Merge remote-tracking branch 'origin/master' into codex/simp-prune-llm-contract
This commit is contained in:
Tianyi Cui
@@ -260,6 +260,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
|
||||
'guard(guard: ToolGuard): () => void',
|
||||
'get(name: string, scope?: ScopeKey): ToolDefinition | undefined',
|
||||
'schemas(scope?: ScopeKey): ToolSchema[]',
|
||||
'executionMode(exec: ToolExecutionInput): ToolExecutionMode',
|
||||
'async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult>',
|
||||
],
|
||||
},
|
||||
@@ -1124,7 +1125,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [
|
||||
},
|
||||
{
|
||||
name: 'ToolDefinition',
|
||||
declaration: 'export interface ToolDefinition extends ToolSchema {\n execute(args: unknown, exec: ToolRunContext): Promise<ToolExecuteReturn>;\n timeoutMs?: number;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n}',
|
||||
declaration: 'export interface ToolDefinition extends ToolSchema {\n execute(args: unknown, exec: ToolRunContext): Promise<ToolExecuteReturn>;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n}',
|
||||
},
|
||||
{
|
||||
name: 'ToolErrorInfo',
|
||||
@@ -1142,6 +1143,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [
|
||||
name: 'ToolExecutionInput',
|
||||
declaration: 'export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n signal?: AbortSignal;\n}',
|
||||
},
|
||||
{
|
||||
name: 'ToolExecutionMode',
|
||||
declaration: 'export type ToolExecutionMode = {\n kind: \'parallel\';\n} | {\n kind: \'exclusive\';\n};',
|
||||
},
|
||||
{
|
||||
name: 'ToolExecutionResult',
|
||||
declaration: 'export interface ToolExecutionResult {\n content: ContentBlock[];\n isError: boolean;\n error?: ToolErrorInfo;\n additionalContexts?: HookContext[];\n meta?: unknown;\n}',
|
||||
|
||||
@@ -29,6 +29,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo
|
||||
|
||||
```ts
|
||||
interface Config {
|
||||
maxParallelToolCalls?: number // default 10; 1 is serial
|
||||
agents: Array<{
|
||||
id: string // required
|
||||
provider?: string
|
||||
@@ -39,7 +40,7 @@ interface Config {
|
||||
}
|
||||
```
|
||||
|
||||
Configured agents start automatically. A model call requires both `provider` and `model`; `agent/request` may supply a missing pair before dispatch. `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`.
|
||||
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
|
||||
|
||||
@@ -55,6 +56,8 @@ Every provider call that reaches a successful finish appends exactly one `assist
|
||||
|
||||
Plugin failure ends the current turn, not the loop. Cancellation clears pending work and aborts the current step without leaking to the next prompt. 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.
|
||||
|
||||
### What belongs to plugins
|
||||
|
||||
Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy:
|
||||
@@ -81,7 +84,7 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p
|
||||
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **Tool calls within a step execute sequentially** — parallel execution waits on concurrency-safety metadata in the tool contract (see `dsh-tools`).
|
||||
- **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 `${id}-session-<uuid>` every run (`TODO(demo)`), and a config `resumeSessionId` whose resume fails logs a warning and creates no agent.
|
||||
- **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options.
|
||||
- **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin.
|
||||
|
||||
@@ -54,15 +54,16 @@ export interface PreparedReactLoopAgent {
|
||||
* @param id - the concrete agent identity.
|
||||
* @param options - loop options for the agent.
|
||||
* @param session - the prepared session the agent will own.
|
||||
* @param maxParallelToolCalls - resolved in-flight cap for this agent.
|
||||
* @returns the agent and closures bound only to that exact instance.
|
||||
*/
|
||||
export function prepareReactLoopAgent(
|
||||
ctx: Context, id: AgentId, options: AgentOptions, session: Session,
|
||||
ctx: Context, id: AgentId, options: AgentOptions, session: Session, maxParallelToolCalls: number,
|
||||
): PreparedReactLoopAgent {
|
||||
if (claimedDriverSessions.has(session)) {
|
||||
throw new Error(`session "${session.id}" already has a concrete agent driver`)
|
||||
}
|
||||
const agent = new ReactLoopAgent(ctx, id, options, session)
|
||||
const agent = new ReactLoopAgent(ctx, id, options, session, maxParallelToolCalls)
|
||||
claimedDriverSessions.add(session)
|
||||
const dispose = () => agent[stopDriver]()
|
||||
return {
|
||||
@@ -143,6 +144,8 @@ export class ReactLoopAgent implements Agent {
|
||||
* the `disposed` transition fires and leave the promise hanging.
|
||||
*/
|
||||
private idleWaiters: (() => void)[] = []
|
||||
/** Maximum parallel-safe calls allowed in one step. */
|
||||
private readonly maxParallelToolCalls: number
|
||||
/**
|
||||
* Durability checkpoints started by idle {@link inject} calls. `inject()` is
|
||||
* synchronous, so it cannot await them itself; the driver disposer drains
|
||||
@@ -159,7 +162,9 @@ export class ReactLoopAgent implements Agent {
|
||||
public readonly id: AgentId,
|
||||
public readonly options: AgentOptions,
|
||||
public readonly session: Session,
|
||||
maxParallelToolCalls: number,
|
||||
) {
|
||||
this.maxParallelToolCalls = maxParallelToolCalls
|
||||
const { promise, resolve } = Promise.withResolvers<void>()
|
||||
this.disposed = promise
|
||||
this.resolveDisposed = resolve
|
||||
@@ -380,6 +385,7 @@ export class ReactLoopAgent implements Agent {
|
||||
this.driverStarted = true
|
||||
this.done = runLoop(this.loopCtx, this, {
|
||||
inbox: this.#inbox,
|
||||
maxParallelToolCalls: this.maxParallelToolCalls,
|
||||
setStatus: (status) => { this.setStatus(status) },
|
||||
setAbort: controller => void (this.currentAbort = controller),
|
||||
disposed: this.disposed,
|
||||
|
||||
6
packages/core/agent-loop/src/constants.ts
Normal file
6
packages/core/agent-loop/src/constants.ts
Normal file
@@ -0,0 +1,6 @@
|
||||
/** Shared agent-loop scheduler defaults.
|
||||
* @module dsh-agent-loop/constants
|
||||
*/
|
||||
|
||||
/** Default maximum in-flight parallel-safe calls per agent step. */
|
||||
export const DEFAULT_MAX_PARALLEL_TOOL_CALLS = 10
|
||||
@@ -32,6 +32,7 @@ import {
|
||||
ReactLoopAgent,
|
||||
} from './agent.ts'
|
||||
import type { PreparedReactLoopAgent } from './agent.ts'
|
||||
import { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from './constants.ts'
|
||||
|
||||
export { ReactLoopAgent } from './agent.ts'
|
||||
|
||||
@@ -73,6 +74,15 @@ function signalAbortError(id: AgentId, signal: AbortSignal): Error {
|
||||
return new Error(`agent "${id}" creation aborted`, { cause: signal.reason })
|
||||
}
|
||||
|
||||
/** Resolve the deployment-wide scheduler cap at the owning config boundary. */
|
||||
function resolveMaxParallelToolCalls(value: number | undefined): number {
|
||||
const maxParallelToolCalls = value ?? DEFAULT_MAX_PARALLEL_TOOL_CALLS
|
||||
if (!Number.isInteger(maxParallelToolCalls) || maxParallelToolCalls < 1) {
|
||||
throw new Error('maxParallelToolCalls must be a positive integer')
|
||||
}
|
||||
return maxParallelToolCalls
|
||||
}
|
||||
|
||||
/**
|
||||
* Caller-owned create/resume transaction through rollback-covered publication
|
||||
* and quiescent teardown. Resources remain private until the final registry
|
||||
@@ -163,13 +173,13 @@ class AgentCreationTransaction {
|
||||
}
|
||||
|
||||
/** Construct the driver and scope, then install their complete ordered lifecycle. */
|
||||
prepare(options: AgentOptions, session: Session): ReactLoopAgent {
|
||||
prepare(options: AgentOptions, session: Session, maxParallelToolCalls: number): ReactLoopAgent {
|
||||
this.assertActive()
|
||||
const gate = Promise.withResolvers<void>()
|
||||
this.preparing = gate.promise
|
||||
try {
|
||||
this.session = session
|
||||
const driver = prepareReactLoopAgent(this.loopCtx, this.id, options, session)
|
||||
const driver = prepareReactLoopAgent(this.loopCtx, this.id, options, session, maxParallelToolCalls)
|
||||
this.driver = driver
|
||||
const agent = driver.agent
|
||||
const scope = createScope(this.loopCtx, agent)
|
||||
@@ -318,8 +328,15 @@ declare module 'cordis' {
|
||||
}
|
||||
}
|
||||
|
||||
/** Plugin configuration for declarative startup agents. */
|
||||
export { DEFAULT_MAX_PARALLEL_TOOL_CALLS }
|
||||
|
||||
/** Agent-loop plugin configuration. */
|
||||
export interface Config {
|
||||
/**
|
||||
* Maximum parallel-safe calls in flight per agent step. `1` is serial;
|
||||
* omission defaults to {@link DEFAULT_MAX_PARALLEL_TOOL_CALLS}.
|
||||
*/
|
||||
maxParallelToolCalls?: number
|
||||
/** Agents created or resumed at plugin startup. */
|
||||
agents: (AgentOptions & {
|
||||
/** Registry identity for the live agent. */
|
||||
@@ -337,6 +354,7 @@ export class AgentLoop extends Service implements AgentFactory {
|
||||
|
||||
/** 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(),
|
||||
provider: z.string(),
|
||||
@@ -347,11 +365,14 @@ export class AgentLoop extends Service implements AgentFactory {
|
||||
}) as unknown as z<Config>
|
||||
|
||||
private readonly ownership: FactoryOwnership
|
||||
/** Resolved concurrency cap for every driver created by this factory. */
|
||||
private readonly maxParallelToolCalls: number
|
||||
/** Plain holder prevents Cordis from re-tracing the factory's dependency context through a caller shadow. */
|
||||
private readonly runtime: { ctx: Context }
|
||||
|
||||
constructor(ctx: Context, public config: Config) {
|
||||
super(ctx, 'agentLoop')
|
||||
this.maxParallelToolCalls = resolveMaxParallelToolCalls(config.maxParallelToolCalls)
|
||||
this.ownership = new FactoryOwnership(ctx.fiber)
|
||||
this.runtime = { ctx }
|
||||
ctx.effect(() => () => this.ownership.dispose(), 'agentLoop.transactions()')
|
||||
@@ -394,7 +415,7 @@ export class AgentLoop extends Service implements AgentFactory {
|
||||
try {
|
||||
const sessionId = SessionId(`${id}-session-${randomUUID()}`)
|
||||
const session = loopCtx.sessions.prepare(sessionId, { meta })
|
||||
const agent = transaction.prepare(options, session)
|
||||
const agent = transaction.prepare(options, session, this.maxParallelToolCalls)
|
||||
transaction.publish('startup')
|
||||
return agent
|
||||
} catch (error: unknown) {
|
||||
@@ -412,6 +433,7 @@ export class AgentLoop extends Service implements AgentFactory {
|
||||
* @returns the published handle.
|
||||
*/
|
||||
async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise<AgentHandle> {
|
||||
const agentOptions = options.agentOptions ?? {}
|
||||
const transaction = new AgentCreationTransaction(
|
||||
this.runtime.ctx,
|
||||
ownerCtx,
|
||||
@@ -424,7 +446,7 @@ export class AgentLoop extends Service implements AgentFactory {
|
||||
...options.seed === undefined ? {} : { seed: options.seed },
|
||||
...options.meta === undefined ? {} : { meta: options.meta },
|
||||
})
|
||||
const agent = transaction.prepare(options.agentOptions ?? {}, session)
|
||||
const agent = transaction.prepare(agentOptions, session, this.maxParallelToolCalls)
|
||||
await transaction.waitFor(options.setup?.(agent.ctx))
|
||||
transaction.assertActive()
|
||||
return transaction.publish('startup')
|
||||
@@ -456,6 +478,7 @@ export class AgentLoop extends Service implements AgentFactory {
|
||||
persistence: SessionPersistence,
|
||||
options: ResumeAgentOptions,
|
||||
): Promise<AgentHandle> {
|
||||
const agentOptions = options.agentOptions ?? {}
|
||||
const transaction = new AgentCreationTransaction(
|
||||
this.runtime.ctx,
|
||||
ownerCtx,
|
||||
@@ -475,7 +498,7 @@ export class AgentLoop extends Service implements AgentFactory {
|
||||
...loaded.meta.seedLength === undefined ? {} : { seedLength: loaded.meta.seedLength },
|
||||
},
|
||||
})
|
||||
const agent = transaction.prepare(options.agentOptions ?? {}, session)
|
||||
const agent = transaction.prepare(agentOptions, session, this.maxParallelToolCalls)
|
||||
await transaction.waitFor(options.setup?.(agent.ctx))
|
||||
transaction.assertActive()
|
||||
return transaction.publish('resume')
|
||||
|
||||
@@ -18,6 +18,7 @@ import type { TransmissionLog } from './request-log.ts'
|
||||
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'
|
||||
|
||||
@@ -73,6 +74,8 @@ function stepFinishReason(finish: FinishReason): TurnEndReason | undefined {
|
||||
export interface LoopHandle {
|
||||
/** Native-private agent inbox handed to the driver only at internal startup. */
|
||||
readonly inbox: Inbox
|
||||
/** Maximum parallel-safe calls allowed in one step. */
|
||||
readonly maxParallelToolCalls: number
|
||||
setStatus(status: 'idle' | 'running'): void
|
||||
setAbort(controller: AbortController | undefined): void
|
||||
/** Resolves when the agent is disposed — unblocks the idle wait. */
|
||||
@@ -559,49 +562,13 @@ async function runStep(
|
||||
// empty chunk provenance for a contentless, usage-less provider response.
|
||||
recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs)
|
||||
|
||||
// Tool execution stays sequential; recheck abort around each normalized result.
|
||||
// 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) => {
|
||||
for (const call of toolCalls) {
|
||||
/* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */
|
||||
if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted'))
|
||||
const callEvent = session.append('tool/call', { turn, step, callId: call.id, name: call.name, arguments: call.arguments })
|
||||
let parsedArguments: unknown
|
||||
try {
|
||||
parsedArguments = call.arguments ? JSON.parse(call.arguments) : {}
|
||||
} catch {
|
||||
parsedArguments = call.arguments
|
||||
}
|
||||
// TODO(pre-tool-input-rewrite): Keep logged history and live presentation aligned;
|
||||
// see docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md.
|
||||
const result = await ctx.tools.execute({
|
||||
callId: call.id,
|
||||
name: call.name,
|
||||
arguments: parsedArguments,
|
||||
agent,
|
||||
signal,
|
||||
})
|
||||
session.append('tool/result', {
|
||||
turn, step,
|
||||
// Correlation comes from the immutable execution input; the result does
|
||||
// not duplicate this authoritative transcript identity.
|
||||
callId: call.id,
|
||||
content: result.content,
|
||||
isError: result.isError,
|
||||
...result.error ? { error: result.error } : {},
|
||||
// Persist tool-owned presentation data for replay.
|
||||
...result.meta !== undefined ? { meta: result.meta } : {},
|
||||
}, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] })
|
||||
// Accept into the batch FIFO immediately; entries remain deferred until
|
||||
// every recorded result settles and survive abort or disposal afterward.
|
||||
for (const context of result.additionalContexts ?? []) acceptContext(context)
|
||||
// The signal may flip while the tool is awaited.
|
||||
/* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */
|
||||
// eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
|
||||
if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted'))
|
||||
/* v8 ignore stop */
|
||||
}
|
||||
await executeToolCalls(
|
||||
ctx, agent, turn, step, toolCalls, signal, handle.maxParallelToolCalls, acceptContext,
|
||||
)
|
||||
return { hadToolCalls: true, finish: assembler.finish }
|
||||
})
|
||||
}
|
||||
|
||||
229
packages/core/agent-loop/src/tool-calls.ts
Normal file
229
packages/core/agent-loop/src/tool-calls.ts
Normal file
@@ -0,0 +1,229 @@
|
||||
/**
|
||||
* Schedules one assistant step's tool calls. Exclusive calls form barriers;
|
||||
* parallel calls use a bounded rolling pool and are reclassified before start.
|
||||
* 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.
|
||||
* @module dsh-agent-loop/tool-calls
|
||||
*/
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
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 {
|
||||
block: ToolCallBlock
|
||||
exec: ToolExecutionInput
|
||||
}
|
||||
|
||||
/** Settled dispatch awaiting model-order finalization. */
|
||||
interface Slot {
|
||||
exec: ToolRunContext
|
||||
result: ToolExecutionResult
|
||||
needsPost: 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.
|
||||
*
|
||||
* @param ctx - loop context that owns the tool registry.
|
||||
* @param agent - agent and session receiving the call lifecycle.
|
||||
* @param turn - current turn number.
|
||||
* @param step - current step number.
|
||||
* @param toolCalls - assistant calls in model order.
|
||||
* @param signal - abort signal shared by the step.
|
||||
* @param maxParallel - validated in-flight cap.
|
||||
* @param acceptContext - accepts committed result context into the active batch.
|
||||
*/
|
||||
export async function executeToolCalls(
|
||||
ctx: Context,
|
||||
agent: ReactLoopAgent,
|
||||
turn: number,
|
||||
step: number,
|
||||
toolCalls: ToolCallBlock[],
|
||||
signal: AbortSignal,
|
||||
maxParallel: number,
|
||||
acceptContext: (context: HookContext) => void,
|
||||
): Promise<void> {
|
||||
const { session } = agent
|
||||
|
||||
// Inputs are distinct because tools/execute wrappers may replace `exec.signal`.
|
||||
const planned: PlannedCall[] = toolCalls.map(block => ({
|
||||
block,
|
||||
exec: {
|
||||
callId: block.id,
|
||||
name: block.name,
|
||||
arguments: parseArguments(block.arguments),
|
||||
agent,
|
||||
signal,
|
||||
},
|
||||
}))
|
||||
|
||||
let next = 0
|
||||
while (next < planned.length) {
|
||||
// Commit before classifying again so registry changes affect unstarted calls.
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded by the loop condition
|
||||
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)
|
||||
}
|
||||
}
|
||||
|
||||
/** Parse model arguments, preserving invalid JSON as text and mapping empty input to `{}`. */
|
||||
function parseArguments(raw: string): unknown {
|
||||
try {
|
||||
return raw ? JSON.parse(raw) : {}
|
||||
} catch {
|
||||
return raw
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Run one exclusive barrier or parallel pool. Later calls are reclassified
|
||||
* 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.
|
||||
*/
|
||||
async function runGroup(
|
||||
ctx: Context,
|
||||
session: Session,
|
||||
turn: number,
|
||||
step: number,
|
||||
group: PlannedCall[],
|
||||
mode: ToolExecutionMode['kind'],
|
||||
signal: AbortSignal,
|
||||
maxParallel: number,
|
||||
acceptContext: (context: HookContext) => void,
|
||||
): Promise<number> {
|
||||
/* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */
|
||||
if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted'))
|
||||
const slots: (Slot | undefined)[] = group.map(() => undefined)
|
||||
// Started slots retain their tool/call seq for result provenance.
|
||||
const callSeqs: number[] = group.map(() => -1)
|
||||
let nextToStart = 0
|
||||
let committed = 0
|
||||
let started = 0
|
||||
let aborted: boolean = signal.aborted
|
||||
|
||||
// `committed` advances only across contiguous model-order slots.
|
||||
const commitReady = async (): Promise<void> => {
|
||||
while (committed < group.length) {
|
||||
const slot = slots[committed]
|
||||
if (slot === undefined) break
|
||||
const call = group[committed]
|
||||
const result = slot.needsPost
|
||||
? await ctx.tools[TOOL_REGISTRY_SCHEDULER].finalize(slot.exec, slot.result)
|
||||
: ctx.tools[TOOL_REGISTRY_SCHEDULER].finish(slot.exec, slot.result)
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index
|
||||
appendToolResult(session, turn, step, call!.block, result, callSeqs[committed]!)
|
||||
for (const context of result.additionalContexts ?? []) acceptContext(context)
|
||||
committed++
|
||||
}
|
||||
}
|
||||
|
||||
const inFlight = new Map<number, Promise<number>>()
|
||||
|
||||
const startCall = async (index: number): Promise<void> => {
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index
|
||||
const call = group[index]!
|
||||
callSeqs[index] = appendToolCall(session, turn, step, call.block)
|
||||
started++
|
||||
const prepared = await ctx.tools[TOOL_REGISTRY_SCHEDULER].prepare(call.exec)
|
||||
switch (prepared.kind) {
|
||||
case 'dispatch': {
|
||||
const promise = ctx.tools[TOOL_REGISTRY_SCHEDULER].dispatch(prepared.exec).then((outcome) => {
|
||||
slots[index] = { exec: prepared.exec, result: outcome.result, needsPost: outcome.kind === 'post-result' }
|
||||
return index
|
||||
})
|
||||
inFlight.set(index, promise)
|
||||
break
|
||||
}
|
||||
case 'post-result':
|
||||
slots[index] = { exec: prepared.exec, result: prepared.result, needsPost: true }
|
||||
break
|
||||
case 'final-result':
|
||||
slots[index] = { exec: prepared.exec, result: prepared.result, needsPost: false }
|
||||
break
|
||||
/* v8 ignore next -- closed-union exhaustiveness guard */
|
||||
default:
|
||||
assertNever(prepared, 'tool-call scheduler prepare result')
|
||||
}
|
||||
}
|
||||
|
||||
const fillPool = async (): Promise<void> => {
|
||||
while (!aborted && nextToStart < group.length && inFlight.size < maxParallel) {
|
||||
// Re-read later modes after ordered commits so registry changes can create a barrier.
|
||||
// eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded by the loop condition
|
||||
const nextCall = group[nextToStart]!
|
||||
if (nextToStart > 0 && mode === 'parallel'
|
||||
&& ctx.tools.executionMode(nextCall.exec).kind !== 'parallel') break
|
||||
await startCall(nextToStart)
|
||||
nextToStart++
|
||||
await commitReady()
|
||||
// Abort may arrive while pre-execute awaits.
