structuredClone(snapshot))
await Promise.resolve()
await Promise.resolve()
expect(ctx.agents.get(agentId)).toBe(retry.agent)
expect(ctx.agents.get(sessionId)).toBe(retry.agent)
expect(ctx.sessions.get(sessionId)).toBe(retry.agent.session)
expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start'])
@@ -384,7 +372,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
it('AgentLoop unload aborts persistence load and awaits wrapper settlement', async () => {
const sessionId = SessionId('resume-load-factory-unload')
const agentId = AgentId('resume-load-factory-race')
const root = await persistSession(sessionId)
const ctx = new Context()
await ctx.plugin(LlmService)
@@ -392,7 +379,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
const loopFiber = await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(SessionPersistenceJsonl, { root })
ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('next')]))
@@ -409,14 +395,14 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
ctx.on('session/created', () => void published.push('session/created'))
ctx.on('agent/created', () => void published.push('agent/created'))
const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
const resuming = ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
await loadStarted.promise
const rejection = expect(promptly(resuming)).rejects.toThrow(/agent loop is not active/)
await promptly(loopFiber.dispose())
await rejection
expect(published).toEqual([])
expect(ctx.agents.get(agentId)).toBeUndefined()
expect(ctx.agents.get(sessionId)).toBeUndefined()
expect(ctx.sessions.get(sessionId)).toBeUndefined()
lateLoad.resolve(structuredClone(snapshot))
await Promise.resolve()
@@ -425,7 +411,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx.fiber.dispose()
})
it('resume of a forked session preserves the parentSession lineage and seed boundary in the header', async () => {
it('resume of a forked session preserves the lineage, seed boundary, and delegation depth in the header', async () => {
// Lifecycle 1: persist a FORKED session (carries parentSession + seedLength
// in its header) by creating it with a complete-turn seed — the write path
// materializes the fork (header + seed) on disk.
@@ -437,7 +423,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
const { ctx: ctx1, root } = await persistentHarness(adapter1)
const forked = ctx1.sessions.create(SessionId('forked-sess'), {
seed,
meta: { cwd: '/w', parentSession: SessionId('parent-sess'), seedLength: seed.length },
meta: { cwd: '/w', parentSession: SessionId('parent-sess'), seedLength: seed.length, delegationDepth: 1 },
})
await ctx1.parallel('session/flush', forked)
await ctx1.fiber.dispose()
@@ -454,14 +440,16 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentExecutionProvider)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent
const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent
expect(a2.session.header.parentSession).toBe('parent-sess')
expect(a2.session.header.cwd).toBe('/w')
expect(a2.session.header.seedLength).toBe(seed.length)
// The recursion budget survives resume — a dropped depth would let a
// resumed child delegate as if it were top-level.
expect(a2.session.header.delegationDepth).toBe(1)
await ctx2.fiber.dispose()
})
@@ -470,7 +458,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
// clean disposal follows, so disk presence proves its own checkpoint ran.
const adapter1 = new MockAdapter([textResponse('answer')])
const { ctx: ctx1, root } = await persistentHarness(adapter1)
const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent
const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent
a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
await waitForIdle(ctx1, a1)
a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } })
@@ -493,7 +481,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
// survive persistence and resume.
const adapter1 = new MockAdapter([textResponse('answer')])
const { ctx: ctx1, root } = await persistentHarness(adapter1)
const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent
const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent
a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
await waitForIdle(ctx1, a1)
a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } })
@@ -508,11 +496,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentExecutionProvider)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent
const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent
const flat = JSON.stringify(a2.session.deriveMessages())
expect(flat).toContain('background task 42 finished')
await ctx2.fiber.dispose()
@@ -522,7 +509,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
// Lifecycle 1: run one full turn, persisting it.
const adapter1 = new MockAdapter([textResponse('first answer')])
const { ctx: ctx1, root } = await persistentHarness(adapter1)
const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent
const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent
a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } })
await waitForIdle(ctx1, a1)
const events1 = [...a1.session.events]
@@ -538,12 +525,11 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentExecutionProvider)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const a2 = (await ctx2.agents.resume({ agentId: AgentId('main'), resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent
const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent
// The resumed session carries the prior history…
expect(a2.session.id).toBe('sess-resume')
expect(a2.session.events.length).toBe(events1.length)
@@ -569,10 +555,9 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
await expect(ctx.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nope') }))
await expect(ctx.agents.resume({ resumeSessionId: SessionId('nope') }))
.rejects.toThrow(/session persistence is not configured/)
await ctx.fiber.dispose()
})

221
packages/core/agent-loop/tests/scope-lifecycle.spec.ts
View File

@@ -4,11 +4,11 @@ import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId, agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent'
import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { scopeOf } from '@deepseek-ai/dsh-scope'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
import { MockAdapter, textResponse } from './mock-adapter.ts'
@@ -19,7 +19,6 @@ async function harnessWithLoop(adapter: MockAdapter = new MockAdapter([textRespo
await ctx.plugin(SystemPrompt, { persona: 'You are the deployment.' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
const loopFiber = await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return { ctx, loopFiber }
@@ -29,7 +28,7 @@ async function harness(adapter: MockAdapter = new MockAdapter([textResponse('ok'
return (await harnessWithLoop(adapter)).ctx
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -59,33 +58,31 @@ function disposeCurrentLifecycle(ownerCtx: Context): void {
}
describe('agent scope lifecycle', () => {
it('rejects an already-aborted creation signal before publishing either identity', async () => {
it('rejects an already-aborted creation signal before publishing either object', async () => {
const ctx = await harness()
const reason = new Error('cancelled before creation')
const controller = new AbortController()
controller.abort(reason)
await expect(ctx.agents.create({
agentId: AgentId('pre-aborted'),
sessionId: SessionId('pre-aborted-s'),
signal: controller.signal,
})).rejects.toBe(reason)
expect(ctx.agents.get(AgentId('pre-aborted'))).toBeUndefined()
expect(ctx.agents.get(SessionId('pre-aborted-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('pre-aborted-s'))).toBeUndefined()
const valueController = new AbortController()
valueController.abort('plain cancellation reason')
await expect(ctx.agents.create({
agentId: AgentId('pre-aborted-value'),
sessionId: SessionId('pre-aborted-value-s'),
signal: valueController.signal,
})).rejects.toMatchObject({
message: 'agent "pre-aborted-value" creation aborted',
message: 'agent "pre-aborted-value-s" creation aborted',
cause: 'plain cancellation reason',
})
expect(ctx.agents.get(AgentId('pre-aborted-value'))).toBeUndefined()
expect(ctx.agents.get(SessionId('pre-aborted-value-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('pre-aborted-value-s'))).toBeUndefined()
await ctx.fiber.dispose()
})
@@ -102,12 +99,11 @@ describe('agent scope lifecycle', () => {
})
await expect(ctx.agents.create({
agentId: AgentId('prepare-abort'),
sessionId: SessionId('prepare-abort-s'),
signal: controller.signal,
})).rejects.toBe(reason)
expect(ctx.agents.get(AgentId('prepare-abort'))).toBeUndefined()
expect(ctx.agents.get(SessionId('prepare-abort-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('prepare-abort-s'))).toBeUndefined()
await ctx.fiber.dispose()
})
@@ -126,7 +122,7 @@ describe('agent scope lifecycle', () => {
thrown = createFailure
let createCaught: unknown
try {
ctx.agentLoop.create(AgentId('unknown-create'))
ctx.agentLoop.create(SessionId('unknown-create'))
} catch (error: unknown) {
createCaught = error
}
@@ -135,28 +131,45 @@ describe('agent scope lifecycle', () => {
const ownedFailure = { source: 'createAgent' }
thrown = ownedFailure
await expect(ctx.agents.create({
agentId: AgentId('unknown-owned-create'),
sessionId: SessionId('unknown-owned-create-s'),
})).rejects.toBe(ownedFailure)
expect(ctx.agents.get(AgentId('unknown-create'))).toBeUndefined()
expect(ctx.agents.get(AgentId('unknown-owned-create'))).toBeUndefined()
expect(ctx.agents.get(SessionId('unknown-create'))).toBeUndefined()
expect(ctx.agents.get(SessionId('unknown-owned-create-s'))).toBeUndefined()
await ctx.fiber.dispose()
})
it('wires agent.ctx: tagged with the agent, DX field set, ctx.agent safe elsewhere', async () => {
const ctx = await harness()
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
expect(scopeOf(agent.ctx)).toBe(agent)
expect(agent.ctx.agent).toBe(agent)
// The root accessor default: a plain context answers undefined, not a throw.
expect(ctx.agent).toBeUndefined()
await ctx.agents.get(AgentId('a1'))?.whenIdle()
await ctx.agents.get(SessionId('a1'))?.whenIdle()
})
it('records agents created through an agent context as non-root runtime children', async () => {
const ctx = await harness()
const root = await ctx.agents.create({
sessionId: SessionId('runtime-root'),
agentOptions: { model: 'mock' },
})
const child = await root.agent.ctx.agents.create({
sessionId: SessionId('runtime-child'),
agentOptions: { model: 'mock' },
})
expect(ctx.agents.list()).toEqual([root.agent, child.agent])
expect(ctx.agents.roots()).toEqual([root.agent])
await child.dispose()
await root.dispose()
})
it('scoped registrations live in the agent world and die with the agent', async () => {
const ctx = await harness()
const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } })
const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } })
const { agent } = handle
agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' })
agent.ctx.tools.register({
@@ -181,8 +194,8 @@ describe('agent scope lifecycle', () => {
it('agent.ctx listeners hear only their own agent (scoped dispatch end to end)', async () => {
const ctx = await harness(new MockAdapter([textResponse('one'), textResponse('two')]))
const a = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' })
const b = ctx.agentLoop.create(AgentId('b'), { provider: 'mock', model: 'mock' })
const a = ctx.agentLoop.create(SessionId('a'), { provider: 'mock', model: 'mock' })
const b = ctx.agentLoop.create(SessionId('b'), { provider: 'mock', model: 'mock' })
const heard: string[] = []
a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`))
@@ -212,7 +225,6 @@ describe('agent scope lifecycle', () => {
})
const handle = await ctx.agents.create({
agentId: AgentId('child'),
sessionId: SessionId('child-s'),
agentOptions: { provider: 'mock', model: 'mock' },
setup: async (agentCtx) => {
@@ -226,14 +238,14 @@ describe('agent scope lifecycle', () => {
await handle.dispose()
})
it('keeps both identities unpublished until async setup completes, then announces in order', async () => {
it('keeps both objects unpublished until async setup completes, then announces in order', async () => {
const ctx = await harness()
const gate = Promise.withResolvers<undefined>()
const setupStarted = Promise.withResolvers<undefined>()
const order: string[] = []
ctx.on('session/created', (session) => {
expect(ctx.sessions.get(session.id)).toBe(session)
expect(ctx.agents.get(AgentId('atomic'))?.session).toBe(session)
expect(ctx.agents.get(session.id)?.session).toBe(session)
order.push('session/created')
})
ctx.on('agent/created', () => void order.push('agent/created'))
@@ -241,11 +253,10 @@ describe('agent scope lifecycle', () => {
const acceptedOptions = { provider: 'mock', model: 'mock' }
const creating = ctx.agents.create({
agentId: AgentId('atomic'),
sessionId: SessionId('atomic-s'),
sessionId: SessionId('atomic'),
agentOptions: acceptedOptions,
setup: async (agentCtx) => {
expect(agentCtx.agent?.id).toBe(AgentId('atomic'))
expect(agentCtx.agent?.id).toBe(SessionId('atomic'))
agentCtx.on('session/created', () => void order.push('setup-listener:session/created'))
agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created'))
order.push('setup:start')
@@ -255,8 +266,8 @@ describe('agent scope lifecycle', () => {
},
})
await setupStarted.promise
expect(ctx.agents.get(AgentId('atomic'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined()
expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('atomic'))).toBeUndefined()
expect(order).toEqual(['setup:start'])
gate.resolve(undefined)
const handle = await creating
@@ -283,16 +294,14 @@ describe('agent scope lifecycle', () => {
if (started === 2) bothStarted.resolve(undefined)
await gate.promise
}
const agentId = AgentId('concurrent-final-enter')
const sessionId = SessionId('concurrent-final-enter')
const first = ctx.agents.create({
agentId,
sessionId: SessionId('concurrent-final-enter-a'),
sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
setup,
})
const second = ctx.agents.create({
agentId,
sessionId: SessionId('concurrent-final-enter-b'),
sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
setup,
})
@@ -306,7 +315,7 @@ describe('agent scope lifecycle', () => {
const rejected = outcomes.filter((outcome): outcome is PromiseRejectedResult => outcome.status === 'rejected')
expect(fulfilled).toHaveLength(1)
expect(rejected).toHaveLength(1)
expect(String(rejected[0]!.reason)).toMatch(/already registered/)
expect(String(rejected[0]!.reason)).toMatch(/already exists/)
expect(ctx.agents.list()).toEqual([fulfilled[0]!.value.agent])
expect(ctx.sessions.list()).toEqual([fulfilled[0]!.value.agent.session])
@@ -320,7 +329,6 @@ describe('agent scope lifecycle', () => {
const pendingController = new AbortController()
const setupStarted = Promise.withResolvers<undefined>()
const pending = ctx.agents.create({
agentId: AgentId('signal-pending'),
sessionId: SessionId('signal-pending-s'),
agentOptions: { provider: 'mock', model: 'mock' },
signal: pendingController.signal,
@@ -332,12 +340,11 @@ describe('agent scope lifecycle', () => {
await setupStarted.promise
pendingController.abort(new Error('cancel pending creation'))
await expect(pending).rejects.toThrow('cancel pending creation')
expect(ctx.agents.get(AgentId('signal-pending'))).toBeUndefined()
expect(ctx.agents.get(SessionId('signal-pending-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('signal-pending-s'))).toBeUndefined()
const liveController = new AbortController()
const live = await ctx.agents.create({
agentId: AgentId('signal-live'),
sessionId: SessionId('signal-live-s'),
agentOptions: { provider: 'mock', model: 'mock' },
signal: liveController.signal,
@@ -360,7 +367,6 @@ describe('agent scope lifecycle', () => {
let creating!: ReturnType<typeof ctx.agents.create>
const owner = await ctx.plugin(Object.assign((inner: Context) => {
creating = inner.agents.create({
agentId: AgentId('owner-race'),
sessionId: SessionId('owner-race-s'),
agentOptions: { provider: 'mock', model: 'mock' },
setup: async () => {
@@ -374,7 +380,7 @@ describe('agent scope lifecycle', () => {
await owner.dispose()
await expect(creating).rejects.toThrow(/owner disposed during setup/)
expect(published).toEqual([])
expect(ctx.agents.get(AgentId('owner-race'))).toBeUndefined()
expect(ctx.agents.get(SessionId('owner-race-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('owner-race-s'))).toBeUndefined()
// Let the losing callback settle; Promise.race already observes it.
gate.resolve(undefined)
@@ -388,7 +394,6 @@ describe('agent scope lifecycle', () => {
let creating2!: ReturnType<typeof ctx.agents.create>
const owner2 = await ctx.plugin(Object.assign((inner: Context) => {
creating2 = inner.agents.create({
agentId: AgentId('owner-race-2'),
sessionId: SessionId('owner-race-s-2'),
agentOptions: { provider: 'mock', model: 'mock' },
setup: async () => {
@@ -402,7 +407,7 @@ describe('agent scope lifecycle', () => {
const unload2 = owner2.dispose()
await expect(creating2).rejects.toThrow(/owner disposed during setup/)
await unload2
expect(ctx.agents.get(AgentId('owner-race-2'))).toBeUndefined()
expect(ctx.agents.get(SessionId('owner-race-s-2'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('owner-race-s-2'))).toBeUndefined()
})
@@ -415,7 +420,6 @@ describe('agent scope lifecycle', () => {
ctx.on('agent/created', () => void published.push('agent/created'))
const creating = ctx.agents.create({
agentId: AgentId('factory-setup-race'),
sessionId: SessionId('factory-setup-race-s'),
agentOptions: { provider: 'mock', model: 'mock' },
setup: async () => {
@@ -428,7 +432,7 @@ describe('agent scope lifecycle', () => {
await loopFiber.dispose()
await expect(creating).rejects.toThrow(/agent loop is not active/)
expect(published).toEqual([])
expect(ctx.agents.get(AgentId('factory-setup-race'))).toBeUndefined()
expect(ctx.agents.get(SessionId('factory-setup-race-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('factory-setup-race-s'))).toBeUndefined()
gate.resolve(undefined)
@@ -446,7 +450,6 @@ describe('agent scope lifecycle', () => {
})
const creating = ctx.agents.create({
agentId: AgentId('factory-scope-race'),
sessionId: SessionId('factory-scope-race-s'),
agentOptions: { provider: 'mock', model: 'mock' },
setup: () => { setupCalls += 1 },
@@ -454,7 +457,7 @@ describe('agent scope lifecycle', () => {
await expect(creating).rejects.toThrow(/agent loop is not active/)
await loopFiber.dispose()
expect(setupCalls).toBe(0)
expect(ctx.agents.get(AgentId('factory-scope-race'))).toBeUndefined()
expect(ctx.agents.get(SessionId('factory-scope-race-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('factory-scope-race-s'))).toBeUndefined()
await ctx.fiber.dispose()
@@ -481,7 +484,6 @@ describe('agent scope lifecycle', () => {
const owner = ctx.plugin(Object.assign((inner: Context) => {
ownerFiber = inner.fiber
creating = inner.agents.create({
agentId: AgentId('caller-scope-race'),
sessionId: SessionId('caller-scope-race-s'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -497,7 +499,7 @@ describe('agent scope lifecycle', () => {
await ownerDisposal
await owner
expect(scopeFiber?.uid).toBeNull()
expect(ctx.agents.get(AgentId('caller-scope-race'))).toBeUndefined()
expect(ctx.agents.get(SessionId('caller-scope-race-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('caller-scope-race-s'))).toBeUndefined()
await owner.dispose()
await ctx.fiber.dispose()
@@ -513,17 +515,17 @@ describe('agent scope lifecycle', () => {
void loopFiber.dispose()
})
expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { provider: 'mock', model: 'mock' }))
expect(() => ctx.agentLoop.create(SessionId('config-scope-race'), { provider: 'mock', model: 'mock' }))
.toThrow(/agent loop is not active/)
await loopFiber.dispose()
expect(ctx.agents.get(AgentId('config-scope-race'))).toBeUndefined()
expect(ctx.agents.get(SessionId('config-scope-race'))).toBeUndefined()
expect(ctx.sessions.list()).toHaveLength(sessionsBefore)
await ctx.fiber.dispose()
})
it('synchronous create leaves no lifecycle state when session preparation fails', async () => {
const ctx = await harness()
const id = AgentId('config-prepare-failure')
const id = SessionId('config-prepare-failure')
expect(() => ctx.agentLoop.create(id, { provider: 'mock', model: 'mock' }, { cwd: 'relative' }))
.toThrow(/absolute path/)
@@ -544,12 +546,11 @@ describe('agent scope lifecycle', () => {
})
await expect(ctx.agents.create({
agentId: AgentId('factory-scope-throw'),
sessionId: SessionId('factory-scope-throw-s'),
agentOptions: { provider: 'mock', model: 'mock' },
})).rejects.toThrow('scope preparation failed')
await loopFiber.dispose()
expect(ctx.agents.get(AgentId('factory-scope-throw'))).toBeUndefined()
expect(ctx.agents.get(SessionId('factory-scope-throw-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('factory-scope-throw-s'))).toBeUndefined()
await ctx.fiber.dispose()
@@ -558,23 +559,21 @@ describe('agent scope lifecycle', () => {
it('AgentLoop unload is a structural co-owner of every live programmatic agent', async () => {
const { ctx, loopFiber } = await harnessWithLoop()
const loop = ctx.agentLoop
const agentId = AgentId('factory-live')
const sessionId = SessionId('factory-live')
const handle = await ctx.agents.create({
agentId,
sessionId: SessionId('factory-live-s'),
agentOptions: { provider: 'mock', model: 'mock' },
})
await loopFiber.dispose()
expect(handle.agent.status).toBe('disposed')
expect(ctx.agents.get(agentId)).toBeUndefined()
expect(ctx.sessions.get(SessionId('factory-live-s'))).toBeUndefined()
expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([])
expect(ctx.agents.get(sessionId)).toBeUndefined()
expect(ctx.sessions.get(sessionId)).toBeUndefined()
expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([])
// The consumer handle shares the provider's completed quiescence boundary.
await handle.dispose()
await expect(loop.createAgent(ctx, {
agentId: AgentId('factory-inactive'),
sessionId: SessionId('factory-inactive-s'),
})).rejects.toThrow('agent loop is not active')
await ctx.fiber.dispose()
@@ -585,7 +584,6 @@ describe('agent scope lifecycle', () => {
let creating!: ReturnType<typeof ctx.agents.create>
const owner = await ctx.plugin(Object.assign((inner: Context) => {
creating = inner.agents.create({
agentId: AgentId('dependency-origin'),
sessionId: SessionId('dependency-origin-s'),
agentOptions: { provider: 'mock', model: 'mock' },
setup: (agentCtx) => {
@@ -625,7 +623,7 @@ describe('agent scope lifecycle', () => {
})
ctx.on('session/created', (session) => {
if (session.id !== SessionId('session-created-barrier-s')) return
const agent = ctx.agents.get(AgentId('session-created-barrier'))!
const agent = ctx.agents.get(SessionId('session-created-barrier-s'))!
expect(ctx.sessions.get(session.id)).toBe(session)
expect(agent.session).toBe(session)
agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') })
@@ -640,7 +638,6 @@ describe('agent scope lifecycle', () => {
const owner = await ctx.plugin(Object.assign((inner: Context) => {
ownerCtx = inner
creating = inner.agents.create({
agentId: AgentId('session-created-barrier'),
sessionId: SessionId('session-created-barrier-s'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -654,7 +651,7 @@ describe('agent scope lifecycle', () => {
'session-disposed',
'scope-disposed',
])
expect(ctx.agents.get(AgentId('session-created-barrier'))).toBeUndefined()
expect(ctx.agents.get(SessionId('session-created-barrier-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('session-created-barrier-s'))).toBeUndefined()
await ctx.fiber.dispose()
})
@@ -668,19 +665,19 @@ describe('agent scope lifecycle', () => {
if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-created')
})
ctx.on('agent/created', (agent) => {
if (agent.id !== AgentId('agent-created-barrier')) return
if (agent.id !== SessionId('agent-created-barrier-s')) return
lifecycle.push('agent-created:dispose')
disposeCurrentLifecycle(ownerCtx)
})
ctx.on('agent/created', (agent) => {
if (agent.id !== AgentId('agent-created-barrier')) return
if (agent.id !== SessionId('agent-created-barrier-s')) return
expect(ctx.agents.get(agent.id)).toBe(agent)
expect(ctx.sessions.get(agent.session.id)).toBe(agent.session)
agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') })
lifecycle.push('agent-created:observer')
})
ctx.on('agent/disposed', (agent) => {
if (agent.id === AgentId('agent-created-barrier')) lifecycle.push('agent-disposed')
if (agent.id === SessionId('agent-created-barrier-s')) lifecycle.push('agent-disposed')
})
ctx.on('session/disposed', (session) => {
if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-disposed')
@@ -689,7 +686,6 @@ describe('agent scope lifecycle', () => {
const owner = await ctx.plugin(Object.assign((inner: Context) => {
ownerCtx = inner
creating = inner.agents.create({
agentId: AgentId('agent-created-barrier'),
sessionId: SessionId('agent-created-barrier-s'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -705,7 +701,7 @@ describe('agent scope lifecycle', () => {
'session-disposed',
'scope-disposed',
])
expect(ctx.agents.get(AgentId('agent-created-barrier'))).toBeUndefined()
expect(ctx.agents.get(SessionId('agent-created-barrier-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('agent-created-barrier-s'))).toBeUndefined()
await ctx.fiber.dispose()
})
@@ -717,13 +713,12 @@ describe('agent scope lifecycle', () => {
let creating!: ReturnType<typeof ctx.agents.create>
ctx.on('agent/session-start', agent => void starts.push(agent.id))
ctx.on('agent/created', (agent) => {
if (agent.id === AgentId('listener-dispose')) void ownerCtx.fiber.dispose()
if (agent.id === SessionId('listener-dispose-s')) void ownerCtx.fiber.dispose()
})
const owner = await ctx.plugin(Object.assign((inner: Context) => {
ownerCtx = inner
creating = inner.agents.create({
agentId: AgentId('listener-dispose'),
sessionId: SessionId('listener-dispose-s'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -732,7 +727,7 @@ describe('agent scope lifecycle', () => {
await expect(creating).rejects.toThrow(/owner disposed during setup/)
await owner.dispose()
expect(starts).toEqual([])
expect(ctx.agents.get(AgentId('listener-dispose'))).toBeUndefined()
expect(ctx.agents.get(SessionId('listener-dispose-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('listener-dispose-s'))).toBeUndefined()
await ctx.fiber.dispose()
})
@@ -741,20 +736,20 @@ describe('agent scope lifecycle', () => {
const ctx = await harness()
let ownerCtx!: Context
let creating!: ReturnType<typeof ctx.agents.create>
let announced!: ReactLoopAgent
let announced!: Agent
const statuses: string[] = []
let scopeDisposed = false
let observerSawLive = false
ctx.on('agent/status', (agent, status) => {
if (agent.id === AgentId('session-start-dispose')) statuses.push(status)
if (agent.id === SessionId('session-start-dispose-s')) statuses.push(status)
})
ctx.on('agent/session-start', (agent) => {
if (agent.id !== AgentId('session-start-dispose')) return
announced = agent as ReactLoopAgent
if (agent.id !== SessionId('session-start-dispose-s')) return
announced = agent
disposeCurrentLifecycle(ownerCtx)
})
ctx.on('agent/session-start', (agent) => {
if (agent.id !== AgentId('session-start-dispose')) return
if (agent.id !== SessionId('session-start-dispose-s')) return
expect(ctx.agents.get(agent.id)).toBe(agent)
expect(ctx.sessions.get(agent.session.id)).toBe(agent.session)
agent.ctx.effect(() => () => { scopeDisposed = true })
@@ -764,7 +759,6 @@ describe('agent scope lifecycle', () => {
const owner = await ctx.plugin(Object.assign((inner: Context) => {
ownerCtx = inner
creating = inner.agents.create({
agentId: AgentId('session-start-dispose'),
sessionId: SessionId('session-start-dispose-s'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -777,7 +771,7 @@ describe('agent scope lifecycle', () => {
expect(observerSawLive).toBe(true)
expect(scopeDisposed).toBe(true)
expect(announced.session.events).toEqual([])
expect(ctx.agents.get(AgentId('session-start-dispose'))).toBeUndefined()
expect(ctx.agents.get(SessionId('session-start-dispose-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('session-start-dispose-s'))).toBeUndefined()
await ctx.fiber.dispose()
})
@@ -789,7 +783,6 @@ describe('agent scope lifecycle', () => {
ctx.on('agent/created', () => void published.push('agent/created'))
ctx.on('agent/session-start', () => void published.push('agent/session-start'))
await expect(ctx.agents.create({
agentId: AgentId('bad'),
sessionId: SessionId('bad-s'),
agentOptions: { provider: 'mock', model: 'mock' },
setup: async () => {
@@ -800,13 +793,13 @@ describe('agent scope lifecycle', () => {
// Nothing leaked: no agent, no session, and the ids are reusable.
expect(published).toEqual([])
expect(ctx.agents.get(AgentId('bad'))).toBeUndefined()
expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined()
const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } })
const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } })
await retry.dispose()
})
it('rejects an exotic durable seed before publishing either identity', async () => {
it('rejects an exotic durable seed before publishing either object', async () => {
const ctx = await harness()
const published: string[] = []
ctx.on('session/created', () => { published.push('session') })
@@ -819,17 +812,15 @@ describe('agent scope lifecycle', () => {
}] as unknown as SessionEvent[]
await expect(ctx.agents.create({
agentId: AgentId('exotic-seed'),
sessionId: SessionId('exotic-seed-session'),
agentOptions: { provider: 'mock', model: 'mock' },
seed,
})).rejects.toThrow(/seed event at index 0 is not losslessly JSON-serializable/)
expect(published).toEqual([])
expect(ctx.agents.get(AgentId('exotic-seed'))).toBeUndefined()
expect(ctx.agents.get(SessionId('exotic-seed-session'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('exotic-seed-session'))).toBeUndefined()
const retry = await ctx.agents.create({
agentId: AgentId('exotic-seed'),
sessionId: SessionId('exotic-seed-session'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -845,13 +836,13 @@ describe('agent scope lifecycle', () => {
if (boom) { boom = false; throw new Error('boom created') }
})
await expect(ctx.agents.create({
agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' },
sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' },
})).rejects.toThrow('boom created')
expect(ctx.agents.get(AgentId('bad'))).toBeUndefined()
expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined()
expect(disposed).toEqual([]) // inserted but never announced: no impossible disposed edge
// The rollback also disposed the scope fiber: re-creating works cleanly.
const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } })
const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } })
expect(scopeOf(retry.agent.ctx)).toBe(retry.agent)
await retry.dispose()
})
@@ -868,18 +859,17 @@ describe('agent scope lifecycle', () => {
ctx.on('agent/disposed', (agent) => { lifecycle.push(`agent-disposed:${agent.id}`) })
await expect(ctx.agents.create({
agentId: AgentId('partial-agent'),
sessionId: SessionId('partial-session'),
agentOptions: { provider: 'mock', model: 'mock' },
})).rejects.toThrow('agent observer failed')
expect(lifecycle).toEqual([
'session-created:partial-session',
'agent-created:partial-agent',
'agent-disposed:partial-agent',
'agent-created:partial-session',
'agent-disposed:partial-session',
'session-disposed:partial-session',
])
expect(ctx.agents.get(AgentId('partial-agent'))).toBeUndefined()
expect(ctx.agents.get(SessionId('partial-session'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('partial-session'))).toBeUndefined()
})
@@ -894,23 +884,23 @@ describe('agent scope lifecycle', () => {
}
})
expect(() => ctx.agentLoop.create(AgentId('config-bad'), { provider: 'mock', model: 'mock' }))
expect(() => ctx.agentLoop.create(SessionId('config-bad'), { provider: 'mock', model: 'mock' }))
.toThrow('config publish failed')
expect(ctx.agents.get(AgentId('config-bad'))).toBeUndefined()
expect(ctx.agents.get(SessionId('config-bad'))).toBeUndefined()
expect(ctx.sessions.list()).toHaveLength(sessionsBefore)
})
it('registrations through a disposed agent ctx throw INACTIVE_EFFECT', async () => {
const ctx = await harness()
const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } })
const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } })
await handle.dispose()
expect(() => handle.agent.ctx.on('agent/status', () => {})).toThrow(/inactive context/)
})
it('agentEvents fuses carrier and subject for custom drivers', async () => {
const ctx = await harness()
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const other = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const other = ctx.agentLoop.create(SessionId('a2'), { provider: 'mock', model: 'mock' })
const heard: string[] = []
agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`))
@@ -923,7 +913,7 @@ describe('agent scope lifecycle', () => {
const ctx = await harness()
let handle!: Awaited<ReturnType<typeof ctx.agents.create>>
const owner = await ctx.plugin(Object.assign(async (inner: Context) => {
handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { provider: 'mock', model: 'mock' } })
handle = await inner.agents.create({ sessionId: SessionId('o1-s'), agentOptions: { provider: 'mock', model: 'mock' } })
}, { inject: ['agents'] }))
const { agent } = handle
@@ -932,7 +922,7 @@ describe('agent scope lifecycle', () => {
if (event.type === 'turn/end') order.push('turn-end')
})
ctx.on('agent/disposed', () => {
order.push(`disposed(listed=${ctx.agents.get(AgentId('o1')) !== undefined})`)
order.push(`disposed(listed=${ctx.agents.get(SessionId('o1-s')) !== undefined})`)
order.push(`session-still-stored=${ctx.sessions.get(SessionId('o1-s')) !== undefined}`)
})
@@ -955,7 +945,7 @@ describe('agent scope lifecycle', () => {
const ctx = await harness()
let handle!: Awaited<ReturnType<typeof ctx.agents.create>>
const owner = await ctx.plugin(Object.assign(async (inner: Context) => {
handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { provider: 'mock', model: 'mock' } })
handle = await inner.agents.create({ sessionId: SessionId('h1-s'), agentOptions: { provider: 'mock', model: 'mock' } })
}, { inject: ['agents'] }))
const teardownDone: string[] = []
@@ -967,23 +957,22 @@ describe('agent scope lifecycle', () => {
// actually finished (the raw wrapper returns undefined on a repeat call).
await handle.dispose()
expect(teardownDone).toContain('unregistered')
expect(ctx.agents.get(AgentId('h1'))).toBeUndefined()
expect(ctx.agents.get(SessionId('h1-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('h1-s'))).toBeUndefined()
await unload
})
it('successful handle disposal retires its caller ownership effect', async () => {
const ctx = await harness()
const agentId = AgentId('retired-owner-effect')
const sessionId = SessionId('retired-owner-effect')
const handle = await ctx.agents.create({
agentId,
sessionId: SessionId('retired-owner-effect-s'),
sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
})
expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${agentId})`)
expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${sessionId})`)
await handle.dispose()
expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([])
expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([])
await ctx.fiber.dispose()
})
@@ -994,7 +983,6 @@ describe('agent scope lifecycle', () => {
let handle!: Awaited<ReturnType<typeof ctx.agents.create>>
const owner = await ctx.plugin(Object.assign(async (inner: Context) => {
handle = await inner.agents.create({
agentId: AgentId('manual-first'),
sessionId: SessionId('manual-first-s'),
agentOptions: { provider: 'mock', model: 'mock' },
setup(agentCtx) {
@@ -1014,7 +1002,7 @@ describe('agent scope lifecycle', () => {
expect(ownerSettled).toBe(false)
gate.resolve(undefined)
await Promise.all([disposing, unloading])
expect(ctx.agents.get(AgentId('manual-first'))).toBeUndefined()
expect(ctx.agents.get(SessionId('manual-first-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('manual-first-s'))).toBeUndefined()
await ctx.fiber.dispose()
})
@@ -1024,13 +1012,11 @@ describe('agent scope lifecycle', () => {
const gate = Promise.withResolvers<undefined>()
const cleanupStarted = Promise.withResolvers<undefined>()
const sessionDisposed = Promise.withResolvers<undefined>()
const agentId = AgentId('quiescent-reuse')
const sessionId = SessionId('quiescent-reuse-s')
const sessionId = SessionId('quiescent-reuse')
ctx.on('session/disposed', (session) => {
if (session.id === sessionId) sessionDisposed.resolve(undefined)
})
const first = await ctx.agents.create({
agentId,
sessionId,
agentOptions: { provider: 'mock', model: 'mock' },
setup(agentCtx) {
@@ -1043,10 +1029,10 @@ describe('agent scope lifecycle', () => {
const disposing = first.dispose()
await Promise.all([sessionDisposed.promise, cleanupStarted.promise])
expect(ctx.agents.get(agentId)).toBeUndefined()
expect(ctx.agents.get(sessionId)).toBeUndefined()
expect(ctx.sessions.get(sessionId)).toBeUndefined()
const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
expect(ctx.agents.get(agentId)).toBe(replacement.agent)
const replacement = await ctx.agents.create({ sessionId, agentOptions: { provider: 'mock', model: 'mock' } })
expect(ctx.agents.get(sessionId)).toBe(replacement.agent)
expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session)
gate.resolve(undefined)
@@ -1058,7 +1044,6 @@ describe('agent scope lifecycle', () => {
it('handle.dispose() awaits an idle-injection flush before unregistering or detaching', async () => {
const ctx = await harness()
const handle = await ctx.agents.create({
agentId: AgentId('idle-flush'),
sessionId: SessionId('idle-flush-s'),
agentOptions: { provider: 'mock', model: 'mock' },
})
@@ -1077,12 +1062,12 @@ describe('agent scope lifecycle', () => {
const disposal = handle.dispose().then(() => { disposed = true })
await new Promise(resolve => setTimeout(resolve, 0))
expect(disposed).toBe(false)
expect(ctx.agents.get(AgentId('idle-flush'))).toBe(handle.agent)
expect(ctx.agents.get(SessionId('idle-flush-s'))).toBe(handle.agent)
expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBe(handle.agent.session)
gate.resolve(undefined)
await disposal
expect(ctx.agents.get(AgentId('idle-flush'))).toBeUndefined()
expect(ctx.agents.get(SessionId('idle-flush-s'))).toBeUndefined()
expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBeUndefined()
})
})

