Merge origin/master into worktree/llm-reasoning-effort

This commit is contained in:
Yichen Jiang
2026-07-25 07:59:21 +08:00
856 changed files with 23972 additions and 1907 deletions

View File

@@ -311,7 +311,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
ctx = await codeModeHarness(workdir)
const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
agent.followup([{
type: 'text',
text: 'Using one run_code program: run `echo alpha-7` with the bash tool, run `echo beta-9` with the bash tool, '
+ 'then write both outputs joined by a plus sign into combined.txt (bash heredoc or redirect), '
@@ -363,7 +363,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})
handle.agent.send([{
handle.agent.followup([{
type: 'text',
text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
}])
@@ -372,7 +372,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
const events: SessionEvent[] = [...handle.agent.session.events]
const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
const outerResult = events.find(event => event.type === 'tool/result')
const workspaceContext = events.find(event => event.type === 'context/message'
const workspaceContext = events.find(event => event.type === 'user/message'
&& event.data.source.kind === 'plugin'
&& typeof event.data.meta === 'object'
&& event.data.meta !== null
&& !Array.isArray(event.data.meta)

View File

@@ -56,7 +56,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(SessionId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
agent.followup([{
type: 'text',
text: 'In the current directory, `node add.test.js` fails because add.js has a bug. '
+ 'Fix add.js so the test passes, run `node add.test.js` to verify, and report the result. '

View File

@@ -46,7 +46,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
})
const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
agent.followup([{
type: 'text',
text: 'Read file1.txt, file2.txt, file3.txt, and file4.txt one at a '
+ 'time using cat (a separate bash command for each). After reading all four, tell me how '

View File

@@ -30,7 +30,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas
ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
agent.followup([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
await waitForIdle(ctx, agent)
const events = [...agent.session.events]

View File

@@ -263,9 +263,14 @@ describe('headless stream-json snapshots', () => {
const records = parseJsonl(logs[0]?.content ?? '')
const calls = records.filter(record => record.type === 'tool/call')
.map(record => (record.data as JsonObject | undefined)?.name)
expect(calls).toEqual(['create_goal', 'get_goal'])
expect(calls).toEqual(['update_goal', 'create_goal', 'get_goal'])
const probeResult = records.find(record => record.type === 'tool/result'
&& (record.data as JsonObject | undefined)?.callId === 'call_goal_probe')
const probeData = probeResult?.data as JsonObject | undefined
expect(probeData?.isError).toBe(true)
expect((probeData?.error as JsonObject | undefined)?.code).toBe('GOAL_NOT_FOUND')
const goalChanges = records.filter((record) => {
if (record.type !== 'context/message') return false
if (record.type !== 'user/message') return false
const data = record.data as JsonObject | undefined
const meta = data?.meta as JsonObject | undefined
return meta?.kind === 'goal/change'

View File

@@ -41,7 +41,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
sessionId: SESSION_ID,
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})).agent
first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
first.followup([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
await waitForIdle(ctx, first)
await ctx.fiber.dispose()
ctx = undefined
@@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
// The prior user turn is in the rehydrated log before the model is asked.
expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET)
resumed.send([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
resumed.followup([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
await waitForIdle(ctx, resumed)
// The model recalls it — only possible from the resumed history.

View File

@@ -2,7 +2,7 @@
"steps": [
{
"op": "prompt",
"text": "Create a durable goal to finish the snapshot proof, then inspect it."
"text": "Probe strict-schema fillers against missing-goal revision 1, then create a durable goal to finish the snapshot proof and inspect it."
}
]
}

View File

@@ -1,4 +1,14 @@
[
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 0, "id": "call_goal_probe", "name": "update_goal", "argumentsDelta": "{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_goal_probe", "name": "update_goal", "arguments": "{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}" } },
{ "type": "usage", "usage": { "inputTokens": 15, "outputTokens": 6 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [

View File

@@ -1,35 +1,45 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Create a durable goal to finish the snapshot proof, then inspect it."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Create a durable goal to","messageSeqs":[1],"source":{"kind":"fallback"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Probe strict-schema fillers against missing-goal revision 1, then create a durable goal to finish the snapshot proof and inspect it."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":2,"time":0,"data":{"title":"Probe strict-schema fillers against miss","messageSeqs":[1],"source":{"kind":"fallback"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"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 headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"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 headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_probe","name":"update_goal","argumentsDelta":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":15,"outputTokens":6}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[11],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"context/message","seq":13,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":14,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":15,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"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":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":21,"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":[16,17,18,19,20],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":23,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[22],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_goal_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":15,"outputTokens":6}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_probe","name":"update_goal","arguments":"{\"goal_id\":\"missing-goal\",\"revision\":1,\"action\":\"pause\",\"objective\":\"\",\"max_goal_rounds\":0,\"blocked_reason\":\"\"}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_goal_probe","content":[{"type":"text","text":"Error: no current goal"}],"isError":true,"error":{"name":"GoalError","code":"GOAL_NOT_FOUND"}},"sourceEventSeqs":[11],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":13,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":14,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_create","name":"create_goal","argumentsDelta":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"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_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":23,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":24,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":25,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":31,"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":[26,27,28,29,30],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":32,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":33,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":85,"outputTokens":14}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"call_goal_get","name":"get_goal","argumentsDelta":"{}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_goal_get","name":"get_goal","arguments":"{}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"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":[26,27,28,29,30],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":32,"time":0,"data":{"turn":1,"step":3,"callId":"call_goal_get","name":"get_goal","arguments":"{}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":33,"time":0,"data":{"turn":1,"step":3,"callId":"call_goal_get","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[32],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":34,"time":0,"data":{"turn":1,"step":3}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":35,"time":0,"data":{"turn":1,"step":4}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"text-delta","index":0,"text":"GOAL READY"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"GOAL READY"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":35,"outputTokens":2}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":41,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"text","text":"GOAL READY"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":35,"outputTokens":2}},"sourceEventSeqs":[36,37,38,39,40],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":42,"time":0,"data":{"turn":1,"step":4}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":43,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"GOAL READY","reason":{"kind":"completed"},"usage":{"inputTokens":100,"outputTokens":20}}

View File

@@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT })
const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{ type: 'text', text:
agent.followup([{ type: 'text', text:
'Use the todo_write tool to record a plan of exactly two steps: first '
+ '"inspect the failing test" (in_progress), then "apply the fix" (pending). '
+ 'Send both in one todo_write call, then reply with the single word DONE.' }])