Merge remote-tracking branch 'origin/master' into codex/pr224-rfc-rewrite

# Conflicts:
#	docs/architecture.md
#	docs/capability-seams.md
#	docs/config-catalog.md
#	docs/cookbook/extension-cookbook.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	docs/rfc/implemented/feature/2026-06-30-interception-seams.md
#	docs/rfc/proposed/feature/2026-06-14-acp-agent-client-protocol.md
#	docs/tool-execution-pipeline.md
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-core/README.md
#	packages/core/agent-loop/README.md
#	packages/core/tools/README.md
#	packages/core/tools/src/index.ts
#	packages/core/tools/tests/tools.spec.ts
#	packages/core/tools/tsconfig.json
#	packages/ui/acp/src/index.ts
#	scripts/doc-budgets.manifest.json
#	scripts/gen-cordis-catalog.ts
#	scripts/gen-doc-graphs.ts
This commit is contained in:
Tianyi Cui
2026-07-11 23:14:09 +08:00
185 changed files with 11901 additions and 414 deletions

View File

@@ -39,4 +39,4 @@ A scenario booting a differently-composed tree sets its own `configPath` (an ove
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 plus comparable session-log goldens 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).
Constraints: `suite.ts` imports vitest, so the package is importable only inside a vitest run (the harness and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the harness 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).
Constraints: `suite.ts` imports vitest, so the package is importable only inside a vitest run (the harness and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the harness 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).

View File

@@ -85,6 +85,8 @@ export type InputStep =
| { op: 'promptExpectError'; text: string }
| { op: 'promptAndCancel'; text: string }
| { op: 'cancel' }
| { op: 'setConfigOption'; configId: string; value: string }
| { op: 'setConfigOptionExpectError'; configId: string; value: string }
/** A scenario's `input.json`: an ordered list of input steps. */
export interface InputScript {
@@ -210,6 +212,8 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise
DSH_SNAPSHOT: opts.mode,
DSH_SNAPSHOT_FILE: opts.fixtureFile,
DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot,
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) }
@@ -406,6 +410,24 @@ async function runStep(
await client.cancel({ sessionId })
return
}
case 'setConfigOption': {
const sessionId = getSessionId()
if (sessionId === undefined) throw new Error('snapshot-harness: setConfigOption before newSession')
await client.setSessionConfigOption({ sessionId, configId: step.configId, value: step.value })
return
}
case 'setConfigOptionExpectError': {
const sessionId = getSessionId()
if (sessionId === undefined) throw new Error('snapshot-harness: setConfigOptionExpectError before newSession')
// The bridge rejects an unknown id / out-of-vocabulary value; 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.setSessionConfigOption({ sessionId, configId: step.configId, value: step.value }).then(
() => { throw new Error('snapshot-harness: expected set_config_option to be rejected but it succeeded') },
() => { /* expected: the bridge rejected the id or value */ },
)
return
}
default:
throw new Error(`snapshot-harness: unknown input op ${JSON.stringify(step)}`)
}

View File

@@ -98,6 +98,15 @@ export interface Scenario {
* Defaults to false.
*/
pinsHeader?: boolean
/**
* How many `request/header-delta` events this PINNING scenario's fixture
* legitimately carries (default 0). A recorded mid-run header change — a
* config-option switch rewriting a prompt section — is part of the pinned
* surface, committed verbatim like the header itself; any OTHER count
* still fails, so fixture rot stays caught. Meaningless off the pin (the
* live uniformity guard keeps non-pinning scenarios delta-free).
*/
expectedHeaderDeltas?: number
/**
* Which header-composition class this scenario belongs to. Scenarios that
* boot the same config compose the same header; each class has exactly one
@@ -511,17 +520,19 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
}
})
it('every pinning fixture carries exactly one request/header and no deltas', async () => {
it('every pinning fixture carries exactly one request/header and its declared deltas', async () => {
// The live uniformity guard runs only in NON-pinning scenarios, so a
// class made of just its pinning scenario would otherwise accept a
// re-recorded pin with several headers or a mid-run header-delta —
// shapes the pin design cannot represent. Assert the committed pins
// directly.
// re-recorded pin with several headers or an undeclared mid-run
// header-delta — shapes the pin design cannot represent. Assert the
// committed pins directly; a scenario whose arc legitimately rewrites
// a prompt section declares the exact count via expectedHeaderDeltas.
for (const scenario of pinningByClass.values()) {
const fixture = await readFile(join(snapshotsDir, scenario.name, 'session.jsonl'), 'utf8')
const headers = normalizedHeaders(fixture, fixtureContext(fixture))
expect(headers.length, `${scenario.name}: a pinning fixture must carry exactly one request/header`).toBe(1)
expect(headerDeltaCount(fixture), `${scenario.name}: a pinning fixture must carry no request/header-delta`).toBe(0)
expect(headerDeltaCount(fixture), `${scenario.name}: a pinning fixture must carry exactly its declared request/header-deltas`)
.toBe(scenario.expectedHeaderDeltas ?? 0)
}
})