80
packages/core/agent-loop/tests/tool-calls.spec.ts
View File

@@ -1,18 +1,17 @@
/**
* Exercises scheduler ordering and cancellation with deterministic gated tools.
* ACP goldens own transcript-facing coverage.
* ACP expected outputs own transcript-facing coverage.
*/
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import { CallId, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionEvent } from '@deepseek-ai/dsh-session'
import SessionStore, { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import LlmService from '@deepseek-ai/dsh-llm'
import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse } from './mock-adapter.ts'
async function harness(adapter: MockAdapter, maxParallelToolCalls?: number) {
@@ -22,7 +21,6 @@ async function harness(adapter: MockAdapter, maxParallelToolCalls?: number) {
await ctx.plugin(SystemPrompt, { persona: '' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, {
agents: [],
...maxParallelToolCalls === undefined ? {} : { maxParallelToolCalls },
@@ -31,7 +29,7 @@ async function harness(adapter: MockAdapter, maxParallelToolCalls?: number) {
return ctx
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') { dispose(); resolve() }
@@ -39,7 +37,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
})
}
function events(agent: ReactLoopAgent): SessionEvent[] {
function events(agent: Agent): SessionEvent[] {
return [...agent.session.events]
}
@@ -105,7 +103,7 @@ describe('tool-call scheduler: grouping and barriers', () => {
const ctx = await harness(adapter)
const gated = gatedParallelTool('p')
ctx.tools.register(gated.tool)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 3)
@@ -134,7 +132,7 @@ describe('tool-call scheduler: grouping and barriers', () => {
name: 'w', description: 'write', parameters: { id: { type: 'string', required: true } },
async execute(args) { order.push(`w-${args.id}`); return [{ type: 'text', text: 'w' }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
@@ -169,7 +167,7 @@ describe('tool-call scheduler: grouping and barriers', () => {
return [{ type: 'text', text: 'replaced' }]
},
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => replacement.started.length === 1)
@@ -200,7 +198,7 @@ describe('tool-call scheduler: grouping and barriers', () => {
disposeInitial()
ctx.tools.register(replacement.tool)
})
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => initial.started.length === 2)
@@ -226,7 +224,7 @@ describe('tool-call scheduler: model-order results despite out-of-order settleme
const ctx = await harness(adapter)
const gated = gatedParallelTool('p')
ctx.tools.register(gated.tool)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 2)
@@ -249,7 +247,7 @@ describe('tool-call scheduler: model-order results despite out-of-order settleme
const ctx = await harness(adapter)
const gated = gatedParallelTool('p')
ctx.tools.register(gated.tool)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 2)
gated.release('2'); gated.release('1')
@@ -294,7 +292,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () =>
const ctx = await harness(adapter, 2)
const gated = gatedParallelTool('p')
ctx.tools.register(gated.tool)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 2)
@@ -324,7 +322,7 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () =>
const ctx = await harness(adapter, 1)
const gated = gatedParallelTool('p')
ctx.tools.register(gated.tool)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 1)
await new Promise(r => setTimeout(r, 5))
@@ -346,12 +344,11 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () =>
await ctx.plugin(SystemPrompt, { persona: '' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [], maxParallelToolCalls: 1 })
ctx.llm.registerAdapter(['mock'], adapter)
const gated = gatedParallelTool('p')
ctx.tools.register(gated.tool)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 1)
await new Promise(r => setTimeout(r, 5))
@@ -377,7 +374,7 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () =
const post: string[] = []
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => { pre.push(String(exec.callId)); return next() })
ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => { post.push(String(exec.callId)); return next() })
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 3)
@@ -398,7 +395,7 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () =
ctx.tools.register(gated.tool)
ctx.on('tools/post-execute', async (exec, _result): Promise<PostToolDecision> =>
({ kind: 'accept', additionalContexts: [{ content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }] }))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 2)
@@ -436,7 +433,7 @@ describe('tool-call scheduler: ordered middleware and additional contexts', () =
post.push(String(exec.callId))
return next()
})
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 1)
@@ -461,7 +458,7 @@ describe('tool-call scheduler: abort handling', () => {
const ctx = await harness(adapter)
const gated = gatedParallelTool('p')
ctx.tools.register(gated.tool)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'assistant/message') {
agent.cancel({ kind: 'user' })
@@ -472,8 +469,16 @@ describe('tool-call scheduler: abort handling', () => {
await waitForIdle(ctx, agent)
expect(gated.started).toEqual([])
expect(events(agent).filter(e => e.type === 'tool/call')).toEqual([])
expect(events(agent).filter(e => e.type === 'tool/result')).toEqual([])
expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
.toEqual([CallId('c1'), CallId('c2')])
expect(events(agent).filter(e => e.type === 'tool/result').map(e => ({
callId: e.data.callId,
isError: e.data.isError,
error: e.data.error,
}))).toEqual([
{ callId: CallId('c1'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } },
{ callId: CallId('c2'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } },
])
})
it('stops starting siblings when abort fires during ordered pre-execute', async () => {
@@ -484,7 +489,7 @@ describe('tool-call scheduler: abort handling', () => {
const ctx = await harness(adapter)
const gated = gatedParallelTool('p')
ctx.tools.register(gated.tool)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
if (exec.callId === CallId('c1')) {
agent.cancel({ kind: 'user' })
@@ -500,9 +505,11 @@ describe('tool-call scheduler: abort handling', () => {
await waitForIdle(ctx, agent)
expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
.toEqual([CallId('c1')])
.toEqual([CallId('c1'), CallId('c2')])
expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
.toEqual([CallId('c1')])
.toEqual([CallId('c1'), CallId('c2')])
expect(events(agent).filter(e => e.type === 'tool/result').at(-1)?.data)
.toMatchObject({ callId: CallId('c2'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } })
})
it('stops replenishing after abort, commits started results, and drains accepted additional contexts', async () => {
@@ -517,7 +524,7 @@ describe('tool-call scheduler: abort handling', () => {
...await next(),
additionalContexts: [{ content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }],
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 2)
@@ -528,12 +535,17 @@ describe('tool-call scheduler: abort handling', () => {
expect(gated.started).toEqual(['1', '2'])
expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
.toEqual([CallId('c1'), CallId('c2')])
.toEqual([CallId('c1'), CallId('c2'), CallId('c3'), CallId('c4')])
expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
.toEqual([CallId('c1'), CallId('c2')])
.toEqual([CallId('c1'), CallId('c2'), CallId('c3'), CallId('c4')])
expect(events(agent).filter(e => e.type === 'tool/result').slice(-2).map(e => e.data))
.toEqual([
expect.objectContaining({ callId: CallId('c3'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } }),
expect.objectContaining({ callId: CallId('c4'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } }),
])
const settled = events(agent).filter(e => e.type === 'tool/result' || e.type === 'context/message')
expect(settled.map(e => e.type))
.toEqual(['tool/result', 'tool/result', 'context/message', 'context/message'])
.toEqual(['tool/result', 'tool/result', 'tool/result', 'tool/result', 'context/message', 'context/message'])
expect(settled.filter(e => e.type === 'context/message')
.map(e => (e.data.content[0] as { text: string }).text))
.toEqual(['ctx-c1', 'ctx-c2'])
@@ -558,7 +570,7 @@ describe('tool-call scheduler: abort handling', () => {
parameters: { id: { type: 'string', required: true } },
async execute(args) { exclusive.push(args.id); return [{ type: 'text', text: 'x' }] },
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 2)
@@ -569,6 +581,8 @@ describe('tool-call scheduler: abort handling', () => {
expect(exclusive).toEqual([])
expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
.toEqual([CallId('c1'), CallId('c2')])
.toEqual([CallId('c1'), CallId('c2'), CallId('c3')])
expect(events(agent).filter(e => e.type === 'tool/result').at(-1)?.data)
.toMatchObject({ callId: CallId('c3'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } })
})
})

15
packages/core/agent-loop/tests/tool-order.spec.ts
View File

@@ -9,13 +9,13 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore, { foldRequestHeader } from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session'
import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt'
import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse } from './mock-adapter.ts'
async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['toolOrder']) {
@@ -25,13 +25,12 @@ async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['too
await ctx.plugin(SystemPrompt, { persona: 'stable base', ...toolOrder !== undefined ? { toolOrder } : {} })
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
@@ -58,7 +57,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf
const adapter = new MockAdapter([textResponse('done')])
const ctx = await harness(adapter, toolOrder)
for (const name of registrationOrder) registerNamed(ctx, name)
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
return { ctx, agent, adapter }
@@ -100,7 +99,7 @@ describe('loop-level canonical tool order', () => {
registerNamed(ctx, 'alpha')
const errors: Error[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'go' }])
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(0)

25
packages/core/agent-loop/tests/turn-stop.spec.ts
View File

@@ -1,12 +1,12 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore, { type TurnEndReason } from '@deepseek-ai/dsh-session'
import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { AgentId, type ContinuationStop } from '@deepseek-ai/dsh-agent'
import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution'
import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import AgentRegistry, { type Agent, type ContinuationStop } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import * as Invariants from '@deepseek-ai/dsh-invariants'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
@@ -18,13 +18,12 @@ async function harness(adapter: MockAdapter): Promise<Context> {
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(Invariants)
await ctx.plugin(AgentExecutionProvider)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function send(agent: ReactLoopAgent, text = 'go'): Promise<void> {
function send(agent: Agent, text = 'go'): Promise<void> {
agent.send([{ type: 'text', text }])
return agent.whenIdle()
}
@@ -47,7 +46,7 @@ describe('agent/turn-stop', () => {
textResponse('must not be requested'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('terminal-steering'), { provider: 'mock', model: 'mock' })
agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
let steered = false
@@ -74,7 +73,7 @@ describe('agent/turn-stop', () => {
textResponse('must not become a late-steering turn'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('terminal-flush-steering'), { provider: 'mock', model: 'mock' })
agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
let injected = false
@@ -100,7 +99,7 @@ describe('agent/turn-stop', () => {
textResponse('queued follow-up answer'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('terminal-flush-send'), { provider: 'mock', model: 'mock' })
agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
let queued = false
@@ -126,8 +125,8 @@ describe('agent/turn-stop', () => {
])
const ctx = await harness(adapter)
registerEcho(ctx)
const stopped = ctx.agentLoop.create(AgentId('stopped'), { provider: 'mock', model: 'mock' })
const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { provider: 'mock', model: 'mock' })
const stopped = ctx.agentLoop.create(SessionId('stopped'), { provider: 'mock', model: 'mock' })
const ordinary = ctx.agentLoop.create(SessionId('ordinary'), { provider: 'mock', model: 'mock' })
stopped.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
await send(stopped)
@@ -147,7 +146,7 @@ describe('agent/turn-stop', () => {
])
const ctx = await harness(adapter)
registerEcho(ctx)
const agent = ctx.agentLoop.create(AgentId('owned-listener'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('owned-listener'), { provider: 'mock', model: 'mock' })
const disposeStop = agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
await send(agent, 'first turn')
@@ -164,7 +163,7 @@ describe('agent/turn-stop', () => {
textResponse('healthy later turn'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('bad-policy'), { provider: 'mock', model: 'mock' })
const agent = ctx.agentLoop.create(SessionId('bad-policy'), { provider: 'mock', model: 'mock' })
const reasons: TurnEndReason[] = []
const errors: string[] = []
ctx.on('session/event', (session, event) => {

