fix: mock all agent creation in _build_workflow test

fix: address CodeRabbit feedback and CI failure

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

fix: update references to Europe PMC in examples and documentation

refactor(tests): add type annotations and clean up test functions

feat(search): implement ClinicalTrials.gov filtering (Phase 03)

feat(search): implement PubMed query preprocessing (Phase 02)

refactor(tools): replace BioRxiv with Europe PMC (Phase 01)

fix: address CodeRabbit feedback and P0 blockers

feat: implement HFInferenceJudgeHandler for free-tier AI analysis

fix: address CodeRabbit review feedback

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

feat: add smoke tests and fix Gradio 6.x compatibility

style: add pytest.mark.unit to test_models (CodeRabbit)

fix: make ResearchReport.references optional with default

refactor: address CodeRabbit nitpick suggestions

fix: address CodeRabbit review feedback for Phase 13

feat: implement phase 13 modal pipeline integration

docs: address CodeRabbit feedback for Phase 12 PR

feat: enhance Gradio UI with MCP server support and new tool interfaces

chore: update Gradio dependency to include MCP extras and version bump

feat: Phase 11 bioRxiv Preprint Integration (#19)

refactor: address CodeRabbit nitpicks for Phase 10

feat: Implement Phase 10 (ClinicalTrials.gov) with requests

feat: Complete Phase 9 Source Cleanup (Remove WebTool) (#14)

fix: address all CodeRabbit Phase 8 review feedback

fix: apply lazy init pattern and pydantic-ai fixes to ReportAgent (#12)

fix: mock get_model in tests to avoid API key requirement in CI

fix: address CodeRabbit Phase 7 nitpicks

feat(phase7): implement Hypothesis Agent for mechanistic reasoning

fix: address CodeRabbit Phase 6 review feedback

feat(phase6): Embeddings & Semantic Search implementation

fix(ci): add E402/RUF100 to ignore for cross-env compatibility

fix(ci): skip agent tests when agent-framework not installed

fix(phase5): align configs and add agent tests

fix: pydantic-ai v1 compatibility and Anthropic model update

feat(phase4): Orchestrator and UI complete

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(phase2): add sample_evidence fixture to conftest.py

feat(phase2): implement search slice (PubMed, Web, Orchestrator) (#4)

feat(phase1): Foundation & Tooling complete