fix: restore libSQL vector search with dynamic dimensions (#1393)

* fix: restore libSQL vector search with dynamic embedding dimensions (#655)

The V9 migration dropped the libsql_vector_idx and changed
memory_chunks.embedding from F32_BLOB(1536) to BLOB, but the
documented brute-force cosine fallback was never implemented.
hybrid_search silently returned empty vector results — search was
FTS5-only on libSQL.

Add ensure_vector_index() which dynamically creates the vector index
with the correct F32_BLOB(N) dimension, inferred from EMBEDDING_DIMENSION
/ EMBEDDING_MODEL env vars during run_migrations(). Uses _migrations
version=0 as a metadata row to track the current dimension (no-op if
unchanged, rebuilds table on dimension change).

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* style: move safety comments above multi-line assertions for rustfmt stability

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* refactor: remove unnecessary safety comments from test code

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: address review comments from PR #1393 [skip-regression-check]

- Share model→dimension mapping via config::embeddings::default_dimension_for_model()
  instead of duplicating the match table (zmanian, Copilot)
- Add dimension bounds check (1..=65536) to prevent overflow (zmanian, Copilot)
- DROP stale memory_chunks_new before CREATE to handle crashed previous attempts
  (zmanian, Copilot)
- Use plain INSERT instead of INSERT OR IGNORE to surface constraint errors
  (Copilot)

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: add missing builder field to AgentDeps in telegram routing test [skip-regression-check]

The self-repair builder field was added to AgentDeps in #712 but this
test was not updated.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: address zmanian's second review on PR #1393

- Add tracing::info when resolve_embedding_dimension returns None (#2)
- Document connection scoping for transaction safety (#1)
- Document _rowid preservation for FTS5 consistency (#4)
- Document precondition that migrations must run first (#5)
- Note F32_BLOB dimension enforcement in insert_chunk (#3)
- Add unit tests for resolve_embedding_dimension (#6)

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
This commit is contained in:
Illia Polosukhin
2026-03-19 20:51:37 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 8920322589
commit 8526cde1be
7 changed files with 494 additions and 20 deletions
+1 -1
View File
@@ -57,7 +57,7 @@ impl Default for EmbeddingsConfig {
/// Infer the embedding dimension from a well-known model name.
///
/// Falls back to 1536 (OpenAI text-embedding-3-small default) for unknown models.
fn default_dimension_for_model(model: &str) -> usize {
pub(crate) fn default_dimension_for_model(model: &str) -> usize {
match model {
"text-embedding-3-small" => 1536,
"text-embedding-3-large" => 3072,
+1 -1
View File
@@ -9,7 +9,7 @@ mod agent;
mod builder;
mod channels;
mod database;
mod embeddings;
pub(crate) mod embeddings;
mod heartbeat;
pub(crate) mod helpers;
mod hygiene;