3
packages/core/agent-loop/tsconfig.json
View File

@@ -35,9 +35,6 @@
{
"path": "../../core/agent"
},
{
"path": "../../core/agent-execution"
},
{
"path": "../../core/scope"
}

77
packages/core/agent/README.md
View File

@@ -1,41 +1,52 @@
# dsh-agent
Agent interface, registry, and `agent/*` event vocabulary. Every plugin (UI, hooks, orchestrators) programs against the `Agent` handle defined here — it has zero loop dependency, so the loop is swappable.
Agent interface, registry, process-local initiator scope, and `agent/*` event vocabulary. Every plugin (UI, hooks, orchestrators) programs against the `Agent` handle defined here — it has zero loop dependency, so the loop is swappable.
## Service: `AgentRegistry` (ctx key: `agents`)
Tracks live agents so UI, hook, and orchestrator plugins can find them without importing the concrete loop package.
Tracks live agents and carries the initiating Agent through asynchronous driver work without importing the concrete loop package.
### Public API
`Agent.ctx` owns registrations visible only to that agent. `agentEvents()` couples event subjects to their scope carrier, and `assembleContextFor()` couples the agent and prompt scope. Creation and resume may compose this context through `setup`; the agent remains unpublished and must not be driven until creation resolves.
The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves.
- `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber.
- Advanced factory lifecycle: `enter(agent)` publishes without announcing and returns an entry-bound detach; `announce(agent)` emits creation once. Detach during creation dispatch is deferred. Ordinary plugins use `register()`.
- `ctx.agents.get(id: AgentId): Agent | undefined`
- Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`.
- `ctx.agents.get(id: SessionId): Agent | undefined`
- `ctx.agents.isOwnedBy(id: SessionId, owner: Agent): boolean` — whether the exact live entry was created through that parent agent's scoped context; runtime ownership is independent of durable session lineage.
- `ctx.agents.list(): Agent[]`
- `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root.
#### Initiating Agent scope
`AgentLoop` runs each concrete driver's complete lifetime inside an initiator boundary. Concurrent drivers remain isolated: a child driver's continuations carry the child, while the parent continuation regains the parent as soon as `withInitiator()` returns; drain tracking continues until the child driver's Promise settles. Creation, persistence load, and unpublished setup remain outside the child's boundary, so setup initiated by a parent inherits the parent while `agentCtx.agent` identifies the child explicitly.
- `ctx.agents.currentInitiator(): Agent | undefined` — read the inherited initiator without requiring one.
- `ctx.agents.requireInitiator(): Agent` — read it or throw `no initiating agent is active`.
- `ctx.agents.withInitiator(agent, operation)` — run with one exact Agent and preserve the operation's exact synchronous value or Promise.
- `ctx.agents.withoutInitiator(operation)` — hide an inherited initiator for unrelated process-local work.
The scope carries the `Agent` itself and is process-local. Ambient presence is neither liveness proof nor authorization; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. Teardown rejects new boundaries, lets injected dependents and returned-Promise boundaries drain, then disables the underlying `AsyncLocalStorage`; unreturned work remains owned by the subsystem that detached it. If a boundary's inherited async chain starts an owning Cordis fiber's unload, that nested boundary chain is released from the drain so the unload cannot wait on itself; its continuations observe the disposed service after teardown. The [initiator-scope decision](../../../.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns the detailed boundary and teardown contract.
#### Factory seam (creation)
The loop plugin registers `AgentFactory`, keeping consumers independent of its concrete package. Each call is traced through the caller's context so the caller owns the resulting transaction and handle.
Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-agent-loop`), registered via `setFactory`. This keeps creation on the `dsh-agent` interface so consumers (UI, the ACP bridge) program against `ctx.agents` without depending on the concrete loop package. The registry canonicalizes an already traced Service to its concrete target and re-traces each call through the caller's context; this avoids nested Cordis shadows while passing an explicit caller-bound `ownerCtx` to plain factories.
- `ctx.agents.setFactory(factory: AgentFactory): () => void` — register the creation factory (the loop calls this on construction). Throws on a second factory; the slot clears on dispose.
- `ctx.agents.create(options)` creates and composes an unpublished session and agent, then atomically enters the registries and starts the loop. A creation-only signal cancels before publication; same-ID contenders arbitrate at entry and losers roll back.
- `ctx.agents.resume(options)` loads a persisted session and follows the same composition and publication boundary. It requires [session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md).
- `ctx.agents.create(options: CreateAgentOptions): Promise<AgentHandle>` — create a session and agent, await optional setup while unpublished, then publish through final `SessionStore.enter()` and `AgentRegistry.enter()` checks. Concurrent same-ID creation is unsupported: more than one operation may prepare, but only one can enter; every loser rolls its private scope/session/driver back. An optional creation-only `signal` cancels unpublished setup and is detached before the handle is returned; later cancellation uses `handle.dispose()` or `agent.cancel()`. Publication is rollback-covered and every delivered creation edge is paired during rollback. Rejects if no factory is registered.
- `ctx.agents.resume(options: ResumeAgentOptions): Promise<AgentHandle>` — load a persisted session ([session persistence](../../../.agents/notes/implemented/architecture/2026-06-14-session-persistence.md)), mint a fresh unpublished agent scope, await optional setup, and use the same final-entry publication sequence. Its optional `signal` is likewise creation-only. Rejects if no factory is registered or session persistence is unconfigured.
`AgentHandle = { agent, dispose }` is the consumer teardown capability; registry observers receive only the bare agent. Disposal stops and drains the loop and idle-injection flushes before unregistering the agent, detaching its session, and unwinding its scope. Caller and factory unload share that memoized boundary.
`AgentHandle = { agent: Agent; dispose(): Promise<void> }`. The disposer is a **consumer capability** — no observer holding the bare registry entry can tear the agent down. The caller fiber and the registered factory provider are structural co-owners: caller unload enforces structured ownership, while factory unload must stop old instances because their scoped dependency surface belongs to that provider. `dispose()` from any owner reaches one memoized quiescence boundary: it stops the loop, `await`s its exit plus every outstanding idle-injection flush (not just the `disposed` status flip), unregisters the agent, removes its session from the store, and finally unwinds its scoped world. This order captures every agent-started `session/flush` before the session is detached and keeps scoped listeners alive through those checkpoints. `ctx.agents.get(id)` still returns a bare `Agent`; the ACP bridge and in-process subagent backends hold consumer handles, while config-created agents are already owned by the loop fiber.
### Live events
`dsh-agent` declares the live `agent/*` coordination vocabulary so plugins do not depend on the concrete loop. Exact signatures, dispatch modes, scope-filtering rules, and payload contracts live in the generated [Cordis event catalog](../../../docs/cordis-catalog/events.md); the [architecture turn flow](../../../docs/architecture.md#turn-flow) shows their order relative to durable session events.
`agent/created` runs after setup and both registry entries; the following `agent/session-start` is the first supported startup injection point. `agent/disposed` means the exact entry left the registry. The loop quiesces its driver first; directly registered custom agents own any stronger ordering.
The lifecycle edges have two important local caveats. `agent/created` runs after scoped setup and after both session and agent registry entries exist. Setup is trusted composition-only code; the immediately following non-vetoing `agent/session-start` notification is the first supported startup injection point. `agent/disposed` always means the exact agent has left the registry. AgentLoop emits it after its driver is quiescent, while ordered teardown may still be detaching the session and unwinding the scope; custom agents registered directly own any stronger driver-ordering contract themselves.
Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` is a serial surface-mutation checkpoint, while `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way).
Most interception points are cooperative waterfalls returning seam-specific decisions. Turn-scoped asynchronous seams receive one explicit `AbortSignal`, with `signal` immediately before a waterfall's final `next`; listeners may cooperate but must not retain it as authority over another turn. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: a retry opens a new numbered step after the failed step closes. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The [explicit-cancellation decision](../../../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md) owns signal lifetime; the [agent-scope runtime-design Agent Note](../../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way) owns scoped dispatch and terminal settlement.
Every asynchronous turn seam receives the same explicit `AbortSignal` for that turn. Listeners may cooperate with cancellation but must not retain the signal to control another turn; ambient `ctx.agentExecution` identity carries no liveness or cancellation authority. The signal and typed cancellation contract are defined by the [explicit turn cancellation RFC](../../../docs/rfc/implemented/architecture/2026-07-16-explicit-turn-cancellation.md).
`PromptDecision.additionalContexts` is an array so every injected context keeps its own source, envelope, and metadata. A `ContinuationDecision` reason is narrower: it becomes a `steering/message`, not a `context/message`, and therefore carries only content and source.
`PromptDecision.additionalContexts` is an array so every injected context keeps its own source and metadata. A `ContinuationDecision` reason is narrower: it becomes a `steering/message`, not a `context/message`, and therefore carries only content and source.
Turn and step boundaries and the model token stream are durable `session/event` facts rather than mirrored `agent/*` notifications. Consumers read `turn/*`, `step/*`, and `assistant/chunk` from the session feed; tool policy and outcome observation belong to the complete pipeline documented by [`dsh-tools`](../tools/README.md).
@@ -43,13 +54,15 @@ Turn and step boundaries and the model token stream are durable `session/event`
The handle every plugin programs against:
- `agent.send(content, options?)` — queue a message; starts a turn when idle. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content).
- `agent.steer(content, options?)` — steer a running turn (inject between steps); uses the same owned acceptance boundary and behaves like `send` when idle
- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message`. `options.envelope` defaults to the canonical `<context>` framing and may be `'raw'` when the caller owns a complete familiar frame; `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)).
- `agent.cancel(cause?)` — cancel ALL pending work: clears the queued + steering FIFOs, aborts the active turn, and drops queued work not yet claimed by the driver. `AgentCancelCause` is the runtime-only `{ kind: 'user' } | { kind: 'parent' }`; omission means `user`, the first cause wins for an active turn, and ACP `session/cancel` maps to `user`. `normalizeAgentCancelCause()` provides the same strict detached-value boundary used by the concrete loop: validation is synchronous even while idle, accepts only an exact plain object, and returns a frozen detached cause. After validation, `agent.cancel()` is a safe no-op when no work exists.
- `agent.send(content, options?)` — queue one independent FIFO item. If claimed, that item becomes the sole ordinary message in its turn; a claimed FIFO successor waits for that turn's checkpoint to settle. Broad cancellation, disposal, or a pre-start failure may instead drop it without a turn. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the rationale.
- `agent.steer(content, options?)` — submit steering while the agent is `running`. An open turn records it at the next steering checkpoint before a request or continuation decision; policy can still stop before another step. After turn close and its checkpoint, remaining steering becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. The method uses the same synchronous snapshot-and-validation boundary as `send` and delegates to `send` when idle
- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message` with `content` rendered verbatim as a user-role message. `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)).
- `agent.cancel(cause?)` — cancel ALL pending work: an omitted cause means `{ kind: 'user' }`; the exact `user | parent` object is validated, detached, and frozen before queues are cleared and the current turn's shared signal is aborted. Invalid causes throw synchronously, repeated active-turn cancellation is first-wins, and idle cancellation is a safe no-op that does not arm the next turn. ACP maps to `user`, while in-process parent propagation maps to `parent`. The cause is runtime-only; durable `turn/end` stays coarse `aborted`.
- `agent.whenIdle()` — resolve once the agent reaches quiescence after settling out of `running` (idle → immediately; disposed → awaits the loop exit). A non-owner's quiescence-observation hook: it observes the work settling WITHOUT tearing the agent down. Teardown is separate — a lifecycle owner stops and unregisters via `AgentHandle.dispose()`, which awaits the loop exit directly.
- `agent.session`, `agent.status`, `agent.options`, `agent.id`
`running` describes a driver-wide drain interval, not proof that a turn is still open; it can cover turn close, the durability checkpoint, and consecutive queued turns.
### Extension points
- Agent creation: `AgentLoop.create()` is the concrete config-path implementation (in `dsh-agent-loop`), while programmatic consumers create/resume owned agents through `ctx.agents.create()` / `ctx.agents.resume()`. Replace the loop by implementing `Agent` and registering via `ctx.agents.register()`.
@@ -60,20 +73,38 @@ The handle every plugin programs against:
### User, steering, and injected messages
**What the model sees**: `send`, `steer`, and `inject` feed the owning session. `agent/prompt-submit`, `agent/session-prefix`, and other declared events let plugins block a prompt or add request material; this interface contributes no fixed prose itself.
#### What the model sees
**Token effect**: Accepted content becomes retained history or a repeated session prefix; blocked content contributes no request tokens. Size is caller- and plugin-dependent.
`send`, `steer`, and `inject` feed the owning session. `agent/prompt-submit`, `agent/session-prefix`, and other declared events let plugins block a prompt or add request material; this interface contributes no fixed prose itself.
#### Token effect
Accepted content becomes retained history or a repeated session prefix; blocked content contributes no request tokens. Size is caller- and plugin-dependent.
#### KV Cache effect
Accepted history and steering are append-only; a blocked submission sends no request. A session prefix remains stable within its loop instance, while a new or resumed instance may establish a different prefix.
### Agent-scoped request composition
**What the model sees**: Registrations through `agent.ctx` can shadow prompt sections or tools and can install agent-only interceptors during unpublished setup.
#### What the model sees
**Token effect**: The package adds zero tokens itself; scoped contributions affect only that agent and disappear on disposal.
Registrations through `agent.ctx` can shadow prompt sections or tools and can install agent-only interceptors during unpublished setup.
#### Token effect
The package adds zero tokens itself; scoped contributions affect only that agent and disappear on disposal.
#### KV Cache effect
Prefix-stable while an agent's scoped registrations are unchanged. Setup or reload that changes prompt sections, tool definitions, or request listeners may invalidate reuse from the first affected request token.
## Known Limitations and Deferred Work
- **Initiator scope is process-local** — workers, child processes, HTTP, durable queues, and restarts materialize any required identity explicitly.
- **Ambient identity may outlive liveness** — consumers still check `agent.status`, cancellation, and the owning capability contract before lifecycle-sensitive work.
- **Inter-agent channels beyond delegation** — shared state, streaming child output, and background/poll semantics remain outside the current synchronous `ctx.subagents` seam.
- **`agent/session-start` cannot gate startup** — it remains a synchronous, veto-less notification; async composition that must finish before publication belongs in the factory's `setup(agentCtx)` transaction instead.
- **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface RFC](../../../docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md)).
- **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface Agent Note](../../../.agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.md)).
- **`HookContext` carries exactly one `MessageSource`** — contributions from several plugins merged onto one tool call collapse under one source; mixed provenance is unrepresentable.
- **`SessionStartSource` reserves `'clear'`/`'compact'` with no emitter yet** — only `'startup'`/`'resume'` occur until the driving subsystems land (`TODO(compaction)`).

2
packages/core/agent/package.json
View File

@@ -1,6 +1,6 @@
{
"name": "@deepseek-ai/dsh-agent",
"description": "Agent interface, registry, and event vocabulary for the DeepSeek Harness",
"description": "Agent interface, registry, initiator scope, and event vocabulary for the DeepSeek Harness",
"version": "0.0.1",
"private": true,
"type": "module",

59
packages/core/agent/src/cancellation.ts Normal file
View File

@@ -0,0 +1,59 @@
/** Public normalization helpers for explicit turn cancellation. @module @deepseek-ai/dsh-agent/cancellation */
import type { AgentCancelCause, AgentInterruptReason } from './types.ts'
/**
* Validate and detach a caller-supplied Agent cancellation cause.
* @param value - the candidate cancellation cause.
* @returns a fresh frozen cause suitable for the current turn signal.
* @throws {TypeError} when the value is not an exact supported cause.
*/
export function normalizeAgentCancelCause(value: unknown): AgentCancelCause {
if (typeof value !== 'object' || value === null || Array.isArray(value)) {
throw new TypeError('agent cancel cause must be an exact plain object with kind "user" or "parent"')
}
const prototype = Object.getPrototypeOf(value) as unknown
if (prototype !== Object.prototype && prototype !== null) {
throw new TypeError('agent cancel cause must be an exact plain object with kind "user" or "parent"')
}
const keys = Reflect.ownKeys(value)
if (keys.length !== 1 || keys[0] !== 'kind') {
throw new TypeError('agent cancel cause must contain exactly one field: kind')
}
const kind = (value as { readonly kind?: unknown }).kind
switch (kind) {
case 'user':
return Object.freeze({ kind: 'user' })
case 'parent':
return Object.freeze({ kind: 'parent' })
default:
throw new TypeError(`unsupported agent cancel cause kind: ${String(kind)}`)
}
}
/**
* Read a supported agent interruption from an explicitly supplied signal.
* Unknown reasons return `undefined`; ambient initiator identity does not grant
* cancellation authority.
* @param signal - the current turn's explicit control signal.
* @returns its canonical reason, or `undefined` while live or unsupported.
*/
export function agentInterruptReasonOf(signal: AbortSignal): AgentInterruptReason | undefined {
if (!signal.aborted) return undefined
const reason: unknown = signal.reason
if (typeof reason === 'object' && reason !== null && !Array.isArray(reason)) {
const prototype = Object.getPrototypeOf(reason) as unknown
const keys = Reflect.ownKeys(reason)
if ((prototype === Object.prototype || prototype === null)
&& keys.length === 1 && keys[0] === 'kind'
&& (reason as { readonly kind?: unknown }).kind === 'disposed') {
return Object.freeze({ kind: 'disposed' })
}
}
try {
return normalizeAgentCancelCause(reason)
} catch (error: unknown) {
if (error instanceof TypeError) return undefined
throw error
}
}

