Commit History
Merge branch 'dev' - P1 bug fixes + CodeRabbit feedback
8f45b69
fix: replace deprecated OpenAIModel with OpenAIChatModel
c881895
fix(config): use gpt-5.1 (actually available) not gpt-5 (deprecated)
75bc69f
fix: P0 bugs + model config stabilization (November 2025) (#59)
622c8ba
unverified
fix(config): update default LLM models to stable Nov 2025 versions
bfc953b
fix: complete audit fixes for documentation accuracy
e720905
rebrand: DeepCritical → DeepBoner (sexual health research agent)
5d12635
feat: add hierarchical orchestration with web search (integrates PR #44) (#46)
20f762e
unverified
feat: implement dual-mode architecture (Simple + Advanced) (#45)
b2929fc
unverified
feat: add roadmap summary and detailed improvement plans for data sources
9286db5
fix: address CodeRabbit feedback and CI failure
2ff16a3
fix(magentic): defensive text extraction & cleanup biorxiv refs
3bfd42c
fix: update references to Europe PMC in examples and documentation
9d21bf8
fix(config): increase max iterations to 10
72b2667
refactor(tools): replace BioRxiv with Europe PMC (Phase 01)
2f8ae1f
chore: clean up env config and upgrade model defaults
9e9bc6b
fix: make ResearchReport.references optional with default
f882609
refactor: address CodeRabbit nitpick suggestions
901acc3
feat: implement phase 13 modal pipeline integration
7cc8b69
feat: Phase 11 bioRxiv Preprint Integration (#19)
e67c99f
unverified
refactor: centralize embedding configuration in Settings
20c7bad
feat: Integrate Mario's Modal code execution + LlamaIndex RAG
3aa91e9
refactor: address CodeRabbit nitpicks for Phase 10
1bc9785
feat: Implement Phase 10 (ClinicalTrials.gov) with requests
4e2ccbf
feat: Complete Phase 9 Source Cleanup (Remove WebTool) (#14)
cd004e1
fix: address all CodeRabbit Phase 8 review feedback
f1e4e5b
fix: apply lazy init pattern and pydantic-ai fixes to ReportAgent (#12)
3139749
fix: address CodeRabbit Phase 7 review feedback
bc74531
feat(phase7): implement Hypothesis Agent for mechanistic reasoning
c690006
fix: address CodeRabbit Phase 5 review feedback
d247864
fix: linting and types for phase 5
1922dbd
fix: pass API keys explicitly to pydantic-ai providers
1f96735
fix: pydantic-ai v1 compatibility and Anthropic model update
4732667
refactor(phase4): address CodeRabbit review
36983ae
feat(phase4): Orchestrator and UI complete
25c3a8b
feat(phase3): implement judge slice (LLM Judge, Prompts, Models)
d7e5abb
feat(phase2): implement search slice (PubMed, Web, Orchestrator) (#4)
499170b
feat(phase1): Foundation & Tooling complete
069f0a0
adds scaffolding
6fbbcda
Joseph Pollack
commited on