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

Merge master into codex/simp-session-log-representation

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-17 22:33:42 +08:00
parent b79e7a5e30 ad16d306cb
commit 7a2d5cd28d
310 changed files with 4718 additions and 1903 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
View File

@@ -2,13 +2,13 @@
{"type":"turn/start","seq":0,"time":1783778297065,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":1,"time":1783778297066,"data":{"content":[{"type":"text","text":"Read nested/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"step/start","seq":2,"time":1783778297069,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":3,"time":1783778297070,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}]}]},"reason":"initial"}}
{"type":"request/header","seq":3,"time":1783778297070,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":[{"role":"user","content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}]}]},"reason":"initial"}}
{"type":"assistant/chunk","seq":4,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":5,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_workspace_read","name":"read","argumentsDelta":"{\"file_path\":\"nested/task.txt\"}"}}}
{"type":"assistant/chunk","seq":6,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}}}
{"type":"assistant/chunk","seq":7,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":8,"time":1783778297070,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":9,"time":1783778297070,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
{"type":"assistant/message","seq":9,"time":1783778297070,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"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":1783778297070,"data":{"turn":1,"step":1,"callId":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}
{"type":"tool/result","seq":11,"time":1783778297072,"data":{"turn":1,"step":1,"callId":"call_workspace_read","content":[{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
{"type":"context/message","seq":12,"time":1783778297072,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"plugin","plugin":"workspace-context"},"envelope":"raw","meta":{"kind":"workspace-instructions","version":1,"changes":[{"action":"set","scope":"nested","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]}},"surfaceOp":"append"}
@@ -19,6 +19,6 @@
{"type":"assistant/chunk","seq":17,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":18,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":19,"time":1783778297073,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":20,"time":1783778297073,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}
{"type":"assistant/message","seq":20,"time":1783778297073,"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":1783778297073,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":22,"time":1783778297073,"data":{"turn":1,"reason":{"kind":"completed"}}}

6
examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.golden.json
View File

@@ -257,7 +257,7 @@
},
{
"name": "workflow",
"description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
"description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
"parameters": {
"type": "object",
"properties": {
@@ -295,6 +295,10 @@
"type": "string",
"description": "Optional one-line description of the phase."
},
"provider": {
"type": "string",
"description": "Optional provider override this phase is expected to use."
},
"model": {
"type": "string",
"description": "Optional model override this phase is expected to use."