447
packages/core/agent/src/index.ts
View File

@@ -1,17 +1,21 @@
/**
* Agent registry service. Tracks live agents so plugins can find them without
* depending on the concrete loop package. Agent creation belongs to the loop.
* Agent service: live registry, factory delegation, and process-local
* initiator scope. Concrete creation and driving belong to the loop.
*
* @module @deepseek-ai/dsh-agent
*/
import { Context, getTraceable, Service, symbols } from 'cordis'
import { Context, FiberState, getTraceable, Service, symbols } from 'cordis'
import type { Fiber } from 'cordis'
import { AsyncLocalStorage } from 'node:async_hooks'
import { isPromise } from 'node:util/types'
import { scopeTarget } from '@deepseek-ai/dsh-scope'
import type { Scoped } from '@deepseek-ai/dsh-scope'
import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
import type { Agent, AgentId, AgentOptions } from './types.ts'
import type { Agent, AgentOptions } from './types.ts'
export * from './types.ts'
export { agentInterruptReasonOf, normalizeAgentCancelCause } from './cancellation.ts'
export { agentEvents, assembleContextFor } from './dispatch.ts'
export type { AgentEventDispatch, AgentSubjectEvent } from './dispatch.ts'
@@ -31,23 +35,63 @@ declare module 'cordis' {
}
}
/** Options for creating an agent and its caller-named session. */
/**
* Options for programmatically creating an agent through the registry factory
* ({@link AgentRegistry.create}). The caller supplies the single live
* `sessionId` shared by the agent registry and session log (e.g. an
* ACP-generated id), plus optional session metadata (the validated `cwd`, fork
* lineage); the factory creates the session and agent under that identity.
*/
export interface CreateAgentOptions {
/** The agent's id (the registry handle). */
readonly agentId: AgentId
/** The live session's id (NOT derived from agentId). */
/** The live agent/session identity. */
readonly sessionId: SessionId
/** Durable session metadata, validated and detached before setup. */
readonly meta?: { readonly cwd?: string; readonly parentSession?: SessionId; readonly seedLength?: number }
/** Balanced contiguous event prefix for a forked session. */
/**
* Session creation metadata: validated absolute `cwd`, `parentSession`
* fork lineage, the `seedLength` seed boundary, and the `delegationDepth`
* recursion budget. Mirrors the
* `cwd`/`parentSession`/`seedLength`/`delegationDepth` fields of
* {@link CreateSessionOptions.meta} in dsh-session (the internal-only
* `createdAt`, used when reconstructing a persisted session, is deliberately
* excluded — a factory caller never sets it). This is durable session data,
* so the session boundary validates and snapshots it before asynchronous
* setup begins.
*/
readonly meta?: {
readonly cwd?: string
readonly parentSession?: SessionId
readonly seedLength?: number
readonly delegationDepth?: number
}
/**
* Seed events to reconstruct the child session's log from (the fork lineage
* primitive). When present, the factory creates the session with this event
* prefix so `deriveMessages()`/`lastTurnNumber` continue from it — used by the
* in-process FORK subagent backend to seed a child with a balanced
* completed-turn prefix of the parent's log. The prefix MUST be contiguous
* from seq 0, carry only lossless-JSON data, and be balanced (no open
* turn/step, no dangling tool-call), or the session constructor (and the
* dev-mode invariants replay) reject it. The factory passes the raw seed to
* the session's durable validator/snapshot boundary. Absent for a fresh
* (spawn) child.
*/
readonly seed?: readonly SessionEvent[]
/** Per-agent options (model, …). */
readonly agentOptions?: AgentOptions
/** Optional creation-only cancellation signal; detached before the returned handle becomes visible. */
readonly signal?: AbortSignal
/**
* Compose the unpublished scoped context before lifecycle announcements.
* Failure rolls back without publishing either id; setup must not drive the agent.
* Creation-time composition of the agent's scoped world. The factory awaits
* setup after minting `agentCtx` but BEFORE inserting or announcing either
* the session or agent, so observers can never see a partially configured
* world. Everything registered through `agentCtx` (scoped tools, prompt
* sections/variables, `restrict()`, listeners, awaited child plugins) exists
* before `session/created`, `agent/created`, `agent/session-start`, and the
* first prompt assembly. A throw/rejection or owner disposal rolls the scope
* back without publishing either id.
*
* **Setup composes, it never drives**: the callback is trusted same-process
* code and receives the full scoped context, so this is a contract rather
* than a runtime restriction. Drive the agent only after creation resolves.
*/
readonly setup?: (agentCtx: Context) => Promise<void> | void
}
@@ -57,23 +101,41 @@ export interface CreateAgentOptions {
* ({@link AgentRegistry.resume}).
*/
export interface ResumeAgentOptions {
/** The agent's id (the registry handle). */
readonly agentId: AgentId
/** The persisted session id to load and resume on. */
/** The persisted session id to load and use as the live agent/session identity. */
readonly resumeSessionId: SessionId
/** Per-agent options (model, …). */
readonly agentOptions?: AgentOptions
/** Optional creation-only cancellation signal for persistence load/setup; detached before return. */
readonly signal?: AbortSignal
/** Compose after persistence load under the same unpublished rollback contract as create. */
/**
* Resume-time composition of the agent's fresh scoped world. Persistence is
* loaded first; the factory then mints `agentCtx` and awaits setup while the
* reconstructed session and agent remain unpublished. The callback has the
* same trusted composition-only contract as
* {@link CreateAgentOptions.setup}: all registrations exist before either
* creation announcement, and rejection or owner disposal rolls the
* transaction back without publishing either id.
*/
readonly setup?: (agentCtx: Context) => Promise<void> | void
}
/**
* Holder-owned agent capability. Disposal stops and drains the loop and idle
* flushes before unregistering the agent, detaching its session, and unwinding
* its scoped context. Provider unload reaches the same quiescence boundary;
* registry observers receive only the bare {@link Agent}.
* An owned agent plus its disposer, returned by {@link AgentRegistry.create} /
* {@link AgentRegistry.resume}. The disposer is a CAPABILITY: among consumers,
* only the holder can tear this agent down. The registered factory provider is
* also a structural owner because the scoped agent depends on that provider's
* service surface; provider unload stops and drains every live handle it made.
* `dispose()` stops the loop, awaits its exit and every outstanding
* idle-injection flush (quiescence — NOT just the `disposed`
* status flip), unregisters the agent, removes its session from the store, and
* finally unwinds its scoped world. This order captures every agent-started
* `session/flush` before the session is detached and keeps scoped listeners
* alive through those checkpoints.
*
* `ctx.agents.get(id)` still returns a bare {@link Agent} — the handle is
* exposed only to the consumer owner that created it; the structural provider
* reaches the same teardown internally. Config-created agents (the loop's own
* startup) are owned by the loop fiber and never need a handle.
*/
export interface AgentHandle {
agent: Agent
@@ -88,16 +150,30 @@ export interface AgentHandle {
*/
export interface AgentFactory {
/**
* Create and compose under caller ownership, publish and announce session then
* agent, emit session-start, and start the driver. Rollback pairs any creation
* announcement that began.
* Create a new agent on a caller-supplied session id. Async because creation
* awaits unpublished setup, inserts both session and agent, emits their
* creation notifications in order, emits `agent/session-start`, and only
* then starts the loop. The sequence is
* rollback-covered, but notifications delivered before a later listener
* failure remain observable; every agent or session creation announcement
* that began is paired by `agent/disposed` or `session/disposed` during
* rollback. The owner disposes the resolved handle to stop/drain,
* unregister, remove the session, and unwind the scope.
* The registry passes a context carrying the `create()` caller's fiber and
* scope as `ownerCtx`. The implementation attaches the unpublished
* transaction and resulting lifecycle to that owner; it must not infer
* ownership from the factory object's registration context.
* @param ownerCtx - caller-bound context that owns the transaction and live handle.
* @param options - agent/session identity, configuration, and optional setup.
* @returns the owned handle after setup, both announcements, and loop start complete.
*/
createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise<AgentHandle>
/**
* Load, compose, publish, announce, and resume an agent under caller ownership.
* Load a persisted session and resume an agent on it. Async because it awaits
* both `ctx.sessionPersistence.load` and the optional unpublished setup
* transaction; must be called after that service exists (consumers inject
* `sessionPersistence`). Publication follows the same ordered boundary as
* {@link createAgent}.
* @param ownerCtx - caller-bound context that owns load, setup, and the live handle.
* @param options - persisted identity, configuration, and optional setup.
* @returns the owned handle after setup, both announcements, and loop start complete.
@@ -107,57 +183,160 @@ export interface AgentFactory {
/** Thrown when create/resume is called before an agent factory is registered. */
const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plugin)'
const NO_INITIATOR_MESSAGE = 'no initiating agent is active'
const DISPOSED_INITIATOR_MESSAGE = 'agent initiator scope is disposed'
/** All mutable lifecycle state for one exact registry entry. */
interface AgentEntry {
readonly id: AgentId
readonly id: SessionId
readonly agent: Agent
/** Runtime creator-agent ownership; independent of durable session lineage. */
readonly owner: Agent | undefined
readonly carrier: Scoped<Agent>
announced: boolean
announcing: boolean
detachRequested: boolean
}
/** One tracked boundary plus its inherited nesting chain. */
interface InitiatorRun {
active: boolean
readonly parent: InitiatorRun | undefined
}
/** Plain holder prevents Cordis from tracing the factory field before the caller context is known. */
interface FactorySlot {
readonly target: AgentFactory
}
/**
* 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
* {@link AgentFactory} (`@deepseek-ai/dsh-agent-loop`), registered via
* {@link setFactory}.
* Agent service (`ctx.agents`): tracks live agents and carries the initiating
* Agent through one process-local asynchronous driver chain. Agent *creation*
* is provided by whichever plugin implements the {@link AgentFactory}
* (`@deepseek-ai/dsh-agent-loop`), registered via {@link setFactory}.
*
* Initiator methods provide same-process causal attribution only. Ambient
* presence is neither liveness proof nor authorization; subjects and owners
* remain explicit, as does identity at worker, process, persistence, and wire
* boundaries. Returned Promise boundaries drain during teardown, except a
* nested lineage that starts an owning-fiber unload is excluded from its own drain.
*/
export class AgentRegistry extends Service {
private store = new Map<AgentId, AgentEntry>()
// TODO(agent-entry-mirror): derive exact-object checks from store.get(agent.id)
// plus entry.agent identity; this WeakMap mirrors the authoritative id map.
private entries = new WeakMap<Agent, AgentEntry>()
private store = new Map<SessionId, AgentEntry>()
private factory: FactorySlot | undefined
private readonly initiators = new AsyncLocalStorage<Agent | undefined>()
private readonly initiatorRuns = new AsyncLocalStorage<InitiatorRun>()
private initiatorState: 'active' | 'closing' | 'disposed' = 'active'
private activeInitiatorRuns = 0
private initiatorDrain: PromiseWithResolvers<void> | undefined
private initiatorDisposal: Promise<void> | undefined
constructor(ctx: Context) {
super(ctx, 'agents')
// Agent contexts shadow this plain-context default with an own property.
// The `ctx.agent` DX accessor: default `undefined` on every context, so a
// plain plugin context reads cleanly instead of hitting the Cordis
// unknown-property throw. Each Agent.ctx shadows it with an own property
// (own properties resolve before the context proxy is consulted), so the
// accessor body never needs to resolve a scope itself. Effect-scoped:
// unwinds with this service's fiber.
ctx.accessor('agent', { get: () => undefined })
ctx.on('internal/status', (fiber) => {
if (fiber.state === FiberState.UNLOADING && this.hasLifecycleAncestor(fiber)) {
this.closeInitiators()
}
})
ctx.effect(function* (this: AgentRegistry) {
yield () => this.disposeInitiators()
yield () => { this.closeInitiators() }
}.bind(this), 'agents.initiatorLifecycle()')
}
/**
* Register the effect-scoped creation factory, rejecting a duplicate. Service
* factories are retraced through each create/resume caller for ownership.
* Read the Agent that initiated the inherited asynchronous driver chain.
* Use this optional form for logging, tracing, metrics, or host attribution
* that also supports agentless calls. When a parent creates a child, setup
* reports the causal parent while `agentCtx.agent` identifies the child.
* @returns the inherited Agent, or `undefined` outside an initiator boundary
* and inside an explicit clearing boundary.
* @throws when this service instance has been disposed.
*/
currentInitiator(): Agent | undefined {
this.assertInitiatorsReadable()
return this.initiators.getStore()
}
/**
* Read the initiating Agent and fail when no initiator boundary is active.
* Use this for private helpers contractually below a driver, or for a
* deployment-owned outbound request whose contract forbids agentless calls.
* Generic or direct-call seams use optional lookup or explicit request fields.
* @returns the inherited Agent.
* @throws when no initiator is active or this service instance has been disposed.
*/
requireInitiator(): Agent {
const agent = this.currentInitiator()
if (agent === undefined) throw new Error(NO_INITIATOR_MESSAGE)
return agent
}
/**
* Run an operation with one exact Agent as its process-local initiator. The
* exact synchronous value or Promise returned by the operation is preserved.
* Custom drivers and test harnesses wrap their complete returned foreground
* lifetime.
* A queue or wire receiver may establish this boundary only after validating
* explicit identity and resolving the exact live Agent; this method does neither.
* Detached work remains owned by the subsystem that starts it.
* @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization.
* @param operation - synchronous or asynchronous operation to invoke.
* @returns the exact value returned by `operation`.
* @throws when the initiator scope is closing/disposed, or when `operation` throws.
*/
withInitiator<T>(agent: Agent, operation: () => T): T {
return this.runWithInitiator(agent, operation)
}
/**
* Run an operation inside a boundary that hides any inherited initiating
* Agent. The exact synchronous value or Promise is preserved.
* Use this while creating lazy shared timers, queue pumps, pool maintenance,
* watchers, or exporters so they do not inherit the first Agent that happens
* to initialize them. It clears only initiator attribution, not explicit
* fields, and does not own or drain detached resources.
* @param operation - synchronous or asynchronous operation to invoke without an initiator.
* @returns the exact value returned by `operation`.
* @throws when the initiator scope is closing/disposed, or when `operation` throws.
*/
withoutInitiator<T>(operation: () => T): T {
return this.runWithInitiator(undefined, operation)
}
/**
* Register the agent-creation factory (the loop calls this on construction,
* effect-scoped). A traced Cordis service is canonicalized to its concrete
* target; each create/resume call is then traced through that caller's
* context so ownership follows the caller without stacking proxy layers.
* Throws if a factory is already registered. Returns the disposer; on
* dispose the factory slot is cleared.
* @param factory - the loop-owned factory {@link create}/{@link resume} delegate to.
* @returns the exact Cordis effect disposer.
* @returns the disposer that clears the factory slot. The exact
* Cordis effect disposer (single-shot): composite (generator) effects may
* yield it directly — exact identity nests the teardown in order.
*/
setFactory(factory: AgentFactory): () => void {
const dispose = this.ctx.effect(() => {
if (this.factory !== undefined) throw new Error('an agent factory is already registered')
// Store the concrete service; calls are retraced through their owner.
// Avoid stacking two Cordis shadow layers when a caller passes a Service
// already read through a context. Calls are re-traced through their
// actual owner context below.
const target = (factory as AgentFactory & { [symbols.original]?: AgentFactory })[symbols.original] ?? factory
this.factory = { target }
return () => { this.factory = undefined }
}, 'agents.setFactory()')
// Return the exact disposer so composite effects preserve teardown order.
// The exact cordis effect disposer (the agents.register() convention): a
// caller's composite effect can yield it for in-order teardown; the
// loop's constructor effect returns it directly, identity-nesting the
// registration under that effect.
// eslint-disable-next-line @typescript-eslint/no-misused-promises -- synchronous cleanup; direct return preserves disposer identity
return dispose
}
@@ -169,14 +348,20 @@ export class AgentRegistry extends Service {
}
/**
* Create and publish an owned agent and session through the active factory.
* Rejects if no factory is registered or creation, setup, or publication fails.
* @param options - agent id, session id/seed/metadata, and agent options.
* Create and publish a new agent through the registered factory.
* Distinct from {@link register} (which records an already-constructed
* agent): this constructs the agent and its session. Rejects if no factory is
* registered or creation/setup fails. The resolved {@link AgentHandle} lets
* the owner tear down exactly this agent.
* @param options - shared identity, session seed/metadata, and agent options.
* @returns the handle after setup, rollback-covered publication, and loop start complete.
*/
async create(options: CreateAgentOptions): Promise<AgentHandle> {
const ownerCtx = this.ctx
// Bind service effects to this caller while preserving factory dependencies.
// Re-trace a Service-backed factory through the accessing context
// explicitly. This preserves AgentLoop's dependency origin while binding
// its effects to ownerCtx; plain factories receive ownerCtx as an explicit
// capability and need no Cordis tracker magic.
const { target } = this.requireFactory()
const receiver = getTraceable(ownerCtx, target)
// eslint-disable-next-line @typescript-eslint/unbound-method -- Reflect.apply intentionally supplies the caller-traced receiver
@@ -199,14 +384,26 @@ export class AgentRegistry extends Service {
}
/**
* Register a live agent in the calling effect scope, with scope-filtered
* creation and disposal events. Duplicate ids throw.
* Register a live agent. Throws if an agent with the same id is already
* registered. Emits `agent/created` on registration and `agent/disposed`
* when the calling fiber is disposed — both with the agent's scope carrier
* (`scopeTarget(agent, agent)`): the subject is the agent in hand, so the
* emits are scope-filtered regardless of which context invoked `register`
* (calling through `agent.ctx` scopes EFFECTS; dispatch scoping always
* requires passing the carrier). Returns the disposer.
* @param agent - the already-constructed agent to record in the store.
* @returns the exact Cordis effect disposer for nested teardown ordering.
* @returns the EXACT Cordis effect disposer (single-shot; a repeat call
* returns undefined without awaiting an in-flight teardown). Exact
* identity is load-bearing: a composite (generator) effect that owns a
* teardown ORDER — the agent factory's lifecycle chain — must yield THIS
* function so Cordis nests the unregistration at that yield position;
* yielding a wrapper would leave it disposing as a concurrent sibling on
* owner unload, unregistering the agent (and emitting `agent/disposed`)
* while its final turn is still draining.
*/
register(agent: Agent): () => void {
const dispose = this.ctx.effect(function* (this: AgentRegistry) {
yield this.enter(agent)
yield this.enter(agent, this.ctx.agent)
this.announce(agent)
}.bind(this), 'agents.register()')
// eslint-disable-next-line @typescript-eslint/no-misused-promises -- synchronous cleanup; direct return preserves disposer identity
@@ -214,31 +411,48 @@ export class AgentRegistry extends Service {
}
/**
* Insert an unpublished agent for an ordered factory transaction.
* Insert an already-constructed agent without announcing it. This is the
* advanced ordered-lifecycle primitive used by the async agent factory: it
* first completes setup while the agent is unpublished, then assigns the
* returned detach closure into its pre-installed composite teardown before
* calling {@link announce}. Ordinary callers use {@link register}.
* @param agent - the prepared, unpublished agent.
* @returns an idempotent closure that removes this exact entry and emits the
* paired disposal edge; detachment during creation dispatch is deferred.
* @param owner - live agent whose scoped context created this agent, or
* undefined for a top-level runtime root. This is runtime ownership, not
* the resumed session's durable parent lineage.
* @returns an idempotent closure that removes this exact entry and emits
* `agent/disposed` with listener failures contained. When called from a
* synchronous `agent/created` listener, removal and disposal wait until
* that creation dispatch unwinds.
*/
enter(agent: Agent): () => void {
enter(agent: Agent, owner: Agent | undefined): () => void {
const id = agent.id
if (id !== agent.session.id) {
throw new Error(`agent id "${id}" does not match session id "${agent.session.id}"`)
}
const carrier = scopeTarget(agent, agent)
// Prepared transactions arbitrate identity at this publication boundary.
if (this.entries.has(agent) || this.store.has(id)) throw new Error(`agent "${id}" is already registered`)
// This is the authoritative collision boundary. Concurrent create/resume
// operations may both prepare, but only one exact entry can publish.
if (this.store.has(id)) throw new Error(`agent "${id}" is already registered`)
const entry: AgentEntry = {
id,
agent,
owner,
carrier,
announced: false,
announcing: false,
detachRequested: false,
}
this.store.set(id, entry)
this.entries.set(agent, entry)
let entered = true
const detach = (): void => {
if (!entered) return
entered = false
// Creation listeners observe one stable entry before paired disposal.
// Every callback reached by this creation dispatch must observe the same
// live entry, and disposal must follow creation. A listener may own
// the advanced detach capability, so make that ordering structural:
// visibility and the paired disposal are deferred until announce()'s
// synchronous dispatch has unwound.
if (entry.announcing) {
entry.detachRequested = true
return
@@ -256,7 +470,6 @@ export class AgentRegistry extends Service {
/* v8 ignore next -- enter() rejects replacement while this single-shot detach capability is live. */
if (this.store.get(entry.id) !== entry) return
this.store.delete(entry.id)
this.entries.delete(entry.agent)
// An insertion rolled back before announce was never externally created,
// so emitting disposed would invent an impossible lifecycle edge. Marking
// happens before the created emit: if a later created listener throws,
@@ -288,8 +501,8 @@ export class AgentRegistry extends Service {
* creation listener).
*/
announce(agent: Agent): void {
const entry = this.entries.get(agent)
if (entry === undefined || this.store.get(entry.id) !== entry) {
const entry = this.store.get(agent.id)
if (entry === undefined || entry.agent !== agent) {
throw new Error(`agent "${agent.id}" is not live in this registry`)
}
if (entry.announced || entry.announcing) {
@@ -318,13 +531,25 @@ export class AgentRegistry extends Service {
/**
* Look up a live agent.
* @param id - the agent id to look up.
* @param id - the shared agent/session id to look up.
* @returns the agent, or undefined when no live agent has that id.
*/
get(id: AgentId): Agent | undefined {
get(id: SessionId): Agent | undefined {
return this.store.get(id)?.agent
}
/**
* Test whether a live agent was created through one exact parent agent's
* scoped context. Runtime ownership is independent of durable session
* lineage and remains unambiguous when unrelated providers reuse an id.
* @param id - the candidate child agent's shared agent/session id.
* @param owner - the expected runtime creator agent.
* @returns true only while the exact child entry is live under that owner.
*/
isOwnedBy(id: SessionId, owner: Agent): boolean {
return this.store.get(id)?.owner === owner
}
/**
* All live agents, in registration order.
* @returns a fresh array; mutating it does not affect the registry.
@@ -332,6 +557,104 @@ export class AgentRegistry extends Service {
list(): Agent[] {
return [...this.store.values()].map(entry => entry.agent)
}
/**
* All live top-level agents in registration order. A top-level agent was
* created without an owning agent context; durable session lineage does not
* affect this runtime relation, so a resumed fork may still be a root.
* @returns a fresh array; mutating it does not affect the registry.
*/
roots(): Agent[] {
return [...this.store.values()]
.filter(entry => entry.owner === undefined)
.map(entry => entry.agent)
}
/** Reject new initiator boundaries while inherited continuations drain. */
private closeInitiators(): void {
if (this.initiatorState === 'active') this.initiatorState = 'closing'
}
/** Wait for returned-Promise boundaries, then invalidate retained references. */
private disposeInitiators(): Promise<void> {
return (this.initiatorDisposal ??= (async () => {
this.closeInitiators()
this.releaseReentrantInitiatorRuns()
if (this.activeInitiatorRuns !== 0) {
this.initiatorDrain ??= Promise.withResolvers<void>()
await this.initiatorDrain.promise
}
this.initiatorState = 'disposed'
this.initiators.disable()
this.initiatorRuns.disable()
})())
}
/** Establish one tracked initiator or clearing boundary. */
private runWithInitiator<T>(agent: Agent | undefined, operation: () => T): T {
if (this.initiatorState !== 'active') throw new Error(DISPOSED_INITIATOR_MESSAGE)
const run: InitiatorRun = {
active: true,
parent: this.initiatorRuns.getStore(),
}
this.activeInitiatorRuns += 1
let result: T
try {
result = this.initiatorRuns.run(run, () => this.initiators.run(agent, operation))
} catch (error: unknown) {
this.releaseInitiatorRun(run)
throw error
}
if (isPromise(result)) {
try {
void Promise.prototype.then.call(
result,
() => { this.releaseInitiatorRun(run) },
() => { this.releaseInitiatorRun(run) },
)
} catch {
// A branded Promise may expose a failing @@species. Observer setup did
// not attach, so preserve the exact return without leaking the run.
this.releaseInitiatorRun(run)
}
} else {
this.releaseInitiatorRun(run)
}
return result
}
/** Whether one unloading fiber owns this service's lifecycle. */
private hasLifecycleAncestor(candidate: Fiber): boolean {
let fiber = this.ctx.fiber
while (true) {
if (fiber === candidate) return true
const parent = fiber.parent.fiber
if (parent === fiber) return false
fiber = parent
}
}
private assertInitiatorsReadable(): void {
if (this.initiatorState === 'disposed') throw new Error(DISPOSED_INITIATOR_MESSAGE)
}
/** Exclude the boundary chain that initiated this teardown from its own drain. */
private releaseReentrantInitiatorRuns(): void {
let run = this.initiatorRuns.getStore()
while (run !== undefined) {
this.releaseInitiatorRun(run)
run = run.parent
}
}
private releaseInitiatorRun(run: InitiatorRun): void {
if (!run.active) return
run.active = false
this.activeInitiatorRuns -= 1
if (this.activeInitiatorRuns !== 0) return
this.initiatorDrain?.resolve()
this.initiatorDrain = undefined
}
}
export default AgentRegistry

