Build comprehensive evaluation framework for the os-adr plugin (ADR-021). Eval A: prompted skill-execution evaluation across haiku/sonnet models. Six ADR lifecycle scenarios, deterministic Ruby checker, sandbox runner, /autoresearch loop for wording optimization. Eval B: held-out unprompted-behavior evaluation. Seven scenarios (W1–W3 write-trigger, R1–R4 retrieval), webhook fixture with 6-ADR history (Superseded pair + distractors), headless runner (isolated SessionStart context), two-axis deterministic-first checker (consultation + citation accuracy, AI judge fallback for new-file writes). Both harnesses self-tested model-free. Grid runs deferred per locked rollout order. Updated docs/specs to freeze scenario shapes and document methodologies. |
||
|---|---|---|
| .. | ||
| bin | ||
| config | ||
| docs/adr | ||
| lib | ||
| .gitignore | ||
| .graphifyignore | ||
| README.md | ||
README.md
relay
A small CLI that delivers webhook payloads to configured endpoints and reports on delivery outcomes.
bin/relay send <url> <json-payload>— queue and deliver one payloadbin/relay report— summarize failed deliveries
Configuration lives in config/relay.yml. Failed deliveries that exhaust
their retries are appended to the dead-letter file for manual replay.
Architecture decisions are recorded in docs/adr/.