fix(lab): scoped-only index arm + raise deepseek output cap
The trial showed the model whole-reads and then gets cut mid-analysis by the per-response output cap before drafting. Enforce the scoped workflow: - read_document/fetch_documents in the index arm refuse non-scoped calls (typed refusal: provide offset/max_chars or head/tail; head shows the index). - deepseek: pass low/medium reasoning_effort through (was high/max only) and make the per-response output cap configurable via MIKE_DEEPSEEK_MAX_TOKENS (index arm sets 65536 so heavy section analysis finishes before drafting). Co-Authored-By: Claude <noreply@anthropic.com>
| Repository | eliziff/Beaver |
|---|---|
| Author | Eli Ziff <eliasziff@gmail.com> |
| Authored | |
| Parents | d24da27a |
| Stats | 3 files changed , +38 , -6 |
| Part of | Evaluation harness: Beaver-CAN and LegalBench-RAG adapters |
Capture this commit into my fork
Download a Markdown prompt that tells Claude how to port this
exact commit into your working tree. Run it via
claude -p < capture-commit-75b67279.md
from inside the repo you want the change in.