6 commits

Author	SHA1	Message	Date
Dhravya Shah	7fa452b6b8	feat(tools): SDK-level cross-source memory deduplication ... Move profile deduplication into the SDK middleware. Facts are normalized (strip leading date, trim, collapse whitespace, casefold) and deduplicated in static > dynamic > search priority within each request, then injected as one owned <supermemory> block that replaces the previous block instead of accumulating. Dedup is mode-aware so query-mode search results are not dropped against an omitted profile. No global/browser Set: request-local only, safe for concurrent requests and Cloudflare Workers. Covers AI SDK, OpenAI Chat/Responses, Mastra, and VoltAgent. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	2026-08-24 20:31:15 +05:30
sreedharsreeram	c76d27f284	custom id implementation (#877)	2026-04-24 23:43:16 +00:00
sreedharsreeram	3c02aefe44	withSupermemory config object signature (#876)	2026-04-24 23:43:16 +00:00
MaheshtheDev	23a60f90f6	tools: timeout and default option on error to skip (#875) ... **`withSupermemory`** **(AI SDK)** - **`skipMemoryOnError`** **defaults to** **`true`**. memory errors/timeouts log and the model runs on the **original** prompt unless you set `skipMemoryOnError: false`. - **Pre-LLM** **`/v4/profile`** **is aborted after 5s** via `AbortSigna` **Docs** - `packages/tools/README.md`, **`apps/docs/integrations/ai-sdk.md`**	2026-04-23 00:11:20 +00:00
MaheshtheDev	76b0f2746b	fix: Multi Params issue with @supermemory/tools (#854) ... testing for now fix proxy issue upgraded the package	2026-04-16 07:37:09 +00:00
MaheshtheDev	32a7eff3af	fix(tools): multi step agent prompt caching (#685)	2026-01-20 01:30:43 +00:00