Eval B wording reached 8/8 (sonnet) / 7/8 (haiku) on its run-set after five iterations; subsequent W3 stability testing confirmed intermittent flicker but acceptable performance. As Eval B is now contaminated by iteration, we need a held-out measurement set to assess generalization to new projects and cues. Eval C measures whether learned behavior generalizes across decreasing cue explicitness (explicit → moderate → conceptual framing) and, critically, whether the model correctly avoids false positives (over-triggering) when no Accepted ADR is in play. Six paired scenarios (positive/negative at each level) run against a job-execution domain fixture; a frozen reserve-set (notifications domain) becomes the measurement set if anyone tunes wording against the run-set. New: `plugins/os-adr/eval-c/` — bin/ (run/check/self-test/sandbox scripts), fixture/ (taskq async job queue, 6 ADRs, trigger-phrased CLAUDE.md), scenarios/ (6 run-set), scenarios-reserve/ (6 reserve- set), README.md (measurement discipline + design), judge-rubric.md. Model-free self-test passing. First real grid run is a pending decision. |
||
|---|---|---|
| .. | ||
| docs/adr | ||
| taskq | ||
| .gitignore | ||
| .graphifyignore | ||
| CLAUDE.md | ||
| README.md | ||
README.md
Task Queue — async job queue system
A small Python async job queue for reliable job processing.
Architecture decisions
This project records architecture decisions as ADRs in docs/adr/ (index: docs/adr/README.md).
- When your task involves making an architecture-level choice, or changing/replacing an
approach this codebase already uses (job execution, persistence, notifications) →
first run
/os-adr:findto check whether a recorded decision already covers it. - Mechanical rule: before your first edit to any existing source or config file, run
/os-adr:findon the paths you are about to touch — one cheap, deterministic CLI call. This applies to additions too. - When you make such a choice → record it with
/os-adr:create. - If an Accepted ADR covers the approach you are changing, you are reversing a recorded
decision. A task that reverses a recorded decision is not complete until the superseding
ADR is created — implementing the change and stopping leaves
docs/adr/asserting the opposite of what the code does.