Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 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
examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
+7 -7
View File
@@ -5,7 +5,7 @@
{"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}}
{"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}}
{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
{"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
@@ -63,7 +63,7 @@
{"type":"assistant/chunk","seq":61,"time":1783962244582,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","arguments":"{\"command\": \"printf 'before\\\\n' > out.txt && cat out.txt\", \"description\": \"Write and then read out.txt\"}"}}}}
{"type":"assistant/chunk","seq":62,"time":1783962244582,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1411,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":17}}}}
{"type":"assistant/chunk","seq":63,"time":1783962244582,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":64,"time":1783962244582,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","arguments":"{\"command\": \"printf 'before\\\\n' > out.txt && cat out.txt\", \"description\": \"Write and then read out.txt\"}"}],"usage":{"inputTokens":1411,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"}
{"type":"assistant/message","seq":64,"time":1783962244582,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","arguments":"{\"command\": \"printf 'before\\\\n' > out.txt && cat out.txt\", \"description\": \"Write and then read out.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1411,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"}
{"type":"tool/call","seq":65,"time":1783962244582,"data":{"turn":1,"step":1,"callId":"call_00_E1vtulcKU1LKUgLahxdR3767","name":"bash","arguments":"{\"command\": \"printf 'before\\\\n' > out.txt && cat out.txt\", \"description\": \"Write and then read out.txt\"}"}}
{"type":"tool/result","seq":66,"time":1783962244599,"data":{"turn":1,"step":1,"callId":"call_00_E1vtulcKU1LKUgLahxdR3767","content":[{"type":"text","text":"before\n"}],"isError":false},"sourceEventSeqs":[65],"surfaceOp":"append"}
{"type":"step/end","seq":67,"time":1783962244599,"data":{"turn":1,"step":1}}
@@ -97,7 +97,7 @@
{"type":"assistant/chunk","seq":95,"time":1783962244601,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":96,"time":1783962244601,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":109,"outputTokens":24,"cacheReadTokens":1408,"reasoningTokens":21}}}}
{"type":"assistant/chunk","seq":97,"time":1783962244601,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":98,"time":1783962244601,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully, output \"before\". Now I need to reply with just the word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":109,"outputTokens":24,"cacheReadTokens":1408,"reasoningTokens":21}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97],"surfaceOp":"append"}
{"type":"assistant/message","seq":98,"time":1783962244601,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully, output \"before\". Now I need to reply with just the word DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":109,"outputTokens":24,"cacheReadTokens":1408,"reasoningTokens":21}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97],"surfaceOp":"append"}
{"type":"step/end","seq":99,"time":1783962244601,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":100,"time":1783962244601,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":101,"time":1783962244623,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}}
@@ -107,7 +107,7 @@
{"type":"user/message","seq":105,"time":1783962244624,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"context/message","seq":106,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"}
{"type":"step/start","seq":107,"time":1783962244624,"data":{"turn":2,"step":1}}
{"type":"request/header","seq":108,"time":1784000791271,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
{"type":"request/header","seq":108,"time":1784000791271,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
{"type":"assistant/chunk","seq":109,"time":1783860671025,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":110,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
{"type":"assistant/chunk","seq":111,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}
@@ -155,7 +155,7 @@
{"type":"assistant/chunk","seq":153,"time":1783962244626,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","arguments":"{\"description\": \"Read out.txt\", \"command\": \"cat out.txt\"}"}}}}
{"type":"assistant/chunk","seq":154,"time":1783962244626,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1608,"outputTokens":82,"cacheReadTokens":0,"reasoningTokens":19}}}}
{"type":"assistant/chunk","seq":155,"time":1783962244626,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":156,"time":1783962244626,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `cat out.txt` and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","arguments":"{\"description\": \"Read out.txt\", \"command\": \"cat out.txt\"}"}],"usage":{"inputTokens":1608,"outputTokens":82,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"}
{"type":"assistant/message","seq":156,"time":1783962244626,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `cat out.txt` and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","arguments":"{\"description\": \"Read out.txt\", \"command\": \"cat out.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1608,"outputTokens":82,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"}