|
||||
if (signal.aborted) aborted = true
|
||||
}
|
||||
}
|
||||
|
||||
// Ordered pre-execute may await; only dispatch/body overlaps.
|
||||
// TODO: Drain every started call before rethrowing a scheduler error; tool
|
||||
// bodies must not outlive the failed turn.
|
||||
await fillPool()
|
||||
while (inFlight.size > 0) {
|
||||
const settledIndex = await Promise.race(inFlight.values())
|
||||
inFlight.delete(settledIndex)
|
||||
await commitReady()
|
||||
// Abort may arrive while a tool or ordered commit awaits.
|
||||
// eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
|
||||
if (signal.aborted) aborted = true
|
||||
await fillPool()
|
||||
}
|
||||
|
||||
if (aborted) {
|
||||
// Started calls and accepted context settle before the turn records the abort.
|
||||
/* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */
|
||||
throw new Error(String(signal.reason ?? 'aborted'))
|
||||
}
|
||||
/* 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
|
||||
}
|
||||
|
||||
/** Append a started call and return its provenance sequence. */
|
||||
function appendToolCall(session: Session, turn: number, step: number, block: ToolCallBlock): number {
|
||||
const event = session.append('tool/call', { turn, step, callId: block.id, name: block.name, arguments: block.arguments })
|
||||
return event.seq
|
||||
}
|
||||
|
||||
/** Append a model-ordered result linked to its call event. */
|
||||
function appendToolResult(
|
||||
session: Session,
|
||||
turn: number,
|
||||
step: number,
|
||||
block: ToolCallBlock,
|
||||
result: ToolExecutionResult,
|
||||
callSeq: number,
|
||||
): void {
|
||||
session.append('tool/result', {
|
||||
turn, step,
|
||||
// Correlation stays with the loop's authoritative model-transcript call id;
|
||||
// registry results deliberately do not duplicate it.
|
||||
callId: block.id,
|
||||
content: result.content,
|
||||
isError: result.isError,
|
||||
...result.error ? { error: result.error } : {},
|
||||
// The tool's private presentation payload (e.g. a result-time diff),
|
||||
// persisted so a UI bridge reproduces the card on replay.
|
||||
...result.meta !== undefined ? { meta: result.meta } : {},
|
||||
}, { surfaceOp: 'append', sourceEventSeqs: [callSeq] })
|
||||
}
|
||||
@@ -6,7 +6,7 @@ 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 AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
||||
import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
||||
import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts'
|
||||
import { MockAdapter, textResponse } from './mock-adapter.ts'
|
||||
|
||||
@@ -53,10 +53,14 @@ describe('ReactLoopAgent', () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
const session = ctx.sessions.create(SessionId('exclusive-driver'))
|
||||
const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { provider: 'mock', model: 'mock' }, session)
|
||||
const prepared = prepareReactLoopAgent(
|
||||
ctx, AgentId('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))
|
||||
expect(() => prepareReactLoopAgent(
|
||||
ctx, AgentId('second-driver'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
|
||||
))
|
||||
.toThrow('already has a concrete agent driver')
|
||||
|
||||
await prepared.dispose()
|
||||
@@ -254,7 +258,9 @@ describe('ReactLoopAgent', () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
const session = ctx.sessions.create(SessionId('test'))
|
||||
const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session)
|
||||
const prepared = prepareReactLoopAgent(
|
||||
ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
|
||||
)
|
||||
const { agent } = prepared
|
||||
|
||||
prepared.markPublished()
|
||||
@@ -272,7 +278,9 @@ describe('ReactLoopAgent', () => {
|
||||
const ctx = new Context()
|
||||
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)
|
||||
const prepared = prepareReactLoopAgent(
|
||||
ctx, AgentId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
|
||||
)
|
||||
|
||||
await prepared.dispose()
|
||||
expect(prepared.agent.status).toBe('disposed')
|
||||
@@ -369,7 +377,9 @@ describe('ReactLoopAgent', () => {
|
||||
const adapter = new MockAdapter(['hang'])
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
const session = ctx.sessions.create(SessionId('bare'))
|
||||
const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session)
|
||||
const prepared = prepareReactLoopAgent(
|
||||
ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
|
||||
)
|
||||
const { agent } = prepared
|
||||
prepared.markPublished()
|
||||
const dispose = prepared.startDriver()
|
||||
|
||||
@@ -5,7 +5,7 @@ import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@
|
||||
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 AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
||||
import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS, ReactLoopAgent } 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'
|
||||
@@ -822,7 +822,9 @@ describe('turn numbering continues across seeded sessions', () => {
|
||||
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)
|
||||
const prepared = prepareReactLoopAgent(
|
||||
ctx2, AgentId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded, DEFAULT_MAX_PARALLEL_TOOL_CALLS,
|
||||
)
|
||||
const forked = prepared.agent
|
||||
prepared.markPublished()
|
||||
ctx2.effect(() => prepared.startDriver())
|
||||
|
||||
571
packages/core/agent-loop/tests/tool-calls.spec.ts
Normal file
571
packages/core/agent-loop/tests/tool-calls.spec.ts
Normal file
@@ -0,0 +1,571 @@
|
||||
/**
|
||||
* Exercises scheduler ordering and cancellation with deterministic gated tools.
|
||||
* ACP goldens 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 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 AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
||||
import { MockAdapter, textResponse } from './mock-adapter.ts'
|
||||
|
||||
async function harness(adapter: MockAdapter, maxParallelToolCalls?: number) {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt, { persona: '' })
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(AgentLoop, {
|
||||
agents: [],
|
||||
...maxParallelToolCalls === undefined ? {} : { maxParallelToolCalls },
|
||||
})
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
return ctx
|
||||
}
|
||||
|
||||
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = ctx.on('agent/status', (subject, status) => {
|
||||
if (subject === agent && status === 'idle') { dispose(); resolve() }
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
function events(agent: ReactLoopAgent): SessionEvent[] {
|
||||
return [...agent.session.events]
|
||||
}
|
||||
|
||||
/** Build one assistant response containing the supplied tool calls. */
|
||||
function multiCall(calls: { id: string; name: string; args: object }[]): StreamChunk[] {
|
||||
const chunks: StreamChunk[] = []
|
||||
calls.forEach((call, index) => {
|
||||
chunks.push(
|
||||
{ type: 'block-start', index, blockType: 'tool-call' },
|
||||
{ type: 'block-end', index, block: { type: 'tool-call', id: CallId(call.id), name: call.name, arguments: JSON.stringify(call.args) } },
|
||||
)
|
||||
})
|
||||
chunks.push(
|
||||
{ type: 'usage', usage: { inputTokens: 5, outputTokens: 5 } },
|
||||
{ type: 'finish', reason: { kind: 'tool-calls' } },
|
||||
)
|
||||
return chunks
|
||||
}
|
||||
|
||||
/** A tool whose calls block until the test releases them by callId. */
|
||||
function gatedTool(name: string, parallel: boolean) {
|
||||
const gates = new Map<string, () => void>()
|
||||
const started: string[] = []
|
||||
const tool = defineTool({
|
||||
name,
|
||||
description: `gated ${name}`,
|
||||
parameters: { id: { type: 'string', required: true } },
|
||||
...parallel ? { isConcurrencySafe: () => true } : {},
|
||||
async execute(args) {
|
||||
started.push(args.id)
|
||||
await new Promise<void>((resolve) => { gates.set(args.id, resolve) })
|
||||
return [{ type: 'text', text: `done-${args.id}` }]
|
||||
},
|
||||
})
|
||||
return {
|
||||
tool,
|
||||
started,
|
||||
release(id: string) { gates.get(id)?.(); gates.delete(id) },
|
||||
pending() { return [...gates.keys()] },
|
||||
}
|
||||
}
|
||||
|
||||
function gatedParallelTool(name: string) {
|
||||
return gatedTool(name, true)
|
||||
}
|
||||
|
||||
function gatedExclusiveTool(name: string) {
|
||||
return gatedTool(name, false)
|
||||
}
|
||||
|
||||
/** Poll until `predicate` holds, letting microtasks/timers drain between checks. */
|
||||
async function until(predicate: () => boolean): Promise<void> {
|
||||
for (let i = 0; i < 1000 && !predicate(); i++) await new Promise(r => setTimeout(r, 0))
|
||||
if (!predicate()) throw new Error('until: condition never held')
|
||||
}
|
||||
|
||||
describe('tool-call scheduler: grouping and barriers', () => {
|
||||
it('runs parallel-safe siblings concurrently (all start before any completes)', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }, { id: 'c3', name: 'p', args: { id: '3' } }]),
|
||||
textResponse('done'),
|
||||
])
|
||||
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' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 3)
|
||||
expect(gated.started).toEqual(['1', '2', '3'])
|
||||
gated.release('1'); gated.release('2'); gated.release('3')
|
||||
await waitForIdle(ctx, agent)
|
||||
})
|
||||
|
||||
it('an exclusive call between two parallel-safe calls forms a barrier (3 groups)', async () => {
|
||||
const order: string[] = []
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([
|
||||
{ id: 'c1', name: 'r', args: { id: 'A1' } },
|
||||
{ id: 'c2', name: 'w', args: { id: 'A2' } },
|
||||
{ id: 'c3', name: 'r', args: { id: 'A3' } },
|
||||
]),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'r', description: 'read', parameters: { id: { type: 'string', required: true } },
|
||||
isConcurrencySafe: () => true,
|
||||
async execute(args) { order.push(`r-start-${args.id}`); order.push(`r-end-${args.id}`); return [{ type: 'text', text: 'r' }] },
|
||||
}))
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'w', description: 'write', parameters: { id: { type: 'string', required: true } },
|
||||
async execute(args) { order.push(`w-${args.id}`); return [{ type: 'text', text: 'w' }] },
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
expect(order).toEqual(['r-start-A1', 'r-end-A1', 'w-A2', 'r-start-A3', 'r-end-A3'])
|
||||
})
|
||||
|
||||
it('reclassifies pending calls after an exclusive barrier replaces their tool', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([
|
||||
{ id: 'c1', name: 'replace', args: { id: '0' } },
|
||||
{ id: 'c2', name: 'x', args: { id: '1' } },
|
||||
{ id: 'c3', name: 'x', args: { id: '2' } },
|
||||
]),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
const replacement = gatedExclusiveTool('x')
|
||||
const disposeSafe = ctx.tools.register(defineTool({
|
||||
name: 'x',
|
||||
description: 'initially safe',
|
||||
parameters: { id: { type: 'string', required: true } },
|
||||
isConcurrencySafe: () => true,
|
||||
async execute(args) { return [{ type: 'text', text: `old-${args.id}` }] },
|
||||
}))
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'replace',
|
||||
description: 'replace x',
|
||||
parameters: { id: { type: 'string', required: true } },
|
||||
async execute() {
|
||||
disposeSafe()
|
||||
ctx.tools.register(replacement.tool)
|
||||
return [{ type: 'text', text: 'replaced' }]
|
||||
},
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => replacement.started.length === 1)
|
||||
await new Promise(r => setTimeout(r, 5))
|
||||
expect(replacement.started).toEqual(['1'])
|
||||
replacement.release('1')
|
||||
await until(() => replacement.started.length === 2)
|
||||
expect(replacement.started).toEqual(['1', '2'])
|
||||
replacement.release('2')
|
||||
await waitForIdle(ctx, agent)
|
||||
})
|
||||
|
||||
it('stops replenishing when a result observer makes the next call exclusive', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([
|
||||
{ id: 'c1', name: 'x', args: { id: '1' } },
|
||||
{ id: 'c2', name: 'x', args: { id: '2' } },
|
||||
{ id: 'c3', name: 'x', args: { id: '3' } },
|
||||
]),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = await harness(adapter, 2)
|
||||
const initial = gatedParallelTool('x')
|
||||
const replacement = gatedExclusiveTool('x')
|
||||
const disposeInitial = ctx.tools.register(initial.tool)
|
||||
ctx.on('tools/result', (exec) => {
|
||||
if (exec.callId !== CallId('c1')) return
|
||||
disposeInitial()
|
||||
ctx.tools.register(replacement.tool)
|
||||
})
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => initial.started.length === 2)
|
||||
initial.release('1')
|
||||
await until(() => events(agent).some(event =>
|
||||
event.type === 'tool/result' && event.data.callId === CallId('c1')))
|
||||
await new Promise(r => setTimeout(r, 5))
|
||||
expect(replacement.started).toEqual([])
|
||||
initial.release('2')
|
||||
await until(() => replacement.started.length === 1)
|
||||
expect(replacement.started).toEqual(['3'])
|
||||
replacement.release('3')
|
||||
await waitForIdle(ctx, agent)
|
||||
})
|
||||
})
|
||||
|
||||
describe('tool-call scheduler: model-order results despite out-of-order settlement', () => {
|
||||
it('commits tool/result in model order even when a later call settles first', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
|
||||
textResponse('done'),
|
||||
])
|
||||
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' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 2)
|
||||
gated.release('2')
|
||||
await new Promise(r => setTimeout(r, 5))
|
||||
const beforeFirst = events(agent).filter(e => e.type === 'tool/result')
|
||||
expect(beforeFirst).toEqual([])
|
||||
gated.release('1')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const results = events(agent).filter(e => e.type === 'tool/result')
|
||||
expect(results.map(e => e.data.callId)).toEqual([CallId('c1'), CallId('c2')])
|
||||
})
|
||||
|
||||
it('derived history pairs calls in model order regardless of tool/call log interleaving', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
|
||||
textResponse('done'),
|
||||
])
|
||||
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' })
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 2)
|
||||
gated.release('2'); gated.release('1')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const messages = agent.session.deriveMessages()
|
||||
const toolResults = messages.flatMap(m => m.content.filter(b => b.type === 'tool-result'))
|
||||
expect(toolResults.map(b => b.toolCallId)).toEqual([CallId('c1'), CallId('c2')])
|
||||
})
|
||||
})
|
||||
|
||||
describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => {
|
||||
it('rejects invalid global maxParallelToolCalls config at plugin load', async () => {
|
||||
await expect(harness(new MockAdapter([]), 0)).rejects.toThrow()
|
||||
await expect(harness(new MockAdapter([]), 1.5)).rejects.toThrow()
|
||||
})
|
||||
|
||||
it('defensively rejects invalid caps when direct construction bypasses the config schema', () => {
|
||||
expect(() => new AgentLoop(new Context(), { agents: [], maxParallelToolCalls: 0 }))
|
||||
.toThrow('maxParallelToolCalls must be a positive integer')
|
||||
expect(() => new AgentLoop(new Context(), { agents: [], maxParallelToolCalls: 1.5 }))
|
||||
.toThrow('maxParallelToolCalls must be a positive integer')
|
||||
})
|
||||
|
||||
it('defaults the cap when direct construction bypasses the config schema', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt, { persona: '' })
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
|
||||
expect(() => new AgentLoop(ctx, { agents: [] })).not.toThrow()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('starts at most the cap, replenishing as calls settle', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = await harness(adapter, 2)
|
||||
const gated = gatedParallelTool('p')
|
||||
ctx.tools.register(gated.tool)
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 2)
|
||||
await new Promise(r => setTimeout(r, 5))
|
||||
expect(gated.started).toEqual(['1', '2'])
|
||||
gated.release('1')
|
||||
await until(() => gated.started.length === 3)
|
||||
expect(gated.started).toEqual(['1', '2', '3'])
|
||||
expect(events(agent)
|
||||
.filter(e => e.type === 'tool/call' || e.type === 'tool/result')
|
||||
.map(e => `${e.type}:${String(e.data.callId)}`)
|
||||
.slice(0, 4))
|
||||
.toEqual(['tool/call:c1', 'tool/call:c2', 'tool/result:c1', 'tool/call:c3'])
|
||||
gated.release('2'); gated.release('3')
|
||||
await until(() => gated.started.length === 4)
|
||||
gated.release('4')
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
|
||||
.toEqual([CallId('c1'), CallId('c2'), CallId('c3'), CallId('c4')])
|
||||
})
|
||||
|
||||
it('maxParallelToolCalls: 1 is fully serial (no second start before the first settles)', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
|
||||
textResponse('done'),
|
||||
])
|
||||
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' })
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 1)
|
||||
await new Promise(r => setTimeout(r, 5))
|
||||
expect(gated.started).toEqual(['1'])
|
||||
gated.release('1')
|
||||
await until(() => gated.started.length === 2)
|
||||
gated.release('2')
|
||||
await waitForIdle(ctx, agent)
|
||||
})
|
||||
|
||||
it('applies the configured cap to every factory-created agent', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SystemPrompt, { persona: '' })
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
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' })
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 1)
|
||||
await new Promise(r => setTimeout(r, 5))
|
||||
expect(gated.started).toEqual(['1'])
|
||||
gated.release('1')
|
||||
await until(() => gated.started.length === 2)
|
||||
gated.release('2')
|
||||
await waitForIdle(ctx, agent)
|
||||
})
|
||||
|
||||
})
|
||||
|
||||
describe('tool-call scheduler: ordered middleware and additional contexts', () => {
|
||||
it('tools/pre-execute and tools/post-execute observe model call order', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }, { id: 'c3', name: 'p', args: { id: '3' } }]),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
const gated = gatedParallelTool('p')
|
||||
ctx.tools.register(gated.tool)
|
||||
const pre: string[] = []
|
||||
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' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 3)
|
||||
gated.release('3'); gated.release('2'); gated.release('1')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
expect(pre).toEqual([CallId('c1'), CallId('c2'), CallId('c3')].map(String))
|
||||
expect(post).toEqual([CallId('c1'), CallId('c2'), CallId('c3')].map(String))
|
||||
})
|
||||
|
||||
it('injects additional contexts in model call order, not settlement order', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = await harness(adapter, 2)
|
||||
const gated = gatedParallelTool('p')
|
||||
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' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 2)
|
||||
gated.release('2'); gated.release('1')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const log = events(agent)
|
||||
const contextTexts = log.filter(e => e.type === 'context/message')
|
||||
.map(e => (e.data.content[0] as { text: string }).text)
|
||||
expect(contextTexts).toEqual(['ctx-c1', 'ctx-c2'])
|
||||
const lastResult = log.findLastIndex(e => e.type === 'tool/result')
|
||||
const firstContext = log.findIndex(e => e.type === 'context/message')
|
||||
expect(lastResult).toBeLessThan(firstContext)
|
||||
})
|
||||
|
||||
it('orders pre-execute denials and errors without dispatching them', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([
|
||||
{ id: 'c1', name: 'p', args: { id: '1' } },
|
||||
{ id: 'c2', name: 'p', args: { id: '2' } },
|
||||
{ id: 'c3', name: 'p', args: { id: '3' } },
|
||||
]),
|
||||
textResponse('done'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
const gated = gatedParallelTool('p')
|
||||
ctx.tools.register(gated.tool)
|
||||
const post: string[] = []
|
||||
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
|
||||
if (exec.callId === CallId('c2')) return { kind: 'deny', reason: 'blocked by policy' }
|
||||
if (exec.callId === CallId('c3')) throw new Error('pre exploded')
|
||||
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' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 1)
|
||||
gated.release('1')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
expect(gated.started).toEqual(['1'])
|
||||
expect(post).toEqual(['c1', 'c2'])
|
||||
const results = events(agent).filter(e => e.type === 'tool/result')
|
||||
expect(results.map(e => e.data.callId)).toEqual([CallId('c1'), CallId('c2'), CallId('c3')])
|
||||
expect((results[1]!.data.content[0] as { text: string }).text).toContain('blocked by policy')
|
||||
expect((results[2]!.data.content[0] as { text: string }).text).toContain('pre exploded')
|
||||
})
|
||||
})
|
||||
|
||||
describe('tool-call scheduler: abort handling', () => {
|
||||
it('starts no calls when the signal is already aborted before a parallel group', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
|
||||
textResponse('should never be requested'),
|
||||
])
|
||||
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' })
|
||||
ctx.on('session/event', (session, event) => {
|
||||
if (session === agent.session && event.type === 'assistant/message') {
|
||||
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('already aborted')
|
||||
}
|
||||
})
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
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([])
|
||||
})
|
||||
|
||||
it('stops starting siblings when abort fires during ordered pre-execute', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
|
||||
textResponse('should never be requested'),
|
||||
])
|
||||
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' })
|
||||
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
|
||||
if (exec.callId === CallId('c1')) {
|
||||
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('pre cancelled')
|
||||
}
|
||||
return next()
|
||||
})
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 1)
|
||||
await new Promise(r => setTimeout(r, 5))
|
||||
expect(gated.started).toEqual(['1'])
|
||||
gated.release('1')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
|
||||
.toEqual([CallId('c1')])
