adds interface

.env.example

@@ -1,83 +1,63 @@
-# HuggingFace
-HF_TOKEN=your_huggingface_token_here
+# ============== LLM CONFIGURATION ==============
 
-# OpenAI (optional)
-OPENAI_API_KEY=your_openai_key_here
+# Provider: "openai", "anthropic", or "huggingface"
+LLM_PROVIDER=openai
 
-# Anthropic (optional)
-ANTHROPIC_API_KEY=your_anthropic_key_here
+# API Keys (at least one required for full LLM analysis)
+OPENAI_API_KEY=sk-your-key-here
+ANTHROPIC_API_KEY=sk-ant-your-key-here
 
 # Model names (optional - sensible defaults set in config.py)
-# ANTHROPIC_MODEL=claude-sonnet-4-5-20250929
 # OPENAI_MODEL=gpt-5.1
+# ANTHROPIC_MODEL=claude-sonnet-4-5-20250929
 
+# ============== HUGGINGFACE CONFIGURATION ==============
 
-# ============================================
-# Audio Processing Configuration (TTS)
-# ============================================
-# Kokoro TTS Model Configuration
-TTS_MODEL=hexgrad/Kokoro-82M
-TTS_VOICE=af_heart
-TTS_SPEED=1.0
-TTS_GPU=T4
-TTS_TIMEOUT=60
-
-# Available TTS Voices:
-# American English Female: af_heart, af_bella, af_nicole, af_aoede, af_kore, af_sarah, af_nova, af_sky, af_alloy, af_jessica, af_river
-# American English Male: am_michael, am_fenrir, am_puck, am_echo, am_eric, am_liam, am_onyx, am_santa, am_adam
-
-# Available GPU Types (Modal):
-# T4 - Cheapest, good for testing (default)
-# A10 - Good balance of cost/performance
-# A100 - Fastest, most expensive
-# L4 - NVIDIA L4 GPU
-# L40S - NVIDIA L40S GPU
-# Note: GPU type is set at function definition time. Changes require app restart.
-
-# ============================================
-# Audio Processing Configuration (STT)
-# ============================================
-# Speech-to-Text API Configuration
-STT_API_URL=nvidia/canary-1b-v2
-STT_SOURCE_LANG=English
-STT_TARGET_LANG=English
-
-# Available STT Languages:
-# English, Bulgarian, Croatian, Czech, Danish, Dutch, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish, Russian, Ukrainian
-
-# ============================================
-# Audio Feature Flags
-# ============================================
-ENABLE_AUDIO_INPUT=true
-ENABLE_AUDIO_OUTPUT=true
-
-# ============================================
-# Image OCR Configuration
-# ============================================
-OCR_API_URL=prithivMLmods/Multimodal-OCR3
-ENABLE_IMAGE_INPUT=true
-
-# ============== EMBEDDINGS ==============
-
-# OpenAI Embedding Model (used if LLM_PROVIDER is openai and performing RAG/Embeddings)
-OPENAI_EMBEDDING_MODEL=text-embedding-3-small
-
-# Local Embedding Model (used for local/offline embeddings)
-LOCAL_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
-
-# ============== HUGGINGFACE (FREE TIER) ==============
-
-# HuggingFace Token - enables Llama 3.1 (best quality free model)
+# HuggingFace Token - enables gated models and higher rate limits
 # Get yours at: https://huggingface.co/settings/tokens
-#
-# WITHOUT HF_TOKEN: Falls back to ungated models (zephyr-7b-beta)
-# WITH HF_TOKEN: Uses Llama 3.1 8B Instruct (requires accepting license)
+# 
+# WITHOUT HF_TOKEN: Falls back to ungated models (zephyr-7b-beta, Qwen2-7B)
+# WITH HF_TOKEN: Uses gated models (Llama 3.1, Gemma-2) via inference providers
 #
 # For HuggingFace Spaces deployment:
 #   Set this as a "Secret" in Space Settings -> Variables and secrets
 #   Users/judges don't need their own token - the Space secret is used
 #
 HF_TOKEN=hf_your-token-here
+# Alternative: HUGGINGFACE_API_KEY (same as HF_TOKEN)
+
+# Default HuggingFace model for inference (gated, requires auth)
+# Can be overridden in UI dropdown
+# Latest reasoning models: Qwen3-Next-80B-A3B-Thinking, Qwen3-Next-80B-A3B-Instruct, Llama-3.3-70B-Instruct
+HUGGINGFACE_MODEL=Qwen/Qwen3-Next-80B-A3B-Thinking
+
+# Fallback models for HuggingFace Inference API (comma-separated)
+# Models are tried in order until one succeeds
+# Format: model1,model2,model3
+# Latest reasoning models first, then reliable fallbacks
+# Reasoning models: Qwen3-Next (thinking/instruct), Llama-3.3-70B, Qwen3-235B
+# Fallbacks: Llama-3.1-8B, Zephyr-7B (ungated), Qwen2-7B (ungated)
+HF_FALLBACK_MODELS=Qwen/Qwen3-Next-80B-A3B-Thinking,Qwen/Qwen3-Next-80B-A3B-Instruct,meta-llama/Llama-3.3-70B-Instruct,meta-llama/Llama-3.1-8B-Instruct,HuggingFaceH4/zephyr-7b-beta,Qwen/Qwen2-7B-Instruct
+
+# Override model/provider selection (optional, usually set via UI)
+# HF_MODEL=Qwen/Qwen3-Next-80B-A3B-Thinking
+# HF_PROVIDER=hyperbolic
+
+# ============== EMBEDDING CONFIGURATION ==============
+
+# Embedding Provider: "openai", "local", or "huggingface"
+# Default: "local" (no API key required)
+EMBEDDING_PROVIDER=local
+
+# OpenAI Embedding Model (used if EMBEDDING_PROVIDER=openai)
+OPENAI_EMBEDDING_MODEL=text-embedding-3-small
+
+# Local Embedding Model (sentence-transformers, used if EMBEDDING_PROVIDER=local)
+# BAAI/bge-small-en-v1.5 is newer, faster, and better than all-MiniLM-L6-v2
+LOCAL_EMBEDDING_MODEL=BAAI/bge-small-en-v1.5
+
+# HuggingFace Embedding Model (used if EMBEDDING_PROVIDER=huggingface)
+HUGGINGFACE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
 
 # ============== AGENT CONFIGURATION ==============
 
@@ -85,23 +65,60 @@ MAX_ITERATIONS=10
 SEARCH_TIMEOUT=30
 LOG_LEVEL=INFO
 
-# ============================================
-# Modal Configuration (Required for TTS)
-# ============================================
-# Modal credentials are required for TTS (Text-to-Speech) functionality
-# Get your credentials from: https://modal.com/
-MODAL_TOKEN_ID=your_modal_token_id_here
-MODAL_TOKEN_SECRET=your_modal_token_secret_here
+# Graph-based execution (experimental)
+# USE_GRAPH_EXECUTION=false
+
+# Budget & Rate Limiting
+# DEFAULT_TOKEN_LIMIT=100000
+# DEFAULT_TIME_LIMIT_MINUTES=10
+# DEFAULT_ITERATIONS_LIMIT=10
+
+# ============== WEB SEARCH CONFIGURATION ==============
+
+# Web Search Provider: "serper", "searchxng", "brave", "tavily", or "duckduckgo"
+# Default: "duckduckgo" (no API key required)
+WEB_SEARCH_PROVIDER=duckduckgo
+
+# Serper API Key (for Google search via Serper)
+# SERPER_API_KEY=your-serper-key-here
+
+# SearchXNG Host URL (for self-hosted search)
+# SEARCHXNG_HOST=http://localhost:8080
+
+# Brave Search API Key
+# BRAVE_API_KEY=your-brave-key-here
+
+# Tavily API Key
+# TAVILY_API_KEY=your-tavily-key-here
 
 # ============== EXTERNAL SERVICES ==============
 
-# PubMed (optional - higher rate limits)
+# PubMed (optional - higher rate limits: 10 req/sec vs 3 req/sec)
 NCBI_API_KEY=your-ncbi-key-here
 
-# Vector Database (optional - for LlamaIndex RAG)
+# Modal (optional - for secure code execution sandbox)
+# MODAL_TOKEN_ID=your-modal-token-id
+# MODAL_TOKEN_SECRET=your-modal-token-secret
+
+# ============== VECTOR DATABASE (ChromaDB) ==============
+
+# ChromaDB storage path
 CHROMA_DB_PATH=./chroma_db
-# Neo4j Knowledge Graph
-NEO4J_URI=bolt://localhost:7687
-NEO4J_USER=neo4j
-NEO4J_PASSWORD=your_neo4j_password_here
-NEO4J_DATABASE=your_database_name
+
+# Persist ChromaDB to disk (default: true)
+# CHROMA_DB_PERSIST=true
+
+# Remote ChromaDB server (optional)
+# CHROMA_DB_HOST=localhost
+# CHROMA_DB_PORT=8000
+
+# ============== RAG SERVICE CONFIGURATION ==============
+
+# ChromaDB collection name for RAG
+# RAG_COLLECTION_NAME=deepcritical_evidence
+
+# Number of top results to retrieve from RAG
+# RAG_SIMILARITY_TOP_K=5
+
+# Automatically ingest evidence into RAG
+# RAG_AUTO_INGEST=true

.github/README.md

@@ -0,0 +1,65 @@
+
+> [!IMPORTANT]
+> **You are reading the Github README!**
+> 
+> - 📚 **Documentation**: See our [technical documentation](https://deepcritical.github.io/GradioDemo/) for detailed information
+> - 📖 **Demo README**: Check out the [Demo README](..README.md) for setup, configuration, and contribution guidelines
+> - 🏆 **Hackathon Submission**: Keep reading below for more information about our MCP Hackathon submission
+
+
+<div align="center">
+
+[![GitHub](https://img.shields.io/github/stars/DeepCritical/GradioDemo?style=for-the-badge&logo=github&logoColor=white&label=🐙%20GitHub&labelColor=181717&color=181717)](https://github.com/DeepCritical/GradioDemo)
+[![Documentation](https://img.shields.io/badge/Docs-0080FF?style=for-the-badge&logo=readthedocs&logoColor=white&labelColor=0080FF&color=0080FF)](deepcritical.github.io/GradioDemo/)
+[![Demo](https://img.shields.io/badge/🚀%20Demo-FFD21E?style=for-the-badge&logo=huggingface&logoColor=white&labelColor=FFD21E&color=FFD21E)](https://huggingface.co/spaces/DataQuests/DeepCritical)
+[![codecov](https://codecov.io/gh/DeepCritical/GradioDemo/graph/badge.svg?token=B1f05RCGpz)](https://codecov.io/gh/DeepCritical/GradioDemo)
+[![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/qdfnvSPcqP) 
+
+</div>
+
+## Quick Start
+
+### 1. Environment Setup
+
+```bash
+# Install uv if you haven't already
+pip install uv
+
+# Sync dependencies
+uv sync --all-extras
+```
+
+### 2. Run the UI
+
+```bash
+# Start the Gradio app
+gradio run "src/app.py"
+```
+
+Open your browser to `http://localhost:7860`.
+
+### 3. Authentication (Optional)
+
+**HuggingFace OAuth Login**:
+- Click the "Sign in with HuggingFace" button at the top of the app
+- Your HuggingFace API token will be automatically used for AI inference
+- No need to manually enter API keys when logged in
+- OAuth token is used only for the current session and never stored
+
+### 4. Connect via MCP
+
+This application exposes a Model Context Protocol (MCP) server, allowing you to use its search tools directly from Claude Desktop or other MCP clients.
+
+**MCP Server URL**: `http://localhost:7860/gradio_api/mcp/`
+
+**Claude Desktop Configuration**:
+Add this to your `claude_desktop_config.json`:
+```json
+{
+  "mcpServers": {
+    "deepcritical": {
+      "url": "http://localhost:7860/gradio_api/mcp/"
+    }
+  }
+}
+```

.github/workflows/ci.yml

@@ -0,0 +1,80 @@
+name: CI
+
+on:
+  push:
+    branches: [main, dev]
+  pull_request:
+    branches: [main, dev]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          uv sync --extra dev
+
+      - name: Lint with ruff
+        continue-on-error: true
+        run: |
+          uv run ruff check . --exclude tests --exclude reference_repos
+          uv run ruff format --check . --exclude tests --exclude reference_repos
+
+      - name: Type check with mypy
+        continue-on-error: true
+        run: |
+          uv run mypy src --ignore-missing-imports
+
+      - name: Run unit tests (No OpenAI/Anthropic, HuggingFace only)
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          LLM_PROVIDER: huggingface
+        run: |
+          uv run pytest tests/unit/ -v -m "not openai and not anthropic and not embedding_provider" --tb=short -p no:logfire --cov --cov-branch --cov-report=xml
+
+      - name: Run local embeddings tests
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          LLM_PROVIDER: huggingface
+        run: |
+          uv run pytest tests/ -v -m "local_embeddings" --tb=short -p no:logfire --cov --cov-branch --cov-report=xml --cov-append || true
+        continue-on-error: true  # Allow failures if dependencies not available
+
+      - name: Run HuggingFace integration tests
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          LLM_PROVIDER: huggingface
+        run: |
+          uv run pytest tests/integration/ -v -m "huggingface and not embedding_provider" --tb=short -p no:logfire --cov --cov-branch --cov-report=xml --cov-append || true
+        continue-on-error: true  # Allow failures if HF_TOKEN not set
+
+      - name: Run non-OpenAI/Anthropic integration tests (excluding embedding providers)
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          LLM_PROVIDER: huggingface
+        run: |
+          uv run pytest tests/integration/ -v -m "integration and not openai and not anthropic and not embedding_provider" --tb=short -p no:logfire --cov --cov-branch --cov-report=xml --cov-append || true
+        continue-on-error: true  # Allow failures if dependencies not available
+
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v5
+        continue-on-error: true
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: DeepCritical/GradioDemo

.github/workflows/docs.yml

@@ -0,0 +1,61 @@
+name: Documentation
+
+on:
+  push:
+    branches:
+      - main
+      - dev
+    paths:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - '.github/workflows/docs.yml'
+  pull_request:
+    branches:
+      - main
+      - dev
+    paths:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - '.github/workflows/docs.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+
+      - name: Install dependencies
+        run: |
+          uv sync --extra dev
+
+      - name: Build documentation
+        run: |
+          uv run mkdocs build --strict
+
+      - name: Deploy to GitHub Pages
+        if: (github.ref == 'refs/heads/main' || github.ref == 'refs/heads/dev') && github.event_name == 'push'
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./site
+          publish_branch: dev
+          cname: false
+          keep_files: true
+
+
+
+

.gitignore

@@ -1,7 +1,10 @@
+=0.22.0
+=0.22.0,
 folder/
 site/
 .cursor/
 .ruff_cache/
+docs/contributing/
 # Python
 __pycache__/
 *.py[cod]
@@ -69,13 +72,12 @@ logs/
 .pytest_cache/
 .mypy_cache/
 .coverage
+.coverage.*
+coverage.xml
 htmlcov/
-test_output*.txt
 
 # Database files
 chroma_db/
 *.sqlite3
 
-
 # Trigger rebuild Wed Nov 26 17:51:41 EST 2025
-.env

.pre-commit-config.yaml

@@ -0,0 +1,54 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.14.7  # Compatible with ruff>=0.14.6 (matches CI)
+    hooks:
+      - id: ruff
+        args: [--fix, --exclude, tests, --exclude, reference_repos]
+        exclude: ^reference_repos/
+      - id: ruff-format
+        args: [--exclude, tests, --exclude, reference_repos]
+        exclude: ^reference_repos/
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.18.2  # Matches CI version mypy>=1.18.2
+    hooks:
+      - id: mypy
+        files: ^src/
+        exclude: ^folder
+        additional_dependencies:
+          - pydantic>=2.7
+          - pydantic-settings>=2.2
+          - tenacity>=8.2
+          - pydantic-ai>=0.0.16
+        args: [--ignore-missing-imports]
+
+  - repo: local
+    hooks:
+      - id: pytest-unit
+        name: pytest unit tests (no OpenAI)
+        entry: uv
+        language: system
+        types: [python]
+        args: [
+          "run",
+          "python",
+          ".pre-commit-hooks/run_pytest_with_sync.py",
+          "unit",
+        ]
+        pass_filenames: false
+        always_run: true
+        require_serial: false
+      - id: pytest-local-embeddings
+        name: pytest local embeddings tests
+        entry: uv
+        language: system
+        types: [python]
+        args: [
+          "run",
+          "python",
+          ".pre-commit-hooks/run_pytest_with_sync.py",
+          "embeddings",
+        ]
+        pass_filenames: false
+        always_run: true
+        require_serial: false

Makefile

@@ -0,0 +1,51 @@
+.PHONY: install test lint format typecheck check clean all cov cov-html
+
+# Default target
+all: check
+
+install:
+	uv sync --all-extras
+	uv run pre-commit install
+
+test:
+	uv run pytest tests/unit/ -v -m "not openai" -p no:logfire
+
+test-hf:
+	uv run pytest tests/ -v -m "huggingface" -p no:logfire
+
+test-all:
+	uv run pytest tests/ -v -p no:logfire
+
+# Coverage aliases
+cov: test-cov
+test-cov:
+	uv run pytest --cov=src --cov-report=term-missing -m "not openai" -p no:logfire
+
+cov-html:
+	uv run pytest --cov=src --cov-report=html -p no:logfire
+	@echo "Coverage report: open htmlcov/index.html"
+
+lint:
+	uv run ruff check src tests
+
+format:
+	uv run ruff format src tests
+
+typecheck:
+	uv run mypy src
+
+check: lint typecheck test-cov
+	@echo "All checks passed!"
+
+docs-build:
+	uv run mkdocs build
+
+docs-serve:
+	uv run mkdocs serve
+
+docs-clean:
+	rm -rf site/
+
+clean:
+	rm -rf .pytest_cache .mypy_cache .ruff_cache __pycache__ .coverage htmlcov
+	find . -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true

README.md

@@ -1,5 +1,5 @@
 ---
-title: The DETERMINATOR
+title: Critical Deep Resarch
 emoji: 🐉
 colorFrom: red
 colorTo: yellow
@@ -10,54 +10,114 @@ app_file: src/app.py
 hf_oauth: true
 hf_oauth_expiration_minutes: 480
 hf_oauth_scopes:
-  # Required for HuggingFace Inference API (includes all third-party providers)
-  # This scope grants access to:
-  # - HuggingFace's own Inference API
-  # - Third-party inference providers (nebius, together, scaleway, hyperbolic, novita, nscale, sambanova, ovh, fireworks, etc.)
-  # - All models available through the Inference Providers API
-  - inference-api
-  # Optional: Uncomment if you need to access user's billing information
-  # - read-billing
+ - inference-api
 pinned: true
 license: mit
 tags:
   - mcp-in-action-track-enterprise
   - mcp-hackathon
-  - deep-research
+  - drug-repurposing
   - biomedical-ai
   - pydantic-ai
   - llamaindex
   - modal
-  - building-mcp-track-enterprise
-  - building-mcp-track-consumer
-  - mcp-in-action-track-enterprise
-  - mcp-in-action-track-consumer
-  - building-mcp-track-modal
-  - building-mcp-track-blaxel
-  - building-mcp-track-llama-index
-  - building-mcp-track-HUGGINGFACE 
 ---
 
