2 commits

Author	SHA1	Message	Date
MaheshtheDev	a00a751e10	pkg(tools): Expose raw search results in MemoryPromptData for prompt templates (#787) ... Expose raw search results in `MemoryPromptData` so prompt templates can traverse, filter, and selectively include results based on metadata (e.g. score, source). ##### Usage example ```typescript const promptTemplate = (data: MemoryPromptData) => { const relevant = data.searchResults.filter( (r) => (r.metadata?.score as number) > 0.7 ) return `${data.userMemories}\n${relevant.map(r => r.memory).join('\n')}` } ```	2026-03-19 00:38:53 +00:00
nexxeln	9553434c9a	mastra integration (#717) ... adds withSupermemory wrapper and input/output processors for mastra agents: - input processor fetches and injects memories into system prompt before llm calls - output processor saves conversations to supermemory after responses - supports profile, query, and full memory search modes - includes custom prompt templates and requestcontext support const agent = new Agent(withSupermemory( { id: "my-assistant", model: openai("gpt-4o"), instructions: "..." }, "user-123", { mode: "full", addMemory: "always", threadId: "conv-456" } )) includes docs as well this pr also reworks how the tools package works into shared modules	2026-02-03 00:43:08 +00:00