fix: complete DeepBoner rebrand with test fixes and CodeRabbit feedback

* docs: add deep research roadmap and GradioDemo analysis

- Introduced a comprehensive roadmap for implementing GPT-Researcher-style deep research in DeepCritical, detailing phases from input parsing to long-form writing.
- Added an analysis of the GradioDemo codebase, highlighting redundant components and useful patterns, while emphasizing a streamlined approach to integration and implementation.

* rebrand: DeepCritical → DeepBoner (sexual health research agent)

🍆 AI-Native Sexual Health Research Agent

- Package renamed: deepcritical → deepboner
- New focus: sexual wellness, ED, hormone therapy, libido, reproductive health
- Exception class: DeepCriticalError → DeepBonerError (with backwards compat)
- UI examples updated for sexual health queries
- Modal app renamed: deepboner-code-execution
- Fixed pre-existing mypy issue (Modal API: uv_pip_install → pip_install)

46 files updated across:
- Core: pyproject.toml, README.md, CLAUDE.md, AGENTS.md, GEMINI.md
- Source: app.py, mcp_tools.py, exceptions.py, code_execution.py
- Docs: ~25 markdown files
- Examples: 8 demo scripts
- Tests: exception tests updated

All tests passing (102 passed, 6 skipped)

* fix: resolve all test warnings and complete DeepBoner rebrand

Code fixes:
- Update OpenAIModel → OpenAIChatModel (pydantic-ai deprecation)
- Add pytest.importorskip guards to 3 test files for optional deps

Rebrand fixes (missed in initial rename):
- src/services/llamaindex_rag.py: collection name
- src/tools/clinicaltrials.py: User-Agent header
- 7 doc files: package names, URLs, examples

Config:
- Add targeted pytest warning filters for Pydantic mock introspection
(known upstream issue: pydantic/pydantic#9927)

Result: 127 tests pass, 0 warnings (was 50 warnings)

* fix: address CodeRabbit review feedback

Fixes from CodeRabbit analysis:
- docs/to_do/DEEP_RESEARCH_ROADMAP.md: Fix MagenticBuilder → MagenticOrchestrator
- docs/to_do/DEEP_RESEARCH_ROADMAP.md: Add note clarifying RAGService vs EmbeddingService
- src/services/llamaindex_rag.py: Add migration note for collection name change
- tests/unit/utils/test_exceptions.py: Add pytestmark = pytest.mark.unit
- docs/implementation/12_phase_mcp_server.md: Update all bioRxiv refs → Europe PMC

All 127 tests pass, 0 warnings.

.gitignore

@@ -49,6 +49,7 @@ reference_repos/claude-agent-sdk/
 reference_repos/pydanticai-research-agent/
 reference_repos/pubmed-mcp-server/
 reference_repos/DeepCritical/
+reference_repos/GradioDemo/
 
 # Keep the README in reference_repos
 !reference_repos/README.md

AGENTS.md

@@ -4,7 +4,7 @@ This file provides guidance to AI agents when working with code in this reposito
 
 ## Project Overview
 
-DeepCritical is an AI-native drug repurposing research agent for a HuggingFace hackathon. It uses a search-and-judge loop to autonomously search biomedical databases (PubMed, ClinicalTrials.gov, bioRxiv) and synthesize evidence for queries like "What existing drugs might help treat long COVID fatigue?".
+DeepBoner is an AI-native sexual health research agent. It uses a search-and-judge loop to autonomously search biomedical databases (PubMed, ClinicalTrials.gov, Europe PMC) and synthesize evidence for queries like "What drugs improve female libido post-menopause?" or "Evidence for testosterone therapy in women with HSDD?".
 
 **Current Status:** Phases 1-13 COMPLETE (Foundation through Modal sandbox integration).
 
@@ -39,7 +39,7 @@ uv run pytest -m integration
 User Question → Orchestrator
     ↓
 Search Loop:
-  1. Query PubMed, ClinicalTrials.gov, bioRxiv
+  1. Query PubMed, ClinicalTrials.gov, Europe PMC
   2. Gather evidence
   3. Judge quality ("Do we have enough?")
   4. If NO → Refine query, search more
@@ -53,7 +53,7 @@ Research Report with Citations
 - `src/orchestrator.py` - Main agent loop
 - `src/tools/pubmed.py` - PubMed E-utilities search
 - `src/tools/clinicaltrials.py` - ClinicalTrials.gov API
-- `src/tools/biorxiv.py` - bioRxiv/medRxiv preprint search
+- `src/tools/europepmc.py` - Europe PMC search
 - `src/tools/code_execution.py` - Modal sandbox execution
 - `src/tools/search_handler.py` - Scatter-gather orchestration
 - `src/services/embeddings.py` - Semantic search & deduplication (ChromaDB)
@@ -82,7 +82,7 @@ Settings via pydantic-settings from `.env`:
 ## Exception Hierarchy
 
 ```text
-DeepCriticalError (base)
+DeepBonerError (base)
 ├── SearchError
 │   └── RateLimitError
 ├── JudgeError

CLAUDE.md

@@ -4,7 +4,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 ## Project Overview
 
-DeepCritical is an AI-native drug repurposing research agent for a HuggingFace hackathon. It uses a search-and-judge loop to autonomously search biomedical databases (PubMed, ClinicalTrials.gov, bioRxiv) and synthesize evidence for queries like "What existing drugs might help treat long COVID fatigue?".
+DeepBoner is an AI-native sexual health research agent. It uses a search-and-judge loop to autonomously search biomedical databases (PubMed, ClinicalTrials.gov, Europe PMC) and synthesize evidence for queries like "What drugs improve female libido post-menopause?" or "Evidence for testosterone therapy in women with HSDD?".
 
 **Current Status:** Phases 1-13 COMPLETE (Foundation through Modal sandbox integration).
 
@@ -39,7 +39,7 @@ uv run pytest -m integration
 User Question → Orchestrator
     ↓
 Search Loop:
-  1. Query PubMed, ClinicalTrials.gov, bioRxiv
+  1. Query PubMed, ClinicalTrials.gov, Europe PMC
   2. Gather evidence
   3. Judge quality ("Do we have enough?")
   4. If NO → Refine query, search more
@@ -53,7 +53,7 @@ Research Report with Citations
 - `src/orchestrator.py` - Main agent loop
 - `src/tools/pubmed.py` - PubMed E-utilities search
 - `src/tools/clinicaltrials.py` - ClinicalTrials.gov API
-- `src/tools/biorxiv.py` - bioRxiv/medRxiv preprint search
+- `src/tools/europepmc.py` - Europe PMC search
 - `src/tools/code_execution.py` - Modal sandbox execution
 - `src/tools/search_handler.py` - Scatter-gather orchestration
 - `src/services/embeddings.py` - Semantic search & deduplication (ChromaDB)
@@ -82,7 +82,7 @@ Settings via pydantic-settings from `.env`:
 ## Exception Hierarchy
 
 ```text
-DeepCriticalError (base)
+DeepBonerError (base)
 ├── SearchError
 │   └── RateLimitError
 ├── JudgeError

Dockerfile

@@ -1,4 +1,4 @@
-# Dockerfile for DeepCritical
+# Dockerfile for DeepBoner
 FROM python:3.11-slim
 
 # Set working directory

GEMINI.md

@@ -1,9 +1,9 @@
-# DeepCritical Context
+# DeepBoner Context
 
 ## Project Overview
 
-**DeepCritical** is an AI-native Medical Drug Repurposing Research Agent.
-**Goal:** To accelerate the discovery of new uses for existing drugs by intelligently searching biomedical literature (PubMed, ClinicalTrials.gov, bioRxiv), evaluating evidence, and hypothesizing potential applications.
+**DeepBoner** is an AI-native Sexual Health Research Agent.
+**Goal:** To accelerate research into sexual health, wellness, and reproductive medicine by intelligently searching biomedical literature (PubMed, ClinicalTrials.gov, Europe PMC), evaluating evidence, and synthesizing findings.
 
 **Architecture:**
 The project follows a **Vertical Slice Architecture** (Search -> Judge -> Orchestrator) and adheres to **Strict TDD** (Test-Driven Development).
@@ -11,7 +11,7 @@ The project follows a **Vertical Slice Architecture** (Search -> Judge -> Orches
 **Current Status:**
 
 - **Phases 1-9:** COMPLETE. Foundation, Search, Judge, UI, Orchestrator, Embeddings, Hypothesis, Report, Cleanup.
-- **Phases 10-11:** COMPLETE. ClinicalTrials.gov and bioRxiv integration.
+- **Phases 10-11:** COMPLETE. ClinicalTrials.gov and Europe PMC integration.
 - **Phase 12:** COMPLETE. MCP Server integration (Gradio MCP at `/gradio_api/mcp/`).
 - **Phase 13:** COMPLETE. Modal sandbox for statistical analysis.
 
@@ -41,7 +41,7 @@ The project follows a **Vertical Slice Architecture** (Search -> Judge -> Orches
 
 - `src/`: Source code
   - `utils/`: Shared utilities (`config.py`, `exceptions.py`, `models.py`)
-  - `tools/`: Search tools (`pubmed.py`, `clinicaltrials.py`, `biorxiv.py`, `code_execution.py`)
+  - `tools/`: Search tools (`pubmed.py`, `clinicaltrials.py`, `europepmc.py`, `code_execution.py`)
   - `services/`: Services (`embeddings.py`, `statistical_analyzer.py`)
   - `agents/`: Magentic multi-agent mode agents
   - `agent_factory/`: Agent definitions (judges, prompts)
@@ -58,7 +58,7 @@ The project follows a **Vertical Slice Architecture** (Search -> Judge -> Orches
 - `src/orchestrator.py` - Main agent loop
 - `src/tools/pubmed.py` - PubMed E-utilities search
 - `src/tools/clinicaltrials.py` - ClinicalTrials.gov API
-- `src/tools/biorxiv.py` - bioRxiv/medRxiv preprint search
+- `src/tools/europepmc.py` - Europe PMC search
 - `src/tools/code_execution.py` - Modal sandbox execution
 - `src/services/statistical_analyzer.py` - Statistical analysis via Modal
 - `src/mcp_tools.py` - MCP tool wrappers

README.md

@@ -1,7 +1,7 @@
 ---
-title: DeepCritical
-emoji: 🧬
-colorFrom: blue
+title: DeepBoner
+emoji: 🍆
+colorFrom: pink
 colorTo: purple
 sdk: gradio
 sdk_version: "6.0.1"
@@ -10,26 +10,37 @@ app_file: src/app.py
 pinned: false
 license: mit
 tags:
-  - mcp-in-action-track-enterprise
+  - sexual-health
+  - reproductive-medicine
+  - hormone-therapy
+  - wellness-research
   - mcp-hackathon
-  - drug-repurposing
-  - biomedical-ai
   - pydantic-ai
   - llamaindex
   - modal
 ---
 
-# DeepCritical
+# DeepBoner 🍆
 
-AI-Powered Drug Repurposing Research Agent
+AI-Native Sexual Health Research Agent
+
+Deep research for sexual wellness, ED treatments, hormone therapy, libido, and reproductive health - for all genders.
 
