HomerandClaude Opus 5.5
f9bad01ed7
ci / check (push) Waiting to run
The first public release of LLeMbas CLI: a terminal coding agent and project manager for any LLM API, with permission modes, git snapshots, memory and skills, knowledge bases, MCP, voice, and a link to a LLeMbas instance whose web UI can work its sessions too. Signed Linux binaries for x64 and arm64. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
82 lines
3.2 KiB
JSON
82 lines
3.2 KiB
JSON
{
|
||
"name": "ask_user",
|
||
"scope": "shared",
|
||
"risk": "interact",
|
||
"exclusive": true,
|
||
"block": "tool",
|
||
"purpose": false,
|
||
"aliases": {
|
||
"cli": [
|
||
"question"
|
||
],
|
||
"llembas": []
|
||
},
|
||
"description": "Ask the user when you genuinely cannot proceed well without their decision: a choice that is theirs to make, a requirement the request leaves open, a trade-off only they can weigh. Do not ask what you can find out yourself by reading the code or running something, and do not ask for approval of an action — the harness does that.\n\n- Ask everything you need in ONE call (up to 4 questions); never a question per call.\n- Give 2–6 options per question: the answers you actually think are plausible, each with a short description of what it means. Mark the one you would choose with recommended: true.\n- Do NOT add an \"Other\" or \"Something else\" option: the user always gets a free-text row, and can also answer with a question back.\n- header: a 1–3 word chip label, at most 30 characters.\n- multiple: true when several options can apply together.\n- Never ask for a password, key or other secret.\n\nThe answer comes back as one line per question: \"→ label\", \"→ custom: …\", or \"↩ counter-question: …\". When the user asks a question back, answer it, then ask again — only that question.",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"why": {
|
||
"description": "One line: why you are asking now",
|
||
"type": "string"
|
||
},
|
||
"questions": {
|
||
"minItems": 1,
|
||
"maxItems": 4,
|
||
"type": "array",
|
||
"items": {
|
||
"type": "object",
|
||
"properties": {
|
||
"header": {
|
||
"type": "string",
|
||
"description": "A chip label, at most 30 characters"
|
||
},
|
||
"question": {
|
||
"type": "string",
|
||
"minLength": 1,
|
||
"description": "The full question"
|
||
},
|
||
"options": {
|
||
"description": "2–6 answers you consider plausible, the recommended one marked",
|
||
"maxItems": 6,
|
||
"type": "array",
|
||
"items": {
|
||
"type": "object",
|
||
"properties": {
|
||
"label": {
|
||
"type": "string",
|
||
"minLength": 1,
|
||
"description": "1–5 words"
|
||
},
|
||
"description": {
|
||
"description": "What choosing it means, the trade-off",
|
||
"type": "string"
|
||
},
|
||
"recommended": {
|
||
"description": "At most one per question: the one you would pick",
|
||
"type": "boolean"
|
||
}
|
||
},
|
||
"required": [
|
||
"label"
|
||
]
|
||
}
|
||
},
|
||
"multiple": {
|
||
"description": "The user may pick several",
|
||
"type": "boolean"
|
||
}
|
||
},
|
||
"required": [
|
||
"header",
|
||
"question"
|
||
]
|
||
},
|
||
"description": "1–4 questions, all you need, asked together"
|
||
}
|
||
},
|
||
"required": [
|
||
"questions"
|
||
]
|
||
}
|
||
}
|