 > [!IMPORTANT]
 > **You are reading the Gradio Demo README!**
 > 
-> - 📚 **Documentation**: See our [technical documentation](https://deepcritical.github.io/GradioDemo/) for detailed information
-> - 📖 **Complete README**: Check out the [Github README](.github/README.md) for setup, configuration, and contribution guidelines
-> - ⚠️**This README is for our Gradio Demo Only !** 
+> - 📚 **Documentation**: See our [technical documentation](deepcritical.github.io/GradioDemo/) for detailed information
+> - 📖 **Complete README**: Check out the [full README](.github/README.md) for setup, configuration, and contribution guidelines
+> - 🏆 **Hackathon Submission**: Keep reading below for more information about our MCP Hackathon submission
 
 <div align="center">
 
-[![GitHub](https://img.shields.io/github/stars/DeepCritical/GradioDemo?style=for-the-badge&logo=github&logoColor=white&label=GitHub&labelColor=181717&color=181717)](https://github.com/DeepCritical/GradioDemo)
-[![Documentation](https://img.shields.io/badge/Docs-0080FF?style=for-the-badge&logo=readthedocs&logoColor=white&labelColor=0080FF&color=0080FF)](deepcritical.github.io/GradioDemo/)
-[![Demo](https://img.shields.io/badge/Demo-FFD21E?style=for-the-badge&logo=huggingface&logoColor=white&labelColor=FFD21E&color=FFD21E)](https://huggingface.co/spaces/DataQuests/DeepCritical)
+[![GitHub](https://img.shields.io/github/stars/DeepCritical/GradioDemo?style=for-the-badge&logo=github&logoColor=white&label=🐙%20GitHub&labelColor=181717&color=181717)](https://github.com/DeepCritical/GradioDemo)
+[![Documentation](https://img.shields.io/badge/📚%20Docs-0080FF?style=for-the-badge&logo=readthedocs&logoColor=white&labelColor=0080FF&color=0080FF)](deepcritical.github.io/GradioDemo/)
+[![Demo](https://img.shields.io/badge/🚀%20Demo-FFD21E?style=for-the-badge&logo=huggingface&logoColor=white&labelColor=FFD21E&color=FFD21E)](https://huggingface.co/spaces/DataQuests/DeepCritical)
 [![codecov](https://codecov.io/gh/DeepCritical/GradioDemo/graph/badge.svg?token=B1f05RCGpz)](https://codecov.io/gh/DeepCritical/GradioDemo)
 [![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/qdfnvSPcqP) 
 
 
 </div>
 
-# The DETERMINATOR
+# DeepCritical
 
 ## About
 
-The DETERMINATOR is a powerful generalist deep research agent system that stops at nothing until finding precise answers to complex questions. It uses iterative search-and-judge loops to comprehensively investigate any research question from any domain.
+The [Deep Critical Gradio Hackathon Team](### Team) met online in the Alzheimer's Critical Literature Review Group in the Hugging Science initiative. We're building the agent framework we want to use for ai assisted research to [turn the vast amounts of clinical data into cures](https://github.com/DeepCritical/GradioDemo).
+
+For this hackathon we're proposing a simple yet powerful Deep Research Agent that iteratively looks for the answer until it finds it using general purpose websearch and special purpose retrievers for technical retrievers. 
+
+## Deep Critical In the Medial 
+
+- Social Medial Posts about Deep Critical :
+  - 
+  -
+  -
+  -
+  -
+  -
+  -
+
+## Important information
+
+- **[readme](.github\README.md)**: configure, deploy , contribute and learn more here.
+- **[docs](deepcritical.github.io/GradioDemo/)**: want to know how all this works ? read our detailed technical documentation here.
+- **[demo](https://huggingface/spaces/DataQuests/DeepCritical)**: Try our demo on huggingface
+- **[team](### Team)**: Join us , or follow us !
+- **[video]**: See our demo video
+
+## Future Developments
+
+- [] Apply Deep Research Systems To Generate Short Form Video (up to 5 minutes)
+- [] Visualize Pydantic Graphs as Loading Screens in the UI
+- [] Improve Data Science with more Complex Graph Agents
+- [] Create Deep Critical Drug Reporposing / Discovery Demo
+- [] Create Deep Critical Literal Review
+- [] Create Deep Critical Hypothesis Generator
+- [] Create PyPi Package 
+
+## Completed
+
+- [] **Multi-Source Search**: PubMed, ClinicalTrials.gov, bioRxiv/medRxiv
+- [] **MCP Integration**: Use our tools from Claude Desktop or any MCP client
+- [] **HuggingFace OAuth**: Sign in with HuggingFace 
+- [] **Modal Sandbox**: Secure execution of AI-generated statistical code
+- [] **LlamaIndex RAG**: Semantic search and evidence synthesis
+- [] **HuggingfaceInference**: 
+- [] **HuggingfaceMCP Custom Config To Use Community Tools**:
+- [] **Strongly Typed Composable Graphs**:
+- [] **Specialized Research Teams of Agents**: 
+
+
+
+### Team
+
+- ZJ
+- MarioAderman
+- Josephrp
+
+
+## Acknowledgements
+
+- McSwaggins
+- Magentic
+- Huggingface
+- Gradio
+- DeepCritical
+- Sponsors
+- Microsoft
+- Pydantic
+- Llama-index
+- Anthhropic/MCP
+- List of Tools Makers
+
+
+## Links
+
+[![GitHub](https://img.shields.io/github/stars/DeepCritical/GradioDemo?style=for-the-badge&logo=github&logoColor=white&label=🐙%20GitHub&labelColor=181717&color=181717)](https://github.com/DeepCritical/GradioDemo)
+[![Documentation](https://img.shields.io/badge/📚%20Docs-0080FF?style=for-the-badge&logo=readthedocs&logoColor=white&labelColor=0080FF&color=0080FF)](deepcritical.github.io/GradioDemo/)
+[![Demo](https://img.shields.io/badge/🚀%20Demo-FFD21E?style=for-the-badge&logo=huggingface&logoColor=white&labelColor=FFD21E&color=FFD21E)](https://huggingface.co/spaces/DataQuests/DeepCritical)
+[![codecov](https://codecov.io/gh/DeepCritical/GradioDemo/graph/badge.svg?token=B1f05RCGpz)](https://codecov.io/gh/DeepCritical/GradioDemo)
+[![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/qdfnvSPcqP) 

.cursorrules → dev/.cursorrules

@@ -238,3 +238,4 @@
 
 
 
+

dev/AGENTS.txt

@@ -0,0 +1,236 @@
+# DeepCritical Project - Rules
+
+## Project-Wide Rules
+
+**Architecture**: Multi-agent research system using Pydantic AI for agent orchestration, supporting iterative and deep research patterns. Uses middleware for state management, budget tracking, and workflow coordination.
+
+**Type Safety**: ALWAYS use complete type hints. All functions must have parameter and return type annotations. Use `mypy --strict` compliance. Use `TYPE_CHECKING` imports for circular dependencies: `from typing import TYPE_CHECKING; if TYPE_CHECKING: from src.services.embeddings import EmbeddingService`
+
+**Async Patterns**: ALL I/O operations must be async (`async def`, `await`). Use `asyncio.gather()` for parallel operations. CPU-bound work must use `run_in_executor()`: `loop = asyncio.get_running_loop(); result = await loop.run_in_executor(None, cpu_bound_function, args)`. Never block the event loop.
+
+**Error Handling**: Use custom exceptions from `src/utils/exceptions.py`: `DeepCriticalError`, `SearchError`, `RateLimitError`, `JudgeError`, `ConfigurationError`. Always chain exceptions: `raise SearchError(...) from e`. Log with structlog: `logger.error("Operation failed", error=str(e), context=value)`.
+
+**Logging**: Use `structlog` for ALL logging (NOT `print` or `logging`). Import: `import structlog; logger = structlog.get_logger()`. Log with structured data: `logger.info("event", key=value)`. Use appropriate levels: DEBUG, INFO, WARNING, ERROR.
+
+**Pydantic Models**: All data exchange uses Pydantic models from `src/utils/models.py`. Models are frozen (`model_config = {"frozen": True}`) for immutability. Use `Field()` with descriptions. Validate with `ge=`, `le=`, `min_length=`, `max_length=` constraints.
+
+**Code Style**: Ruff with 100-char line length. Ignore rules: `PLR0913` (too many arguments), `PLR0912` (too many branches), `PLR0911` (too many returns), `PLR2004` (magic values), `PLW0603` (global statement), `PLC0415` (lazy imports).
+
+**Docstrings**: Google-style docstrings for all public functions. Include Args, Returns, Raises sections. Use type hints in docstrings only if needed for clarity.
+
+**Testing**: Unit tests in `tests/unit/` (mocked, fast). Integration tests in `tests/integration/` (real APIs, marked `@pytest.mark.integration`). Use `respx` for httpx mocking, `pytest-mock` for general mocking.
+
+**State Management**: Use `ContextVar` in middleware for thread-safe isolation. Never use global mutable state (except singletons via `@lru_cache`). Use `WorkflowState` from `src/middleware/state_machine.py` for workflow state.
+
+**Citation Validation**: ALWAYS validate references before returning reports. Use `validate_references()` from `src/utils/citation_validator.py`. Remove hallucinated citations. Log warnings for removed citations.
+
+---
+
+## src/agents/ - Agent Implementation Rules
+
+**Pattern**: All agents use Pydantic AI `Agent` class. Agents have structured output types (Pydantic models) or return strings. Use factory functions in `src/agent_factory/agents.py` for creation.
+
+**Agent Structure**: 
+- System prompt as module-level constant (with date injection: `datetime.now().strftime("%Y-%m-%d")`)
+- Agent class with `__init__(model: Any | None = None)`
+- Main method (e.g., `async def evaluate()`, `async def write_report()`)
+- Factory function: `def create_agent_name(model: Any | None = None) -> AgentName`
+
+**Model Initialization**: Use `get_model()` from `src/agent_factory/judges.py` if no model provided. Support OpenAI/Anthropic/HF Inference via settings.
+
+**Error Handling**: Return fallback values (e.g., `KnowledgeGapOutput(research_complete=False, outstanding_gaps=[...])`) on failure. Log errors with context. Use retry logic (3 retries) in Pydantic AI Agent initialization.
+
+**Input Validation**: Validate query/inputs are not empty. Truncate very long inputs with warnings. Handle None values gracefully.
+
+**Output Types**: Use structured output types from `src/utils/models.py` (e.g., `KnowledgeGapOutput`, `AgentSelectionPlan`, `ReportDraft`). For text output (writer agents), return `str` directly.
+
+**Agent-Specific Rules**:
+- `knowledge_gap.py`: Outputs `KnowledgeGapOutput`. Evaluates research completeness.
+- `tool_selector.py`: Outputs `AgentSelectionPlan`. Selects tools (RAG/web/database).
+- `writer.py`: Returns markdown string. Includes citations in numbered format.
+- `long_writer.py`: Uses `ReportDraft` input/output. Handles section-by-section writing.
+- `proofreader.py`: Takes `ReportDraft`, returns polished markdown.
+- `thinking.py`: Returns observation string from conversation history.
+- `input_parser.py`: Outputs `ParsedQuery` with research mode detection.
+
+---
+
+## src/tools/ - Search Tool Rules
+
+**Protocol**: All tools implement `SearchTool` protocol from `src/tools/base.py`: `name` property and `async def search(query, max_results) -> list[Evidence]`.
+
+**Rate Limiting**: Use `@retry` decorator from tenacity: `@retry(stop=stop_after_attempt(3), wait=wait_exponential(...))`. Implement `_rate_limit()` method for APIs with limits. Use shared rate limiters from `src/tools/rate_limiter.py`.
+
+**Error Handling**: Raise `SearchError` or `RateLimitError` on failures. Handle HTTP errors (429, 500, timeout). Return empty list on non-critical errors (log warning).
+
+**Query Preprocessing**: Use `preprocess_query()` from `src/tools/query_utils.py` to remove noise and expand synonyms.
+
+**Evidence Conversion**: Convert API responses to `Evidence` objects with `Citation`. Extract metadata (title, url, date, authors). Set relevance scores (0.0-1.0). Handle missing fields gracefully.
+
+**Tool-Specific Rules**:
+- `pubmed.py`: Use NCBI E-utilities (ESearch → EFetch). Rate limit: 0.34s between requests. Parse XML with `xmltodict`. Handle single vs. multiple articles.
+- `clinicaltrials.py`: Use `requests` library (NOT httpx - WAF blocks httpx). Run in thread pool: `await asyncio.to_thread(requests.get, ...)`. Filter: Only interventional studies, active/completed.
+- `europepmc.py`: Handle preprint markers: `[PREPRINT - Not peer-reviewed]`. Build URLs from DOI or PMID.
+- `rag_tool.py`: Wraps `LlamaIndexRAGService`. Returns Evidence from RAG results. Handles ingestion.
+- `search_handler.py`: Orchestrates parallel searches across multiple tools. Uses `asyncio.gather()` with `return_exceptions=True`. Aggregates results into `SearchResult`.
+
+---
+
+## src/middleware/ - Middleware Rules
+
+**State Management**: Use `ContextVar` for thread-safe isolation. `WorkflowState` uses `ContextVar[WorkflowState | None]`. Initialize with `init_workflow_state(embedding_service)`. Access with `get_workflow_state()` (auto-initializes if missing).
+
+**WorkflowState**: Tracks `evidence: list[Evidence]`, `conversation: Conversation`, `embedding_service: Any`. Methods: `add_evidence()` (deduplicates by URL), `async search_related()` (semantic search).
+
+**WorkflowManager**: Manages parallel research loops. Methods: `add_loop()`, `run_loops_parallel()`, `update_loop_status()`, `sync_loop_evidence_to_state()`. Uses `asyncio.gather()` for parallel execution. Handles errors per loop (don't fail all if one fails).
+
+**BudgetTracker**: Tracks tokens, time, iterations per loop and globally. Methods: `create_budget()`, `add_tokens()`, `start_timer()`, `update_timer()`, `increment_iteration()`, `check_budget()`, `can_continue()`. Token estimation: `estimate_tokens(text)` (~4 chars per token), `estimate_llm_call_tokens(prompt, response)`.
+
+**Models**: All middleware models in `src/utils/models.py`. `IterationData`, `Conversation`, `ResearchLoop`, `BudgetStatus` are used by middleware.
+
+---
+
+## src/orchestrator/ - Orchestration Rules
+
+**Research Flows**: Two patterns: `IterativeResearchFlow` (single loop) and `DeepResearchFlow` (plan → parallel loops → synthesis). Both support agent chains (`use_graph=False`) and graph execution (`use_graph=True`).
+
+**IterativeResearchFlow**: Pattern: Generate observations → Evaluate gaps → Select tools → Execute → Judge → Continue/Complete. Uses `KnowledgeGapAgent`, `ToolSelectorAgent`, `ThinkingAgent`, `WriterAgent`, `JudgeHandler`. Tracks iterations, time, budget.
+
+**DeepResearchFlow**: Pattern: Planner → Parallel iterative loops per section → Synthesizer. Uses `PlannerAgent`, `IterativeResearchFlow` (per section), `LongWriterAgent` or `ProofreaderAgent`. Uses `WorkflowManager` for parallel execution.
+
+**Graph Orchestrator**: Uses Pydantic AI Graphs (when available) or agent chains (fallback). Routes based on research mode (iterative/deep/auto). Streams `AgentEvent` objects for UI.
+
+**State Initialization**: Always call `init_workflow_state()` before running flows. Initialize `BudgetTracker` per loop. Use `WorkflowManager` for parallel coordination.
+
+**Event Streaming**: Yield `AgentEvent` objects during execution. Event types: "started", "search_complete", "judge_complete", "hypothesizing", "synthesizing", "complete", "error". Include iteration numbers and data payloads.
+
+---
+
+## src/services/ - Service Rules
+
+**EmbeddingService**: Local sentence-transformers (NO API key required). All operations async-safe via `run_in_executor()`. ChromaDB for vector storage. Deduplication threshold: 0.85 (85% similarity = duplicate).
+
+**LlamaIndexRAGService**: Uses OpenAI embeddings (requires `OPENAI_API_KEY`). Methods: `ingest_evidence()`, `retrieve()`, `query()`. Returns documents with metadata (source, title, url, date, authors). Lazy initialization with graceful fallback.
+
+**StatisticalAnalyzer**: Generates Python code via LLM. Executes in Modal sandbox (secure, isolated). Library versions pinned in `SANDBOX_LIBRARIES` dict. Returns `AnalysisResult` with verdict (SUPPORTED/REFUTED/INCONCLUSIVE).
+
+**Singleton Pattern**: Use `@lru_cache(maxsize=1)` for singletons: `@lru_cache(maxsize=1); def get_service() -> Service: return Service()`. Lazy initialization to avoid requiring dependencies at import time.
+
+---
+
+## src/utils/ - Utility Rules
+
+**Models**: All Pydantic models in `src/utils/models.py`. Use frozen models (`model_config = {"frozen": True}`) except where mutation needed. Use `Field()` with descriptions. Validate with constraints.
+
+**Config**: Settings via Pydantic Settings (`src/utils/config.py`). Load from `.env` automatically. Use `settings` singleton: `from src.utils.config import settings`. Validate API keys with properties: `has_openai_key`, `has_anthropic_key`.
+
+**Exceptions**: Custom exception hierarchy in `src/utils/exceptions.py`. Base: `DeepCriticalError`. Specific: `SearchError`, `RateLimitError`, `JudgeError`, `ConfigurationError`. Always chain exceptions.
+
+**LLM Factory**: Centralized LLM model creation in `src/utils/llm_factory.py`. Supports OpenAI, Anthropic, HF Inference. Use `get_model()` or factory functions. Check requirements before initialization.
+
+**Citation Validator**: Use `validate_references()` from `src/utils/citation_validator.py`. Removes hallucinated citations (URLs not in evidence). Logs warnings. Returns validated report string.
+
+---
+
+## src/orchestrator_factory.py Rules
+
+**Purpose**: Factory for creating orchestrators. Supports "simple" (legacy) and "advanced" (magentic) modes. Auto-detects mode based on API key availability.
+
+**Pattern**: Lazy import for optional dependencies (`_get_magentic_orchestrator_class()`). Handles `ImportError` gracefully with clear error messages.
+
+**Mode Detection**: `_determine_mode()` checks explicit mode or auto-detects: "advanced" if `settings.has_openai_key`, else "simple". Maps "magentic" → "advanced".
+
+**Function Signature**: `create_orchestrator(search_handler, judge_handler, config, mode) -> Any`. Simple mode requires handlers. Advanced mode uses MagenticOrchestrator.
+
+**Error Handling**: Raise `ValueError` with clear messages if requirements not met. Log mode selection with structlog.
+
+---
+
+## src/orchestrator_hierarchical.py Rules
+
+**Purpose**: Hierarchical orchestrator using middleware and sub-teams. Adapts Magentic ChatAgent to SubIterationTeam protocol.
+
+**Pattern**: Uses `SubIterationMiddleware` with `ResearchTeam` and `LLMSubIterationJudge`. Event-driven via callback queue.
+
+**State Initialization**: Initialize embedding service with graceful fallback. Use `init_magentic_state()` (deprecated, but kept for compatibility).
+
+**Event Streaming**: Uses `asyncio.Queue` for event coordination. Yields `AgentEvent` objects. Handles event callback pattern with `asyncio.wait()`.
+
+**Error Handling**: Log errors with context. Yield error events. Process remaining events after task completion.
+
+---
+
+## src/orchestrator_magentic.py Rules
+
+**Purpose**: Magentic-based orchestrator using ChatAgent pattern. Each agent has internal LLM. Manager orchestrates agents.
+
+**Pattern**: Uses `MagenticBuilder` with participants (searcher, hypothesizer, judge, reporter). Manager uses `OpenAIChatClient`. Workflow built in `_build_workflow()`.
+
+**Event Processing**: `_process_event()` converts Magentic events to `AgentEvent`. Handles: `MagenticOrchestratorMessageEvent`, `MagenticAgentMessageEvent`, `MagenticFinalResultEvent`, `MagenticAgentDeltaEvent`, `WorkflowOutputEvent`.
+
+**Text Extraction**: `_extract_text()` defensively extracts text from messages. Priority: `.content` → `.text` → `str(message)`. Handles buggy message objects.
+
+**State Initialization**: Initialize embedding service with graceful fallback. Use `init_magentic_state()` (deprecated).
+
+**Requirements**: Must call `check_magentic_requirements()` in `__init__`. Requires `agent-framework-core` and OpenAI API key.
+
+**Event Types**: Maps agent names to event types: "search" → "search_complete", "judge" → "judge_complete", "hypothes" → "hypothesizing", "report" → "synthesizing".
+
+---
+
+## src/agent_factory/ - Factory Rules
+
+**Pattern**: Factory functions for creating agents and handlers. Lazy initialization for optional dependencies. Support OpenAI/Anthropic/HF Inference.
+
+**Judges**: `create_judge_handler()` creates `JudgeHandler` with structured output (`JudgeAssessment`). Supports `MockJudgeHandler`, `HFInferenceJudgeHandler` as fallbacks.
+
+**Agents**: Factory functions in `agents.py` for all Pydantic AI agents. Pattern: `create_agent_name(model: Any | None = None) -> AgentName`. Use `get_model()` if model not provided.
+
+**Graph Builder**: `graph_builder.py` contains utilities for building research graphs. Supports iterative and deep research graph construction.
+
+**Error Handling**: Raise `ConfigurationError` if required API keys missing. Log agent creation. Handle import errors gracefully.
+
+---
+
+## src/prompts/ - Prompt Rules
+
+**Pattern**: System prompts stored as module-level constants. Include date injection: `datetime.now().strftime("%Y-%m-%d")`. Format evidence with truncation (1500 chars per item).
+
+**Judge Prompts**: In `judge.py`. Handle empty evidence case separately. Always request structured JSON output.
+
+**Hypothesis Prompts**: In `hypothesis.py`. Use diverse evidence selection (MMR algorithm). Sentence-aware truncation.
+
+**Report Prompts**: In `report.py`. Include full citation details. Use diverse evidence selection (n=20). Emphasize citation validation rules.
+
+---
+
+## Testing Rules
+
+**Structure**: Unit tests in `tests/unit/` (mocked, fast). Integration tests in `tests/integration/` (real APIs, marked `@pytest.mark.integration`).
+
+**Mocking**: Use `respx` for httpx mocking. Use `pytest-mock` for general mocking. Mock LLM calls in unit tests (use `MockJudgeHandler`).
+
+**Fixtures**: Common fixtures in `tests/conftest.py`: `mock_httpx_client`, `mock_llm_response`.
+
+**Coverage**: Aim for >80% coverage. Test error handling, edge cases, and integration paths.
+
+---
+
+## File-Specific Agent Rules
+
+**knowledge_gap.py**: Outputs `KnowledgeGapOutput`. System prompt evaluates research completeness. Handles conversation history. Returns fallback on error.
+
+**writer.py**: Returns markdown string. System prompt includes citation format examples. Validates inputs. Truncates long findings. Retry logic for transient failures.
+
+**long_writer.py**: Uses `ReportDraft` input/output. Writes sections iteratively. Reformats references (deduplicates, renumbers). Reformats section headings.
+
+**proofreader.py**: Takes `ReportDraft`, returns polished markdown. Removes duplicates. Adds summary. Preserves references.
+
+**tool_selector.py**: Outputs `AgentSelectionPlan`. System prompt lists available agents (WebSearchAgent, SiteCrawlerAgent, RAGAgent). Guidelines for when to use each.
+
+**thinking.py**: Returns observation string. Generates observations from conversation history. Uses query and background context.
+
+**input_parser.py**: Outputs `ParsedQuery`. Detects research mode (iterative/deep). Extracts entities and research questions. Improves/refines query.
+
+
+