176
packages/core/agent/src/types.ts
View File

@@ -5,25 +5,11 @@
* @module @deepseek-ai/dsh-agent/types
*/
import type { Branded } from '@deepseek-ai/dsh-brand'
import type { Context } from 'cordis'
import type { Scoped } from '@deepseek-ai/dsh-scope'
import type { ContentBlock, LlmCallConfig, Message, MessageSource } from '@deepseek-ai/dsh-llm'
import type { JsonValue, Session, SessionId } from '@deepseek-ai/dsh-session'
import type {} from '@deepseek-ai/dsh-system-prompt'
import type { ContextEnvelope, JsonValue, Session } from '@deepseek-ai/dsh-session'
/** Identifies one live agent in the registry. */
export type AgentId = Branded<'AgentId'>
/**
* Brand a string as an {@link AgentId}.
* @param id - the raw agent id string.
* @returns the same string, branded (a compile-time cast — no runtime cost).
*/
export function AgentId(id: string): AgentId {
return id as AgentId
}
declare module '@deepseek-ai/dsh-system-prompt' {
interface AssembleContext {
/** Agent for this assembly; absent on diagnostics. When present, `scope` must identify the same agent. */
@@ -46,17 +32,15 @@ export interface SendOptions {
/** Options specific to durable synthetic context injection. */
export 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
}
/**
* An agent's lifecycle state, emitted on every transition as `agent/status`:
* `idle` (parked, waiting for queued work), `running` (a turn is in progress),
* `disposed` (terminal — no transition leaves it, and `send`/`steer`/`inject`
* throw).
* `idle` (parked, waiting for queued work), `running` (the driver is draining
* work and may be closing or checkpointing a turn), `disposed` (terminal — no
* transition leaves it, and `send`/`steer`/`inject` throw).
*/
export type AgentStatus = 'idle' | 'running' | 'disposed'
@@ -64,16 +48,15 @@ export type AgentStatus = 'idle' | 'running' | 'disposed'
export 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
}
/**
* 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.
*/
export type PromptDecision =
| { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: HookContext[] }
@@ -84,6 +67,12 @@ export type ContinuationDecision =
| { action: 'stop' }
| { action: 'continue'; reason?: { content: ContentBlock[]; source: MessageSource } }
/** Failed-request recovery decision; `retry` opens another numbered step while listeners delegate by calling `next()`. */
export type RequestErrorDecision = { action: 'fail' } | { action: 'retry' }
/** Model-request failure with an optional machine-routable provider code. */
export type RequestError = Error & { code?: string }
/**
* The terminal subset of {@link ContinuationDecision}. A listener on
* `agent/turn-stop` returns this to make the already-composed continuation
@@ -99,70 +88,13 @@ export type AgentCancelCause =
| { readonly kind: 'user' }
| { readonly kind: 'parent' }
/**
* Validate and detach a caller-supplied Agent cancellation cause.
* @param value - the candidate cancellation cause.
* @returns a fresh frozen cause suitable for the current turn signal.
* @throws {TypeError} when the value is not an exact supported cause.
*/
export function normalizeAgentCancelCause(value: unknown): AgentCancelCause {
if (typeof value !== 'object' || value === null || Array.isArray(value)) {
throw new TypeError('agent cancel cause must be an exact plain object with kind "user" or "parent"')
}
const prototype = Object.getPrototypeOf(value) as unknown
if (prototype !== Object.prototype && prototype !== null) {
throw new TypeError('agent cancel cause must be an exact plain object with kind "user" or "parent"')
}
const keys = Reflect.ownKeys(value)
if (keys.length !== 1 || keys[0] !== 'kind') {
throw new TypeError('agent cancel cause must contain exactly one field: kind')
}
const kind = (value as { readonly kind?: unknown }).kind
switch (kind) {
case 'user':
return Object.freeze({ kind: 'user' })
case 'parent':
return Object.freeze({ kind: 'parent' })
default:
throw new TypeError(`unsupported agent cancel cause kind: ${String(kind)}`)
}
}
/** Runtime reason carried by the signal that controls one live turn. */
export type AgentInterruptReason = AgentCancelCause | { readonly kind: 'disposed' }
/**
* Read a supported agent interruption from an explicitly supplied signal.
* Unknown reasons return `undefined`; this helper never consults ambient agent
* execution identity, which does not grant cancellation authority.
*
* @param signal - the current turn's explicit control signal.
* @returns its canonical supported reason, or `undefined` while live or when an
* unrelated controller supplied an unsupported reason.
*/
export function agentInterruptReasonOf(signal: AbortSignal): AgentInterruptReason | undefined {
if (!signal.aborted) return undefined
const reason: unknown = signal.reason
if (typeof reason === 'object' && reason !== null && !Array.isArray(reason)) {
const prototype = Object.getPrototypeOf(reason) as unknown
const keys = Reflect.ownKeys(reason)
if ((prototype === Object.prototype || prototype === null)
&& keys.length === 1 && keys[0] === 'kind'
&& (reason as { readonly kind?: unknown }).kind === 'disposed') {
return Object.freeze({ kind: 'disposed' })
}
}
try {
return normalizeAgentCancelCause(reason)
} catch (error: unknown) {
if (error instanceof TypeError) return undefined
throw error
}
}
/** Public agent handle; the concrete driver belongs to `@deepseek-ai/dsh-agent-loop`. */
/** Public agent handle; its concrete implementation is internal to `@deepseek-ai/dsh-agent-loop`. */
export interface Agent {
readonly id: AgentId
/** The single identity shared with {@link session}. */
readonly id: SessionId
readonly options: AgentOptions
readonly session: Session
readonly status: AgentStatus
@@ -170,15 +102,20 @@ export 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
@@ -192,11 +129,11 @@ export interface Agent {
inject(content: ContentBlock[], options?: InjectOptions): void
/**
* Clear queued and steering work, including work waiting to start, and abort
* the active turn. The first cause wins for that turn, and `whenIdle()` resolves
* after cancellation reaches quiescence. Omission means `{ kind: 'user' }`;
* invalid causes throw synchronously even while idle. Idle cancellation is a
* no-op after validation and does not arm a later cancel.
* Clear all queued and steering work, including items waiting to start, and
* abort the active turn. The first cause wins for that turn, and `whenIdle()`
* resolves after cancellation reaches quiescence. Omission means
* `{ kind: 'user' }`; invalid causes throw synchronously even while idle.
* Idle cancellation is a no-op after validation and does not arm a later cancel.
* @param cause - the stable caller intent carried by the current turn signal.
*/
cancel(cause?: AgentCancelCause): void
@@ -266,30 +203,24 @@ declare module 'cordis' {
// ---- step/request extension seams (serial + waterfall) ----
/**
* Awaited serial checkpoint for session-surface mutation after prompt
* assembly and before `step/start`; appends land outside the pending step.
* The loop derives history once afterward, so compaction records and
* replacements are included without rewriting an assembled request. The
* prompt and prefix are the exact pressure inputs for that request, and
* Awaited serial checkpoint before `step/start`; appends land outside the
* pending step and are included when the loop derives request history.
* `signal` cancels listener work.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @param agent - the agent opening the step.
* @param turn - the open turn number.
* @param step - the pending step number.
* @param fullSystemPrompt - the assembled prompt.
* @param sessionPrefix - the frozen request prefix.
* @param signal - the turn abort signal.
* @mode serial
*/
// TODO: Move prompt-pressure inputs behind a compaction-specific seam if no second consumer appears.
'agent/pre-step'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise<void> | void
'agent/pre-step'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise<void> | void
/**
* Allow, rewrite, or block one drained prompt before it becomes a user
* Allow, rewrite, or block one claimed prompt before it becomes a user
* message. Call `next()` for the unchanged default. The signal controls only
* this turn; listeners may cooperate with it but must not retain it to
* control another turn.
* @param agent - the agent draining its inbox.
* @param content - the drained message's blocks, as queued.
* @param agent - the agent whose turn claimed the message.
* @param content - the claimed message's blocks, as queued.
* @param source - the message's resolved source.
* @param signal - the current turn's explicit abort signal.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
@@ -304,7 +235,8 @@ declare module 'cordis' {
* @param turn - the open turn number.
* @param step - the step whose request this is.
* @param config - the config the loop would use (frozen); return a replacement to switch.
* @param signal - the current turn's explicit abort signal; ambient agent identity does not imply liveness or cancellation authority.
* @param signal - the current turn's explicit abort signal; ambient
* initiator identity does not imply liveness or cancellation authority.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
@@ -314,9 +246,9 @@ declare module 'cordis' {
* result is computed once per loop instance, logged on its anchoring request
* header, and reused so the provider prefix remains stable. Interrupted
* composition is discarded. Composition precedes the first `agent/pre-step`
* and request boundary, so listener appends join the current request and
* pressure accounting sees the composed prefix. Changing context belongs in
* history; contributors should prepend to `await next()` to preserve registration order.
* and request boundary, so listener appends join the current request.
* Changing context belongs in history; contributors should prepend to
* `await next()` to preserve registration order.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @param agent - the agent whose session prefix is being composed.
* @param prefix - the frozen seed; return an extended replacement.
@@ -336,6 +268,32 @@ declare module 'cordis' {
* @mode waterfall
*/
'agent/step-result'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, message: Message, signal: AbortSignal, next: () => Promise<Message>): Promise<Message>
/**
* Awaited serial checkpoint after the response, real or synthetic tool
* results, injected context, and steering are durable but before `step/end`.
* A cancelled tool batch reaches this checkpoint with an aborted signal.
* @param agent - the agent whose step is settling.
* @param turn - the open turn number.
* @param step - the open step number.
* @param signal - the turn abort signal.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode serial
*/
'agent/post-step'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise<void> | void
/**
* Recover a model-request failure after its failed step has closed. `retry`
* opens a new numbered step; `fail` preserves the original request error.
* Call `next()` to delegate to the next recovery listener or the default.
* @param agent - the agent whose request failed.
* @param turn - the open turn number.
* @param step - the failed step number.
* @param error - the original model-request failure.
* @param retryAttempt - zero-based number of prior recovery retries.
* @param signal - the turn abort signal.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
'agent/request-error'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, error: RequestError, retryAttempt: number, signal: AbortSignal, next: () => Promise<RequestErrorDecision>): Promise<RequestErrorDecision>
/**
* Override whether the turn continues. The default continues after tool
* calls or steering and stops otherwise; a continue reason becomes steering.

265
packages/core/agent/tests/agent-initiator.spec.ts Normal file
View File

@@ -0,0 +1,265 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import { runInNewContext } from 'node:vm'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { SessionId } from '@deepseek-ai/dsh-session'
function agent(id: string): Agent {
return { id: SessionId(id) } as Agent
}
async function harness(): Promise<{
ctx: Context
service: AgentRegistry
dispose: () => Promise<void>
}> {
const ctx = new Context()
const fiber = await ctx.plugin(AgentRegistry)
return {
ctx,
service: ctx.agents,
dispose: fiber.dispose,
}
}
/** Fail a lifecycle regression promptly instead of waiting for Vitest's suite timeout. */
async function promptly<T>(task: Promise<T>): Promise<T> {
const timeout = Promise.withResolvers<never>()
const timer = setTimeout(() => { timeout.reject(new Error('initiator teardown did not settle promptly')) }, 1000)
try {
return await Promise.race([task, timeout.promise])
} finally {
clearTimeout(timer)
}
}
describe('AgentRegistry initiator scope', () => {
it('reports an absent initiator and requires an active boundary', async () => {
const { service, dispose } = await harness()
expect(service.currentInitiator()).toBeUndefined()
expect(() => service.requireInitiator()).toThrow('no initiating agent is active')
await dispose()
})
it('preserves exact synchronous and Promise return identities across await', async () => {
const { service, dispose } = await harness()
const initiator = agent('identity')
const value = { result: true }
expect(service.withInitiator(initiator, () => {
expect(service.requireInitiator()).toBe(initiator)
return value
})).toBe(value)
const promise = service.withInitiator(initiator, async () => {
expect(service.requireInitiator()).toBe(initiator)
await Promise.resolve()
expect(service.requireInitiator()).toBe(initiator)
return value
})
expect(service.withInitiator(initiator, () => promise)).toBe(promise)
await expect(promise).resolves.toBe(value)
expect(service.currentInitiator()).toBeUndefined()
await dispose()
})
it('tracks a branded Promise without calling its overridable then property', async () => {
const { service, dispose } = await harness()
const initiator = agent('overridden-then')
const release = Promise.withResolvers<boolean>()
void Object.defineProperty(release.promise, 'then', {
value: () => { throw new Error('overridden then called') },
})
const pending = service.withInitiator(initiator, () => release.promise)
expect(pending).toBe(release.promise)
let disposed = false
const disposal = dispose().then(() => { disposed = true })
await Promise.resolve()
expect(disposed).toBe(false)
release.resolve(true)
await new Promise<void>((resolve, reject) => {
void Promise.prototype.then.call(pending, resolve, reject)
})
await disposal
expect(disposed).toBe(true)
})
it('preserves a settled branded Promise when its species blocks observer construction', async () => {
const { service, dispose } = await harness()
const initiator = agent('invalid-species')
const promise = Promise.resolve()
const constructor = {}
Object.defineProperty(constructor, Symbol.species, {
get: () => { throw new Error('invalid species') },
})
void Object.defineProperty(promise, 'constructor', { value: constructor })
expect(service.withInitiator(initiator, () => promise)).toBe(promise)
await dispose()
})
it('isolates overlapping initiators', async () => {
const { service, dispose } = await harness()
const a = agent('a')
const b = agent('b')
const bothStarted = Promise.withResolvers<boolean>()
const release = Promise.withResolvers<boolean>()
let starts = 0
const run = (initiator: Agent): Promise<void> => service.withInitiator(initiator, async () => {
expect(service.requireInitiator()).toBe(initiator)
starts += 1
if (starts === 2) bothStarted.resolve(true)
await release.promise
expect(service.requireInitiator()).toBe(initiator)
})
const pending = [run(a), run(b)]
await bothStarted.promise
expect(service.currentInitiator()).toBeUndefined()
release.resolve(true)
await Promise.all(pending)
await dispose()
})
it('restores nested and explicitly cleared boundaries', async () => {
const { service, dispose } = await harness()
const parent = agent('parent')
const child = agent('child')
service.withInitiator(parent, () => {
expect(service.requireInitiator()).toBe(parent)
service.withInitiator(child, () => { expect(service.requireInitiator()).toBe(child) })
expect(service.requireInitiator()).toBe(parent)
service.withoutInitiator(() => {
expect(service.currentInitiator()).toBeUndefined()
expect(() => service.requireInitiator()).toThrow('no initiating agent is active')
})
expect(service.requireInitiator()).toBe(parent)
})
expect(service.currentInitiator()).toBeUndefined()
await dispose()
})
it('restores the parent after synchronous throws and rejected operations', async () => {
const { service, dispose } = await harness()
const parent = agent('parent')
const child = agent('child')
const syncError = new Error('sync failure')
const asyncError = new Error('async failure')
service.withInitiator(parent, () => {
expect(() => service.withInitiator(child, () => { throw syncError })).toThrow(syncError)
expect(service.requireInitiator()).toBe(parent)
})
await expect(service.withInitiator(child, async () => {
await Promise.resolve()
throw asyncError
})).rejects.toBe(asyncError)
expect(service.currentInitiator()).toBeUndefined()
await dispose()
})
it('stops new boundaries, drains active Promises, and invalidates retained references', async () => {
const { ctx, service, dispose } = await harness()
const initiator = agent('draining')
const release = Promise.withResolvers<boolean>()
const pending = service.withInitiator(initiator, async () => {
await release.promise
expect(service.requireInitiator()).toBe(initiator)
})
let disposed = false
const disposal = dispose().then(() => { disposed = true })
await Promise.resolve()
expect(() => service.withInitiator(initiator, () => 1)).toThrow('agent initiator scope is disposed')
expect(() => service.withoutInitiator(() => 1)).toThrow('agent initiator scope is disposed')
expect(disposed).toBe(false)
expect(ctx.get('agents')).toBeUndefined()
release.resolve(true)
await pending
await disposal
expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed')
expect(() => service.requireInitiator()).toThrow('agent initiator scope is disposed')
})
it('drains cross-realm Promise boundaries before disposal', async () => {
const { service, dispose } = await harness()
const initiator = agent('cross-realm')
const release = Promise.withResolvers<boolean>()
const operation = runInNewContext(
'(async () => { await release; inspect() })',
{
release: release.promise,
inspect: () => { expect(service.requireInitiator()).toBe(initiator) },
},
) as () => Promise<void>
const pending = service.withInitiator(initiator, operation)
expect(pending).not.toBeInstanceOf(Promise)
let disposed = false
const disposal = dispose().then(() => { disposed = true })
await Promise.resolve()
expect(disposed).toBe(false)
release.resolve(true)
await pending
await disposal
expect(disposed).toBe(true)
})
it('does not self-deadlock when a boundary returns service disposal', async () => {
const { service, dispose } = await harness()
const initiator = agent('service-disposer')
const returned = service.withInitiator(initiator, dispose)
await promptly(returned)
expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed')
})
it('does not self-deadlock when nested boundaries return ancestor disposal', async () => {
const { ctx, service } = await harness()
const parent = agent('parent-disposer')
const child = agent('child-disposer')
let disposal: Promise<void> | undefined
const returned = service.withInitiator(parent, () => service.withInitiator(child, () => {
disposal = ctx.fiber.dispose()
return disposal
}))
expect(returned).toBe(disposal)
await promptly(returned)
expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed')
})
it('excludes an asynchronous teardown initiator while draining unrelated boundaries', async () => {
const { ctx, service } = await harness()
const initiator = agent('async-disposer')
const unrelated = agent('unrelated')
const release = Promise.withResolvers<boolean>()
const pending = service.withInitiator(unrelated, async () => {
await release.promise
expect(service.requireInitiator()).toBe(unrelated)
})
const returned = service.withInitiator(initiator, async () => {
await Promise.resolve()
await ctx.fiber.dispose()
})
let disposed = false
void returned.then(() => { disposed = true })
await Promise.resolve()
await Promise.resolve()
expect(disposed).toBe(false)
release.resolve(true)
await pending
await promptly(returned)
expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed')
})
})

142
packages/core/agent/tests/agent.spec.ts
View File

@@ -2,15 +2,20 @@ import { describe, expect, expectTypeOf, it } from 'vitest'
import { Context, Service, symbols } from 'cordis'
import type { Events } from 'cordis'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import AgentRegistry, { AgentId, agentEvents } from '@deepseek-ai/dsh-agent'
import AgentRegistry, {
agentEvents,
agentInterruptReasonOf,
normalizeAgentCancelCause,
} from '@deepseek-ai/dsh-agent'
import type { Agent, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent'
function stubAgent(rawId: string): Agent {
const id = AgentId(rawId)
const id = SessionId(rawId)
return {
id,
options: {},
session: new Session(SessionId(`${id}-session`)),
session: new Session(id),
status: 'idle',
ctx: new Context(),
send() {},
@@ -41,6 +46,7 @@ describe('AgentRegistry', () => {
const dispose = ctx.agents.register(agent)
expect(ctx.agents.get(agent.id)).toBe(agent)
expect(ctx.agents.list()).toEqual([agent])
expect(ctx.agents.roots()).toEqual([agent])
expect(() => ctx.agents.register(stubAgent('a1'))).toThrow(/already registered/)
dispose()
@@ -48,6 +54,37 @@ describe('AgentRegistry', () => {
expect(lifecycle).toEqual(['created:a1', 'disposed:a1'])
})
it('rejects an agent whose registry and session identities differ', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
const agent = { ...stubAgent('agent-id'), session: new Session(SessionId('session-id')) }
expect(() => ctx.agents.enter(agent, undefined))
.toThrow('agent id "agent-id" does not match session id "session-id"')
expect(ctx.agents.list()).toEqual([])
})
it('tracks runtime creator ownership separately from registry order', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
const root = stubAgent('root')
const child = stubAgent('child')
const detachRoot = ctx.agents.enter(root, undefined)
ctx.agents.announce(root)
const detachChild = ctx.agents.enter(child, root)
ctx.agents.announce(child)
expect(ctx.agents.list()).toEqual([root, child])
expect(ctx.agents.roots()).toEqual([root])
expect(ctx.agents.isOwnedBy(child.id, root)).toBe(true)
expect(ctx.agents.isOwnedBy(root.id, root)).toBe(false)
expect(ctx.agents.isOwnedBy(SessionId('missing'), root)).toBe(false)
detachChild()
expect(ctx.agents.isOwnedBy(child.id, root)).toBe(false)
detachRoot()
})
it('rolls an entry back and pairs a partially delivered creation when a listener throws', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
@@ -57,7 +94,7 @@ describe('AgentRegistry', () => {
ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`))
expect(() => ctx.agents.register(stubAgent('vetoed'))).toThrow('creation veto')
expect(ctx.agents.get(AgentId('vetoed'))).toBeUndefined()
expect(ctx.agents.get(SessionId('vetoed'))).toBeUndefined()
expect(lifecycle).toEqual(['created:vetoed', 'disposed:vetoed'])
})
@@ -93,7 +130,7 @@ describe('AgentRegistry', () => {
ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`))
const first = stubAgent('split')
const detachFirst = ctx.agents.enter(first)
const detachFirst = ctx.agents.enter(first, undefined)
expect(lifecycle).toEqual([])
ctx.agents.announce(first)
expect(() => { ctx.agents.announce(first) }).toThrow(/already announced/)
@@ -101,7 +138,7 @@ describe('AgentRegistry', () => {
detachFirst()
const replacement = stubAgent('split')
const detachReplacement = ctx.agents.enter(replacement)
const detachReplacement = ctx.agents.enter(replacement, undefined)
detachFirst()
expect(ctx.agents.get(replacement.id)).toBe(replacement)
expect(() => { ctx.agents.announce(first) }).toThrow(/not live/)
@@ -121,7 +158,7 @@ describe('AgentRegistry', () => {
})
ctx.on('agent/created', () => void order.push(`second:${ctx.agents.get(agent.id) === agent}`))
ctx.on('agent/disposed', () => void order.push('disposed'))
const detach = ctx.agents.enter(agent)
const detach = ctx.agents.enter(agent, undefined)
ctx.agents.announce(agent)
expect(order).toEqual(['first:true', 'after-detach:true', 'second:true', 'disposed'])
expect(ctx.agents.get(agent.id)).toBeUndefined()
@@ -149,6 +186,75 @@ describe('agentEvents()', () => {
})
})
describe('explicit cancellation helpers', () => {
it('normalizes exact causes into detached frozen values', () => {
const user = { kind: 'user' as const }
const parent = Object.assign(Object.create(null) as object, { kind: 'parent' })
const normalizedUser = normalizeAgentCancelCause(user)
const normalizedParent = normalizeAgentCancelCause(parent)
expect(normalizedUser).toEqual({ kind: 'user' })
expect(normalizedUser).not.toBe(user)
expect(Object.isFrozen(normalizedUser)).toBe(true)
expect(normalizedParent).toEqual({ kind: 'parent' })
expect(Object.getPrototypeOf(normalizedParent)).toBe(Object.prototype)
expect(Object.isFrozen(normalizedParent)).toBe(true)
})
it.each([
undefined,
null,
'user',
[],
new Error('user'),
{ kind: 'user', detail: true },
Object.assign({ kind: 'user' }, { [Symbol('extra')]: true }),
{ kind: 'timeout' },
])('rejects unsupported cancellation cause %#', (cause) => {
expect(() => normalizeAgentCancelCause(cause)).toThrow(TypeError)
})
it('reads only supported reasons from an explicit signal', () => {
const live = new AbortController()
expect(agentInterruptReasonOf(live.signal)).toBeUndefined()
const user = new AbortController()
user.abort({ kind: 'user' })
expect(agentInterruptReasonOf(user.signal)).toEqual({ kind: 'user' })
const disposed = new AbortController()
disposed.abort(Object.assign(Object.create(null) as object, { kind: 'disposed' }))
const disposedReason = agentInterruptReasonOf(disposed.signal)
expect(disposedReason).toEqual({ kind: 'disposed' })
expect(Object.isFrozen(disposedReason)).toBe(true)
const unsupported = new AbortController()
unsupported.abort(new Error('private runtime reason'))
expect(agentInterruptReasonOf(unsupported.signal)).toBeUndefined()
const primitive = new AbortController()
primitive.abort('private runtime reason')
expect(agentInterruptReasonOf(primitive.signal)).toBeUndefined()
})
it('does not swallow non-validation failures while reading a cause', () => {
let reads = 0
const reason = Object.defineProperty({}, 'kind', {
enumerable: true,
get() {
reads += 1
if (reads === 1) return 'user'
throw new Error('kind getter failed')
},
})
const controller = new AbortController()
controller.abort(reason)
expect(() => agentInterruptReasonOf(controller.signal)).toThrow('kind getter failed')
})
})
describe('AgentRegistry factory seam', () => {
function stubFactory() {
const calls: {
@@ -158,11 +264,11 @@ describe('AgentRegistry factory seam', () => {
const factory: AgentFactory = {
async createAgent(ownerCtx, options) {
calls.create.push({ ownerCtx, options })
return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() }
return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() }
},
async resume(ownerCtx, options) {
calls.resume.push({ ownerCtx, options })
return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() }
return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() }
},
}
return { factory, calls }
@@ -171,15 +277,15 @@ describe('AgentRegistry factory seam', () => {
it('requires a factory and delegates through the calling context', async () => {
const ctx = new Context()
await ctx.plugin(AgentRegistry)
await expect(ctx.agents.create({ agentId: AgentId('a'), sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/)
await expect(ctx.agents.create({ sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/)
const { factory, calls } = stubFactory()
ctx.agents.setFactory(factory)
let callerFiber: Context['fiber'] | undefined
await ctx.plugin(Object.assign(async (inner: Context) => {
callerFiber = inner.fiber
await inner.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') })
await inner.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') })
await inner.agents.create({ sessionId: SessionId('create-s') })
await inner.agents.resume({ resumeSessionId: SessionId('resume-s') })
}, { inject: ['agents'] }))
expect(calls.create[0]?.ownerCtx.fiber).toBe(callerFiber)
expect(calls.resume[0]?.ownerCtx.fiber).toBe(callerFiber)
@@ -192,9 +298,9 @@ describe('AgentRegistry factory seam', () => {
inner.agents.setFactory(stubFactory().factory)
expect(() => inner.agents.setFactory(stubFactory().factory)).toThrow(/already registered/)
}, { inject: ['agents'] }))
await expect(ctx.agents.create({ agentId: AgentId('before'), sessionId: SessionId('before-s') })).resolves.toBeDefined()
await expect(ctx.agents.create({ sessionId: SessionId('before-s') })).resolves.toBeDefined()
await owner.dispose()
await expect(ctx.agents.create({ agentId: AgentId('after'), sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/)
await expect(ctx.agents.create({ sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/)
})
it('canonicalizes an already traced Service before tracing it for the caller', async () => {
@@ -214,18 +320,18 @@ describe('AgentRegistry factory seam', () => {
}
async createAgent(_ownerCtx: Context, options: CreateAgentOptions) {
this.calls().push('create')
return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() }
return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() }
}
async resume(_ownerCtx: Context, options: ResumeAgentOptions) {
this.calls().push('resume')
return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() }
return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() }
}
}
await ctx.plugin(TracedFactory)
const traced = (ctx as Context & { tracedFactory: TracedFactory }).tracedFactory
ctx.agents.setFactory(traced)
await ctx.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') })
await ctx.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') })
await ctx.agents.create({ sessionId: SessionId('create-s') })
await ctx.agents.resume({ resumeSessionId: SessionId('resume-s') })
const raw = (traced as unknown as { [symbols.original]?: TracedFactory })[symbols.original]
expect(states.get(raw!)).toEqual(['create', 'resume'])
})

