Record first real-LLM lifecycle baseline#264
Merged
CalebisGross merged 1 commit intomainfrom Mar 20, 2026
Merged
Conversation
First end-to-end lifecycle test run with gemini-3-flash-preview and gemini-embedding-2-preview (3072-dim embeddings). Results: 8/8 phases PASS, 23/23 assertions, ~70 min total. Key findings: - 115 unique memories from 862 raw (87% dedup rate) - 704 associations, 4 patterns, 4 abstractions - Retrieval avg 758ms latency, 4.8 results/query - Consolidation correctly separates signal from noise - FTS5 scan column mismatch discovered (pre-existing bug) Also adds FTS5 bug to Known Issues in CLAUDE.md and renumbers experiment registry baselines. Closes #262 Co-Authored-By: Claude Opus 4.6 (1M context) <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Results
8/8 phases PASS, 23/23 assertions, ~70 min total with gemini-3-flash-preview + gemini-embedding-2-preview (3072-dim).
Bug found
FTS5 scan column mismatch: SearchByFullText fails with "sql: expected 19 destination arguments in Scan, not 21". Pre-existing — memories table has 2 new columns not in the FTS scan query. Retrieval falls back to embedding search.
Test plan
Closes #262