dev/Makefile

@@ -0,0 +1,51 @@
+.PHONY: install test lint format typecheck check clean all cov cov-html
+
+# Default target
+all: check
+
+install:
+	uv sync --all-extras
+	uv run pre-commit install
+
+test:
+	uv run pytest tests/unit/ -v -m "not openai" -p no:logfire
+
+test-hf:
+	uv run pytest tests/ -v -m "huggingface" -p no:logfire
+
+test-all:
+	uv run pytest tests/ -v -p no:logfire
+
+# Coverage aliases
+cov: test-cov
+test-cov:
+	uv run pytest --cov=src --cov-report=term-missing -m "not openai" -p no:logfire
+
+cov-html:
+	uv run pytest --cov=src --cov-report=html -p no:logfire
+	@echo "Coverage report: open htmlcov/index.html"
+
+lint:
+	uv run ruff check src tests
+
+format:
+	uv run ruff format src tests
+
+typecheck:
+	uv run mypy src
+
+check: lint typecheck test-cov
+	@echo "All checks passed!"
+
+docs-build:
+	uv run mkdocs build
+
+docs-serve:
+	uv run mkdocs serve
+
+docs-clean:
+	rm -rf site/
+
+clean:
+	rm -rf .pytest_cache .mypy_cache .ruff_cache __pycache__ .coverage htmlcov
+	find . -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true

dev/docs_plugins.py

@@ -0,0 +1,74 @@
+"""Custom MkDocs extension to handle code anchor format: ```start:end:filepath"""
+
+import re
+from pathlib import Path
+
+from markdown import Markdown
+from markdown.extensions import Extension
+from markdown.preprocessors import Preprocessor
+
+
+class CodeAnchorPreprocessor(Preprocessor):
+    """Preprocess code blocks with anchor format: ```start:end:filepath"""
+
+    def __init__(self, md: Markdown, base_path: Path):
+        super().__init__(md)
+        self.base_path = base_path
+        self.pattern = re.compile(r"^```(\d+):(\d+):([^\n]+)\n(.*?)```$", re.MULTILINE | re.DOTALL)
+
+    def run(self, lines: list[str]) -> list[str]:
+        """Process lines and convert code anchor format to standard code blocks."""
+        text = "\n".join(lines)
+        new_text = self.pattern.sub(self._replace_code_anchor, text)
+        return new_text.split("\n")
+
+    def _replace_code_anchor(self, match) -> str:
+        """Replace code anchor format with standard code block + link."""
+        start_line = int(match.group(1))
+        end_line = int(match.group(2))
+        file_path = match.group(3).strip()
+        existing_code = match.group(4)
+
+        # Determine language from file extension
+        ext = Path(file_path).suffix.lower()
+        lang_map = {
+            ".py": "python",
+            ".js": "javascript",
+            ".ts": "typescript",
+            ".md": "markdown",
+            ".yaml": "yaml",
+            ".yml": "yaml",
+            ".toml": "toml",
+            ".json": "json",
+            ".html": "html",
+            ".css": "css",
+            ".sh": "bash",
+        }
+        language = lang_map.get(ext, "python")
+
+        # Generate GitHub link
+        repo_url = "https://github.com/DeepCritical/GradioDemo"
+        github_link = f"{repo_url}/blob/main/{file_path}#L{start_line}-L{end_line}"
+
+        # Return standard code block with source link
+        return (
+            f'[View source: `{file_path}` (lines {start_line}-{end_line})]({github_link}){{: target="_blank" }}\n\n'
+            f"```{language}\n{existing_code}\n```"
+        )
+
+
+class CodeAnchorExtension(Extension):
+    """Markdown extension for code anchors."""
+
+    def __init__(self, base_path: str = ".", **kwargs):
+        super().__init__(**kwargs)
+        self.base_path = Path(base_path)
+
+    def extendMarkdown(self, md: Markdown):  # noqa: N802
+        """Register the preprocessor."""
+        md.preprocessors.register(CodeAnchorPreprocessor(md, self.base_path), "codeanchor", 25)
+
+
+def makeExtension(**kwargs):  # noqa: N802
+    """Create the extension."""
+    return CodeAnchorExtension(**kwargs)

docs/api/agents.md

@@ -0,0 +1,266 @@
+# Agents API Reference
+
+This page documents the API for DeepCritical agents.
+
+## KnowledgeGapAgent
+
+**Module**: `src.agents.knowledge_gap`
+
+**Purpose**: Evaluates research state and identifies knowledge gaps.
+
+### Methods
+
+#### `evaluate`
+
+```python
+async def evaluate(
+    self,
+    query: str,
+    background_context: str,
+    conversation_history: Conversation,
+    iteration: int,
+    time_elapsed_minutes: float,
+    max_time_minutes: float
+) -> KnowledgeGapOutput
+```
+
+Evaluates research completeness and identifies outstanding knowledge gaps.
+
+**Parameters**:
+- `query`: Research query string
+- `background_context`: Background context for the query
+- `conversation_history`: Conversation history with previous iterations
+- `iteration`: Current iteration number
+- `time_elapsed_minutes`: Elapsed time in minutes
+- `max_time_minutes`: Maximum time limit in minutes
+
+**Returns**: `KnowledgeGapOutput` with:
+- `research_complete`: Boolean indicating if research is complete
+- `outstanding_gaps`: List of remaining knowledge gaps
+
+## ToolSelectorAgent
+
+**Module**: `src.agents.tool_selector`
+
+**Purpose**: Selects appropriate tools for addressing knowledge gaps.
+
+### Methods
+
+#### `select_tools`
+
+```python
+async def select_tools(
+    self,
+    query: str,
+    knowledge_gaps: list[str],
+    available_tools: list[str]
+) -> AgentSelectionPlan
+```
+
+Selects tools for addressing knowledge gaps.
+
+**Parameters**:
+- `query`: Research query string
+- `knowledge_gaps`: List of knowledge gaps to address
+- `available_tools`: List of available tool names
+
+**Returns**: `AgentSelectionPlan` with list of `AgentTask` objects.
+
+## WriterAgent
+
+**Module**: `src.agents.writer`
+
+**Purpose**: Generates final reports from research findings.
+
+### Methods
+
+#### `write_report`
+
+```python
+async def write_report(
+    self,
+    query: str,
+    findings: str,
+    output_length: str = "medium",
+    output_instructions: str | None = None
+) -> str
+```
+
+Generates a markdown report from research findings.
+
+**Parameters**:
+- `query`: Research query string
+- `findings`: Research findings to include in report
+- `output_length`: Desired output length ("short", "medium", "long")
+- `output_instructions`: Additional instructions for report generation
+
+**Returns**: Markdown string with numbered citations.
+
+## LongWriterAgent
+
+**Module**: `src.agents.long_writer`
+
+**Purpose**: Long-form report generation with section-by-section writing.
+
+### Methods
+
+#### `write_next_section`
+
+```python
+async def write_next_section(
+    self,
+    query: str,
+    draft: ReportDraft,
+    section_title: str,
+    section_content: str
+) -> LongWriterOutput
+```
+
+Writes the next section of a long-form report.
+
+**Parameters**:
+- `query`: Research query string
+- `draft`: Current report draft
+- `section_title`: Title of the section to write
+- `section_content`: Content/guidance for the section
+
+**Returns**: `LongWriterOutput` with updated draft.
+
+#### `write_report`
+
+```python
+async def write_report(
+    self,
+    query: str,
+    report_title: str,
+    report_draft: ReportDraft
+) -> str
+```
+
+Generates final report from draft.
+
+**Parameters**:
+- `query`: Research query string
+- `report_title`: Title of the report
+- `report_draft`: Complete report draft
+
+**Returns**: Final markdown report string.
+
+## ProofreaderAgent
+
+**Module**: `src.agents.proofreader`
+
+**Purpose**: Proofreads and polishes report drafts.
+
+### Methods
+
+#### `proofread`
+
+```python
+async def proofread(
+    self,
+    query: str,
+    report_title: str,
+    report_draft: ReportDraft
+) -> str
+```
+
+Proofreads and polishes a report draft.
+
+**Parameters**:
+- `query`: Research query string
+- `report_title`: Title of the report
+- `report_draft`: Report draft to proofread
+
+**Returns**: Polished markdown string.
+
+## ThinkingAgent
+
+**Module**: `src.agents.thinking`
+
+**Purpose**: Generates observations from conversation history.
+
+### Methods
+
+#### `generate_observations`
+
+```python
+async def generate_observations(
+    self,
+    query: str,
+    background_context: str,
+    conversation_history: Conversation
+) -> str
+```
+
+Generates observations from conversation history.
+
+**Parameters**:
+- `query`: Research query string
+- `background_context`: Background context
+- `conversation_history`: Conversation history
+
+**Returns**: Observation string.
+
+## InputParserAgent
+
+**Module**: `src.agents.input_parser`
+
+**Purpose**: Parses and improves user queries, detects research mode.
+
+### Methods
+
+#### `parse_query`
+
+```python
+async def parse_query(
+    self,
+    query: str
+) -> ParsedQuery
+```
+
+Parses and improves a user query.
+
+**Parameters**:
+- `query`: Original query string
+
+**Returns**: `ParsedQuery` with:
+- `original_query`: Original query string
+- `improved_query`: Refined query string
+- `research_mode`: "iterative" or "deep"
+- `key_entities`: List of key entities
+- `research_questions`: List of research questions
+
+## Factory Functions
+
+All agents have factory functions in `src.agent_factory.agents`:
+
+```python
+def create_knowledge_gap_agent(model: Any | None = None) -> KnowledgeGapAgent
+def create_tool_selector_agent(model: Any | None = None) -> ToolSelectorAgent
+def create_writer_agent(model: Any | None = None) -> WriterAgent
+def create_long_writer_agent(model: Any | None = None) -> LongWriterAgent
+def create_proofreader_agent(model: Any | None = None) -> ProofreaderAgent
+def create_thinking_agent(model: Any | None = None) -> ThinkingAgent
+def create_input_parser_agent(model: Any | None = None) -> InputParserAgent
+```
+
+**Parameters**:
+- `model`: Optional Pydantic AI model. If None, uses `get_model()` from settings.
+
+**Returns**: Agent instance.
+
+## See Also
+
+- [Architecture - Agents](../architecture/agents.md) - Architecture overview
+- [Models API](models.md) - Data models used by agents
+
+
+
+
+
+
+
+
+
+

docs/api/models.md

@@ -0,0 +1,244 @@
+# Models API Reference
+
+This page documents the Pydantic models used throughout DeepCritical.
+
+## Evidence
+
+**Module**: `src.utils.models`
+
+**Purpose**: Represents evidence from search results.
+
+```python
+class Evidence(BaseModel):
+    citation: Citation
+    content: str
+    relevance_score: float = Field(ge=0.0, le=1.0)
+    metadata: dict[str, Any] = Field(default_factory=dict)
+```
+
+**Fields**:
+- `citation`: Citation information (title, URL, date, authors)
+- `content`: Evidence text content
+- `relevance_score`: Relevance score (0.0-1.0)
+- `metadata`: Additional metadata dictionary
+
+## Citation
+
+**Module**: `src.utils.models`
+
+**Purpose**: Citation information for evidence.
+
+```python
+class Citation(BaseModel):
+    title: str
+    url: str
+    date: str | None = None
+    authors: list[str] = Field(default_factory=list)
+```
+
+**Fields**:
+- `title`: Article/trial title
+- `url`: Source URL
+- `date`: Publication date (optional)
+- `authors`: List of authors (optional)
+
+## KnowledgeGapOutput
+
+**Module**: `src.utils.models`
+
+**Purpose**: Output from knowledge gap evaluation.
+
+```python
+class KnowledgeGapOutput(BaseModel):
+    research_complete: bool
+    outstanding_gaps: list[str] = Field(default_factory=list)
+```
+
+**Fields**:
+- `research_complete`: Boolean indicating if research is complete
+- `outstanding_gaps`: List of remaining knowledge gaps
+
+## AgentSelectionPlan
+
+**Module**: `src.utils.models`
+
+**Purpose**: Plan for tool/agent selection.
+
+```python
+class AgentSelectionPlan(BaseModel):
+    tasks: list[AgentTask] = Field(default_factory=list)
+```
+
+**Fields**:
+- `tasks`: List of agent tasks to execute
+
+## AgentTask
+
+**Module**: `src.utils.models`
+
+**Purpose**: Individual agent task.
+
+```python
+class AgentTask(BaseModel):
+    agent_name: str
+    query: str
+    context: dict[str, Any] = Field(default_factory=dict)
+```
+
+**Fields**:
+- `agent_name`: Name of agent to use
+- `query`: Task query
+- `context`: Additional context dictionary
+
+## ReportDraft
+
+**Module**: `src.utils.models`
+
+**Purpose**: Draft structure for long-form reports.
+
+```python
+class ReportDraft(BaseModel):
+    title: str
+    sections: list[ReportSection] = Field(default_factory=list)
+    references: list[Citation] = Field(default_factory=list)
+```
+
+**Fields**:
+- `title`: Report title
+- `sections`: List of report sections
+- `references`: List of citations
+
+## ReportSection
+
+**Module**: `src.utils.models`
+
+**Purpose**: Individual section in a report draft.
+
+```python
+class ReportSection(BaseModel):
+    title: str
+    content: str
+    order: int
+```
+
+**Fields**:
+- `title`: Section title
+- `content`: Section content
+- `order`: Section order number
+
+## ParsedQuery
+
+**Module**: `src.utils.models`
+
+**Purpose**: Parsed and improved query.
+
+```python
+class ParsedQuery(BaseModel):
+    original_query: str
+    improved_query: str
+    research_mode: Literal["iterative", "deep"]
+    key_entities: list[str] = Field(default_factory=list)
+    research_questions: list[str] = Field(default_factory=list)
+```
+
+**Fields**:
+- `original_query`: Original query string
+- `improved_query`: Refined query string
+- `research_mode`: Research mode ("iterative" or "deep")
+- `key_entities`: List of key entities
+- `research_questions`: List of research questions
+
+## Conversation
+
+**Module**: `src.utils.models`
+
+**Purpose**: Conversation history with iterations.
+
+```python
+class Conversation(BaseModel):
+    iterations: list[IterationData] = Field(default_factory=list)
+```
+
+**Fields**:
+- `iterations`: List of iteration data
+
+## IterationData
+
+**Module**: `src.utils.models`
+
+**Purpose**: Data for a single iteration.
+
+```python
+class IterationData(BaseModel):
+    iteration: int
+    observations: str | None = None
+    knowledge_gaps: list[str] = Field(default_factory=list)
+    tool_calls: list[dict[str, Any]] = Field(default_factory=list)
+    findings: str | None = None
+    thoughts: str | None = None
+```
+
+**Fields**:
+- `iteration`: Iteration number
+- `observations`: Generated observations
+- `knowledge_gaps`: Identified knowledge gaps
+- `tool_calls`: Tool calls made
+- `findings`: Findings from tools
+- `thoughts`: Agent thoughts
+
+## AgentEvent
+
+**Module**: `src.utils.models`
+
+**Purpose**: Event emitted during research execution.
+
+```python
+class AgentEvent(BaseModel):
+    type: str
+    iteration: int | None = None
+    data: dict[str, Any] = Field(default_factory=dict)
+```
+
+**Fields**:
+- `type`: Event type (e.g., "started", "search_complete", "complete")
+- `iteration`: Iteration number (optional)
+- `data`: Event data dictionary
+
+## BudgetStatus
+
+**Module**: `src.utils.models`
+
+**Purpose**: Current budget status.
+
+```python
+class BudgetStatus(BaseModel):
+    tokens_used: int
+    tokens_limit: int
+    time_elapsed_seconds: float
+    time_limit_seconds: float
+    iterations: int
+    iterations_limit: int
+```
+
+**Fields**:
+- `tokens_used`: Tokens used so far
+- `tokens_limit`: Token limit
+- `time_elapsed_seconds`: Elapsed time in seconds
+- `time_limit_seconds`: Time limit in seconds
+- `iterations`: Current iteration count
+- `iterations_limit`: Iteration limit
+
+## See Also
+
+- [Architecture - Agents](../architecture/agents.md) - How models are used
+- [Configuration](../configuration/index.md) - Model configuration
+
+
+
+
+
+
+
+
+
+