View File

@@ -58,6 +58,13 @@ interface Behavior {
strayBucketFile?: boolean
/** Delete the sessions root entirely (harvest must yield no logs). */
deleteSessionsRoot?: boolean
/**
* Vocabulary for `session/set_config_option`: allowed values per config id.
* A set naming an unknown id or an out-of-vocabulary value rejects (the
* real bridge's rule); a valid set answers with the complete refreshed
* option state, `currentValue` updated. Absent: every set rejects.
*/
configOptions?: Record<string, string[]>
}
const sessionsRoot = process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? ''
@@ -81,6 +88,8 @@ let sessionCwd = ''
let parkedPromptId: number | string | null = null
/** Resolvers for permission-probe responses, keyed by outbound request id. */
const pendingPermission = new Map<number, (outcome: unknown) => void>()
/** Per-run `session/set_config_option` state: config id → current value (first vocabulary entry until set). */
const currentConfig: Record<string, string> = {}
function send(frame: Record<string, unknown>): void {
process.stdout.write(`${JSON.stringify({ jsonrpc: '2.0', ...frame })}\n`)
@@ -195,6 +204,32 @@ function handleFrame(frame: Record<string, unknown>): void {
case 'session/prompt':
void handlePrompt(id as number | string)
return
case 'session/set_config_option': {
const vocabulary = behavior.configOptions
const configId = params.configId as string
const value = params.value as string
const values = vocabulary?.[configId]
if (values === undefined) {
respondError(id as number | string, `unknown config option ${configId}`)
return
}
if (!values.includes(value)) {
respondError(id as number | string, `unknown ${configId} value ${value}`)
return
}
currentConfig[configId] = value
// The real bridge's contract: every set answers with the COMPLETE
// refreshed option state, not just the changed entry.
respond(id as number | string, {
configOptions: Object.entries(vocabulary as Record<string, string[]>).map(([cid, vs]) => ({
id: cid,
type: 'select',
currentValue: currentConfig[cid] ?? vs[0],
options: vs.map(v => ({ value: v, name: v })),
})),
})
return
}
case 'session/cancel':
if (parkedPromptId !== null) {
const parked = parkedPromptId