{"type":"tool/call","seq":157,"time":1783962244626,"data":{"turn":2,"step":1,"callId":"call_00_7Jb7FWHNjIBVML49dEJl1990","name":"bash","arguments":"{\"description\": \"Read out.txt\", \"command\": \"cat out.txt\"}"}}
{"type":"tool/result","seq":158,"time":1783962244631,"data":{"turn":2,"step":1,"callId":"call_00_7Jb7FWHNjIBVML49dEJl1990","content":[{"type":"text","text":"before\n"}],"isError":false},"sourceEventSeqs":[157],"surfaceOp":"append"}
{"type":"step/end","seq":159,"time":1783962244631,"data":{"turn":2,"step":1}}
@@ -166,7 +166,7 @@
{"type":"assistant/chunk","seq":164,"time":1783962244632,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":165,"time":1783962244632,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":3,"cacheReadTokens":1664,"reasoningTokens":0}}}}
{"type":"assistant/chunk","seq":166,"time":1783962244632,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":167,"time":1783962244632,"data":{"turn":2,"step":2,"content":[{"type":"text","text":"DONE"}],"usage":{"inputTokens":40,"outputTokens":3,"cacheReadTokens":1664,"reasoningTokens":0}},"sourceEventSeqs":[161,162,163,164,165,166],"surfaceOp":"append"}
{"type":"assistant/message","seq":167,"time":1783962244632,"data":{"turn":2,"step":2,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":40,"outputTokens":3,"cacheReadTokens":1664,"reasoningTokens":0}},"sourceEventSeqs":[161,162,163,164,165,166],"surfaceOp":"append"}
{"type":"step/end","seq":168,"time":1783962244632,"data":{"turn":2,"step":2}}
{"type":"turn/end","seq":169,"time":1783962244632,"data":{"turn":2,"reason":{"kind":"completed"}}}
{"type":"turn/start","seq":170,"time":1783962244637,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"user"}}}}
@@ -233,6 +233,6 @@
{"type":"assistant/chunk","seq":231,"time":1783962244639,"data":{"turn":3,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"My approval policy is set to \"never\" — no actions requiring approval are permitted, and they are rejected automatically."}}}}
{"type":"assistant/chunk","seq":232,"time":1783962244639,"data":{"turn":3,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":64,"outputTokens":56,"cacheReadTokens":1664,"reasoningTokens":32}}}}
{"type":"assistant/chunk","seq":233,"time":1783962244639,"data":{"turn":3,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":234,"time":1783962244640,"data":{"turn":3,"step":1,"content":[{"type":"reasoning","text":"The user wants me to state the current approval policy without using any tools. From the context provided, the approval policy changed from \"ask\" to \"never\"."},{"type":"text","text":"My approval policy is set to \"never\" — no actions requiring approval are permitted, and they are rejected automatically."}],"usage":{"inputTokens":64,"outputTokens":56,"cacheReadTokens":1664,"reasoningTokens":32}},"sourceEventSeqs":[173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233],"surfaceOp":"append"}
{"type":"assistant/message","seq":234,"time":1783962244640,"data":{"turn":3,"step":1,"content":[{"type":"reasoning","text":"The user wants me to state the current approval policy without using any tools. From the context provided, the approval policy changed from \"ask\" to \"never\"."},{"type":"text","text":"My approval policy is set to \"never\" — no actions requiring approval are permitted, and they are rejected automatically."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":64,"outputTokens":56,"cacheReadTokens":1664,"reasoningTokens":32}},"sourceEventSeqs":[173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233],"surfaceOp":"append"}
{"type":"step/end","seq":235,"time":1783962244640,"data":{"turn":3,"step":1}}
{"type":"turn/end","seq":236,"time":1783962244640,"data":{"turn":3,"reason":{"kind":"completed"}}}
examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl
+3 -3
View File
@@ -1,6 +1,6 @@
{"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":"Sets this session's sandbox and approval behavior.","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","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","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","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":"Sets this session's sandbox and approval behavior.","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","id":3,"result":{"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":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","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":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
@@ -44,7 +44,7 @@
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}}
{"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}}
{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","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","id":5,"result":{"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":"Sets this session's sandbox and approval behavior.","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":"agent_thought_chunk","content":{"type":"text","text":"The"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}}
examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json
+10 -2
View File
@@ -203,7 +203,7 @@
},
{
"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": {
@@ -241,6 +241,10 @@
"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."
@@ -474,7 +478,7 @@
},
{
"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": {
@@ -512,6 +516,10 @@
"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."