|
||||
expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
|
||||
.toEqual([CallId('c1')])
|
||||
})
|
||||
|
||||
it('stops replenishing after abort, commits started results, and drains accepted additional contexts', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([1, 2, 3, 4].map(n => ({ id: `c${n}`, name: 'p', args: { id: String(n) } }))),
|
||||
textResponse('should never be requested'),
|
||||
])
|
||||
const ctx = await harness(adapter, 2)
|
||||
const gated = gatedParallelTool('p')
|
||||
ctx.tools.register(gated.tool)
|
||||
ctx.on('tools/post-execute', async (exec, _result, next): Promise<PostToolDecision> => ({
|
||||
...await next(),
|
||||
additionalContexts: [{ content: [{ type: 'text', text: `ctx-${exec.callId}` }], source: { kind: 'plugin', plugin: 'p' } }],
|
||||
}))
|
||||
const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 2)
|
||||
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('stop now')
|
||||
gated.release('1')
|
||||
gated.release('2')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
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')])
|
||||
expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
|
||||
.toEqual([CallId('c1'), CallId('c2')])
|
||||
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'])
|
||||
expect(settled.filter(e => e.type === 'context/message')
|
||||
.map(e => (e.data.content[0] as { text: string }).text))
|
||||
.toEqual(['ctx-c1', 'ctx-c2'])
|
||||
})
|
||||
|
||||
it('does not run an exclusive barrier after a parallel group aborts', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
multiCall([
|
||||
{ id: 'c1', name: 'p', args: { id: '1' } },
|
||||
{ id: 'c2', name: 'p', args: { id: '2' } },
|
||||
{ id: 'c3', name: 'x', args: { id: '3' } },
|
||||
]),
|
||||
textResponse('should never be requested'),
|
||||
])
|
||||
const ctx = await harness(adapter, 2)
|
||||
const gated = gatedParallelTool('p')
|
||||
const exclusive: string[] = []
|
||||
ctx.tools.register(gated.tool)
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'x',
|
||||
description: 'exclusive',
|
||||
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' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'go' }])
|
||||
await until(() => gated.started.length === 2)
|
||||
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('stop before barrier')
|
||||
gated.release('1')
|
||||
gated.release('2')
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
expect(exclusive).toEqual([])
|
||||
expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
|
||||
.toEqual([CallId('c1'), CallId('c2')])
|
||||
})
|
||||
})
|
||||
@@ -9,6 +9,7 @@ import { join } from 'node:path'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import {
|
||||
annotateSurface,
|
||||
collectEventEnvelopeTypes,
|
||||
collectLogEvents,
|
||||
collectSurfaceEventTypes,
|
||||
render,
|
||||
@@ -56,6 +57,7 @@ describe('gen-persistence-catalog collectLogEvents', () => {
|
||||
scope: 'fix',
|
||||
doc: 'A thing was recorded.',
|
||||
payload: '{ turn: number }',
|
||||
declaration: '/** A thing was recorded. */\n\'fix/happened\': { turn: number }',
|
||||
source: 'packages/core/fix/src/types.ts:3',
|
||||
})
|
||||
})
|
||||
@@ -102,10 +104,13 @@ describe('gen-persistence-catalog collectLogEvents', () => {
|
||||
it('collapses a newline-separated multi-line payload to a valid one-line fragment', () => {
|
||||
const events = collectLogEvents(make({
|
||||
'packages/group/fix/src/types.ts': merge(
|
||||
' /** Wide payload. */\n \'fix/wide\': {\n alpha: string[]\n range: { start: number; end: number }\n count: number\n }',
|
||||
' /** Wide payload. */\n \'fix/wide\': {\n /** Alpha values. */\n alpha: string[]\n range: { start: number; end: number }\n count: number\n }',
|
||||
),
|
||||
}))
|
||||
expect(events[0]?.payload).toBe('{ alpha: string[]; range: { start: number; end: number }; count: number }')
|
||||
expect(events[0]?.declaration).toBe(
|
||||
'/** Wide payload. */\n\'fix/wide\': {\n /** Alpha values. */\n alpha: string[]\n range: { start: number; end: number }\n count: number\n}',
|
||||
)
|
||||
})
|
||||
|
||||
it('hard-errors on a member with no description prose', () => {
|
||||
@@ -158,6 +163,59 @@ describe('gen-persistence-catalog collectLogEvents', () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe('gen-persistence-catalog collectEventEnvelopeTypes', () => {
|
||||
const declarations = `/** Event keys. */
|
||||
export type SessionEventType = keyof SessionEventMap
|
||||
/** Surface-producing event keys. */
|
||||
export type SurfaceEventType = 'fix/message'
|
||||
/** Surface placement. */
|
||||
export type SurfaceOp = 'append'
|
||||
/** One persisted event. */
|
||||
export type SessionEvent<T extends SessionEventType = SessionEventType> = { type: T }
|
||||
`
|
||||
|
||||
it('extracts the envelope declarations with their complete JSDoc in canonical order', () => {
|
||||
const entries = collectEventEnvelopeTypes(make({
|
||||
'packages/core/fix/package.json': OWNER_MANIFEST,
|
||||
'packages/core/fix/src/types.ts': declarations,
|
||||
}))
|
||||
expect(entries.map(entry => entry.name)).toEqual([
|
||||
'SessionEventType',
|
||||
'SurfaceEventType',
|
||||
'SurfaceOp',
|
||||
'SessionEvent',
|
||||
])
|
||||
expect(entries[3]).toMatchObject({
|
||||
declaration: '/** One persisted event. */\nexport type SessionEvent<T extends SessionEventType = SessionEventType> = { type: T }',
|
||||
source: 'packages/core/fix/src/types.ts:8',
|
||||
})
|
||||
})
|
||||
|
||||
it('hard-errors when an envelope declaration is missing', () => {
|
||||
expect(() => collectEventEnvelopeTypes(make({
|
||||
'packages/core/fix/package.json': OWNER_MANIFEST,
|
||||
'packages/core/fix/src/types.ts': declarations.replace('/** Surface placement. */\nexport type SurfaceOp = \'append\'\n', ''),
|
||||
}))).toThrow(/missing event-envelope declaration\(s\): SurfaceOp/)
|
||||
})
|
||||
|
||||
it('hard-errors on duplicate, unexported, undocumented, or mistagged envelope declarations', () => {
|
||||
const violations = new RegExp([
|
||||
'4 JSDoc completeness violation\\(s\\)',
|
||||
'[\\s\\S]*not exported',
|
||||
'[\\s\\S]*@mode tag',
|
||||
'[\\s\\S]*SurfaceOp.*no description prose',
|
||||
'[\\s\\S]*SessionEvent.*already declared',
|
||||
].join(''))
|
||||
expect(() => collectEventEnvelopeTypes(make({
|
||||
'packages/core/fix/package.json': OWNER_MANIFEST,
|
||||
'packages/core/fix/src/types.ts': declarations
|
||||
.replace('/** Event keys. */\nexport type SessionEventType', '/** Event keys.\n * @mode emit\n */\ntype SessionEventType')
|
||||
.replace('/** Surface placement. */\n', '')
|
||||
+ '/** Duplicate event. */\nexport type SessionEvent = { type: never }\n',
|
||||
}))).toThrow(violations)
|
||||
})
|
||||
})
|
||||
|
||||
describe('gen-persistence-catalog collectSurfaceEventTypes', () => {
|
||||
it('parses the literal union', () => {
|
||||
const types = collectSurfaceEventTypes(make({
|
||||
@@ -192,9 +250,21 @@ describe('gen-persistence-catalog annotateSurface + render', () => {
|
||||
scope: name.split('/')[0] ?? name,
|
||||
payload: '{ turn: number }',
|
||||
doc: `Records ${name}.`,
|
||||
declaration: `/** Records ${name}. */\n'${name}': { turn: number }`,
|
||||
source: 'packages/core/fix/src/types.ts:3',
|
||||
})
|
||||
|
||||
const envelopeTypes = [
|
||||
'SessionEventType',
|
||||
'SurfaceEventType',
|
||||
'SurfaceOp',
|
||||
'SessionEvent',
|
||||
].map(name => ({
|
||||
name: name as 'SessionEventType' | 'SurfaceEventType' | 'SurfaceOp' | 'SessionEvent',
|
||||
declaration: `/** ${name}. */\nexport type ${name} = never`,
|
||||
source: 'packages/core/fix/src/types.ts:1',
|
||||
}))
|
||||
|
||||
it('badges union members surface and everything else log-only', () => {
|
||||
const annotated = annotateSurface([entry('fix/message'), entry('fix/marker')], ['fix/message'])
|
||||
expect(annotated.map(e => [e.name, e.surface])).toEqual([['fix/message', true], ['fix/marker', false]])
|
||||
@@ -205,11 +275,13 @@ describe('gen-persistence-catalog annotateSurface + render', () => {
|
||||
.toThrow(/'fix\/ghost' name no declared log event/)
|
||||
})
|
||||
|
||||
it('renders badges, payload fences, and the generated-file header', () => {
|
||||
const out = render(annotateSurface([entry('fix/message'), entry('fix/marker')], ['fix/message']))
|
||||
it('renders badges, declaration fences, and the generated-file header', () => {
|
||||
const out = render(annotateSurface([entry('fix/message'), entry('fix/marker')], ['fix/message']), envelopeTypes)
|
||||
expect(out).toContain('Generated by scripts/gen-persistence-catalog.ts')
|
||||
expect(out).toContain('# Session Persistence Event Catalog')
|
||||
expect(out).toContain('```ts persistence-catalog\n/** SessionEventType. */\nexport type SessionEventType = never')
|
||||
expect(out).toContain('#### `fix/message` — surface')
|
||||
expect(out).toContain('#### `fix/marker` — log-only')
|
||||
expect(out).toContain('```ts persistence-catalog\n\'fix/marker\': { turn: number }\n```')
|
||||
expect(out).toContain('```ts persistence-catalog\n/** Records fix/marker. */\n\'fix/marker\': { turn: number }\n```')
|
||||
})
|
||||
})
|
||||
|
||||
@@ -21,6 +21,7 @@ tools:
|
||||
- `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.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.
|
||||
|
||||
### Injected services
|
||||
|
||||
@@ -32,7 +33,7 @@ The live registry pipeline has three transformable waterfalls followed by the ob
|
||||
|
||||
### Key types
|
||||
|
||||
- `ToolDefinition` — `ToolSchema` + `execute(args, exec)`, optional presentation callbacks, and cooperative `timeoutMs`.
|
||||
- `ToolDefinition` — `ToolSchema` + `execute(args, exec)`, optional presentation callbacks, cooperative `timeoutMs`, and optional per-call `isConcurrencySafe(args)` classification.
|
||||
- `ToolExecutionInput` — the caller-supplied call description: `{ callId, name, arguments, agent?, parent?, signal? }`; callers may pass an enclosing execution's opaque token as `parent` but never choose the new execution's own token.
|
||||
- `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.
|
||||
@@ -87,6 +88,8 @@ 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.
|
||||
|
||||
### Structured-output schema subset
|
||||
|
||||
`StructuredOutputSchema` is the object-rooted raw JSON Schema subset used by subagents and workflows for machine-readable results. It accepts one scalar `type`, object `properties`/`required`/boolean `additionalProperties`, array `items`, and scalar `enum`/`const`. The annotations `description`, `title`, `default`, and `examples` are ignored but must remain JSON data. Type arrays, undeclared required keys, and unsupported keywords fail through `OutputSchemaError` rather than being ignored; `validateStructuredValue()` returns path-qualified violations without throwing.
|
||||
@@ -108,6 +111,10 @@ Under `code` or `both`, the registry exposes the reserved `run_code` transport a
|
||||
- **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.
|
||||
- **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.
|
||||
|
||||
## Model Experience
|
||||
|
||||
### Normal tool schemas
|
||||
@@ -145,7 +152,7 @@ The available tools:
|
||||
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
- **Native tool calls execute sequentially** — `ToolDefinition` carries no concurrency-safety metadata; adding it (and parallel execution in the loop) waits on the deferred tool-shapes review (`TODO(review)`).
|
||||
- **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.
|
||||
- **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-timeout-policy` wrapper.
|
||||
|
||||
@@ -117,9 +117,6 @@ declare module 'cordis' {
|
||||
}
|
||||
}
|
||||
|
||||
// TODO(concurrency): revisit these shapes when concurrency metadata becomes useful
|
||||
// (for example, a read-only hint that would permit safe parallel execution).
|
||||
|
||||
/** Tool output, optionally with lossless-JSON presentation metadata persisted for replay. */
|
||||
export type ToolExecuteReturn = ContentBlock[] | { content: ContentBlock[]; meta?: unknown }
|
||||
|
||||
@@ -134,6 +131,20 @@ export interface ToolDefinition extends ToolSchema {
|
||||
* cooperative implementation that can reach quiescence when the signal aborts.
|
||||
*/
|
||||
timeoutMs?: number
|
||||
/**
|
||||
* Pure synchronous classifier for overlap with sibling tool calls. Only
|
||||
* `true` opts in; omission, exceptions, non-`true` returns, and invalid
|
||||
* `defineTool` arguments are exclusive. This metadata is never model-visible.
|
||||
*
|
||||
* 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)
|
||||
* for the full contract.
|
||||
* @param args - parsed arguments; `defineTool` validates before calling.
|
||||
* @returns Whether this call may join a parallel group.
|
||||
*/
|
||||
isConcurrencySafe?(args: unknown): boolean
|
||||
/**
|
||||
* Optional: how to present the PENDING state of one call in a UI, derived from
|
||||
* the call's `args` (parsed arguments, `unknown` — the tool validates/narrows
|
||||
@@ -195,6 +206,14 @@ export interface ToolExecutionInput {
|
||||
signal?: AbortSignal
|
||||
}
|
||||
|
||||
/**
|
||||
* Scheduling mode for one pending call. `parallel` may overlap with siblings;
|
||||
* `exclusive` runs alone and forms an ordering barrier.
|
||||
*/
|
||||
export type ToolExecutionMode =
|
||||
| { kind: 'parallel' }
|
||||
| { kind: 'exclusive' }
|
||||
|
||||
/**
|
||||
* One pending tool call inside the registry pipeline. Parsed arguments cross
|
||||
* one lossless-JSON materialization boundary before policy and are deep-frozen;
|
||||
@@ -222,6 +241,47 @@ export interface ToolRunContext extends ToolExecution {
|
||||
deferContext(context: HookContext): void
|
||||
}
|
||||
|
||||
/**
|
||||
* Scheduler-only result after ordered pre-execute and guards. A `post-result`
|
||||
* still receives post-execute; a `final-result` bypasses it.
|
||||
* @internal
|
||||
*/
|
||||
export type ScheduledToolPreparation =
|
||||
| { kind: 'dispatch'; exec: ToolRunContext }
|
||||
| { kind: 'post-result'; exec: ToolRunContext; result: ToolExecutionResult }
|
||||
| { kind: 'final-result'; exec: ToolRunContext; result: ToolExecutionResult }
|
||||
|
||||
/**
|
||||
* Scheduler-only dispatch result. A `post-result` still receives post-execute;
|
||||
* a `final-result` already matches {@link ToolRegistry.execute} failure semantics.
|
||||
* @internal
|
||||
*/
|
||||
export type ScheduledToolDispatch =
|
||||
| { kind: 'post-result'; result: ToolExecutionResult }
|
||||
| { kind: 'final-result'; result: ToolExecutionResult }
|
||||
|
||||
/**
|
||||
* Symbol-keyed scheduler view that keeps pre/post policy ordered while
|
||||
* overlapping dispatch. Ordinary callers use {@link ToolRegistry.execute};
|
||||
* this is not a plugin seam.
|
||||
* @internal
|
||||
*/
|
||||
export interface ToolRegistryScheduler {
|
||||
/** Materialize input, run the ordered pre-execute/guard gate, and decide what stage follows. */
|
||||
prepare(exec: ToolExecutionInput): Promise<ScheduledToolPreparation>
|
||||
/** Run only the around-dispatch/body stage. */
|
||||
dispatch(exec: ToolRunContext): Promise<ScheduledToolDispatch>
|
||||
/** Run ordered post-execute finalization, then materialize and notify the final outcome. */
|
||||
finalize(exec: ToolRunContext, result: ToolExecutionResult): Promise<ToolExecutionResult>
|
||||
/** Materialize and notify a final outcome that must bypass post-execute. */
|
||||
finish(exec: ToolRunContext, result: ToolExecutionResult): ToolExecutionResult
|
||||
}
|
||||
|
||||
/**
|
||||
* Scheduler entry point omitted from the generated named service API.
|
||||
* @internal
|
||||
*/
|
||||
export const TOOL_REGISTRY_SCHEDULER: unique symbol = Symbol('@deepseek-ai/dsh-tools.scheduler')
|
||||
/** Structured error metadata for a failed tool call (alongside the model-facing text). */
|
||||
export interface ToolErrorInfo {
|
||||
name: string
|
||||
@@ -382,6 +442,16 @@ export class ToolRegistry extends Service {
|
||||
mode: z.union(['native', 'code', 'both'] as const).default('native'),
|
||||
})
|
||||
|
||||
/** Internal staged view consumed by `dsh-agent-loop`'s parallel scheduler. */
|
||||
readonly [TOOL_REGISTRY_SCHEDULER]: ToolRegistryScheduler = {
|
||||
prepare: exec => this.prepareScheduledExecution(exec),
|
||||
dispatch: exec => this.dispatchScheduledExecution(exec),
|
||||
finalize: (exec, result) => this.finalizeScheduledExecution(exec, result),
|
||||
finish: (exec, result) => this.finishScheduledExecution(exec, result),
|
||||
}
|
||||
|
||||
/** Context deferred by a running tool body, keyed by its scheduler-owned execution. */
|
||||
private deferredContexts = new WeakMap<ToolRunContext, HookContext[]>()
|
||||
private global = new Map<string, ToolDefinition>()
|
||||
private scoped = new Map<ScopeKey, Map<string, ToolDefinition>>()
|
||||
/** Compiled restriction filters, per scope (see {@link restrict}). */
|
||||
@@ -682,6 +752,24 @@ export class ToolRegistry extends Service {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Classify a pending call through the caller's visible tool definition. Only
|
||||
* an exact `true` is parallel; unknown, hidden, undeclared, invalid, or
|
||||
* throwing classifiers are exclusive.
|
||||
* @param exec - call name, parsed arguments, and optional agent scope.
|
||||
* @returns the fail-closed scheduling mode.
|
||||
*/
|
||||
executionMode(exec: ToolExecutionInput): ToolExecutionMode {
|
||||
const tool = this.get(exec.name, exec.agent)
|
||||
if (!tool?.isConcurrencySafe) return { kind: 'exclusive' }
|
||||
try {
|
||||
const concurrencySafe: unknown = tool.isConcurrencySafe(exec.arguments)
|
||||
return concurrencySafe === true ? { kind: 'parallel' } : { kind: 'exclusive' }
|
||||
} catch {
|
||||
return { kind: 'exclusive' }
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Execute through pre-policy, guards, around-dispatch, post-policy, and final
|
||||
* notification. Tool and listener failures resolve as materialized error
|
||||
@@ -692,6 +780,28 @@ export class ToolRegistry extends Service {
|
||||
* @returns the materialized final result.
|
||||
*/
|
||||
async execute(exec: ToolExecutionInput): Promise<ToolExecutionResult> {
|
||||
return this.prepareExecution(exec, prepared => this.completeScheduledExecution(prepared))
|
||||
}
|
||||
|
||||
private async completeScheduledExecution(prepared: ScheduledToolPreparation): Promise<ToolExecutionResult> {
|
||||
switch (prepared.kind) {
|
||||
case 'dispatch': {
|
||||
const dispatched = await this.dispatchScheduledExecution(prepared.exec)
|
||||
return dispatched.kind === 'post-result'
|
||||
? await this.finalizeScheduledExecution(prepared.exec, dispatched.result)
|
||||
: this.finishScheduledExecution(prepared.exec, dispatched.result)
|
||||
}
|
||||
case 'post-result':
|
||||
return await this.finalizeScheduledExecution(prepared.exec, prepared.result)
|
||||
case 'final-result':
|
||||
return this.finishScheduledExecution(prepared.exec, prepared.result)
|
||||
/* v8 ignore next -- closed-union exhaustiveness guard */
|
||||
default:
|
||||
return assertNever(prepared, 'scheduled tool preparation')
|
||||
}
|
||||
}
|
||||
|
||||
private createExecution(exec: ToolExecutionInput): ScheduledToolPreparation | { kind: 'ready'; exec: ToolRunContext } {
|
||||
const deferredContexts: HookContext[] = []
|
||||
const token = createExecutionToken()
|
||||
const callId = exec.callId
|
||||
@@ -710,105 +820,143 @@ export class ToolRegistry extends Service {
|
||||
deferredContexts.push(context)
|
||||
},
|
||||
}
|
||||
let execution: ToolRunContext
|
||||
try {
|
||||
const detached = snapshotJsonValue(exec.arguments)
|
||||
if (detached === undefined) {
|
||||
throw new TypeError('tool execution arguments must be losslessly JSON-serializable')
|
||||
}
|
||||
execution = {
|
||||
...base,
|
||||
arguments: deepFreeze(detached),
|
||||
}
|
||||
const execution: ToolRunContext = { ...base, arguments: deepFreeze(detached) }
|
||||
this.deferredContexts.set(execution, deferredContexts)
|
||||
return { kind: 'ready', exec: execution }
|
||||
} catch (error: unknown) {
|
||||
execution = { ...base, arguments: undefined }
|
||||
const result = this.materializeFinalResult(toolErrorResult(error))
|
||||
this.notifyResult(execution, result)
|
||||
return result
|
||||
const execution: ToolRunContext = { ...base, arguments: undefined }
|
||||
return { kind: 'final-result', exec: execution, result: toolErrorResult(error) }
|
||||
}
|
||||
let result: ToolExecutionResult
|
||||
}
|
||||
|
||||
/**
|
||||
* Run the ordered pre-execute and monotonic guard stages for the scheduler.
|
||||
* @param input - the caller-supplied execution input.
|
||||
* @returns the prepared execution plus the next scheduler stage.
|
||||
* @internal
|
||||
*/
|
||||
private async prepareScheduledExecution(input: ToolExecutionInput): Promise<ScheduledToolPreparation> {
|
||||
return this.prepareExecution(input, prepared => prepared)
|
||||
}
|
||||
|
||||
private async prepareExecution<T>(
|
||||
input: ToolExecutionInput,
|
||||
next: (prepared: ScheduledToolPreparation) => T | PromiseLike<T>,
|
||||
): Promise<T> {
|
||||
const created = this.createExecution(input)
|
||||
if (created.kind !== 'ready') return next(created)
|
||||
const exec = created.exec
|
||||
try {
|
||||
result = this.materializeFinalResult(await this.executePipeline(execution, deferredContexts))
|
||||
const carrier = scopeTarget(this, exec.agent)
|
||||
const gate = await this.ctx.waterfall(
|
||||
carrier, 'tools/pre-execute', exec,
|
||||
() => Promise.resolve<PreToolDecision>({ kind: 'allow' }),
|
||||
)
|
||||
const decision = gate.kind === 'ask' ? await this.serviceAsk(exec, gate) : gate
|
||||
const denialReason = decision.kind === 'allow'
|
||||
? this.guardReason(exec)
|
||||
: decision.reason
|
||||
if (denialReason !== undefined) {
|
||||
return await next({
|
||||
kind: 'post-result',
|
||||
exec,
|
||||
result: {
|
||||
content: [{ type: 'text', text: `Error: ${denialReason}` }],
|
||||
isError: true,
|
||||
},
|
||||
})
|
||||
}
|
||||
return await next({ kind: 'dispatch', exec })
|
||||
} catch (error: unknown) {
|
||||
// Outer backstop: a throwing pre/post-execute listener, guard, or the
|
||||
// waterfall machinery becomes an isError result, never a turn failure.
