fix: resolve streaming spam and API key persistence bugs

fix: replace deprecated OpenAIModel with OpenAIChatModel

docs: add P1 bug report for streaming spam + API key persistence

fix: align all docs/tests to gpt-5.1 (actual current model)

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

docs: add senior agent audit prompt for comprehensive bug hunt

docs: add P0 critical bugs report - demo is broken

docs: add UI/UX brainstorming for mode selection

docs: update UI simplification spec with senior review fixes

docs: add UI simplification spec for BYOK cleanup

fix: replace remaining bioRxiv refs with Europe PMC in docs

fix: complete audit fixes for documentation accuracy

docs: reorganize documentation structure for clarity

fix: address CodeRabbit review feedback

fix: resolve all test warnings and complete DeepBoner rebrand

rebrand: DeepCritical → DeepBoner (sexual health research agent)

docs: add deep research roadmap and GradioDemo analysis

docs: document withdrawal of @The-Obstacle-Is-The-Way from hackathon participation

docs: fix misleading 'upstream' wording in PR #55 decision record

docs: clarify project relationships and add reciprocity note

docs: add decision record for PR #55 evaluation

docs: add decision record for PR #55 evaluation

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

feat: add roadmap summary and detailed improvement plans for data sources

fix: repair Gradio accordion bug and cleanup env vars

docs: update P1 bug report with actual Gradio accordion root cause

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

docs: add TDD fix plan for Magentic mode report generation

docs: replace completed bug docs with new Magentic bug report

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

fix: exclude reference_repos from mypy and cleanup

fix: simplify Gradio UI to fit single viewport

chore: remove resolved bug documentation

fix: pin agent-framework-core and remove resolved bug doc

fix: address CodeRabbit feedback and P0 blockers

docs: add P0 blockers documentation for Magentic mode implementation

feat: add documentation for Magentic mode bug and implementation spec

feat: implement HFInferenceJudgeHandler for free-tier AI analysis

fix: wire EmbeddingService to simple orchestrator + improve search quality

docs: add bug report for intermittent gradio loading issues

fix: resolve Gradio UI cutoff by removing fill_height=True and restructuring layout

fix: move title/description into ChatInterface for proper HF Spaces layout

fix: upgrade Gradio SDK to 6.0.1 and add fill_height for HF Spaces UI fix

chore: improve DevEx and clean up obsolete docs (#25)

docs: address CodeRabbit feedback for Phase 12 PR

docs: update MCP server integration documentation and status

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