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

Merge remote-tracking branch 'origin/master' into codex/pr335-merge-master-20260719

Browse Source 
# Conflicts:
#	packages/support/acp-snapshot/README.md
#	packages/support/acp-snapshot/src/harness.ts
#	packages/support/acp-snapshot/src/suite.ts
#	packages/support/acp-snapshot/tests/harness.spec.ts
#	packages/support/acp-snapshot/tests/suite.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-19 11:41:10 +08:00
parent 64f64724e5 383a305bd4
commit 39c1c3df4f
330 changed files with 7947 additions and 4450 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
packages/subagent/subagent-acp/tests/mock-acp-server.ts
View File

@@ -1,9 +1,45 @@
/**
* Minimal no-network ACP child process for keyless backend tests. Environment variables script its
* text and stop reason, a cancel-cooperative or cancel-ignoring hang, permission requests, and a
* readiness marker. Disposal fixtures can delay an EOF flush, ignore EOF but exit and mark
* SIGTERM, or trap SIGTERM to require SIGKILL. The specs run this protocol-only fixture directly
* with Node's type stripping; it imports no harness code or workspace paths.
* A minimal mock ACP AGENT, run as a subprocess, for the keyless
* `dsh-subagent-acp` tests. It speaks the agent side of ACP over stdio and is
* fully scripted by environment variables — no model, no network:
*
* - `MOCK_TEXT` — the assistant text it streams as one `agent_message_chunk`.
* - `MOCK_STOP` — the ACP `StopReason` it returns from `prompt`
* (`end_turn` default, or `max_tokens`/`refusal`/…).
* - `MOCK_HANG` — if `1`, `prompt` never resolves on its own (it waits for
* a `session/cancel`), to exercise the client's cancel path.
* - `MOCK_IGNORE_CANCEL` — if `1` (with MOCK_HANG), the agent receives
* `session/cancel` but NEVER resolves the pending prompt
* and never exits — a non-cooperative child. The backend's
* `result` must still settle `aborted` on its own and
* `dispose()` must still kill the process.
* - `MOCK_PERMISSION` — if `1`, the agent calls `session/request_permission`
* before answering, to exercise the client's auto-answer.
* - `MOCK_READY_FILE` — if set, the path the agent touches once its `prompt`
* handler is in flight (it has streamed its chunk). A test
* polls for this file to cancel on a CONDITION rather than
* an arbitrary timeout (subprocess cold-start is variable).
* - `MOCK_MISSING_SESSION_ID` — if `1`, return a malformed empty `session/new`
* response to exercise startup rollback.
* - `MOCK_FLUSH_ON_EOF` — if set, on stdin EOF the agent takes an async beat
* (MOCK_FLUSH_DELAY_MS, default 150) simulating the real
* acp-agent's EOF-driven quiesce+flush, then touches this
* path and exits ON ITS OWN — no signal. Stands in for a
* child whose durable flush completes only if dispose
* gives EOF a real window before escalating to SIGTERM.
* - `MOCK_IGNORE_EOF` — if `1`, keep the event loop alive past stdin EOF (a bare
* timer) but install a SIGTERM handler that exits (and, if
* MOCK_SIGTERM_FILE is set, touches it as an observable
* proof the SIGTERM rung fired). The child ignores the
* graceful EOF window yet dies cooperatively on SIGTERM —
* exercising dispose's middle tier (exit during the SIGTERM
* grace, before the SIGKILL escalation). Touches
* MOCK_READY_FILE once armed.
*
* It is not a test spec: the specs launch this protocol-only fixture through
* the mode-aware example resolver (tsx in source mode, Node type stripping in
* built mode). It imports no harness code or workspace paths.
*
* @module @deepseek-ai/dsh-subagent-acp/tests/mock-acp-server
*/
@@ -64,7 +100,8 @@ function makeAgent(conn: AgentSideConnection): Agent {
writeFileSync(NEWSESSION_GATE.ready, 'at-newSession')
while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10))
}
return { sessionId: randomUUID() }
if (process.env.MOCK_MISSING_SESSION_ID === '1') return {} as NewSessionResponse
return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() }
},
