feat: Implement Free Tier synthesis using HuggingFace Inference

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

feat: SPEC_15 Advanced Mode Performance Optimization (#101)

feat(clinicaltrials): SPEC_14 Outcome Measures (#100)

feat(search): SPEC_13 Evidence Deduplication (#98)

fix: use logger.error with stack trace for synthesis failures (CodeRabbit)

fix(ui): CSS autofill override and text centering

fix(ui): resolve Gradio 6 breaking change and align text

feat(ui): force dark mode for api key input and enhance synthesis error handling

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

feat(SPEC_11): finalize transition to Sexual Health Research Specialist

feat(SPEC_11): narrow scope to sexual health only

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

ci: upgrade to ironclad CI/CD configuration

feat: Wire LlamaIndex RAG into Simple Mode (Tiered Embedding) (#83)

fix: add future annotations to workflow.py for runtime type compatibility

feat(SPEC-08): Integrate shared memory layer + CodeRabbit fixes (#74)

fix: implement proper hypothesis conversion in synthesize_node

feat: Enhance research workflow with embedding service integration

feat: Integrate LangGraph for enhanced research orchestration

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

feat: add service loader + SPEC_06 + P0 bug report

fix: Address audit findings in orchestrators package

refactor: Organize orchestrators into dedicated package

fix: implement SPEC_04 (Magentic UX) and SPEC_05 (cleanup)

feat(tools): add OpenAlex integration with citation-based ranking

fix: address CodeRabbit review feedback

feat: Implement SPEC_01 (Termination) and SPEC_02 (E2E Tests)

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

fix: P0 dedup bug + HF judge infinite loop prevention

fix: simplify HSDD example to fix Gradio click issue (P2)

Merge pull request #62 from The-Obstacle-Is-The-Way/dev

fix: remove duplicate backend line (CodeRabbit feedback)

Fix P3 bug: Guarantee termination event in Magentic mode

fix: P0/P1/P2 - Gradio crash, UX improvements, thinking state (#61)

fix: enhance UX with "thinking" state and API key persistence

fix: multiple UX improvements (P1 bugs)

fix: handle None parameters from Gradio example caching (P0)

Merge branch 'dev' - P1 bug fixes + CodeRabbit feedback

style: integrate CodeRabbit review feedback

fix: resolve P1 bugs (streaming UX + api key persistence) and update tests/docs

fix: resolve streaming spam and API key persistence bugs

fix: replace deprecated OpenAIModel with OpenAIChatModel

fix(config): use gpt-5.1 (actually available) not gpt-5 (deprecated)

fix: P0 bugs + model config stabilization (November 2025) (#59)

refactor(judges): extract shared title-extraction helper

fix(config): update default LLM models to stable Nov 2025 versions

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

fix: resolve all P0 critical bugs blocking demo

fix(ui): clarify mode compatibility in radio button info