2 Commits

Author SHA1 Message Date
Trevin Chow 68ae74ff4f docs: capture eval-not-in-CI design decision under docs/solutions/
Closes #374 (adapted, not 1:1 merged).

@hnshah opened PR #374 proposing a docs/adr/ directory for architecture
decision records. The intent is right -- the "why is search-quality eval
manual?" reasoning drifts out of memory if it isn't written down -- but
the docs/adr/ convention doesn't fit alongside the existing
docs/solutions/ structure (compound-engineering ce-compound pattern with
frontmatter metadata, additive entries, no membership-contract test).

This commit adopts hnshah's ADR 002 content (search-quality eval is
manual by default) as a docs/solutions/architecture/ entry with the
canonical compound-style frontmatter (module, problem_type, applies_when,
related_components, tags). Drops the docs/adr/ directory pattern, the
README index, and the test_adr_docs.py contract test.

ADR 001 (multi-surface packaging) is intentionally not adopted here: it
referenced sync.sh as the deploy mechanism, but sync.sh was removed in
PR #405 in favor of `npx skills add . -g -y`. The multi-surface
packaging story is still real but has moved beyond what the original
ADR captured; a fresh "how we ship to multiple harnesses" entry would
make sense as a separate doc.

Co-authored-by: hnshah <hnshah@users.noreply.github.com>
2026-05-16 22:22:59 -07:00
Trevin Chow 0fd532d249 docs: compound learning on release-time consistency-test cascade failures
Documents the cascade pattern surfaced during this session's install-modernization
arc: a `test_sync_cache_path_uses_skill_version` test asserted that a hardcoded
version pin in `sync.sh` matched the version frontmatter in SKILL.md. When a
release bumped SKILL.md, every open PR's CI failed simultaneously on the
unrelated stale-pin assertion. Affected at least 5 PRs across the 2026-05-13
to 2026-05-15 window (#400, #390, #392, and two others) plus required hotfix
PR #397 to unblock the queue.

The permanent fix shipped in PR #405 (deleted sync.sh + the test). This doc
captures the design lesson so the pattern doesn't reappear: don't write
consistency tests that read two files and assert one matches a value derived
from the other. Either derive at runtime from a single source of truth, or
self-skip / merge-base-scope the test so deletion is a non-event.

Created via /ce-compound. Includes:

- docs/solutions/workflow-issues/release-consistency-test-cascade-2026-05-16.md
  (the new learning — first entry under docs/solutions/)
- CONCEPTS.md (new — 4 entries: Skill, Engine, Harness, Beta channel,
  capturing project-specific vocabulary that surfaced across the session)
- AGENTS.md (added one-line Structure entries surfacing docs/solutions/ and
  CONCEPTS.md so fresh agents discover them)
- docs/plans/2026-04-22-{002,003,005,006}-*-plan.md (added deprecation banner
  to each, pointing readers at PR #405 and the new docs/solutions entry —
  these 4 historical plans still reference the deleted sync.sh inline)

Also: closed PR #379 (j-sperling's workaround for the same cascade,
superseded by PR #405's permanent fix).
2026-05-16 19:08:02 -07:00