authenticate(_params: AuthenticateRequest): Promise<void> {
// No auth methods advertised; nothing to do.
@@ -124,8 +161,11 @@ function makeAgent(conn: AgentSideConnection): Agent {
process.exit(1)
}
if (IGNORE_CANCEL) {
// A non-cooperative child receives cancellation but neither resolves nor exits. The
// backend must still settle `aborted`, and disposal must kill the process.
// A NON-COOPERATIVE child: receive session/cancel but never resolve the
// pending prompt and never exit. The backend's `result` must still settle
// `aborted` on its own (the cancel-settle race), and `dispose()` must
// still kill the process — proving cancellation does not depend on the
// child cooperating.
return Promise.resolve()
}
resolveCancel?.('cancelled')
@@ -142,9 +182,12 @@ new AgentSideConnection(
),
)
// Under MOCK_TRAP_SIGTERM, ignore SIGTERM and keep stdin open so the process neither quiesces
// on EOF nor dies on the graceful signal — exercising the backend dispose path's SIGKILL
// escalation. READY_FILE proves the trap was armed before the test disposes the run.
// Under MOCK_TRAP_SIGTERM, ignore SIGTERM and keep stdin open so the process
// neither quiesces on EOF nor dies on the graceful signal — exercising the
// backend dispose path's SIGKILL escalation. Without this the process exits
// normally on SIGTERM / stdin end. Touch READY_FILE once the trap is armed, so
// a test waits for that CONDITION before disposing (the trap must be in place,
// not merely the process spawned — otherwise SIGTERM hits the default handler).
if (process.env.MOCK_TRAP_SIGTERM === '1') {
process.on('SIGTERM', () => { /* trapped: refuse to exit on the graceful signal */ })
// Keep the event loop alive (a bare timer) so nothing else lets it exit.
@@ -152,10 +195,13 @@ if (process.env.MOCK_TRAP_SIGTERM === '1') {
if (READY_FILE !== undefined) writeFileSync(READY_FILE, 'trap-armed')
}
// Under MOCK_FLUSH_ON_EOF, model the real acp-agent's EOF-driven quiesce: on stdin 'end' (the
// dispose path's `child.stdin.end()`), take an ASYNC beat to "flush", then touch the marker and
// exit on its own. A signal sent before MOCK_FLUSH_DELAY_MS would suppress the marker, so it proves
// the EOF grace window was long enough for durable flush.
// Under MOCK_FLUSH_ON_EOF, model the real acp-agent's EOF-driven quiesce: on
// stdin 'end' (the dispose path's `child.stdin.end()`), take an ASYNC beat to
// "flush", then touch the marker and exit ON OUR OWN — no signal involved. The
// beat is MOCK_FLUSH_DELAY_MS (default 150). A dispose that sends SIGTERM before
// the beat completes (no graceful window, or an EOF grace shorter than the
// flush) default-terminates this process and the marker is missing; a dispose
// that gives the EOF quiesce enough window first lets the flush land.
if (FLUSH_ON_EOF !== undefined) {
const flushDelayMs = Number(process.env.MOCK_FLUSH_DELAY_MS ?? '150')
process.stdin.on('end', () => {
@@ -166,9 +212,14 @@ if (FLUSH_ON_EOF !== undefined) {
})
}
// Ignore EOF but exit on SIGTERM to exercise the middle disposal tier before SIGKILL. The signal
// marker distinguishes that catchable rung from an immediate, uncatchable SIGKILL; READY_FILE
// proves the handler was armed before disposal.
// Under MOCK_IGNORE_EOF, keep the loop alive past stdin EOF (so the graceful EOF
// window times out) but INSTALL A SIGTERM HANDLER that records it and exits — the
// child ignores the graceful EOF window yet dies cooperatively on SIGTERM,
// exercising dispose's MIDDLE tier (exit during the SIGTERM grace, before the
// SIGKILL escalation). When MOCK_SIGTERM_FILE is set the handler touches it, an
// OBSERVABLE proof that the SIGTERM rung fired: if dispose skipped the middle
// rung and jumped EOF→SIGKILL, SIGKILL is uncatchable so the handler never runs
// and the marker is missing. Touch READY_FILE once armed (a test waits on it).
if (process.env.MOCK_IGNORE_EOF === '1') {
const sigtermFile = process.env.MOCK_SIGTERM_FILE
process.on('SIGTERM', () => {

