HomerandClaude Opus 5.5
d09d51cfec
context.md §8: every assistant message of the current turn (after the last message that started a turn — a step-boundary delivery does not) carries its reasoning back, as reasoning_content in OpenAI chat and as thinking blocks in Anthropic; earlier turns carry none, which the common templates render identically. §11: an agent session's prompt names no absolute machine path: the environment block names the project and says paths are relative to its root (loop.json context.env), files outside the project under home as ~/…; relative paths resolve against the project root, absolute ones still accepted. agents-missing.md and init.md no longer name the root. New conformance areas: reasoning, paths. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
324 lines
8.7 KiB
JSON
324 lines
8.7 KiB
JSON
{
|
|
"about": "What a request sends back of the model's reasoning (context.md §8, spec 3.2.0). `messages` is the history a request is built from, in order: `role` user, assistant or tool; `content`; an assistant message's stored `reasoning` (absent: it came with none); a user message's `turn` — false for a delivery at a step boundary (a job's note, a team message, words added to a running turn), which does not start a turn; absent or true for one that does (the person's, or a machine message starting a turn of its own). The answer is the messages as the OpenAI chat dialect sends them — `role`, `content`, and `reasoning_content` on an assistant message after the last user message that started a turn, when its reasoning is not empty (tool calls and ids are left out of the cases: they are sent as always). The Anthropic dialect sends the same messages' thinking blocks. LLeMbas: services/llm/openai_client.py, services/generation.py; CLI: provider/openai-chat.ts, session/engine.ts.",
|
|
"cases": [
|
|
{
|
|
"about": "One turn, three steps: every reply of the turn carries its reasoning back.",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Fix the failing test."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "The test name points at the parser."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001 src/parse.ts lines 1-40 of 40 sha 1c9e04ab]\n…"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "Line 12 drops the last token."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0002 src/parse.ts sha 7d0a91c3]\n@@ -12 +12 @@"
|
|
}
|
|
],
|
|
"expect": [
|
|
{
|
|
"role": "user",
|
|
"content": "Fix the failing test."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning_content": "The test name points at the parser."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001 src/parse.ts lines 1-40 of 40 sha 1c9e04ab]\n…"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning_content": "Line 12 drops the last token."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0002 src/parse.ts sha 7d0a91c3]\n@@ -12 +12 @@"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"about": "A second turn: the first turn's replies go without their reasoning, the current one's with it.",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Where is the config loaded?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "Search for load."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001] src/config/load.ts:40"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "In src/config/load.ts.",
|
|
"reasoning": "Found it at line 40."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "And who calls it?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "Grep for loadConfig."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0002] src/app.ts:120"
|
|
}
|
|
],
|
|
"expect": [
|
|
{
|
|
"role": "user",
|
|
"content": "Where is the config loaded?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": ""
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001] src/config/load.ts:40"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "In src/config/load.ts."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "And who calls it?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning_content": "Grep for loadConfig."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0002] src/app.ts:120"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"about": "A job's note delivered at a step boundary does not start a turn: the turn's earlier replies keep their reasoning.",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Run the tests in the background and fix the lint."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "Start the tests, then lint."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001] job1 started"
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "[A background job you started has finished:]\njob1 (npm test) exited with 0 after 5s.",
|
|
"turn": false
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "Tests pass; now the lint."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0002] 0 problems"
|
|
}
|
|
],
|
|
"expect": [
|
|
{
|
|
"role": "user",
|
|
"content": "Run the tests in the background and fix the lint."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning_content": "Start the tests, then lint."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001] job1 started"
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "[A background job you started has finished:]\njob1 (npm test) exited with 0 after 5s."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning_content": "Tests pass; now the lint."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0002] 0 problems"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"about": "A machine message that starts a turn of its own (a team report to an idle lead) does: the replies before it go without.",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Split the work."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Started alice.",
|
|
"reasoning": "Add one member."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "[Team report from alice to lead:]\nDone.",
|
|
"turn": true
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "Review alice's change."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001 src/a.ts lines 1-10 of 10 sha 52b6e3a0]\n…"
|
|
}
|
|
],
|
|
"expect": [
|
|
{
|
|
"role": "user",
|
|
"content": "Split the work."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Started alice."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "[Team report from alice to lead:]\nDone."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning_content": "Review alice's change."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001 src/a.ts lines 1-10 of 10 sha 52b6e3a0]\n…"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"about": "A reply that came with no reasoning, or an empty one, carries no field.",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Hello"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"reasoning": "Greet."
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001] ok"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Hi."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Again"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Hi again.",
|
|
"reasoning": ""
|
|
}
|
|
],
|
|
"expect": [
|
|
{
|
|
"role": "user",
|
|
"content": "Hello"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": ""
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"content": "[#0001] ok"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Hi."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Again"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Hi again."
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"about": "The last message the person wrote starts the turn even when nothing has answered it yet: every earlier reply goes without.",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "One"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Done.",
|
|
"reasoning": "Easy."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Two"
|
|
}
|
|
],
|
|
"expect": [
|
|
{
|
|
"role": "user",
|
|
"content": "One"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Done."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Two"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|