cceeaadbea
Replace the prose-recall test ("Based on what we've talked about, what do you know about me?") with a forced honcho_search call. Prose recall depended on the model getting deriver-built representation/peer-card in its system prompt, which is gated behind DERIVER_REPRESENTATION_BATCH_MAX_TOKENS=1024 — short tutorial-length conversations don't trigger it, producing false negatives on a working integration.
honcho_search hits message embeddings, which are computed synchronously at message persist time (src/crud/message.py:262-276), so peer-scoped retrieval works regardless of how short the prior session was. Also folds the result.steps[i].toolCalls inspection snippet from the old Step 5 into Step 4 — same prompt, no need for two sections.
Drops Step 5 entirely.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| claude-code.mdx | ||
| crewai.mdx | ||
| hermes.mdx | ||
| langgraph.mdx | ||
| mcp.mdx | ||
| n8n.mdx | ||
| openclaw.mdx | ||
| opencode.mdx | ||
| paperclip.mdx | ||
| reachy-mini.mdx | ||
| sillytavern.mdx | ||
| vercel-ai-sdk.mdx | ||
| zo-computer.mdx | ||