|
||||
result = this.materializeFinalResult(toolErrorResult(error))
|
||||
return next({ kind: 'final-result', exec, result: toolErrorResult(error) })
|
||||
}
|
||||
this.notifyResult(execution, result)
|
||||
return result
|
||||
}
|
||||
|
||||
/** Run the transformable pipeline; {@link execute} owns final normalization and notification. */
|
||||
private async executePipeline(exec: ToolRunContext, deferredContexts: HookContext[]): Promise<ToolExecutionResult> {
|
||||
// --- Gate: tools/pre-execute. An `ask` resolves through the optional
|
||||
// approval seam (or degrades to deny) before the monotonic guards run. The
|
||||
// carrier keys dispatch by exec.agent, so an `agent.ctx` listener gates only
|
||||
// its own agent's calls (agent-less calls are subject-less).
|
||||
const carrier = scopeTarget(this, exec.agent)
|
||||
const gate = await this.ctx.waterfall(
|
||||
carrier, 'tools/pre-execute', exec,
|
||||
() => Promise.resolve<PreToolDecision>({ kind: 'allow' }),
|
||||
)
|
||||
const decision = gate.kind === 'ask' ? await this.serviceAsk(exec, gate) : gate
|
||||
const denialReason = decision.kind === 'allow'
|
||||
? this.guardReason(exec)
|
||||
: decision.reason
|
||||
if (denialReason !== undefined) {
|
||||
// Every non-grant, including a failed/unavailable approval request, takes
|
||||
// the same deny path and still reaches post-policy plus result observers.
|
||||
const denied: ToolExecutionResult = {
|
||||
content: [{ type: 'text', text: `Error: ${denialReason}` }],
|
||||
isError: true,
|
||||
}
|
||||
return await this.postExecute(exec, denied)
|
||||
}
|
||||
|
||||
// --- Around-dispatch: tools/execute. The base `next` is the dispatch-
|
||||
// with-normalization thunk — the tool body's own try/catch turns a throw
|
||||
// into an isError result so a wrapper (and post-execute) can inspect it;
|
||||
// an unknown tool routes through the same catch. A `tools/execute` listener
|
||||
// (e.g. a timeout plugin) wraps this thunk: it may replace `exec.signal`
|
||||
// before delegating and inspect the normalized result after. Dispatched with the
|
||||
// same carrier as the gate, so an `agent.ctx` wrapper wraps only its own
|
||||
// agent's calls. ---
|
||||
const result = await this.ctx.waterfall(
|
||||
carrier, 'tools/execute', exec,
|
||||
async (): Promise<ToolExecutionResult> => {
|
||||
try {
|
||||
// Resolve through the CALLER's visible view ({@link get}): a scoped
|
||||
// tool shadows its global name-twin for that agent, and a
|
||||
// restricted-away global tool is exactly as absent as a nonexistent
|
||||
// one — same UNKNOWN_TOOL result, no capability leak in the error.
|
||||
const tool = this.get(exec.name, exec.agent)
|
||||
if (!tool) throw new ToolNotFoundError(exec.name)
|
||||
// Normalize the two `execute` return shapes: a bare ContentBlock[] (no
|
||||
// meta) or a { content, meta } object (a tool attaching a private
|
||||
// presentation payload). An array IS the content; the object carries it.
|
||||
const returned = await tool.execute(exec.arguments, exec)
|
||||
const content = Array.isArray(returned) ? returned : returned.content
|
||||
const meta = Array.isArray(returned) ? undefined : returned.meta
|
||||
return { content, isError: false, ...meta !== undefined ? { meta } : {} }
|
||||
} catch (error: unknown) {
|
||||
return toolErrorResult(error)
|
||||
/**
|
||||
* Run around-dispatch and the tool body. Tool and unknown-tool failures still
|
||||
* receive post-execute; pipeline failures are already final.
|
||||
* @param exec - the prepared execution.
|
||||
* @returns whether the result still needs post-execute.
|
||||
* @internal
|
||||
*/
|
||||
private async dispatchScheduledExecution(exec: ToolRunContext): Promise<ScheduledToolDispatch> {
|
||||
try {
|
||||
const carrier = scopeTarget(this, exec.agent)
|
||||
const result = await this.ctx.waterfall(
|
||||
carrier, 'tools/execute', exec,
|
||||
async (): Promise<ToolExecutionResult> => {
|
||||
try {
|
||||
const tool = this.get(exec.name, exec.agent)
|
||||
if (!tool) throw new ToolNotFoundError(exec.name)
|
||||
const returned = await tool.execute(exec.arguments, exec)
|
||||
const content = Array.isArray(returned) ? returned : returned.content
|
||||
const meta = Array.isArray(returned) ? undefined : returned.meta
|
||||
return { content, isError: false, ...meta !== undefined ? { meta } : {} }
|
||||
} catch (error: unknown) {
|
||||
return toolErrorResult(error)
|
||||
}
|
||||
},
|
||||
)
|
||||
const deferredContexts = this.deferredContexts.get(exec)
|
||||
/* v8 ignore next -- dispatch only receives executions minted by this registry's prepare stage */
|
||||
if (deferredContexts === undefined) throw new Error('tool registry scheduler invariant violated: unprepared execution')
|
||||
const resultWithDeferredContexts: ToolExecutionResult = deferredContexts.length === 0
|
||||
? result
|
||||
: {
|
||||
...result,
|
||||
additionalContexts: [
|
||||
...deferredContexts,
|
||||
...result.additionalContexts ?? [],
|
||||
],
|
||||
}
|
||||
},
|
||||
)
|
||||
const resultWithDeferredContexts: ToolExecutionResult = deferredContexts.length === 0
|
||||
? result
|
||||
: {
|
||||
...result,
|
||||
additionalContexts: [
|
||||
...deferredContexts,
|
||||
...result.additionalContexts ?? [],
|
||||
],
|
||||
}
|
||||
return await this.postExecute(exec, resultWithDeferredContexts)
|
||||
return { kind: 'post-result', result: resultWithDeferredContexts }
|
||||
} catch (error: unknown) {
|
||||
return { kind: 'final-result', result: toolErrorResult(error) }
|
||||
}
|
||||
}
|
||||
|
||||
/** Notify final-result observers without giving them a mutation/error channel into the outcome. */
|
||||
/**
|
||||
* Run ordered post-execute, then materialize and notify the final outcome.
|
||||
* @param exec - the prepared execution.
|
||||
* @param result - dispatch/pre result that still needs post-execute.
|
||||
* @returns the materialized final result.
|
||||
* @internal
|
||||
*/
|
||||
private async finalizeScheduledExecution(exec: ToolRunContext, result: ToolExecutionResult): Promise<ToolExecutionResult> {
|
||||
try {
|
||||
return this.finishScheduledExecution(exec, await this.postExecute(exec, result))
|
||||
} catch (error: unknown) {
|
||||
return this.finishScheduledExecution(exec, toolErrorResult(error))
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Materialize and notify a final result that must bypass post-execute.
|
||||
* @param exec - the prepared execution.
|
||||
* @param result - final result.
|
||||
* @returns the materialized final result.
|
||||
* @internal
|
||||
*/
|
||||
private finishScheduledExecution(exec: ToolRunContext, result: ToolExecutionResult): ToolExecutionResult {
|
||||
let finalResult: ToolExecutionResult
|
||||
try {
|
||||
finalResult = this.materializeFinalResult(result)
|
||||
} catch (error: unknown) {
|
||||
finalResult = this.materializeFinalResult(toolErrorResult(error))
|
||||
}
|
||||
this.notifyResult(exec, finalResult)
|
||||
return finalResult
|
||||
}
|
||||
|
||||
/** Notify observers without exposing a mutation or error channel into the outcome. */
|
||||
private notifyResult(exec: ToolExecution, result: ToolExecutionResult): void {
|
||||
// The pipeline is over: freeze the remaining mutable signal slot so every
|
||||
// observer sees the SAME WeakMap-keyable execution without a mutation race.
|
||||
// Freeze the remaining mutable signal slot before observers receive the
|
||||
// shared WeakMap-keyable execution object.
|
||||
Object.freeze(exec)
|
||||
const callbacks = this.ctx.events.dispatch('emit', [
|
||||
scopeTarget(this, exec.agent), 'tools/result', exec, result,
|
||||
|
||||
@@ -283,6 +283,14 @@ export interface DefineToolOptions<S extends SchemaSpec> {
|
||||
* is never sent to the model.
|
||||
*/
|
||||
readonly timeoutMs?: number
|
||||
/**
|
||||
* Optional pure synchronous classifier for sibling overlap. It receives typed
|
||||
* arguments after soft validation; invalid input returns `false` without
|
||||
* invoking it. See {@link ToolDefinition.isConcurrencySafe}.
|
||||
* @param args - typed validated arguments.
|
||||
* @returns whether this call may join a parallel group.
|
||||
*/
|
||||
isConcurrencySafe?(args: InferArgs<S>): boolean
|
||||
/**
|
||||
* Tool execution function. `args` is typed as {@link InferArgs<S>} — zero
|
||||
* casts needed. Returns either a bare {@link ContentBlock}`[]` (model-facing
|
||||
@@ -315,7 +323,7 @@ export interface DefineToolOptions<S extends SchemaSpec> {
|
||||
* @param options - the tool's name, description, typed parameter schema,
|
||||
* execute body, and optional presenters.
|
||||
* @returns a registry-ready definition with strict execution validation and
|
||||
* soft presenter validation for replay compatibility.
|
||||
* soft presenter and classifier validation for replay compatibility.
|
||||
*/
|
||||
export function defineTool<S extends SchemaSpec>(options: DefineToolOptions<S>): ToolDefinition {
|
||||
// Object-literal execute methods don't use `this`; the reference is safe.
|
||||
@@ -325,6 +333,8 @@ export function defineTool<S extends SchemaSpec>(options: DefineToolOptions<S>):
|
||||
const userPresentCall = options.presentCall
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userPresentResult = options.presentResult
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userIsConcurrencySafe = options.isConcurrencySafe
|
||||
if (options.timeoutMs !== undefined && (!Number.isFinite(options.timeoutMs) || options.timeoutMs <= 0)) {
|
||||
throw new Error(`defineTool(${options.name}): timeoutMs must be a positive finite number`)
|
||||
}
|
||||
@@ -359,5 +369,12 @@ export function defineTool<S extends SchemaSpec>(options: DefineToolOptions<S>):
|
||||
return userPresentResult(args as InferArgs<S>, result)
|
||||
}
|
||||
}
|
||||
// Invalid arguments fail closed without invoking the typed classifier.
|
||||
if (userIsConcurrencySafe) {
|
||||
tool.isConcurrencySafe = (args: unknown): boolean => {
|
||||
if (validateArgs(options.parameters, args).length > 0) return false
|
||||
return userIsConcurrencySafe(args as InferArgs<S>)
|
||||
}
|
||||
}
|
||||
return tool
|
||||
}
|
||||
|
||||
136
packages/core/tools/tests/execution-mode.spec.ts
Normal file
136
packages/core/tools/tests/execution-mode.spec.ts
Normal file
@@ -0,0 +1,136 @@
|
||||
/** Covers fail-closed per-call classification and model-schema isolation. */
|
||||
|
||||
import { describe, expect, expectTypeOf, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, {
|
||||
defineTool,
|
||||
type ToolDefinition,
|
||||
type ToolExecutionInput,
|
||||
type ToolExecutionMode,
|
||||
} from '@deepseek-ai/dsh-tools'
|
||||
|
||||
async function setup() {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
return ctx
|
||||
}
|
||||
|
||||
function exec(name: string, args: unknown): ToolExecutionInput {
|
||||
return { callId: CallId('c1'), name, arguments: args }
|
||||
}
|
||||
|
||||
describe('ToolRegistry.executionMode', () => {
|
||||
it('returns parallel only for an explicit true classifier', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'safe',
|
||||
description: 'parallel-safe',
|
||||
parameters: {},
|
||||
isConcurrencySafe: () => true,
|
||||
async execute() { return [] },
|
||||
}))
|
||||
expect(ctx.tools.executionMode(exec('safe', {}))).toEqual({ kind: 'parallel' })
|
||||
})
|
||||
|
||||
it('defaults to exclusive for a tool with no isConcurrencySafe declaration', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'plain',
|
||||
description: 'no declaration',
|
||||
parameters: {},
|
||||
async execute() { return [] },
|
||||
}))
|
||||
expect(ctx.tools.executionMode(exec('plain', {}))).toEqual({ kind: 'exclusive' })
|
||||
})
|
||||
|
||||
it('returns exclusive for an unknown tool', async () => {
|
||||
const ctx = await setup()
|
||||
expect(ctx.tools.executionMode(exec('nonexistent', {}))).toEqual({ kind: 'exclusive' })
|
||||
})
|
||||
|
||||
it('returns exclusive when the classifier returns false for these args', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'rw',
|
||||
description: 'read or write',
|
||||
parameters: { mode: { type: 'string', required: true } },
|
||||
isConcurrencySafe: args => args.mode === 'read',
|
||||
async execute() { return [] },
|
||||
}))
|
||||
expect(ctx.tools.executionMode(exec('rw', { mode: 'read' }))).toEqual({ kind: 'parallel' })
|
||||
expect(ctx.tools.executionMode(exec('rw', { mode: 'write' }))).toEqual({ kind: 'exclusive' })
|
||||
})
|
||||
|
||||
it('classifies invalid defineTool arguments as exclusive without throwing', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'needs-mode',
|
||||
description: 'requires mode',
|
||||
parameters: { mode: { type: 'string', required: true } },
|
||||
isConcurrencySafe: () => true,
|
||||
async execute() { return [] },
|
||||
}))
|
||||
expect(ctx.tools.executionMode(exec('needs-mode', {}))).toEqual({ kind: 'exclusive' })
|
||||
})
|
||||
|
||||
it('treats a throwing raw classifier as exclusive', async () => {
|
||||
const ctx = await setup()
|
||||
const raw: ToolDefinition = {
|
||||
name: 'thrower',
|
||||
description: 'classifier throws',
|
||||
parameters: { type: 'object', properties: {} },
|
||||
isConcurrencySafe() { throw new Error('boom') },
|
||||
async execute() { return [] },
|
||||
}
|
||||
ctx.tools.register(raw)
|
||||
expect(ctx.tools.executionMode(exec('thrower', {}))).toEqual({ kind: 'exclusive' })
|
||||
})
|
||||
|
||||
it('treats a truthy non-boolean raw result as exclusive', async () => {
|
||||
const ctx = await setup()
|
||||
const raw = {
|
||||
name: 'truthy',
|
||||
description: 'classifier returns a truthy string',
|
||||
parameters: { type: 'object', properties: {} },
|
||||
isConcurrencySafe() { return 'yes' },
|
||||
async execute() { return [] },
|
||||
} as unknown as ToolDefinition
|
||||
ctx.tools.register(raw)
|
||||
expect(ctx.tools.executionMode(exec('truthy', {}))).toEqual({ kind: 'exclusive' })
|
||||
})
|
||||
|
||||
it('passes parsed arguments directly to a raw definition', async () => {
|
||||
const ctx = await setup()
|
||||
let seen: unknown
|
||||
ctx.tools.register({
|
||||
name: 'raw-safe',
|
||||
description: 'raw',
|
||||
parameters: { type: 'object', properties: {} },
|
||||
isConcurrencySafe(args) { seen = args; return true },
|
||||
async execute() { return [] },
|
||||
})
|
||||
expect(ctx.tools.executionMode(exec('raw-safe', { anything: 1 }))).toEqual({ kind: 'parallel' })
|
||||
expect(seen).toEqual({ anything: 1 })
|
||||
})
|
||||
|
||||
it('isConcurrencySafe never reaches the model-facing schemas() projection', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'safe',
|
||||
description: 'parallel-safe',
|
||||
parameters: { x: { type: 'string', required: true } },
|
||||
isConcurrencySafe: () => true,
|
||||
async execute() { return [] },
|
||||
}))
|
||||
const schema = ctx.tools.schemas()[0] as unknown as Record<string, unknown>
|
||||
expect(Object.keys(schema).sort()).toEqual(['description', 'name', 'parameters'])
|
||||
expect(schema.isConcurrencySafe).toBeUndefined()
|
||||
})
|
||||
|
||||
it('ToolExecutionMode is the object-tagged union', () => {
|
||||
expectTypeOf<ToolExecutionMode>().toEqualTypeOf<{ kind: 'parallel' } | { kind: 'exclusive' }>()
|
||||
})
|
||||
})
|
||||
@@ -27,6 +27,7 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron
|
||||
|---|---|---|
|
||||
| `provider` | (required) | the initial provider route for each per-session agent the bridge creates; ACP model selection may replace it per session |
|
||||
| `model` | (required) | the initial model for each per-session agent; ACP clients may switch among adapter-advertised models |
|
||||
| `maxParallelToolCalls` | agent-loop default | positive-integer concurrent tool-call cap shared by the bundled loop's agents; `1` is serial |
|
||||
| `persona` | — | the deployment persona template (may reference `{{provider}}`/`{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` |
|
||||
| `toolOrder` | — | explicit model-facing tool order (a name list with one `'<unlisted-tools>'` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` |
|
||||
| `dshHome` | `$DSH_HOME` or `~/.dsh` | Harness home exposed to model bash and used by local skill discovery |
|
||||
|
||||
@@ -34,6 +34,8 @@ export interface Config {
|
||||
provider: string
|
||||
/** Model name for ACP-created agents (must have a registered adapter). */
|
||||
model: string
|
||||
/** Bundled agent-loop concurrency cap; `1` is serial and omission uses its default. */
|
||||
maxParallelToolCalls?: number
|
||||
/** Deployment persona (the system-prompt plugin's `persona` config). */
|
||||
persona?: string
|
||||
/** Explicit model-facing tool order (the system-prompt plugin's `toolOrder` config; see dsh-system-prompt). */
|
||||
@@ -60,6 +62,7 @@ export interface Config {
|
||||
export const Config: z<Config> = z.object({
|
||||
provider: z.string().required(),
|
||||
model: z.string().required(),
|
||||
maxParallelToolCalls: z.number().step(1).min(1),
|
||||
persona: z.string(),
|
||||
// The array default is forced to undefined: ABSENT means "lexicographic
|
||||
// order" (the owning dsh-system-prompt schema does the same), while
|
||||
|
||||
@@ -127,6 +127,19 @@ describe('dsh-acp-demo composition', () => {
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('forwards maxParallelToolCalls to the bundled agent loop', async () => {
|
||||
const ctx = await mount({
|
||||
provider: 'mock',
|
||||
model: 'mock',
|
||||
maxParallelToolCalls: 3,
|
||||
persistenceRoot: '/tmp/dsh-acp-demo-test-parallel',
|
||||
skills: await isolatedSkillsConfig(),
|
||||
workspaceContext: false,
|
||||
})
|
||||
expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3)
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('forwards bundled tool config into agent-core', async () => {
|
||||
const ctx = await mount({
|
||||
provider: 'mock',
|
||||
|
||||
@@ -42,11 +42,11 @@ This is the [interface/implementation/consumer seam](../../../docs/rfc/implement
|
||||
|
||||
```ts
|
||||
import type { Config } from '@deepseek-ai/dsh-agent-spine-demo'
|
||||
// { agents?, persona?, toolOrder?, tools?, dshHome?, skills?, workspaceContext, toolBash?, toolTasks? }
|
||||
// { agents?, maxParallelToolCalls?, persona?, toolOrder?, tools?, dshHome?, skills?, workspaceContext, toolBash?, toolTasks? }
|
||||
// workspaceContext requires { maxBytes } or false; the other owner schemas supply defaults.
|
||||
```
|
||||
|
||||
The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer, while `toolTasks` controls generic `task_output` wait bounds; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
|
||||
The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — a stdio app pre-creates `main`, while the ACP app creates agents on demand at `session/new`; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer, while `toolTasks` controls generic `task_output` wait bounds; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
|
||||
|
||||
## Why a code bundle, not a shared YAML include
|
||||
|
||||
|
||||
@@ -57,6 +57,8 @@ export interface SkillConfig {
|
||||
export interface Config {
|
||||
/** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
|
||||
agents?: AgentLoopConfig['agents']
|
||||
/** Agent-loop concurrency cap; `1` is serial. */
|
||||
maxParallelToolCalls?: AgentLoopConfig['maxParallelToolCalls']
|
||||
/** The deployment persona (see dsh-system-prompt's `Config`). */
|
||||
persona?: SystemPromptConfig['persona']
|
||||
/** The explicit model-facing tool order (see dsh-system-prompt's `Config`). */
|
||||
@@ -109,6 +111,7 @@ export const Config = z.intersect([
|
||||
*/
|
||||
export function pickSpineConfig(config: Omit<Config, 'agents'>): Omit<Config, 'agents'> {
|
||||
return {
|
||||
...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {},
|
||||
...config.persona !== undefined ? { persona: config.persona } : {},
|
||||
...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {},
|
||||
...config.tools !== undefined ? { tools: config.tools } : {},
|
||||
@@ -160,5 +163,8 @@ export function apply(ctx: Context, config: Config): void {
|
||||
// rendered order, so workspace instructions must precede the skill catalog.
|
||||
ctx.plugin(toolSkill, config.skills?.tool ?? {})
|
||||
ctx.plugin(toolTasks, config.toolTasks ?? {})
|
||||
ctx.plugin(AgentLoop, { agents: config.agents ?? [] })
|
||||
ctx.plugin(AgentLoop, {
|
||||
agents: config.agents ?? [],
|
||||
...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {},
|
||||
})
|
||||
}
|
||||
|
||||
@@ -145,6 +145,16 @@ describe('dsh-agent-spine-demo bundle', () => {
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('forwards the global maxParallelToolCalls config to agent-loop', async () => {
|
||||
const ctx = await mount({
|
||||
agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock' }],
|
||||
maxParallelToolCalls: 3,
|
||||
workspaceContext: false,
|
||||
})
|
||||
expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3)
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('tolerates a schema-bypassing direct apply (the ?? fallbacks fire)', async () => {
|
||||
// ctx.plugin validates + defaults the bundle config first; a direct apply
|
||||
// skips the schema, so the forwarding `?? []` / `?? ''` are what fire.
