mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-02 06:54:50 +01:00
Garry Tanandcapy-ai[bot]
0cd2b4a9f9
* feat(eval-plan): require a no-gstack arm in every head-to-head preregistration Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(eval-plan): lint loadout arms by their model; refuse arms sharing a ledger attempt Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
34 lines
2.2 KiB
TypeScript
34 lines
2.2 KiB
TypeScript
/**
|
|
* Result codes for the /eval-plan preregistration (bin/gstack-eval-plan prereg
|
|
* --check, the priced pilot's arm list). Kept beside lib/result-codes.ts, which
|
|
* spreads this table into RESULT_CODES; the same rules apply: one stable
|
|
* docs/troubleshooting.md anchor, a summary and a fix clause each. The
|
|
* no-gstack arm rule is documented in docs/TESTING_INTERNALS.md#no-gstack-arm.
|
|
*/
|
|
import type { ResultCode } from './result-codes';
|
|
|
|
export const EVAL_RESULT_CODES = {
|
|
PREREG_INCOMPLETE: {
|
|
anchor: 'prereg-incomplete',
|
|
summary: 'the preregistration file lacks a required section, a section is empty, or the Comparison or Diagnostics declaration is malformed',
|
|
fix: 'fill every section `gstack-eval-plan prereg --check` names (bars, arms, comparison, decoys, stop rules, held-out exposure) before any priced call',
|
|
},
|
|
// Field list 2 (2026-10-16), W8: preregistered diagnostics run before the freeze commit.
|
|
PREREG_DIAGNOSTIC_UNTESTED: {
|
|
anchor: 'prereg-diagnostic-untested',
|
|
summary: 'the declared summarizer, run on the declared synthetic fixture, did not report every preregistered diagnostic at its expected count',
|
|
fix: 'fix the summarizer or the declared definition (expected count, fixture) until every PREREG_DIAGNOSTIC line says ok, then commit the freeze; never freeze a diagnostic the summarizer has not counted',
|
|
},
|
|
// Garry, 2026-10-31: "all of our head to head tests have to test no gstack from here".
|
|
PREREG_NO_GSTACK_ARM: {
|
|
anchor: 'prereg-no-gstack-arm',
|
|
summary: 'the Comparison says stack: loaded and the No-gstack arm section is missing, lacks a key, or does not give every model its own <model>#no-gstack Arms line',
|
|
fix: 'add `## No-gstack arm` with arms:, inputs:, prompt:, panel: and report:, and list each <model>#no-gstack arm under Arms; when no arm loads a skill stack, say stack: none with a why: line',
|
|
},
|
|
EVAL_ARM_DUPLICATE: {
|
|
anchor: 'eval-arm-duplicate',
|
|
summary: 'the pilot was given the same arm identity twice, so two arms would share one set of attempts',
|
|
fix: 'give each arm its own identity, <model> or <model>#<loadout> (for example claude-opus-5-5#no-gstack beside claude-opus-5-5); nothing was reserved',
|
|
},
|
|
} as const satisfies Record<string, ResultCode>;
|