61
packages/core/agent/tests/gen-cordis-catalog.spec.ts
View File

@@ -1,12 +1,13 @@
/**
* Negative-path tests for the cordis catalog generator (`scripts/gen-cordis-catalog.ts`).
* Contract and negative-path tests for the cordis catalog generator
* (`scripts/gen-cordis-catalog.ts`).
*/
import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import { collectEvents, collectServices } from '../../../../scripts/gen-cordis-catalog.ts'
import { collectEvents, collectServices, renderEvents, renderServices } from '../../../../scripts/gen-cordis-catalog.ts'
/** Write a fixture package exposing one `interface Events` block and return the
* scan root to hand `collectEvents`. */
@@ -58,6 +59,8 @@ describe('gen-cordis-catalog collectEvents', () => {
))
expect(events).toHaveLength(1)
expect(events[0]).toMatchObject({ name: 'fix/happened', scope: 'fix', mode: 'emit', doc: 'A thing happened.' })
expect(events[0]?.jsDoc).toBe('/**\n * A thing happened.\n * @param id - which thing.\n * @mode emit\n */')
expect(renderEvents(events)).toContain("```ts cordis-catalog\n/**\n * A thing happened.\n * @param id - which thing.\n * @mode emit\n */\n'fix/happened'(id: string): void\n```")
})
it('classifies a trailing-next signature as a waterfall', () => {
@@ -74,6 +77,33 @@ describe('gen-cordis-catalog collectEvents', () => {
expect(events[0]?.mode).toBe('parallel')
})
it('accepts linked, foundation, generic-parameter, and explicitly exempt signature types', () => {
const events = collectEvents(make(
' /**\n * Carry linked and foundation types.\n * @param value - the linked value.\n * @param preset - deployment metadata outside the core catalog.\n * @param signal - cancellation.\n * @mode parallel\n */\n \'fix/typed\'<T extends SessionEvent>(value: Readonly<T>, preset: PresetSpec, signal: AbortSignal): Promise<T>',
))
expect(events).toHaveLength(1)
expect(renderEvents(events)).toContain('Types: [SessionEvent](../core-data-structures/core.md)')
expect(renderEvents(events)).not.toContain('[PresetSpec]')
})
it('aggregates every unclassified signature type with its source and remediation', () => {
const expected = new RegExp([
'2 signature type-link coverage violation\\(s\\)',
'fix/one',
'packages/group/fix/src/index.ts',
'MissingOne',
'fix/two',
'packages/group/fix/src/index.ts',
'missingTwo',
'Add it to LINK_MAP',
'FOUNDATION_TYPE_NAMES',
'TYPE_LINK_EXEMPTIONS',
].join('[\\s\\S]*'))
expect(() => collectEvents(make(
' /**\n * First.\n * @param value - first value.\n * @mode emit\n */\n \'fix/one\'(value: MissingOne): void\n /**\n * Second.\n * @param value - second value.\n * @mode emit\n */\n \'fix/two\'(value: missingTwo): void',
))).toThrow(expected)
})
it('hard-errors when an event is missing its @mode tag', () => {
expect(() => collectEvents(make(
' /** No mode here. */\n \'fix/untagged\'(): void',
@@ -158,26 +188,17 @@ export class FixService {
expect(services).toHaveLength(1)
expect(services[0]).toMatchObject({ key: 'fix', type: 'FixService', abstract: false, doc: 'Fixture service.' })
expect(services[0]?.methods).toHaveLength(3)
expect(services[0]?.methods[0]).toEqual({
signature: 'run(id: string): string',
jsDoc: '/**\n * Do the thing.\n * @param id - which thing to do.\n * @returns the outcome of doing it.\n */',
})
expect(renderServices(services)).toContain('```ts cordis-catalog\n/**\n * Do the thing.\n * @param id - which thing to do.\n * @returns the outcome of doing it.\n */\nrun(id: string): string\n\n/** Fire and forget (void needs no @returns). */\npoke(): void')
})
it('extracts an interface service as an abstract seam', () => {
const services = collectServices(makeService(`/** Fixture service interface. */
export interface FixService {
/**
* Do the thing.
* @param id - which thing to do.
* @returns the outcome of doing it.
*/
run(id: string): string
}`))
expect(services).toHaveLength(1)
expect(services[0]).toMatchObject({
key: 'fix',
type: 'FixService',
abstract: true,
doc: 'Fixture service interface.',
})
expect(services[0]?.methods).toEqual(['run(id: string): string'])
it('hard-errors on an unclassified service-method signature type', () => {
expect(() => collectServices(makeService(
'/** Fixture service. */\nexport class FixService {\n /**\n * Use an unknown value.\n * @param value - the value.\n */\n run(value: MissingServiceType): void {}\n}',
))).toThrow(/service method ctx\.fix\.run .* references unclassified type 'MissingServiceType'/)
})
it('hard-errors on a public method with no JSDoc at all', () => {

2
packages/core/scope/README.md
View File

@@ -15,7 +15,7 @@ Scoped registration primitive. `createScope(ctx, key)` creates a tagged Cordis c
## Design contract
The registration context determines both visibility and ownership, preventing a registration from being visible in one scope but disposed with another. Scopes route trusted same-process plugins; they are not sandboxes or authority boundaries. See the [agent-scope RFC](../../../docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals) for rationale and security non-goals.
The registration context determines both visibility and ownership, preventing a registration from being visible in one scope but disposed with another. Scopes route trusted same-process plugins; they are not sandboxes or authority boundaries. See the [agent-scope Agent Note](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals) for rationale and security non-goals.
Handing out a scoped context hands out the minting plugin's service-resolution surface (resolution walks the minting fiber's dependency chain, not the holder's) — mint it from the plugin whose dependencies the scoped registrations need to resolve.

59
packages/core/session/README.md
View File

@@ -8,7 +8,7 @@ Creates and holds event-sourced `Session` instances. Persistence is intentionall
### Public API
- `ctx.sessions.create(id?, { seed?, meta? }?)` validates and detaches durable seed/header data, fills the version and id, defaults `createdAt` to now, publishes the session, and binds it to the calling fiber. Persisted reconstruction supplies its original `createdAt` and `seedLength`.
- `ctx.sessions.create(id?, { seed?, meta? }?)` validates and detaches durable seed/header data, fills the version and id, defaults `createdAt` to now, publishes the session, and binds it to the calling fiber. Persisted reconstruction supplies its original `createdAt`, `seedLength`, and `delegationDepth`.
- `ctx.sessions.flush(session)` dispatches the awaited parallel durability checkpoint through the session's captured scope. Every listener starts and the call waits for all to settle before reporting failure; unpublished, detached, and stale objects reject.
- `ctx.sessions.fork(source, boundary?, childSessionId?): Session` — Resolve a live session object or id, select a seed through the inclusive `boundary` event seq (default: current last event), require that boundary to be `turn/end`, and create a live child session with lineage metadata.
- `ctx.sessions.get(id: SessionId): Session | undefined`
@@ -22,7 +22,7 @@ Use the split lifecycle only when teardown must be ordered with another resource
- `enter(session)` performs the collision check, publishes without announcing, and returns an entry-bound idempotent detach. Concurrent same-id preparations are allowed, but only one entry succeeds; a stale detach cannot remove its replacement.
- `announce(session)` emits the single creation edge and rejects repeat or reentrant announcements. Detach during that dispatch is deferred and later emits the paired disposal edge; an unannounced entry emits neither lifecycle edge.
`dsh-agent-loop` uses this split so final loop flush precedes session detach; see the [ownership RFC](../../../docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md).
`dsh-agent-loop` uses this split so final loop flush precedes session detach; see the [ownership Agent Note](../../../.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md).
### Live service events
@@ -32,13 +32,13 @@ The store pairs announced creation with disposal, publishes post-commit append n
Plain class (not a Cordis Service). Create via `ctx.sessions.create()`.
- `session.append(type, data, opts?)` snapshots and freezes durable data and surface metadata, validates marker shape, provenance, and complete replacement coverage, commits synchronously, then notifies observers with independent failure containment. Reentrant attached-session appends reject, and runtime checks cover widened unions and loaded logs.
- `session.append(type, data, opts?)` snapshots and freezes durable data and surface metadata, validates marker shape, provenance, complete replacement coverage, and content-only single-result `tool/result` rewrites, commits synchronously, then notifies observers with independent failure containment. Reentrant attached-session appends reject, and runtime checks cover widened unions and loaded logs.
- `session.deriveMessages()` incrementally projects each new surface entry once and returns a fresh array over shared frozen messages. Assistant projections preserve provider/model provenance and adapter-private replay state. A surface rewrite rebuilds the projection; there is no raw-log fallback.
- `session.deriveEventMessage(event)` is the canonical per-event projection used by reconstruction and invariants.
- `session.surface` lazily folds only new `surfaceOp` markers; `replaceGeneration` changes on every rewrite.
- `session.surface` exposes the readonly `SessionSurface` view owned by the session's single incremental surface manager; `replaceGeneration` changes on every committed rewrite.
- `session.events` is a cached frozen snapshot invalidated by append; accepted events remain deeply frozen.
- `session.seq`, `session.id` — current sequence and readonly typed identity.
- `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Construction validates the durable record and requires its id to match `session.id`.
- `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`/`delegationDepth`). Construction validates the durable record and requires its id to match `session.id`.
### Lossless JSON utilities
@@ -48,14 +48,15 @@ Durable values need one accepted representation, not a check followed by a secon
- `SurfaceOp` — how an event entered the ordered surface: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace entries from `start` through `end` inclusive — both must be valid surface seqs; `start === end` replaces one entry). Used by compaction to shadow old events without deleting them.
- `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types.
- `foldSurface(events)` — replay the canonical surface contract into detached current event sequences and actual replacement ranges. The same pass rejects non-contiguous seqs, misplaced or malformed metadata, empty or duplicate provenance, non-earlier sources, invalid positional ranges, and replacements that fail to cite every shadowed surface entry; `SurfaceManager` shares the atomic transition while retaining only its incremental sequence cache.
- `SessionSurface` — the readonly live `nodes` and `replaceGeneration` projection exposed by `session.surface`; candidate validation remains private to `Session`.
- `foldSurface(events)` — replay the canonical surface contract into detached current event sequences and actual replacement ranges. The same pass rejects non-contiguous seqs, misplaced or malformed metadata, empty or duplicate provenance, non-earlier sources, invalid positional ranges, replacements that fail to cite every shadowed surface entry, and a `tool/result` replacement that changes anything except one current result's `content`; `SurfaceManager` shares the atomic transition while retaining only its incremental sequence cache.
- `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event; the second detects a surface-eligible event missing its marker when validating a seed or loaded log.
### Request-header reconstruction (`request-header.ts`)
`request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. `messagePrefix` remains separate from derived history. See the [reconstructable-requests RFC](../../../docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md).
`request/header` records a full canonical snapshot of the non-history request envelope with reason `initial`, `resume`, or `change`. `foldRequestHeader()` selects the latest snapshot; legacy delta events and the removed `fallback` reason are rejected. `messagePrefix` remains separate from derived history. See the [reconstructable-requests Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md).
`context/message` defaults to the canonical tagged context projection. A producer may set `envelope: 'raw'` when its `content` already contains the complete model-facing frame, and may attach JSON `meta` for replayable plugin state; metadata remains durable but is excluded from `deriveMessages()`.
`context/message` renders its `content` verbatim as a user-role message, and may attach JSON `meta` for replayable plugin state; metadata remains durable but is excluded from `deriveMessages()`.
### Session event vocabulary (`types.ts`)
@@ -74,37 +75,61 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata)
### Metadata types (`types.ts`)
- `SessionHeader` — session metadata written once when published as `Session.header`, where detachment and deep-freezing enforce immutability at runtime: `{ version, id, createdAt, cwd?, parentSession?, seedLength? }`. Persistence loaders may return mutable detached copies of the same data type. Owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export it rather than own it (which would force a package cycle).
- `SessionHeader` — session metadata written once when published as `Session.header`, where detachment and deep-freezing enforce immutability at runtime: `{ version, id, createdAt, cwd?, parentSession?, seedLength?, delegationDepth? }`. Persistence loaders may return mutable detached copies of the same data type. Owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export it rather than own it (which would force a package cycle).
### Extension points
- Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log.
- Replay/fork: `create(id, { seed })` validates and freezes a contiguous current-format log and rebuilds its surface; request headers require provider/model and assistant messages require provider/model provenance. `fork(source, boundary?, childSessionId?)` selects a completed-turn prefix and records lineage.
- Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface entries behind a summary checkpoint. Tool-pairing boundary policy and its cache belong to the [`dsh-compact` seam](../../compact/compact/README.md), while this package owns ordered surface membership and `replaceGeneration`.
- Compaction: `dsh-compact-basic` appends a `user/message` replacement for summary checkpoints, while `dsh-compact-tool-result-prune` appends a content-only `tool/result` replacement. Tool-pairing boundary policy and its cache belong to the [`dsh-compact` seam](../../compact/compact/README.md), while this package owns ordered surface membership, replacement validation, and `replaceGeneration`.
## Model Experience
### Derived message history
**What the model sees**: The model receives projections of `user/message`, `assistant/message`, and `tool/result` surface entries verbatim. A `context/message` is a user-role message containing exactly `<context source="<source-kind>">`, its content blocks, and `</context>`; `steering/message` uses the identical `<steering source="<source-kind>">` / `</steering>` wrapper. Tool calls live inside assistant messages. Chunks, boundaries, usage, hook records, todo records, and other log-only events add no message.
#### What the model sees
**Token effect**: Appended surface entries are resent on later steps. A `replace` surface operation removes the shadowed entries from future inputs without deleting their raw log records.
The model receives projections of `user/message`, `assistant/message`, `tool/result`, `context/message`, and `steering/message` surface entries verbatim: each is a user- or assistant-role message carrying its content blocks unchanged. Tool calls live inside assistant messages. Chunks, boundaries, usage, hook records, todo records, and other log-only events add no message.
#### Token effect
Appended surface entries are resent on later steps. A `replace` surface operation removes the shadowed entries from future inputs without deleting their raw log records.
#### KV Cache effect
Appended surface entries preserve reusable prefixes. A `replace` operation invalidates reuse from the first shadowed message even though the underlying event log stays append-only.
### Crash-repair result
**What the model sees**: If a persisted turn ended with unanswered tool calls, each synthetic error result contains exactly `Tool call interrupted by a crash; no result was recorded.`
#### What the model sees
**Token effect**: Zero tokens in an intact session. Each repaired call adds this retained error text on resume.
If a persisted turn ended with unanswered tool calls, each synthetic error result contains exactly `Tool call interrupted by a crash; no result was recorded.`
#### Token effect
Zero tokens in an intact session. Each repaired call adds this retained error text on resume.
#### KV Cache effect
Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries.
### Logged request header
**What the model sees**: The session reconstructs the system prompt, tool schemas, call config, and session prefix that the loop actually sent. Header events do not add a second copy to message history; the prefix is prepended outside `deriveMessages()`.
#### What the model sees
**Token effect**: Zero duplicate tokens from logging. The reconstructed prefix, system text, and schemas still incur their normal per-request cost.
The session reconstructs the system prompt, tool schemas, call config, and session prefix that the loop actually sent. Header events do not add a second copy to message history; the prefix is prepended outside `deriveMessages()`.
#### Token effect
Zero duplicate tokens from logging. The reconstructed prefix, system text, and schemas still incur their normal per-request cost.
#### KV Cache effect
Logging causes no invalidation, and exact reconstruction preserves request-prefix identity. A later header with changed prefix, prompt, or schemas may invalidate reuse from its first difference.
## Known Limitations and Deferred Work
- **Session branching/tree** (pi-style entry tree) — deferred unless needed beyond boundary-based `fork()`.
- **`fork()` cuts only at closed-turn boundaries of live sessions** — the boundary must be a `turn/end` event and the source must be in the store; forking a persisted-but-unloaded session is excluded from the [fork API](../../../docs/rfc/implemented/feature/2026-06-30-session-store-fork-api.md).
- **`fork()` cuts only at closed-turn boundaries of live sessions** — the boundary must be a `turn/end` event and the source must be in the store; forking a persisted-but-unloaded session is excluded from the [fork API](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md).
- **`SESSION_FORMAT_VERSION` stays pinned at `0`** — pre-release, no compatibility implied: a backend rejects any other version, and no migration path exists until the first release ([policy](../../../AGENTS.md)).
- **`TurnEndReasonMap` omits the ACP-named `refusal` / `max_turn_requests` variants** — producer-gated: they land when an adapter or the loop first emits them.

108
packages/core/session/src/index.ts
View File

@@ -11,18 +11,19 @@ import { isAbsolute } from 'node:path'
import { deepFreeze } from '@deepseek-ai/dsh-llm'
import { scopeOf, scopeTarget } from '@deepseek-ai/dsh-scope'
import type { Scoped } from '@deepseek-ai/dsh-scope'
import type { ContentBlock, Message, MessageSource } from '@deepseek-ai/dsh-llm'
import type { Message } from '@deepseek-ai/dsh-llm'
import { SESSION_FORMAT_VERSION, SessionId } from './types.ts'
import type { ContextEnvelope, CreateSessionOptions, EpochHeader, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts'
import type { CreateSessionOptions, EpochHeader, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts'
import { snapshotJsonValue } from './json.ts'
import { SurfaceManager } from './surface.ts'
import type { SessionSurface } from './surface.ts'
import { foldRequestHeader } from './request-header.ts'
export * from './types.ts'
export { isJsonValue, snapshotJsonValue } from './json.ts'
export type { JsonValue } from './json.ts'
export { interruptedTurnClosers } from './repair.ts'
export type { SurfaceFoldReplacement, SurfaceFoldResult } from './surface.ts'
export type { SessionSurface, SurfaceFoldReplacement, SurfaceFoldResult } from './surface.ts'
export { foldSurface, isSurfaceEvent, isSurfaceEligibleType } from './surface.ts'
export { canonicalHeader, foldRequestHeader, headerEquals } from './request-header.ts'
@@ -79,21 +80,6 @@ declare module 'cordis' {
}
}
/**
* Render injected context as tagged synthetic user-role content, keeping the
* canonical session vocabulary provider-neutral. Adapter-specific exceptions
* belong in the adapter.
*/
function renderTagged(tag: string, content: ContentBlock[], source: MessageSource): ContentBlock[] {
const open = `<${tag} source=${JSON.stringify(source.kind)}>`
const close = `</${tag}>`
return [
{ type: 'text', text: open },
...content,
{ type: 'text', text: close },
]
}
/** Detach, validate, and freeze the creation metadata published by a session. */
function snapshotSessionHeader(id: SessionId, source?: SessionHeader): SessionHeader {
const input: unknown = source === undefined
@@ -127,6 +113,10 @@ function snapshotSessionHeader(id: SessionId, source?: SessionHeader): SessionHe
&& (typeof record.seedLength !== 'number' || !Number.isSafeInteger(record.seedLength) || record.seedLength < 0)) {
throw new Error('session header seedLength must be a non-negative safe integer')
}
if (record.delegationDepth !== undefined
&& (typeof record.delegationDepth !== 'number' || !Number.isSafeInteger(record.delegationDepth) || record.delegationDepth < 0)) {
throw new Error('session header delegationDepth must be a non-negative safe integer')
}
return deepFreeze(record as unknown as SessionHeader)
}
@@ -227,22 +217,6 @@ interface SessionEntry {
/** Store attachment for the append path; module-private to keep Session store-agnostic publicly. */
const attachments = new WeakMap<Session, SessionEntry>()
/**
* Render one context contribution exactly as it will appear in model history.
* @param content - content blocks supplied by the context producer.
* @param source - attribution used by the canonical context envelope.
* @param envelope - canonical tagged framing or caller-owned raw framing.
* @returns a detached block list ready for the derived model transcript.
*/
export function renderContextContent(
content: ContentBlock[],
source: MessageSource,
envelope: ContextEnvelope = 'context',
): ContentBlock[] {
const cloned = structuredClone(content)
return envelope === 'raw' ? cloned : renderTagged('context', cloned, source)
}
/**
* An event-sourced session: an append-only log of {@link SessionEvent}s.
*
@@ -251,22 +225,12 @@ export function renderContextContent(
*/
export class Session {
private log: SessionEvent[] = []
/** Incremental acceptance state, kept separate from the public lazy view. */
private readonly surfaceValidator = new SurfaceManager(this.log)
/**
* Derived surface — a cached order of message-producing event sequences.
* Lazily rebuilt from `surfaceOp` markers in the log; processes only new
* events (delta) on each access — the log is append-only, so prior events
* never change.
* Undefined until first accessed (including after fork/seed).
*/
private _surface: SurfaceManager | undefined
/** Single incremental owner of surface acceptance and projection state. */
private readonly surfaceManager = new SurfaceManager(this.log)
/** The ordered surface over this session's event log. */
get surface(): SurfaceManager {
if (!this._surface) this._surface = new SurfaceManager(this.log)
return this._surface
get surface(): SessionSurface {
return this.surfaceManager
}
/**
@@ -279,7 +243,12 @@ export class Session {
*/
readonly header: SessionHeader
constructor(public readonly id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) {
/** The session identity, derived from its durable header's single copy. */
get id(): SessionId {
return this.header.id
}
constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) {
if (seed) {
// Validate the seed to the SAME invariants `append` enforces, so a
// replay/fork (`ctx.sessions.create(id, { seed })`) cannot construct a
@@ -304,7 +273,7 @@ export class Session {
// live append and a full-log fold. The candidate is planned before it
// enters `log`, so a failure cannot partially mutate the surface.
try {
this.surfaceValidator.validateNext(snapshot)
this.surfaceManager.validateNext(snapshot)
} catch (error: unknown) {
throw new Error(`invalid seed event at index ${index}: ${error instanceof Error ? error.message : 'invalid surface metadata'}`)
}
@@ -397,7 +366,7 @@ export class Session {
data: dataSnapshot,
...(surfaceMetadataSnapshot as { surfaceOp?: unknown; sourceEventSeqs?: unknown }),
} as unknown as SessionEvent<T>)
this.surfaceValidator.validateNext(event as SessionEvent)
this.surfaceManager.validateNext(event as SessionEvent)
if (entry !== undefined) entry.appending = true
try {
@@ -463,7 +432,7 @@ export class Session {
*
* CACHED: each surface node is projected exactly once, when first seen — a
* call costs O(new nodes), and a surface rewrite (a `replace`;
* {@link SurfaceManager.replaceGeneration}) rebuilds. The returned array is
* {@link SessionSurface.replaceGeneration}) rebuilds. The returned array is
* a fresh snapshot per call (later appends never grow an array a caller
* already holds); the `Message` objects in it are SHARED and **deep-frozen**.
* Their content reuses the already frozen durable event data, so the cache
@@ -471,8 +440,9 @@ export class Session {
* @returns a fresh array of the shared, frozen derived history.
*/
deriveMessages(): Message[] {
const nodes = this.surface.nodes
const generation = this.surface.replaceGeneration
const surface = this.surface
const nodes = surface.nodes
const generation = surface.replaceGeneration
if (generation !== this.derivedGeneration) {
this.derived = []
this.derivedNodes = 0
@@ -499,7 +469,7 @@ export class Session {
* The per-node pure function {@link deriveMessages} folds over the surface;
* an external reconstructor (or the dev invariant) folds the same function
* over a log prefix's surface to rebuild the exact messages any request was
* built from (the reconstructability RFC). The returned message wrapper is
* built from (the reconstructability Agent Note). The returned message wrapper is
* fresh; its content reuses the logged event's already deep-frozen durable
* data, so changing the wrapper cannot rewrite the log and changing content
* throws.
@@ -512,7 +482,18 @@ export class Session {
// trace/replay data.
switch (event.type) {
case 'user/message': {
// Injected context and mid-turn steering project identically to a user
// prompt: content verbatim, in user role. context's `source`/`meta` and
// steering's `turn` are log-only and do not reach the model. Do NOT
// re-add per-type framing (e.g. `<context>`/`<steering>`) here: framing is
// caller-owned — a producer bakes it into `content`, as workspace-context
// does with `<system-reminder>` — or, if reintroduced, must be driven by
// the event `meta` map and a dedicated renderer, keeping this projection a
// verbatim pass-through. See the deferred design note in
// ../../../../.agents/notes/implemented/simplification/2026-07-20-unwrap-injected-content-envelopes.md
case 'user/message':
case 'context/message':
case 'steering/message': {
return { role: 'user', content: event.data.content }
}
case 'assistant/message': {
@@ -529,14 +510,6 @@ export class Session {
content: [{ type: 'tool-result', toolCallId: callId, content, isError }],
}
}
case 'context/message': {
const { content, source, envelope } = event.data
return { role: 'user', content: renderContextContent(content, source, envelope) }
}
case 'steering/message': {
const { content, source } = event.data
return { role: 'user', content: renderTagged('steering', content, source) }
}
default:
// A non-surface event (boundary, chunk, log-only record) projects to
// no message. Merge-extensible union: no assertNever here.
@@ -589,9 +562,9 @@ export class SessionStore extends Service {
* Create a session owned by the calling fiber: disposing that fiber stops
* event notification and removes the session from the store. `options.seed`
* populates the session with a copy of those events (replay/fork);
* `options.meta` attaches creation metadata (validated absolute `cwd`,
* `parentSession` lineage) as the immutable {@link SessionHeader} (the store
* fills `version`/`id`/`createdAt`).
* `options.meta` attaches creation metadata (validated absolute `cwd`, seed
* and parent lineage, and delegation depth) as the immutable
* {@link SessionHeader} (the store fills `version`/`id`/`createdAt`).
*
* For an agent whose session must be torn down IN ORDER with its loop (so the
* loop's final flush is captured before the store attachment ends), do NOT use this
@@ -653,6 +626,7 @@ export class SessionStore extends Service {
...meta?.cwd === undefined ? {} : { cwd: meta.cwd },
...meta?.parentSession === undefined ? {} : { parentSession: meta.parentSession },
...meta?.seedLength === undefined ? {} : { seedLength: meta.seedLength },
...meta?.delegationDepth === undefined ? {} : { delegationDepth: meta.delegationDepth },
}
return new Session(sessionId, seed, header)
}