docs/api/orchestrators.md

@@ -0,0 +1,191 @@
+# Orchestrators API Reference
+
+This page documents the API for DeepCritical orchestrators.
+
+## IterativeResearchFlow
+
+**Module**: `src.orchestrator.research_flow`
+
+**Purpose**: Single-loop research with search-judge-synthesize cycles.
+
+### Methods
+
+#### `run`
+
+```python
+async def run(
+    self,
+    query: str,
+    background_context: str = "",
+    max_iterations: int | None = None,
+    max_time_minutes: float | None = None,
+    token_budget: int | None = None
+) -> AsyncGenerator[AgentEvent, None]
+```
+
+Runs iterative research flow.
+
+**Parameters**:
+- `query`: Research query string
+- `background_context`: Background context (default: "")
+- `max_iterations`: Maximum iterations (default: from settings)
+- `max_time_minutes`: Maximum time in minutes (default: from settings)
+- `token_budget`: Token budget (default: from settings)
+
+**Yields**: `AgentEvent` objects for:
+- `started`: Research started
+- `search_complete`: Search completed
+- `judge_complete`: Evidence evaluation completed
+- `synthesizing`: Generating report
+- `complete`: Research completed
+- `error`: Error occurred
+
+## DeepResearchFlow
+
+**Module**: `src.orchestrator.research_flow`
+
+**Purpose**: Multi-section parallel research with planning and synthesis.
+
+### Methods
+
+#### `run`
+
+```python
+async def run(
+    self,
+    query: str,
+    background_context: str = "",
+    max_iterations_per_section: int | None = None,
+    max_time_minutes: float | None = None,
+    token_budget: int | None = None
+) -> AsyncGenerator[AgentEvent, None]
+```
+
+Runs deep research flow.
+
+**Parameters**:
+- `query`: Research query string
+- `background_context`: Background context (default: "")
+- `max_iterations_per_section`: Maximum iterations per section (default: from settings)
+- `max_time_minutes`: Maximum time in minutes (default: from settings)
+- `token_budget`: Token budget (default: from settings)
+
+**Yields**: `AgentEvent` objects for:
+- `started`: Research started
+- `planning`: Creating research plan
+- `looping`: Running parallel research loops
+- `synthesizing`: Synthesizing results
+- `complete`: Research completed
+- `error`: Error occurred
+
+## GraphOrchestrator
+
+**Module**: `src.orchestrator.graph_orchestrator`
+
+**Purpose**: Graph-based execution using Pydantic AI agents as nodes.
+
+### Methods
+
+#### `run`
+
+```python
+async def run(
+    self,
+    query: str,
+    research_mode: str = "auto",
+    use_graph: bool = True
+) -> AsyncGenerator[AgentEvent, None]
+```
+
+Runs graph-based research orchestration.
+
+**Parameters**:
+- `query`: Research query string
+- `research_mode`: Research mode ("iterative", "deep", or "auto")
+- `use_graph`: Whether to use graph execution (default: True)
+
+**Yields**: `AgentEvent` objects during graph execution.
+
+## Orchestrator Factory
+
+**Module**: `src.orchestrator_factory`
+
+**Purpose**: Factory for creating orchestrators.
+
+### Functions
+
+#### `create_orchestrator`
+
+```python
+def create_orchestrator(
+    search_handler: SearchHandlerProtocol,
+    judge_handler: JudgeHandlerProtocol,
+    config: dict[str, Any],
+    mode: str | None = None
+) -> Any
+```
+
+Creates an orchestrator instance.
+
+**Parameters**:
+- `search_handler`: Search handler protocol implementation
+- `judge_handler`: Judge handler protocol implementation
+- `config`: Configuration dictionary
+- `mode`: Orchestrator mode ("simple", "advanced", "magentic", or None for auto-detect)
+
+**Returns**: Orchestrator instance.
+
+**Raises**:
+- `ValueError`: If requirements not met
+
+**Modes**:
+- `"simple"`: Legacy orchestrator
+- `"advanced"` or `"magentic"`: Magentic orchestrator (requires OpenAI API key)
+- `None`: Auto-detect based on API key availability
+
+## MagenticOrchestrator
+
+**Module**: `src.orchestrator_magentic`
+
+**Purpose**: Multi-agent coordination using Microsoft Agent Framework.
+
+### Methods
+
+#### `run`
+
+```python
+async def run(
+    self,
+    query: str,
+    max_rounds: int = 15,
+    max_stalls: int = 3
+) -> AsyncGenerator[AgentEvent, None]
+```
+
+Runs Magentic orchestration.
+
+**Parameters**:
+- `query`: Research query string
+- `max_rounds`: Maximum rounds (default: 15)
+- `max_stalls`: Maximum stalls before reset (default: 3)
+
+**Yields**: `AgentEvent` objects converted from Magentic events.
+
+**Requirements**:
+- `agent-framework-core` package
+- OpenAI API key
+
+## See Also
+
+- [Architecture - Orchestrators](../architecture/orchestrators.md) - Architecture overview
+- [Graph Orchestration](../architecture/graph-orchestration.md) - Graph execution details
+
+
+
+
+
+
+
+
+
+

docs/api/services.md

@@ -0,0 +1,197 @@
+# Services API Reference
+
+This page documents the API for DeepCritical services.
+
+## EmbeddingService
+
+**Module**: `src.services.embeddings`
+
+**Purpose**: Local sentence-transformers for semantic search and deduplication.
+
+### Methods
+
+#### `embed`
+
+```python
+async def embed(self, text: str) -> list[float]
+```
+
+Generates embedding for a text string.
+
+**Parameters**:
+- `text`: Text to embed
+
+**Returns**: Embedding vector as list of floats.
+
+#### `embed_batch`
+
+```python
+async def embed_batch(self, texts: list[str]) -> list[list[float]]
+```
+
+Generates embeddings for multiple texts.
+
+**Parameters**:
+- `texts`: List of texts to embed
+
+**Returns**: List of embedding vectors.
+
+#### `similarity`
+
+```python
+async def similarity(self, text1: str, text2: str) -> float
+```
+
+Calculates similarity between two texts.
+
+**Parameters**:
+- `text1`: First text
+- `text2`: Second text
+
+**Returns**: Similarity score (0.0-1.0).
+
+#### `find_duplicates`
+
+```python
+async def find_duplicates(
+    self,
+    texts: list[str],
+    threshold: float = 0.85
+) -> list[tuple[int, int]]
+```
+
+Finds duplicate texts based on similarity threshold.
+
+**Parameters**:
+- `texts`: List of texts to check
+- `threshold`: Similarity threshold (default: 0.85)
+
+**Returns**: List of (index1, index2) tuples for duplicate pairs.
+
+### Factory Function
+
+#### `get_embedding_service`
+
+```python
+@lru_cache(maxsize=1)
+def get_embedding_service() -> EmbeddingService
+```
+
+Returns singleton EmbeddingService instance.
+
+## LlamaIndexRAGService
+
+**Module**: `src.services.rag`
+
+**Purpose**: Retrieval-Augmented Generation using LlamaIndex.
+
+### Methods
+
+#### `ingest_evidence`
+
+```python
+async def ingest_evidence(self, evidence: list[Evidence]) -> None
+```
+
+Ingests evidence into RAG service.
+
+**Parameters**:
+- `evidence`: List of Evidence objects to ingest
+
+**Note**: Requires OpenAI API key for embeddings.
+
+#### `retrieve`
+
+```python
+async def retrieve(
+    self,
+    query: str,
+    top_k: int = 5
+) -> list[Document]
+```
+
+Retrieves relevant documents for a query.
+
+**Parameters**:
+- `query`: Search query string
+- `top_k`: Number of top results to return (default: 5)
+
+**Returns**: List of Document objects with metadata.
+
+#### `query`
+
+```python
+async def query(
+    self,
+    query: str,
+    top_k: int = 5
+) -> str
+```
+
+Queries RAG service and returns formatted results.
+
+**Parameters**:
+- `query`: Search query string
+- `top_k`: Number of top results to return (default: 5)
+
+**Returns**: Formatted query results as string.
+
+### Factory Function
+
+#### `get_rag_service`
+
+```python
+@lru_cache(maxsize=1)
+def get_rag_service() -> LlamaIndexRAGService | None
+```
+
+Returns singleton LlamaIndexRAGService instance, or None if OpenAI key not available.
+
+## StatisticalAnalyzer
+
+**Module**: `src.services.statistical_analyzer`
+
+**Purpose**: Secure execution of AI-generated statistical code.
+
+### Methods
+
+#### `analyze`
+
+```python
+async def analyze(
+    self,
+    hypothesis: str,
+    evidence: list[Evidence],
+    data_description: str | None = None
+) -> AnalysisResult
+```
+
+Analyzes a hypothesis using statistical methods.
+
+**Parameters**:
+- `hypothesis`: Hypothesis to analyze
+- `evidence`: List of Evidence objects
+- `data_description`: Optional data description
+
+**Returns**: `AnalysisResult` with:
+- `verdict`: SUPPORTED, REFUTED, or INCONCLUSIVE
+- `code`: Generated analysis code
+- `output`: Execution output
+- `error`: Error message if execution failed
+
+**Note**: Requires Modal credentials for sandbox execution.
+
+## See Also
+
+- [Architecture - Services](../architecture/services.md) - Architecture overview
+- [Configuration](../configuration/index.md) - Service configuration
+
+
+
+
+
+
+
+
+
+

docs/api/tools.md

@@ -0,0 +1,231 @@
+# Tools API Reference
+
+This page documents the API for DeepCritical search tools.
+
+## SearchTool Protocol
+
+All tools implement the `SearchTool` protocol:
+
+```python
+class SearchTool(Protocol):
+    @property
+    def name(self) -> str: ...
+    
+    async def search(
+        self, 
+        query: str, 
+        max_results: int = 10
+    ) -> list[Evidence]: ...
+```
+
+## PubMedTool
+
+**Module**: `src.tools.pubmed`
+
+**Purpose**: Search peer-reviewed biomedical literature from PubMed.
+
+### Properties
+
+#### `name`
+
+```python
+@property
+def name(self) -> str
+```
+
+Returns tool name: `"pubmed"`
+
+### Methods
+
+#### `search`
+
+```python
+async def search(
+    self,
+    query: str,
+    max_results: int = 10
+) -> list[Evidence]
+```
+
+Searches PubMed for articles.
+
+**Parameters**:
+- `query`: Search query string
+- `max_results`: Maximum number of results to return (default: 10)
+
+**Returns**: List of `Evidence` objects with PubMed articles.
+
+**Raises**:
+- `SearchError`: If search fails
+- `RateLimitError`: If rate limit is exceeded
+
+## ClinicalTrialsTool
+
+**Module**: `src.tools.clinicaltrials`
+
+**Purpose**: Search ClinicalTrials.gov for interventional studies.
+
+### Properties
+
+#### `name`
+
+```python
+@property
+def name(self) -> str
+```
+
+Returns tool name: `"clinicaltrials"`
+
+### Methods
+
+#### `search`
+
+```python
+async def search(
+    self,
+    query: str,
+    max_results: int = 10
+) -> list[Evidence]
+```
+
+Searches ClinicalTrials.gov for trials.
+
+**Parameters**:
+- `query`: Search query string
+- `max_results`: Maximum number of results to return (default: 10)
+
+**Returns**: List of `Evidence` objects with clinical trials.
+
+**Note**: Only returns interventional studies with status: COMPLETED, ACTIVE_NOT_RECRUITING, RECRUITING, ENROLLING_BY_INVITATION
+
+**Raises**:
+- `SearchError`: If search fails
+
+## EuropePMCTool
+
+**Module**: `src.tools.europepmc`
+
+**Purpose**: Search Europe PMC for preprints and peer-reviewed articles.
+
+### Properties
+
+#### `name`
+
+```python
+@property
+def name(self) -> str
+```
+
+Returns tool name: `"europepmc"`
+
+### Methods
+
+#### `search`
+
+```python
+async def search(
+    self,
+    query: str,
+    max_results: int = 10
+) -> list[Evidence]
+```
+
+Searches Europe PMC for articles and preprints.
+
+**Parameters**:
+- `query`: Search query string
+- `max_results`: Maximum number of results to return (default: 10)
+
+**Returns**: List of `Evidence` objects with articles/preprints.
+
+**Note**: Includes both preprints (marked with `[PREPRINT - Not peer-reviewed]`) and peer-reviewed articles.
+
+**Raises**:
+- `SearchError`: If search fails
+
+## RAGTool
+
+**Module**: `src.tools.rag_tool`
+
+**Purpose**: Semantic search within collected evidence.
+
+### Properties
+
+#### `name`
+
+```python
+@property
+def name(self) -> str
+```
+
+Returns tool name: `"rag"`
+
+### Methods
+
+#### `search`
+
+```python
+async def search(
+    self,
+    query: str,
+    max_results: int = 10
+) -> list[Evidence]
+```
+
+Searches collected evidence using semantic similarity.
+
+**Parameters**:
+- `query`: Search query string
+- `max_results`: Maximum number of results to return (default: 10)
+
+**Returns**: List of `Evidence` objects from collected evidence.
+
+**Note**: Requires evidence to be ingested into RAG service first.
+
+## SearchHandler
+
+**Module**: `src.tools.search_handler`
+
+**Purpose**: Orchestrates parallel searches across multiple tools.
+
+### Methods
+
+#### `search`
+
+```python
+async def search(
+    self,
+    query: str,
+    tools: list[SearchTool] | None = None,
+    max_results_per_tool: int = 10
+) -> SearchResult
+```
+
+Searches multiple tools in parallel.
+
+**Parameters**:
+- `query`: Search query string
+- `tools`: List of tools to use (default: all available tools)
+- `max_results_per_tool`: Maximum results per tool (default: 10)
+
+**Returns**: `SearchResult` with:
+- `evidence`: Aggregated list of evidence
+- `tool_results`: Results per tool
+- `total_count`: Total number of results
+
+**Note**: Uses `asyncio.gather()` for parallel execution. Handles tool failures gracefully.
+
+## See Also
+
+- [Architecture - Tools](../architecture/tools.md) - Architecture overview
+- [Models API](models.md) - Data models used by tools
+
+
+
+
+
+
+
+
+
+

docs/architecture/agents.md

@@ -0,0 +1,188 @@
+# Agents Architecture
+
+DeepCritical uses Pydantic AI agents for all AI-powered operations. All agents follow a consistent pattern and use structured output types.
+
+## Agent Pattern
+
+All agents use the Pydantic AI `Agent` class with the following structure:
+
+- **System Prompt**: Module-level constant with date injection
+- **Agent Class**: `__init__(model: Any | None = None)`
+- **Main Method**: Async method (e.g., `async def evaluate()`, `async def write_report()`)
+- **Factory Function**: `def create_agent_name(model: Any | None = None) -> AgentName`
+
+## Model Initialization
+
+Agents use `get_model()` from `src/agent_factory/judges.py` if no model is provided. This supports:
+
+- OpenAI models
+- Anthropic models
+- HuggingFace Inference API models
+
+The model selection is based on the configured `LLM_PROVIDER` in settings.
+
+## Error Handling
+
+Agents return fallback values on failure rather than raising exceptions:
+
+- `KnowledgeGapOutput(research_complete=False, outstanding_gaps=[...])`
+- Empty strings for text outputs
+- Default structured outputs
+
+All errors are logged with context using structlog.
+
+## Input Validation
+
+All agents validate inputs:
+
+- Check that queries/inputs are not empty
+- Truncate very long inputs with warnings
+- Handle None values gracefully
+
+## Output Types
+
+Agents use structured output types from `src/utils/models.py`:
+
+- `KnowledgeGapOutput`: Research completeness evaluation
+- `AgentSelectionPlan`: Tool selection plan
+- `ReportDraft`: Long-form report structure
+- `ParsedQuery`: Query parsing and mode detection
+
+For text output (writer agents), agents return `str` directly.
+
+## Agent Types
+
+### Knowledge Gap Agent
+
+**File**: `src/agents/knowledge_gap.py`
+
+**Purpose**: Evaluates research state and identifies knowledge gaps.
+
+**Output**: `KnowledgeGapOutput` with:
+- `research_complete`: Boolean indicating if research is complete
+- `outstanding_gaps`: List of remaining knowledge gaps
+
+**Methods**:
+- `async def evaluate(query, background_context, conversation_history, iteration, time_elapsed_minutes, max_time_minutes) -> KnowledgeGapOutput`
+
+### Tool Selector Agent
+
+**File**: `src/agents/tool_selector.py`
+
+**Purpose**: Selects appropriate tools for addressing knowledge gaps.
+
+**Output**: `AgentSelectionPlan` with list of `AgentTask` objects.
+
+**Available Agents**:
+- `WebSearchAgent`: General web search for fresh information
+- `SiteCrawlerAgent`: Research specific entities/companies
+- `RAGAgent`: Semantic search within collected evidence
+
+### Writer Agent
+
+**File**: `src/agents/writer.py`
+
+**Purpose**: Generates final reports from research findings.
+
+**Output**: Markdown string with numbered citations.
+
+**Methods**:
+- `async def write_report(query, findings, output_length, output_instructions) -> str`
+
+**Features**:
+- Validates inputs
+- Truncates very long findings (max 50000 chars) with warning
+- Retry logic for transient failures (3 retries)
+- Citation validation before returning
+
+### Long Writer Agent
+
+**File**: `src/agents/long_writer.py`
+
+**Purpose**: Long-form report generation with section-by-section writing.
+
+**Input/Output**: Uses `ReportDraft` models.
+
+**Methods**:
+- `async def write_next_section(query, draft, section_title, section_content) -> LongWriterOutput`
+- `async def write_report(query, report_title, report_draft) -> str`
+
+**Features**:
+- Writes sections iteratively
+- Aggregates references across sections
+- Reformats section headings and references
+- Deduplicates and renumbers references
+
+### Proofreader Agent
+
+**File**: `src/agents/proofreader.py`
+
+**Purpose**: Proofreads and polishes report drafts.
+
+**Input**: `ReportDraft`
+**Output**: Polished markdown string
+
+**Methods**:
+- `async def proofread(query, report_title, report_draft) -> str`
+
+**Features**:
+- Removes duplicate content across sections
+- Adds executive summary if multiple sections
+- Preserves all references and citations
+- Improves flow and readability
+
+### Thinking Agent
+
+**File**: `src/agents/thinking.py`
+
+**Purpose**: Generates observations from conversation history.
+
+**Output**: Observation string
+
+**Methods**:
+- `async def generate_observations(query, background_context, conversation_history) -> str`
+
+### Input Parser Agent
+
+**File**: `src/agents/input_parser.py`
+
+**Purpose**: Parses and improves user queries, detects research mode.
+
+**Output**: `ParsedQuery` with:
+- `original_query`: Original query string
+- `improved_query`: Refined query string
+- `research_mode`: "iterative" or "deep"
+- `key_entities`: List of key entities
+- `research_questions`: List of research questions
+
+## Factory Functions
+
+All agents have factory functions in `src/agent_factory/agents.py`:
+
+```python
+def create_knowledge_gap_agent(model: Any | None = None) -> KnowledgeGapAgent
+def create_tool_selector_agent(model: Any | None = None) -> ToolSelectorAgent
+def create_writer_agent(model: Any | None = None) -> WriterAgent
+# ... etc
+```
+
+Factory functions:
+- Use `get_model()` if no model provided
+- Raise `ConfigurationError` if creation fails
+- Log agent creation
+
+## See Also
+
+- [Orchestrators](orchestrators.md) - How agents are orchestrated
+- [API Reference - Agents](../api/agents.md) - API documentation
+- [Contributing - Code Style](../contributing/code-style.md) - Development guidelines
+
+
+
+
+
+
+
+
+
+