View File

@@ -168,6 +168,8 @@ describe('runScenario', () => {
[{ op: 'promptExpectError', text: 'x' }, /promptExpectError before newSession/],
[{ op: 'promptAndCancel', text: 'x' }, /promptAndCancel before newSession/],
[{ op: 'cancel' }, /cancel before newSession/],
[{ op: 'setConfigOption', configId: 'sandbox-mode', value: 'read-only' }, /setConfigOption before newSession/],
[{ op: 'setConfigOptionExpectError', configId: 'sandbox-mode', value: 'yolo' }, /setConfigOptionExpectError before newSession/],
] as [InputStep, RegExp][])('rejects %j before newSession', { timeout: 20_000 }, async (step, message) => {
const { fixtureFile } = await scenario({})
await expect(runScenario(
@@ -176,6 +178,53 @@ describe('runScenario', () => {
)).rejects.toThrow(message)
})
it('setConfigOption switches a value and receives the complete refreshed option state', { timeout: 20_000 }, async () => {
const { fixtureFile } = await scenario({
configOptions: { 'sandbox-mode': ['read-only', 'workspace-write'], 'approval-policy': ['ask', 'never'] },
})
const result = await runScenario(
{
steps: [...boot,
{ op: 'setConfigOption', configId: 'sandbox-mode', value: 'workspace-write' },
{ op: 'setConfigOption', configId: 'approval-policy', value: 'never' }],
},
{ agent: AGENT, mode: 'replay', fixtureFile },
)
// Every set answers with the FULL state: the second response carries the
// first switch's value too — the complete-refreshed-state contract.
const frames = result.rawStdout.trim().split('\n').map(line => JSON.parse(line) as { result?: { configOptions?: { id: string; currentValue: string }[] } })
const states = frames
.map(f => f.result?.configOptions)
.filter(options => options !== undefined)
.map(options => Object.fromEntries((options as { id: string; currentValue: string }[]).map(o => [o.id, o.currentValue])))
expect(states).toEqual([
{ 'sandbox-mode': 'workspace-write', 'approval-policy': 'ask' },
{ 'sandbox-mode': 'workspace-write', 'approval-policy': 'never' },
])
})
it('setConfigOptionExpectError swallows the rejection for unknown ids and out-of-vocabulary values', { timeout: 20_000 }, async () => {
const { fixtureFile } = await scenario({ configOptions: { 'sandbox-mode': ['read-only'] } })
const result = await runScenario(
{
steps: [...boot,
{ op: 'setConfigOptionExpectError', configId: 'sandbox-mode', value: 'yolo' },
{ op: 'setConfigOptionExpectError', configId: 'reasoning-effort', value: 'max' }],
},
{ agent: AGENT, mode: 'replay', fixtureFile },
)
expect(result.rawStdout).toContain('unknown sandbox-mode value yolo')
expect(result.rawStdout).toContain('unknown config option reasoning-effort')
})
it('setConfigOptionExpectError throws when the set unexpectedly succeeds', { timeout: 20_000 }, async () => {
const { fixtureFile } = await scenario({ configOptions: { 'sandbox-mode': ['read-only'] } })
await expect(runScenario(
{ steps: [...boot, { op: 'setConfigOptionExpectError', configId: 'sandbox-mode', value: 'read-only' }] },
{ agent: AGENT, mode: 'replay', fixtureFile },
)).rejects.toThrow(/expected set_config_option to be rejected/)
})
it('rejects an unknown input op', { timeout: 20_000 }, async () => {
const { fixtureFile } = await scenario({})
const bogus = { op: 'reticulate' } as unknown as InputStep

View File

@@ -82,6 +82,11 @@ interface SessionTrace {
surface: number[]
}
/** Event payload prefix for scoped seams whose first argument names its agent. */
interface AgentSubject {
agent: Agent
}
/**
* Deep-freeze a value and everything reachable from it.
*
@@ -392,6 +397,7 @@ export function apply(ctx: Context, config: Config = {}): void {
'agent/turn-continuation': args => args[0],
'agent/turn-stop': args => args[0],
'agent/error': args => args[0],
'approval/request': args => (args[0] as AgentSubject).agent,
'tools/pre-execute': args => (args[0] as ToolExecution).agent,
'tools/execute': args => (args[0] as ToolExecution).agent,
'tools/post-execute': args => (args[0] as ToolExecution).agent,

View File

@@ -833,6 +833,7 @@ describe('scoped-dispatch invariants', () => {
['agent/turn-continuation', [agent, 1, { action: 'stop' }, () => Promise.resolve({ action: 'stop' })]],
['agent/turn-stop', [agent, 1]],
['agent/error', [agent, 1, 0, new Error('x')]],
['approval/request', [{ agent, toolName: 'echo' }, () => Promise.resolve('unavailable')]],
['tools/pre-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ kind: 'allow' })]],
['tools/execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ callId: 'c', content: [], isError: false })]],
['tools/post-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, { callId: 'c', content: [], isError: false }, () => Promise.resolve({ kind: 'accept' })]],