1cc7c0e7575925b0ff5a3e284a3860e18c759208
Diagnosis from the FU-5 eval: co-relevant precedents for broad legal questions rank 15-16 (retrieved, not absent — recall ~1.0 by rank 20). Tracked as a deliberate, harness-measured tuning task rather than an unmeasured global limit change (which affects UI + writer agents + token cost). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Description
AI Legal Decision Drafting System — MCP server, web upload, RAG search
Languages
Python
65.8%
TypeScript
32.2%
JavaScript
1%
Shell
0.7%
CSS
0.2%