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

Merge master into codex/session-title

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-21 22:59:41 +08:00
parent 3a895ce815 0cd8424d46
commit 3176d232b8
197 changed files with 3343 additions and 1227 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl
View File

@@ -51,4 +51,4 @@
{"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":3,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}}
{"type":"context/message","seq":50,"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},"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":51,"time":0,"data":{"turn":3,"step":1}}
{"type":"turn/end","seq":52,"time":0,"data":{"turn":3,"reason":{"kind":"aborted","reason":"session/cancel"}}}
{"type":"turn/end","seq":52,"time":0,"data":{"turn":3,"reason":{"kind":"aborted"}}}

4
examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl
View File

@@ -16,6 +16,6 @@
{"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: 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 skipped because the step was aborted before execution"}],"isError":true,"error":{"name":"AbortError","code":"ABORTED"}},"sourceEventSeqs":[16],"surfaceOp":"append"}
{"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}}
{"type":"turn/end","seq":19,"time":1784437195090,"data":{"turn":1,"reason":{"kind":"aborted","reason":"session/cancel"}}}
{"type":"turn/end","seq":19,"time":1784437195090,"data":{"turn":1,"reason":{"kind":"aborted"}}}

2
examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl
View File

@@ -6,4 +6,4 @@
{"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```"}}]}}}
{"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```"}}]}}}

2
examples/acp-agent/tests/snapshots/cancel/session.jsonl
View File

@@ -7,4 +7,4 @@
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}}
{"type":"step/end","seq":7,"time":0,"data":{"turn":1,"step":1}}
{"type":"turn/end","seq":8,"time":0,"data":{"turn":1,"reason":{"kind":"aborted","reason":"session/cancel"}}}
{"type":"turn/end","seq":8,"time":0,"data":{"turn":1,"reason":{"kind":"aborted"}}}

4
examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
View File

File diff suppressed because one or more lines are too long

4
examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
View File

File diff suppressed because one or more lines are too long

41
examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl
View File

@@ -1,23 +1,24 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
{"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":"Use the lsp tool exactly once to find the definition at subject.ts line 1 character 7, then reply with exactly DONE."}],"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_lsp_definition","name":"lsp","argumentsDelta":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}}}
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"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_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}
{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_lsp_definition","content":[{"type":"text","text":"subject.ts:1:7\n… 1 more location omitted (limit 1)."}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}
{"type":"step/end","seq":20,"time":0,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":21,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"session/title","seq":2,"time":0,"data":{"title":"Use the lsp tool exactly","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":4,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_lsp_definition","name":"lsp","argumentsDelta":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}}
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}}}
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":10,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[5,6,7,8,9],"surfaceOp":"append"}
{"type":"tool/call","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_lsp_definition","name":"lsp","arguments":"{\"operation\":\"goToDefinition\",\"file_path\":\"subject.ts\",\"line\":1,\"character\":7}"}}
{"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_lsp_definition","content":[{"type":"text","text":"subject.ts:1:7\n… 1 more location omitted (limit 1)."}],"isError":false},"sourceEventSeqs":[11],"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":"text"}}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
{"type":"step/end","seq":21,"time":0,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":22,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}

1
examples/acp-agent/tests/snapshots/lsp-definition/stdout.expected.jsonl
View File

@@ -1,6 +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":"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]"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"session_info_update","title":"Use the lsp tool exactly","updatedAt":"{{updatedAt}}"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_lsp_definition","title":"LSP goToDefinition subject.ts:1:7","kind":"search","status":"in_progress","locations":[{"path":"subject.ts","line":1}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_lsp_definition","status":"completed","content":[{"type":"content","content":{"type":"text","text":"subject.ts:1:7\n… 1 more location omitted (limit 1)."}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}

5
examples/cordis-agent/tests/cordis-tools.e2e.ts
View File

@@ -4,6 +4,8 @@ import { CallId } from '@deepseek-ai/dsh-llm'
import { cordisHarness, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
const testToolSignal = new AbortController().signal
/**
* With-key smoke for the self-referential cordis tools: a REAL model drives
* cordis_mount/cordis_unmount against the live context the test observes.
@@ -51,6 +53,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
// the mounted listener through the tagged sandbox console.
expect(taggedCalls(log).length).toBeGreaterThan(0)
const mid = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('verify-mounted'), name: 'cordis_inspect', arguments: { what: 'dynamic' },
})
expect(resultText(mid)).toContain('dyn-')
@@ -59,6 +62,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
await waitForIdle(ctx, agent)
const after = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('verify-unmounted'), name: 'cordis_inspect', arguments: { what: 'dynamic' },
})
expect(resultText(after)).toContain('(no dynamic plugins mounted)')
@@ -148,6 +152,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
expect(ctx.get('shouter')).toBeUndefined()
expect(ctx.tools.get('shout_text')).toBeUndefined()
const after = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('verify-parked'), name: 'cordis_inspect', arguments: { what: 'dynamic' },
})
expect(resultText(after)).toContain('waiting for: shouter')