 ## Features
 
-- **Multi-Source Search**: PubMed, ClinicalTrials.gov, bioRxiv/medRxiv
+- **Multi-Source Search**: PubMed, ClinicalTrials.gov, Europe PMC
 - **MCP Integration**: Use our tools from Claude Desktop or any MCP client
 - **Modal Sandbox**: Secure execution of AI-generated statistical code
 - **LlamaIndex RAG**: Semantic search and evidence synthesis
 
+## Example Queries
+
+- "What drugs improve female libido post-menopause?"
+- "Clinical trials for erectile dysfunction alternatives to PDE5 inhibitors?"
+- "Evidence for testosterone therapy in women with HSDD?"
+- "Drug interactions with sildenafil?"
+- "What's the latest research on flibanserin efficacy?"
+
 ## Quick Start
 
 ### 1. Environment Setup
@@ -62,7 +73,7 @@ Add this to your `claude_desktop_config.json`:
 ```json
 {
   "mcpServers": {
-    "deepcritical": {
+    "deepboner": {
       "url": "http://localhost:7860/gradio_api/mcp/"
     }
   }
@@ -72,7 +83,7 @@ Add this to your `claude_desktop_config.json`:
 **Available Tools**:
 - `search_pubmed`: Search peer-reviewed biomedical literature.
 - `search_clinical_trials`: Search ClinicalTrials.gov.
-- `search_biorxiv`: Search bioRxiv/medRxiv preprints.
+- `search_europepmc`: Search Europe PMC preprints and papers.
 - `search_all`: Search all sources simultaneously.
 - `analyze_hypothesis`: Secure statistical analysis using Modal sandboxes.
 
@@ -92,16 +103,16 @@ make check
 
 ## Architecture
 
-DeepCritical uses a Vertical Slice Architecture:
+DeepBoner uses a Vertical Slice Architecture:
 
-1.  **Search Slice**: Retrieving evidence from PubMed, ClinicalTrials.gov, and bioRxiv.
+1.  **Search Slice**: Retrieving evidence from PubMed, ClinicalTrials.gov, and Europe PMC.
 2.  **Judge Slice**: Evaluating evidence quality using LLMs.
 3.  **Orchestrator Slice**: Managing the research loop and UI.
 
 Built with:
 - **PydanticAI**: For robust agent interactions.
 - **Gradio**: For the streaming user interface.
-- **PubMed, ClinicalTrials.gov, bioRxiv**: For biomedical data.
+- **PubMed, ClinicalTrials.gov, Europe PMC**: For biomedical data.
 - **MCP**: For universal tool access.
 - **Modal**: For secure code execution.
 
@@ -110,8 +121,7 @@ Built with:
 - The-Obstacle-Is-The-Way
 - MarioAderman
 - EmployeeNo427
-- Josephrp *(provided initial template)*
 
 ## Links
 
-- [GitHub Repository](https://github.com/The-Obstacle-Is-The-Way/DeepCritical-1)
+- [GitHub Repository](https://github.com/The-Obstacle-Is-The-Way/DeepBoner)

docs/architecture/design-patterns.md

@@ -726,7 +726,7 @@ If evidence is weak, say so clearly."""
 **Architecture**:
 ```
 ┌─────────────────────────────────────────────────┐
-│  DeepCritical Agent                             │
+│  DeepBoner Agent                             │
 │  (uses tools directly OR via MCP)               │
 └─────────────────────────────────────────────────┘
                       │
@@ -811,7 +811,7 @@ uvx fastmcp run src/mcp_servers/pubmed_server.py
     "pubmed": {
       "command": "python",
       "args": ["-m", "src.mcp_servers.pubmed_server"],
-      "cwd": "/path/to/deepcritical"
+      "cwd": "/path/to/deepboner"
     }
   }
 }
@@ -865,7 +865,7 @@ def research_with_streaming(question: str) -> Generator[str, None, None]:
 
 # Gradio 5 UI
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🔬 DeepCritical: Drug Repurposing Research Agent")
+    gr.Markdown("# 🔬 DeepBoner: Drug Repurposing Research Agent")
     gr.Markdown("Ask a question about potential drug repurposing opportunities.")
 
     with gr.Row():

docs/architecture/overview.md

@@ -1,11 +1,11 @@
-# DeepCritical: Medical Drug Repurposing Research Agent
+# DeepBoner: Medical Drug Repurposing Research Agent
 ## Project Overview
 
 ---
 
 ## Executive Summary
 
-**DeepCritical** is a deep research agent designed to accelerate medical drug repurposing research by autonomously searching, analyzing, and synthesizing evidence from multiple biomedical databases.
+**DeepBoner** is a deep research agent designed to accelerate medical drug repurposing research by autonomously searching, analyzing, and synthesizing evidence from multiple biomedical databases.
 
 ### The Problem We Solve
 
@@ -16,7 +16,7 @@ Drug repurposing - finding new therapeutic uses for existing FDA-approved drugs
 - Assess safety profiles
 - Synthesize evidence into actionable insights
 
-**DeepCritical automates this process from hours to minutes.**
+**DeepBoner automates this process from hours to minutes.**
 
 ### What Is Drug Repurposing?
 

docs/brainstorming/00_ROADMAP_SUMMARY.md

@@ -1,4 +1,4 @@
-# DeepCritical Data Sources: Roadmap Summary
+# DeepBoner Data Sources: Roadmap Summary
 
 **Created**: 2024-11-27
 **Purpose**: Future maintainability and hackathon continuation
@@ -131,7 +131,7 @@ Keep current architecture working, add OpenAlex incrementally.
    ```
 
 2. **Copy OpenAlex tool from reference repo**
-   - File: `reference_repos/DeepCritical/DeepResearch/src/tools/openalex_tools.py`
+   - File: `reference_repos/DeepBoner/DeepResearch/src/tools/openalex_tools.py`
    - Adapt to our `SearchTool` base class
 
 3. **Enable NCBI API Key**
@@ -189,6 +189,6 @@ If you're picking this up after the hackathon:
 1. **Start with OpenAlex** - biggest bang for buck
 2. **Add rate limiting** - prevents API blocks
 3. **Don't bother with bioRxiv** - use Europe PMC instead
-4. **Reference repo is gold** - `reference_repos/DeepCritical/` has working implementations
+4. **Reference repo is gold** - `reference_repos/DeepBoner/` has working implementations
 
 Good luck! 🚀

docs/brainstorming/01_PUBMED_IMPROVEMENTS.md

@@ -24,9 +24,9 @@
 
 ---
 
-## Reference Implementation (DeepCritical Reference Repo)
+## Reference Implementation (DeepBoner Reference Repo)
 
-The reference repo at `reference_repos/DeepCritical/DeepResearch/src/tools/bioinformatics_tools.py` has a more sophisticated implementation:
+The reference repo at `reference_repos/DeepBoner/DeepResearch/src/tools/bioinformatics_tools.py` has a more sophisticated implementation:
 
 ### Features We're Missing
 

docs/brainstorming/03_EUROPEPMC_IMPROVEMENTS.md

@@ -182,7 +182,7 @@ Europe PMC is more generous than NCBI:
 # Recommend: 10-20 requests/second max
 # Use email in User-Agent for polite pool
 headers = {
-    "User-Agent": "DeepCritical/1.0 (mailto:your@email.com)"
+    "User-Agent": "DeepBoner/1.0 (mailto:your@email.com)"
 }
 ```
 

docs/brainstorming/04_OPENALEX_INTEGRATION.md

@@ -2,7 +2,7 @@
 
 **Status**: NOT Implemented (Candidate for Addition)
 **Priority**: HIGH - Could Replace Multiple Tools
-**Reference**: Already implemented in `reference_repos/DeepCritical`
+**Reference**: Already implemented in `reference_repos/DeepBoner`
 
 ---
 
@@ -20,7 +20,7 @@ OpenAlex is a **fully open** index of the global research system:
 
 ---
 
-## Why OpenAlex for DeepCritical?
+## Why OpenAlex for DeepBoner?
 
 ### Current Architecture
 
@@ -60,7 +60,7 @@ Orchestrator (enrich with CT.gov for trials)
 
 ## Reference Implementation
 
-From `reference_repos/DeepCritical/DeepResearch/src/tools/openalex_tools.py`:
+From `reference_repos/DeepBoner/DeepResearch/src/tools/openalex_tools.py`:
 
 ```python
 class OpenAlexFetchTool(ToolRunner):
@@ -212,7 +212,7 @@ class OpenAlexTool(SearchTool):
                     "filter": "type:article,is_oa:true",
                     "sort": "cited_by_count:desc",
                     "per_page": max_results,
-                    "mailto": "deepcritical@example.com",  # Polite pool
+                    "mailto": "deepboner@example.com",  # Polite pool
                 },
             )
             data = resp.json()

docs/brainstorming/implementation/15_PHASE_OPENALEX.md

@@ -305,7 +305,7 @@ class OpenAlexTool:
         Args:
             email: Optional email for polite pool (faster responses)
         """
-        self.email = email or "deepcritical@example.com"
+        self.email = email or "deepboner@example.com"
 
     @property
     def name(self) -> str:

docs/brainstorming/magentic-pydantic/00_SITUATION_AND_PLAN.md

@@ -167,7 +167,7 @@ The refactor branch (`feat/pubmed-fulltext`) has some valuable improvements:
 ## 9. Questions to Answer Before Proceeding
 
 1. **For the hackathon**: Do we need full multi-agent orchestration, or is single-agent sufficient?
-2. **For DeepCritical mainline**: Is the plan to use Microsoft Agent Framework for orchestration?
+2. **For DeepBoner mainline**: Is the plan to use Microsoft Agent Framework for orchestration?
 3. **Timeline**: How much time do we have to get this right?
 
 ---

docs/brainstorming/magentic-pydantic/REVIEW_PROMPT_FOR_SENIOR_AGENT.md

@@ -6,7 +6,7 @@ Copy and paste everything below this line to a fresh Claude/AI session:
 
 ## Context
 
-I am a junior developer working on a HuggingFace hackathon project called DeepCritical. We made a significant architectural mistake and are now trying to course-correct. I need you to act as a **senior staff engineer** and critically review our proposed solution.
+I am a junior developer working on a HuggingFace hackathon project called DeepBoner. We made a significant architectural mistake and are now trying to course-correct. I need you to act as a **senior staff engineer** and critically review our proposed solution.
 
