Merge branch 'codex/goal-session' into codex/commands

This commit is contained in:
Tianyi Cui
2026-07-20 17:24:39 +08:00
55 changed files with 860 additions and 891 deletions

View File

@@ -0,0 +1,112 @@
import { readFile, writeFile } from 'node:fs/promises'
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import {
normalizeSessionLog,
normalizeStdout,
runScenario,
scrubRequestHeaders,
type AgentUnderTest,
type InputScript,
type NormalizeContext,
} from '@deepseek-ai/dsh-acp-snapshot'
import { foldGoal } from '@deepseek-ai/dsh-goal'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import { describe, expect, it } from 'vitest'
const scenarioDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots/goal-session')
const fixtureFile = join(scenarioDir, 'session.jsonl')
const overrideFile = join(scenarioDir, 'replay.override.json')
const stdoutExpected = join(scenarioDir, 'stdout.expected.jsonl')
const sessionExpected = join(scenarioDir, 'session.expected.jsonl')
const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
const agent: AgentUnderTest = {
binScript: fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url)),
configPath: fileURLToPath(new URL('../goal.cordis.yml', import.meta.url)),
tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)),
}
interface JsonObject {
[key: string]: unknown
}
/** Parse non-empty records from one JSONL artifact. */
function parseJsonl(content: string): JsonObject[] {
return content.split('\n').filter(line => line.trim().length > 0)
.map(line => JSON.parse(line) as JsonObject)
}
/** Zero durable goal timestamps inside metadata records and rendered XML JSON. */
function normalizeGoalTimestamps(value: unknown): unknown {
if (typeof value === 'string') {
return value.replace(/("(?:createdAt|updatedAt|clearedAt)":)\d+/g, '$10')
}
if (Array.isArray(value)) return value.map(normalizeGoalTimestamps)
if (value !== null && typeof value === 'object') {
return Object.fromEntries(Object.entries(value).map(([key, item]) => [
key,
['createdAt', 'updatedAt', 'clearedAt'].includes(key) && typeof item === 'number'
? 0
: normalizeGoalTimestamps(item),
]))
}
return value
}
/** Normalize one persisted goal log after the shared snapshot scrubbers. */
function normalizeGoalLog(content: string, context: NormalizeContext): string {
return parseJsonl(scrubRequestHeaders(normalizeSessionLog(content, context)))
.map(record => JSON.stringify(normalizeGoalTimestamps(record)))
.join('\n') + '\n'
}
describe('ACP same-session goal snapshot', () => {
it('runs exact automatic rounds in the shipped application and persists cancellation', async () => {
const input = JSON.parse(await readFile(join(scenarioDir, 'input.json'), 'utf8')) as InputScript
const result = await runScenario(input, {
agent,
mode: 'replay',
fixtureFile,
overrideFile,
configPath: agent.configPath,
})
expect(result.stderr).toBe('')
expect(result.sessionLogs).toHaveLength(1)
const log = result.sessionLogs[0]
if (log === undefined) throw new Error('goal snapshot did not persist its ACP session')
const records = parseJsonl(log.content)
const events = records.slice(1) as unknown as SessionEvent[]
const calls = events.filter(event => event.type === 'tool/call').map(event => event.data.name)
expect(calls).toEqual(['create_goal', 'get_goal'])
const rounds = events.flatMap(event => event.type === 'user/message' && event.data.source.kind === 'goal'
? [event.data.source.round]
: [])
expect(rounds).toEqual([1, 2])
expect(foldGoal(events)).toMatchObject({
goal: {
objective: 'Finish the ACP goal-session snapshot proof',
phase: 'paused',
revision: 2,
maxGoalRounds: 2,
},
roundsStarted: 2,
})
const context: NormalizeContext = {
sessionIds: [result.sessionId, log.id].filter((id): id is string => id !== undefined),
cwd: result.cwd,
}
const stdout = normalizeStdout(result.rawStdout, context)
const session = normalizeGoalLog(log.content, context)
if (refreshing) {
await Promise.all([
writeFile(stdoutExpected, stdout),
writeFile(sessionExpected, session),
])
}
expect(stdout).toBe(await readFile(stdoutExpected, 'utf8'))
expect(session).toBe(await readFile(sessionExpected, 'utf8'))
})
})

View File

@@ -0,0 +1,12 @@
{
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{
"op": "promptAndWaitForAgentMessage",
"text": "Create a durable two-round goal for the ACP snapshot, inspect it, then report readiness.",
"waitForText": "partial"
},
{ "op": "cancel" }
]
}

