test(ci): stabilize cancellation and crash checkpoints

This commit is contained in:
Tianyi Cui
2026-07-22 22:14:14 +08:00
parent a3d17feb8c
commit ecb77f5e0c
7 changed files with 72 additions and 17 deletions
@@ -6,6 +6,7 @@
"op": "promptAndCancel",
"text": "Run two shell commands: wait for cancellation, then write skipped.txt.",
"afterUpdate": "tool_call",
"waitForFile": { "path": "started.txt" },
"waitForToolCallUpdate": "call_skipped"
},
{ "op": "waitForTurnEnd" }
@@ -3,8 +3,8 @@
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 0, "id": "call_wait", "name": "bash", "argumentsDelta": "{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_wait", "name": "bash", "arguments": "{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}" } },
{ "type": "tool-call-delta", "index": 0, "id": "call_wait", "name": "bash", "argumentsDelta": "{\"command\":\"node -e \\\"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_wait", "name": "bash", "arguments": "{\"command\":\"node -e \\\"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}" } },
{ "type": "block-start", "index": 1, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 1, "id": "call_skipped", "name": "bash", "argumentsDelta": "{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}" },
{ "type": "block-end", "index": 1, "block": { "type": "tool-call", "id": "call_skipped", "name": "bash", "arguments": "{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}" } },
@@ -5,16 +5,16 @@
{"type":"step/start","seq":3,"time":1784437195076,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":4,"time":1784437195076,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":5,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":6,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_wait","name":"bash","argumentsDelta":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}}
{"type":"assistant/chunk","seq":7,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}}}
{"type":"assistant/chunk","seq":6,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_wait","name":"bash","argumentsDelta":"{\"command\":\"node -e \\\"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}}
{"type":"assistant/chunk","seq":7,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}}}
{"type":"assistant/chunk","seq":8,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":9,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skipped","name":"bash","argumentsDelta":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}}}
{"type":"assistant/chunk","seq":10,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}}}}
{"type":"assistant/chunk","seq":11,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":10}}}}
{"type":"assistant/chunk","seq":12,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":13,"time":1784437195078,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"},{"type":"tool-call","id":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":10}},"sourceEventSeqs":[5,6,7,8,9,10,11,12],"surfaceOp":"append"}
{"type":"tool/call","seq":14,"time":1784437195078,"data":{"turn":1,"step":1,"callId":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}
{"type":"tool/result","seq":15,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_wait","content":[{"type":"text","text":"Error: tool call aborted before dispatch"}],"isError":true,"error":{"name":"AbortError","code":"ABORTED_BEFORE_DISPATCH"}},"sourceEventSeqs":[14],"surfaceOp":"append"}
{"type":"assistant/message","seq":13,"time":1784437195078,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"},{"type":"tool-call","id":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":10}},"sourceEventSeqs":[5,6,7,8,9,10,11,12],"surfaceOp":"append"}
{"type":"tool/call","seq":14,"time":1784437195078,"data":{"turn":1,"step":1,"callId":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}
{"type":"tool/result","seq":15,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_wait","content":[{"type":"text","text":"Error: command aborted"}],"isError":true},"sourceEventSeqs":[14],"surfaceOp":"append"}
{"type":"tool/call","seq":16,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}}
{"type":"tool/result","seq":17,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_skipped","content":[{"type":"text","text":"Error: tool call aborted before dispatch"}],"isError":true,"error":{"name":"AbortError","code":"ABORTED_BEFORE_DISPATCH"}},"sourceEventSeqs":[16],"surfaceOp":"append"}
{"type":"step/end","seq":18,"time":1784437195090,"data":{"turn":1,"step":1}}
@@ -2,8 +2,8 @@
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","modes":{"availableModes":[{"id":"default","name":"default"},{"id":"plan","name":"plan"}],"currentModeId":"default"},"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"available_commands_update","availableCommands":[{"name":"goal","description":"set or view the goal for a long-running task","input":{"hint":"[<objective>|clear|edit <objective>|pause|resume]"}},{"name":"plan","description":"Enter plan mode","input":{"hint":"[message]"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"session_info_update","title":"Run two shell commands: wait","updatedAt":"{{updatedAt}}"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_wait","title":"node -e \"setInterval(() => {}, 1000)\"","kind":"execute","status":"in_progress","rawInput":"node -e \"setInterval(() => {}, 1000)\"","content":[{"type":"content","content":{"type":"text","text":"Wait until cancellation"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_wait","title":"node -e \"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\"","kind":"execute","status":"in_progress","rawInput":"node -e \"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\"","content":[{"type":"content","content":{"type":"text","text":"Wait until cancellation"}}]}}}
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_wait","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: tool call aborted before dispatch\n```"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_wait","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: command aborted\n```"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skipped","title":"printf skipped > skipped.txt","kind":"execute","status":"in_progress","rawInput":"printf skipped > skipped.txt","content":[{"type":"content","content":{"type":"text","text":"Write skipped marker"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skipped","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: tool call aborted before dispatch\n```"}}]}}}
@@ -16,18 +16,20 @@ const childScript = fileURLToPath(new URL('./fixtures/crash-child.ts', import.me
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
const sessionId = SessionId('semantic-checkpoint-crash')
const roots: string[] = []
const CHILD_FAILPOINT_TIMEOUT_MS = 30_000
async function waitForFile(path: string): Promise<void> {
for (let attempt = 0; attempt < 500; attempt += 1) {
const deadline = Date.now() + CHILD_FAILPOINT_TIMEOUT_MS
for (;;) {
try {
await access(path)
return
} catch (error: unknown) {
if ((error as NodeJS.ErrnoException).code !== 'ENOENT') throw error
}
if (Date.now() >= deadline) throw new Error(`crash child did not reach failpoint ${path}`)
await new Promise(resolve => setTimeout(resolve, 10))
}
throw new Error(`crash child did not reach failpoint ${path}`)
}
async function crashAt(mode: 'request' | 'tool'): Promise<{ root: string; markerText: string }> {
+27 -6
View File
@@ -35,8 +35,8 @@ import { launchAcpTestAgent, type AgentUnderTest, type LaunchedAcpTestAgent } fr
export type { AgentUnderTest } from './launcher.ts'
const DEFAULT_TURN_END_TIMEOUT_MS = 10_000
const TURN_END_POLL_INTERVAL_MS = 10
const DEFAULT_WAIT_TIMEOUT_MS = 10_000
const WAIT_POLL_INTERVAL_MS = 10
/**
* One step of a scenario's deterministic input script (`input.json`). The
@@ -46,8 +46,9 @@ const TURN_END_POLL_INTERVAL_MS = 10
*
* `promptAndCancel` starts a prompt without awaiting completion, waits until
* the client observes the selected update (`agent_message_chunk` by default),
* then cancels and awaits completion. A named `waitForToolCallUpdate` keeps the
* step open for a terminal tool update that may follow the prompt response.