41
packages/subagent/subagent-acp/tests/subagent-acp.spec.ts
View File

@@ -6,7 +6,7 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import SubagentService from '@deepseek-ai/dsh-subagent'
import { buildChildEnv, SENSITIVE_ENV_PATTERN } from '@deepseek-ai/dsh-subagent-subprocess'
import { buildChildEnv } from '@deepseek-ai/dsh-subagent-subprocess'
import type { Agent } from '@deepseek-ai/dsh-agent'
import * as acp from '../src/index.ts'
import { acpStopReason, acpContentText, DEFAULT_DISPOSE_EOF_GRACE_MS, DEFAULT_DISPOSE_GRACE_MS, startAcpRun, toAcpPrompt, type AcpRunSpec } from '../src/run.ts'
@@ -58,7 +58,7 @@ function text(blocks: { type: string; text?: string }[]): string {
/**
* Poll until `file` exists (the mock touches it once its prompt is in flight),
* so a cancel test waits on a CONDITION rather than an arbitrary timeout — the
* subprocess cold-start under tsx is variable, and a fixed sleep both flakes and
* subprocess cold-start is variable, and a fixed sleep both flakes and
* slows the suite. Fails loud if the child never signals readiness.
*/
async function waitForFile(file: string, timeoutMs = 5000): Promise<void> {
@@ -108,7 +108,6 @@ describe('buildChildEnv', () => {
// The explicitly-supplied key survives (an opt-in for the child's creds).
expect(env.DEEPSEEK_API_KEY).toBe('explicit')
// A normal ambient var is forwarded.
expect(SENSITIVE_ENV_PATTERN.test('PATH')).toBe(false)
expect(env.PATH).toBe(process.env.PATH)
} finally {
delete process.env.DSH_ACP_TEST_SECRET_TOKEN
@@ -117,15 +116,22 @@ describe('buildChildEnv', () => {
})
describe('dsh-subagent-acp', () => {
it('drives a child process to completion and returns its streamed output', async () => {
const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn' })
it('drives child processes with parent-unique run ids and returns streamed output', async () => {
const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' })
const run = await ctx.subagents.start('acp', request('do X'))
expect(run.id).not.toBe('acp-child-session')
const result = await run.result
expect(result.stopReason).toBe('completed')
expect(text(result.output)).toBe('hello from acp child')
const disposal = run.dispose()
expect(run.dispose()).toBe(disposal)
await disposal
const nextRun = await ctx.subagents.start('acp', request('do X again'))
expect(nextRun.id).not.toBe(run.id)
expect(nextRun.id).not.toBe('acp-child-session')
await nextRun.result
await nextRun.dispose()
})
it('maps a max_tokens stop reason', async () => {
@@ -184,6 +190,31 @@ describe('dsh-subagent-acp', () => {
}
})
it('reaps a child whose session/new response omits the session id', async () => {
const tmp = mkdtempSync(join(tmpdir(), 'acp-malformed-session-'))
const flushed = join(tmp, 'flushed')
try {
await expect(startAcpRun(request(), {
command: process.execPath,
args: [mockServer],
cwd: process.cwd(),
permission: 'reject',
env: {
MOCK_MISSING_SESSION_ID: '1',
MOCK_FLUSH_ON_EOF: flushed,
MOCK_FLUSH_DELAY_MS: '20',
},
disposeEofGraceMs: 1000,
disposeGraceMs: 100,
})).rejects.toThrow('ACP child published without a session id')
// Startup rejects only after its private child reaches quiescence. The
// marker proves rollback closed stdin and allowed the child's EOF flush.
expect(existsSync(flushed)).toBe(true)
} finally {
rmSync(tmp, { recursive: true, force: true })
}
})
it('dispose escalates SIGTERM → SIGKILL for a child that traps SIGTERM (bounded quiescence)', async () => {
// The child traps SIGTERM and keeps its event loop alive, so a graceful
// term alone would hang dispose forever. With a short grace, dispose must