RomanNum3ral
/
honcho
mirror of https://github.com/plastic-labs/honcho.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs(integrations): make Step 4 cross-session test durable via honcho_search 

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>
This commit is contained in:
lowyelling 2026-05-04 16:03:10 -04:00
parent b7a214afb1
commit cceeaadbea
1 changed files with 4 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
docs/v3/guides/integrations/vercel-ai-sdk.mdx
View File

@ -265,25 +265,15 @@ If the model references TypeScript and concise answers without being told again
### 4. Cross-session recall
Start a new session (new `sessionId`). Ask:
```text
Based on what we've talked about, what do you know about me?
```
If the model recalls preferences from previous sessions without them being in the current conversation, cross-session memory is working. Honcho processed the prior turns between sessions and updated the user's representation.
<Note>
The deriver waits until 1024 tokens are accumulated before batch processing - short conversations won't trigger cross-session recall!
</Note>
### 5. Test tool calling directly
Start a new session (new `sessionId`) with the same `userId`. Ask:
```text
Call your honcho_search tool with the query 'TypeScript' and quote the exact verbatim message that contained TypeScript. Do not paraphrase.
```
If the model returns the exact prior message word-for-word, the tool pipeline is functional. To confirm which tool fired, inspect `result.steps[i].toolCalls`:
If the search returns a message from the prior session word-for-word, peer-scoped retrieval is crossing session boundaries. `honcho_search` queries the user's messages across all their sessions and doesn't depend on the deriver, so it works regardless of how short the prior session was.
To confirm the tool actually fired, inspect `result.steps[i].toolCalls`:
```typescript
const toolFires = result.steps?.flatMap((step, i) =>