 ## The Situation
 
@@ -62,28 +62,28 @@ Please perform a **deep, critical review** of:
 
 Please read these files in order:
 
-1. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/docs/brainstorming/magentic-pydantic/00_SITUATION_AND_PLAN.md`
-2. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/docs/brainstorming/magentic-pydantic/01_ARCHITECTURE_SPEC.md`
-3. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/docs/brainstorming/magentic-pydantic/02_IMPLEMENTATION_PHASES.md`
-4. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/docs/brainstorming/magentic-pydantic/03_IMMEDIATE_ACTIONS.md`
+1. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/docs/brainstorming/magentic-pydantic/00_SITUATION_AND_PLAN.md`
+2. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/docs/brainstorming/magentic-pydantic/01_ARCHITECTURE_SPEC.md`
+3. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/docs/brainstorming/magentic-pydantic/02_IMPLEMENTATION_PHASES.md`
+4. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/docs/brainstorming/magentic-pydantic/03_IMMEDIATE_ACTIONS.md`
 
 And the architecture diagram:
-5. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/assets/magentic-pydantic.png`
+5. `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/assets/magentic-pydantic.png`
 
 ## Reference Repositories to Consult
 
 We have local clones of the source-of-truth repositories:
 
-- **Original DeepCritical:** `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/reference_repos/DeepCritical/`
-- **Microsoft Agent Framework:** `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/reference_repos/agent-framework/`
-- **Microsoft AutoGen:** `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/reference_repos/autogen-microsoft/`
+- **Original DeepBoner:** `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/reference_repos/DeepBoner/`
+- **Microsoft Agent Framework:** `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/reference_repos/agent-framework/`
+- **Microsoft AutoGen:** `/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/reference_repos/autogen-microsoft/`
 
 Please cross-reference our hackathon fork against these to verify architectural alignment.
 
 ## Codebase to Analyze
 
 Our hackathon fork is at:
-`/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepCritical-1/`
+`/Users/ray/Desktop/CLARITY-DIGITAL-TWIN/DeepBoner-1/`
 
 Key files to examine:
 - `src/agents/` - Agent framework integration

docs/bugs/P1_GRADIO_SETTINGS_CLEANUP.md

@@ -55,7 +55,7 @@ def create_demo():
 def create_demo():
     return gr.ChatInterface(   # <--- FIX: Top-level component
         ...,
-        title="🧬 DeepCritical",
+        title="🧬 DeepBoner",
         description="*AI-Powered Drug Repurposing Agent...*\n\n---\n**MCP Server Active**...",
         additional_inputs_accordion=gr.Accordion(label="⚙️ Settings", open=False)
     )
@@ -69,7 +69,7 @@ def create_demo():
 2.  **Check**: Open `http://localhost:7860`
 3.  **Verify**:
     *   Settings accordion starts **COLLAPSED**.
-    *   Header title ("DeepCritical") is visible.
+    *   Header title ("DeepBoner") is visible.
     *   Footer text ("MCP Server Active") is visible in the description area.
     *   Chat functionality works (Magentic/Simple modes).
 

docs/development/testing.md

@@ -1,5 +1,5 @@
 # Testing Strategy
-## ensuring DeepCritical is Ironclad
+## ensuring DeepBoner is Ironclad
 
 ---
 

docs/guides/deployment.md

@@ -1,11 +1,11 @@
 # Deployment Guide
-## Launching DeepCritical: Gradio, MCP, & Modal
+## Launching DeepBoner: Gradio, MCP, & Modal
 
 ---
 
 ## Overview
 
-DeepCritical is designed for a multi-platform deployment strategy to maximize hackathon impact:
+DeepBoner is designed for a multi-platform deployment strategy to maximize hackathon impact:
 
 1. **HuggingFace Spaces**: Host the Gradio UI (User Interface).
 2. **MCP Server**: Expose research tools to Claude Desktop/Agents.
@@ -69,10 +69,10 @@ def predict(message, history):
    ```json
    {
      "mcpServers": {
-       "deepcritical": {
+       "deepboner": {
          "command": "uv",
          "args": ["run", "fastmcp", "run", "src/mcp_servers/pubmed_server.py"],
-         "cwd": "/absolute/path/to/DeepCritical"
+         "cwd": "/absolute/path/to/DeepBoner"
        }
      }
    }
@@ -111,7 +111,7 @@ Instead of calling Anthropic API, we call a Modal function:
 # src/llm/modal_client.py
 import modal
 
-stub = modal.Stub("deepcritical-inference")
+stub = modal.Stub("deepboner-inference")
 
 @stub.function(gpu="A100")
 def generate_text(prompt: str):

docs/implementation/01_phase_foundation.md

@@ -23,7 +23,7 @@ uv --version  # Should be >= 0.4.0
 
 ```bash
 # From project root
-uv init --name deepcritical
+uv init --name deepboner
 uv python install 3.11  # Pin Python version
 ```
 
@@ -35,9 +35,9 @@ uv python install 3.11  # Pin Python version
 
 ```toml
 [project]
-name = "deepcritical"
+name = "deepboner"
 version = "0.1.0"
-description = "AI-Native Drug Repurposing Research Agent"
+description = "AI-Native Sexual Health Research Agent"
 readme = "README.md"
 requires-python = ">=3.11"
 dependencies = [
@@ -401,25 +401,25 @@ settings = get_settings()
 ### `src/utils/exceptions.py`
 
 ```python
-"""Custom exceptions for DeepCritical."""
+"""Custom exceptions for DeepBoner."""
 
 
-class DeepCriticalError(Exception):
-    """Base exception for all DeepCritical errors."""
+class DeepBonerError(Exception):
+    """Base exception for all DeepBoner errors."""
     pass
 
 
-class SearchError(DeepCriticalError):
+class SearchError(DeepBonerError):
     """Raised when a search operation fails."""
     pass
 
 
-class JudgeError(DeepCriticalError):
+class JudgeError(DeepBonerError):
     """Raised when the judge fails to assess evidence."""
     pass
 
 
-class ConfigurationError(DeepCriticalError):
+class ConfigurationError(DeepBonerError):
     """Raised when configuration is invalid."""
     pass
 
@@ -558,7 +558,7 @@ uv run pre-commit install
 ## 10. Implementation Checklist
 
 - [ ] Install `uv` and verify version
-- [ ] Run `uv init --name deepcritical`
+- [ ] Run `uv init --name deepboner`
 - [ ] Create `pyproject.toml` (copy from above)
 - [ ] Create directory structure (run mkdir commands)
 - [ ] Create `.env.example` and `.env`

docs/implementation/04_phase_ui.md

@@ -401,7 +401,7 @@ Found {len(evidence)} sources. Consider refining your query for more specific re
 Using Gradio 5 generator pattern for real-time streaming.
 
 ```python
-"""Gradio UI for DeepCritical agent."""
+"""Gradio UI for DeepBoner agent."""
 import asyncio
 import gradio as gr
 from typing import AsyncGenerator
@@ -557,11 +557,11 @@ def create_demo() -> gr.Blocks:
         Configured Gradio Blocks interface
     """
     with gr.Blocks(
-        title="DeepCritical - Drug Repurposing Research Agent",
+        title="DeepBoner - Drug Repurposing Research Agent",
         theme=gr.themes.Soft(),
     ) as demo:
         gr.Markdown("""
-        # 🧬 DeepCritical
+        # 🧬 DeepBoner
         ## AI-Powered Drug Repurposing Research Agent
 
         Ask questions about potential drug repurposing opportunities.
@@ -935,7 +935,7 @@ class TestAgentEvent:
 ## 6. Dockerfile
 
 ```dockerfile
-# Dockerfile for DeepCritical
+# Dockerfile for DeepBoner
 FROM python:3.11-slim
 
 # Set working directory
@@ -975,7 +975,7 @@ Create `README.md` header for HuggingFace Spaces:
 
 ```markdown
 ---
-title: DeepCritical
+title: DeepBoner
 emoji: 🧬
 colorFrom: blue
 colorTo: purple
@@ -986,7 +986,7 @@ pinned: false
 license: mit
 ---
 
-# DeepCritical
+# DeepBoner
 
 AI-Powered Drug Repurposing Research Agent
 ```
@@ -1088,7 +1088,7 @@ After deployment to HuggingFace Spaces:
 
 ## Project Complete! 🎉
 
-When Phase 4 is done, the DeepCritical MVP is complete:
+When Phase 4 is done, the DeepBoner MVP is complete:
 
 - **Phase 1**: Foundation (uv, pytest, config) ✅
 - **Phase 2**: Search Slice (PubMed, DuckDuckGo) ✅

docs/implementation/10_phase_clinicaltrials.md

@@ -185,7 +185,7 @@ class ClinicalTrialsTool:
                 requests.get,
                 self.BASE_URL,
                 params=params,
-                headers={"User-Agent": "DeepCritical-Research-Agent/1.0"},
+                headers={"User-Agent": "DeepBoner-Research-Agent/1.0"},
                 timeout=30,
             )
             response.raise_for_status()
@@ -434,4 +434,4 @@ source .env && uv run python examples/search_demo/run_search.py "metformin alzhe
 | No phase info | Phase I/II/III evidence strength |
 
 **Demo pitch addition**:
-> "DeepCritical searches PubMed for peer-reviewed evidence AND ClinicalTrials.gov for 400,000+ clinical trials."
+> "DeepBoner searches PubMed for peer-reviewed evidence AND ClinicalTrials.gov for 400,000+ clinical trials."

docs/implementation/11_phase_biorxiv.md

@@ -531,7 +531,7 @@ source .env && uv run python examples/search_demo/run_search.py "metformin diabe
 | Miss cutting-edge | Catch breakthroughs early |
 
 **Demo pitch (final)**:
-> "DeepCritical searches PubMed for peer-reviewed evidence, ClinicalTrials.gov for 400,000+ clinical trials, and bioRxiv/medRxiv for cutting-edge preprints - then uses LLMs to generate mechanistic hypotheses and synthesize findings into publication-quality reports."
+> "DeepBoner searches PubMed for peer-reviewed evidence, ClinicalTrials.gov for 400,000+ clinical trials, and bioRxiv/medRxiv for cutting-edge preprints - then uses LLMs to generate mechanistic hypotheses and synthesize findings into publication-quality reports."
 
