mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-02 17:40:02 +02:00
garrytan
53e7f3212f
- B1: delete paid files that assert nothing or cannot pass meaningfully: skill-llm-eval-spec and skill-e2e-spec-execute (test.todo), gemini-e2e (+ gemini-session-runner; no gemini CLI in CI), ship-idempotency (red since v1.63), the two opus-4-7 *-sonnet overlay wrappers, conductor-prose (+ its source-evaluation replay), codex-e2e-plan-format; drop their keys, scripts and census rows. - B2: skill-llm-eval grades browse/sections/command-list.md with one union judge that also carries the baseline score pin; regression-vs-baseline deleted (paid run: pass, c4/c4/a4). - B3: memory-pipeline, ios-qa, ios-qa-swift-build and plan-tune-cathedral make no model calls; renamed out of the paid glob so they run on every PR. Swift builds need GSTACK_TEST_SWIFT=1; device stub deleted. - B4: codex-e2e*, outside-voice, aside and ios-device cannot run in the CI image; excluded from the weekly lane with a tracked re-entry condition. - B6: fold opus-47's negative routing controls into skill-routing-e2e journey-negatives (paid run: 3/3 unrouted) and delete the file. - B7: delete the never-green brain-privacy-gate eval; a free gstack-skill-start test now proves consent precedes artifacts egress.
25 lines
1.3 KiB
TypeScript
25 lines
1.3 KiB
TypeScript
/** Version 2 gates supported behavior; comparative efficacy stays research-only.
|
|
* Version 1 required efficacy lift. Never reinterpret its recorded failures.
|
|
*/
|
|
export const OVERLAY_CONTRACT = {
|
|
name: 'overlay-behavior',
|
|
version: 2,
|
|
releaseGate: 'execution_scope_complete_sampling_and_on_correctness',
|
|
comparisonRole: 'research_only',
|
|
resourceNonRegression: 'not_established',
|
|
} as const;
|
|
|
|
/** A complete fixture owns a process; model-work budgets are unchanged. */
|
|
export const OVERLAY_CASE_WORK_MS = 1_800_000;
|
|
export const OVERLAY_RECORD_GRACE_MS = 5_000;
|
|
export const OVERLAY_CASE_OUTER_MS = OVERLAY_CASE_WORK_MS + 10_000;
|
|
export const OVERLAY_MIN_FILE_WALL_MS = OVERLAY_CASE_WORK_MS + 30_000;
|
|
|
|
/** Canonical wrapper census. Runner integration must serialize these files. */
|
|
export const OVERLAY_CASE_FILES: Record<string, string> = {
|
|
'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash.test.ts': 'claude-dedicated-tools-vs-bash',
|
|
'test/skill-e2e-overlay-harness-opus-4-7-effort-match-trivial.test.ts': 'opus-4-7-effort-match-trivial',
|
|
'test/skill-e2e-overlay-harness-opus-4-7-literal-interpretation.test.ts': 'opus-4-7-literal-interpretation',
|
|
'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-sonnet.test.ts': 'claude-dedicated-tools-vs-bash-sonnet',
|
|
};
|