mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
test(acp): snapshot cancelled queued tool calls
This commit is contained in:
Tianyi Cui
@@ -103,6 +103,7 @@ const SCENARIOS: Scenario[] = [
|
||||
configPath: WORKSPACE_CONTEXT_CONFIG,
|
||||
},
|
||||
{ name: 'cancel', hasModelTurn: true, recorded: false, overridden: true },
|
||||
{ name: 'cancel-tool-calls', hasModelTurn: true, recorded: false, overridden: true },
|
||||
{ name: 'subagent-spawn', hasModelTurn: true, recorded: true },
|
||||
{ name: 'subagent-multi', hasModelTurn: true, recorded: true },
|
||||
{ name: 'subagent-fork', hasModelTurn: true, recorded: true },
|
||||
|
||||
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"steps": [
|
||||
{ "op": "initialize" },
|
||||
{ "op": "newSession" },
|
||||
{
|
||||
"op": "promptAndCancel",
|
||||
"text": "Run two shell commands: wait for cancellation, then write skipped.txt.",
|
||||
"afterUpdate": "tool_call"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
[
|
||||
{
|
||||
"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": "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\"}" } },
|
||||
{ "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 10 } },
|
||||
{ "type": "finish", "reason": { "kind": "tool-calls" } }
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,20 @@
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
|
||||
{"type":"turn/start","seq":0,"time":1784437195072,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1784437195072,"data":{"content":[{"type":"text","text":"Run two shell commands: wait for cancellation, then write skipped.txt."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1784437195076,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1784437195076,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":5,"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":6,"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":7,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":8,"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":9,"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":10,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":10}}}}
|
||||
{"type":"assistant/chunk","seq":11,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":12,"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":[4,5,6,7,8,9,10,11],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":13,"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":14,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_wait","content":[{"type":"text","text":"Error: command aborted"}],"isError":true},"sourceEventSeqs":[13],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":15,"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":16,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_skipped","content":[{"type":"text","text":"Error: tool call skipped because the step was aborted before execution"}],"isError":true,"error":{"name":"AbortError","code":"ABORTED"}},"sourceEventSeqs":[15],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":17,"time":1784437195090,"data":{"turn":1,"step":1}}
|
||||
{"type":"turn/end","seq":18,"time":1784437195090,"data":{"turn":1,"reason":{"kind":"aborted","reason":"session/cancel"}}}
|
||||
@@ -0,0 +1,7 @@
|
||||
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
|
||||
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","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":"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","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: 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 skipped because the step was aborted before execution\n```"}}]}}}
|
||||
@@ -37,11 +37,10 @@ export type { AgentUnderTest } from './launcher.ts'
|
||||
* (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).
|
||||
* `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. This keeps update/cancel order
|
||||
* deterministic for fixtures that a plain `prompt` cannot drive.
|
||||
*/
|
||||
export type InputStep =
|
||||
| { op: 'initialize'; terminalOutput?: boolean }
|
||||
@@ -49,7 +48,7 @@ export type InputStep =
|
||||
| { op: 'newSessionExpectError'; additionalDirectories?: string[] }
|
||||
| { op: 'prompt'; text: string }
|
||||
| { op: 'promptExpectError'; text: string }
|
||||
| { op: 'promptAndCancel'; text: string }
|
||||
| { op: 'promptAndCancel'; text: string; afterUpdate?: 'agent_message_chunk' | 'tool_call' }
|
||||
| { op: 'cancel' }
|
||||
| { op: 'setConfigOption'; configId: string; value: string }
|
||||
| { op: 'setConfigOptionExpectError'; configId: string; value: string }
|
||||
@@ -342,15 +341,12 @@ async function runStep(
|
||||
case 'promptAndCancel': {
|
||||
const sessionId = getSessionId()
|
||||
if (sessionId === undefined) throw new Error('snapshot-harness: promptAndCancel before newSession')
|
||||
// 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.
|
||||
// Dispatch without awaiting because the fixture does not settle on its
|
||||
// own. Waiting for the selected update pins it before cancellation and
|
||||
// the cancelled prompt response in the transcript.
|
||||
const promptDone = client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
|
||||
await waitForUpdate(u => u.sessionUpdate === 'agent_message_chunk')
|
||||
const afterUpdate = step.afterUpdate ?? 'agent_message_chunk'
|
||||
await waitForUpdate(u => u.sessionUpdate === afterUpdate)
|
||||
await client.cancel({ sessionId })
|
||||
await promptDone
|
||||
return
|
||||
|
||||
@@ -33,6 +33,8 @@ interface Behavior {
|
||||
rejectExtraDirs?: boolean
|
||||
/** How `session/prompt` settles: a clean response, a JSON-RPC error, or a hang until `session/cancel`. */
|
||||
prompt?: 'respond' | 'error' | 'hang-until-cancel'
|
||||
/** Emit a tool call instead of a message chunk before parking a cancellable prompt. */
|
||||
cancelAtToolCall?: boolean
|
||||
/** Before responding to a prompt, send a `session/request_permission` request and echo its outcome as a chunk. */
|
||||
permissionProbe?: boolean
|
||||
/** Echo the `DSH_SNAPSHOT_*` env the harness set as a chunk (spec-side env-plumbing assertions). */
|
||||
@@ -126,7 +128,23 @@ async function handlePrompt(id: number | string): Promise<void> {
|
||||
params: { sessionId, update: { sessionUpdate: 'agent_thought_chunk', content: { type: 'text', text: 'mulling' } } },
|
||||
})
|
||||
}
|
||||
chunk('thinking about it')
|
||||
if (behavior.cancelAtToolCall === true) {
|
||||
send({
|
||||
method: 'session/update',
|
||||
params: {
|
||||
sessionId,
|
||||
update: {
|
||||
sessionUpdate: 'tool_call',
|
||||
toolCallId: 'call_fake_1',
|
||||
title: 'fake tool',
|
||||
kind: 'execute',
|
||||
status: 'in_progress',
|
||||
},
|
||||
},
|
||||
})
|
||||
} else {
|
||||
chunk('thinking about it')
|
||||
}
|
||||
if (behavior.echoEnv === true) {
|
||||
chunk(`env:${JSON.stringify({
|
||||
mode: process.env.DSH_SNAPSHOT,
|
||||
|
||||
@@ -334,6 +334,16 @@ describe('runScenario', () => {
|
||||
expect(result.rawStdout.indexOf('thinking about it')).toBeLessThan(result.rawStdout.indexOf('cancelled'))
|
||||
})
|
||||
|
||||
it('promptAndCancel can wait for a tool call before cancelling', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({ prompt: 'hang-until-cancel', cancelAtToolCall: true })
|
||||
const result = await runScenario(
|
||||
{ steps: [...boot, { op: 'promptAndCancel', text: 'hang', afterUpdate: 'tool_call' }] },
|
||||
{ agent: AGENT, mode: 'replay', fixtureFile },
|
||||
)
|
||||
expect(result.rawStdout).toContain('"sessionUpdate":"tool_call"')
|
||||
expect(result.rawStdout.indexOf('"sessionUpdate":"tool_call"')).toBeLessThan(result.rawStdout.indexOf('cancelled'))
|
||||
})
|
||||
|
||||
it('promptExpectError swallows a model-error response as the expected outcome', { timeout: 20_000 }, async () => {
|
||||
const { fixtureFile } = await scenario({ prompt: 'error' })
|
||||
const result = await runScenario(
|
||||
|
||||
Reference in New Issue
Block a user