 ---
 

docs/implementation/12_phase_mcp_server.md

@@ -1,6 +1,6 @@
 # Phase 12 Implementation Spec: MCP Server Integration
 
-**Goal**: Expose DeepCritical search tools as MCP servers for Track 2 compliance.
+**Goal**: Expose DeepBoner search tools as MCP servers for Track 2 compliance.
 **Philosophy**: "MCP is the bridge between tools and LLMs."
 **Prerequisite**: Phase 11 complete (all search tools working)
 **Priority**: P0 - REQUIRED FOR HACKATHON TRACK 2
@@ -121,7 +121,7 @@ https://[space-id].hf.space/gradio_api/mcp/
 ### 4.1 MCP Tool Wrappers (`src/mcp_tools.py`)
 
 ```python
-"""MCP tool wrappers for DeepCritical search tools.
+"""MCP tool wrappers for DeepBoner search tools.
 
 These functions expose our search tools via MCP protocol.
 Each function follows the MCP tool contract:
@@ -130,15 +130,15 @@ Each function follows the MCP tool contract:
 - Formatted string returns
 """
 
-from src.tools.biorxiv import BioRxivTool
 from src.tools.clinicaltrials import ClinicalTrialsTool
+from src.tools.europepmc import EuropePMCTool
 from src.tools.pubmed import PubMedTool
 
 
 # Singleton instances (avoid recreating on each call)
 _pubmed = PubMedTool()
 _trials = ClinicalTrialsTool()
-_biorxiv = BioRxivTool()
+_europepmc = EuropePMCTool()
 
 
 async def search_pubmed(query: str, max_results: int = 10) -> str:
@@ -202,10 +202,10 @@ async def search_clinical_trials(query: str, max_results: int = 10) -> str:
     return "\n".join(formatted)
 
 
-async def search_biorxiv(query: str, max_results: int = 10) -> str:
-    """Search bioRxiv/medRxiv for preprint research.
+async def search_europepmc(query: str, max_results: int = 10) -> str:
+    """Search Europe PMC for preprint and open access research.
 
-    Searches bioRxiv and medRxiv preprint servers for cutting-edge research.
+    Searches Europe PMC for preprints and open access papers.
     Note: Preprints are NOT peer-reviewed but contain the latest findings.
 
     Args:
@@ -217,10 +217,10 @@ async def search_biorxiv(query: str, max_results: int = 10) -> str:
     """
     max_results = max(1, min(50, max_results))
 
-    results = await _biorxiv.search(query, max_results)
+    results = await _europepmc.search(query, max_results)
 
     if not results:
-        return f"No bioRxiv/medRxiv preprints found for: {query}"
+        return f"No Europe PMC results found for: {query}"
 
     formatted = [f"## Preprint Results for: {query}\n"]
     for i, evidence in enumerate(results, 1):
@@ -236,7 +236,7 @@ async def search_biorxiv(query: str, max_results: int = 10) -> str:
 async def search_all_sources(query: str, max_per_source: int = 5) -> str:
     """Search all biomedical sources simultaneously.
 
-    Performs parallel search across PubMed, ClinicalTrials.gov, and bioRxiv.
+    Performs parallel search across PubMed, ClinicalTrials.gov, and Europe PMC.
     This is the most comprehensive search option for drug repurposing research.
 
     Args:
@@ -253,10 +253,10 @@ async def search_all_sources(query: str, max_per_source: int = 5) -> str:
     # Run all searches in parallel
     pubmed_task = search_pubmed(query, max_per_source)
     trials_task = search_clinical_trials(query, max_per_source)
-    biorxiv_task = search_biorxiv(query, max_per_source)
+    europepmc_task = search_europepmc(query, max_per_source)
 
-    pubmed_results, trials_results, biorxiv_results = await asyncio.gather(
-        pubmed_task, trials_task, biorxiv_task, return_exceptions=True
+    pubmed_results, trials_results, europepmc_results = await asyncio.gather(
+        pubmed_task, trials_task, europepmc_task, return_exceptions=True
     )
 
     formatted = [f"# Comprehensive Search: {query}\n"]
@@ -272,10 +272,10 @@ async def search_all_sources(query: str, max_per_source: int = 5) -> str:
     else:
         formatted.append(f"## Clinical Trials\n*Error: {trials_results}*\n")
 
-    if isinstance(biorxiv_results, str):
-        formatted.append(biorxiv_results)
+    if isinstance(europepmc_results, str):
+        formatted.append(europepmc_results)
     else:
-        formatted.append(f"## Preprints\n*Error: {biorxiv_results}*\n")
+        formatted.append(f"## Preprints\n*Error: {europepmc_results}*\n")
 
     return "\n---\n".join(formatted)
 ```
@@ -283,7 +283,7 @@ async def search_all_sources(query: str, max_per_source: int = 5) -> str:
 ### 4.2 Update Gradio App (`src/app.py`)
 
 ```python
-"""Gradio UI for DeepCritical agent with MCP server support."""
+"""Gradio UI for DeepBoner agent with MCP server support."""
 
 import os
 from collections.abc import AsyncGenerator
@@ -294,12 +294,12 @@ import gradio as gr
 from src.agent_factory.judges import JudgeHandler, MockJudgeHandler
 from src.mcp_tools import (
     search_all_sources,
-    search_biorxiv,
+    search_europepmc,
     search_clinical_trials,
     search_pubmed,
 )
 from src.orchestrator_factory import create_orchestrator
-from src.tools.biorxiv import BioRxivTool
+from src.tools.europepmc import EuropePMCTool
 from src.tools.clinicaltrials import ClinicalTrialsTool
 from src.tools.pubmed import PubMedTool
 from src.tools.search_handler import SearchHandler
@@ -317,15 +317,15 @@ def create_demo() -> Any:
         Configured Gradio Blocks interface with MCP server enabled
     """
     with gr.Blocks(
-        title="DeepCritical - Drug Repurposing Research Agent",
+        title="DeepBoner - Drug Repurposing Research Agent",
         theme=gr.themes.Soft(),
     ) as demo:
         gr.Markdown("""
-        # DeepCritical
+        # DeepBoner
         ## AI-Powered Drug Repurposing Research Agent
 
         Ask questions about potential drug repurposing opportunities.
-        The agent searches PubMed, ClinicalTrials.gov, and bioRxiv/medRxiv preprints.
+        The agent searches PubMed, ClinicalTrials.gov, and Europe PMC preprints.
 
         **Example questions:**
         - "What drugs could be repurposed for Alzheimer's disease?"
@@ -381,13 +381,13 @@ def create_demo() -> Any:
 
         with gr.Tab("Preprints"):
             gr.Interface(
-                fn=search_biorxiv,
+                fn=search_europepmc,
                 inputs=[
                     gr.Textbox(label="Query", placeholder="long covid treatment"),
                     gr.Slider(1, 50, value=10, step=1, label="Max Results"),
                 ],
                 outputs=gr.Markdown(label="Results"),
-                api_name="search_biorxiv",
+                api_name="search_europepmc",
             )
 
         with gr.Tab("Search All"):
@@ -406,7 +406,7 @@ def create_demo() -> Any:
         **Note**: This is a research tool and should not be used for medical decisions.
         Always consult healthcare professionals for medical advice.
 
-        Built with PydanticAI + PubMed, ClinicalTrials.gov & bioRxiv
+        Built with PydanticAI + PubMed, ClinicalTrials.gov & Europe PMC
 
         **MCP Server**: Available at `/gradio_api/mcp/` for Claude Desktop integration
         """)
@@ -444,7 +444,7 @@ import pytest
 
 from src.mcp_tools import (
     search_all_sources,
-    search_biorxiv,
+    search_europepmc,
     search_clinical_trials,
     search_pubmed,
 )
@@ -525,18 +525,18 @@ class TestSearchClinicalTrials:
             assert "Clinical Trials" in result
 
 
-class TestSearchBiorxiv:
-    """Tests for search_biorxiv MCP tool."""
+class TestSearchEuropePMC:
+    """Tests for search_europepmc MCP tool."""
 
     @pytest.mark.asyncio
     async def test_returns_formatted_string(self, mock_evidence: Evidence) -> None:
         """Should return formatted markdown string."""
-        mock_evidence.citation.source = "biorxiv"  # type: ignore
+        mock_evidence.citation.source = "europepmc"  # type: ignore
 
-        with patch("src.mcp_tools._biorxiv") as mock_tool:
+        with patch("src.mcp_tools._europepmc") as mock_tool:
             mock_tool.search = AsyncMock(return_value=[mock_evidence])
 
-            result = await search_biorxiv("preprint search", 10)
+            result = await search_europepmc("preprint search", 10)
 
             assert isinstance(result, str)
             assert "Preprint Results" in result
@@ -550,11 +550,11 @@ class TestSearchAllSources:
         """Should combine results from all sources."""
         with patch("src.mcp_tools.search_pubmed", new_callable=AsyncMock) as mock_pubmed, \
              patch("src.mcp_tools.search_clinical_trials", new_callable=AsyncMock) as mock_trials, \
-             patch("src.mcp_tools.search_biorxiv", new_callable=AsyncMock) as mock_biorxiv:
+             patch("src.mcp_tools.search_europepmc", new_callable=AsyncMock) as mock_europepmc:
 
             mock_pubmed.return_value = "## PubMed Results"
             mock_trials.return_value = "## Clinical Trials"
-            mock_biorxiv.return_value = "## Preprints"
+            mock_europepmc.return_value = "## Preprints"
 
             result = await search_all_sources("metformin", 5)
 
@@ -568,11 +568,11 @@ class TestSearchAllSources:
         """Should handle partial failures gracefully."""
         with patch("src.mcp_tools.search_pubmed", new_callable=AsyncMock) as mock_pubmed, \
              patch("src.mcp_tools.search_clinical_trials", new_callable=AsyncMock) as mock_trials, \
-             patch("src.mcp_tools.search_biorxiv", new_callable=AsyncMock) as mock_biorxiv:
+             patch("src.mcp_tools.search_europepmc", new_callable=AsyncMock) as mock_europepmc:
 
             mock_pubmed.return_value = "## PubMed Results"
             mock_trials.side_effect = Exception("API Error")
-            mock_biorxiv.return_value = "## Preprints"
+            mock_europepmc.return_value = "## Preprints"
 
             result = await search_all_sources("metformin", 5)
 
@@ -599,10 +599,10 @@ class TestMCPDocstrings:
         assert search_clinical_trials.__doc__ is not None
         assert "Args:" in search_clinical_trials.__doc__
 
-    def test_search_biorxiv_has_args_section(self) -> None:
+    def test_search_europepmc_has_args_section(self) -> None:
         """Docstring must have Args section for MCP schema generation."""
-        assert search_biorxiv.__doc__ is not None
-        assert "Args:" in search_biorxiv.__doc__
+        assert search_europepmc.__doc__ is not None
+        assert "Args:" in search_europepmc.__doc__
 
     def test_search_all_sources_has_args_section(self) -> None:
         """Docstring must have Args section for MCP schema generation."""
@@ -672,7 +672,7 @@ class TestMCPServerIntegration:
 // %APPDATA%\Claude\claude_desktop_config.json (Windows)
 {
   "mcpServers": {
-    "deepcritical": {
+    "deepboner": {
       "url": "http://localhost:7860/gradio_api/mcp/"
     }
   }
@@ -684,8 +684,8 @@ class TestMCPServerIntegration:
 ```json
 {
   "mcpServers": {
-    "deepcritical": {
-      "url": "https://MCP-1st-Birthday-deepcritical.hf.space/gradio_api/mcp/"
+    "deepboner": {
+      "url": "https://your-space.hf.space/gradio_api/mcp/"
     }
   }
 }
@@ -696,7 +696,7 @@ class TestMCPServerIntegration:
 ```json
 {
   "mcpServers": {
-    "deepcritical": {
+    "deepboner": {
       "url": "https://your-space.hf.space/gradio_api/mcp/",
       "headers": {
         "Authorization": "Bearer hf_xxxxxxxxxxxxx"
@@ -761,7 +761,7 @@ Phase 12 is **COMPLETE** when:
    ```
 
 2. **Show Claude Desktop using our tools**:
-   - Open Claude Desktop with DeepCritical MCP configured
+   - Open Claude Desktop with DeepBoner MCP configured
    - Ask: "Search PubMed for metformin Alzheimer's"
    - Show real results appearing
    - Ask: "Now search clinical trials for the same"
@@ -817,14 +817,14 @@ Phase 12 is **COMPLETE** when:
 │                        Gradio MCP Server                        │
 │                  /gradio_api/mcp/                               │
 │  ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌─────────┐ │
-│  │search_pubmed │ │search_trials │ │search_biorxiv│ │search_  │ │
+│  │search_pubmed │ │search_trials │ │search_epmc   │ │search_  │ │
 │  │              │ │              │ │              │ │all      │ │
 │  └──────┬───────┘ └──────┬───────┘ └──────┬───────┘ └────┬────┘ │
 └─────────┼────────────────┼────────────────┼──────────────┼──────┘
           │                │                │              │
           ▼                ▼                ▼              ▼
    ┌──────────┐     ┌──────────┐     ┌──────────┐    (calls all)
-   │PubMedTool│     │Trials    │     │BioRxiv   │
+   │PubMedTool│     │Trials    │     │EuropePMC │
    │          │     │Tool      │     │Tool      │
    └──────────┘     └──────────┘     └──────────┘
 ```

docs/implementation/13_phase_modal_integration.md

@@ -872,7 +872,7 @@ async def main() -> None:
         sys.exit(1)
 
     print(f"\n{'=' * 60}")
-    print("DeepCritical Modal Analysis Demo")
+    print("DeepBoner Modal Analysis Demo")
     print(f"Query: {args.query}")
     print(f"{'=' * 60}\n")
 

docs/implementation/14_phase_demo_submission.md

@@ -71,7 +71,7 @@ tags:
 