|
||||
|
||||
@@ -27,6 +27,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte
|
||||
|---|---|---|
|
||||
| `provider` | (required) | the pre-created `main` agent's registered provider route |
|
||||
| `model` | (required) | the pre-created `main` agent's model |
|
||||
| `maxParallelToolCalls` | agent-loop default | positive-integer concurrent tool-call cap shared by the bundled loop's agents; `1` is serial |
|
||||
| `persona` | — | the deployment persona template (may reference `{{provider}}`/`{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` |
|
||||
| `toolOrder` | — | explicit model-facing tool order (a name list with one `'<unlisted-tools>'` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` |
|
||||
| `dshHome` | `$DSH_HOME` or `~/.dsh` | Harness home exposed to model bash and used by local skill discovery |
|
||||
|
||||
@@ -39,6 +39,8 @@ export interface Config {
|
||||
provider: string
|
||||
/** Model name for the `main` agent (must have a registered adapter). */
|
||||
model: string
|
||||
/** Bundled agent-loop concurrency cap; `1` is serial and omission uses its default. */
|
||||
maxParallelToolCalls?: number
|
||||
/** Deployment persona (the system-prompt plugin's `persona` config). */
|
||||
persona?: string
|
||||
/** Explicit model-facing tool order (the system-prompt plugin's `toolOrder` config; see dsh-system-prompt). */
|
||||
@@ -70,6 +72,7 @@ export interface Config {
|
||||
export const Config: z<Config> = z.object({
|
||||
provider: z.string().required(),
|
||||
model: z.string().required(),
|
||||
maxParallelToolCalls: z.number().step(1).min(1),
|
||||
persona: z.string(),
|
||||
// The array default is forced to undefined: ABSENT means "lexicographic
|
||||
// order" (the owning dsh-system-prompt schema does the same), while
|
||||
|
||||
@@ -142,6 +142,19 @@ describe('dsh-stdio-demo app', () => {
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('forwards maxParallelToolCalls to the bundled agent loop', async () => {
|
||||
const ctx = await mount({
|
||||
provider: 'mock',
|
||||
model: 'mock',
|
||||
maxParallelToolCalls: 3,
|
||||
persistenceRoot: '/tmp/dsh-stdio-demo-spec-parallel',
|
||||
skills: await isolatedSkillsConfig(),
|
||||
workspaceContext: false,
|
||||
})
|
||||
expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3)
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
|
||||
it('forwards bundled tool config into agent-core', async () => {
|
||||
const ctx = await mount({
|
||||
provider: 'mock',
|
||||
|
||||
@@ -46,6 +46,8 @@ The tool passes `exec` (the tool-execution context) as the opaque `actor` on eve
|
||||
|
||||
`fs/observed` fires AFTER the read/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event.
|
||||
|
||||
`read` opts into concurrent scheduling because its only mutation is the synchronous version recorder. Recorder races fail closed when a later `write` or `edit` re-checks the version under its target lock; both mutation tools remain exclusive. See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md).
|
||||
|
||||
The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them.
|
||||
|
||||
## Model Experience
|
||||
|
||||
@@ -84,6 +84,8 @@ export function applyReadTool(ctx: Context, caps: ReadToolCaps): void {
|
||||
offset: { type: 'number', description: '1-based first line to return. Defaults to 1.' },
|
||||
limit: { type: 'number', description: `Maximum number of lines to return. Defaults to ${caps.limit}.` },
|
||||
},
|
||||
// Observation races fail closed because guarded mutations re-check the version in-lock.
|
||||
isConcurrencySafe: () => true,
|
||||
async execute(args, exec): Promise<ContentBlock[]> {
|
||||
const input = parseReadArgs(args, caps.limit)
|
||||
const target = await ctx.fs.resolve(input.filePath, sessionResolveOptions(exec))
|
||||
|
||||
@@ -384,6 +384,33 @@ describe('signal, concurrency, and the fs/observed contract', () => {
|
||||
expect(onDisk === 'ONE value here' || onDisk === 'base TWO here').toBe(true)
|
||||
})
|
||||
|
||||
it('a stale observed version from an older read fails closed at edit CAS', async () => {
|
||||
await writeFile(join(dir, 'a.txt'), 'older content\n')
|
||||
const target = await ctx.fs.resolve('a.txt')
|
||||
const firstInfo = await ctx.fs.stat(target)
|
||||
if (!firstInfo) throw new Error('expected first stat')
|
||||
|
||||
expect((await callOwned('read', { file_path: 'a.txt' })).isError).toBe(false)
|
||||
|
||||
await writeFile(join(dir, 'a.txt'), 'newer current content\n')
|
||||
const secondInfo = await ctx.fs.stat(target)
|
||||
if (!secondInfo) throw new Error('expected second stat')
|
||||
expect(secondInfo.version).not.toBe(firstInfo.version)
|
||||
expect((await callOwned('read', { file_path: 'a.txt' })).isError).toBe(false)
|
||||
|
||||
// Reproduce an older concurrent read winning the observation race.
|
||||
ctx.emit('fs/observed', target, firstInfo.version, { agent: { session } })
|
||||
|
||||
const edit = await callOwned('edit', {
|
||||
file_path: 'a.txt',
|
||||
old_string: 'newer',
|
||||
new_string: 'edited',
|
||||
})
|
||||
expect(edit.isError).toBe(true)
|
||||
expect(edit.error).toMatchObject({ code: 'FS_STALE_VERSION' })
|
||||
expect(await readFile(join(dir, 'a.txt'), 'utf8')).toBe('newer current content\n')
|
||||
})
|
||||
|
||||
it('a throwing fs/observed listener surfaces as isError, but the mutation already hit disk', async () => {
|
||||
// fs/observed is a plain ctx.emit after the write succeeded; a throwing listener cannot
|
||||
// roll the write back — it only turns the tool result into isError.
|
||||
|
||||
@@ -108,6 +108,16 @@ describe('registration', () => {
|
||||
expect(ctx.tools.schemas().map(s => s.name).sort()).toEqual(['edit', 'read', 'write'])
|
||||
})
|
||||
|
||||
it('declares read parallel-safe while write/edit remain exclusive', async () => {
|
||||
const { ctx } = await setup()
|
||||
expect(ctx.tools.executionMode({ callId: CallId('read-safe'), name: 'read', arguments: { file_path: 'a.txt' } }))
|
||||
.toEqual({ kind: 'parallel' })
|
||||
expect(ctx.tools.executionMode({ callId: CallId('write-exclusive'), name: 'write', arguments: { file_path: 'a.txt', content: 'x' } }))
|
||||
.toEqual({ kind: 'exclusive' })
|
||||
expect(ctx.tools.executionMode({ callId: CallId('edit-exclusive'), name: 'edit', arguments: { file_path: 'a.txt', old_string: 'x', new_string: 'y' } }))
|
||||
.toEqual({ kind: 'exclusive' })
|
||||
})
|
||||
|
||||
it('registers prompt sections for each tool', async () => {
|
||||
const { ctx } = await setup()
|
||||
const prompt = renderPrompt(await ctx.systemPrompt.assemble())
|
||||
|
||||
@@ -24,6 +24,10 @@ With `run_in_background: true`, the tool registers the parent-owned task before
|
||||
| `toolFilter` | Per-child global-tool restriction; requires `toolFilter` capability. |
|
||||
| `maxDepth` | Absolute delegation-depth cap; requires `depthLimit` capability. |
|
||||
|
||||
## Concurrency
|
||||
|
||||
Foreground and background calls are exclusive. Children may share the parent's workspace or external resources, and a unary classifier cannot prove that sibling delegations have disjoint effects. See the [parallel tool-call RFC](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md).
|
||||
|
||||
## Model Experience
|
||||
|
||||
### Tool schema
|
||||
|
||||
@@ -96,6 +96,20 @@ describe('dsh-tool-subagent', () => {
|
||||
expect(foreground.isError).toBe(false)
|
||||
})
|
||||
|
||||
it('keeps foreground and background calls exclusive', async () => {
|
||||
const ctx = await setup({ provider: 'mock' })
|
||||
expect(ctx.tools.executionMode({
|
||||
callId: CallId('subagent-foreground'),
|
||||
name: 'subagent',
|
||||
arguments: { description: 'do work', prompt: 'Reply OK' },
|
||||
})).toEqual({ kind: 'exclusive' })
|
||||
expect(ctx.tools.executionMode({
|
||||
callId: CallId('subagent-background'),
|
||||
name: 'subagent',
|
||||
arguments: { description: 'do work', prompt: 'Reply OK', run_in_background: true },
|
||||
})).toEqual({ kind: 'exclusive' })
|
||||
})
|
||||
|
||||
it.each([
|
||||
{ stopReason: 'aborted' as const, fragment: 'cancelled' },
|
||||
{ stopReason: 'error' as const, fragment: 'failed' },
|
||||
|
||||
@@ -4,11 +4,11 @@ Packages that exist to serve development, testing, and the examples rather than
|
||||
|
||||
| Package | Role | ctx key |
|
||||
|---|---|---|
|
||||
| `acp-snapshot/` | ACP snapshot suite kit: subprocess scenario harness + golden normalizers + the `defineAcpSnapshotSuite` factory | (library — imported by example `*.snapshot.ts` suites) |
|
||||
| `acp-snapshot/` | ACP test kit: shared subprocess/client launcher + snapshot harness, normalizers, and suite factory | (library — imported by ACP e2e and `*.snapshot.ts` suites) |
|
||||
| `agent-loop-testkit/` | Shared prerequisite mounting for tests that exercise the concrete agent loop | (library — imported by AgentLoop integration tests) |
|
||||
| `invariants/` | Runtime event-contract assertions for development diagnostics | (listens on `session/*`, `agent/*`) |
|
||||
| `loader-smoke/` | Shared real-Loader subprocess harness for keyless example smokes | (library — imported by example e2e suites) |
|
||||
| `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) |
|
||||
| `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) |
|
||||
|
||||
`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-spine-demo` bundle mounts it unconditionally. `agent-loop-testkit` centralizes the mandatory service spine for hand-built AgentLoop tests without owning their loop or scenario. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery, while `loader-smoke` owns the parallel stdio/Loader process boundary used by keyless example e2e suites. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.
|
||||
`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-spine-demo` bundle mounts it unconditionally. `agent-loop-testkit` centralizes the mandatory service spine for hand-built AgentLoop tests without owning their loop or scenario. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the ACP subprocess/client boundary plus the snapshot harness, normalizers, and suite machinery, while `loader-smoke` owns the parallel stdio/Loader process boundary used by keyless example e2e suites. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.
|
||||
|
||||
@@ -2,11 +2,12 @@
|
||||
|
||||
The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tier (`pnpm run test:snapshot`, [testing policy](../../../docs/testing.md)). An example gets a full snapshot suite from a scenario table plus a fixtures directory; every compare/guard mechanic lives here, under the per-file coverage gate, instead of being copied per example.
|
||||
|
||||
Three layers, importable separately:
|
||||
Four layers, importable separately:
|
||||
|
||||
- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit, inherited stdio closure, and ACP parser exhaustion before resolving or propagating a child error, so captures are complete and callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy.
|
||||
- **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). Startup failures preserve captured agent stderr in the rejected diagnostic.
|
||||
- **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
|
||||
- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.golden.md` plus `tool-schemas.golden.json`) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Must be called at vitest collection time.
|
||||
- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.golden.md` plus `tool-schemas.golden.json`) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session.<n>.jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time.
|
||||
|
||||
A consuming `*.snapshot.ts` is the scenario table plus one factory call:
|
||||
|
||||
@@ -37,9 +38,9 @@ defineAcpSnapshotSuite({
|
||||
|
||||
A scenario booting a differently-composed tree sets its own `configPath` (an overlay whose basename still ends in `cordis.yml`, so the bin's replay swap finds the sibling `*cordis.snapshot.yml`) and, when that composition changes the request header, its own `headerClass` with its own pinning scenario — the acp-agent example's Code Mode and filesystem scenarios are templates. Each pinning directory stores the normalized full prompt sequence in generated `system-prompt.golden.md` and the corresponding full tool-schema sequence in generated `tool-schemas.golden.json`; `session.jsonl` stores `"system":"{{system}}","tools":"{{tools}}"` while retaining config, reason, and any model-visible prefix. A pin with legitimate mid-run header changes declares `expectedHeaderChanges`, which fixes the length of both sidecar sequences.
|
||||
|
||||
Examples use a `cordis.snapshot.yml` overlay with [`dsh-llm-replay`](../llm-replay/README.md). Recording calls the live model and updates model fixtures; keyless refresh replays those fixtures and updates derived stdout, session-log, prompt, and tool-schema snapshots. See the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md).
|
||||
The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config RFC](../../../docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log goldens, and each pin's prompt and tool-schema sidecars from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md).
|
||||
|
||||
`suite.ts` imports Vitest, so use this package only inside a Vitest run. The ACP-specific script queues permission answers by stable option kind and maps them to current option ids; a missing answer cancels, while an unavailable kind fails the scenario after cancelling the agent request. It can also set session config options or assert that unknown ids and values are rejected in the transcript.
|
||||
Constraints: `suite.ts` imports vitest, so the package entry is importable only inside a vitest run (the launcher, harness, and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection`. Permission round-trips are scriptable: `InputScript.permissionAnswers` is a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) the client maps to the agent-issued `optionId` at answer time; an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run (the agent is answered `cancelled`, so a tolerant agent cannot absorb the scenario bug). Session config options are scriptable too: the `setConfigOption` step switches a knob over `session/set_config_option`, and `setConfigOptionExpectError` asserts the bridge rejects an unknown id or out-of-vocabulary value (the error frame stays in the transcript).
|
||||
|
||||
## Model Experience
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@deepseek-ai/dsh-acp-snapshot",
|
||||
"description": "ACP snapshot suite kit: real-subprocess scenario harness, golden normalizers, and the suite factory behind the keyless snapshot tier",
|
||||
"description": "ACP test kit: shared subprocess launcher, snapshot scenario harness, golden normalizers, and suite factory",
|
||||
"version": "0.0.1",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
|
||||
@@ -1,59 +1,47 @@
|
||||
/**
|
||||
* Shared ACP snapshot subprocess harness. It boots the real agent bin through the Cordis
|
||||
* loader, drives deterministic ACP JSON-RPC over stdio, captures protocol-pure stdout, and
|
||||
* harvests persisted session logs after graceful shutdown. Normalization stays in
|
||||
* `normalize.ts`; suite registration stays in `suite.ts`.
|
||||
* Shared subprocess harness for ACP snapshot suites. A library module driven by
|
||||
* the suite factory in ./suite.ts (and directly by harness-level specs); each
|
||||
* example's `*.snapshot.ts` names its own agent-under-test paths.
|
||||
*
|
||||
* It boots the REAL agent bin subprocess via the cordis Loader (so the
|
||||
* export-shape bug class stays guarded — see docs/postmortem/0001), drives it
|
||||
* over real ACP JSON-RPC stdio with a deterministic input script, tees raw
|
||||
* stdout (for the golden + a purity check) into an SDK `ClientSideConnection`,
|
||||
* and — in record mode — harvests the persisted session JSONL after a graceful
|
||||
* shutdown flush. The pure normalizers in ./normalize.ts turn the captured
|
||||
* stdout frames and the session-log events into stable, snapshot-able text.
|
||||
*
|
||||
* See docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-acp-snapshot/harness
|
||||
*/
|
||||
|
||||
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
|
||||
import { cp, mkdtemp, readFile, readdir, rm } from 'node:fs/promises'
|
||||
import { existsSync } from 'node:fs'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join, delimiter } from 'node:path'
|
||||
import { Readable, Writable } from 'node:stream'
|
||||
import {
|
||||
ClientSideConnection,
|
||||
ndJsonStream,
|
||||
PROTOCOL_VERSION,
|
||||
type Agent as AcpAgent,
|
||||
type Client,
|
||||
type RequestPermissionRequest,
|
||||
type RequestPermissionResponse,
|
||||
type SessionNotification,
|
||||
} from '@agentclientprotocol/sdk'
|
||||
import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
|
||||
import { launchAcpTestAgent, type AgentUnderTest, type LaunchedAcpTestAgent } from './launcher.ts'
|
||||
|
||||
export type { AgentUnderTest } from './launcher.ts'
|
||||
|
||||
/**
|
||||
* The agent composition a scenario runs against: which bin to boot and which
|
||||
* leaf config it loads. All paths are ABSOLUTE — the subprocess cwd is a temp
|
||||
* dir outside the repo, so relative resolution would miss; a suite resolves
|
||||
* them from its own `import.meta.url`.
|
||||
*/
|
||||
export interface AgentUnderTest {
|
||||
/** The agent bin's SOURCE entry (e.g. `packages/examples/acp-demo/src/bin.ts`); the `lib` bin is derived from it. */
|
||||
binScript: string
|
||||
/** Explicit plain-Node entry for `lib` mode; intended for test fixtures outside a package `src/` tree. */
|
||||
libBinScript?: string | undefined
|
||||
/**
|
||||
* The example's live `cordis.yml`. Under `DSH_SNAPSHOT=replay` the bin swaps
|
||||
* it for the sibling `cordis.snapshot.yml` (the keyless replay overlay), so
|
||||
* one path serves both modes.
|
||||
*/
|
||||
configPath: string
|
||||
/**
|
||||
* The repo-root tsconfig whose `paths` map resolves the unbuilt workspace
|
||||
* imports in `src` mode (passed to the child as `TSX_TSCONFIG_PATH`). Ignored
|
||||
* in `lib` mode, where the example resolves plugins through real `exports`.
|
||||
*/
|
||||
tsconfigPath: string
|
||||
}
|
||||
|
||||
/**
|
||||
* One step of a scenario's deterministic input script (`input.json`). The harness interprets
|
||||
* these in order. `newSession` captures the server-issued (random) session id into a
|
||||
* `{{sessionId}}` variable that later steps reference. `promptAndCancel` sends without awaiting,
|
||||
* waits for the first streamed message, then cancels, making transcript order deterministic.
|
||||
* One step of a scenario's deterministic input script (`input.json`). The
|
||||
* harness interprets these in order. `newSession` captures the server-issued
|
||||
* (random) session id into a `{{sessionId}}` variable that later steps
|
||||
* reference, since a committed file cannot know the id in advance.
|
||||
*
|
||||
* `promptAndCancel` sends a prompt WITHOUT awaiting its response, waits until
|
||||
* the client observes the first streamed `agent_message_chunk` (so the emitted
|
||||
* frames deterministically precede the cancellation), then cancels the turn —
|
||||
* the only way to exercise a cancel deterministically (a plain `prompt` step
|
||||
* awaits the response, which a cancel/hang scenario would block on forever).
|
||||
*/
|
||||
export type InputStep =
|
||||
| { op: 'initialize'; terminalOutput?: boolean }
|
||||
@@ -70,9 +58,16 @@ export type InputStep =
|
||||
export interface InputScript {
|
||||
steps: InputStep[]
|
||||
/**
|
||||
* FIFO permission answers selected by stable option kind; the harness maps each kind to the
|
||||
* agent-issued option id. Exhaustion cancels, while a kind the agent did not offer fails the
|
||||
* scenario.
|
||||
* Ordered answers for the agent's `session/request_permission` round-trips,
|
||||
* consumed FIFO — the Nth request gets the Nth answer. Each answer selects
|
||||
* by option KIND: option ids are agent-issued randoms a committed script
|
||||
* cannot know, while kinds are the ACP-stable vocabulary, so the client maps
|
||||
* kind → the offered `optionId` at answer time. A request beyond the queue
|
||||
* (or with no queue at all) is answered `cancelled` — the stub behavior a
|
||||
* scenario without approvals relies on. A scripted kind the request does
|
||||
* not offer REJECTS the run: the scenario scripted an impossible click,
|
||||
* and {@link runScenario} throws once the in-flight step settles (the
|
||||
* agent itself just sees `cancelled`, so it cannot absorb the bug).
|
||||
*/
|
||||
permissionAnswers?: PermissionAnswer[]
|
||||
}
|
||||
@@ -165,93 +160,47 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise
|
||||
// Fixed path length: spill-policy budgets the preview against the REAL path
|
||||
// before stdout normalization, so tmpdir() length differences churn goldens.
|
||||
const spillRoot = '/tmp/dsh-acp-snapshot-spill'
|
||||
// Everything past the temp-dir creation runs under a try/finally that always
|
||||
// removes both dirs — so a failure in workspace seeding, spawn, or any step
|
||||
// never leaks them (the "e2e tests own their resources" rule).
|
||||
let child: ChildProcessWithoutNullStreams | undefined
|
||||
// Everything past the temp-dir creation is followed by failure-safe cleanup,
|
||||
// so a failure in workspace seeding, spawn, or any step never leaks resources.
|
||||
let launched: LaunchedAcpTestAgent | undefined
|
||||
let sessionId: string | undefined
|
||||
let sessionLogs: HarvestedLog[] = []
|
||||
const rawBuffers: Buffer[] = []
|
||||
const stderrChunks: string[] = []
|
||||
try {
|
||||
const outcome = await (async (): Promise<RunResult> => {
|
||||
// Seed the workspace if the scenario ships one (a file the agent reads/edits).
|
||||
// Copied into the temp cwd so the agent's bash tools see it; the goldens
|
||||
// normalize the cwd, so the seeded paths stay stable across runs.
|
||||
if (opts.workspaceDir !== undefined && existsSync(opts.workspaceDir)) {
|
||||
await cp(opts.workspaceDir, cwd, { recursive: true })
|
||||
}
|
||||
// Boot the agent in the environment's mode (DSH_EXAMPLE_MODE): `src` runs the
|
||||
// source bin under tsx with the paths map; `lib` runs the built bin under plain
|
||||
// Node, resolving plugins through the example's workspace node_modules → lib.
|
||||
const launch = resolveExampleLaunch({
|
||||
srcBin: opts.agent.binScript,
|
||||
libBin: opts.agent.libBinScript,
|
||||
configArgs: ['--config', opts.configPath ?? opts.agent.configPath],
|
||||
tsconfigPath: opts.agent.tsconfigPath,
|
||||
env: {
|
||||
DSH_SNAPSHOT: opts.mode,
|
||||
DSH_SNAPSHOT_FILE: opts.fixtureFile,
|
||||
DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot,
|
||||
DSH_SNAPSHOT_SPILL_ROOT: spillRoot,
|
||||
DSH_HOME: join(cwd, '.dsh'),
|
||||
DSH_AGENTS_HOME: join(cwd, '.agents'),
|
||||
...opts.overrideFile !== undefined ? { DSH_SNAPSHOT_OVERRIDE: opts.overrideFile } : {},
|
||||
...opts.childFiles !== undefined && opts.childFiles.length > 0
|
||||
? { DSH_SNAPSHOT_CHILD_FILES: opts.childFiles.join(delimiter) }
|
||||
: {},
|
||||
},
|
||||
})
|
||||
|
||||
child = spawn(
|
||||
launch.command,
|
||||
launch.args,
|
||||
{ cwd, env: { ...process.env, ...launch.env }, stdio: ['pipe', 'pipe', 'pipe'] },
|
||||
)
|
||||
|
||||
child.stderr.setEncoding('utf8')
|
||||
child.stderr.on('data', (c: string) => stderrChunks.push(c))
|
||||
|
||||
// Tee the same raw bytes to the golden and SDK client. Decode once at the end so a UTF-8
|
||||
// sequence split across stream chunks cannot corrupt the transcript.
