6b5d6586dc108c9d596068612d14d42ce2bfa685
Until now only legal-writer referenced the voice corpus. Without these references the qa agent can't validate writer output, the researcher chooses precedents outside Daphna's canon, and the analyst's claims classification doesn't match block-zayin rules. - legal-qa: adds 8th check "voice_compliance" — block ז structure, block י voice (אכן/אולם, "אנחנו" verbs, no numbered lists), correct precedent from canon, acceptance template match. - legal-researcher: must check daphna-precedent-network.md before proposing any precedent; cross-reference with Daphna's own past decisions via search_decisions. - legal-analyst: reads block-zayin-claims.md — its output is the writer's input for block ז. - legal-ceo: lists all 6 voice docs and which agent reads each. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Description
AI Legal Decision Drafting System — MCP server, web upload, RAG search
Languages
Python
59.1%
TypeScript
37.4%
JavaScript
1.7%
Shell
1.2%
CSS
0.5%
Other
0.1%