 [Show Gradio UI]
 
-"DeepCritical is an AI-powered drug repurposing research agent.
+"DeepBoner is an AI-powered drug repurposing research agent.
 It searches peer-reviewed literature, clinical trials, and cutting-edge preprints
 to find new uses for existing drugs."
 
@@ -83,7 +83,7 @@ to find new uses for existing drugs."
 
 [Type query: "Can metformin treat Alzheimer's disease?"]
 
-"When I ask about metformin for Alzheimer's, DeepCritical:
+"When I ask about metformin for Alzheimer's, DeepBoner:
 1. Searches PubMed for peer-reviewed papers
 2. Queries ClinicalTrials.gov for active trials
 3. Scans bioRxiv for the latest preprints"
@@ -101,10 +101,10 @@ synthesize findings into a structured research report."
 
 [Switch to Claude Desktop]
 
-"What makes DeepCritical unique is full MCP integration.
+"What makes DeepBoner unique is full MCP integration.
 These same tools are available to any MCP client."
 
-[Show Claude Desktop with DeepCritical tools]
+[Show Claude Desktop with DeepBoner tools]
 
 "I can ask Claude: 'Search PubMed for aspirin cancer prevention'"
 
@@ -140,7 +140,7 @@ returning verdicts like SUPPORTED, REFUTED, or INCONCLUSIVE."
 
 [Return to Gradio UI]
 
-"DeepCritical brings together:
+"DeepBoner brings together:
 - Three biomedical data sources
 - MCP protocol for universal tool access
 - Modal sandboxes for safe code execution
@@ -164,7 +164,7 @@ and let us know what you think."
 
 ```markdown
 ---
-title: DeepCritical
+title: DeepBoner
 emoji: 🧬
 colorFrom: blue
 colorTo: purple
@@ -183,7 +183,7 @@ tags:
   - modal
 ---
 
-# DeepCritical
+# DeepBoner
 
 AI-Powered Drug Repurposing Research Agent
 
@@ -198,7 +198,7 @@ AI-Powered Drug Repurposing Research Agent
 
 Connect to our MCP server at:
 ```
-https://MCP-1st-Birthday-deepcritical.hf.space/gradio_api/mcp/
+https://your-space.hf.space/gradio_api/mcp/
 ```
 
 Available tools:
@@ -214,7 +214,7 @@ Available tools:
 
 ## Links
 
-- [GitHub Repository](https://github.com/The-Obstacle-Is-The-Way/DeepCritical-1)
+- [GitHub Repository](https://github.com/The-Obstacle-Is-The-Way/DeepBoner-1)
 - [Demo Video](link-to-video)
 ```
 
@@ -237,7 +237,7 @@ MODAL_TOKEN_SECRET=...
 ### Twitter/X Template
 
 ```
-🧬 Excited to submit DeepCritical to MCP's 1st Birthday Hackathon!
+🧬 Excited to submit DeepBoner to MCP's 1st Birthday Hackathon!
 
 An AI agent that:
 ✅ Searches PubMed, ClinicalTrials.gov & bioRxiv
@@ -254,10 +254,10 @@ Demo: [Video link]
 ### LinkedIn Template
 
 ```
-Thrilled to share DeepCritical - our submission to MCP's 1st Birthday Hackathon!
+Thrilled to share DeepBoner - our submission to MCP's 1st Birthday Hackathon!
 
 🔬 What it does:
-DeepCritical is an AI-powered drug repurposing research agent that searches
+DeepBoner is an AI-powered drug repurposing research agent that searches
 peer-reviewed literature, clinical trials, and preprints to find new uses
 for existing drugs.
 

docs/implementation/roadmap.md

@@ -1,8 +1,8 @@
-# Implementation Roadmap: DeepCritical (Vertical Slices)
+# Implementation Roadmap: DeepBoner (Vertical Slices)
 
 **Philosophy:** AI-Native Engineering, Vertical Slice Architecture, TDD, Modern Tooling (2025).
 
-This roadmap defines the execution strategy to deliver **DeepCritical** effectively. We reject "overplanning" in favor of **ironclad, testable vertical slices**. Each phase delivers a fully functional slice of end-to-end value.
+This roadmap defines the execution strategy to deliver **DeepBoner** effectively. We reject "overplanning" in favor of **ironclad, testable vertical slices**. Each phase delivers a fully functional slice of end-to-end value.
 
 ---
 
@@ -114,7 +114,7 @@ tests/
 
 - [ ] Implement `src/orchestrator.py` (Connects Search + Judge loops).
 - [ ] Build `src/app.py` (Gradio with Streaming).
-- **Deliverable**: Working DeepCritical Agent on HuggingFace.
+- **Deliverable**: Working DeepBoner Agent on HuggingFace.
 