|
||||
const passthrough = new Readable({ read() {} })
|
||||
child.stdout.on('data', (buf: Buffer) => {
|
||||
rawBuffers.push(buf)
|
||||
passthrough.push(buf)
|
||||
})
|
||||
child.stdout.on('end', () => passthrough.push(null))
|
||||
|
||||
const stream = ndJsonStream(
|
||||
Writable.toWeb(child.stdin) as WritableStream<Uint8Array>,
|
||||
Readable.toWeb(passthrough) as ReadableStream<Uint8Array>,
|
||||
)
|
||||
// Watcher so a step can block until the client OBSERVES a particular
|
||||
// session/update — used by promptAndCancel to pin frame order (send cancel
|
||||
// only after the streamed agent_message_chunk has arrived, so those frames
|
||||
// deterministically precede the cancelled prompt response).
|
||||
const updateWaiters: { match: (u: SessionNotification['update']) => boolean; resolve: () => void }[] = []
|
||||
const waitForUpdate = (match: (u: SessionNotification['update']) => boolean): Promise<void> =>
|
||||
new Promise<void>(resolve => updateWaiters.push({ match, resolve }))
|
||||
const env: NodeJS.ProcessEnv = {
|
||||
DSH_SNAPSHOT: opts.mode,
|
||||
DSH_SNAPSHOT_FILE: opts.fixtureFile,
|
||||
DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot,
|
||||
DSH_SNAPSHOT_SPILL_ROOT: spillRoot,
|
||||
DSH_HOME: join(cwd, '.dsh'),
|
||||
DSH_AGENTS_HOME: join(cwd, '.agents'),
|
||||
...opts.overrideFile !== undefined ? { DSH_SNAPSHOT_OVERRIDE: opts.overrideFile } : {},
|
||||
...opts.childFiles !== undefined && opts.childFiles.length > 0
|
||||
? { DSH_SNAPSHOT_CHILD_FILES: opts.childFiles.join(delimiter) }
|
||||
: {},
|
||||
}
|
||||
|
||||
// Permission answers are consumed FIFO across the whole run; exhaustion
|
||||
// falls back to `cancelled` so approval-free scenarios keep the plain stub.
|
||||
const permissionQueue = [...input.permissionAnswers ?? []]
|
||||
// A callback throw would become only an RPC error the agent could absorb. Record an
|
||||
// impossible permission choice here, answer cancelled, and fail the outer scenario.
|
||||
// A scenario bug detected inside a client callback (a scripted permission
|
||||
// kind the agent never offered). It cannot fail the run from in there: a
|
||||
// callback throw only becomes a JSON-RPC error RESPONSE to the agent, and
|
||||
// a tolerant agent treats that as a denial and carries on — the run (or
|
||||
// worse, a record) would absorb the impossible click silently. So the
|
||||
// callback answers `cancelled` (a well-defined path for the agent),
|
||||
// captures the error here, and the step loop fails the run on it.
|
||||
let scriptError: Error | undefined
|
||||
const makeClient = (_agent: AcpAgent): Client => ({
|
||||
sessionUpdate(params: SessionNotification): Promise<void> {
|
||||
for (let i = updateWaiters.length - 1; i >= 0; i--) {
|
||||
const waiter = updateWaiters[i]
|
||||
// The index is always in-bounds (i only decreases; splice removes at
|
||||
// i, so lower entries stay valid); the guard satisfies
|
||||
// noUncheckedIndexedAccess.
|
||||
/* v8 ignore next 1 -- unreachable in-bounds guard, see above */
|
||||
if (waiter === undefined) continue
|
||||
if (waiter.match(params.update)) {
|
||||
updateWaiters.splice(i, 1)
|
||||
waiter.resolve()
|
||||
}
|
||||
}
|
||||
return Promise.resolve()
|
||||
},
|
||||
launched = launchAcpTestAgent({
|
||||
agent: opts.agent,
|
||||
cwd,
|
||||
...opts.configPath !== undefined ? { configPath: opts.configPath } : {},
|
||||
env,
|
||||
requestPermission(params: RequestPermissionRequest): Promise<RequestPermissionResponse> {
|
||||
const answer = permissionQueue.shift()
|
||||
if (answer === undefined) return Promise.resolve({ outcome: { outcome: 'cancelled' } })
|
||||
@@ -269,10 +218,12 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise
|
||||
return Promise.resolve({ outcome: { outcome: 'selected', optionId: option.optionId } })
|
||||
},
|
||||
})
|
||||
const client = new ClientSideConnection(makeClient, stream)
|
||||
const active = launched
|
||||
await active.spawned
|
||||
const { client } = active
|
||||
|
||||
for (const step of input.steps) {
|
||||
await runStep(client, step, cwd, waitForUpdate, () => sessionId, (id) => { sessionId = id })
|
||||
await runStep(client, step, cwd, match => active.waitForUpdate(match), () => sessionId, (id) => { sessionId = id })
|
||||
// A permission exchange happens while a step's request is in flight, so
|
||||
// by the time the step settles any script bug it exposed is captured —
|
||||
// fail the run HERE, as a harness error, rather than hoping the agent's
|
||||
@@ -281,35 +232,57 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise
|
||||
}
|
||||
// Done driving: close stdin so the server disposes gracefully (flushing
|
||||
// persistence) and exits. Then await exit so the harvested log is complete.
|
||||
child.stdin.end()
|
||||
await waitForExit(child)
|
||||
await active.close()
|
||||
// Harvest EVERY persisted log (parent + any subagent children) while the
|
||||
// temp dirs still exist, ordered primary-first.
|
||||
sessionLogs = await harvestSessionLogs(sessionsRoot)
|
||||
} catch (error: unknown) {
|
||||
const stderr = stderrChunks.join('')
|
||||
if (stderr === '') throw error
|
||||
throw new Error(`snapshot-harness: scenario failed: ${String(error)}\nagent stderr:\n${stderr}`, { cause: error })
|
||||
} finally {
|
||||
// Failure-safe teardown: kill a still-running child and drop the temp dirs
|
||||
// even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a
|
||||
// process or dir. `child` is undefined only if spawn itself threw.
|
||||
if (child !== undefined && child.exitCode === null && child.signalCode === null) {
|
||||
child.kill('SIGKILL')
|
||||
await waitForExit(child)
|
||||
return {
|
||||
rawStdout: launched.rawStdout(),
|
||||
stderr: launched.stderr(),
|
||||
cwd,
|
||||
...sessionId !== undefined ? { sessionId } : {},
|
||||
sessionLogs,
|
||||
}
|
||||
await rm(cwd, { recursive: true, force: true })
|
||||
await rm(sessionsRoot, { recursive: true, force: true })
|
||||
await rm(spillRoot, { recursive: true, force: true })
|
||||
}
|
||||
})().then(
|
||||
value => ({ status: 'fulfilled', value } as const),
|
||||
(error: unknown) => {
|
||||
const stderr = launched?.stderr() ?? ''
|
||||
return {
|
||||
status: 'rejected',
|
||||
error: stderr === ''
|
||||
? error
|
||||
: new Error(`snapshot-harness: scenario failed: ${String(error)}\nagent stderr:\n${stderr}`, { cause: error }),
|
||||
} as const
|
||||
},
|
||||
)
|
||||
|
||||
return {
|
||||
rawStdout: Buffer.concat(rawBuffers).toString('utf8'),
|
||||
stderr: stderrChunks.join(''),
|
||||
cwd,
|
||||
...sessionId !== undefined ? { sessionId } : {},
|
||||
sessionLogs,
|
||||
// Failure-safe teardown: wait for a still-running child, then attempt every
|
||||
// owned-path removal even when an earlier cleanup rejects. Report every
|
||||
// teardown failure alongside a scenario failure so neither orthogonal
|
||||
// outcome hides the other.
|
||||
const cleanupResults: PromiseSettledResult<unknown>[] = []
|
||||
const cleanup = async (action: () => Promise<unknown>): Promise<void> => {
|
||||
cleanupResults.push(...await Promise.allSettled([action()]))
|
||||
}
|
||||
/* v8 ignore next 1 -- launch itself can only throw on a defensive synchronous spawn API failure */
|
||||
await cleanup(() => launched?.close('SIGKILL') ?? Promise.resolve())
|
||||
await cleanup(() => rm(cwd, { recursive: true, force: true }))
|
||||
await cleanup(() => rm(sessionsRoot, { recursive: true, force: true }))
|
||||
await cleanup(() => rm(spillRoot, { recursive: true, force: true }))
|
||||
|
||||
const cleanupFailures = cleanupResults
|
||||
.filter((result): result is PromiseRejectedResult => result.status === 'rejected')
|
||||
.map(result => result.reason as unknown)
|
||||
if (cleanupFailures.length > 0) {
|
||||
throw new AggregateError(
|
||||
outcome.status === 'rejected' ? [outcome.error, ...cleanupFailures] : cleanupFailures,
|
||||
outcome.status === 'rejected'
|
||||
? 'snapshot scenario and cleanup failed'
|
||||
: 'snapshot cleanup failed',
|
||||
)
|
||||
}
|
||||
if (outcome.status === 'rejected') throw outcome.error
|
||||
return outcome.value
|
||||
}
|
||||
|
||||
/** Drive one input step over the client connection. */
|
||||
@@ -317,7 +290,7 @@ async function runStep(
|
||||
client: ClientSideConnection,
|
||||
step: InputStep,
|
||||
cwd: string,
|
||||
waitForUpdate: (match: (u: SessionNotification['update']) => boolean) => Promise<void>,
|
||||
waitForUpdate: (match: (u: SessionNotification['update']) => boolean) => Promise<SessionNotification['update']>,
|
||||
getSessionId: () => string | undefined,
|
||||
setSessionId: (id: string) => void,
|
||||
): Promise<void> {
|
||||
@@ -334,8 +307,10 @@ async function runStep(
|
||||
return
|
||||
}
|
||||
case 'newSessionExpectError': {
|
||||
// The bridge rejects a session/new that widens the workspace scope (non-empty
|
||||
// additionalDirectories / mcpServers — unimplemented).
|
||||
// The bridge rejects a session/new that widens the workspace scope
|
||||
// (non-empty additionalDirectories / mcpServers — unimplemented). The SDK
|
||||
// surfaces that as a rejected RPC; swallow it so the run completes and the
|
||||
// error frame is captured in the transcript.
|
||||
await client.newSession({
|
||||
cwd,
|
||||
mcpServers: [],
|
||||
@@ -355,8 +330,10 @@ async function runStep(
|
||||
case 'promptExpectError': {
|
||||
const sessionId = getSessionId()
|
||||
if (sessionId === undefined) throw new Error('snapshot-harness: promptExpectError before newSession')
|
||||
// The model fails this turn (a recorded provider error), so the bridge answers the prompt
|
||||
// with a JSON-RPC error and the SDK rejects.
|
||||
// The model fails this turn (a recorded provider error), so the bridge
|
||||
// answers the prompt with a JSON-RPC error and the SDK rejects. That
|
||||
// rejection IS the expected editor experience — swallow it so the run
|
||||
// completes and the stdout transcript (the error frame) is captured.
|
||||
await client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
|
||||
.then(() => { throw new Error('snapshot-harness: expected the prompt to fail but it succeeded') },
|
||||
() => { /* expected: the turn failed and the bridge returned an error */ })
|
||||
@@ -365,8 +342,13 @@ async function runStep(
|
||||
case 'promptAndCancel': {
|
||||
const sessionId = getSessionId()
|
||||
if (sessionId === undefined) throw new Error('snapshot-harness: promptAndCancel before newSession')
|
||||
// A hang fixture never resolves alone. Wait for its streamed chunk before cancellation
|
||||
// so updates deterministically precede the cancelled prompt response.
|
||||
// Dispatch the prompt WITHOUT awaiting (a hang fixture never resolves on
|
||||
// its own). To pin frame order deterministically, wait until the client
|
||||
// has OBSERVED the hang's streamed agent_message_chunk before cancelling —
|
||||
// so those update frames always precede the cancelled prompt response in
|
||||
// the transcript (without this, the late chunk and the response race).
|
||||
// Then cancel and await the prompt, which the bridge settles as
|
||||
// `cancelled` once the abort propagates.
|
||||
const promptDone = client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
|
||||
await waitForUpdate(u => u.sessionUpdate === 'agent_message_chunk')
|
||||
await client.cancel({ sessionId })
|
||||
@@ -402,16 +384,6 @@ async function runStep(
|
||||
}
|
||||
}
|
||||
|
||||
/** Resolve once the child process exits (any code/signal). */
|
||||
function waitForExit(child: ChildProcessWithoutNullStreams): Promise<void> {
|
||||
// Race guard: both call sites run within one synchronous frame of
|
||||
// stdin.end()/kill(), so the exit event cannot have been delivered yet;
|
||||
// kept for any future caller that awaits in between.
|
||||
/* v8 ignore next 1 -- unreachable race guard, see above */
|
||||
if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve()
|
||||
return new Promise<void>(resolve => child.once('exit', () => { resolve() }))
|
||||
}
|
||||
|
||||
/**
|
||||
* Harvest EVERY persisted `.jsonl` session log under a sessions root, parse each
|
||||
* header line, and return them ordered primary-first: the top-level session (no
|
||||
@@ -452,8 +424,14 @@ async function harvestSessionLogs(root: string): Promise<HarvestedLog[]> {
|
||||
})
|
||||
}
|
||||
}
|
||||
// Match replay fixture assignment: primary first, then children by creation time, with id as
|
||||
// a deterministic collision tiebreaker.
|
||||
// Primary (no parentSession) first, then children by ascending createdAt. A
|
||||
// scenario has exactly one top-level session. In the synchronous cut sibling
|
||||
// children are created strictly sequentially, so their createdAt values are
|
||||
// strictly ordered; the recordedId tiebreak only keeps a degenerate
|
||||
// same-millisecond collision (unreachable here) deterministic. This harvest
|
||||
// order must match the replay load order in dsh-llm-replay's loadSessionScripts
|
||||
// so session.<n>.jsonl maps to the same child on record and replay — replay
|
||||
// re-sorts childFiles by the same key, so the two stay consistent.
|
||||
logs.sort((a, b) => {
|
||||
const ap = a.parentSession === undefined ? 0 : 1
|
||||
const bp = b.parentSession === undefined ? 0 : 1
|
||||
|
||||
@@ -1,13 +1,23 @@
|
||||
/**
|
||||
* ACP snapshot suite kit: subprocess scenario harness, pure golden normalizers, and the Vitest
|
||||
* suite factory behind `pnpm run test:snapshot`. Because this entry exports `suite.ts`, importing
|
||||
* it requires a Vitest run.
|
||||
* ACP snapshot suite kit — the shared machinery behind the keyless snapshot
|
||||
* tier (`pnpm run test:snapshot`). Four layers, composable per example: the
|
||||
* shared subprocess/client launcher ({@link launchAcpTestAgent}), the scripted
|
||||
* scenario harness ({@link runScenario}), the pure golden normalizers
|
||||
* ({@link normalizeStdout} / {@link normalizeSessionLog} /
|
||||
* {@link scrubRequestHeaders} / {@link scrubSystemPrompts}), and the suite
|
||||
* factory ({@link defineAcpSnapshotSuite}) that registers a scenario table as a
|
||||
* full describe/it tree. Ordinary ACP e2e tests can use the launcher directly;
|
||||
* an example's `*.snapshot.ts` supplies only its {@link AgentUnderTest} paths,
|
||||
* snapshots directory, and {@link Scenario} table.
|
||||
*
|
||||
* NOTE: ./suite.ts imports vitest, so this package is importable only inside a
|
||||
* vitest run — a support-tier constraint stated in the README.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-acp-snapshot
|
||||
*/
|
||||
|
||||
export {
|
||||
runScenario,
|
||||
type AgentUnderTest,
|
||||
type HarvestedLog,
|
||||
type InputScript,
|
||||
type InputStep,
|
||||
@@ -15,6 +25,12 @@ export {
|
||||
type RunOptions,
|
||||
type RunResult,
|
||||
} from './harness.ts'
|
||||
export {
|
||||
launchAcpTestAgent,
|
||||
type AcpTestLaunchOptions,
|
||||
type AgentUnderTest,
|
||||
type LaunchedAcpTestAgent,
|
||||
} from './launcher.ts'
|
||||
export {
|
||||
normalizeSessionLog,
|
||||
normalizeStdout,
|
||||
|
||||
276
packages/support/acp-snapshot/src/launcher.ts
Normal file
276
packages/support/acp-snapshot/src/launcher.ts
Normal file
@@ -0,0 +1,276 @@
|
||||
/**
|
||||
* Shared launcher for ACP tests that drive an agent subprocess over JSON-RPC
|
||||
* stdio. It owns source-or-built launch resolution, workspace environment,
|
||||
* stdout tee, SDK client, update collection, permission fallback, and process
|
||||
* shutdown so e2e and snapshot suites do not each reconstruct that boundary.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-acp-snapshot/launcher
|
||||
*/
|
||||
|
||||
import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
|
||||
import { join } from 'node:path'
|
||||
import { Readable, Writable } from 'node:stream'
|
||||
import {
|
||||
ClientSideConnection,
|
||||
ndJsonStream,
|
||||
type Agent as AcpAgent,
|
||||
type Client,
|
||||
type RequestPermissionRequest,
|
||||
type RequestPermissionResponse,
|
||||
type SessionNotification,
|
||||
} from '@agentclientprotocol/sdk'
|
||||
import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
|
||||
|
||||
/** The source/built agent entry, leaf config, and workspace tsconfig an ACP test boots. */
|
||||
export interface AgentUnderTest {
|
||||
/** The agent source bin entry (for example `packages/examples/acp-demo/src/bin.ts`). */
|
||||
binScript: string
|
||||
/** Explicit built-mode entry for fixtures whose source path is not under `src/`. */
|
||||
libBinScript?: string | undefined
|
||||
/** The leaf `cordis.yml` loaded by the bin. */
|
||||
configPath: string
|
||||
/** The repo tsconfig whose paths resolve unbuilt workspace imports. */
|
||||
tsconfigPath: string
|
||||
}
|
||||
|
||||
/** Options for one ACP test subprocess. */
|
||||
export interface AcpTestLaunchOptions {
|
||||
/** The agent composition to boot. */
|
||||
agent: AgentUnderTest
|
||||
/** Process cwd and default session-home root. */
|
||||
cwd: string
|
||||
/** Alternate leaf config for this launch. */
|
||||
configPath?: string
|
||||
/** Extra environment values layered over the parent environment. */
|
||||
env?: NodeJS.ProcessEnv
|
||||
/** Permission handler; omitted requests fail closed as `cancelled`. */
|
||||
requestPermission?: (params: RequestPermissionRequest) => Promise<RequestPermissionResponse>
|
||||
}
|
||||
|
||||
/** A running ACP test process and its captured client-side surfaces. */
|
||||
export interface LaunchedAcpTestAgent {
|
||||
/** The child process, exposed for process-level assertions. */
|
||||
child: ChildProcessWithoutNullStreams
|
||||
/** Resolve when the OS spawns the child; reject with its asynchronous spawn failure. */
|
||||
spawned: Promise<void>
|
||||
/** The SDK connection backed by the child's stdio. */
|
||||
client: ClientSideConnection
|
||||
/** Session updates in receive order. */
|
||||
updates: SessionNotification['update'][]
|
||||
/** Decode all stdout bytes captured so far. */
|
||||
rawStdout(): string
|
||||
/** Decode all stderr chunks captured so far. */
|
||||
stderr(): string
|
||||
/** Resolve when a future session update matches the predicate. */
|
||||
waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise<SessionNotification['update']>
|
||||
/** Close the process and drain its streams and callbacks; rejects promptly if fallback termination is refused. */
|
||||
close(signal?: NodeJS.Signals): Promise<void>
|
||||
}
|
||||
|
||||
/**
|
||||
* Boot an ACP agent subprocess and connect an SDK client to its stdio.
|
||||
*
|
||||
* @param options Agent paths, cwd, environment, and optional permission handler.
|
||||
* @returns The running process, connected client, captures, and shutdown handle.
|
||||
*/
|
||||
export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTestAgent {
|
||||
const { agent, cwd } = options
|
||||
const launch = resolveExampleLaunch({
|
||||
srcBin: agent.binScript,
|
||||
libBin: agent.libBinScript,
|
||||
configArgs: ['--config', options.configPath ?? agent.configPath],
|
||||
tsconfigPath: agent.tsconfigPath,
|
||||
env: {
|
||||
...options.env,
|
||||
DSH_HOME: join(cwd, '.dsh'),
|
||||
DSH_AGENTS_HOME: join(cwd, '.agents'),
|
||||
},
|
||||
})
|
||||
const child = spawn(
|
||||
launch.command,
|
||||
launch.args,
|
||||
{
|
||||
cwd,
|
||||
env: { ...process.env, ...launch.env },
|
||||
stdio: ['pipe', 'pipe', 'pipe'],
|
||||
},
|
||||
)
|
||||
// A spawn-level failure is an asynchronous `error` event. Observe it in the
|
||||
// same tick as spawn so a missing cwd or OS rejection cannot crash the test
|
||||
// runner, then make startup and shutdown surface the original error.
|
||||
// Keep observing after the first error: a fallback kill attempted during
|
||||
// shutdown may itself report another process error, which must not become an
|
||||
// unhandled EventEmitter error after the promise has already settled.
|
||||
const childFailure = new Promise<Error>(resolve => child.on('error', resolve))
|
||||
const spawned = Promise.race([
|
||||
new Promise<void>(resolve => child.once('spawn', resolve)),
|
||||
childFailure.then((error): never => { throw error }),
|
||||
])
|
||||
// `spawned` is public and close() also awaits it, but a caller may ignore both.