49
packages/core/session/src/surface.ts
View File

@@ -5,6 +5,7 @@
* @module @deepseek-ai/dsh-session/surface
*/
import { isDeepStrictEqual } from 'node:util'
import type { SessionEvent, SurfaceEvent, SurfaceEventType, SurfaceOp } from './types.ts'
/** Runtime counterpart of the message-producing event union. */
@@ -55,6 +56,14 @@ export interface SurfaceFoldResult {
replacements: SurfaceFoldReplacement[]
}
/** Readonly live projection of the message-producing session events. */
export interface SessionSurface {
/** Current surface event sequences in model-visible order. */
readonly nodes: readonly number[]
/** Monotonic count of committed positional replacements. */
readonly replaceGeneration: number
}
/** Mutable state shared by complete and incremental folds. */
interface SurfaceFoldState {
nodes: number[]
@@ -179,11 +188,37 @@ function replacementRange(
}
}
/** Restrict a tool-result replacement to one current result's content. */
function assertToolResultRewrite(
event: SessionEvent,
shadowedSeqs: readonly number[],
events: readonly SessionEvent[],
): void {
if (event.type !== 'tool/result') return
if (shadowedSeqs.length !== 1) {
throw new Error('tool/result surface replacement must rewrite exactly one current node')
}
for (const originalSeq of shadowedSeqs) {
const original = events[originalSeq]
if (original?.type !== 'tool/result') {
throw new Error('tool/result surface replacement must target a current tool/result')
}
const originalRest = { ...original.data } as Record<string, unknown>
const replacementRest = { ...event.data } as Record<string, unknown>
delete originalRest['content']
delete replacementRest['content']
if (!isDeepStrictEqual(originalRest, replacementRest)) {
throw new Error('tool/result surface replacement may change only content')
}
}
}
/** Validate one event at its replay boundary and prepare its atomic fold transition. */
function planSurfaceEvent(
state: SurfaceFoldState,
event: SessionEvent,
expectedSeq: number,
events: readonly SessionEvent[],
): SurfacePlan | undefined {
if (event.seq !== expectedSeq) {
throw new Error(`session event seq ${event.seq} is not contiguous; expected ${expectedSeq}`)
@@ -196,6 +231,7 @@ function planSurfaceEvent(
}
const range = replacementRange(state, surfaceOp)
assertProvenance(event, range.shadowedSeqs)
assertToolResultRewrite(event, range.shadowedSeqs, events)
return {
kind: 'replace',
seq: event.seq,
@@ -210,8 +246,9 @@ function applySurfaceEvent(
state: SurfaceFoldState,
event: SessionEvent,
expectedSeq: number,
events: readonly SessionEvent[],
): SurfaceFoldReplacement | undefined {
const plan = planSurfaceEvent(state, event, expectedSeq)
const plan = planSurfaceEvent(state, event, expectedSeq, events)
if (plan?.kind === 'append') {
state.nodes.push(plan.seq)
} else if (plan?.kind === 'replace') {
@@ -231,20 +268,20 @@ function applySurfaceEvent(
* Replay a complete session log through the canonical surface fold.
* @param events - session events in contiguous seq order.
* @returns detached current sequences and replacement history.
* @throws when an event violates surface metadata, provenance, or range rules.
* @throws when an event violates surface metadata, provenance, range, or tool-result rewrite rules.
*/
export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult {
const state = createFoldState()
const replacements: SurfaceFoldReplacement[] = []
for (const [index, event] of events.entries()) {
const replacement = applySurfaceEvent(state, event, index)
const replacement = applySurfaceEvent(state, event, index, events)
if (replacement !== undefined) replacements.push(replacement)
}
return { nodes: [...state.nodes], replacements }
}
/** Incremental ordered surface view and append-boundary validator. */
export class SurfaceManager {
export class SurfaceManager implements SessionSurface {
/** Shared transition state; replacement history is not retained. */
private _state = createFoldState()
/** Last processed seq; -1 folds a seeded log on first access. */
@@ -258,7 +295,7 @@ export class SurfaceManager {
*/
validateNext(event: SessionEvent): void {
if (this._lastProcessedSeq < this.log.length - 1) this._processDelta()
planSurfaceEvent(this._state, event, this.log.length)
planSurfaceEvent(this._state, event, this.log.length, this.log)
}
/** Monotonic count of folded positional replacements. */
@@ -277,7 +314,7 @@ export class SurfaceManager {
private _processDelta(): void {
for (let i = this._lastProcessedSeq + 1; i < this.log.length; i++) {
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded by the loop condition
applySurfaceEvent(this._state, this.log[i]!, i)
applySurfaceEvent(this._state, this.log[i]!, i, this.log)
this._lastProcessedSeq = i
}
}

38
packages/core/session/src/types.ts
View File

@@ -2,9 +2,6 @@ import type { Branded } from '@deepseek-ai/dsh-brand'
import type { AssistantProvenance, CallId, ContentBlock, LlmCallConfig, Message, MessageSource, StreamChunk, TokenUsage, ToolSchema } from '@deepseek-ai/dsh-llm'
import type { JsonValue } from './json.ts'
/** Canonical context-tag framing, or caller-owned framing rendered verbatim. */
export type ContextEnvelope = 'context' | 'raw'
/** Identifies one session in the store (and its persistence artifacts). */
export type SessionId = Branded<'SessionId'>
@@ -50,6 +47,12 @@ export 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
}
/**
@@ -69,6 +72,7 @@ export interface CreateSessionOptions {
readonly parentSession?: SessionId
readonly createdAt?: number
readonly seedLength?: number
readonly delegationDepth?: number
}
}
@@ -110,8 +114,8 @@ export interface TurnEndReasonMap {
/** 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 }
/**
@@ -180,40 +184,44 @@ export type RequestHeaderReason = 'initial' | 'resume' | 'change'
*/
export 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. */

2
packages/core/session/tests/properties.spec.ts
View File

@@ -1,5 +1,5 @@
/**
* Property-based tests for the Session event log (the property-testing RFC).
* Property-based tests for the Session event log (the property-testing Agent Note).
*
* Generates arbitrary event logs and asserts the derivation invariants the
* agent loop and replay depend on: deriveMessages is deterministic and

78
packages/core/session/tests/session.spec.ts
View File

@@ -1,10 +1,18 @@
import { describe, expect, it, vi } from 'vitest'
import { describe, expect, expectTypeOf, it, vi } from 'vitest'
import { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import SessionStore, { SESSION_FORMAT_VERSION, Session, SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
import type { CreateSessionOptions, SessionEventType, SessionHeader, TodoItem } from '@deepseek-ai/dsh-session'
import type { CreateSessionOptions, SessionEventType, SessionHeader, SessionSurface, TodoItem } from '@deepseek-ai/dsh-session'
describe('Session', () => {
it('exposes one stable readonly surface view', () => {
const session = new Session(SessionId('surface-view'))
const surface = session.surface
expectTypeOf(surface).toEqualTypeOf<SessionSurface>()
expect(surface).toBe(session.surface)
})
it('derives message history from the event log', () => {
const session = new Session(SessionId('s1'))
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
@@ -50,7 +58,7 @@ describe('Session', () => {
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted' })
})
it('renders context and steering messages as tagged synthetic user content', () => {
it('renders context and steering messages as plain user content', () => {
const session = new Session(SessionId('s2'))
session.append('context/message', {
content: [{ type: 'text', text: 'file changed: a.ts' }],
@@ -64,12 +72,12 @@ describe('Session', () => {
const [contextMessage, steeringMessage] = session.deriveMessages()
expect(contextMessage!.role).toBe('user')
expect(contextMessage!.content[0]).toMatchObject({ type: 'text', text: '<context source="plugin">' })
expect(contextMessage!.content.at(-1)).toMatchObject({ type: 'text', text: '</context>' })
expect(steeringMessage!.content[0]).toMatchObject({ type: 'text', text: '<steering source="user">' })
expect(contextMessage!.content).toEqual([{ type: 'text', text: 'file changed: a.ts' }])
expect(steeringMessage!.role).toBe('user')
expect(steeringMessage!.content).toEqual([{ type: 'text', text: 'focus on tests' }])
})
it('renders raw context without a generic envelope while preserving structured metadata', () => {
it('keeps context meta durable in the event while hiding it from the projection', () => {
const session = new Session(SessionId('s2-raw'))
const meta = {
kind: 'workspace-instructions',
@@ -79,7 +87,6 @@ describe('Session', () => {
session.append('context/message', {
content: [{ type: 'text', text: '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>' }],
source: { kind: 'plugin', plugin: 'workspace-context' },
envelope: 'raw',
meta,
}, { surfaceOp: 'append' })
@@ -884,6 +891,19 @@ describe('SessionStore', () => {
})
})
it('attaches delegationDepth from meta to the header', async () => {
const ctx = new Context()
await ctx.plugin(SessionStore)
const session = ctx.sessions.create(SessionId('delegated-child'), {
meta: { parentSession: SessionId('parent'), delegationDepth: 2 },
})
expect(session.header).toMatchObject({
id: 'delegated-child',
parentSession: 'parent',
delegationDepth: 2,
})
})
it('rejects non-JSON and invalid scalar session metadata', async () => {
const ctx = new Context()
await ctx.plugin(SessionStore)
@@ -895,6 +915,9 @@ describe('SessionStore', () => {
{ meta: { seedLength: '1' }, error: /seedLength must be a non-negative safe integer/ },
{ meta: { seedLength: 0.5 }, error: /seedLength must be a non-negative safe integer/ },
{ meta: { seedLength: -1 }, error: /seedLength must be a non-negative safe integer/ },
{ meta: { delegationDepth: '1' }, error: /delegationDepth must be a non-negative safe integer/ },
{ meta: { delegationDepth: 0.5 }, error: /delegationDepth must be a non-negative safe integer/ },
{ meta: { delegationDepth: -1 }, error: /delegationDepth must be a non-negative safe integer/ },
]
for (const [index, { meta, error }] of cases.entries()) {
@@ -1041,6 +1064,45 @@ describe('SessionStore', () => {
expect(observed).toEqual([appended])
})
it('does not publish a surface transition rejected by internal dispatch', async () => {
const ctx = new Context()
await ctx.plugin(SessionStore)
const session = ctx.sessions.create(SessionId('surface-dispatch-veto'))
session.append('user/message', {
content: [{ type: 'text', text: 'source' }],
source: { kind: 'user' },
}, { surfaceOp: 'append' })
const surface = session.surface
let reject = true
ctx.on('internal/dispatch', (_mode, name) => {
if (name === 'session/event' && reject) {
reject = false
throw new Error('reject surface candidate')
}
})
expect(() => session.append('assistant/message', {
provenance: { provider: 'mock', model: 'mock' },
turn: 1,
step: 1,
content: [{ type: 'text', text: 'replacement' }],
}, {
surfaceOp: { op: 'replace', start: 0, end: 0 },
sourceEventSeqs: [0],
})).toThrow('reject surface candidate')
expect(session.events).toHaveLength(1)
expect(surface.nodes).toEqual([0])
expect(surface.replaceGeneration).toBe(0)
session.append('user/message', {
content: [{ type: 'text', text: 'next' }],
source: { kind: 'user' },
}, { surfaceOp: 'append' })
expect(surface.nodes).toEqual([0, 1])
expect(surface.replaceGeneration).toBe(0)
})
it('resolves session/event dispatch before commit so instrumentation failure cannot hide a logged event', async () => {
const ctx = new Context()
await ctx.plugin(SessionStore)

19
packages/core/session/tests/surface.spec.ts
View File

@@ -142,6 +142,11 @@ describe('SurfaceManager', () => {
it('leaves incremental state unchanged when candidate validation fails', () => {
const s = new Session(SessionId('atomic-validation'))
s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
const surface = s.surface
const nodes = surface.nodes
expect(nodes).toEqual(foldSurface(s.events).nodes)
expect(surface.replaceGeneration).toBe(0)
expect(() => s.append(
'assistant/message',
@@ -150,8 +155,16 @@ describe('SurfaceManager', () => {
)).toThrow(/missing 0/)
expect(s.events).toHaveLength(1)
expect(s.surface).toBe(surface)
expect(surface.nodes).toEqual([0])
expect(surface.replaceGeneration).toBe(0)
expect(surface.nodes).toEqual(foldSurface(s.events).nodes)
s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
expect(s.surface.nodes).toEqual([0, 1])
expect(surface.nodes).toBe(nodes)
expect(surface.nodes).toEqual([0, 1])
expect(surface.replaceGeneration).toBe(0)
expect(surface.nodes).toEqual(foldSurface(s.events).nodes)
})
it('foldSurface rejects a surface-eligible event without its mandatory marker', () => {
@@ -356,8 +369,8 @@ describe('deriveMessages with surface', () => {
s.append('steering/message', { turn: 1, content: [{ type: 'text', text: 'focus' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
const messages = s.deriveMessages()
expect(messages).toHaveLength(2)
expect(messages[0]!.content[0]).toMatchObject({ type: 'text', text: '<context source="plugin">' })
expect(messages[1]!.content[0]).toMatchObject({ type: 'text', text: '<steering source="user">' })
expect(messages[0]!.content).toEqual([{ type: 'text', text: 'file changed' }])
expect(messages[1]!.content).toEqual([{ type: 'text', text: 'focus' }])
})
})

30
packages/core/system-prompt/README.md
View File

@@ -7,7 +7,7 @@ System prompt assembly registry. Plugins contribute ordered sections, tool schem
| Key | Default | Meaning |
|---|---|---|
| `persona` | `''` | The global deployment-persona default: the ONE config-authored prompt fragment, rendered as the order-0 `deployment:persona` section unless an agent-scoped contribution shadows it. A template — complete `{{…}}` groups are interpreted strictly against the registered variables (the shipped loop registers `{{model}}`/`{{cwd}}`), with no escape syntax for literal braces yet. Empty ⇒ the section is dropped at render. |
| `toolOrder` | — | Explicit model-facing tool order, as a list of `ToolSchema.name`s with one `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`): listed tools take their listed position, unlisted tools land at the rest entry in lexicographic name order. Absent ⇒ plain lexicographic name order. Applied to the collected tools BEFORE the `system-prompt/assemble` waterfall — like the sections' `order` sort, it canonicalizes what the registry contributed (registration order is a plugin-load artifact), and a waterfall listener that mutates the list owns the determinism of what it emits. Misconfiguration fails loud: a list without exactly one rest entry, or with duplicates, throws at load; a listed name with no registered tool rejects every `assemble()`; a tool provider returning the reserved rest-entry name also rejects. Under the shipped loop the turn fails before any model request. Why a central list and not per-plugin weights: [Explicit model-facing tool order](../../../docs/rfc/implemented/feature/2026-07-06-explicit-tool-order.md). |
| `toolOrder` | — | Explicit model-facing tool order, as a list of `ToolSchema.name`s with one `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`): listed tools take their listed position, unlisted tools land at the rest entry in lexicographic name order. Absent ⇒ plain lexicographic name order. Applied to the collected tools BEFORE the `system-prompt/assemble` waterfall — like the sections' `order` sort, it canonicalizes what the registry contributed (registration order is a plugin-load artifact), and a waterfall listener that mutates the list owns the determinism of what it emits. Misconfiguration fails loud: a list without exactly one rest entry, or with duplicates, throws at load; a listed name with no registered tool rejects every `assemble()`; a tool provider returning the reserved rest-entry name also rejects. Under the shipped loop the turn fails before any model request. Why a central list and not per-plugin weights: [Explicit model-facing tool order](../../../.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md). |
## Service: `SystemPrompt` (ctx key: `systemPrompt`)
@@ -38,27 +38,43 @@ Merge-extensible: plugins can declare extra fields on `PromptAssembly` and `Asse
- Tool schema providers: `ToolRegistry` registers itself as a tool provider automatically.
- The [`system-prompt/assemble` waterfall](#live-events): cooperatively mutate or replace the assembly per caller.
Design rationale: [the prompt-variables RFC](../../../docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
Design rationale: [the prompt-variables Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
## Model Experience
### System prompt
**What the model sees**: Every assembly starts with the harness identity below, then the configured persona and ordered plugin sections after strict variable interpolation. Empty sections disappear; scoped sections and variables can shadow globals for one agent. The final `system-prompt/assemble` waterfall result is authoritative, so an expert listener's changes determine the delivered prompt and tool schemas.
#### What the model sees
**Token effect**: Identity is a fixed per-request cost. Persona and plugin text are repeated per request and scale with their rendered content.
Every assembly starts with the harness identity below, then the configured persona and ordered plugin sections after strict variable interpolation. Empty sections disappear; scoped sections and variables can shadow globals for one agent. The final `system-prompt/assemble` waterfall result is authoritative, so an expert listener's changes determine the delivered prompt and tool schemas.
#### Harness identity
##### Harness identity
```markdown
You are an AI agent powered by the DeepSeek Harness SDK.
```
#### Token effect
Identity is a fixed per-request cost. Persona and plugin text are repeated per request and scale with their rendered content.
#### KV Cache effect
Prefix-stable while identity, persona, variables, section text, and order render identically. Any change may invalidate reuse from the first changed system-prompt token.
### Tool schemas
**What the model sees**: For shipped tools, the model receives the per-agent-visible subset of the [generated tool schemas](../../../docs/tool-catalog.md#tool-package-map), ordered by configuration or lexicographically after restrictions and assembly interception. Extensions can contribute additional definitions through the same registry. Sections and schema providers are separate assembly inputs, so a tool restriction does not remove independently registered guidance.
#### What the model sees
**Token effect**: Schema tokens repeat on every request. Restricting a tool removes its entire schema cost for that agent but not a separate prompt section; reordering changes cache shape but not semantic content.
For shipped tools, the model receives the per-agent-visible subset of the [generated tool schemas](../../../docs/tool-catalog.md#tool-package-map), ordered by configuration or lexicographically after restrictions and assembly interception. Extensions can contribute additional definitions through the same registry. Sections and schema providers are separate assembly inputs, so a tool restriction does not remove independently registered guidance.
#### Token effect
Schema tokens repeat on every request. Restricting a tool removes its entire schema cost for that agent but not a separate prompt section; reordering changes cache shape but not semantic content.
#### KV Cache effect
Prefix-stable while the visible schema set, rendering, and order are unchanged. Registration, restriction, or reordering may invalidate reuse from the first changed schema token.
## Known Limitations and Deferred Work