 ---
 

docs/index.md

@@ -1,4 +1,4 @@
-# DeepCritical Documentation
+# DeepBoner Documentation
 
 ## Medical Drug Repurposing Research Agent
 

docs/to_do/DEEP_RESEARCH_ROADMAP.md

@@ -0,0 +1,337 @@
+# Deep Research Roadmap
+
+> How to properly add GPT-Researcher-style deep research to DeepBoner
+> using the EXISTING Magentic + Pydantic AI architecture.
+
+## Current State
+
+We already have:
+
+| Feature | Location | Status |
+|---------|----------|--------|
+| Multi-agent orchestration | `orchestrator_magentic.py` | Working |
+| SearchAgent, JudgeAgent, HypothesisAgent, ReportAgent | `agents/magentic_agents.py` | Working |
+| HuggingFace free tier | `agent_factory/judges.py` (HFInferenceJudgeHandler) | Working |
+| Budget constraints | MagenticOrchestrator (max_round_count, max_stall_count) | Built-in |
+| Simple mode (linear) | `orchestrator.py` | Working |
+
+## What Deep Research Adds
+
+GPT-Researcher style "deep research" means:
+
+1. **Query Analysis** - Detect if query needs simple lookup vs comprehensive report
+2. **Section Planning** - Break complex query into 3-7 parallel research sections
+3. **Parallel Research** - Run multiple research loops simultaneously
+4. **Long-form Writing** - Synthesize sections into cohesive report
+5. **RAG** - Semantic search over accumulated evidence
+
+## Implementation Plan (TDD, Vertical Slices)
+
+### Phase 1: Input Parser (Est. 50-100 lines)
+
+**Goal**: Detect research mode from query.
+
+```python
+# src/agents/input_parser.py
+
+class ParsedQuery(BaseModel):
+    original_query: str
+    improved_query: str
+    research_mode: Literal["iterative", "deep"]
+    key_entities: list[str]
+
+async def parse_query(query: str) -> ParsedQuery:
+    """
+    Detect if query needs deep research.
+
+    Deep indicators:
+    - "comprehensive", "report", "overview", "analysis"
+    - Multiple topics/drugs mentioned
+    - Requests for sections/structure
+
+    Iterative indicators:
+    - Single focused question
+    - "what is", "how does", "find"
+    """
+```
+
+**Test first**:
+```python
+def test_parse_query_detects_deep_mode():
+    result = await parse_query("Write a comprehensive report on Alzheimer's treatments")
+    assert result.research_mode == "deep"
+
+def test_parse_query_detects_iterative_mode():
+    result = await parse_query("What is the mechanism of metformin?")
+    assert result.research_mode == "iterative"
+```
+
+**Wire in**:
+```python
+# In app.py or orchestrator_factory.py
+parsed = await parse_query(user_query)
+if parsed.research_mode == "deep":
+    orchestrator = create_deep_orchestrator()
+else:
+    orchestrator = create_orchestrator()  # existing
+```
+
+---
+
+### Phase 2: Section Planner (Est. 80-120 lines)
+
+**Goal**: Create report outline for deep research.
+
+```python
+# src/agents/planner.py
+
+class ReportSection(BaseModel):
+    title: str
+    query: str  # Search query for this section
+    description: str
+
+class ReportPlan(BaseModel):
+    title: str
+    sections: list[ReportSection]
+
+# Use existing ChatAgent pattern from magentic_agents.py
+def create_planner_agent(chat_client: OpenAIChatClient | None = None) -> ChatAgent:
+    return ChatAgent(
+        name="PlannerAgent",
+        description="Creates structured report outlines",
+        instructions="""Given a research query, create a report plan with 3-7 sections.
+        Each section should have:
+        - A clear title
+        - A focused search query
+        - Brief description of what to cover
+
+        Example for "Alzheimer's drug repurposing":
+        1. Current Treatment Landscape
+        2. Mechanism-Based Candidates (targeting amyloid, tau, inflammation)
+        3. Clinical Trial Evidence
+        4. Safety Considerations
+        5. Emerging Research Directions
+        """,
+        chat_client=client,
+    )
+```
+
+**Test first**:
+```python
+def test_planner_creates_sections():
+    plan = await planner.create_plan("Comprehensive Alzheimer's drug repurposing report")
+    assert len(plan.sections) >= 3
+    assert all(s.query for s in plan.sections)
+```
+
+**Wire in**: Used by Phase 3.
+
+---
+
+### Phase 3: Parallel Research Flow (Est. 100-150 lines)
+
+**Goal**: Run multiple MagenticOrchestrator instances in parallel.
+
+```python
+# src/orchestrator_deep.py
+
+class DeepResearchOrchestrator:
+    """
+    Runs parallel research loops using EXISTING MagenticOrchestrator.
+
+    NOT a new orchestration system - just a wrapper that:
+    1. Plans sections
+    2. Runs existing orchestrator per section (in parallel)
+    3. Aggregates results
+    """
+
+    def __init__(self, max_parallel: int = 5):
+        self.planner = create_planner_agent()
+        self.max_parallel = max_parallel
+
+    async def run(self, query: str) -> AsyncGenerator[AgentEvent, None]:
+        # 1. Create plan
+        plan = await self.planner.create_plan(query)
+        yield AgentEvent(type="planning", message=f"Created {len(plan.sections)} section plan")
+
+        # 2. Run parallel research (reuse existing orchestrator!)
+        from src.orchestrator_magentic import MagenticOrchestrator
+
+        async def research_section(section: ReportSection) -> str:
+            orchestrator = MagenticOrchestrator(max_rounds=5)  # Fewer rounds per section
+            result = ""
+            async for event in orchestrator.run(section.query):
+                if event.type == "complete":
+                    result = event.message
+            return result
+
+        # Run in parallel with semaphore
+        semaphore = asyncio.Semaphore(self.max_parallel)
+        async def bounded_research(section):
+            async with semaphore:
+                return await research_section(section)
+
+        results = await asyncio.gather(*[
+            bounded_research(s) for s in plan.sections
+        ])
+
+        # 3. Aggregate
+        yield AgentEvent(
+            type="complete",
+            message=self._aggregate_sections(plan, results)
+        )
+```
+
+**Key insight**: We're NOT replacing MagenticOrchestrator. We're running multiple instances of it.
+
+**Test first**:
+```python
+@pytest.mark.integration
+async def test_deep_orchestrator_runs_parallel():
+    orchestrator = DeepResearchOrchestrator(max_parallel=2)
+    events = [e async for e in orchestrator.run("Comprehensive Alzheimer's report")]
+    assert any(e.type == "planning" for e in events)
+    assert any(e.type == "complete" for e in events)
+```
+
+---
+
+### Phase 4: RAG Integration (Est. 100-150 lines)
+
+**Goal**: Semantic search over accumulated evidence.
+
+> **Note**: We already have `src/services/embeddings.py` (EmbeddingService) which provides
+> ChromaDB + sentence-transformers with `add_evidence()` and `search_similar()` methods.
+> The code below is illustrative - in practice, extend EmbeddingService or use it directly.
+> See also: `src/services/llamaindex_rag.py` for OpenAI-based RAG (different use case).
+
+```python
+# src/services/rag.py (illustrative - use EmbeddingService instead)
+
+class RAGService:
+    """
+    Simple RAG using ChromaDB + sentence-transformers.
+    No LlamaIndex dependency - keep it lightweight.
+    """
+
+    def __init__(self):
+        import chromadb
+        from sentence_transformers import SentenceTransformer
+
+        self.client = chromadb.Client()
+        self.collection = self.client.get_or_create_collection("evidence")
+        self.encoder = SentenceTransformer("all-MiniLM-L6-v2")
+
+    def add_evidence(self, evidence: list[Evidence]) -> int:
+        """Add evidence to vector store, return count added."""
+        # Dedupe by URL
+        existing = set(self.collection.get()["ids"])
+        new_evidence = [e for e in evidence if e.citation.url not in existing]
+
+        if not new_evidence:
+            return 0
+
+        self.collection.add(
+            ids=[e.citation.url for e in new_evidence],
+            documents=[e.content for e in new_evidence],
+            metadatas=[{"title": e.citation.title, "source": e.citation.source} for e in new_evidence],
+        )
+        return len(new_evidence)
+
+    def search(self, query: str, n_results: int = 5) -> list[Evidence]:
+        """Semantic search for relevant evidence."""
+        results = self.collection.query(query_texts=[query], n_results=n_results)
+        # Convert back to Evidence objects
+        ...
+```
+
+**Wire in as tool**:
+```python
+# Add to SearchAgent's tools
+def rag_search(query: str, n_results: int = 5) -> str:
+    """Search previously collected evidence for relevant information."""
+    service = get_rag_service()
+    results = service.search(query, n_results)
+    return format_evidence(results)
+
+# In magentic_agents.py
+ChatAgent(
+    tools=[search_pubmed, search_clinical_trials, search_preprints, rag_search],  # ADD RAG
+)
+```
+
+---
+
+### Phase 5: Long Writer (Est. 80-100 lines)
+
+**Goal**: Write longer reports section-by-section.
+
+```python
+# Extend existing ReportAgent or create LongWriterAgent
+
+def create_long_writer_agent() -> ChatAgent:
+    return ChatAgent(
+        name="LongWriterAgent",
+        description="Writes detailed report sections with proper citations",
+        instructions="""Write a detailed section for a research report.
+
+        You will receive:
+        - Section title
+        - Relevant evidence/findings