docs/architecture/graph-orchestration.md

@@ -0,0 +1,152 @@
+# Graph Orchestration Architecture
+
+## Overview
+
+Phase 4 implements a graph-based orchestration system for research workflows using Pydantic AI agents as nodes. This enables better parallel execution, conditional routing, and state management compared to simple agent chains.
+
+## Graph Structure
+
+### Nodes
+
+Graph nodes represent different stages in the research workflow:
+
+1. **Agent Nodes**: Execute Pydantic AI agents
+   - Input: Prompt/query
+   - Output: Structured or unstructured response
+   - Examples: `KnowledgeGapAgent`, `ToolSelectorAgent`, `ThinkingAgent`
+
+2. **State Nodes**: Update or read workflow state
+   - Input: Current state
+   - Output: Updated state
+   - Examples: Update evidence, update conversation history
+
+3. **Decision Nodes**: Make routing decisions based on conditions
+   - Input: Current state/results
+   - Output: Next node ID
+   - Examples: Continue research vs. complete research
+
+4. **Parallel Nodes**: Execute multiple nodes concurrently
+   - Input: List of node IDs
+   - Output: Aggregated results
+   - Examples: Parallel iterative research loops
+
+### Edges
+
+Edges define transitions between nodes:
+
+1. **Sequential Edges**: Always traversed (no condition)
+   - From: Source node
+   - To: Target node
+   - Condition: None (always True)
+
+2. **Conditional Edges**: Traversed based on condition
+   - From: Source node
+   - To: Target node
+   - Condition: Callable that returns bool
+   - Example: If research complete → go to writer, else → continue loop
+
+3. **Parallel Edges**: Used for parallel execution branches
+   - From: Parallel node
+   - To: Multiple target nodes
+   - Execution: All targets run concurrently
+
+## Graph Patterns
+
+### Iterative Research Graph
+
+```
+[Input] → [Thinking] → [Knowledge Gap] → [Decision: Complete?]
+                                              ↓ No          ↓ Yes
+                                    [Tool Selector]    [Writer]
+                                              ↓
+                                    [Execute Tools] → [Loop Back]
+```
+
+### Deep Research Graph
+
+```
+[Input] → [Planner] → [Parallel Iterative Loops] → [Synthesizer]
+                           ↓         ↓         ↓
+                        [Loop1]  [Loop2]  [Loop3]
+```
+
+## State Management
+
+State is managed via `WorkflowState` using `ContextVar` for thread-safe isolation:
+
+- **Evidence**: Collected evidence from searches
+- **Conversation**: Iteration history (gaps, tool calls, findings, thoughts)
+- **Embedding Service**: For semantic search
+
+State transitions occur at state nodes, which update the global workflow state.
+
+## Execution Flow
+
+1. **Graph Construction**: Build graph from nodes and edges
+2. **Graph Validation**: Ensure graph is valid (no cycles, all nodes reachable)
+3. **Graph Execution**: Traverse graph from entry node
+4. **Node Execution**: Execute each node based on type
+5. **Edge Evaluation**: Determine next node(s) based on edges
+6. **Parallel Execution**: Use `asyncio.gather()` for parallel nodes
+7. **State Updates**: Update state at state nodes
+8. **Event Streaming**: Yield events during execution for UI
+
+## Conditional Routing
+
+Decision nodes evaluate conditions and return next node IDs:
+
+- **Knowledge Gap Decision**: If `research_complete` → writer, else → tool selector
+- **Budget Decision**: If budget exceeded → exit, else → continue
+- **Iteration Decision**: If max iterations → exit, else → continue
+
+## Parallel Execution
+
+Parallel nodes execute multiple nodes concurrently:
+
+- Each parallel branch runs independently
+- Results are aggregated after all branches complete
+- State is synchronized after parallel execution
+- Errors in one branch don't stop other branches
+
+## Budget Enforcement
+
+Budget constraints are enforced at decision nodes:
+
+- **Token Budget**: Track LLM token usage
+- **Time Budget**: Track elapsed time
+- **Iteration Budget**: Track iteration count
+
+If any budget is exceeded, execution routes to exit node.
+
+## Error Handling
+
+Errors are handled at multiple levels:
+
+1. **Node Level**: Catch errors in individual node execution
+2. **Graph Level**: Handle errors during graph traversal
+3. **State Level**: Rollback state changes on error
+
+Errors are logged and yield error events for UI.
+
+## Backward Compatibility
+
+Graph execution is optional via feature flag:
+
+- `USE_GRAPH_EXECUTION=true`: Use graph-based execution
+- `USE_GRAPH_EXECUTION=false`: Use agent chain execution (existing)
+
+This allows gradual migration and fallback if needed.
+
+
+
+
+
+
+
+
+
+
+
+
+
+

docs/architecture/graph_orchestration.md

@@ -0,0 +1,159 @@
+# Graph Orchestration Architecture
+
+## Overview
+
+Phase 4 implements a graph-based orchestration system for research workflows using Pydantic AI agents as nodes. This enables better parallel execution, conditional routing, and state management compared to simple agent chains.
+
+## Graph Structure
+
+### Nodes
+
+Graph nodes represent different stages in the research workflow:
+
+1. **Agent Nodes**: Execute Pydantic AI agents
+   - Input: Prompt/query
+   - Output: Structured or unstructured response
+   - Examples: `KnowledgeGapAgent`, `ToolSelectorAgent`, `ThinkingAgent`
+
+2. **State Nodes**: Update or read workflow state
+   - Input: Current state
+   - Output: Updated state
+   - Examples: Update evidence, update conversation history
+
+3. **Decision Nodes**: Make routing decisions based on conditions
+   - Input: Current state/results
+   - Output: Next node ID
+   - Examples: Continue research vs. complete research
+
+4. **Parallel Nodes**: Execute multiple nodes concurrently
+   - Input: List of node IDs
+   - Output: Aggregated results
+   - Examples: Parallel iterative research loops
+
+### Edges
+
+Edges define transitions between nodes:
+
+1. **Sequential Edges**: Always traversed (no condition)
+   - From: Source node
+   - To: Target node
+   - Condition: None (always True)
+
+2. **Conditional Edges**: Traversed based on condition
+   - From: Source node
+   - To: Target node
+   - Condition: Callable that returns bool
+   - Example: If research complete → go to writer, else → continue loop
+
+3. **Parallel Edges**: Used for parallel execution branches
+   - From: Parallel node
+   - To: Multiple target nodes
+   - Execution: All targets run concurrently
+
+## Graph Patterns
+
+### Iterative Research Graph
+
+```
+[Input] → [Thinking] → [Knowledge Gap] → [Decision: Complete?]
+                                              ↓ No          ↓ Yes
+                                    [Tool Selector]    [Writer]
+                                              ↓
+                                    [Execute Tools] → [Loop Back]
+```
+
+### Deep Research Graph
+
+```
+[Input] → [Planner] → [Parallel Iterative Loops] → [Synthesizer]
+                           ↓         ↓         ↓
+                        [Loop1]  [Loop2]  [Loop3]
+```
+
+## State Management
+
+State is managed via `WorkflowState` using `ContextVar` for thread-safe isolation:
+
+- **Evidence**: Collected evidence from searches
+- **Conversation**: Iteration history (gaps, tool calls, findings, thoughts)
+- **Embedding Service**: For semantic search
+
+State transitions occur at state nodes, which update the global workflow state.
+
+## Execution Flow
+
+1. **Graph Construction**: Build graph from nodes and edges
+2. **Graph Validation**: Ensure graph is valid (no cycles, all nodes reachable)
+3. **Graph Execution**: Traverse graph from entry node
+4. **Node Execution**: Execute each node based on type
+5. **Edge Evaluation**: Determine next node(s) based on edges
+6. **Parallel Execution**: Use `asyncio.gather()` for parallel nodes
+7. **State Updates**: Update state at state nodes
+8. **Event Streaming**: Yield events during execution for UI
+
+## Conditional Routing
+
+Decision nodes evaluate conditions and return next node IDs:
+
+- **Knowledge Gap Decision**: If `research_complete` → writer, else → tool selector
+- **Budget Decision**: If budget exceeded → exit, else → continue
+- **Iteration Decision**: If max iterations → exit, else → continue
+
+## Parallel Execution
+
+Parallel nodes execute multiple nodes concurrently:
+
+- Each parallel branch runs independently
+- Results are aggregated after all branches complete
+- State is synchronized after parallel execution
+- Errors in one branch don't stop other branches
+
+## Budget Enforcement
+
+Budget constraints are enforced at decision nodes:
+
+- **Token Budget**: Track LLM token usage
+- **Time Budget**: Track elapsed time
+- **Iteration Budget**: Track iteration count
+
+If any budget is exceeded, execution routes to exit node.
+
+## Error Handling
+
+Errors are handled at multiple levels:
+
+1. **Node Level**: Catch errors in individual node execution
+2. **Graph Level**: Handle errors during graph traversal
+3. **State Level**: Rollback state changes on error
+
+Errors are logged and yield error events for UI.
+
+## Backward Compatibility
+
+Graph execution is optional via feature flag:
+
+- `USE_GRAPH_EXECUTION=true`: Use graph-based execution
+- `USE_GRAPH_EXECUTION=false`: Use agent chain execution (existing)
+
+This allows gradual migration and fallback if needed.
+
+## See Also
+
+- [Orchestrators](orchestrators.md) - Overview of all orchestrator patterns
+- [Workflows](workflows.md) - Workflow diagrams and patterns
+- [Workflow Diagrams](workflow-diagrams.md) - Detailed workflow diagrams
+- [API Reference - Orchestrators](../api/orchestrators.md) - API documentation
+
+
+
+
+
+
+
+
+
+
+
+
+
+

docs/architecture/middleware.md

@@ -0,0 +1,138 @@
+# Middleware Architecture
+
+DeepCritical uses middleware for state management, budget tracking, and workflow coordination.
+
+## State Management
+
+### WorkflowState
+
+**File**: `src/middleware/state_machine.py`
+
+**Purpose**: Thread-safe state management for research workflows
+
+**Implementation**: Uses `ContextVar` for thread-safe isolation
+
+**State Components**:
+- `evidence: list[Evidence]`: Collected evidence from searches
+- `conversation: Conversation`: Iteration history (gaps, tool calls, findings, thoughts)
+- `embedding_service: Any`: Embedding service for semantic search
+
+**Methods**:
+- `add_evidence(evidence: Evidence)`: Adds evidence with URL-based deduplication
+- `async search_related(query: str, top_k: int = 5) -> list[Evidence]`: Semantic search
+
+**Initialization**:
+```python
+from src.middleware.state_machine import init_workflow_state
+
+init_workflow_state(embedding_service)
+```
+
+**Access**:
+```python
+from src.middleware.state_machine import get_workflow_state
+
+state = get_workflow_state()  # Auto-initializes if missing
+```
+
+## Workflow Manager
+
+**File**: `src/middleware/workflow_manager.py`
+
+**Purpose**: Coordinates parallel research loops
+
+**Methods**:
+- `add_loop(loop: ResearchLoop)`: Add a research loop to manage
+- `async run_loops_parallel() -> list[ResearchLoop]`: Run all loops in parallel
+- `update_loop_status(loop_id: str, status: str)`: Update loop status
+- `sync_loop_evidence_to_state()`: Synchronize evidence from loops to global state
+
+**Features**:
+- Uses `asyncio.gather()` for parallel execution
+- Handles errors per loop (doesn't fail all if one fails)
+- Tracks loop status: `pending`, `running`, `completed`, `failed`, `cancelled`
+- Evidence deduplication across parallel loops
+
+**Usage**:
+```python
+from src.middleware.workflow_manager import WorkflowManager
+
+manager = WorkflowManager()
+manager.add_loop(loop1)
+manager.add_loop(loop2)
+completed_loops = await manager.run_loops_parallel()
+```
+
+## Budget Tracker
+
+**File**: `src/middleware/budget_tracker.py`
+
+**Purpose**: Tracks and enforces resource limits
+
+**Budget Components**:
+- **Tokens**: LLM token usage
+- **Time**: Elapsed time in seconds
+- **Iterations**: Number of iterations
+
+**Methods**:
+- `create_budget(token_limit, time_limit_seconds, iterations_limit) -> BudgetStatus`
+- `add_tokens(tokens: int)`: Add token usage
+- `start_timer()`: Start time tracking
+- `update_timer()`: Update elapsed time
+- `increment_iteration()`: Increment iteration count
+- `check_budget() -> BudgetStatus`: Check current budget status
+- `can_continue() -> bool`: Check if research can continue
+
+**Token Estimation**:
+- `estimate_tokens(text: str) -> int`: ~4 chars per token
+- `estimate_llm_call_tokens(prompt: str, response: str) -> int`: Estimate LLM call tokens
+
+**Usage**:
+```python
+from src.middleware.budget_tracker import BudgetTracker
+
+tracker = BudgetTracker()
+budget = tracker.create_budget(
+    token_limit=100000,
+    time_limit_seconds=600,
+    iterations_limit=10
+)
+tracker.start_timer()
+# ... research operations ...
+if not tracker.can_continue():
+    # Budget exceeded, stop research
+    pass
+```
+
+## Models
+
+All middleware models are defined in `src/utils/models.py`:
+
+- `IterationData`: Data for a single iteration
+- `Conversation`: Conversation history with iterations
+- `ResearchLoop`: Research loop state and configuration
+- `BudgetStatus`: Current budget status
+
+## Thread Safety
+
+All middleware components use `ContextVar` for thread-safe isolation:
+
+- Each request/thread has its own workflow state
+- No global mutable state
+- Safe for concurrent requests
+
+## See Also
+
+- [Orchestrators](orchestrators.md) - How middleware is used in orchestration
+- [API Reference - Orchestrators](../api/orchestrators.md) - API documentation
+- [Contributing - Code Style](../contributing/code-style.md) - Development guidelines
+
+
+
+
+
+
+
+
+
+

docs/architecture/orchestrators.md

@@ -0,0 +1,198 @@
+# Orchestrators Architecture
+
+DeepCritical supports multiple orchestration patterns for research workflows.
+
+## Research Flows
+
+### IterativeResearchFlow
+
+**File**: `src/orchestrator/research_flow.py`
+
+**Pattern**: Generate observations → Evaluate gaps → Select tools → Execute → Judge → Continue/Complete
+
+**Agents Used**:
+- `KnowledgeGapAgent`: Evaluates research completeness
+- `ToolSelectorAgent`: Selects tools for addressing gaps
+- `ThinkingAgent`: Generates observations
+- `WriterAgent`: Creates final report
+- `JudgeHandler`: Assesses evidence sufficiency
+
+**Features**:
+- Tracks iterations, time, budget
+- Supports graph execution (`use_graph=True`) and agent chains (`use_graph=False`)
+- Iterates until research complete or constraints met
+
+**Usage**:
+```python
+from src.orchestrator.research_flow import IterativeResearchFlow
+
+flow = IterativeResearchFlow(
+    search_handler=search_handler,
+    judge_handler=judge_handler,
+    use_graph=False
+)
+
+async for event in flow.run(query):
+    # Handle events
+    pass
+```
+
+### DeepResearchFlow
+
+**File**: `src/orchestrator/research_flow.py`
+
+**Pattern**: Planner → Parallel iterative loops per section → Synthesizer
+
+**Agents Used**:
+- `PlannerAgent`: Breaks query into report sections
+- `IterativeResearchFlow`: Per-section research (parallel)
+- `LongWriterAgent` or `ProofreaderAgent`: Final synthesis
+
+**Features**:
+- Uses `WorkflowManager` for parallel execution
+- Budget tracking per section and globally
+- State synchronization across parallel loops
+- Supports graph execution and agent chains
+
+**Usage**:
+```python
+from src.orchestrator.research_flow import DeepResearchFlow
+
+flow = DeepResearchFlow(
+    search_handler=search_handler,
+    judge_handler=judge_handler,
+    use_graph=True
+)
+
+async for event in flow.run(query):
+    # Handle events
+    pass
+```
+
+## Graph Orchestrator
+
+**File**: `src/orchestrator/graph_orchestrator.py`
+
+**Purpose**: Graph-based execution using Pydantic AI agents as nodes
+
+**Features**:
+- Uses Pydantic AI Graphs (when available) or agent chains (fallback)
+- Routes based on research mode (iterative/deep/auto)
+- Streams `AgentEvent` objects for UI
+
+**Node Types**:
+- **Agent Nodes**: Execute Pydantic AI agents
+- **State Nodes**: Update or read workflow state
+- **Decision Nodes**: Make routing decisions
+- **Parallel Nodes**: Execute multiple nodes concurrently
+
+**Edge Types**:
+- **Sequential Edges**: Always traversed
+- **Conditional Edges**: Traversed based on condition
+- **Parallel Edges**: Used for parallel execution branches
+
+## Orchestrator Factory
+
+**File**: `src/orchestrator_factory.py`
+
+**Purpose**: Factory for creating orchestrators
+
+**Modes**:
+- **Simple**: Legacy orchestrator (backward compatible)
+- **Advanced**: Magentic orchestrator (requires OpenAI API key)
+- **Auto-detect**: Chooses based on API key availability
+
+**Usage**:
+```python
+from src.orchestrator_factory import create_orchestrator
+
+orchestrator = create_orchestrator(
+    search_handler=search_handler,
+    judge_handler=judge_handler,
+    config={},
+    mode="advanced"  # or "simple" or None for auto-detect
+)
+```
+
+## Magentic Orchestrator
+
+**File**: `src/orchestrator_magentic.py`
+
+**Purpose**: Multi-agent coordination using Microsoft Agent Framework
+
+**Features**:
+- Uses `agent-framework-core`
+- ChatAgent pattern with internal LLMs per agent
+- `MagenticBuilder` with participants: searcher, hypothesizer, judge, reporter
+- Manager orchestrates agents via `OpenAIChatClient`
+- Requires OpenAI API key (function calling support)
+- Event-driven: converts Magentic events to `AgentEvent` for UI streaming
+
+**Requirements**:
+- `agent-framework-core` package
+- OpenAI API key
+
+## Hierarchical Orchestrator
+
+**File**: `src/orchestrator_hierarchical.py`
+
+**Purpose**: Hierarchical orchestrator using middleware and sub-teams
+
+**Features**:
+- Uses `SubIterationMiddleware` with `ResearchTeam` and `LLMSubIterationJudge`
+- Adapts Magentic ChatAgent to `SubIterationTeam` protocol
+- Event-driven via `asyncio.Queue` for coordination
+- Supports sub-iteration patterns for complex research tasks
+
+## Legacy Simple Mode
+
+**File**: `src/legacy_orchestrator.py`
+
+**Purpose**: Linear search-judge-synthesize loop
+
+**Features**:
+- Uses `SearchHandlerProtocol` and `JudgeHandlerProtocol`
+- Generator-based design yielding `AgentEvent` objects
+- Backward compatibility for simple use cases
+
+## State Initialization
+
+All orchestrators must initialize workflow state:
+
+```python
+from src.middleware.state_machine import init_workflow_state
+from src.services.embeddings import get_embedding_service
+
+embedding_service = get_embedding_service()
+init_workflow_state(embedding_service)
+```
+
+## Event Streaming
+
+All orchestrators yield `AgentEvent` objects:
+
+**Event Types**:
+- `started`: Research started
+- `search_complete`: Search completed
+- `judge_complete`: Evidence evaluation completed
+- `hypothesizing`: Generating hypotheses
+- `synthesizing`: Synthesizing results
+- `complete`: Research completed
+- `error`: Error occurred
+
+**Event Structure**:
+```python
+class AgentEvent:
+    type: str
+    iteration: int | None
+    data: dict[str, Any]
+```
+
+## See Also
+
+- [Graph Orchestration](graph-orchestration.md) - Graph-based execution details
+- [Graph Orchestration (Detailed)](graph_orchestration.md) - Detailed graph architecture
+- [Workflows](workflows.md) - Workflow diagrams and patterns
+- [Workflow Diagrams](workflow-diagrams.md) - Detailed workflow diagrams
+- [API Reference - Orchestrators](../api/orchestrators.md) - API documentation
+