View File

@@ -0,0 +1,43 @@
[
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 0, "id": "call_goal_create", "name": "create_goal", "argumentsDelta": "{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_create", "name": "create_goal", "arguments": "{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}" } },
{ "type": "usage", "usage": { "inputTokens": 20, "outputTokens": 8 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 0, "id": "call_goal_get", "name": "get_goal", "argumentsDelta": "{}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_get", "name": "get_goal", "arguments": "{}" } },
{ "type": "usage", "usage": { "inputTokens": 30, "outputTokens": 4 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "GOAL READY" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "GOAL READY" } },
{ "type": "usage", "usage": { "inputTokens": 35, "outputTokens": 2 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "GOAL ROUND ONE" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "GOAL ROUND ONE" } },
{ "type": "usage", "usage": { "inputTokens": 40, "outputTokens": 3 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
},
{ "kind": "hang" }
]

View File

@@ -0,0 +1,53 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"}
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Create a durable two-round goal for the ACP snapshot, inspect it, then report readiness."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}}}
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the ACP goal-session snapshot proof\",\"max_goal_rounds\":2}"}}
{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
{"type":"context/message","seq":12,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":2},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"envelope":"raw","meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the ACP goal-session snapshot proof","phase":"active","maxGoalRounds":2},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}
{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}
{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}
{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}
{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}
{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}
{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}
{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}
{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}
{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":30,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"}
{"type":"step/end","seq":31,"time":0,"data":{"turn":1,"step":3}}
{"type":"turn/end","seq":32,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":33,"time":0,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1}}}}
{"type":"user/message","seq":34,"time":0,"data":{"content":[{"type":"text","text":"<goal_round>\nObjective: \"Finish the ACP goal-session snapshot proof\"\nRound: 1/2\n\nContinue working toward the objective in this same session. Treat the current workspace, tool results, and durable session state as authoritative; inspect them instead of assuming earlier narration is still current. Make concrete progress and verify the result. Before claiming completion, gather evidence that the whole objective is achieved, read the current goal, and mark it complete. If work remains, leave the goal active for the next round. Follow the configured goal-tool policy before reporting a blocker.\n</goal_round>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":1}},"surfaceOp":"append"}
{"type":"step/start","seq":35,"time":0,"data":{"turn":2,"step":1}}
{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"GOAL ROUND ONE"}}}
{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL ROUND ONE"}}}}
{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":3}}}}
{"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":41,"time":0,"data":{"turn":2,"step":1,"content":[{"type":"text","text":"GOAL ROUND ONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":40,"outputTokens":3}},"sourceEventSeqs":[36,37,38,39,40],"surfaceOp":"append"}
{"type":"step/end","seq":42,"time":0,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":43,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":44,"time":0,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2}}}}
{"type":"user/message","seq":45,"time":0,"data":{"content":[{"type":"text","text":"<goal_round>\nObjective: \"Finish the ACP goal-session snapshot proof\"\nRound: 2/2\n\nContinue working toward the objective in this same session. Treat the current workspace, tool results, and durable session state as authoritative; inspect them instead of assuming earlier narration is still current. Make concrete progress and verify the result. Before claiming completion, gather evidence that the whole objective is achieved, read the current goal, and mark it complete. If work remains, leave the goal active for the next round. Follow the configured goal-tool policy before reporting a blocker.\n</goal_round>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":2}},"surfaceOp":"append"}
{"type":"step/start","seq":46,"time":0,"data":{"turn":3,"step":1}}
{"type":"assistant/chunk","seq":47,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}}
{"type":"context/message","seq":49,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":2,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"paused\",\"maxGoalRounds\":2},\"roundsStarted\":2,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":2,"round":0},"envelope":"raw","meta":{"kind":"goal/change","version":1,"operation":"pause","goal":{"id":"goal-{{sessionId}}","revision":2,"objective":"Finish the ACP goal-session snapshot proof","phase":"paused","maxGoalRounds":2},"roundsStarted":2,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}
{"type":"step/end","seq":50,"time":0,"data":{"turn":3,"step":1}}
{"type":"turn/end","seq":51,"time":0,"data":{"turn":3,"reason":{"kind":"aborted","reason":"session/cancel"}}}

View File

@@ -0,0 +1 @@
{"type":"session","version":0,"id":"goal-session-placeholder","createdAt":0,"cwd":"/tmp/goal-session-placeholder"}

View File

@@ -0,0 +1,10 @@
{"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_goal_create","title":"Create goal","kind":"other","status":"in_progress","rawInput":"Finish the ACP goal-session snapshot proof"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_create","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_goal_get","title":"Read current goal","kind":"read","status":"in_progress"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_goal_get","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the ACP goal-session snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":2},\"activation\":\"armed\"}"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GOAL READY"}}}}
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"GOAL ROUND ONE"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}}