refactor(cleanup): Remove Anthropic + Modal partial wiring (P3 Tech Debt) (#130)

fix(coderabbit): Address all CodeRabbit review findings

fix(arch): End-to-end BYOK support for unified architecture

fix(P1): Replace stale 72B model fallbacks with 7B to avoid Novita 500 errors

fix(P1): Switch from Llama-3.1-70B to Qwen2.5-72B for HuggingFace free tier

fix: P0 Advanced Mode timeout synthesis + CodeRabbit recommendations

feat: Implement Free Tier synthesis using HuggingFace Inference

fix: P0 provider mismatch and code quality audit fixes (#102)

fix(SPEC_11): address CodeRabbit review feedback (#92)

feat: SPEC_10 - Domain-Agnostic Refactor + License Fix (#87)

fix(P0): Implement SPEC_06 - Simple Mode Synthesis Fix (#71)

refactor: add session reset + document magic number (senior review feedback)

fix: P0 dedup bug + HF judge infinite loop prevention

style: integrate CodeRabbit review feedback

refactor(judges): extract shared title-extraction helper

fix(judges): fallback to heuristic extraction when HF quota exhausted

fix: resolve all P0 critical bugs blocking demo

fix: resolve all test warnings and complete DeepBoner rebrand

feat: implement dual-mode architecture (Simple + Advanced) (#45)

fix(magentic): defensive text extraction & cleanup biorxiv refs

fix: address CodeRabbit feedback and P0 blockers

feat: implement HFInferenceJudgeHandler for free-tier AI analysis

fix: wire EmbeddingService to simple orchestrator + improve search quality

feat: add demo mode warnings and BYOK (Bring Your Own Key) support

fix: pass API keys explicitly to pydantic-ai providers

fix: pydantic-ai v1 compatibility and Anthropic model update

fix: add type ignore comment for Agent instantiation in JudgeHandler

fix(tests): resolve mypy divergence and test failures

feat(phase3): implement judge slice (LLM Judge, Prompts, Models)

feat(phase1): Foundation & Tooling complete

adds scaffolding