docs/architecture/services.md

@@ -0,0 +1,138 @@
+# Services Architecture
+
+DeepCritical provides several services for embeddings, RAG, and statistical analysis.
+
+## Embedding Service
+
+**File**: `src/services/embeddings.py`
+
+**Purpose**: Local sentence-transformers for semantic search and deduplication
+
+**Features**:
+- **No API Key Required**: Uses local sentence-transformers models
+- **Async-Safe**: All operations use `run_in_executor()` to avoid blocking
+- **ChromaDB Storage**: Vector storage for embeddings
+- **Deduplication**: 0.85 similarity threshold (85% similarity = duplicate)
+
+**Model**: Configurable via `settings.local_embedding_model` (default: `all-MiniLM-L6-v2`)
+
+**Methods**:
+- `async def embed(text: str) -> list[float]`: Generate embeddings
+- `async def embed_batch(texts: list[str]) -> list[list[float]]`: Batch embedding
+- `async def similarity(text1: str, text2: str) -> float`: Calculate similarity
+- `async def find_duplicates(texts: list[str], threshold: float = 0.85) -> list[tuple[int, int]]`: Find duplicates
+
+**Usage**:
+```python
+from src.services.embeddings import get_embedding_service
+
+service = get_embedding_service()
+embedding = await service.embed("text to embed")
+```
+
+## LlamaIndex RAG Service
+
+**File**: `src/services/rag.py`
+
+**Purpose**: Retrieval-Augmented Generation using LlamaIndex
+
+**Features**:
+- **OpenAI Embeddings**: Requires `OPENAI_API_KEY`
+- **ChromaDB Storage**: Vector database for document storage
+- **Metadata Preservation**: Preserves source, title, URL, date, authors
+- **Lazy Initialization**: Graceful fallback if OpenAI key not available
+
+**Methods**:
+- `async def ingest_evidence(evidence: list[Evidence]) -> None`: Ingest evidence into RAG
+- `async def retrieve(query: str, top_k: int = 5) -> list[Document]`: Retrieve relevant documents
+- `async def query(query: str, top_k: int = 5) -> str`: Query with RAG
+
+**Usage**:
+```python
+from src.services.rag import get_rag_service
+
+service = get_rag_service()
+if service:
+    documents = await service.retrieve("query", top_k=5)
+```
+
+## Statistical Analyzer
+
+**File**: `src/services/statistical_analyzer.py`
+
+**Purpose**: Secure execution of AI-generated statistical code
+
+**Features**:
+- **Modal Sandbox**: Secure, isolated execution environment
+- **Code Generation**: Generates Python code via LLM
+- **Library Pinning**: Version-pinned libraries in `SANDBOX_LIBRARIES`
+- **Network Isolation**: `block_network=True` by default
+
+**Libraries Available**:
+- pandas, numpy, scipy
+- matplotlib, scikit-learn
+- statsmodels
+
+**Output**: `AnalysisResult` with:
+- `verdict`: SUPPORTED, REFUTED, or INCONCLUSIVE
+- `code`: Generated analysis code
+- `output`: Execution output
+- `error`: Error message if execution failed
+
+**Usage**:
+```python
+from src.services.statistical_analyzer import StatisticalAnalyzer
+
+analyzer = StatisticalAnalyzer()
+result = await analyzer.analyze(
+    hypothesis="Metformin reduces cancer risk",
+    evidence=evidence_list
+)
+```
+
+## Singleton Pattern
+
+All services use the singleton pattern with `@lru_cache(maxsize=1)`:
+
+```python
+@lru_cache(maxsize=1)
+def get_embedding_service() -> EmbeddingService:
+    return EmbeddingService()
+```
+
+This ensures:
+- Single instance per process
+- Lazy initialization
+- No dependencies required at import time
+
+## Service Availability
+
+Services check availability before use:
+
+```python
+from src.utils.config import settings
+
+if settings.modal_available:
+    # Use Modal sandbox
+    pass
+
+if settings.has_openai_key:
+    # Use OpenAI embeddings for RAG
+    pass
+```
+
+## See Also
+
+- [Tools](tools.md) - How services are used by search tools
+- [API Reference - Services](../api/services.md) - API documentation
+- [Configuration](../configuration/index.md) - Service configuration
+
+
+
+
+
+
+
+
+
+

docs/architecture/tools.md

@@ -0,0 +1,171 @@
+# Tools Architecture
+
+DeepCritical implements a protocol-based search tool system for retrieving evidence from multiple sources.
+
+## SearchTool Protocol
+
+All tools implement the `SearchTool` protocol from `src/tools/base.py`:
+
+```python
+class SearchTool(Protocol):
+    @property
+    def name(self) -> str: ...
+    
+    async def search(
+        self, 
+        query: str, 
+        max_results: int = 10
+    ) -> list[Evidence]: ...
+```
+
+## Rate Limiting
+
+All tools use the `@retry` decorator from tenacity:
+
+```python
+@retry(
+    stop=stop_after_attempt(3), 
+    wait=wait_exponential(...)
+)
+async def search(self, query: str, max_results: int = 10) -> list[Evidence]:
+    # Implementation
+```
+
+Tools with API rate limits implement `_rate_limit()` method and use shared rate limiters from `src/tools/rate_limiter.py`.
+
+## Error Handling
+
+Tools raise custom exceptions:
+
+- `SearchError`: General search failures
+- `RateLimitError`: Rate limit exceeded
+
+Tools handle HTTP errors (429, 500, timeout) and return empty lists on non-critical errors (with warning logs).
+
+## Query Preprocessing
+
+Tools use `preprocess_query()` from `src/tools/query_utils.py` to:
+
+- Remove noise from queries
+- Expand synonyms
+- Normalize query format
+
+## Evidence Conversion
+
+All tools convert API responses to `Evidence` objects with:
+
+- `Citation`: Title, URL, date, authors
+- `content`: Evidence text
+- `relevance_score`: 0.0-1.0 relevance score
+- `metadata`: Additional metadata
+
+Missing fields are handled gracefully with defaults.
+
+## Tool Implementations
+
+### PubMed Tool
+
+**File**: `src/tools/pubmed.py`
+
+**API**: NCBI E-utilities (ESearch → EFetch)
+
+**Rate Limiting**: 
+- 0.34s between requests (3 req/sec without API key)
+- 0.1s between requests (10 req/sec with NCBI API key)
+
+**Features**:
+- XML parsing with `xmltodict`
+- Handles single vs. multiple articles
+- Query preprocessing
+- Evidence conversion with metadata extraction
+
+### ClinicalTrials Tool
+
+**File**: `src/tools/clinicaltrials.py`
+
+**API**: ClinicalTrials.gov API v2
+
+**Important**: Uses `requests` library (NOT httpx) because WAF blocks httpx TLS fingerprint.
+
+**Execution**: Runs in thread pool: `await asyncio.to_thread(requests.get, ...)`
+
+**Filtering**:
+- Only interventional studies
+- Status: `COMPLETED`, `ACTIVE_NOT_RECRUITING`, `RECRUITING`, `ENROLLING_BY_INVITATION`
+
+**Features**:
+- Parses nested JSON structure
+- Extracts trial metadata
+- Evidence conversion
+
+### Europe PMC Tool
+
+**File**: `src/tools/europepmc.py`
+
+**API**: Europe PMC REST API
+
+**Features**:
+- Handles preprint markers: `[PREPRINT - Not peer-reviewed]`
+- Builds URLs from DOI or PMID
+- Checks `pubTypeList` for preprint detection
+- Includes both preprints and peer-reviewed articles
+
+### RAG Tool
+
+**File**: `src/tools/rag_tool.py`
+
+**Purpose**: Semantic search within collected evidence
+
+**Implementation**: Wraps `LlamaIndexRAGService`
+
+**Features**:
+- Returns Evidence from RAG results
+- Handles evidence ingestion
+- Semantic similarity search
+- Metadata preservation
+
+### Search Handler
+
+**File**: `src/tools/search_handler.py`
+
+**Purpose**: Orchestrates parallel searches across multiple tools
+
+**Features**:
+- Uses `asyncio.gather()` with `return_exceptions=True`
+- Aggregates results into `SearchResult`
+- Handles tool failures gracefully
+- Deduplicates results by URL
+
+## Tool Registration
+
+Tools are registered in the search handler:
+
+```python
+from src.tools.pubmed import PubMedTool
+from src.tools.clinicaltrials import ClinicalTrialsTool
+from src.tools.europepmc import EuropePMCTool
+
+search_handler = SearchHandler(
+    tools=[
+        PubMedTool(),
+        ClinicalTrialsTool(),
+        EuropePMCTool(),
+    ]
+)
+```
+
+## See Also
+
+- [Services](services.md) - RAG and embedding services
+- [API Reference - Tools](../api/tools.md) - API documentation
+- [Contributing - Implementation Patterns](../contributing/implementation-patterns.md) - Development guidelines
+
+
+
+
+
+
+
+
+
+

