docs(eval): SMI-4764 Wave 4 Step 3 — README Baseline Lifecycle reflects automation#1029
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
📊 Retrieval Eval — recall@5 deltasOverall: 0.4182 → 0.4182 (Δ +0.0000, +0.00%)
Repro locally: Generated by |
E2E Test ResultsE2E Test Results - May 8, 2026Summary
Test Results
Generated by skillsmith E2E test suite |
…ts automation Updates packages/doc-retrieval-mcp/eval/README.md "Baseline Lifecycle" section to describe the post-automation flow that Waves 0-3 introduced: - Step 4: pre-push validator (Wave 0) replaces the legacy manual "developer must run real-mode locally and commit the updated baseline" language. Canonical mode rejects, advisory mode warns. - New Step 5: weekly cron (Wave 2) Sunday 03:00 local on canonical dev's machine; auto-PR on drift; heartbeat tracked; audit check 44 watches freshness. - New Step 6: CI gate (Wave 3) sticky comment with per-category recall@5 deltas + audit check 45 advisory provenance annotation. Also bumps docs/internal pointer to include the Wave 4 implementation plan at docs/internal/implementation/smi-4764-wave-4-implementation.md. Rebased onto origin/main via git plumbing (no checkout) to avoid parallel-session smudge-filter branch hijacks. Parent: origin/main (9aea126). docs/internal: ff516edf (rebased Wave 4 plan branch). Co-Authored-By: claude-flow <ruv@ruv.net> Co-Authored-By: Claude <noreply@anthropic.com>
wrsmith108
force-pushed
the
feat/smi-4764-w4-step3-docs-v2
branch
from
c0f5648 to
df12b36
Compare
E2E Test ResultsE2E Test Results - May 8, 2026Summary
Test Results
Generated by skillsmith E2E test suite |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Wave 4 Step 3 doc update. Replaces the legacy "developer must run real-mode locally and commit the updated baseline" copy in
packages/doc-retrieval-mcp/eval/README.mdBaseline Lifecycle section with a 6-step automated flow that reflects what Waves 0-3 actually delivered:Also bumps
docs/internalpointer to include the Wave 4 implementation plan atdocs/internal/implementation/smi-4764-wave-4-implementation.md.Out of scope
.cron-heartbeat; check 44 reports freshness automatically.Operational note
This branch was created via
git push <commit>:refs/heads/<branch>(direct ref push) after two consecutive smudge-filter branch hijacks during local commit (commitc0f5648afirst landed onchore/smi-4779-pr-staleness-watcher, then onfix/smi-4808-quota-monitor-window-180). Both hijacked branches were restored to their prior HEAD (fb4aa835) locally; the commit reached remote via direct ref push so no local checkout of the feature branch was needed. SMI-2536 / SMI-4782 smudge-filter pattern.Push uses
--no-verifyper CLAUDE.md SMI-4767/4769 host vitest leak workaround.Test plan
[skip-impl-check]
🤖 Generated with Ruflo