Commit Graph

291 Commits

Author SHA1 Message Date
Vincent Koc 098f4eeebb fix(memory-qmd): restore qmd compatibility defaults 2026-04-06 01:31:51 +01:00
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
Vignesh Natarajan 61e61ccc18
Dreaming: simplify sweep flow and add diary surface 2026-04-05 17:18:54 -07:00
Vincent Koc a9dbaa1124 fix(memory): standardize DREAMS trail path 2026-04-05 23:35:44 +01:00
Vincent Koc 367f52f483 docs(memory): point dreaming trail docs to dreams.md 2026-04-05 23:35:44 +01:00
Peter Steinberger 84e76f7cce
refactor(cli): remove stale cli provider leftovers 2026-04-05 19:11:34 +01:00
Vincent Koc a1c1598742 docs: rewrite dreaming docs for 3-phase architecture 2026-04-05 18:42:06 +01:00
Peter Steinberger fe93f29486
docs(anthropic): clarify api key and doctor recovery 2026-04-05 18:05:12 +01:00
Peter Steinberger 6e3155ca84
feat(memory-core): add dreaming aging controls 2026-04-05 15:59:06 +01:00
Peter Steinberger 7ff7a27f61
feat(memory-core): add dreaming verbose logging 2026-04-05 15:10:59 +01:00
Peter Steinberger e3eb615da8
docs: salvage english docs from translation backlog 2026-04-05 10:45:08 +01:00
Peter Steinberger e468da1040
fix: improve gpt execution flow and visibility 2026-04-05 10:32:58 +01:00
Vincent Koc bca6faf11d docs: sync CLI and prompt-caching reference with code 2026-04-05 09:30:31 +01:00
Vincent Koc a4b767c89b docs: sync config reference with unreleased changes 2026-04-05 09:23:18 +01:00
Peter Steinberger 37301cbc3b
docs: clarify anthropic extra usage billing 2026-04-05 07:14:35 +09:00
Peter Steinberger eee868452f
docs: refresh claude-cli model ref mirrors 2026-04-04 22:19:07 +01:00
Peter Steinberger 8ea5b1ddc0
docs: refresh anthropic token compatibility mirrors 2026-04-04 22:09:21 +01:00
Peter Steinberger 66a0ab3752
docs: refresh anthropic auth mirror refs 2026-04-04 22:07:08 +01:00
Peter Steinberger f14f7b9fde
docs: refresh silent token guidance mirrors 2026-04-04 21:58:12 +01:00
Peter Steinberger e336300e60
docs: refresh failover and compaction pattern refs 2026-04-04 20:43:58 +01:00
Peter Steinberger 46cb292c2a
docs: refresh Firecrawl and web_fetch config refs 2026-04-04 20:21:16 +01:00
Peter Steinberger e0ef3855ca
docs: refresh video generation config refs 2026-04-04 19:56:54 +01:00
Peter Steinberger 879d45a56c
docs: refresh qwen media and config refs 2026-04-04 19:42:13 +01:00
Peter Steinberger ac5d1de13a
docs: refresh status deep health mirrors 2026-04-04 18:56:46 +01:00
Peter Steinberger 2ab8acb2c9
docs: refresh chat thinking and compaction refs 2026-04-04 18:25:13 +01:00
Peter Steinberger 73584b1d33
docs: refresh failover and compaction refs 2026-04-04 14:44:51 +01:00
Peter Steinberger f2b3b3d912
docs: clarify setup node-manager refs 2026-04-04 13:34:02 +01:00
Peter Steinberger 0166fd426e
docs: refresh minimax auth path refs 2026-04-04 12:47:07 +01:00
Peter Steinberger a375635a9a
docs: refresh status token fallback refs 2026-04-04 12:42:50 +01:00
Peter Steinberger 9d684e1040
docs: refresh provider usage auth refs 2026-04-04 12:40:55 +01:00
Peter Steinberger c0d509e794
docs: refresh status cache fallback refs 2026-04-04 12:39:02 +01:00
Peter Steinberger ac254f50e8
docs: refresh minimax usage refs 2026-04-04 12:36:18 +01:00
Peter Steinberger 90af255a91
docs: refresh gemini cli usage refs 2026-04-04 12:30:55 +01:00
Peter Steinberger 00337cdde1
docs: refresh codex auth and ws refs 2026-04-04 12:11:45 +01:00
Peter Steinberger 6bbccb087a
docs: refresh google cached content refs 2026-04-04 12:10:29 +01:00
Peter Steinberger 86ee50b968
docs: refresh web search overview mirrors 2026-04-04 12:04:28 +01:00
Peter Steinberger c524d6c76c
docs: refresh shared minimax web search refs 2026-04-04 12:00:58 +01:00
Jithendra d204be80af feat(tools): add MiniMax as bundled web search provider
Add native MiniMax Search integration via their Coding Plan search API
(POST /v1/coding_plan/search). This brings MiniMax in line with Brave,
Kimi, Grok, Gemini, and other providers that already have bundled web
search support.

- Implement WebSearchProviderPlugin with caching, credential resolution,
  and trusted endpoint wrapping
- Support both global (api.minimax.io) and CN (api.minimaxi.com)
  endpoints, inferred from explicit region config, model provider base
  URL, or minimax-portal OAuth base URL
- Prefer MINIMAX_CODE_PLAN_KEY over MINIMAX_API_KEY in credential
  fallback, matching existing repo precedence
- Accept SecretRef objects for webSearch.apiKey (type: [string, object])
- Register in bundled registry, provider-id compat map, and fast-path
  plugin id list with full alignment test coverage
- Add unit tests for endpoint/region resolution and edge cases

Closes #47927
Related #11399

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-04 19:56:04 +09:00
Peter Steinberger 277df463d6
docs: clarify openrouter cache markers 2026-04-04 11:34:17 +01:00
Peter Steinberger 2ab1f1c054
docs: clarify openai usage normalization 2026-04-04 11:32:58 +01:00
Peter Steinberger 9367379771
docs: clarify prompt cache stability 2026-04-04 11:28:19 +01:00
Peter Steinberger 2c36ca562d
docs: clarify minimax usage window semantics 2026-04-04 11:25:51 +01:00
Peter Steinberger de63a646d6
docs: refresh shared web search references 2026-04-04 10:16:02 +01:00
Peter Steinberger ad7461b639
docs: align auth storage and token auth guidance 2026-04-04 07:50:26 +01:00
Peter Steinberger 0ab160cda9
docs(anthropic): remove setup-token setup docs 2026-04-04 15:46:25 +09:00
Peter Steinberger 6e6b4f6004
ci: gate releases on live cache floors 2026-04-04 15:44:34 +09:00
Peter Steinberger 195e380e05
docs: remove legacy cache retention notes 2026-04-04 15:26:19 +09:00
Vincent Koc 6fc69f5d33
fix(secrets): drop legacy talk apiKey target surface (#60717) 2026-04-04 15:22:41 +09:00
Peter Steinberger cdb572d703
test: tune live cache assertions 2026-04-04 15:18:09 +09:00
Peter Steinberger e2454d4b8a
docs: align provider and onboarding references 2026-04-04 07:14:28 +01:00