docs/architecture/workflow-diagrams.md

@@ -0,0 +1,670 @@
+# DeepCritical Workflow - Simplified Magentic Architecture
+
+> **Architecture Pattern**: Microsoft Magentic Orchestration
+> **Design Philosophy**: Simple, dynamic, manager-driven coordination
+> **Key Innovation**: Intelligent manager replaces rigid sequential phases
+
+---
+
+## 1. High-Level Magentic Workflow
+
+```mermaid
+flowchart TD
+    Start([User Query]) --> Manager[Magentic Manager<br/>Plan • Select • Assess • Adapt]
+
+    Manager -->|Plans| Task1[Task Decomposition]
+    Task1 --> Manager
+
+    Manager -->|Selects & Executes| HypAgent[Hypothesis Agent]
+    Manager -->|Selects & Executes| SearchAgent[Search Agent]
+    Manager -->|Selects & Executes| AnalysisAgent[Analysis Agent]
+    Manager -->|Selects & Executes| ReportAgent[Report Agent]
+
+    HypAgent -->|Results| Manager
+    SearchAgent -->|Results| Manager
+    AnalysisAgent -->|Results| Manager
+    ReportAgent -->|Results| Manager
+
+    Manager -->|Assesses Quality| Decision{Good Enough?}
+    Decision -->|No - Refine| Manager
+    Decision -->|No - Different Agent| Manager
+    Decision -->|No - Stalled| Replan[Reset Plan]
+    Replan --> Manager
+
+    Decision -->|Yes| Synthesis[Synthesize Final Result]
+    Synthesis --> Output([Research Report])
+
+    style Start fill:#e1f5e1
+    style Manager fill:#ffe6e6
+    style HypAgent fill:#fff4e6
+    style SearchAgent fill:#fff4e6
+    style AnalysisAgent fill:#fff4e6
+    style ReportAgent fill:#fff4e6
+    style Decision fill:#ffd6d6
+    style Synthesis fill:#d4edda
+    style Output fill:#e1f5e1
+```
+
+## 2. Magentic Manager: The 6-Phase Cycle
+
+```mermaid
+flowchart LR
+    P1[1. Planning<br/>Analyze task<br/>Create strategy] --> P2[2. Agent Selection<br/>Pick best agent<br/>for subtask]
+    P2 --> P3[3. Execution<br/>Run selected<br/>agent with tools]
+    P3 --> P4[4. Assessment<br/>Evaluate quality<br/>Check progress]
+    P4 --> Decision{Quality OK?<br/>Progress made?}
+    Decision -->|Yes| P6[6. Synthesis<br/>Combine results<br/>Generate report]
+    Decision -->|No| P5[5. Iteration<br/>Adjust plan<br/>Try again]
+    P5 --> P2
+    P6 --> Done([Complete])
+
+    style P1 fill:#fff4e6
+    style P2 fill:#ffe6e6
+    style P3 fill:#e6f3ff
+    style P4 fill:#ffd6d6
+    style P5 fill:#fff3cd
+    style P6 fill:#d4edda
+    style Done fill:#e1f5e1
+```
+
+## 3. Simplified Agent Architecture
+
+```mermaid
+graph TB
+    subgraph "Orchestration Layer"
+        Manager[Magentic Manager<br/>• Plans workflow<br/>• Selects agents<br/>• Assesses quality<br/>• Adapts strategy]
+        SharedContext[(Shared Context<br/>• Hypotheses<br/>• Search Results<br/>• Analysis<br/>• Progress)]
+        Manager <--> SharedContext
+    end
+
+    subgraph "Specialist Agents"
+        HypAgent[Hypothesis Agent<br/>• Domain understanding<br/>• Hypothesis generation<br/>• Testability refinement]
+        SearchAgent[Search Agent<br/>• Multi-source search<br/>• RAG retrieval<br/>• Result ranking]
+        AnalysisAgent[Analysis Agent<br/>• Evidence extraction<br/>• Statistical analysis<br/>• Code execution]
+        ReportAgent[Report Agent<br/>• Report assembly<br/>• Visualization<br/>• Citation formatting]
+    end
+
+    subgraph "MCP Tools"
+        WebSearch[Web Search<br/>PubMed • arXiv • bioRxiv]
+        CodeExec[Code Execution<br/>Sandboxed Python]
+        RAG[RAG Retrieval<br/>Vector DB • Embeddings]
+        Viz[Visualization<br/>Charts • Graphs]
+    end
+
+    Manager -->|Selects & Directs| HypAgent
+    Manager -->|Selects & Directs| SearchAgent
+    Manager -->|Selects & Directs| AnalysisAgent
+    Manager -->|Selects & Directs| ReportAgent
+
+    HypAgent --> SharedContext
+    SearchAgent --> SharedContext
+    AnalysisAgent --> SharedContext
+    ReportAgent --> SharedContext
+
+    SearchAgent --> WebSearch
+    SearchAgent --> RAG
+    AnalysisAgent --> CodeExec
+    ReportAgent --> CodeExec
+    ReportAgent --> Viz
+
+    style Manager fill:#ffe6e6
+    style SharedContext fill:#ffe6f0
+    style HypAgent fill:#fff4e6
+    style SearchAgent fill:#fff4e6
+    style AnalysisAgent fill:#fff4e6
+    style ReportAgent fill:#fff4e6
+    style WebSearch fill:#e6f3ff
+    style CodeExec fill:#e6f3ff
+    style RAG fill:#e6f3ff
+    style Viz fill:#e6f3ff
+```
+
+## 4. Dynamic Workflow Example
+
+```mermaid
+sequenceDiagram
+    participant User
+    participant Manager
+    participant HypAgent
+    participant SearchAgent
+    participant AnalysisAgent
+    participant ReportAgent
+
+    User->>Manager: "Research protein folding in Alzheimer's"
+
+    Note over Manager: PLAN: Generate hypotheses → Search → Analyze → Report
+
+    Manager->>HypAgent: Generate 3 hypotheses
+    HypAgent-->>Manager: Returns 3 hypotheses
+    Note over Manager: ASSESS: Good quality, proceed
+
+    Manager->>SearchAgent: Search literature for hypothesis 1
+    SearchAgent-->>Manager: Returns 15 papers
+    Note over Manager: ASSESS: Good results, continue
+
+    Manager->>SearchAgent: Search for hypothesis 2
+    SearchAgent-->>Manager: Only 2 papers found
+    Note over Manager: ASSESS: Insufficient, refine search
+
+    Manager->>SearchAgent: Refined query for hypothesis 2
+    SearchAgent-->>Manager: Returns 12 papers
+    Note over Manager: ASSESS: Better, proceed
+
+    Manager->>AnalysisAgent: Analyze evidence for all hypotheses
+    AnalysisAgent-->>Manager: Returns analysis with code
+    Note over Manager: ASSESS: Complete, generate report
+
+    Manager->>ReportAgent: Create comprehensive report
+    ReportAgent-->>Manager: Returns formatted report
+    Note over Manager: SYNTHESIZE: Combine all results
+
+    Manager->>User: Final Research Report
+```
+
+## 5. Manager Decision Logic
+
+```mermaid
+flowchart TD
+    Start([Manager Receives Task]) --> Plan[Create Initial Plan]
+
+    Plan --> Select[Select Agent for Next Subtask]
+    Select --> Execute[Execute Agent]
+    Execute --> Collect[Collect Results]
+
+    Collect --> Assess[Assess Quality & Progress]
+
+    Assess --> Q1{Quality Sufficient?}
+    Q1 -->|No| Q2{Same Agent Can Fix?}
+    Q2 -->|Yes| Feedback[Provide Specific Feedback]
+    Feedback --> Execute
+    Q2 -->|No| Different[Try Different Agent]
+    Different --> Select
+
+    Q1 -->|Yes| Q3{Task Complete?}
+    Q3 -->|No| Q4{Making Progress?}
+    Q4 -->|Yes| Select
+    Q4 -->|No - Stalled| Replan[Reset Plan & Approach]
+    Replan --> Plan
+
+    Q3 -->|Yes| Synth[Synthesize Final Result]
+    Synth --> Done([Return Report])
+
+    style Start fill:#e1f5e1
+    style Plan fill:#fff4e6
+    style Select fill:#ffe6e6
+    style Execute fill:#e6f3ff
+    style Assess fill:#ffd6d6
+    style Q1 fill:#ffe6e6
+    style Q2 fill:#ffe6e6
+    style Q3 fill:#ffe6e6
+    style Q4 fill:#ffe6e6
+    style Synth fill:#d4edda
+    style Done fill:#e1f5e1
+```
+
+## 6. Hypothesis Agent Workflow
+
+```mermaid
+flowchart LR
+    Input[Research Query] --> Domain[Identify Domain<br/>& Key Concepts]
+    Domain --> Context[Retrieve Background<br/>Knowledge]
+    Context --> Generate[Generate 3-5<br/>Initial Hypotheses]
+    Generate --> Refine[Refine for<br/>Testability]
+    Refine --> Rank[Rank by<br/>Quality Score]
+    Rank --> Output[Return Top<br/>Hypotheses]
+
+    Output --> Struct[Hypothesis Structure:<br/>• Statement<br/>• Rationale<br/>• Testability Score<br/>• Data Requirements<br/>• Expected Outcomes]
+
+    style Input fill:#e1f5e1
+    style Output fill:#fff4e6
+    style Struct fill:#e6f3ff
+```
+
+## 7. Search Agent Workflow
+
+```mermaid
+flowchart TD
+    Input[Hypotheses] --> Strategy[Formulate Search<br/>Strategy per Hypothesis]
+
+    Strategy --> Multi[Multi-Source Search]
+
+    Multi --> PubMed[PubMed Search<br/>via MCP]
+    Multi --> ArXiv[arXiv Search<br/>via MCP]
+    Multi --> BioRxiv[bioRxiv Search<br/>via MCP]
+
+    PubMed --> Aggregate[Aggregate Results]
+    ArXiv --> Aggregate
+    BioRxiv --> Aggregate
+
+    Aggregate --> Filter[Filter & Rank<br/>by Relevance]
+    Filter --> Dedup[Deduplicate<br/>Cross-Reference]
+    Dedup --> Embed[Embed Documents<br/>via MCP]
+    Embed --> Vector[(Vector DB)]
+    Vector --> RAGRetrieval[RAG Retrieval<br/>Top-K per Hypothesis]
+    RAGRetrieval --> Output[Return Contextualized<br/>Search Results]
+
+    style Input fill:#fff4e6
+    style Multi fill:#ffe6e6
+    style Vector fill:#ffe6f0
+    style Output fill:#e6f3ff
+```
+
+## 8. Analysis Agent Workflow
+
+```mermaid
+flowchart TD
+    Input1[Hypotheses] --> Extract
+    Input2[Search Results] --> Extract[Extract Evidence<br/>per Hypothesis]
+
+    Extract --> Methods[Determine Analysis<br/>Methods Needed]
+
+    Methods --> Branch{Requires<br/>Computation?}
+    Branch -->|Yes| GenCode[Generate Python<br/>Analysis Code]
+    Branch -->|No| Qual[Qualitative<br/>Synthesis]
+
+    GenCode --> Execute[Execute Code<br/>via MCP Sandbox]
+    Execute --> Interpret1[Interpret<br/>Results]
+    Qual --> Interpret2[Interpret<br/>Findings]
+
+    Interpret1 --> Synthesize[Synthesize Evidence<br/>Across Sources]
+    Interpret2 --> Synthesize
+
+    Synthesize --> Verdict[Determine Verdict<br/>per Hypothesis]
+    Verdict --> Support[• Supported<br/>• Refuted<br/>• Inconclusive]
+    Support --> Gaps[Identify Knowledge<br/>Gaps & Limitations]
+    Gaps --> Output[Return Analysis<br/>Report]
+
+    style Input1 fill:#fff4e6
+    style Input2 fill:#e6f3ff
+    style Execute fill:#ffe6e6
+    style Output fill:#e6ffe6
+```
+
+## 9. Report Agent Workflow
+
+```mermaid
+flowchart TD
+    Input1[Query] --> Assemble
+    Input2[Hypotheses] --> Assemble
+    Input3[Search Results] --> Assemble
+    Input4[Analysis] --> Assemble[Assemble Report<br/>Sections]
+
+    Assemble --> Exec[Executive Summary]
+    Assemble --> Intro[Introduction]
+    Assemble --> Methods[Methods]
+    Assemble --> Results[Results per<br/>Hypothesis]
+    Assemble --> Discussion[Discussion]
+    Assemble --> Future[Future Directions]
+    Assemble --> Refs[References]
+
+    Results --> VizCheck{Needs<br/>Visualization?}
+    VizCheck -->|Yes| GenViz[Generate Viz Code]
+    GenViz --> ExecViz[Execute via MCP<br/>Create Charts]
+    ExecViz --> Combine
+    VizCheck -->|No| Combine[Combine All<br/>Sections]
+
+    Exec --> Combine
+    Intro --> Combine
+    Methods --> Combine
+    Discussion --> Combine
+    Future --> Combine
+    Refs --> Combine
+
+    Combine --> Format[Format Output]
+    Format --> MD[Markdown]
+    Format --> PDF[PDF]
+    Format --> JSON[JSON]
+
+    MD --> Output[Return Final<br/>Report]
+    PDF --> Output
+    JSON --> Output
+
+    style Input1 fill:#e1f5e1
+    style Input2 fill:#fff4e6
+    style Input3 fill:#e6f3ff
+    style Input4 fill:#e6ffe6
+    style Output fill:#d4edda
+```
+
+## 10. Data Flow & Event Streaming
+
+```mermaid
+flowchart TD
+    User[👤 User] -->|Research Query| UI[Gradio UI]
+    UI -->|Submit| Manager[Magentic Manager]
+
+    Manager -->|Event: Planning| UI
+    Manager -->|Select Agent| HypAgent[Hypothesis Agent]
+    HypAgent -->|Event: Delta/Message| UI
+    HypAgent -->|Hypotheses| Context[(Shared Context)]
+
+    Context -->|Retrieved by| Manager
+    Manager -->|Select Agent| SearchAgent[Search Agent]
+    SearchAgent -->|MCP Request| WebSearch[Web Search Tool]
+    WebSearch -->|Results| SearchAgent
+    SearchAgent -->|Event: Delta/Message| UI
+    SearchAgent -->|Documents| Context
+    SearchAgent -->|Embeddings| VectorDB[(Vector DB)]
+
+    Context -->|Retrieved by| Manager
+    Manager -->|Select Agent| AnalysisAgent[Analysis Agent]
+    AnalysisAgent -->|MCP Request| CodeExec[Code Execution Tool]
+    CodeExec -->|Results| AnalysisAgent
+    AnalysisAgent -->|Event: Delta/Message| UI
+    AnalysisAgent -->|Analysis| Context
+
+    Context -->|Retrieved by| Manager
+    Manager -->|Select Agent| ReportAgent[Report Agent]
+    ReportAgent -->|MCP Request| CodeExec
+    ReportAgent -->|Event: Delta/Message| UI
+    ReportAgent -->|Report| Context
+
+    Manager -->|Event: Final Result| UI
+    UI -->|Display| User
+
+    style User fill:#e1f5e1
+    style UI fill:#e6f3ff
+    style Manager fill:#ffe6e6
+    style Context fill:#ffe6f0
+    style VectorDB fill:#ffe6f0
+    style WebSearch fill:#f0f0f0
+    style CodeExec fill:#f0f0f0
+```
+
+## 11. MCP Tool Architecture
+
+```mermaid
+graph TB
+    subgraph "Agent Layer"
+        Manager[Magentic Manager]
+        HypAgent[Hypothesis Agent]
+        SearchAgent[Search Agent]
+        AnalysisAgent[Analysis Agent]
+        ReportAgent[Report Agent]
+    end
+
+    subgraph "MCP Protocol Layer"
+        Registry[MCP Tool Registry<br/>• Discovers tools<br/>• Routes requests<br/>• Manages connections]
+    end
+
+    subgraph "MCP Servers"
+        Server1[Web Search Server<br/>localhost:8001<br/>• PubMed<br/>• arXiv<br/>• bioRxiv]
+        Server2[Code Execution Server<br/>localhost:8002<br/>• Sandboxed Python<br/>• Package management]
+        Server3[RAG Server<br/>localhost:8003<br/>• Vector embeddings<br/>• Similarity search]
+        Server4[Visualization Server<br/>localhost:8004<br/>• Chart generation<br/>• Plot rendering]
+    end
+
+    subgraph "External Services"
+        PubMed[PubMed API]
+        ArXiv[arXiv API]
+        BioRxiv[bioRxiv API]
+        Modal[Modal Sandbox]
+        ChromaDB[(ChromaDB)]
+    end
+
+    SearchAgent -->|Request| Registry
+    AnalysisAgent -->|Request| Registry
+    ReportAgent -->|Request| Registry
+
+    Registry --> Server1
+    Registry --> Server2
+    Registry --> Server3
+    Registry --> Server4
+
+    Server1 --> PubMed
+    Server1 --> ArXiv
+    Server1 --> BioRxiv
+    Server2 --> Modal
+    Server3 --> ChromaDB
+
+    style Manager fill:#ffe6e6
+    style Registry fill:#fff4e6
+    style Server1 fill:#e6f3ff
+    style Server2 fill:#e6f3ff
+    style Server3 fill:#e6f3ff
+    style Server4 fill:#e6f3ff
+```
+
+## 12. Progress Tracking & Stall Detection
+
+```mermaid
+stateDiagram-v2
+    [*] --> Initialization: User Query
+
+    Initialization --> Planning: Manager starts
+
+    Planning --> AgentExecution: Select agent
+
+    AgentExecution --> Assessment: Collect results
+
+    Assessment --> QualityCheck: Evaluate output
+
+    QualityCheck --> AgentExecution: Poor quality<br/>(retry < max_rounds)
+    QualityCheck --> Planning: Poor quality<br/>(try different agent)
+    QualityCheck --> NextAgent: Good quality<br/>(task incomplete)
+    QualityCheck --> Synthesis: Good quality<br/>(task complete)
+
+    NextAgent --> AgentExecution: Select next agent
+
+    state StallDetection <<choice>>
+    Assessment --> StallDetection: Check progress
+    StallDetection --> Planning: No progress<br/>(stall count < max)
+    StallDetection --> ErrorRecovery: No progress<br/>(max stalls reached)
+
+    ErrorRecovery --> PartialReport: Generate partial results
+    PartialReport --> [*]
+
+    Synthesis --> FinalReport: Combine all outputs
+    FinalReport --> [*]
+
+    note right of QualityCheck
+        Manager assesses:
+        • Output completeness
+        • Quality metrics
+        • Progress made
+    end note
+
+    note right of StallDetection
+        Stall = no new progress
+        after agent execution
+        Triggers plan reset
+    end note
+```
+
+## 13. Gradio UI Integration
+
+```mermaid
+graph TD
+    App[Gradio App<br/>DeepCritical Research Agent]
+
+    App --> Input[Input Section]
+    App --> Status[Status Section]
+    App --> Output[Output Section]
+
+    Input --> Query[Research Question<br/>Text Area]
+    Input --> Controls[Controls]
+    Controls --> MaxHyp[Max Hypotheses: 1-10]
+    Controls --> MaxRounds[Max Rounds: 5-20]
+    Controls --> Submit[Start Research Button]
+
+    Status --> Log[Real-time Event Log<br/>• Manager planning<br/>• Agent selection<br/>• Execution updates<br/>• Quality assessment]
+    Status --> Progress[Progress Tracker<br/>• Current agent<br/>• Round count<br/>• Stall count]
+
+    Output --> Tabs[Tabbed Results]
+    Tabs --> Tab1[Hypotheses Tab<br/>Generated hypotheses with scores]
+    Tabs --> Tab2[Search Results Tab<br/>Papers & sources found]
+    Tabs --> Tab3[Analysis Tab<br/>Evidence & verdicts]
+    Tabs --> Tab4[Report Tab<br/>Final research report]
+    Tab4 --> Download[Download Report<br/>MD / PDF / JSON]
+
+    Submit -.->|Triggers| Workflow[Magentic Workflow]
+    Workflow -.->|MagenticOrchestratorMessageEvent| Log
+    Workflow -.->|MagenticAgentDeltaEvent| Log
+    Workflow -.->|MagenticAgentMessageEvent| Log
+    Workflow -.->|MagenticFinalResultEvent| Tab4
+
+    style App fill:#e1f5e1
+    style Input fill:#fff4e6
+    style Status fill:#e6f3ff
+    style Output fill:#e6ffe6
+    style Workflow fill:#ffe6e6
+```
+
+## 14. Complete System Context
+
+```mermaid
+graph LR
+    User[👤 Researcher<br/>Asks research questions] -->|Submits query| DC[DeepCritical<br/>Magentic Workflow]
+
+    DC -->|Literature search| PubMed[PubMed API<br/>Medical papers]
+    DC -->|Preprint search| ArXiv[arXiv API<br/>Scientific preprints]
+    DC -->|Biology search| BioRxiv[bioRxiv API<br/>Biology preprints]
+    DC -->|Agent reasoning| Claude[Claude API<br/>Sonnet 4 / Opus]
+    DC -->|Code execution| Modal[Modal Sandbox<br/>Safe Python env]
+    DC -->|Vector storage| Chroma[ChromaDB<br/>Embeddings & RAG]
+
+    DC -->|Deployed on| HF[HuggingFace Spaces<br/>Gradio 6.0]
+
+    PubMed -->|Results| DC
+    ArXiv -->|Results| DC
+    BioRxiv -->|Results| DC
+    Claude -->|Responses| DC
+    Modal -->|Output| DC
+    Chroma -->|Context| DC
+
+    DC -->|Research report| User
+
+    style User fill:#e1f5e1
+    style DC fill:#ffe6e6
+    style PubMed fill:#e6f3ff
+    style ArXiv fill:#e6f3ff
+    style BioRxiv fill:#e6f3ff
+    style Claude fill:#ffd6d6
+    style Modal fill:#f0f0f0
+    style Chroma fill:#ffe6f0
+    style HF fill:#d4edda
+```
+
+## 15. Workflow Timeline (Simplified)
+
+```mermaid
+gantt
+    title DeepCritical Magentic Workflow - Typical Execution
+    dateFormat mm:ss
+    axisFormat %M:%S
+
+    section Manager Planning
+    Initial planning         :p1, 00:00, 10s
+
+    section Hypothesis Agent
+    Generate hypotheses      :h1, after p1, 30s
+    Manager assessment       :h2, after h1, 5s
+
+    section Search Agent
+    Search hypothesis 1      :s1, after h2, 20s
+    Search hypothesis 2      :s2, after s1, 20s
+    Search hypothesis 3      :s3, after s2, 20s
+    RAG processing          :s4, after s3, 15s
+    Manager assessment      :s5, after s4, 5s
+
+    section Analysis Agent
+    Evidence extraction     :a1, after s5, 15s
+    Code generation        :a2, after a1, 20s
+    Code execution         :a3, after a2, 25s
+    Synthesis              :a4, after a3, 20s
+    Manager assessment     :a5, after a4, 5s
+
+    section Report Agent
+    Report assembly        :r1, after a5, 30s
+    Visualization          :r2, after r1, 15s
+    Formatting             :r3, after r2, 10s
+
+    section Manager Synthesis
+    Final synthesis        :f1, after r3, 10s
+```
+
+---
+
+## Key Differences from Original Design
+
+| Aspect | Original (Judge-in-Loop) | New (Magentic) |
+|--------|-------------------------|----------------|
+| **Control Flow** | Fixed sequential phases | Dynamic agent selection |
+| **Quality Control** | Separate Judge Agent | Manager assessment built-in |
+| **Retry Logic** | Phase-level with feedback | Agent-level with adaptation |
+| **Flexibility** | Rigid 4-phase pipeline | Adaptive workflow |
+| **Complexity** | 5 agents (including Judge) | 4 agents (no Judge) |
+| **Progress Tracking** | Manual state management | Built-in round/stall detection |
+| **Agent Coordination** | Sequential handoff | Manager-driven dynamic selection |
+| **Error Recovery** | Retry same phase | Try different agent or replan |
+
+---
+
+## Simplified Design Principles
+
+1. **Manager is Intelligent**: LLM-powered manager handles planning, selection, and quality assessment
+2. **No Separate Judge**: Manager's assessment phase replaces dedicated Judge Agent
+3. **Dynamic Workflow**: Agents can be called multiple times in any order based on need
+4. **Built-in Safety**: max_round_count (15) and max_stall_count (3) prevent infinite loops
+5. **Event-Driven UI**: Real-time streaming updates to Gradio interface
+6. **MCP-Powered Tools**: All external capabilities via Model Context Protocol
+7. **Shared Context**: Centralized state accessible to all agents
+8. **Progress Awareness**: Manager tracks what's been done and what's needed
+
+---
+
+## Legend
+
+- 🔴 **Red/Pink**: Manager, orchestration, decision-making
+- 🟡 **Yellow/Orange**: Specialist agents, processing
+- 🔵 **Blue**: Data, tools, MCP services
+- 🟣 **Purple/Pink**: Storage, databases, state
+- 🟢 **Green**: User interactions, final outputs
+- ⚪ **Gray**: External services, APIs
+
+---
+
+## Implementation Highlights
+
+**Simple 4-Agent Setup:**
+```python
+workflow = (
+    MagenticBuilder()
+    .participants(
+        hypothesis=HypothesisAgent(tools=[background_tool]),
+        search=SearchAgent(tools=[web_search, rag_tool]),
+        analysis=AnalysisAgent(tools=[code_execution]),
+        report=ReportAgent(tools=[code_execution, visualization])
+    )
+    .with_standard_manager(
+        chat_client=AnthropicClient(model="claude-sonnet-4"),
+        max_round_count=15,    # Prevent infinite loops
+        max_stall_count=3      # Detect stuck workflows
+    )
+    .build()
+)
+```
+
+**Manager handles quality assessment in its instructions:**
+- Checks hypothesis quality (testable, novel, clear)
+- Validates search results (relevant, authoritative, recent)
+- Assesses analysis soundness (methodology, evidence, conclusions)
+- Ensures report completeness (all sections, proper citations)
+
+No separate Judge Agent needed - manager does it all!
+
+---
+
+**Document Version**: 2.0 (Magentic Simplified)
+**Last Updated**: 2025-11-24
+**Architecture**: Microsoft Magentic Orchestration Pattern
+**Agents**: 4 (Hypothesis, Search, Analysis, Report) + 1 Manager
+**License**: MIT
+
+## See Also
+
+- [Orchestrators](orchestrators.md) - Overview of all orchestrator patterns
+- [Graph Orchestration](graph-orchestration.md) - Graph-based execution overview
+- [Graph Orchestration (Detailed)](graph_orchestration.md) - Detailed graph architecture
+- [Workflows](workflows.md) - Workflow patterns summary
+- [API Reference - Orchestrators](../api/orchestrators.md) - API documentation