+        - What previous sections covered (to avoid repetition)
+
+        Output:
+        - 500-1000 words per section
+        - Proper citations [1], [2], etc.
+        - Smooth transitions
+        - No repetition of earlier content
+        """,
+        tools=[get_bibliography, rag_search],
+    )
+```
+
+---
+
+## What NOT To Build
+
+These are REDUNDANT with existing Magentic system:
+
+| Component | Why Skip |
+|-----------|----------|
+| GraphOrchestrator | MagenticBuilder already handles agent coordination |
+| BudgetTracker | MagenticBuilder has max_round_count, max_stall_count |
+| WorkflowManager | asyncio.gather() + Semaphore is simpler |
+| StateMachine | contextvars already used in agents/state.py |
+| New agent primitives | ChatAgent pattern already works |
+
+## Implementation Order
+
+```
+Week 1: Phase 1 (InputParser) - Ship it working
+Week 2: Phase 2 (Planner) - Ship it working
+Week 3: Phase 3 (Parallel Flow) - Ship it working
+Week 4: Phase 4 (RAG) - Ship it working
+Week 5: Phase 5 (LongWriter) - Ship it working
+```
+
+Each phase:
+1. Write tests first
+2. Implement minimal code
+3. Wire into app.py
+4. Manual test
+5. PR with <200 lines
+6. Ship
+
+## References
+
+- GPT-Researcher: https://github.com/assafelovic/gpt-researcher
+- LangGraph patterns: https://python.langchain.com/docs/langgraph
+- Your existing Magentic setup: `src/orchestrator_magentic.py`
+
+## Why This Approach
+
+1. **Builds on existing working code** - Don't replace, extend
+2. **Each phase ships value** - User sees improvement after each PR
+3. **Tests prove it works** - Not "trust me it imports"
+4. **Minimal new abstractions** - Reuse ChatAgent, MagenticOrchestrator
+5. **~500 total lines** vs 7,000 lines of parallel infrastructure

docs/to_do/REFERENCE_GRADDIO_DEMO_ANALYSIS.md

@@ -0,0 +1,229 @@
+# Reference: GradioDemo Analysis
+
+> Analysis of code from https://github.com/DeepBoner/GradioDemo
+> Purpose: Extract good ideas, understand patterns, avoid mistakes
+
+## Overview
+
+| Metric | Value |
+|--------|-------|
+| Total lines added | ~7,000 |
+| New Python files | +20 |
+| Test pass rate | 80% (62 errors due to missing mocks) |
+| Integration status | **NOT WIRED IN** |
+
+## Component Catalog
+
+### REDUNDANT (Already have equivalent)
+
+| Component | Lines | What We Have Instead |
+|-----------|-------|---------------------|
+| `orchestrator/graph_orchestrator.py` | 974 | MagenticBuilder |
+| `middleware/budget_tracker.py` | 391 | MagenticBuilder max_round_count |
+| `middleware/state_machine.py` | 130 | agents/state.py with contextvars |
+| `middleware/workflow_manager.py` | 300 | asyncio.gather() |
+| `orchestrator/research_flow.py` (IterativeResearchFlow) | 500 | MagenticOrchestrator |
+| HuggingFace integration | various | HFInferenceJudgeHandler |
+
+### POTENTIALLY USEFUL (Ideas to cherry-pick)
+
+#### 1. InputParser (`agents/input_parser.py` - 179 lines)
+
+**Idea**: Detect research mode from query text.
+
+```python
+# Key logic (simplified)
+research_mode: Literal["iterative", "deep"] = "iterative"
+if any(keyword in query.lower() for keyword in [
+    "comprehensive", "report", "sections", "analyze", "analysis", "overview", "market"
+]):
+    research_mode = "deep"
+```
+
+**Good pattern**: Heuristic fallback when LLM fails.
+**Our implementation**: See Phase 1 in DEEP_RESEARCH_ROADMAP.md
+
+#### 2. PlannerAgent (`orchestrator/planner_agent.py` - 184 lines)
+
+**Idea**: LLM creates section outline for report.
+
+```python
+class ReportPlan(BaseModel):
+    title: str
+    sections: list[ReportSection]
+    estimated_time_minutes: int
+
+class ReportSection(BaseModel):
+    title: str
+    query: str
+    description: str
+    priority: int
+```
+
+**Good pattern**: Structured output with Pydantic models.
+**Our implementation**: See Phase 2 in DEEP_RESEARCH_ROADMAP.md
+
+#### 3. DeepResearchFlow (`orchestrator/research_flow.py` - 500 lines)
+
+**Idea**: Run parallel research loops per section.
+
+```python
+# Their pattern (simplified)
+async def run_parallel_loops(sections: list[ReportSection]):
+    tasks = [run_single_loop(s) for s in sections]
+    results = await asyncio.gather(*tasks, return_exceptions=True)
+```
+
+**Problem**: They built new IterativeResearchFlow instead of reusing MagenticOrchestrator.
+**Our implementation**: Just run multiple MagenticOrchestrator instances.
+
+#### 4. LlamaIndex RAG (`services/llamaindex_rag.py` - 454 lines)
+
+**Idea**: Semantic search over collected evidence.
+
+```python
+# Their approach
+class LlamaIndexRAGService:
+    def __init__(self):
+        # ChromaDB + LlamaIndex + HuggingFace embeddings
+        self.vector_store = ChromaVectorStore(...)
+        self.index = VectorStoreIndex(...)
+
+    def retrieve(self, query: str, top_k: int = 5) -> list[dict]:
+        retriever = VectorIndexRetriever(index=self.index, similarity_top_k=top_k)
+        return retriever.retrieve(query)
+```
+
+**Good**: Full-featured RAG with multiple embedding providers.
+**Simpler alternative**: Direct ChromaDB + sentence-transformers (no LlamaIndex).
+**Our implementation**: See Phase 4 in DEEP_RESEARCH_ROADMAP.md
+
+#### 5. LongWriterAgent (`agents/long_writer.py` - ~300 lines)
+
+**Idea**: Write reports section-by-section to handle length.
+
+```python
+class SectionOutput(BaseModel):
+    section_content: str
+    references: list[str]
+    next_section_context: str  # What to avoid repeating
+
+async def write_next_section(
+    section_title: str,
+    findings: str,
+    previous_sections: str,  # Avoid repetition
+) -> SectionOutput:
+```
+
+**Good pattern**: Passing context to avoid repetition.
+**Our implementation**: See Phase 5 in DEEP_RESEARCH_ROADMAP.md
+
+#### 6. ProofreaderAgent (`agents/proofreader.py` - ~200 lines)
+
+**Idea**: Final cleanup pass on report.
+
+```python
+# Tasks:
+# 1. Remove duplicate information
+# 2. Fix citation numbering
+# 3. Add executive summary
+# 4. Ensure consistent formatting
+```
+
+**Good pattern**: Separate concerns - writer writes, proofreader polishes.
+**Our implementation**: Optional Phase 6 if needed.
+
+### Graph Architecture (Educational Reference)
+
+The graph system is well-designed in theory:
+
+```python
+# Node types
+class AgentNode(GraphNode):
+    agent: Any  # Pydantic AI agent
+    input_transformer: Callable  # Transform input
+    output_transformer: Callable  # Transform output
+
+class DecisionNode(GraphNode):
+    decision_function: Callable[[Any], str]  # Returns next node ID
+    options: list[str]
+
+class ParallelNode(GraphNode):
+    parallel_nodes: list[str]  # Run these in parallel
+    aggregator: Callable  # Combine results
+
+# Graph structure
+class ResearchGraph:
+    nodes: dict[str, GraphNode]
+    edges: dict[str, list[GraphEdge]]
+    entry_node: str
+    exit_nodes: list[str]
+```
+
+**Why we don't need it**: MagenticBuilder already provides:
+- Agent coordination via manager
+- Conditional routing (manager decides)
+- Multiple participants
+
+This is essentially reimplementing what `agent-framework` already does.
+
+## Key Lessons
+
+### What Went Wrong
+
+1. **Parallel architecture** - Built new system instead of extending existing
+2. **Horizontal sprawl** - All infrastructure, nothing wired in
+3. **Test mocking** - Tests don't mock API clients properly
+4. **No manual testing** - Code never ran end-to-end
+
+### What To Learn From
+
+1. **Pydantic models for structured output** - Good pattern
+2. **Heuristic fallbacks** - When LLM fails, have a fallback
+3. **Section-by-section writing** - For long reports
+4. **RAG for evidence retrieval** - Useful for large evidence sets
+
+### The 7,000 Line vs 500 Line Comparison
+
+**Their approach**:
+- New GraphOrchestrator (974 lines)
+- New ResearchFlow (999 lines)
+- New BudgetTracker (391 lines)
+- New StateMachine (130 lines)
+- New WorkflowManager (300 lines)
+- New agents (InputParser, Writer, LongWriter, Proofreader, etc.)
+- Total: ~7,000 lines, not integrated
+
+**Our approach**:
+- InputParser (50-100 lines) - extends existing
+- PlannerAgent (80-120 lines) - uses ChatAgent pattern
+- DeepOrchestrator (100-150 lines) - wraps MagenticOrchestrator
+- RAGService (100-150 lines) - simple ChromaDB
+- LongWriter (80-100 lines) - extends ReportAgent
+- Total: ~500 lines, each phase ships working
+
+## File Locations (for reference)
+
+```
+reference_repos/GradioDemo/src/
+├── orchestrator/
+│   ├── graph_orchestrator.py    # 974 lines - graph execution
+│   ├── research_flow.py         # 999 lines - iterative/deep flows
+│   └── planner_agent.py         # 184 lines - section planning
+├── agents/
+│   ├── input_parser.py          # 179 lines - query analysis
+│   ├── writer.py                # 210 lines - report writing
+│   ├── long_writer.py           # ~300 lines - section writing
+│   ├── proofreader.py           # ~200 lines - cleanup
+│   └── knowledge_gap.py         # gap detection
+├── middleware/
+│   ├── budget_tracker.py        # 391 lines - token/time tracking
+│   ├── state_machine.py         # 130 lines - workflow state
+│   └── workflow_manager.py      # 300 lines - parallel loop mgmt
+├── services/
+│   └── llamaindex_rag.py        # 454 lines - RAG service
+├── tools/
+│   └── rag_tool.py              # 191 lines - RAG as search tool
+└── agent_factory/
+    └── graph_builder.py         # ~400 lines - graph construction
+```

