67 lines
2.7 KiB
JSON
67 lines
2.7 KiB
JSON
{
|
|
"id": "llama-cpp",
|
|
"role": "reviewer",
|
|
"version": "1.14.0",
|
|
"title": "llama.cpp",
|
|
"description": "llama.cpp server — cross-AI /gsd:review reviewer lane only; not a GSD install target (no runtime body, no artifacts). OpenAI-compatible HTTP transport against a user-configured `review.llama_cpp_host` (POST /v1/chat/completions); model discovered via GET /v1/models piped through jq. Capability id/folder are kebab (`llama-cpp`, required by KEBAB_RE); `reviewer.slug` stays snake (`llama_cpp`) to match the shipped roster and the `review.llama_cpp_host` config key (ADR-2782's three-namespace trap).",
|
|
"tier": "full",
|
|
"requires": [],
|
|
"engines": {
|
|
"gsd": ">=1.8.0"
|
|
},
|
|
"reviewer": {
|
|
"slug": "llama_cpp",
|
|
"flags": [
|
|
"--llama-cpp"
|
|
],
|
|
"transport": "openai-http",
|
|
"probe": {
|
|
"kind": "http-reachable",
|
|
"hostConfigKey": "review.llama_cpp_host",
|
|
"path": "/v1/models",
|
|
"timeoutMs": 2000
|
|
},
|
|
"invoke": {
|
|
"hostConfigKey": "review.llama_cpp_host",
|
|
"defaultHost": "http://localhost:8080",
|
|
"path": "/v1/chat/completions",
|
|
"modelDiscovery": "first-from-models-endpoint",
|
|
"fallbackModel": "local-model",
|
|
"effortChannel": "none"
|
|
},
|
|
"timeoutFloorMs": 120000,
|
|
"timeoutConfigKey": "review.timeouts.llama_cpp",
|
|
"emptyOutput": "stub-with-stderr",
|
|
"reviewsSection": "llama.cpp",
|
|
"evidenceClass": "source-grounded",
|
|
"requiresBinaries": [],
|
|
"promptBudgetKey": "review.max_prompt_tokens_per_reviewer.llama_cpp",
|
|
"modelConfigKey": "review.models.llama_cpp",
|
|
"effortConfigKey": null,
|
|
"defaultEffort": null,
|
|
"handler": "openai-compatible"
|
|
},
|
|
"config": {
|
|
"review.models.llama_cpp": {
|
|
"type": "string",
|
|
"default": "",
|
|
"description": "Model requested from the llama.cpp reviewer lane; empty discovers the first model from /v1/models."
|
|
},
|
|
"review.llama_cpp_host": {
|
|
"type": "string",
|
|
"default": "",
|
|
"description": "Base URL of the llama.cpp OpenAI-compatible server."
|
|
},
|
|
"review.max_prompt_tokens_per_reviewer.llama_cpp": {
|
|
"type": "number",
|
|
"default": -1,
|
|
"description": "Prompt-token budget for the llama.cpp reviewer lane. Unset is -1, a sentinel: 0 is a legitimate value meaning \"do not trim this lane\", so it cannot double as \"not configured\"."
|
|
},
|
|
"review.timeouts.llama_cpp": {
|
|
"type": "number",
|
|
"default": -1,
|
|
"description": "Outer wall-clock timeout override (seconds) for the llama.cpp reviewer lane. Unset is -1, a sentinel: 0 or a negative number is also treated as unset (a timeout has no legitimate zero/negative value), so no second sentinel is needed. Falls back to the lane's built-in timeoutFloorMs when unset."
|
|
}
|
|
}
|
|
}
|