feat(query): gate LIP semantic rerank on !MixedModels#208
Merged
Conversation
When the LIP index contains vectors from more than one embedding model (e.g. during a partial re-index after a model upgrade), cosine similarity across those vector spaces is mathematically meaningless. The MixedModels flag was already surfaced in `ckb doctor` but no query path consumed it — so RerankWithLIP and SemanticSearchWithLIP silently ranked on garbage. Adds a cached health check on Engine (60 s TTL) that short-circuits both semantic call sites when the daemon reports MixedModels, falling back to pure lexical ranking. Surfaces the state via a `lip_mixed_models` DegradationWarning so users learn why semantic ranking is inactive. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
🟢 Change Impact Analysis
Blast Radius: 0 modules, 0 files, 0 unique callers 📝 Changed Symbols (4)
Recommendations
Generated by CKB |
NFR Tests ✅ 39 unchangedComparing PR against main branch (dynamic baseline). Regressions: 0 ✅ Thresholds: WARN ≥ +5% • FAIL ≥ +10% All scenarios
* = new scenario, compared against static baseline |
CKB Analysis
Risk factors: Touches 1 hotspot(s) 👥 Suggested: @lisa.welsch1985@gmail.com (100%), @talantyyr@gmail.com (40%), @lisa@tastehub.io (40%)
🎯 Change Impact Analysis · 🟢 LOW · 4 changed → 0 affected
Symbols changed in this PR:
Recommendations:
💣 Blast radius · 0 symbols · 1 tests · 0 consumersTests that may break:
🔥 Hotspots · 1 volatile files
📊 Complexity · 1 violations
💡 Quick wins · 10 suggestions
📚 Stale docs · 197 broken references
Generated by CKB · Run details |
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #208 +/- ##
=====================================
Coverage 43.0% 43.0%
=====================================
Files 525 526 +1
Lines 81073 81101 +28
=====================================
+ Hits 34896 34935 +39
+ Misses 43709 43702 -7
+ Partials 2468 2464 -4
Flags with carried forward coverage won't be shown. Click here to find out more. 📢 Thoughts on this report? Let us know! 🚀 New features to boost your workflow:
|
|
CKB review failed to generate output. |
SimplyLiz
added a commit
that referenced
this pull request
Apr 15, 2026
CKB used to re-probe IndexStatus on a 60 s TTL every time the rerank path checked whether the LIP index was mixed-models. The LIP daemon has pushed IndexChanged frames to all active sessions since v1.5.0, so the polling was pure debt. New internal/lip/subscribe.go opens a long-lived connection, pings IndexStatus every 3 s to flush the daemon's broadcast channel (the session loop drains queued pushes only after writing a response), reads every frame in a loop, and routes index_changed and index_status by type tag. Reconnects with exponential backoff to 30 s on daemon drop. Engine owns one subscriber, started in NewEngine and cancelled in Close. The cached availability/mixed flags are now written by the subscriber, not the query path — lipSemanticAvailable is lock-free RLock+read, no RPC. Worst-case staleness for the rerank gate drops from 60 s to ~3 s. Tests rewritten: the fake daemon now serves multiple requests per connection and tests wait for the first health frame before asserting, plus a new TestLipSubscriber_ReusesSingleConnection verifies the hot path issues zero requests. Also: CHANGELOG entries for #208 and #209 which landed on develop without one. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
6 tasks
SimplyLiz
added a commit
that referenced
this pull request
Apr 15, 2026
* feat(lip): push-driven health via long-lived subscribe CKB used to re-probe IndexStatus on a 60 s TTL every time the rerank path checked whether the LIP index was mixed-models. The LIP daemon has pushed IndexChanged frames to all active sessions since v1.5.0, so the polling was pure debt. New internal/lip/subscribe.go opens a long-lived connection, pings IndexStatus every 3 s to flush the daemon's broadcast channel (the session loop drains queued pushes only after writing a response), reads every frame in a loop, and routes index_changed and index_status by type tag. Reconnects with exponential backoff to 30 s on daemon drop. Engine owns one subscriber, started in NewEngine and cancelled in Close. The cached availability/mixed flags are now written by the subscriber, not the query path — lipSemanticAvailable is lock-free RLock+read, no RPC. Worst-case staleness for the rerank gate drops from 60 s to ~3 s. Tests rewritten: the fake daemon now serves multiple requests per connection and tests wait for the first health frame before asserting, plus a new TestLipSubscriber_ReusesSingleConnection verifies the hot path issues zero requests. Also: CHANGELOG entries for #208 and #209 which landed on develop without one. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: drop stray cmd/ckb-bench/version_test.go Had a package-level init() that printed cartographer version on import under the cartographer build tag — not a test, and leaked output into unrelated test runs when the tag was enabled. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
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
Engine.lipSemanticAvailable()— a 60 s TTL-cached probe oflip.IndexStatus()— and gates both semantic call sites insearchSymbols(SemanticSearchWithLIPfallback atsymbols.go:519,RerankWithLIPat:646) behind it. Mixed-model state → pure lexical fallback.lip_mixed_modelsDegradationWarning(capability 70%) so users learn why semantic ranking is inactive instead of quietly getting worse results.No change to the
internal/lipclient, the LIP daemon protocol, or the rerank function signatures — the gate is entirely on theEngineside.Test plan
go test ./internal/query/... -run 'TestLipSemanticAvailable|TestGetDegradationWarnings' -v— 6 new tests covering healthy, mixed, daemon-down, TTL-cache, warning-emitted, and no-warning-before-first-probe.go test ./internal/query/...— full package suite still passes.go build ./...clean.gofmtclean.ckb doctoragainst a real LIP daemon — confirm MixedModels reporting unchanged.searchSymbolswith single-model index (rerank fires) vs. induced mixed-model index (rerank skipped, warning present in response metadata).🤖 Generated with Claude Code