62b0d939b6
* feat(#3274): make reviewer-lane timeout configurable via timeoutConfigKey Add an optional `timeoutConfigKey` field to the reviewer lane descriptor, resolved in `resolveLanePlan` at invocation time and falling back to the frozen `timeoutFloorMs` when unset or invalid, in the same spirit as the existing `promptBudgetKey`/`modelConfigKey` fields. All 12 shipped lanes declare `review.timeouts.<slug>` on both surfaces (the descriptor and their capability.json manifest), validated by capability-validator.cjs. For the antigravity lane, the native `agy --print-timeout` flag — previously a second hardcoded literal (`540s`) independent of the outer cap — is now derived from the same resolved outer timeout in `antigravityArgv`, preserving the existing 60-second buffer relationship (ADR-2782 D6: the outer bound is declared data, the inner one is handler-owned). The antigravity default timeoutFloorMs stays at 600s per the maintainer's disposition; users raise it through the new config key instead. * docs(#3274): document review.timeouts.* and extract resolveTimeoutMs helper Address code-review findings on the timeoutConfigKey change: extract the inline timeout-resolution logic into a named, exported, directly-tested resolveTimeoutMs helper (matching the file's existing configString/ normalizeHost convention); document the new review.timeouts.* federated config keys in docs/CONFIGURATION.md, docs/reference/capability-manifest.md, and docs/how-to/ship-a-reviewer-lane.md; add the changeset fragment. * fix(#3274): resolve native antigravity timeout in resolveLanePlan, not the runner gsd-test caught two design mistakes in the prior commits: 1. SpawnPlan.argv is documented and tested as fully resolved by resolveLanePlan (model/effort/output/prompt already folded in) — leaving the antigravity '{{nativeTimeout}}' marker unresolved until the runner's antigravityArgv violated that contract and broke tests that read plan.argv directly (tests/antigravity-reviewer.test.cjs, tests/review-default-reviewers-workflow.test.cjs). Fix: '{{nativeTimeout}}' is now a fifth ARGV_PLACEHOLDER member, resolved by resolveLanePlan itself via the new nativeTimeoutToken() helper, exactly like the other four. antigravityArgv reverts to its pre-#3274 four-argument form. Also missed updating capabilities/antigravity/capability.json's invoke.args to match the descriptor, which broke the manifest/descriptor parity test. 2. tests/reviewer-config-federation.test.cjs enforces a deliberate, narrow invariant (#3691 narrows #2797): qwen, cursor, and coderabbit — the three lanes with neither a model flag nor a host — may own no config key beyond their own prompt-budget key. Adding review.timeouts.<slug> to all 12 lanes violated it. Fix: those three keep timeoutConfigKey: null and own no review.timeouts.* key, matching their existing modelConfigKey: null. The other 9 lanes are unaffected. * chore(#3274): backfill changeset PR number (pr:0 -> 4083) --------- Co-authored-by: sim <sim@local>
65 lines
2.7 KiB
JSON
65 lines
2.7 KiB
JSON
{
|
|
"id": "llama-cpp",
|
|
"role": "reviewer",
|
|
"version": "1.12.0",
|
|
"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",
|
|
"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."
|
|
}
|
|
}
|
|
}
|