|
||||
// Keep that misuse from turning the already-observed child error into an
|
||||
// unhandled promise rejection.
|
||||
void spawned.catch(() => undefined)
|
||||
|
||||
const stderrChunks: string[] = []
|
||||
child.stderr.setEncoding('utf8')
|
||||
child.stderr.on('data', (chunk: string) => stderrChunks.push(chunk))
|
||||
|
||||
const rawBuffers: Buffer[] = []
|
||||
const passthrough = new Readable({ read() {} })
|
||||
const updates: SessionNotification['update'][] = []
|
||||
const updateWaiters: {
|
||||
match: (update: SessionNotification['update']) => boolean
|
||||
resolve: (update: SessionNotification['update']) => void
|
||||
reject: (reason: unknown) => void
|
||||
}[] = []
|
||||
let updateStreamFailure: Error | undefined
|
||||
const closeUpdateStream = (): void => {
|
||||
if (updateStreamFailure !== undefined) return
|
||||
updateStreamFailure = new Error('ACP test agent update stream closed before a matching session update arrived')
|
||||
for (const waiter of updateWaiters.splice(0)) waiter.reject(updateStreamFailure)
|
||||
}
|
||||
child.stdout.on('data', (buffer: Buffer) => {
|
||||
rawBuffers.push(buffer)
|
||||
passthrough.push(buffer)
|
||||
})
|
||||
child.stdout.on('end', () => {
|
||||
passthrough.push(null)
|
||||
})
|
||||
const stream = ndJsonStream(
|
||||
Writable.toWeb(child.stdin) as WritableStream<Uint8Array>,
|
||||
Readable.toWeb(passthrough) as ReadableStream<Uint8Array>,
|
||||
)
|
||||
const inFlightClientCallbacks = new Set<Promise<unknown>>()
|
||||
const trackClientCallback = <T>(callback: () => T | PromiseLike<T>): Promise<T> => {
|
||||
const pending = Promise.resolve().then(callback)
|
||||
inFlightClientCallbacks.add(pending)
|
||||
const untrack = (): void => { inFlightClientCallbacks.delete(pending) }
|
||||
void pending.then(untrack, untrack)
|
||||
return pending
|
||||
}
|
||||
const requestPermission = options.requestPermission
|
||||
?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' as const } }))
|
||||
const makeClient = (_agent: AcpAgent): Client => ({
|
||||
sessionUpdate(params: SessionNotification): Promise<void> {
|
||||
return trackClientCallback(() => {
|
||||
updates.push(params.update)
|
||||
for (let index = updateWaiters.length - 1; index >= 0; index--) {
|
||||
const waiter = updateWaiters[index]
|
||||
/* v8 ignore next 1 -- index is bounded by the array length */
|
||||
if (waiter === undefined) continue
|
||||
let matches: boolean
|
||||
try {
|
||||
matches = waiter.match(params.update)
|
||||
} catch (error: unknown) {
|
||||
updateWaiters.splice(index, 1)
|
||||
waiter.reject(error)
|
||||
continue
|
||||
}
|
||||
if (!matches) continue
|
||||
updateWaiters.splice(index, 1)
|
||||
waiter.resolve(params.update)
|
||||
}
|
||||
})
|
||||
},
|
||||
requestPermission: params => trackClientCallback(() => requestPermission(params)),
|
||||
})
|
||||
const client = new ClientSideConnection(makeClient, stream)
|
||||
// `exit` only reports the parent process's status. Descendants may retain
|
||||
// inherited stdout/stderr handles and buffered ACP frames may still be
|
||||
// crossing the SDK parser. Node's `close` follows stdio closure; the SDK's
|
||||
// `closed` follows parser exhaustion. Capture both eagerly so a caller that
|
||||
// invokes close after process exit still joins the complete drain boundary.
|
||||
const stdioClosed = new Promise<void>(resolve => child.once('close', () => { resolve() }))
|
||||
const drained = Promise.all([stdioClosed, client.closed]).then(async () => {
|
||||
// The ACP SDK's readable loop dispatches client callbacks without awaiting
|
||||
// them. Once `closed` settles no new callbacks can start, but callbacks
|
||||
// already in flight still belong to this launch's teardown boundary.
|
||||
while (inFlightClientCallbacks.size > 0) {
|
||||
await Promise.allSettled([...inFlightClientCallbacks])
|
||||
}
|
||||
})
|
||||
// A caller may await a pending update without calling close(). Make natural
|
||||
// stream exhaustion terminal for those waiters too, but only after the
|
||||
// parser has dispatched every buffered frame.
|
||||
void client.closed.then(closeUpdateStream)
|
||||
|
||||
return {
|
||||
child,
|
||||
spawned,
|
||||
client,
|
||||
updates,
|
||||
rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'),
|
||||
stderr: () => stderrChunks.join(''),
|
||||
waitForUpdate(match): Promise<SessionNotification['update']> {
|
||||
if (updateStreamFailure !== undefined) return Promise.reject(updateStreamFailure)
|
||||
return new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject }))
|
||||
},
|
||||
async close(signal?: NodeJS.Signals): Promise<void> {
|
||||
try {
|
||||
await spawned
|
||||
} catch (error: unknown) {
|
||||
await drained
|
||||
closeUpdateStream()
|
||||
throw error
|
||||
}
|
||||
if (!isRunning(child)) {
|
||||
await drained
|
||||
closeUpdateStream()
|
||||
return
|
||||
}
|
||||
const exited = waitForExit(child)
|
||||
if (signal === undefined) child.stdin.end()
|
||||
else child.kill(signal)
|
||||
const failure = await Promise.race([
|
||||
exited.then((): undefined => undefined),
|
||||
childFailure,
|
||||
])
|
||||
if (failure === undefined) {
|
||||
await drained
|
||||
closeUpdateStream()
|
||||
return
|
||||
}
|
||||
|
||||
// An `error` after spawn is not an exit edge: in particular, a failed
|
||||
// signal can leave the subprocess live. Force termination, await the
|
||||
// already-observed exit edge, and only then propagate the child error so
|
||||
// callers may safely remove cwd/session resources after close rejects.
|
||||
const fallbackError = Promise.withResolvers<Error>()
|
||||
const observeFallbackError = (error: Error): void => { fallbackError.resolve(error) }
|
||||
child.once('error', observeFallbackError)
|
||||
if (!child.kill('SIGKILL')) {
|
||||
child.off('error', observeFallbackError)
|
||||
closeUpdateStream()
|
||||
throw new AggregateError(
|
||||
[failure, new Error('Fallback SIGKILL was not accepted by the child process')],
|
||||
'ACP test agent failed and fallback termination was refused',
|
||||
)
|
||||
}
|
||||
const fallbackFailure = await Promise.race([
|
||||
exited.then((): undefined => undefined),
|
||||
fallbackError.promise,
|
||||
])
|
||||
child.off('error', observeFallbackError)
|
||||
if (fallbackFailure !== undefined) {
|
||||
closeUpdateStream()
|
||||
throw new AggregateError(
|
||||
[failure, fallbackFailure],
|
||||
'ACP test agent failed and fallback termination was refused',
|
||||
)
|
||||
}
|
||||
await drained
|
||||
closeUpdateStream()
|
||||
throw failure
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
/** Resolve once a running child exits. */
|
||||
function waitForExit(child: ChildProcessWithoutNullStreams): Promise<void> {
|
||||
return new Promise<void>(resolve => child.once('exit', () => { resolve() }))
|
||||
}
|
||||
|
||||
/** Whether the child still lacks either OS termination marker. */
|
||||
function isRunning(child: ChildProcessWithoutNullStreams): boolean {
|
||||
return child.exitCode === null && child.signalCode === null
|
||||
}
|
||||
@@ -15,7 +15,7 @@
|
||||
* @module @deepseek-ai/dsh-acp-snapshot/suite
|
||||
*/
|
||||
|
||||
import { readFile, readdir, writeFile } from 'node:fs/promises'
|
||||
import { readFile, readdir, rm, writeFile } from 'node:fs/promises'
|
||||
import { existsSync } from 'node:fs'
|
||||
import { join } from 'node:path'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
@@ -71,14 +71,6 @@ export interface Scenario {
|
||||
* false (replay derives from the fixture's `assistant/chunk` events).
|
||||
*/
|
||||
overridden?: boolean
|
||||
/**
|
||||
* How many SUBAGENT child sessions this scenario records beyond the top-level
|
||||
* one (0 for a single-session scenario). Each child rides in a sibling fixture
|
||||
* `session.<n>.jsonl` (1-based); replay forwards them to `dsh-llm-replay` so
|
||||
* each child session replays from its own script, and record mode writes the
|
||||
* harvested child logs back to those files. Defaults to 0.
|
||||
*/
|
||||
childSessions?: number
|
||||
/**
|
||||
* Whether this scenario is its header class's sole request-header pin. Dedicated sidecars own
|
||||
* the prompt and tool schemas, while every classmate is checked for equality.
|
||||
@@ -129,14 +121,40 @@ export interface SnapshotSuiteOptions {
|
||||
}
|
||||
|
||||
/**
|
||||
* The sibling child-fixture paths for a scenario (`session.1.jsonl` …).
|
||||
* Validate and order a scenario directory's session-fixture filenames.
|
||||
*
|
||||
* @param dir The scenario's snapshots directory (`<snapshotsDir>/<name>`).
|
||||
* @param childSessions How many subagent child sessions the scenario records.
|
||||
* @returns One path per child, 1-based, in fixture order.
|
||||
* The primary fixture is always `session.jsonl`; child sessions are discovered
|
||||
* from contiguous `session.1.jsonl` … filenames. The directory is the source of
|
||||
* truth, so scenario tables do not duplicate a child count that can drift from
|
||||
* the files. A session-like JSONL with any other suffix fails loud.
|
||||
*
|
||||
* @param names File names in one scenario directory.
|
||||
* @returns The primary and child fixture names in replay/harvest order.
|
||||
*/
|
||||
export function childFixturePaths(dir: string, childSessions: number): string[] {
|
||||
return Array.from({ length: childSessions }, (_, i) => join(dir, `session.${i + 1}.jsonl`))
|
||||
export function sessionFixtureNames(names: readonly string[]): string[] {
|
||||
if (!names.includes('session.jsonl')) throw new Error('missing session.jsonl')
|
||||
const children: { name: string; index: number }[] = []
|
||||
for (const name of names) {
|
||||
if (name === 'session.jsonl') continue
|
||||
if (!name.startsWith('session.') || !name.endsWith('.jsonl')) continue
|
||||
const match = /^session\.([1-9]\d*)\.jsonl$/.exec(name)
|
||||
if (match === null) throw new Error(`invalid child session fixture name: ${name}`)
|
||||
children.push({ name, index: Number(match[1]) })
|
||||
}
|
||||
children.sort((a, b) => a.index - b.index)
|
||||
for (const [offset, child] of children.entries()) {
|
||||
const expected = offset + 1
|
||||
if (child.index !== expected) {
|
||||
throw new Error(`child session fixtures must be contiguous: expected session.${expected}.jsonl, found ${child.name}`)
|
||||
}
|
||||
}
|
||||
return ['session.jsonl', ...children.map(child => child.name)]
|
||||
}
|
||||
|
||||
/** Read one scenario directory's validated session-fixture inventory. */
|
||||
async function sessionFixtures(dir: string): Promise<string[]> {
|
||||
const entries = await readdir(dir, { withFileTypes: true })
|
||||
return sessionFixtureNames(entries.filter(entry => entry.isFile()).map(entry => entry.name))
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -454,7 +472,12 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
||||
const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript
|
||||
const overrideFile = join(dir, 'replay.override.json')
|
||||
const workspaceDir = join(dir, 'workspace')
|
||||
const childSessions = scenario.childSessions ?? 0
|
||||
// Replay/refresh need the committed inventory up front because those
|
||||
// files drive the model scripts. Record mode creates that inventory
|
||||
// from the harvested live logs, so it must also work for a brand-new
|
||||
// scenario with no session.jsonl yet.
|
||||
let fixtureFiles = RECORDING ? [] : await sessionFixtures(dir)
|
||||
const childFixtureFiles = fixtureFiles.slice(1)
|
||||
const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn
|
||||
const result = await runScenario(input, {
|
||||
agent,
|
||||
@@ -463,7 +486,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
||||
...existsSync(overrideFile) ? { overrideFile } : {},
|
||||
// In REPLAY, forward the recorded child fixtures so each subagent session
|
||||
// replays from its own script. In RECORD they are harvested, not read.
|
||||
...!RECORDING && childSessions > 0 ? { childFiles: childFixturePaths(dir, childSessions) } : {},
|
||||
...!RECORDING && childFixtureFiles.length > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {},
|
||||
...existsSync(workspaceDir) ? { workspaceDir } : {},
|
||||
// A scenario booting an overlay tree passes its own live config; the
|
||||
// bin's replay swap derives the sibling `*cordis.snapshot.yml` from it.
|
||||
@@ -491,7 +514,6 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
||||
const scrub = scenario.pinsHeader === true
|
||||
? (log: string): string => scrubToolSchemas(scrubSystemPrompts(log))
|
||||
: scrubRequestHeaders
|
||||
const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)]
|
||||
const existingFixtures = REFRESHING
|
||||
? await Promise.all(fixtureFiles.map(file => readFile(join(dir, file), 'utf8')))
|
||||
: []
|
||||
@@ -500,18 +522,37 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
||||
|| (REFRESHING && comparesLog)
|
||||
if (writesSessionFixtures) {
|
||||
expect(result.sessionLogs.length, `${mode} produced no session log to harvest`).toBeGreaterThan(0)
|
||||
expect(result.sessionLogs.length, `expected ${childSessions + 1} session logs (parent + children)`)
|
||||
.toBe(childSessions + 1)
|
||||
if (REFRESHING) {
|
||||
expect(result.sessionLogs.length, `expected ${fixtureFiles.length} session logs (parent + children)`)
|
||||
.toBe(fixtureFiles.length)
|
||||
}
|
||||
const outputFixtureFiles = [
|
||||
'session.jsonl',
|
||||
...Array.from({ length: result.sessionLogs.length - 1 }, (_, i) => `session.${i + 1}.jsonl`),
|
||||
]
|
||||
const primary = (result.sessionLogs[0] as HarvestedLog).content
|
||||
await writeFile(join(dir, 'session.jsonl'), scrub(
|
||||
await writeFile(join(dir, outputFixtureFiles[0] as string), scrub(
|
||||
REFRESHING ? stabilizeRefreshLog(primary, existingFixtures[0] as string, replacements) : primary,
|
||||
))
|
||||
for (let i = 1; i < result.sessionLogs.length; i++) {
|
||||
const child = (result.sessionLogs[i] as HarvestedLog).content
|
||||
await writeFile(join(dir, `session.${i}.jsonl`), scrub(
|
||||
await writeFile(join(dir, outputFixtureFiles[i] as string), scrub(
|
||||
REFRESHING ? stabilizeRefreshLog(child, existingFixtures[i] as string, replacements) : child,
|
||||
))
|
||||
}
|
||||
if (RECORDING) {
|
||||
const outputNames = new Set(outputFixtureFiles)
|
||||
const entries = await readdir(dir, { withFileTypes: true })
|
||||
await Promise.all(entries
|
||||
.filter(entry => entry.isFile()
|
||||
// Only valid numbered children are record-owned stale output.
|
||||
// Malformed session-like names stay for the inventory guard to
|
||||
// reject instead of being silently deleted during mutation.
|
||||
&& /^session\.[1-9]\d*\.jsonl$/.test(entry.name)
|
||||
&& !outputNames.has(entry.name))
|
||||
.map(entry => rm(join(dir, entry.name))))
|
||||
fixtureFiles = outputFixtureFiles
|
||||
}
|
||||
if (scenario.pinsHeader === true) {
|
||||
const primary = result.sessionLogs[0] as HarvestedLog
|
||||
const prompts = normalizedSystemPrompts(primary.content, ctx)
|
||||
@@ -540,7 +581,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
||||
// produce one without a model turn (a `rejected` turn carrying `hook/*`).
|
||||
if (comparesLog) {
|
||||
// The harvested logs (primary-first) must match their committed fixtures 1:1.
|
||||
expect(result.sessionLogs.length, 'this scenario must persist a session log').toBe(childSessions + 1)
|
||||
expect(result.sessionLogs.length, 'this scenario must persist one log per session fixture').toBe(fixtureFiles.length)
|
||||
for (let i = 0; i < fixtureFiles.length; i++) {
|
||||
const harvested = scrub((result.sessionLogs[i] as HarvestedLog).content)
|
||||
const fixture = scrub(await readFile(join(dir, fixtureFiles[i] as string), 'utf8'))
|
||||
@@ -619,9 +660,9 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
||||
expect(onDisk).toEqual(registered)
|
||||
})
|
||||
|
||||
it('every registered scenario has its required fixture files', () => {
|
||||
// Every scenario has an input script and an stdout golden.
|
||||
for (const { name, overridden, childSessions, pinsHeader } of scenarios) {
|
||||
it('every registered scenario has its required fixture files', async () => {
|
||||
// Every scenario needs input, stdout, a primary session fixture, and matching optional sidecars.
|
||||
for (const { name, overridden, pinsHeader } of scenarios) {
|
||||
const dir = join(snapshotsDir, name)
|
||||
expect(existsSync(join(dir, 'input.json')), `${name}/input.json`).toBe(true)
|
||||
expect(existsSync(join(dir, 'stdout.golden.jsonl')), `${name}/stdout.golden.jsonl`).toBe(true)
|
||||
@@ -632,11 +673,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
||||
.toBe(pinsHeader === true)
|
||||
expect(existsSync(join(dir, TOOL_SCHEMAS_SNAPSHOT)), `${name}/${TOOL_SCHEMAS_SNAPSHOT} presence must match \`pinsHeader\``)
|
||||
.toBe(pinsHeader === true)
|
||||
// A nested-agent scenario ships one child fixture per recorded subagent
|
||||
// session (`session.1.jsonl` …), the replay source for that child session.
|
||||
for (const childFixture of childFixturePaths(dir, childSessions ?? 0)) {
|
||||
expect(existsSync(childFixture), childFixture).toBe(true)
|
||||
}
|
||||
await expect(sessionFixtures(dir), `${name}: session fixture inventory`).resolves.toBeDefined()
|
||||
}
|
||||
})
|
||||
|
||||
@@ -688,10 +725,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
|
||||
// storage rules fail loud.
|
||||
for (const scenario of scenarios) {
|
||||
const dir = join(snapshotsDir, scenario.name)
|
||||
const files = [
|
||||
'session.jsonl',
|
||||
...Array.from({ length: scenario.childSessions ?? 0 }, (_, i) => `session.${i + 1}.jsonl`),
|
||||
]
|
||||
const files = await sessionFixtures(dir)
|
||||
for (const file of files) {
|
||||
const fixture = await readFile(join(dir, file), 'utf8')
|
||||
expect(unknownToolCallIds(fixture), `${scenario.name}/${file} contains UNKNOWN_TOOL`)
|
||||
|
||||
@@ -6,6 +6,7 @@
|
||||
|
||||
import { mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs'
|
||||
import { readdirSync } from 'node:fs'
|
||||
import { spawn } from 'node:child_process'
|
||||
import { dirname, join } from 'node:path'
|
||||
import { randomUUID } from 'node:crypto'
|
||||
import { createInterface } from 'node:readline'
|
||||
@@ -40,6 +41,8 @@ interface Behavior {
|
||||
echoWorkspace?: boolean
|
||||
/** Write a line to stderr on boot (spec-side stderr-capture assertions). */
|
||||
stderrNote?: string
|
||||
/** Let a short-lived descendant retain stdio and emit one final ACP update plus stderr line after this parent exits. */
|
||||
lateInheritedOutput?: boolean
|
||||
/** Session logs to persist on stdin EOF. */
|
||||
logs?: ScriptedLog[]
|
||||
/** Leave a stray FILE directly under the sessions root (harvest must skip it). */
|
||||
@@ -247,6 +250,24 @@ function flushLogsAndExit(): void {
|
||||
writeFileSync(join(sessionsRoot, 'bucket-noise', 'notes.txt'), 'not a session log\n')
|
||||
}
|
||||
if (behavior.deleteSessionsRoot === true) rmSync(sessionsRoot, { recursive: true, force: true })
|
||||
if (behavior.lateInheritedOutput === true) {
|
||||
const frame = JSON.stringify({
|
||||
jsonrpc: '2.0',
|
||||
method: 'session/update',
|
||||
params: {
|
||||
sessionId,
|
||||
update: {
|
||||
sessionUpdate: 'agent_message_chunk',
|
||||
content: { type: 'text', text: 'late inherited stdout' },
|
||||
},
|
||||
},
|
||||
})
|
||||
const code = [
|
||||
`setTimeout(() => process.stdout.write(${JSON.stringify(`${frame}\n`)}), 50)`,
|
||||
`setTimeout(() => process.stderr.write(${JSON.stringify('late inherited stderr\n')}), 75)`,
|
||||
].join(';')
|
||||
spawn(process.execPath, ['-e', code], { stdio: ['ignore', 1, 2] }).unref()
|
||||
}
|
||||
process.exit(0)
|
||||
}
|
||||
|
||||
|
||||
@@ -1,13 +1,34 @@
|
||||
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { once } from 'node:events'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { delimiter, join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterAll, describe, expect, it } from 'vitest'
|
||||
import { afterAll, describe, expect, it, vi } from 'vitest'
|
||||
import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
|
||||
import { runScenario, type AgentUnderTest, type InputStep } from '../src/harness.ts'
|
||||
import { launchAcpTestAgent } from '../src/launcher.ts'
|
||||
|
||||
const fsControl = vi.hoisted(() => ({ cleanupFailure: undefined as Error | undefined }))
|
||||
|
||||
vi.mock('node:fs/promises', async (importOriginal) => {
|
||||
const actual = await importOriginal<typeof import('node:fs/promises')>()
|
||||
return {
|
||||
...actual,
|
||||
async rm(...args: Parameters<typeof actual.rm>): Promise<void> {
|
||||
if (String(args[0]).includes('acp-snap-cwd-') && fsControl.cleanupFailure !== undefined) {
|
||||
const failure = fsControl.cleanupFailure
|
||||
fsControl.cleanupFailure = undefined
|
||||
await actual.rm(...args)
|
||||
throw failure
|
||||
}
|
||||
await actual.rm(...args)
|
||||
},
|
||||
}
|
||||
})
|
||||
|
||||
/**
|
||||
* Unit tests for the subprocess harness, driven through the REAL spawn path
|
||||
* (tsx loader, temp cwd, env plumbing) against the scripted fake ACP bin in
|
||||
* (mode-aware launcher, temp cwd, env plumbing) against the scripted fake ACP bin in
|
||||
* ./fixtures/fake-acp-agent.ts. Each case writes a `behavior.json` next to a
|
||||
* throwaway fixture path; the fake bin echoes observable facts (env, seeded
|
||||
* workspace, permission outcomes) into `agent_message_chunk` text, so the
|
||||
@@ -40,6 +61,181 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s
|
||||
const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }]
|
||||
|
||||
describe('runScenario', () => {
|
||||
it('surfaces an asynchronous child spawn failure through startup and close', async () => {
|
||||
const { dir } = await scenario({})
|
||||
const launched = launchAcpTestAgent({ agent: AGENT, cwd: join(dir, 'missing') })
|
||||
let stdioClosed = false
|
||||
let clientClosed = false
|
||||
launched.child.once('close', () => { stdioClosed = true })
|
||||
void launched.client.closed.then(
|
||||
() => { clientClosed = true },
|
||||
() => { clientClosed = true },
|
||||
)
|
||||
await expect(launched.spawned).rejects.toMatchObject({ code: 'ENOENT' })
|
||||
await expect(launched.close()).rejects.toMatchObject({ code: 'ENOENT' })
|
||||
expect(stdioClosed).toBe(true)
|
||||
expect(clientClosed).toBe(true)
|
||||
})
|
||||
|
||||
it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => {
|
||||
const { dir, fixtureFile } = await scenario({ permissionProbe: true, echoEnv: true, stderrNote: 'launcher stderr' })
|
||||
const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-launcher-sessions-'))
|
||||
tempDirs.push(sessionsRoot)
|
||||
const launched = launchAcpTestAgent({
|
||||
agent: AGENT,
|
||||
cwd: dir,
|
||||
configPath: AGENT.configPath,
|
||||
env: {
|
||||
DSH_SNAPSHOT: 'replay',
|
||||
DSH_SNAPSHOT_FILE: fixtureFile,
|
||||
DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot,
|
||||
},
|
||||
})
|
||||
await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
|
||||
const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] })
|
||||
const nextChunk = launched.waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk')
|
||||
const predicateFailure = new Error('predicate failed')
|
||||
const failedPredicate = launched.waitForUpdate(() => { throw predicateFailure })
|
||||
.catch((error: unknown): unknown => error)
|
||||
await launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
|
||||
expect(await failedPredicate).toBe(predicateFailure)
|
||||
expect((await nextChunk).sessionUpdate).toBe('agent_message_chunk')
|
||||
expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true)
|
||||
expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}')
|
||||
expect(launched.stderr()).toContain('launcher stderr')
|
||||
const unmatched = expect(launched.waitForUpdate(() => false)).rejects.toThrow(/update stream closed/)
|
||||
await launched.close()
|
||||
await unmatched
|
||||
await expect(launched.waitForUpdate(() => true)).rejects.toThrow(/update stream closed/)
|
||||
await launched.close('SIGKILL')
|
||||
|
||||
// The minimal shape needs no environment or config override.