docs/workflow-diagrams.md

@@ -1,4 +1,4 @@
-# DeepCritical Workflow - Simplified Magentic Architecture
+# DeepBoner Workflow - Simplified Magentic Architecture
 
 > **Architecture Pattern**: Microsoft Magentic Orchestration
 > **Design Philosophy**: Simple, dynamic, manager-driven coordination
@@ -475,7 +475,7 @@ stateDiagram-v2
 
 ```mermaid
 graph TD
-    App[Gradio App<br/>DeepCritical Research Agent]
+    App[Gradio App<br/>DeepBoner Research Agent]
 
     App --> Input[Input Section]
     App --> Status[Status Section]
@@ -514,7 +514,7 @@ graph TD
 
 ```mermaid
 graph LR
-    User[👤 Researcher<br/>Asks research questions] -->|Submits query| DC[DeepCritical<br/>Magentic Workflow]
+    User[👤 Researcher<br/>Asks research questions] -->|Submits query| DC[DeepBoner<br/>Magentic Workflow]
 
     DC -->|Literature search| PubMed[PubMed API<br/>Medical papers]
     DC -->|Preprint search| ArXiv[arXiv API<br/>Scientific preprints]
@@ -549,7 +549,7 @@ graph LR
 
 ```mermaid
 gantt
-    title DeepCritical Magentic Workflow - Typical Execution
+    title DeepBoner Magentic Workflow - Typical Execution
     dateFormat mm:ss
     axisFormat %M:%S
 

examples/README.md

@@ -1,4 +1,4 @@
-# DeepCritical Examples
+# DeepBoner Examples
 
 **NO MOCKS. NO FAKE DATA. REAL SCIENCE.**
 
@@ -181,4 +181,4 @@ Mocks belong in `tests/unit/`, not in demos. When you run these examples, you se
 - Real scientific hypotheses
 - Real research reports
 
-This is what DeepCritical actually does. No fake data. No canned responses.
+This is what DeepBoner actually does. No fake data. No canned responses.

examples/embeddings_demo/run_embeddings.py

@@ -35,7 +35,7 @@ def create_fresh_service(name_suffix: str = "") -> EmbeddingService:
 async def demo_real_pipeline() -> None:
     """Run the demo using REAL PubMed data."""
     print("\n" + "=" * 60)
-    print("DeepCritical Embeddings Demo (REAL DATA)")
+    print("DeepBoner Embeddings Demo (REAL DATA)")
     print("=" * 60)
 
     # 1. Fetch Real Data

examples/full_stack_demo/run_full.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Demo: Full Stack DeepCritical Agent (Phases 1-8).
+Demo: Full Stack DeepBoner Agent (Phases 1-8).
 
 This script demonstrates the COMPLETE REAL drug repurposing research pipeline:
 - Phase 2: REAL Search (PubMed + ClinicalTrials + Europe PMC)
@@ -104,7 +104,7 @@ async def _handle_judge_step(
 
 async def run_full_demo(query: str, max_iterations: int) -> None:
     """Run the REAL full stack pipeline."""
-    print_header("DeepCritical Full Stack Demo (REAL)")
+    print_header("DeepBoner Full Stack Demo (REAL)")
     print(f"Query: {query}")
     print(f"Max iterations: {max_iterations}")
     print("Mode: REAL (All live API calls - no mocks)\n")
@@ -172,7 +172,7 @@ async def run_full_demo(query: str, max_iterations: int) -> None:
 async def main() -> None:
     """Entry point."""
     parser = argparse.ArgumentParser(
-        description="DeepCritical Full Stack Demo - REAL, No Mocks",
+        description="DeepBoner Full Stack Demo - REAL, No Mocks",
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog="""
 This demo runs the COMPLETE pipeline with REAL API calls:
@@ -222,7 +222,7 @@ Examples:
     await run_full_demo(args.query, args.iterations)
 
     print("\n" + "=" * 70)
-    print("  DeepCritical Full Stack Demo Complete!")
+    print("  DeepBoner Full Stack Demo Complete!")
     print("  ")
     print("  Everything you just saw was REAL:")
     print("    - Real PubMed + ClinicalTrials + Europe PMC searches")

examples/hypothesis_demo/run_hypothesis.py

@@ -31,7 +31,7 @@ async def run_hypothesis_demo(query: str) -> None:
     """Run the REAL hypothesis generation pipeline."""
     try:
         print(f"\n{'=' * 60}")
-        print("DeepCritical Hypothesis Agent Demo (Phase 7)")
+        print("DeepBoner Hypothesis Agent Demo (Phase 7)")
         print(f"Query: {query}")
         print("Mode: REAL (Live API calls)")
         print(f"{'=' * 60}\n")

examples/modal_demo/run_analysis.py

@@ -32,7 +32,7 @@ async def main() -> None:
         sys.exit(1)
 
     print(f"\n{'=' * 60}")
-    print("DeepCritical Modal Analysis Demo")
+    print("DeepBoner Modal Analysis Demo")
     print(f"Query: {args.query}")
     print(f"{'=' * 60}\n")
 

examples/orchestrator_demo/run_agent.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Demo: DeepCritical Agent Loop (Search + Judge + Orchestrator).
+Demo: DeepBoner Agent Loop (Search + Judge + Orchestrator).
 
 This script demonstrates the REAL Phase 4 orchestration:
 - REAL Iterative Search (PubMed + ClinicalTrials + Europe PMC)
@@ -36,7 +36,7 @@ MAX_ITERATIONS = 10
 async def main() -> None:
     """Run the REAL agent demo."""
     parser = argparse.ArgumentParser(
-        description="DeepCritical Agent Demo - REAL, No Mocks",
+        description="DeepBoner Agent Demo - REAL, No Mocks",
         formatter_class=argparse.RawDescriptionHelpFormatter,
         epilog="""
 This demo runs the REAL search-judge-synthesize loop:
@@ -72,7 +72,7 @@ Examples:
         sys.exit(1)
 
     print(f"\n{'=' * 60}")
-    print("DeepCritical Agent Demo (REAL)")
+    print("DeepBoner Agent Demo (REAL)")
     print(f"Query: {args.query}")
     print(f"Max Iterations: {args.iterations}")
     print("Mode: REAL (All live API calls)")

examples/orchestrator_demo/run_magentic.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Demo: Magentic-One Orchestrator for DeepCritical.
+Demo: Magentic-One Orchestrator for DeepBoner.
 
 This script demonstrates Phase 5 functionality:
 - Multi-Agent Coordination (Searcher + Judge + Manager)
@@ -27,7 +27,7 @@ from src.utils.models import OrchestratorConfig
 
 async def main() -> None:
     """Run the magentic agent demo."""
-    parser = argparse.ArgumentParser(description="Run DeepCritical Magentic Agent")
+    parser = argparse.ArgumentParser(description="Run DeepBoner Magentic Agent")
     parser.add_argument("query", help="Research query (e.g., 'metformin cancer')")
     parser.add_argument("--iterations", type=int, default=10, help="Max rounds")
     args = parser.parse_args()
@@ -40,7 +40,7 @@ async def main() -> None:
         sys.exit(1)
 
     print(f"\n{'=' * 60}")
-    print("DeepCritical Magentic Agent Demo")
+    print("DeepBoner Magentic Agent Demo")
     print(f"Query: {args.query}")
     print("Mode: MAGENTIC (Multi-Agent)")
     print(f"{'=' * 60}\n")

examples/search_demo/run_search.py

@@ -30,7 +30,7 @@ from src.tools.search_handler import SearchHandler
 async def main(query: str) -> None:
     """Run search demo with the given query."""
     print(f"\n{'=' * 60}")
-    print("DeepCritical Search Demo")
+    print("DeepBoner Search Demo")
     print(f"Query: {query}")
     print(f"{'=' * 60}\n")
 

main.py

@@ -1,5 +1,5 @@
 def main():
-    print("Hello from deepcritical!")
+    print("Hello from deepboner!")
 
 
 if __name__ == "__main__":

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
-name = "deepcritical"
+name = "deepboner"
 version = "0.1.0"
-description = "AI-Native Drug Repurposing Research Agent"
+description = "AI-Native Sexual Health Research Agent"
 readme = "README.md"
 requires-python = ">=3.11"
 dependencies = [
@@ -126,6 +126,18 @@ markers = [
     "integration: Integration tests (real APIs)",
     "slow: Slow tests",
 ]
+# Filter warnings from unittest.mock introspecting Pydantic models.
+# This is a known upstream issue: https://github.com/pydantic/pydantic/issues/9927
+# When autospec=True, mock.py accesses deprecated Pydantic attributes during introspection.
+# We filter these specifically because it's NOT our code triggering deprecations.
+filterwarnings = [
+    # Pydantic 2.0 deprecations triggered by mock introspection
+    "ignore:The `__fields__` attribute is deprecated:pydantic.warnings.PydanticDeprecatedSince20",
+    "ignore:The `__fields_set__` attribute is deprecated:pydantic.warnings.PydanticDeprecatedSince20",
+    # Pydantic 2.11 deprecations triggered by mock introspection
+    "ignore:Accessing the 'model_computed_fields' attribute on the instance is deprecated:pydantic.warnings.PydanticDeprecatedSince211",
+    "ignore:Accessing the 'model_fields' attribute on the instance is deprecated:pydantic.warnings.PydanticDeprecatedSince211",
+]
 
 # ============== COVERAGE CONFIG ==============
 [tool.coverage.run]

src/agent_factory/judges.py

@@ -9,7 +9,7 @@ from huggingface_hub import InferenceClient
 from pydantic_ai import Agent
 from pydantic_ai.models.anthropic import AnthropicModel
 from pydantic_ai.models.huggingface import HuggingFaceModel
-from pydantic_ai.models.openai import OpenAIModel
+from pydantic_ai.models.openai import OpenAIChatModel
 from pydantic_ai.providers.anthropic import AnthropicProvider
 from pydantic_ai.providers.huggingface import HuggingFaceProvider
 from pydantic_ai.providers.openai import OpenAIProvider
@@ -48,7 +48,7 @@ def get_model() -> Any:
         logger.warning("Unknown LLM provider, defaulting to OpenAI", provider=llm_provider)
 
     openai_provider = OpenAIProvider(api_key=settings.openai_api_key)
-    return OpenAIModel(settings.openai_model, provider=openai_provider)
+    return OpenAIChatModel(settings.openai_model, provider=openai_provider)
 
 
 class JudgeHandler:

src/app.py

@@ -1,4 +1,4 @@
-"""Gradio UI for DeepCritical agent with MCP server support."""
+"""Gradio UI for DeepBoner agent with MCP server support."""
 
 import os
 from collections.abc import AsyncGenerator
@@ -197,29 +197,31 @@ def create_demo() -> gr.ChatInterface:
     # 1. Unwrapped ChatInterface (Fixes Accordion Bug)
     demo = gr.ChatInterface(
         fn=research_agent,
-        title="🧬 DeepCritical",
+        title="🍆 DeepBoner",
         description=(
-            "*AI-Powered Drug Repurposing Agent — searches PubMed, "
+            "*AI-Powered Sexual Health Research Agent — searches PubMed, "
             "ClinicalTrials.gov & Europe PMC*\n\n"
+            "Deep research for sexual wellness, ED treatments, hormone therapy, "
+            "libido, and reproductive health - for all genders.\n\n"
             "---\n"
             "*Research tool only — not for medical advice.*  \n"
             "**MCP Server Active**: Connect Claude Desktop to `/gradio_api/mcp/`"
         ),
         examples=[
             [
-                "What drugs could be repurposed for Alzheimer's disease?",
+                "What drugs improve female libido post-menopause?",
                 "simple",
                 "",
                 "openai",
             ],
             [
-                "Is metformin effective for treating cancer?",
+                "Clinical trials for erectile dysfunction alternatives to PDE5 inhibitors?",
                 "simple",
                 "",
                 "openai",
             ],
             [
-                "What medications show promise for Long COVID treatment?",
+                "Evidence for testosterone therapy in women with HSDD?",
                 "simple",
                 "",
                 "openai",

src/mcp_tools.py

@@ -1,4 +1,4 @@
-"""MCP tool wrappers for DeepCritical search tools.
+"""MCP tool wrappers for DeepBoner search tools.
 
 These functions expose our search tools via MCP protocol.
 Each function follows the MCP tool contract:

src/services/__init__.py

@@ -1 +1 @@
-"""Services for DeepCritical."""
+"""Services for DeepBoner."""

src/services/llamaindex_rag.py

@@ -1,6 +1,10 @@
 """LlamaIndex RAG service for evidence retrieval and indexing.
 
 Requires optional dependencies: uv sync --extra modal
+
+Migration Note (v1.0 rebrand):
+    Default collection_name changed from "deepcritical_evidence" to "deepboner_evidence".
+    To preserve existing data, explicitly pass collection_name="deepcritical_evidence".
 """
 
 from typing import Any
@@ -25,7 +29,7 @@ class LlamaIndexRAGService:
 
     def __init__(
         self,
-        collection_name: str = "deepcritical_evidence",
+        collection_name: str = "deepboner_evidence",
         persist_dir: str | None = None,
         embedding_model: str | None = None,
         similarity_top_k: int = 5,
@@ -34,7 +38,8 @@ class LlamaIndexRAGService:
         Initialize LlamaIndex RAG service.
 
         Args:
-            collection_name: Name of the ChromaDB collection
+            collection_name: Name of the ChromaDB collection (default changed from
+                "deepcritical_evidence" to "deepboner_evidence" in v1.0 rebrand)
             persist_dir: Directory to persist ChromaDB data
             embedding_model: OpenAI embedding model (defaults to settings.openai_embedding_model)
             similarity_top_k: Number of top results to retrieve
@@ -248,7 +253,7 @@ class LlamaIndexRAGService:
 
 
 def get_rag_service(
-    collection_name: str = "deepcritical_evidence",
+    collection_name: str = "deepboner_evidence",
     **kwargs: Any,
 ) -> LlamaIndexRAGService:
     """

src/tools/clinicaltrials.py

@@ -75,7 +75,7 @@ class ClinicalTrialsTool:
                 requests.get,
                 self.BASE_URL,
                 params=params,
-                headers={"User-Agent": "DeepCritical-Research-Agent/1.0"},
+                headers={"User-Agent": "DeepBoner-Research-Agent/1.0"},
                 timeout=30,
             )
             response.raise_for_status()

src/tools/code_execution.py

@@ -109,10 +109,10 @@ class ModalCodeExecutor:
 
         try:
             # Create or lookup Modal app
-            app = modal.App.lookup("deepcritical-code-execution", create_if_missing=True)
+            app = modal.App.lookup("deepboner-code-execution", create_if_missing=True)
 
             # Define scientific computing image with common libraries
-            scientific_image = modal.Image.debian_slim(python_version="3.11").uv_pip_install(
+            scientific_image = modal.Image.debian_slim(python_version="3.11").pip_install(
                 *get_sandbox_library_list()
             )
 

src/utils/exceptions.py

@@ -1,25 +1,25 @@
-"""Custom exceptions for DeepCritical."""
+"""Custom exceptions for DeepBoner."""
 
 
-class DeepCriticalError(Exception):
-    """Base exception for all DeepCritical errors."""
+class DeepBonerError(Exception):
+    """Base exception for all DeepBoner errors."""
 
     pass
 
 
-class SearchError(DeepCriticalError):
+class SearchError(DeepBonerError):
     """Raised when a search operation fails."""
 
     pass
 
 
-class JudgeError(DeepCriticalError):
+class JudgeError(DeepBonerError):
     """Raised when the judge fails to assess evidence."""
 
     pass
 
 
-class ConfigurationError(DeepCriticalError):
+class ConfigurationError(DeepBonerError):
     """Raised when configuration is invalid."""
 
     pass
@@ -29,3 +29,7 @@ class RateLimitError(SearchError):
     """Raised when we hit API rate limits."""
 
     pass
+
+
+# Backwards compatibility alias
+DeepCriticalError = DeepBonerError

tests/unit/agent_factory/test_judges_factory.py

@@ -10,7 +10,7 @@ from pydantic_ai.models.anthropic import AnthropicModel
 # We expect this import to exist after we implement it, or we mock it if it's not there yet
 # For TDD, we assume we will use the library class
 from pydantic_ai.models.huggingface import HuggingFaceModel
-from pydantic_ai.models.openai import OpenAIModel
+from pydantic_ai.models.openai import OpenAIChatModel
 
 from src.agent_factory.judges import get_model
 
@@ -28,7 +28,7 @@ def test_get_model_openai(mock_settings):
     mock_settings.openai_model = "gpt-5.1"
 
     model = get_model()
-    assert isinstance(model, OpenAIModel)
+    assert isinstance(model, OpenAIChatModel)
     assert model.model_name == "gpt-5.1"
 
 
@@ -61,4 +61,4 @@ def test_get_model_default_fallback(mock_settings):
     mock_settings.openai_model = "gpt-5.1"
 
     model = get_model()
-    assert isinstance(model, OpenAIModel)
+    assert isinstance(model, OpenAIChatModel)

tests/unit/agents/test_hypothesis_agent.py

@@ -3,10 +3,19 @@
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
-from agent_framework import AgentRunResponse
 
-from src.agents.hypothesis_agent import HypothesisAgent
-from src.utils.models import Citation, Evidence, HypothesisAssessment, MechanismHypothesis
+# Skip all tests if agent_framework not installed (optional dep)
+pytest.importorskip("agent_framework")
+
+from agent_framework import AgentRunResponse  # noqa: E402
+
+from src.agents.hypothesis_agent import HypothesisAgent  # noqa: E402
+from src.utils.models import (  # noqa: E402
+    Citation,
+    Evidence,
+    HypothesisAssessment,
+    MechanismHypothesis,
+)
 
 
 @pytest.fixture