1a46109b97
* feat(#1579): deterministic gsd-tools query eval.score verb Split C of #1573 (pure code, lowest risk). Adds an eval.score query verb (coverage*0.6 + infra*0.4; bands 80/60/40) mirroring the verify.* chain; gsd-eval-auditor consumes it instead of doing weighted arithmetic in-prompt. Non-breaking — additive only. arXiv: 2601.15130 (Plausibility Trap/DPDM), 2507.10281 (Table Agent), 2508.15754 (TIR). * fix(#1579): address review — domain guard, property test, glossary, SKIP_ROOT, inventory/baseline - C3 input-domain: reject out-of-domain eval.score (require 0<=covered<=total; was emitting overall_score>100 / negatives) - C1 property test: add tests/eval.property.test.cjs (fast-check) — determinism, band monotonicity, [0,100] bounds, never-throws - C2 glossary: CONTEXT.md "Eval Scoring Module" entry (source-of-truth path + interface) - C4: add `eval` to SKIP_ROOT_RESOLUTION (pure arithmetic; no .planning/ access) - inventory: register generated eval.cjs/eval-command-router.cjs (INVENTORY-MANIFEST.json + INVENTORY.md rows) - size: regen agent-size baseline for gsd-eval-auditor (reused gsd_run shim + eval.score step) - eslint: ignore generated eval*.cjs (ADR-457 bin/lib migration coverage) * fix(#1579): register eval family in alias-drift gates Add EVAL_COMMAND_ALIASES/EVAL_SUBCOMMANDS to scripts/check-alias-drift.cjs families and to familyArrayKeys in the manifest-coverage test, so the eval family lands under the same drift guard as every sibling family (state/verify/init/phase/phases/validate/roadmap). Addresses trek-e review. check:alias-drift ok; feat-3251 coverage 9/9; eval suites 10/10. * docs(#1579): use half-open verdict band ranges in CLI-TOOLS overall_score is fractional and thresholds are >=80/>=60/>=40, so a score in [79,80) is correctly NEEDS WORK despite the old '60-79' label. Relabel bands as 60-<80 / 40-<60 / 0-<40 to match the code. Addresses trek-e nit. * fix(#1579): validate eval.score CLI inputs Reject unknown infra tokens and fractional counts, and pin the 80-point verdict boundary including rounding-before-banding behavior.
36 lines
996 B
TypeScript
36 lines
996 B
TypeScript
/**
|
|
* Manifest-backed eval subcommand router (#10).
|
|
*/
|
|
|
|
import { EVAL_SUBCOMMANDS } from './command-aliases.cjs';
|
|
// eslint-disable-next-line @typescript-eslint/no-require-imports
|
|
import cjsCommandRouterAdapter = require('./cjs-command-router-adapter.cjs');
|
|
const { routeCjsCommandFamily } = cjsCommandRouterAdapter;
|
|
|
|
interface EvalModule {
|
|
cmdEvalScore(cwd: string, args: string[], raw: boolean): void;
|
|
}
|
|
|
|
interface RouteEvalCommandOptions {
|
|
evalMod: EvalModule;
|
|
args: string[];
|
|
cwd: string;
|
|
raw: boolean;
|
|
error: (message: string) => void;
|
|
}
|
|
|
|
function routeEvalCommand({ evalMod, args, cwd, raw, error }: RouteEvalCommandOptions): void {
|
|
routeCjsCommandFamily({
|
|
args,
|
|
subcommands: EVAL_SUBCOMMANDS,
|
|
unsupported: {},
|
|
error,
|
|
unknownMessage: (_s: string, available: string[]) => `Unknown eval subcommand. Available: ${available.join(', ')}`,
|
|
handlers: {
|
|
score: () => evalMod.cmdEvalScore(cwd, args, raw),
|
|
},
|
|
});
|
|
}
|
|
|
|
export = { routeEvalCommand };
|