mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-04 10:26:52 +02:00
test: clean up the paid eval lane (B1-B4, B6, B7)
- 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.
This commit is contained in:
1 parent
5d032ef299
commit
53e7f3212f
58 files changed
+273
-2594
No files matched your search
@@ -15,20 +15,32 @@
|
||||
* the re-entry mechanism.
|
||||
*/
|
||||
export const PERIODIC_CI_EXCLUDE: Record<string, { reason: string; tracking: string }> = {
|
||||
'test/skill-e2e-ship-idempotency.test.ts': {
|
||||
reason:
|
||||
'documented-red: the PTY child sits at the Claude Code welcome screen for the full budget '
|
||||
+ '(readiness/typing race vs CLI 2.1.x); never green since it was born in v1.63',
|
||||
tracking: 'TODOS.md "periodic tier — three documented-red tests need structural repair" (1 of 3 resolved: sidebar trio already deleted)',
|
||||
'test/codex-e2e.test.ts': {
|
||||
reason: 'the codex CLI is not installed in the CI image (Dockerfile.ci ships only claude-code); every case self-skips',
|
||||
tracking: 'TODOS.md "CI-unrunnable paid evals" (re-entry: the CLI/device is available in the CI image; review by 2026-12-28)',
|
||||
},
|
||||
'test/skill-e2e-brain-privacy-gate.test.ts': {
|
||||
reason:
|
||||
'documented-red: the artifacts-sync stop-gate preconditions do not survive the hermetic env '
|
||||
+ 'even with per-test HOME/GSTACK_HOME injection; never green anywhere',
|
||||
tracking: 'TODOS.md "periodic tier — three documented-red tests need structural repair"',
|
||||
'test/codex-e2e-sol-scope.test.ts': {
|
||||
reason: 'the codex CLI is not installed in the CI image (Dockerfile.ci ships only claude-code); every case self-skips',
|
||||
tracking: 'TODOS.md "CI-unrunnable paid evals" (re-entry: the CLI/device is available in the CI image; review by 2026-12-28)',
|
||||
},
|
||||
'test/skill-e2e-ios.test.ts': {
|
||||
reason: 'requires a live iOS device/simulator toolchain (xcodebuild, devicectl) — manual hardware, not a CI runner capability',
|
||||
tracking: 'TODOS.md "skill-e2e-ios CI story" (device/runner decision)',
|
||||
'test/codex-e2e-shared-libs.test.ts': {
|
||||
reason: 'the codex CLI is not installed in the CI image (Dockerfile.ci ships only claude-code); every case self-skips',
|
||||
tracking: 'TODOS.md "CI-unrunnable paid evals" (re-entry: the CLI/device is available in the CI image; review by 2026-12-28)',
|
||||
},
|
||||
'test/codex-e2e-recommendation-substance.test.ts': {
|
||||
reason: 'the codex CLI is not installed in the CI image (Dockerfile.ci ships only claude-code); every case self-skips',
|
||||
tracking: 'TODOS.md "CI-unrunnable paid evals" (re-entry: the CLI/device is available in the CI image; review by 2026-12-28)',
|
||||
},
|
||||
'test/skill-e2e-outside-voice.test.ts': {
|
||||
reason: 'needs both the claude and codex CLIs; codex is not in the CI image, so every case self-skips',
|
||||
tracking: 'TODOS.md "CI-unrunnable paid evals" (re-entry: the CLI/device is available in the CI image; review by 2026-12-28)',
|
||||
},
|
||||
'test/skill-e2e-aside.test.ts': {
|
||||
reason: 'needs macOS with the Aside app open (asideAvailable()); CI runners are Linux, so every case self-skips',
|
||||
tracking: 'TODOS.md "CI-unrunnable paid evals" (re-entry: the CLI/device is available in the CI image; review by 2026-12-28)',
|
||||
},
|
||||
'test/skill-e2e-ios-device.test.ts': {
|
||||
reason: 'needs a physical iPhone over USB/devicectl — manual hardware, not a CI runner capability',
|
||||
tracking: 'TODOS.md "CI-unrunnable paid evals" (re-entry: the CLI/device is available in the CI image; review by 2026-12-28)',
|
||||
},
|
||||
};
|
||||
Reference in new issue
Block a user