cc-os/plugins/os-adr/eval-b/fixture/project/docs/adr
jared 00e22f1676 Add os-adr evaluation harnesses (Eval A and Eval B)
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(Superseded pair + distractors), headless runner (isolated SessionStart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.
2026-07-03 16:44:42 -04:00
..
0001-retry-failed-deliveries-a-fixed-three-times.md Add os-adr evaluation harnesses (Eval A and Eval B) 2026-07-03 16:44:42 -04:00
0002-route-all-outbound-http-through-the-shared-httpclient.md Add os-adr evaluation harnesses (Eval A and Eval B) 2026-07-03 16:44:42 -04:00
0003-retry-failed-deliveries-with-exponential-backoff-capped-at-five-attempts.md Add os-adr evaluation harnesses (Eval A and Eval B) 2026-07-03 16:44:42 -04:00
0004-cap-outbound-http-timeouts-at-five-seconds.md Add os-adr evaluation harnesses (Eval A and Eval B) 2026-07-03 16:44:42 -04:00
0005-record-event-times-as-utc-iso-8601-strings.md Add os-adr evaluation harnesses (Eval A and Eval B) 2026-07-03 16:44:42 -04:00
0006-dead-letter-deliveries-that-exhaust-retries-to-a-jsonl-file.md Add os-adr evaluation harnesses (Eval A and Eval B) 2026-07-03 16:44:42 -04:00
README.md Add os-adr evaluation harnesses (Eval A and Eval B) 2026-07-03 16:44:42 -04:00

README.md

Architecture Decision Records

One file per decision, NNNN-kebab-title.md, created via /os-adr:create.

ID Title Status Date
0001 Retry failed deliveries a fixed three times Superseded 2026-02-10
0002 Route all outbound HTTP through the shared HttpClient Accepted 2026-02-18
0003 Retry failed deliveries with exponential backoff, capped at five attempts Accepted 2026-03-05
0004 Cap outbound HTTP timeouts at five seconds Accepted 2026-03-12
0005 Record event times as UTC ISO-8601 strings Accepted 2026-04-02
0006 Dead-letter deliveries that exhaust retries to a JSONL file Accepted 2026-04-20