|
||||
const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir })
|
||||
await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
|
||||
const childFailure = new Error('child process failed')
|
||||
let exited = false
|
||||
minimal.child.once('exit', () => { exited = true })
|
||||
minimal.child.emit('error', childFailure)
|
||||
await expect(minimal.close('SIGTERM')).rejects.toBe(childFailure)
|
||||
// close rejects only after the fallback SIGKILL has produced an exit edge.
|
||||
expect(exited).toBe(true)
|
||||
})
|
||||
|
||||
it('waits for inherited stdio and buffered ACP parsing after the parent exits', { timeout: 20_000 }, async () => {
|
||||
const { dir, fixtureFile } = await scenario({ lateInheritedOutput: true })
|
||||
const launched = launchAcpTestAgent({
|
||||
agent: AGENT,
|
||||
cwd: dir,
|
||||
env: { DSH_SNAPSHOT_FILE: fixtureFile },
|
||||
})
|
||||
await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
|
||||
await launched.client.newSession({ cwd: dir, mcpServers: [] })
|
||||
const lateUpdate = launched.waitForUpdate(update =>
|
||||
update.sessionUpdate === 'agent_message_chunk'
|
||||
&& update.content.type === 'text'
|
||||
&& update.content.text === 'late inherited stdout')
|
||||
|
||||
await launched.close()
|
||||
|
||||
await expect(lateUpdate).resolves.toMatchObject({ sessionUpdate: 'agent_message_chunk' })
|
||||
expect(launched.rawStdout()).toContain('late inherited stdout')
|
||||
expect(launched.stderr()).toContain('late inherited stderr')
|
||||
})
|
||||
|
||||
it('rejects promptly when fallback termination is refused', async () => {
|
||||
const { dir } = await scenario({})
|
||||
const launched = launchAcpTestAgent({ agent: AGENT, cwd: dir })
|
||||
await launched.spawned
|
||||
|
||||
const childFailure = Object.assign(new Error('signal refused'), { code: 'EPERM' })
|
||||
const originalKill = launched.child.kill.bind(launched.child)
|
||||
const kill = vi.spyOn(launched.child, 'kill').mockReturnValue(false)
|
||||
const closed = new Promise<void>(resolve => launched.child.once('close', () => { resolve() }))
|
||||
try {
|
||||
launched.child.emit('error', childFailure)
|
||||
const rejection = await launched.close('SIGTERM').catch((error: unknown): unknown => error)
|
||||
expect(rejection).toBeInstanceOf(AggregateError)
|
||||
expect(rejection).toMatchObject({
|
||||
message: 'ACP test agent failed and fallback termination was refused',
|
||||
errors: [
|
||||
childFailure,
|
||||
expect.objectContaining({ message: 'Fallback SIGKILL was not accepted by the child process' }),
|
||||
],
|
||||
})
|
||||
expect(kill).toHaveBeenNthCalledWith(1, 'SIGTERM')
|
||||
expect(kill).toHaveBeenNthCalledWith(2, 'SIGKILL')
|
||||
} finally {
|
||||
kill.mockRestore()
|
||||
originalKill('SIGKILL')
|
||||
await closed
|
||||
}
|
||||
})
|
||||
|
||||
it('rejects promptly when fallback termination emits an error', async () => {
|
||||
const { dir } = await scenario({})
|
||||
const launched = launchAcpTestAgent({ agent: AGENT, cwd: dir })
|
||||
await launched.spawned
|
||||
|
||||
const childFailure = Object.assign(new Error('signal refused'), { code: 'EPERM' })
|
||||
const fallbackFailure = Object.assign(new Error('fallback signal refused'), { code: 'EPERM' })
|
||||
const originalKill = launched.child.kill.bind(launched.child)
|
||||
const kill = vi.spyOn(launched.child, 'kill').mockImplementation((signal) => {
|
||||
if (signal === 'SIGKILL') queueMicrotask(() => launched.child.emit('error', fallbackFailure))
|
||||
return signal === 'SIGKILL'
|
||||
})
|
||||
const closed = new Promise<void>(resolve => launched.child.once('close', () => { resolve() }))
|
||||
try {
|
||||
launched.child.emit('error', childFailure)
|
||||
const rejection = await launched.close('SIGTERM').catch((error: unknown): unknown => error)
|
||||
expect(rejection).toBeInstanceOf(AggregateError)
|
||||
expect(rejection).toMatchObject({
|
||||
message: 'ACP test agent failed and fallback termination was refused',
|
||||
errors: [childFailure, fallbackFailure],
|
||||
})
|
||||
expect(kill).toHaveBeenNthCalledWith(1, 'SIGTERM')
|
||||
expect(kill).toHaveBeenNthCalledWith(2, 'SIGKILL')
|
||||
} finally {
|
||||
kill.mockRestore()
|
||||
originalKill('SIGKILL')
|
||||
await closed
|
||||
}
|
||||
})
|
||||
|
||||
it('waits for in-flight client callbacks after the ACP stream closes', { timeout: 20_000 }, async () => {
|
||||
const { dir, fixtureFile } = await scenario({ permissionProbe: true })
|
||||
let releasePermission: (() => void) | undefined
|
||||
const permissionReleased = new Promise<void>((resolve) => { releasePermission = resolve })
|
||||
let markPermissionStarted: (() => void) | undefined
|
||||
const permissionStarted = new Promise<void>((resolve) => { markPermissionStarted = resolve })
|
||||
let permissionFinished = false
|
||||
const launched = launchAcpTestAgent({
|
||||
agent: AGENT,
|
||||
cwd: dir,
|
||||
env: { DSH_SNAPSHOT_FILE: fixtureFile },
|
||||
async requestPermission() {
|
||||
markPermissionStarted?.()
|
||||
await permissionReleased
|
||||
permissionFinished = true
|
||||
return { outcome: { outcome: 'cancelled' } }
|
||||
},
|
||||
})
|
||||
await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
|
||||
const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] })
|
||||
void launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => undefined)
|
||||
await permissionStarted
|
||||
|
||||
const childClosed = once(launched.child, 'close')
|
||||
let closeSettled = false
|
||||
const closing = launched.close('SIGKILL').then(() => { closeSettled = true })
|
||||
await childClosed
|
||||
await launched.client.closed
|
||||
expect(closeSettled).toBe(false)
|
||||
|
||||
releasePermission?.()
|
||||
await closing
|
||||
expect(permissionFinished).toBe(true)
|
||||
})
|
||||
|
||||
it('includes agent stderr when the ACP connection closes during startup', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({ failOnBoot: true, stderrNote: 'fake agent requested startup failure' })
|
||||
await expect(runScenario(
|
||||
@@ -48,6 +244,23 @@ describe('runScenario', () => {
|
||||
)).rejects.toThrow(/agent stderr:\nfake agent requested startup failure/)
|
||||
})
|
||||
|
||||
it('preserves launch-resolution errors when no child process exists', async () => {
|
||||
const { dir, fixtureFile } = await scenario({})
|
||||
vi.stubEnv('DSH_EXAMPLE_MODE', 'lib')
|
||||
try {
|
||||
await expect(runScenario(
|
||||
{ steps: [] },
|
||||
{
|
||||
agent: { ...AGENT, binScript: join(dir, 'outside-src.ts'), libBinScript: undefined },
|
||||
mode: 'replay',
|
||||
fixtureFile,
|
||||
},
|
||||
)).rejects.toThrow(/expected a "\/src\/" segment/)
|
||||
} finally {
|
||||
vi.unstubAllEnvs()
|
||||
}
|
||||
})
|
||||
|
||||
it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({
|
||||
permissionProbe: true,
|
||||
@@ -138,6 +351,39 @@ describe('runScenario', () => {
|
||||
)).rejects.toThrow(/expected the prompt to fail/)
|
||||
})
|
||||
|
||||
it('reports scenario and cleanup failures together', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({ prompt: 'respond' })
|
||||
const cleanupFailure = new Error('cleanup failed')
|
||||
fsControl.cleanupFailure = cleanupFailure
|
||||
|
||||
const failure = await runScenario(
|
||||
{ steps: [...boot, { op: 'promptExpectError', text: 'fine' }] },
|
||||
{ agent: AGENT, mode: 'replay', fixtureFile },
|
||||
).catch((error: unknown): unknown => error)
|
||||
|
||||
expect(failure).toBeInstanceOf(AggregateError)
|
||||
const failures = (failure as AggregateError).errors as unknown[]
|
||||
expect(failures).toHaveLength(2)
|
||||
expect(failures[0]).toBeInstanceOf(Error)
|
||||
expect((failures[0] as Error).message).toMatch(/expected the prompt to fail/)
|
||||
expect(failures[1]).toBe(cleanupFailure)
|
||||
})
|
||||
|
||||
it('reports cleanup failure after an otherwise successful scenario', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({})
|
||||
const cleanupFailure = new Error('cleanup failed')
|
||||
fsControl.cleanupFailure = cleanupFailure
|
||||
|
||||
const failure = await runScenario(
|
||||
{ steps: boot },
|
||||
{ agent: AGENT, mode: 'replay', fixtureFile },
|
||||
).catch((error: unknown): unknown => error)
|
||||
|
||||
expect(failure).toBeInstanceOf(AggregateError)
|
||||
expect((failure as AggregateError).message).toBe('snapshot cleanup failed')
|
||||
expect((failure as AggregateError).errors as unknown[]).toEqual([cleanupFailure])
|
||||
})
|
||||
|
||||
it('newSessionExpectError swallows the rejection, with and without extra dirs', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({ rejectExtraDirs: true })
|
||||
const result = await runScenario(
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { cpSync, mkdtempSync, readFileSync, writeFileSync } from 'node:fs'
|
||||
import { cpSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'node:fs'
|
||||
import { rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
@@ -6,7 +6,6 @@ import { fileURLToPath } from 'node:url'
|
||||
import { afterAll, describe, expect, it } from 'vitest'
|
||||
import { defineAcpSnapshotSuite, type HarvestedLog, type Scenario } from '../src/index.ts'
|
||||
import {
|
||||
childFixturePaths,
|
||||
fixtureContext,
|
||||
formatSystemPromptSnapshot,
|
||||
headerChangeCount,
|
||||
@@ -16,6 +15,7 @@ import {
|
||||
normalizedToolSchemas,
|
||||
parseToolSchemasSnapshot,
|
||||
refreshFixtureReplacements,
|
||||
sessionFixtureNames,
|
||||
restorePinnedToolSchemas,
|
||||
stabilizeRefreshLog,
|
||||
unknownToolCallIds,
|
||||
@@ -46,7 +46,7 @@ const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta.
|
||||
// Replay pins explicit header classes; recording covers the default fallback.
|
||||
const REPLAY_SCENARIOS: Scenario[] = [
|
||||
{ name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'main' },
|
||||
{ name: 'plain-turn', hasModelTurn: true, recorded: true, childSessions: 1, headerClass: 'main', configPath: AGENT.configPath },
|
||||
{ name: 'plain-turn', hasModelTurn: true, recorded: true, headerClass: 'main', configPath: AGENT.configPath },
|
||||
{ name: 'no-model', hasModelTurn: false, recorded: false, headerClass: 'main' },
|
||||
{ name: 'blocked-log', hasModelTurn: false, comparesLog: true, recorded: false, headerClass: 'main' },
|
||||
{ name: 'authored-error', hasModelTurn: true, recorded: false, overridden: true, headerClass: 'main' },
|
||||
@@ -54,7 +54,7 @@ const REPLAY_SCENARIOS: Scenario[] = [
|
||||
|
||||
const RECORD_SCENARIOS: Scenario[] = [
|
||||
{ name: 'rec-pin', hasModelTurn: true, recorded: true, pinsHeader: true },
|
||||
{ name: 'rec-child', hasModelTurn: true, recorded: true, childSessions: 1 },
|
||||
{ name: 'rec-child', hasModelTurn: true, recorded: true },
|
||||
// recorded:false in record mode → registered but skipped (never re-recorded).
|
||||
{ name: 'rec-skip', hasModelTurn: true, recorded: false, overridden: true },
|
||||
]
|
||||
@@ -64,7 +64,13 @@ const RECORD_SCENARIOS: Scenario[] = [
|
||||
// committed record fixtures/goldens in place.
|
||||
const BOOTSTRAP = process.env.ACP_SNAPSHOT_SPEC_BOOTSTRAP === '1'
|
||||
const recordDir = BOOTSTRAP ? RECORD_SRC : mkdtempSync(join(tmpdir(), 'acp-snap-record-suite-'))
|
||||
if (!BOOTSTRAP) cpSync(RECORD_SRC, recordDir, { recursive: true })
|
||||
if (!BOOTSTRAP) {
|
||||
cpSync(RECORD_SRC, recordDir, { recursive: true })
|
||||
// Record mode owns its output inventory: a new scenario has no primary yet,
|
||||
// while a changed child count can leave old numbered fixtures behind.
|
||||
rmSync(join(recordDir, 'rec-pin', 'session.jsonl'))
|
||||
writeFileSync(join(recordDir, 'rec-child', 'session.2.jsonl'), 'stale child\n')
|
||||
}
|
||||
const refreshDir = mkdtempSync(join(tmpdir(), 'acp-snap-refresh-suite-'))
|
||||
cpSync(REPLAY_DIR, refreshDir, { recursive: true })
|
||||
staleRefreshFixtures(refreshDir)
|
||||
@@ -140,6 +146,13 @@ describe('defineAcpSnapshotSuite: refresh write-back', () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe('defineAcpSnapshotSuite: record inventory write-back', () => {
|
||||
it('creates a missing primary fixture and prunes stale child fixtures', () => {
|
||||
expect(readFileSync(join(recordDir, 'rec-pin', 'session.jsonl'), 'utf8')).toContain('"type":"session"')
|
||||
expect(() => readFileSync(join(recordDir, 'rec-child', 'session.2.jsonl'), 'utf8')).toThrow()
|
||||
})
|
||||
})
|
||||
|
||||
describe('defineAcpSnapshotSuite: registration contract', () => {
|
||||
it("throws when a scenario's header class has no pinning scenario", () => {
|
||||
expect(() => {
|
||||
@@ -179,13 +192,41 @@ describe('defineAcpSnapshotSuite: registration contract', () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe('childFixturePaths', () => {
|
||||
it('yields one sibling path per child, 1-based', () => {
|
||||
expect(childFixturePaths('/snap/s', 2)).toEqual(['/snap/s/session.1.jsonl', '/snap/s/session.2.jsonl'])
|
||||
describe('sessionFixtureNames', () => {
|
||||
it('orders the primary and contiguous child fixtures while ignoring other files', () => {
|
||||
expect(sessionFixtureNames([
|
||||
'stdout.golden.jsonl',
|
||||
'session.2.jsonl',
|
||||
'session.jsonl',
|
||||
'session.1.jsonl',
|
||||
'input.json',
|
||||
])).toEqual(['session.jsonl', 'session.1.jsonl', 'session.2.jsonl'])
|
||||
})
|
||||
|
||||
it('yields nothing for a single-session scenario', () => {
|
||||
expect(childFixturePaths('/snap/s', 0)).toEqual([])
|
||||
it('accepts a primary-only scenario', () => {
|
||||
expect(sessionFixtureNames(['session.jsonl'])).toEqual(['session.jsonl'])
|
||||
})
|
||||
|
||||
it('rejects a directory without the primary fixture', () => {
|
||||
expect(() => sessionFixtureNames(['session.1.jsonl'])).toThrow('missing session.jsonl')
|
||||
})
|
||||
|
||||
it('rejects gapped child fixtures', () => {
|
||||
expect(() => sessionFixtureNames(['session.jsonl', 'session.2.jsonl']))
|
||||
.toThrow('expected session.1.jsonl, found session.2.jsonl')
|
||||
})
|
||||
|
||||
it.each(['session.0.jsonl', 'session.child.jsonl', 'session.01.jsonl'])(
|
||||
'rejects invalid child fixture name %s',
|
||||
(name) => {
|
||||
expect(() => sessionFixtureNames(['session.jsonl', name]))
|
||||
.toThrow(`invalid child session fixture name: ${name}`)
|
||||
},
|
||||
)
|
||||
|
||||
it('rejects duplicate child indexes', () => {
|
||||
expect(() => sessionFixtureNames(['session.jsonl', 'session.1.jsonl', 'session.1.jsonl']))
|
||||
.toThrow('expected session.2.jsonl, found session.1.jsonl')
|
||||
})
|
||||
})
|
||||
|
||||
|
||||
@@ -11,6 +11,8 @@ Each tool is registered independently; a product that wants only one disables th
|
||||
| `web_search` | `query` (string) | Discovery. Returns an optional answer plus source URLs. `max_results` is **not** model-facing — the tool sets the bound (the `searchMaxResults` config, default 8) and passes it to the seam. |
|
||||
| `web_fetch` | `url` (string) | Retrieves a specific URL. HTML bodies are rendered to markdown-ish text; text bodies pass through. A non-2xx status is reported, not an error. The tool-call timeout is deployment policy (`dsh-timeout-policy`), not a model argument. |
|
||||
|
||||
Both tools opt into concurrent scheduling because provider reads return content without mutating parent-agent state.
|
||||
|
||||
## Config
|
||||
|
||||
| Key | Default | Meaning |
|
||||
|
||||
@@ -92,6 +92,8 @@ export function applyWebFetchTool(ctx: Context, timeoutMs: number): void {
|
||||
url: { type: 'string', required: true, description: 'The HTTP(S) URL to fetch.' },
|
||||
},
|
||||
timeoutMs,
|
||||
// Provider reads do not mutate parent-agent state.
|
||||
isConcurrencySafe: () => true,
|
||||
async execute(args, exec): Promise<ContentBlock[]> {
|
||||
const input = parseFetchArgs(args)
|
||||
const result = await ctx.web.fetch(
|
||||
|
||||
@@ -109,6 +109,8 @@ export function applyWebSearchTool(ctx: Context, maxResults: number, timeoutMs:
|
||||
query: { type: 'string', required: true, description: 'The search query.' },
|
||||
},
|
||||
timeoutMs,
|
||||
// Provider reads do not mutate parent-agent state.
|
||||
isConcurrencySafe: () => true,
|
||||
async execute(args, exec): Promise<ContentBlock[]> {
|
||||
const input = parseSearchArgs(args)
|
||||
const result = await ctx.web.search(
|
||||
|
||||
@@ -166,6 +166,10 @@ describe('tool-web registration', () => {
|
||||
const names = ctx.tools.schemas().map(s => s.name)
|
||||
expect(names).toContain('web_search')
|
||||
expect(names).toContain('web_fetch')
|
||||
expect(ctx.tools.executionMode({ callId: CallId('search-safe'), name: 'web_search', arguments: { query: 'q' } }))
|
||||
.toEqual({ kind: 'parallel' })
|
||||
expect(ctx.tools.executionMode({ callId: CallId('fetch-safe'), name: 'web_fetch', arguments: { url: 'https://a.test' } }))
|
||||
.toEqual({ kind: 'parallel' })
|
||||
await fiber.dispose()
|
||||
expect(ctx.tools.schemas().map(s => s.name)).not.toContain('web_search')
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user