Commit Graph

24 Commits

Author SHA1 Message Date
Peter Steinberger
6fc564278d feat(agents): sessions_search full-text recall over past session transcripts (#105057)
Adds a core sessions_search agent tool backed by a SQLite FTS5 index that
lives next to the transcript rows in the per-agent database. Indexing is
transactional: user/assistant text is indexed inside the same write
transaction that persists the event, deletes drop index rows in the same
transaction, and branch rewinds mark the session dirty so the next search
rebuilds it from the same visible-path resolution sessions_history uses
(which also lazily backfills doctor-migrated databases). Search executes
gateway-side behind an additive sessions.search method with a bounded
session-key allowlist; visibility, sandbox restrictions, and snippet
redaction mirror sessions_history.

Closes #100978
2026-07-12 09:15:41 +01:00
Peter Steinberger
e9b7a9a912 fix(memory): search by filenames and paths (#104449)
Co-authored-by: Pick-cat <huang.ting3@xydigit.com>
2026-07-11 10:54:34 -07:00
Peter Steinberger
f7d7148cf0 docs: rewrite published docs grounded in current source (#100142)
Source-grounded rewrite of 529 published docs pages with per-unit information-loss verification: 1,713 factual corrections cited to src/**, generated surfaces regenerated, frontmatter titles preserved for i18n, release notes pages untouched. All docs gates green.

Closes #100141
2026-07-05 00:32:47 -04:00
JC
78029e43d2 fix(doctor): warn and document QMD session recall gates (#80947)
* Warn on QMD session recall export mismatch

* Clarify session transcript recall gates
2026-06-28 13:55:27 -07:00
Onur Solmaz
3137110167 fix(memory): move local llama.cpp runtime to provider plugin
* fix(memory): move local llama.cpp runtime to provider plugin

* chore: ignore llama cpp dynamic dependency

* test: remove invalid local provider alias fixture

* chore: refresh llama cpp shrinkwrap

* chore: drop stale memory embedding defaults facade
2026-06-09 14:30:35 +08:00
Onur Solmaz
0aea58ab66 fix(memory): fail fast when embeddings provider is unavailable
Fixes #89691.

Memory search now treats explicitly configured non-local embedding providers as required. When that provider is unavailable, search and sync surface an unavailable memory-search result instead of silently returning FTS-only recall.

Unset/default/local/none-style paths keep FTS fallback so existing workflows do not lose keyword recall entirely. The fallback state is now surfaced in diagnostics/status instead of being hidden.

Maintainer merge note: current CI still has unrelated baseline boundary failures in extensions/google/google.live.test.ts and extensions/minimax/minimax.live.test.ts. This PR does not touch those files; the PR-specific memory, docs, lint, type, security, and ClawSweeper checks were reviewed before merge.
2026-06-06 20:39:38 +08:00
Bob
4d89e00c50 feat(embeddings): add OpenAI-compatible core provider (#85269)
Merged via squash.

Prepared head SHA: dc9a5d5397
Co-authored-by: dutifulbob <261991368+dutifulbob@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-05-27 14:37:17 +02:00
Peter Steinberger
ed8f50f240 refactor: simplify plugin dependency handling
Simplify plugin installation and runtime loading around package-manager-owned dependencies, with Jiti reserved for local/TS fallback paths.

Also scans npm plugin install roots so hoisted transitive dependencies are covered by dependency denylist and node_modules symlink checks.
2026-05-01 21:32:22 +01:00
Peter Steinberger
ac599c9e53 fix: retain local memory runtime deps 2026-04-30 15:22:26 +01:00
Peter Steinberger
a0a0ab4d9e fix(memory): resolve custom embedding provider ids 2026-04-28 03:11:19 +01:00
Peter Steinberger
775ed36c16 feat(memory): support asymmetric embedding input types 2026-04-27 11:25:40 +01:00
Peter Steinberger
956cb1c7db fix: keep local embedding batches from flooding providers 2026-04-26 00:11:35 +01:00
Vincent Koc
9895ecead3 fix(memory): keep llama runtime optional (#71425)
* fix(memory): keep llama runtime optional

