Commit Graph
16 Commits
Author SHA1 Message Date
Drew Ritter b994fedcca fix(e2e): scope tmux cleanup to owned sessions
Replace deterministic shared tmux names and preemptive deletion with a readable run-unique name, an ownership bit set only after successful creation, and cleanup guarded by that ownership. A collision now fails closed: the runner chooses another unique name or reports failure and never reclassifies the existing session as stale.\n\nwriting-skills pressure evidence used three fresh subjects per arm with real sentinel sessions. RED was 0/3: every subject followed the old recipe by killing the pre-existing session, recreating the same name, and cleaning it again. GREEN was 3/3: every subject preserved the original session identity, created a distinct owned session, captured READY, and removed only the owned session. The controller independently verified original IDs $9, $10, and $11 before removing the disposable sentinels.
2026-08-06 14:57:57 -07:00
Drew Ritter 7dff0b2d48 fix(e2e): confine scenario card validation
Reuse the bounded fence filter for every scenario-card structural check so headings, coverage text, and falsification prose inside examples cannot satisfy the gate. Valid cards may still contain unrelated fenced examples.\n\nTreat each Card cell as a filename stem: remove at most one enclosing backtick pair, require lowercase kebab case, and reject invalid values before they can be stored or joined to the cards directory. This blocks parent traversal, subdirectories, uppercase names, and empty segments.\n\nAdd real-process RED/GREEN coverage for fenced-only cards, traversal, invalid stems, preserved backtick behavior, and the explicit diagnostic for intentionally unsupported pipe-less tables.
2026-08-06 14:50:46 -07:00
Drew Ritter 2a2e0b41c2 fix(e2e): reject fenced and malformed scenario tables
Filter backtick and tilde fenced examples before locating the E2E scenario-card table, so illustrative Markdown cannot satisfy the mechanical gate or shadow a later real table.\n\nParse only the documented leading/trailing-pipe row form and require a same-width delimiter row whose cells contain at least three hyphens with optional alignment colons. Missing or malformed delimiters now remain check failures instead of being silently treated as data.\n\nThe process-level harness records RED reproductions for both false-pass forms, fenced-only tables, and fenced examples before real tables, then verifies the focused GREEN behavior and prior contracts.
2026-08-06 14:49:13 -07:00
Jesse VincentandDrew Ritter 7fb15f0dd1 fix(skills): close checker false-pass on level-1 headings, tighten section matching 2026-07-19 15:17:52 -07:00
Jesse VincentandDrew Ritter fdc8310a29 feat(skills): add spec-derived card authoring recipe and routing 2026-07-19 15:16:56 -07:00
Jesse VincentandDrew Ritter 357d5028e0 fix(skills): scope card falsification match to the Expected section 2026-07-19 15:16:56 -07:00
Jesse VincentandDrew Ritter 688b560bd4 feat(skills): add spec-vs-cards checker with test harness 2026-07-19 15:16:56 -07:00
Jesse VincentandDrew Ritter a7cb9d495c fix(skills): use [DATE] placeholder in demo-movie end card
<date> inside the innerHTML string literal parses as an empty HTML
element in the browser rather than literal text if left unsubstituted.
Use the house bracket convention instead.
2026-07-19 15:16:55 -07:00
Jesse VincentandDrew Ritter d639609808 refactor(skills): finalize e2e rationalization table and red flags 2026-07-19 15:16:55 -07:00
Jesse VincentandDrew Ritter 2541ac5e9e feat(skills): add proof-movie and demo-movie evidence recipes 2026-07-19 15:16:55 -07:00
Jesse VincentandDrew Ritter b6276d097c docs(skills): name concrete macOS tools in the computer-use ladder 2026-07-19 15:16:55 -07:00
Jesse VincentandDrew Ritter f48daf84f7 feat(skills): add e2e desktop computer-use driving recipe 2026-07-19 15:16:55 -07:00
Jesse VincentandDrew Ritter caed843a72 fix(skills): restore interleaved sleeps in TUI form-fill recipe 2026-07-19 15:16:55 -07:00
Jesse VincentandDrew Ritter cb7b11ab2a feat(skills): add e2e browser and CLI/TUI driving recipes 2026-07-19 15:16:55 -07:00
Jesse VincentandDrew Ritter e3d65b5c31 feat(skills): add e2e verification-runner dispatch template 2026-07-19 15:16:55 -07:00
Jesse VincentandDrew Ritter 36d6aec57a feat(skills): add agentic-end-to-end-testing decision core 2026-07-19 15:16:55 -07:00