* then cancels and awaits completion. An optional `waitForFile` first observes
* a cwd-relative readiness marker, and a named `waitForToolCallUpdate` keeps
* the step open for a terminal tool update that may follow the prompt response.
* `promptAndWaitForAgentMessage` arms an exact text-chunk waiter before sending
* the prompt, then keeps the application live until that later update arrives.
* `waitForTurnEnd` holds the subprocess open until the selected session's latest
@@ -64,6 +65,7 @@ export type InputStep =
op: 'promptAndCancel'
text: string
afterUpdate?: 'agent_message_chunk' | 'tool_call'
waitForFile?: { path: string; timeoutMs?: number }
waitForToolCallUpdate?: string
}
| { op: 'waitForTurnEnd'; timeoutMs?: number }
@@ -445,6 +447,9 @@ async function runStep(
const promptDone = client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
const afterUpdate = step.afterUpdate ?? 'agent_message_chunk'
await waitForUpdate(u => u.sessionUpdate === afterUpdate)
if (step.waitForFile !== undefined) {
await waitForWorkspaceFile(cwd, step.waitForFile.path, step.waitForFile.timeoutMs)
}
// Arm this before cancellation so a fast tool drain cannot outrun the waiter.
const toolCallUpdateDone = step.waitForToolCallUpdate === undefined
? undefined
@@ -516,7 +521,7 @@ async function runStep(
async function waitForPersistedTurnEnd(
root: string,
sessionId: string,
timeoutMs = DEFAULT_TURN_END_TIMEOUT_MS,
timeoutMs = DEFAULT_WAIT_TIMEOUT_MS,
): Promise<void> {
const deadline = Date.now() + timeoutMs
while (true) {
@@ -525,7 +530,23 @@ async function waitForPersistedTurnEnd(
if (Date.now() >= deadline) {
throw new Error(`snapshot-harness: session "${sessionId}" did not persist turn/end within ${timeoutMs}ms`)
}
await delay(TURN_END_POLL_INTERVAL_MS)
await delay(WAIT_POLL_INTERVAL_MS)
}
}
/** Wait for a cwd-relative marker proving an external action reached readiness. */
async function waitForWorkspaceFile(
cwd: string,
path: string,
timeoutMs = DEFAULT_WAIT_TIMEOUT_MS,
): Promise<void> {
const target = join(cwd, path)
const deadline = Date.now() + timeoutMs
while (!existsSync(target)) {
if (Date.now() >= deadline) {
throw new Error(`snapshot-harness: workspace file "${path}" did not appear within ${timeoutMs}ms`)
}
await delay(WAIT_POLL_INTERVAL_MS)
}
}
@@ -493,6 +493,37 @@ describe('runScenario', () => {
expect(result.rawStdout.indexOf('thinking about it')).toBeLessThan(result.rawStdout.indexOf('cancelled'))
})
it('promptAndCancel can wait for cwd-relative readiness before cancelling', { timeout: 20_000 }, async () => {
const { dir, fixtureFile } = await scenario({ prompt: 'hang-until-cancel' })
const workspaceDir = join(dir, 'workspace')
const { mkdir } = await import('node:fs/promises')
await mkdir(workspaceDir, { recursive: true })
await writeFile(join(workspaceDir, 'started.txt'), 'started')
const result = await runScenario(
{
steps: [...boot, {
op: 'promptAndCancel',
text: 'hang',
waitForFile: { path: 'started.txt' },
}],
},
{ agent: AGENT, mode: 'replay', fixtureFile, workspaceDir },
)
expect(result.rawStdout).toContain('"stopReason":"cancelled"')
const missing = await scenario({ prompt: 'hang-until-cancel' })
await expect(runScenario(
{
steps: [...boot, {
op: 'promptAndCancel',
text: 'hang',
waitForFile: { path: 'never.txt', timeoutMs: 20 },
}],
},
{ agent: AGENT, mode: 'replay', fixtureFile: missing.fixtureFile },
)).rejects.toThrow(/workspace file "never\.txt" did not appear within 20ms/)
})
it('promptAndWaitForAgentMessage keeps the app live through a matching later update', { timeout: 20_000 }, async () => {
const { fixtureFile } = await scenario({ prompt: 'respond' })
const result = await runScenario(