feat: constrain agent questions to user-friendly abstraction level (#13) afd1605 unverified Daniel Tu Claude Opus 4.6 (1M context) commited on Apr 13
feat: add severity field to GeneratedQuestionCard 54db1da CallMeDaniel Claude Sonnet 4.6 commited on Apr 13
fix: pass max_tokens to LLM, add debug log for JSON parse fallback a3f1aa5 CallMeDaniel Claude Opus 4.6 (1M context) commited on Apr 13
feat: replace keyword gap analyzer with LLM-based analyze_gaps 2919322 CallMeDaniel Claude Opus 4.6 (1M context) commited on Apr 13
refactor: update CrewOrchestrator to return ChatTurnResponse 98e04b1 CallMeDaniel Claude Opus 4.6 (1M context) commited on Apr 12
refactor: type analyze_gaps and extract_decisions with AgentResponse a9d0aec CallMeDaniel Claude Opus 4.6 (1M context) commited on Apr 12
fix: prevent question card loop when agent mentions keywords as context e65e6f8 CallMeDaniel Claude Opus 4.6 (1M context) commited on Apr 12
feat: add gap analyzer with analyze_gaps() and generate_question_cards() 523f06c CallMeDaniel Claude Opus 4.6 (1M context) commited on Apr 12