60
packages/core/tools/README.md
View File

@@ -16,9 +16,9 @@ tools:
### Public API
- `ctx.tools.register(definition: ToolDefinition): () => void` Register a trusted typed same-process definition. The layer is the calling context's scope: a plain plugin context registers globally; an agent's `agent.ctx` registers for that agent alone, shadowing a same-named global tool there. Duplicate names within one layer throw; non-native modes also reject the reserved `run_code` transport name. `timeoutMs`, when present, must be positive and finite. Disposed with the calling fiber.
- `ctx.tools.restrict(filter)` applies an agent-scoped allow/deny mask to global tools and throws from a plain context. The filter is snapshotted at registration; multiple masks intersect and scope-local tools merge afterwards. Deny masks admit later unnamed globals, while allow masks exclude later names. Unknown, local, or reserved names and empty filters reject. This is live visibility composition, not an authority boundary; see the [scope security non-goal](../../../docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals).
- `ctx.tools.restrict(filter)` applies an agent-scoped allow/deny mask to global tools and throws from a plain context. The filter is snapshotted at registration; multiple masks intersect and scope-local tools merge afterwards. Deny masks admit later unnamed globals, while allow masks exclude later names. Unknown, local, or reserved names and empty filters reject. This is live visibility composition, not an authority boundary; see the [scope security non-goal](../../../.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md#security-and-authority-are-explicit-non-goals).
- `ctx.tools.get(name: string, scope?: ScopeKey): ToolDefinition | undefined` Resolution as one scope sees it (shadowing applied; a restricted-away global reads as absent) — presenters pass the calling agent so the card matches what executed.
- `ctx.tools.schemas(scope?: ScopeKey): ToolSchema[]` Schemas of everything the scope can see (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog RFC](../../../docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md)).
- `ctx.tools.schemas(scope?: ScopeKey): ToolSchema[]` Schemas of everything the scope can see (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog Agent Note](../../../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md)).
- `ctx.tools.guard(guard: ToolGuard): () => void` Register a monotonic synchronous execution guard after `tools/pre-execute`: returning a reason denies the call, while `undefined` leaves it unchanged. A plain-context guard applies globally; an `agent.ctx` guard applies only to that agent. Later waterfall listeners cannot turn a guard denial back into permission. Disposed with the calling fiber.
- `ctx.tools.execute(exec)` losslessly snapshots and freezes arguments, assigns an opaque token, runs the complete policy/dispatch/result pipeline, then independently snapshots the authoritative outcome before final observation. Invalid arguments use the same result path without reaching policy or the body; around wrappers may replace only `signal`.
- `ctx.tools.executionMode(exec)` returns `parallel` only when the visible definition's `isConcurrencySafe(exec.arguments)` classifier returns exactly `true`; unknown, hidden, undeclared, invalid, or throwing classifications are exclusive.
@@ -38,7 +38,7 @@ The live registry pipeline has three transformable waterfalls followed by the ob
- `ToolExecutionToken` — a fresh branded `Symbol` assigned by the registry. It supports equality correlation only and never crosses a model, log, or worker boundary.
- `ToolExecution` — the pipeline-owned call: immutable `{ token, callId, name, arguments, agent?, parent? }` identity plus optional operational `signal`, which an around wrapper may add, replace, remove, and restore. A nested call's `parent` is a `ToolExecutionToken`, not an execution object.
- `ToolRunContext` — the execution passed to a tool body, extending `ToolExecution` with `deferContext(context)`. Composite tools use it to ferry context produced by nested dispatches to the outer result even when the tool later throws; it never injects immediately.
- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ content, isError, error?, additionalContexts?, meta? }`. Call identity stays on the immutable `ToolExecution` supplied alongside the result instead of being duplicated on the outcome. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text. `additionalContexts` preserves each deferred or post-execute `HookContext` with its own source, envelope, and durable JSON metadata; the loop buffers the array and appends each entry as a `context/message` after all `tool/result`s in the step.
- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ content, isError, error?, additionalContexts?, meta? }`. Call identity stays on the immutable `ToolExecution` supplied alongside the result instead of being duplicated on the outcome. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text. `additionalContexts` preserves each deferred or post-execute `HookContext` with its own source and durable JSON metadata; the loop buffers the array and appends each entry as a `context/message` after all `tool/result`s in the step.
- `PreToolDecision` — `{kind:'allow'}` | `{kind:'deny', reason}` | `{kind:'ask', reason?}`. Input rewrite is deliberately not offered; `ask` is serviced by [`ctx.approval`](../../ui/user-approval/README.md) when mounted and otherwise degrades to deny.
- `PostToolDecision` — `{kind:'accept', content?, additionalContexts?}` (keep the call successful, optionally replacing the model-facing content) | `{kind:'block', feedback, additionalContexts?}` (turn it into an `isError` whose content is the corrective feedback). Accept preserves tool-deferred contexts before decision contexts; block discards tool-deferred contexts and exposes only contexts explicitly supplied by the blocking decision.
- `ToolGuard` — `(execution) => string | undefined`; the returned string is a final monotonic denial reason evaluated after the reorderable pre-execute waterfall and before dispatch.
@@ -88,7 +88,7 @@ See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, an
Optional `timeoutMs` must be positive and finite; it is policy metadata, not model-visible schema.
Optional `isConcurrencySafe(args)` receives typed, softly validated arguments. Exact `true` permits concurrent dispatch/body execution; invalid input and all other outcomes remain exclusive. Opted-in bodies do not mutate parent-owned state, and shared-state races must commute or fail closed. The [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the full safety contract.
Optional `isConcurrencySafe(args)` receives typed, softly validated arguments. Exact `true` permits concurrent dispatch/body execution; invalid input and all other outcomes remain exclusive. Opted-in bodies do not mutate parent-owned state, and shared-state races must commute or fail closed. The [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the full safety contract.
### Structured-output schema subset
@@ -101,35 +101,43 @@ Tools optionally own pure `presentCall()` and `presentResult()` render intents,
- Call views are `{ card: 'generic', title, kind?, rawInput?, content?, locations? }`, `{ card: 'terminal', title, description?, cwd? }`, or `{ card: 'diff', title, diffs, locations? }`.
- Result views are `{ card: 'generic', title?, content? }`, `{ card: 'terminal', title?, output?, exitCode?, signal? }`, or `{ card: 'diff', title?, diffs }`.
Returning `undefined` selects generic fallback. Presenters depend only on their arguments because UIs call them during live streaming and log replay. Result presentation may read JSON-serializable `result.meta`, which persists with the result; `defineTool` soft-validates older logged arguments and falls back instead of crashing replay. `dsh-tool-bash` and `dsh-tool-fs` are the reference implementations; the [render-intent RFC](../../../docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md) owns the rationale.
Returning `undefined` selects generic fallback. Presenters depend only on their arguments because UIs call them during live streaming and log replay. Result presentation may read JSON-serializable `result.meta`, which persists with the result; `defineTool` soft-validates older logged arguments and falls back instead of crashing replay. `dsh-tool-bash` and `dsh-tool-fs` are the reference implementations; the [render-intent Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md) owns the rationale.
### Code Mode
Under `code` or `both`, the registry exposes the reserved `run_code` transport and a deterministic TypeScript SDK for the current scope; only program output re-enters model context. Each JSON-normalized binding re-enters the complete tool pipeline sequentially with logged correlation to the outer call. Denials reject that binding, ordinary side effects are not rolled back, and sub-call `additionalContexts` are deferred through the parent result to preserve call/result adjacency. Run settlement aborts and drains outstanding bindings; failures surface as `CodeRunFailedError`. See the [Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) and [code-runtime seam](../../code-runtime/README.md). Try `pnpm run demo:code-mode`.
Under `code` or `both`, the registry exposes the reserved `run_code` transport and a deterministic TypeScript SDK for the current scope; only program output re-enters model context. Each JSON-normalized binding re-enters the complete tool pipeline sequentially with logged correlation to the outer call. Denials reject that binding, ordinary side effects are not rolled back, and sub-call `additionalContexts` are deferred through the parent result to preserve call/result adjacency. Run settlement aborts and drains outstanding bindings; failures surface as `CodeRunFailedError`. See the [Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md) and [code-runtime seam](../../code-runtime/README.md). Try `pnpm run demo:code-mode`.
- **The SDK section** (`tools:sdk`, order 150): a lazy prompt section regenerating, at each assembly, a `declare const tools: {...}` TypeScript declaration of the calling scope's visible end capabilities (exotic names via quoted keys), plus fixed usage instructions. Deterministic — lexicographic tool order, byte-identical text for an unchanged tool set (prefix-cache-friendly). The codegen (`jsonSchemaToTs`, exported) is total: constructs outside the `defineTool` subset degrade to `unknown`, never throw.
- **The dispatch bridge** (`run_code`'s execute): every binding call is JSON-normalized before dispatch (a value that does not survive — `BigInt`, circulars — rejects that one call, so the dispatched form and logged form are the same JSON value by construction), serialized through a per-run queue (even `Promise.all` executes underlying calls one at a time in submission order), given the outer execution's opaque token as `parent`, and run through the complete pre-execute → guards → execute → post-execute → result pipeline. A denial reaches the program as a binding rejection, and each sub-call is logged as a `tool/code-dispatch` session event with deterministic id `<parent>:code:<n>`; `deriveMessages()` does not surface that event. Token correlation lets commit-style observers defer an inner success until the final `run_code` result without exposing the live outer execution; ordinary tool side effects are not rolled back. Every sub-call `additionalContexts` entry is deferred through the outer `ToolRunContext` in dispatch order; the loop appends those contexts only after the parent `run_code` result, preserving adjacency and retaining each source/envelope/meta even when the program later fails.
- **The dispatch bridge** (`run_code`'s execute): every binding call is JSON-normalized before dispatch (a value that does not survive — `BigInt`, circulars — rejects that one call, so the dispatched form and logged form are the same JSON value by construction), serialized through a per-run queue (even `Promise.all` executes underlying calls one at a time in submission order), given the outer execution's opaque token as `parent`, and run through the complete pre-execute → guards → execute → post-execute → result pipeline. A denial reaches the program as a binding rejection, and each sub-call is logged as a `tool/code-dispatch` session event with deterministic id `<parent>:code:<n>`; `deriveMessages()` does not surface that event. Token correlation lets commit-style observers defer an inner success until the final `run_code` result without exposing the live outer execution; ordinary tool side effects are not rolled back. Every sub-call `additionalContexts` entry is deferred through the outer `ToolRunContext` in dispatch order; the loop appends those contexts only after the parent `run_code` result, preserving adjacency and retaining each source/meta even when the program later fails.
- **Settlement discipline**: the bridge owns a run-scoped abort that follows the outer signal in and fires when the run settles for any reason, so a budget expiry aborts an in-flight sub-tool instead of orphaning it; the bridge then drains its queue BEFORE returning, so every `tool/code-dispatch` lands inside the open turn. A failed run throws `CodeRunFailedError` (`code: 'CODE_RUN_FAILED'`, message = the failure kind + captured logs), which the pipeline converts to a structured `isError` the model self-corrects from.
### Parallel execution
The agent loop groups consecutive `parallel` calls into a bounded rolling pool and treats each `exclusive` call as an ordering barrier. Only dispatch/body overlaps; policy, durable results, and context retain model order. Code Mode bindings remain serial. The [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the shipped declarations and rationale.
The agent loop groups consecutive `parallel` calls into a bounded rolling pool and treats each `exclusive` call as an ordering barrier. Only dispatch/body overlaps; policy, durable results, and context retain model order. Code Mode bindings remain serial. The [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md) owns the shipped declarations and rationale.
## Model Experience
### Normal tool schemas
**What the model sees**: In normal mode the model sees each visible definition's exact name, description, and JSON schema; the shipped definitions are recorded in the generated [tool package map and schema sections](../../../docs/tool-catalog.md#tool-package-map). Agent-scoped restrictions, shadows, and extension registrations change that agent's end-tool set.
#### What the model sees
**Token effect**: Fixed per-request cost proportional to the visible definitions. Restrictions that hide tools remove their entire schema cost for that agent.
In normal mode the model sees each visible definition's exact name, description, and JSON schema; the shipped definitions are recorded in the generated [tool package map and schema sections](../../../docs/tool-catalog.md#tool-package-map). Agent-scoped restrictions, shadows, and extension registrations change that agent's end-tool set.
#### Token effect
Fixed per-request cost proportional to the visible definitions. Restrictions that hide tools remove their entire schema cost for that agent.
#### KV Cache effect
Prefix-stable while visible definitions and their order are unchanged. Registration, disposal, or scoped restriction may invalidate reuse from the first changed schema token.
### Code Mode schema and system prompt
**What the model sees**: Code Mode exposes the generated [`run_code` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tools), the SDK instructions below, and the generated exact `declare const tools` block. `both` exposes normal schemas and this Code Mode surface.
#### What the model sees
**Token effect**: Fixed per-request cost proportional to the visible definitions. Code Mode trades end-tool schemas for generated SDK text plus one transport schema rather than promising a universal reduction.
Code Mode exposes the generated [`run_code` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tools), the SDK instructions below, and the generated exact `declare const tools` block. `both` exposes normal schemas and this Code Mode surface.
#### Code Mode SDK instructions
##### Code Mode SDK instructions
```markdown
## Writing code for run_code
@@ -144,18 +152,34 @@ Pass `run_code` the body of an async TypeScript function (erasable syntax only
The available tools:
```
#### Token effect
Fixed per-request cost proportional to the visible definitions. Code Mode trades end-tool schemas for generated SDK text plus one transport schema rather than promising a universal reduction.
#### KV Cache effect
Prefix-stable while the Code Mode selection, generated SDK, transport schema, and visible tool set are unchanged. Mode or filter changes may invalidate reuse from the first changed prompt or schema token.
### Tool-call history and results
**What the model sees**: The loop retains model-emitted arguments and the registry's final content. Any thrown or denied call becomes exactly `Error: <message>`. Code Mode returns only the outer program's printed lines and rendered return value, `(run_code completed with no output)` when both are empty, or `Error: code run failed (<kind>): <message>` followed conditionally by `Captured output:` and the captured lines. Inner dispatch events stay log-only; post-execute listeners may append source-attributed context after the result.
#### What the model sees
**Token effect**: Arguments, results, and additional context are data-dependent and resent until compaction. Restrictions that hide tools also remove their schemas before the model can call them.
The loop retains model-emitted arguments and the registry's final content. Any thrown or denied call becomes exactly `Error: <message>`. Code Mode returns only the outer program's printed lines and rendered return value, `(run_code completed with no output)` when both are empty, or `Error: code run failed (<kind>): <message>` followed conditionally by `Captured output:` and the captured lines. Inner dispatch events stay log-only; post-execute listeners may append source-attributed context after the result.
#### Token effect
Arguments, results, and additional context are data-dependent and resent until compaction. Restrictions that hide tools also remove their schemas before the model can call them.
#### KV Cache effect
Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries.
## Known Limitations and Deferred Work
- **Concurrency policy is not an event seam** — `executionMode()` reads the resolved tool definition directly; plugins can only declare a classifier on definitions they own.
- **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md).
- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and never applies `default` (`XXX(unused-default)` flags removing that field); raw-registered JSON-Schema tools validate their own input.
- **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md).
- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and preserves `default` as a model-visible JSON Schema annotation without applying it during validation; dynamic Cordis mounts may supply defaults even though first-party definitions do not, while raw-registered JSON-Schema tools validate their own input.
- **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-timeout-policy` wrapper.
- **Code Mode is TypeScript-only and the presentation mode is service-wide** — `mode: code`/`both` rejects prompt assembly unless `ctx.codeRuntime.language === 'typescript'`; scoped restrictions/shadows still choose each agent's visible bindings, but one tool cannot be native-only while another is code-only.
- **Code Mode bindings return text only** — non-text content blocks in a sub-call result collapse to `[<type> content]` placeholders.
- **`run_code` state is fresh per run** — a persistent REPL-style kernel is rejected for the MVP (cross-call state would be invisible to the log); see [the Code Mode RFC](../../../docs/rfc/implemented/feature/2026-06-15-code-mode.md).
- **`run_code` state is fresh per run** — a persistent REPL-style kernel is rejected for the MVP (cross-call state would be invisible to the log); see [the Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md).

15
packages/core/tools/src/index.ts
View File

@@ -139,7 +139,7 @@ export interface ToolDefinition extends ToolSchema {
* Opted-in executions must not mutate parent-owned state. Shared state must
* tolerate concurrent dispatch; recorder races are permitted only when they
* commute or fail closed. See the
* [parallel-tool-call RFC](../../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)
* [parallel-tool-call Agent Note](../../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)
* for the full contract.
* @param args - parsed arguments; `defineTool` validates before calling.
* @returns Whether this call may join a parallel group.
@@ -235,8 +235,8 @@ export interface ToolExecution extends ToolExecutionInput {
export 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
}
@@ -958,14 +958,19 @@ export class ToolRegistry extends Service {
// Freeze the remaining mutable signal slot before observers receive the
// shared WeakMap-keyable execution object.
Object.freeze(exec)
const { name: toolName, callId } = exec
const reportFailure = (error: unknown): void => {
this.ctx.logger.warn(`tool "${toolName}" (${callId}): tools/result observer failed: ${errorMessage(error)}`)
}
const callbacks = this.ctx.events.dispatch('emit', [
scopeTarget(this, exec.agent), 'tools/result', exec, result,
])
for (const callback of callbacks) {
try {
callback(exec, result)
const returned: unknown = callback(exec, result)
void Promise.resolve(returned).catch(reportFailure)
} catch (error: unknown) {
this.ctx.logger.warn(`tool "${exec.name}" (${exec.callId}): tools/result observer failed: ${errorMessage(error)}`)
reportFailure(error)
}
}
}

8
packages/core/tools/src/schema.ts
View File

@@ -21,12 +21,8 @@ export interface SchemaProp {
/** Enum of allowed values (strings only). */
enum?: string[]
/**
* Default value, emitted into the JSON Schema only (validation never applies
* it — see the validator note below).
*
* XXX(unused-default): no tool definition in the repo sets `default`; it rides
* into the wire schema for a model that no tool surfaces it to. Drop the field
* and its converter line unless a real tool needs a model-visible default.
* Model-visible JSON Schema default annotation. Validation does not apply it;
* dynamic tool mounts may supply it even though first-party definitions do not.
*/
default?: unknown
/** Nested properties for type: 'object'. */

2
packages/core/tools/src/ts-types.ts
View File

@@ -75,7 +75,7 @@ export function jsonSchemaToTs(schema: unknown, indent = 0): string {
}
}
/** The fixed model-facing usage contract rendered above the declarations (see the Code Mode RFC's "What the model sees"). */
/** The fixed model-facing usage contract rendered above the declarations (see the Code Mode Agent Note's "What the model sees"). */
const SDK_INSTRUCTIONS = `## Writing code for run_code
Pass \`run_code\` the body of an async TypeScript function (erasable syntax only — no \`enum\` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:

8
packages/core/tools/tests/code-mode.spec.ts
View File

@@ -8,13 +8,12 @@ import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools'
import type { Config, PostToolDecision, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
import { AgentId } from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEventMap } from '@deepseek-ai/dsh-session'
/**
* Code Mode unit tier (per the RFC's plan): provider contribution per mode,
* Code Mode unit tier (per the Agent Note's plan): provider contribution per mode,
* misconfiguration rejections, the run_code dispatch bridge (serialization,
* abort, JSON normalization, error mapping, events, quiescence), and HMR
* safety — all against an in-repo fake runtime, exactly the
@@ -59,7 +58,7 @@ async function setup(options: SetupOptions = {}) {
/** Mint one production-shaped agent scope that can register scoped tool policy. */
async function mintAgentScope(ctx: Context, name = 'scoped'): Promise<{ scope: Scope; agent: Agent }> {
const agent = { id: AgentId(name) } as Agent
const agent = { id: SessionId(name) } as Agent
let scope!: Scope
await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, agent) },
{ inject: ['tools', 'systemPrompt'] }))
@@ -488,7 +487,6 @@ describe('the run_code dispatch bridge', () => {
additionalContexts: [{
content: [{ type: 'text' as const, text: `context for ${exec.callId}` }],
source: { kind: 'plugin' as const, plugin: 'test' },
envelope: 'raw' as const,
meta: { callId: exec.callId },
}],
})
@@ -506,13 +504,11 @@ describe('the run_code dispatch bridge', () => {
{
content: [{ type: 'text', text: 'context for call-1:code:1' }],
source: { kind: 'plugin', plugin: 'test' },
envelope: 'raw',
meta: { callId: 'call-1:code:1' },
},
{
content: [{ type: 'text', text: 'context for call-1:code:2' }],
source: { kind: 'plugin', plugin: 'test' },
envelope: 'raw',
meta: { callId: 'call-1:code:2' },
},
])

13
packages/core/tools/tests/gen-tool-catalog.spec.ts
View File

@@ -49,6 +49,19 @@ describe('gen-tool-catalog collectToolCatalog', () => {
expect(bash?.source).toBe('packages/bash/tool-bash/src/index.ts')
})
it('harvests search tools without depending on the generator process PATH', async () => {
const oldPath = process.env.PATH
try {
process.env.PATH = ''
const catalog = await collectToolCatalog()
const search = catalog.find(entry => entry.pkg === '@deepseek-ai/dsh-tool-fs-search')
expect(search?.schemas.map(s => s.name).sort()).toEqual(['glob', 'grep'])
} finally {
if (oldPath === undefined) delete process.env.PATH
else process.env.PATH = oldPath
}
})
it('records the shipped `subagent_fork` alias in a note (config-driven tool name)', async () => {
// `tool-subagent`'s registered name is the load-time `toolName` config, so the shipped
// agents surface this one package as both `subagent` and `subagent_fork`.

4
packages/core/tools/tests/properties.spec.ts
View File

@@ -1,8 +1,8 @@
/**
* Property-based tests for the tool-schema DSL (the property-testing RFC), including
* Property-based tests for the tool-schema DSL (the property-testing Agent Note), including
* the the property-testing ↔ runtime-validation composition composition: generated args that satisfy a SchemaSpec must
* pass validateArgs, and targeted corruptions must be rejected. This closes the
* validator/InferArgs drift risk noted in the arg-validation RFC.
* validator/InferArgs drift risk noted in the arg-validation Agent Note.
*/
import { describe, expect, it } from 'vitest'

23
packages/core/tools/tests/scoped.spec.ts
View File

@@ -6,9 +6,11 @@ import type { Scope } from '@deepseek-ai/dsh-scope'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import type { PreToolDecision, ToolDefinition, ToolExecution, ToolExecutionInput, ToolExecutionToken } from '@deepseek-ai/dsh-tools'
import type { Agent, AgentId } from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { CallId } from '@deepseek-ai/dsh-llm'
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
import type { SessionId } from '@deepseek-ai/dsh-session'
/** Mount the registry (with its systemPrompt dependency) on a fresh context. */
async function mount(): Promise<Context> {
@@ -20,7 +22,7 @@ async function mount(): Promise<Context> {
/** Mint a scope whose key doubles as a minimal Agent-like object. */
async function mintAgentScope(ctx: Context, name: string): Promise<{ scope: Scope; key: Agent }> {
const key = { id: name as AgentId } as Agent
const key = { id: name as SessionId } as Agent
let scope!: Scope
// The scoped context resolves services through the MINTING plugin's
// dependency chain — the minter must inject what scope holders will reach
@@ -62,7 +64,7 @@ describe('scoped tool registration', () => {
it('files a scoped tool in its layer: visible/executable for that scope only', async () => {
const ctx = await mount()
const { scope, key } = await mintAgentScope(ctx, 'a')
const other = { id: 'other' as AgentId } as Agent
const other = { id: 'other' as SessionId } as Agent
ctx.tools.register(tool('shared'))
scope.ctx.tools.register(tool('mine'))
@@ -195,7 +197,7 @@ describe('scoped execution dispatch', () => {
it('an agent.ctx pre-execute listener gates only its own agent (and never subject-less calls)', async () => {
const ctx = await mount()
const { scope, key } = await mintAgentScope(ctx, 'a')
const other = { id: 'other' as AgentId } as Agent
const other = { id: 'other' as SessionId } as Agent
ctx.tools.register(tool('t'))
const seen: (string | undefined)[] = []
@@ -213,7 +215,7 @@ describe('scoped execution dispatch', () => {
it('applies scoped guards after pre-execute and unwinds duplicate registrations independently', async () => {
const ctx = await mount()
const { scope, key } = await mintAgentScope(ctx, 'a')
const other = { id: 'other' as AgentId } as Agent
const other = { id: 'other' as SessionId } as Agent
let bodyCalls = 0
ctx.tools.register({
...tool('t'),
@@ -428,7 +430,7 @@ describe('scoped execution dispatch', () => {
it('uses one input snapshot for the normalized error shell', async () => {
const ctx = await mount()
const { scope, key } = await mintAgentScope(ctx, 'accepted')
const driftAgent = { id: 'drift' as AgentId } as Agent
const driftAgent = { id: 'drift' as SessionId } as Agent
ctx.tools.register(tool('parent'))
ctx.tools.register(tool('t'))
let parent!: ToolExecutionToken
@@ -580,13 +582,18 @@ describe('scoped execution dispatch', () => {
ctx.on('tools/result', () => {
throw { toString: () => { throw new Error('coercion trap') } }
})
ctx.on('tools/result', () => Promise.reject(new Error('async observer failure')) as never)
ctx.on('tools/result', (_exec, result) => { seen.push(result.isError) })
const result = await ctx.tools.execute({ callId: CallId('final'), name: 't', arguments: {}, agent: key })
await Promise.resolve()
expect(result).toMatchObject({ isError: true, content: [{ type: 'text', text: 'outer failure' }] })
expect(seen).toEqual([true, true])
expect(dispatchModes).toEqual(['emit'])
expect(warn).toHaveBeenCalledOnce()
expect(String(warn.mock.calls[0]?.[0])).toContain('<unprintable thrown value>')
expect(warn).toHaveBeenCalledTimes(2)
expect(warn.mock.calls.map(call => String(call[0]))).toEqual(expect.arrayContaining([
expect.stringContaining('<unprintable thrown value>'),
expect.stringContaining('async observer failure'),
]))
})
})

7
packages/core/tools/tests/tools.spec.ts
View File

@@ -384,7 +384,7 @@ describe('ToolRegistry', () => {
parameters: {},
async execute(_args, exec) {
exec.deferContext({ content: [{ type: 'text', text: 'nested-1' }], source: { kind: 'plugin', plugin: 'nested-1' }, meta: { n: 1 } })
exec.deferContext({ content: [{ type: 'text', text: 'nested-2' }], source: { kind: 'plugin', plugin: 'nested-2' }, envelope: 'raw' })
exec.deferContext({ content: [{ type: 'text', text: 'nested-2' }], source: { kind: 'plugin', plugin: 'nested-2' } })
return [{ type: 'text', text: 'done' }]
},
}))
@@ -418,7 +418,6 @@ describe('ToolRegistry', () => {
{ kind: 'plugin', plugin: 'post' },
])
expect(result.additionalContexts?.[0]?.meta).toEqual({ n: 1 })
expect(result.additionalContexts?.[1]?.envelope).toBe('raw')
})
it('keeps deferred contexts when a composite tool throws, but drops them when the outer call is blocked', async () => {
@@ -1174,7 +1173,7 @@ describe('ToolRegistry.get', () => {
})
})
describe('validateArgs (the runtime-validation RFC, part 1)', () => {
describe('validateArgs (the runtime-validation Agent Note, part 1)', () => {
it('returns [] for valid args and is total over malformed input', () => {
const spec = {
path: { type: 'string', required: true },
@@ -1274,7 +1273,7 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => {
})
})
describe('defineTool validation (the runtime-validation RFC, part 1)', () => {
describe('defineTool validation (the runtime-validation Agent Note, part 1)', () => {
it('returns an isError result with the violations when the model sends bad args', async () => {
const ctx = await setup()
ctx.tools.register(defineTool({