* fix(memory): harden optional llama runtime guard
2026-04-25 00:09:12 -07:00
Vincent Koc
367b9721b6 docs(concepts,automation,plugins): add Related sections to pages missing them 2026-04-23 15:48:46 -07:00
Vincent Koc
c5c163d078 docs: standardize frontmatter field order (summary before title) 2026-04-23 13:18:17 -07:00
Vincent Koc
2777b089b5 docs: normalize frontmatter titles to sentence case 2026-04-23 13:15:17 -07:00
Vincent Koc
4a2cd533ac docs: remove duplicate H1 where frontmatter title already sets it 2026-04-23 13:11:14 -07:00
Pengfei Ni
88d3620a85 feat(github-copilot): add embedding provider for memory search (#61718)
Merged via squash.

Prepared head SHA: 05a78ce7f2
Co-authored-by: feiskyer <676637+feiskyer@users.noreply.github.com>
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Reviewed-by: @vincentkoc
2026-04-15 10:39:28 +01:00
Anonymous Amit
42590106ab improve memory fallback lexical ranking (#65395)
* improve memory fallback lexical ranking

* use neutral lexical fallback fixtures

* fix(memory-core): keep lexical boosts out of hybrid search

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-04-12 18:36:28 +01:00
Tak Hoffman
b83726d13e Feat: Add Active Memory recall plugin (#63286)
* Refine plugin debug plumbing

* Tighten plugin debug handling

* Reduce active memory overhead

* Abort active memory sidecar on timeout

* Rename active memory blocking subagent wording

* Fix active memory cache and recall selection

* Preserve active memory session scope

* Sanitize recalled context before retrieval

* Add active memory changelog entry

* Harden active memory debug and transcript handling

* Add active memory policy config

* Raise active memory timeout default

* Keep usage footer on primary reply

* Clear stale active memory status lines

* Match legacy active memory status prefixes

* Preserve numeric active memory bullets

* Reuse canonical session keys for active memory

* Let active memory subagent decide relevance

* Refine active memory plugin summary flow

* Fix active memory main-session DM detection

* Trim active memory summaries at word boundaries

* Add active memory prompt styles

* Fix active memory stale status cleanup

* Rename active memory subagent wording

* Add active memory prompt and thinking overrides

* Remove active memory legacy status compat

* Resolve active memory session id status

* Add active memory session toggle

* Add active memory global toggle

* Fix active memory toggle state handling

* Harden active memory transcript persistence

* Fix active memory chat type gating

* Scope active memory transcripts by agent

* Show plugin debug before replies
2026-04-09 11:27:37 -05:00
wirjo
699b2320a8 feat(memory): add Bedrock embedding provider for memory search (#61547)
* feat(memory): add Bedrock embedding provider for memory search

Add Amazon Bedrock as a native embedding provider for memory search.
Supports Titan Embed Text v1/v2 and Cohere Embed models via AWS SDK.

- New embeddings-bedrock.ts: BedrockRuntimeClient + InvokeModel
- Auth via AWS default credential chain (same as Bedrock inference)
- Auto-selected in 'auto' mode when AWS credentials are detected
- Titan V2: configurable dimensions (256/512/1024), normalization
- Cohere: native batch support with search_query/search_document types
- 16 new tests covering all model types, auth detection, edge cases

Closes #26289

* fix(memory): harden bedrock embedding selection

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-04-06 01:19:56 +01:00
Vincent Koc
c9eb31382e docs: add dedicated memory engine pages, replace ASCII diagram with Mermaid 2026-03-30 07:34:14 +09:00
Vincent Koc
143b4c54ba docs: simplify sessions/memory concept pages and fix QMD experimental label 2026-03-30 07:32:20 +09:00
Vincent Koc
3584a893e8 docs: rewrite sessions/memory section -- compaction, memory, and new memory-search page 2026-03-30 07:10:01 +09:00