docs/architecture/workflows.md

@@ -0,0 +1,662 @@
+# DeepCritical Workflow - Simplified Magentic Architecture
+
+> **Architecture Pattern**: Microsoft Magentic Orchestration
+> **Design Philosophy**: Simple, dynamic, manager-driven coordination
+> **Key Innovation**: Intelligent manager replaces rigid sequential phases
+
+---
+
+## 1. High-Level Magentic Workflow
+
+```mermaid
+flowchart TD
+    Start([User Query]) --> Manager[Magentic Manager<br/>Plan • Select • Assess • Adapt]
+
+    Manager -->|Plans| Task1[Task Decomposition]
+    Task1 --> Manager
+
+    Manager -->|Selects & Executes| HypAgent[Hypothesis Agent]
+    Manager -->|Selects & Executes| SearchAgent[Search Agent]
+    Manager -->|Selects & Executes| AnalysisAgent[Analysis Agent]
+    Manager -->|Selects & Executes| ReportAgent[Report Agent]
+
+    HypAgent -->|Results| Manager
+    SearchAgent -->|Results| Manager
+    AnalysisAgent -->|Results| Manager
+    ReportAgent -->|Results| Manager
+
+    Manager -->|Assesses Quality| Decision{Good Enough?}
+    Decision -->|No - Refine| Manager
+    Decision -->|No - Different Agent| Manager
+    Decision -->|No - Stalled| Replan[Reset Plan]
+    Replan --> Manager
+
+    Decision -->|Yes| Synthesis[Synthesize Final Result]
+    Synthesis --> Output([Research Report])
+
+    style Start fill:#e1f5e1
+    style Manager fill:#ffe6e6
+    style HypAgent fill:#fff4e6
+    style SearchAgent fill:#fff4e6
+    style AnalysisAgent fill:#fff4e6
+    style ReportAgent fill:#fff4e6
+    style Decision fill:#ffd6d6
+    style Synthesis fill:#d4edda
+    style Output fill:#e1f5e1
+```
+
+## 2. Magentic Manager: The 6-Phase Cycle
+
+```mermaid
+flowchart LR
+    P1[1. Planning<br/>Analyze task<br/>Create strategy] --> P2[2. Agent Selection<br/>Pick best agent<br/>for subtask]
+    P2 --> P3[3. Execution<br/>Run selected<br/>agent with tools]
+    P3 --> P4[4. Assessment<br/>Evaluate quality<br/>Check progress]
+    P4 --> Decision{Quality OK?<br/>Progress made?}
+    Decision -->|Yes| P6[6. Synthesis<br/>Combine results<br/>Generate report]
+    Decision -->|No| P5[5. Iteration<br/>Adjust plan<br/>Try again]
+    P5 --> P2
+    P6 --> Done([Complete])
+
+    style P1 fill:#fff4e6
+    style P2 fill:#ffe6e6
+    style P3 fill:#e6f3ff
+    style P4 fill:#ffd6d6
+    style P5 fill:#fff3cd
+    style P6 fill:#d4edda
+    style Done fill:#e1f5e1
+```
+
+## 3. Simplified Agent Architecture
+
+```mermaid
+graph TB
+    subgraph "Orchestration Layer"
+        Manager[Magentic Manager<br/>• Plans workflow<br/>• Selects agents<br/>• Assesses quality<br/>• Adapts strategy]
+        SharedContext[(Shared Context<br/>• Hypotheses<br/>• Search Results<br/>• Analysis<br/>• Progress)]
+        Manager <--> SharedContext
+    end
+
+    subgraph "Specialist Agents"
+        HypAgent[Hypothesis Agent<br/>• Domain understanding<br/>• Hypothesis generation<br/>• Testability refinement]
+        SearchAgent[Search Agent<br/>• Multi-source search<br/>• RAG retrieval<br/>• Result ranking]
+        AnalysisAgent[Analysis Agent<br/>• Evidence extraction<br/>• Statistical analysis<br/>• Code execution]
+        ReportAgent[Report Agent<br/>• Report assembly<br/>• Visualization<br/>• Citation formatting]
+    end
+
+    subgraph "MCP Tools"
+        WebSearch[Web Search<br/>PubMed • arXiv • bioRxiv]
+        CodeExec[Code Execution<br/>Sandboxed Python]
+        RAG[RAG Retrieval<br/>Vector DB • Embeddings]
+        Viz[Visualization<br/>Charts • Graphs]
+    end
+
+    Manager -->|Selects & Directs| HypAgent
+    Manager -->|Selects & Directs| SearchAgent
+    Manager -->|Selects & Directs| AnalysisAgent
+    Manager -->|Selects & Directs| ReportAgent
+
+    HypAgent --> SharedContext
+    SearchAgent --> SharedContext
+    AnalysisAgent --> SharedContext
+    ReportAgent --> SharedContext
+
+    SearchAgent --> WebSearch
+    SearchAgent --> RAG
+    AnalysisAgent --> CodeExec
+    ReportAgent --> CodeExec
+    ReportAgent --> Viz
+
+    style Manager fill:#ffe6e6
+    style SharedContext fill:#ffe6f0
+    style HypAgent fill:#fff4e6
+    style SearchAgent fill:#fff4e6
+    style AnalysisAgent fill:#fff4e6
+    style ReportAgent fill:#fff4e6
+    style WebSearch fill:#e6f3ff
+    style CodeExec fill:#e6f3ff
+    style RAG fill:#e6f3ff
+    style Viz fill:#e6f3ff
+```
+
+## 4. Dynamic Workflow Example
+
+```mermaid
+sequenceDiagram
+    participant User
+    participant Manager
+    participant HypAgent
+    participant SearchAgent
+    participant AnalysisAgent
+    participant ReportAgent
+
+    User->>Manager: "Research protein folding in Alzheimer's"
+
+    Note over Manager: PLAN: Generate hypotheses → Search → Analyze → Report
+
+    Manager->>HypAgent: Generate 3 hypotheses
+    HypAgent-->>Manager: Returns 3 hypotheses
+    Note over Manager: ASSESS: Good quality, proceed
+
+    Manager->>SearchAgent: Search literature for hypothesis 1
+    SearchAgent-->>Manager: Returns 15 papers
+    Note over Manager: ASSESS: Good results, continue
+
+    Manager->>SearchAgent: Search for hypothesis 2
+    SearchAgent-->>Manager: Only 2 papers found
+    Note over Manager: ASSESS: Insufficient, refine search
+
+    Manager->>SearchAgent: Refined query for hypothesis 2
+    SearchAgent-->>Manager: Returns 12 papers
+    Note over Manager: ASSESS: Better, proceed
+
+    Manager->>AnalysisAgent: Analyze evidence for all hypotheses
+    AnalysisAgent-->>Manager: Returns analysis with code
+    Note over Manager: ASSESS: Complete, generate report
+
+    Manager->>ReportAgent: Create comprehensive report
+    ReportAgent-->>Manager: Returns formatted report
+    Note over Manager: SYNTHESIZE: Combine all results
+
+    Manager->>User: Final Research Report
+```
+
+## 5. Manager Decision Logic
+
+```mermaid
+flowchart TD
+    Start([Manager Receives Task]) --> Plan[Create Initial Plan]
+
+    Plan --> Select[Select Agent for Next Subtask]
+    Select --> Execute[Execute Agent]
+    Execute --> Collect[Collect Results]
+
+    Collect --> Assess[Assess Quality & Progress]
+
+    Assess --> Q1{Quality Sufficient?}
+    Q1 -->|No| Q2{Same Agent Can Fix?}
+    Q2 -->|Yes| Feedback[Provide Specific Feedback]
+    Feedback --> Execute
+    Q2 -->|No| Different[Try Different Agent]
+    Different --> Select
+
+    Q1 -->|Yes| Q3{Task Complete?}
+    Q3 -->|No| Q4{Making Progress?}
+    Q4 -->|Yes| Select
+    Q4 -->|No - Stalled| Replan[Reset Plan & Approach]
+    Replan --> Plan
+
+    Q3 -->|Yes| Synth[Synthesize Final Result]
+    Synth --> Done([Return Report])
+
+    style Start fill:#e1f5e1
+    style Plan fill:#fff4e6
+    style Select fill:#ffe6e6
+    style Execute fill:#e6f3ff
+    style Assess fill:#ffd6d6
+    style Q1 fill:#ffe6e6
+    style Q2 fill:#ffe6e6
+    style Q3 fill:#ffe6e6
+    style Q4 fill:#ffe6e6
+    style Synth fill:#d4edda
+    style Done fill:#e1f5e1
+```
+
+## 6. Hypothesis Agent Workflow
+
+```mermaid
+flowchart LR
+    Input[Research Query] --> Domain[Identify Domain<br/>& Key Concepts]
+    Domain --> Context[Retrieve Background<br/>Knowledge]
+    Context --> Generate[Generate 3-5<br/>Initial Hypotheses]
+    Generate --> Refine[Refine for<br/>Testability]
+    Refine --> Rank[Rank by<br/>Quality Score]
+    Rank --> Output[Return Top<br/>Hypotheses]
+
+    Output --> Struct[Hypothesis Structure:<br/>• Statement<br/>• Rationale<br/>• Testability Score<br/>• Data Requirements<br/>• Expected Outcomes]
+
+    style Input fill:#e1f5e1
+    style Output fill:#fff4e6
+    style Struct fill:#e6f3ff
+```
+
+## 7. Search Agent Workflow
+
+```mermaid
+flowchart TD
+    Input[Hypotheses] --> Strategy[Formulate Search<br/>Strategy per Hypothesis]
+
+    Strategy --> Multi[Multi-Source Search]
+
+    Multi --> PubMed[PubMed Search<br/>via MCP]
+    Multi --> ArXiv[arXiv Search<br/>via MCP]
+    Multi --> BioRxiv[bioRxiv Search<br/>via MCP]
+
+    PubMed --> Aggregate[Aggregate Results]
+    ArXiv --> Aggregate
+    BioRxiv --> Aggregate
+
+    Aggregate --> Filter[Filter & Rank<br/>by Relevance]
+    Filter --> Dedup[Deduplicate<br/>Cross-Reference]
+    Dedup --> Embed[Embed Documents<br/>via MCP]
+    Embed --> Vector[(Vector DB)]
+    Vector --> RAGRetrieval[RAG Retrieval<br/>Top-K per Hypothesis]
+    RAGRetrieval --> Output[Return Contextualized<br/>Search Results]
+
+    style Input fill:#fff4e6
+    style Multi fill:#ffe6e6
+    style Vector fill:#ffe6f0
+    style Output fill:#e6f3ff
+```
+
+## 8. Analysis Agent Workflow
+
+```mermaid
+flowchart TD
+    Input1[Hypotheses] --> Extract
+    Input2[Search Results] --> Extract[Extract Evidence<br/>per Hypothesis]
+
+    Extract --> Methods[Determine Analysis<br/>Methods Needed]
+
+    Methods --> Branch{Requires<br/>Computation?}
+    Branch -->|Yes| GenCode[Generate Python<br/>Analysis Code]
+    Branch -->|No| Qual[Qualitative<br/>Synthesis]
+
+    GenCode --> Execute[Execute Code<br/>via MCP Sandbox]
+    Execute --> Interpret1[Interpret<br/>Results]
+    Qual --> Interpret2[Interpret<br/>Findings]
+
+    Interpret1 --> Synthesize[Synthesize Evidence<br/>Across Sources]
+    Interpret2 --> Synthesize
+
+    Synthesize --> Verdict[Determine Verdict<br/>per Hypothesis]
+    Verdict --> Support[• Supported<br/>• Refuted<br/>• Inconclusive]
+    Support --> Gaps[Identify Knowledge<br/>Gaps & Limitations]
+    Gaps --> Output[Return Analysis<br/>Report]
+
+    style Input1 fill:#fff4e6
+    style Input2 fill:#e6f3ff
+    style Execute fill:#ffe6e6
+    style Output fill:#e6ffe6
+```
+
+## 9. Report Agent Workflow
+
+```mermaid
+flowchart TD
+    Input1[Query] --> Assemble
+    Input2[Hypotheses] --> Assemble
+    Input3[Search Results] --> Assemble
+    Input4[Analysis] --> Assemble[Assemble Report<br/>Sections]
+
+    Assemble --> Exec[Executive Summary]
+    Assemble --> Intro[Introduction]
+    Assemble --> Methods[Methods]
+    Assemble --> Results[Results per<br/>Hypothesis]
+    Assemble --> Discussion[Discussion]
+    Assemble --> Future[Future Directions]
+    Assemble --> Refs[References]
+
+    Results --> VizCheck{Needs<br/>Visualization?}
+    VizCheck -->|Yes| GenViz[Generate Viz Code]
+    GenViz --> ExecViz[Execute via MCP<br/>Create Charts]
+    ExecViz --> Combine
+    VizCheck -->|No| Combine[Combine All<br/>Sections]
+
+    Exec --> Combine
+    Intro --> Combine
+    Methods --> Combine
+    Discussion --> Combine
+    Future --> Combine
+    Refs --> Combine
+
+    Combine --> Format[Format Output]
+    Format --> MD[Markdown]
+    Format --> PDF[PDF]
+    Format --> JSON[JSON]
+
+    MD --> Output[Return Final<br/>Report]
+    PDF --> Output
+    JSON --> Output
+
+    style Input1 fill:#e1f5e1
+    style Input2 fill:#fff4e6
+    style Input3 fill:#e6f3ff
+    style Input4 fill:#e6ffe6
+    style Output fill:#d4edda
+```
+
+## 10. Data Flow & Event Streaming
+
+```mermaid
+flowchart TD
+    User[👤 User] -->|Research Query| UI[Gradio UI]
+    UI -->|Submit| Manager[Magentic Manager]
+
+    Manager -->|Event: Planning| UI
+    Manager -->|Select Agent| HypAgent[Hypothesis Agent]
+    HypAgent -->|Event: Delta/Message| UI
+    HypAgent -->|Hypotheses| Context[(Shared Context)]
+
+    Context -->|Retrieved by| Manager
+    Manager -->|Select Agent| SearchAgent[Search Agent]
+    SearchAgent -->|MCP Request| WebSearch[Web Search Tool]
+    WebSearch -->|Results| SearchAgent
+    SearchAgent -->|Event: Delta/Message| UI
+    SearchAgent -->|Documents| Context
+    SearchAgent -->|Embeddings| VectorDB[(Vector DB)]
+
+    Context -->|Retrieved by| Manager
+    Manager -->|Select Agent| AnalysisAgent[Analysis Agent]
+    AnalysisAgent -->|MCP Request| CodeExec[Code Execution Tool]
+    CodeExec -->|Results| AnalysisAgent
+    AnalysisAgent -->|Event: Delta/Message| UI
+    AnalysisAgent -->|Analysis| Context
+
+    Context -->|Retrieved by| Manager
+    Manager -->|Select Agent| ReportAgent[Report Agent]
+    ReportAgent -->|MCP Request| CodeExec
+    ReportAgent -->|Event: Delta/Message| UI
+    ReportAgent -->|Report| Context
+
+    Manager -->|Event: Final Result| UI
+    UI -->|Display| User
+
+    style User fill:#e1f5e1
+    style UI fill:#e6f3ff
+    style Manager fill:#ffe6e6
+    style Context fill:#ffe6f0
+    style VectorDB fill:#ffe6f0
+    style WebSearch fill:#f0f0f0
+    style CodeExec fill:#f0f0f0
+```
+
+## 11. MCP Tool Architecture
+
+```mermaid
+graph TB
+    subgraph "Agent Layer"
+        Manager[Magentic Manager]
+        HypAgent[Hypothesis Agent]
+        SearchAgent[Search Agent]
+        AnalysisAgent[Analysis Agent]
+        ReportAgent[Report Agent]
+    end
+
+    subgraph "MCP Protocol Layer"
+        Registry[MCP Tool Registry<br/>• Discovers tools<br/>• Routes requests<br/>• Manages connections]
+    end
+
+    subgraph "MCP Servers"
+        Server1[Web Search Server<br/>localhost:8001<br/>• PubMed<br/>• arXiv<br/>• bioRxiv]
+        Server2[Code Execution Server<br/>localhost:8002<br/>• Sandboxed Python<br/>• Package management]
+        Server3[RAG Server<br/>localhost:8003<br/>• Vector embeddings<br/>• Similarity search]
+        Server4[Visualization Server<br/>localhost:8004<br/>• Chart generation<br/>• Plot rendering]
+    end
+
+    subgraph "External Services"
+        PubMed[PubMed API]
+        ArXiv[arXiv API]
+        BioRxiv[bioRxiv API]
+        Modal[Modal Sandbox]
+        ChromaDB[(ChromaDB)]
+    end
+
+    SearchAgent -->|Request| Registry
+    AnalysisAgent -->|Request| Registry
+    ReportAgent -->|Request| Registry
+
+    Registry --> Server1
+    Registry --> Server2
+    Registry --> Server3
+    Registry --> Server4
+
+    Server1 --> PubMed
+    Server1 --> ArXiv
+    Server1 --> BioRxiv
+    Server2 --> Modal
+    Server3 --> ChromaDB
+
+    style Manager fill:#ffe6e6
+    style Registry fill:#fff4e6
+    style Server1 fill:#e6f3ff
+    style Server2 fill:#e6f3ff
+    style Server3 fill:#e6f3ff
+    style Server4 fill:#e6f3ff
+```
+
+## 12. Progress Tracking & Stall Detection
+
+```mermaid
+stateDiagram-v2
+    [*] --> Initialization: User Query
+
+    Initialization --> Planning: Manager starts
+
+    Planning --> AgentExecution: Select agent
+
+    AgentExecution --> Assessment: Collect results
+
+    Assessment --> QualityCheck: Evaluate output
+
+    QualityCheck --> AgentExecution: Poor quality<br/>(retry < max_rounds)
+    QualityCheck --> Planning: Poor quality<br/>(try different agent)
+    QualityCheck --> NextAgent: Good quality<br/>(task incomplete)
+    QualityCheck --> Synthesis: Good quality<br/>(task complete)
+
+    NextAgent --> AgentExecution: Select next agent
+
+    state StallDetection <<choice>>
+    Assessment --> StallDetection: Check progress
+    StallDetection --> Planning: No progress<br/>(stall count < max)
+    StallDetection --> ErrorRecovery: No progress<br/>(max stalls reached)
+
+    ErrorRecovery --> PartialReport: Generate partial results
+    PartialReport --> [*]
+
+    Synthesis --> FinalReport: Combine all outputs
+    FinalReport --> [*]
+
+    note right of QualityCheck
+        Manager assesses:
+        • Output completeness
+        • Quality metrics
+        • Progress made
+    end note
+
+    note right of StallDetection
+        Stall = no new progress
+        after agent execution
+        Triggers plan reset
+    end note
+```
+
+## 13. Gradio UI Integration
+
+```mermaid
+graph TD
+    App[Gradio App<br/>DeepCritical Research Agent]
+
+    App --> Input[Input Section]
+    App --> Status[Status Section]
+    App --> Output[Output Section]
+
+    Input --> Query[Research Question<br/>Text Area]
+    Input --> Controls[Controls]
+    Controls --> MaxHyp[Max Hypotheses: 1-10]
+    Controls --> MaxRounds[Max Rounds: 5-20]
+    Controls --> Submit[Start Research Button]
+
+    Status --> Log[Real-time Event Log<br/>• Manager planning<br/>• Agent selection<br/>• Execution updates<br/>• Quality assessment]
+    Status --> Progress[Progress Tracker<br/>• Current agent<br/>• Round count<br/>• Stall count]
+
+    Output --> Tabs[Tabbed Results]
+    Tabs --> Tab1[Hypotheses Tab<br/>Generated hypotheses with scores]
+    Tabs --> Tab2[Search Results Tab<br/>Papers & sources found]
+    Tabs --> Tab3[Analysis Tab<br/>Evidence & verdicts]
+    Tabs --> Tab4[Report Tab<br/>Final research report]
+    Tab4 --> Download[Download Report<br/>MD / PDF / JSON]
+
+    Submit -.->|Triggers| Workflow[Magentic Workflow]
+    Workflow -.->|MagenticOrchestratorMessageEvent| Log
+    Workflow -.->|MagenticAgentDeltaEvent| Log
+    Workflow -.->|MagenticAgentMessageEvent| Log
+    Workflow -.->|MagenticFinalResultEvent| Tab4
+
+    style App fill:#e1f5e1
+    style Input fill:#fff4e6
+    style Status fill:#e6f3ff
+    style Output fill:#e6ffe6
+    style Workflow fill:#ffe6e6
+```
+
+## 14. Complete System Context
+
+```mermaid
+graph LR
+    User[👤 Researcher<br/>Asks research questions] -->|Submits query| DC[DeepCritical<br/>Magentic Workflow]
+
+    DC -->|Literature search| PubMed[PubMed API<br/>Medical papers]
+    DC -->|Preprint search| ArXiv[arXiv API<br/>Scientific preprints]
+    DC -->|Biology search| BioRxiv[bioRxiv API<br/>Biology preprints]
+    DC -->|Agent reasoning| Claude[Claude API<br/>Sonnet 4 / Opus]
+    DC -->|Code execution| Modal[Modal Sandbox<br/>Safe Python env]
+    DC -->|Vector storage| Chroma[ChromaDB<br/>Embeddings & RAG]
+
+    DC -->|Deployed on| HF[HuggingFace Spaces<br/>Gradio 6.0]
+
+    PubMed -->|Results| DC
+    ArXiv -->|Results| DC
+    BioRxiv -->|Results| DC
+    Claude -->|Responses| DC
+    Modal -->|Output| DC
+    Chroma -->|Context| DC
+
+    DC -->|Research report| User
+
+    style User fill:#e1f5e1
+    style DC fill:#ffe6e6
+    style PubMed fill:#e6f3ff
+    style ArXiv fill:#e6f3ff
+    style BioRxiv fill:#e6f3ff
+    style Claude fill:#ffd6d6
+    style Modal fill:#f0f0f0
+    style Chroma fill:#ffe6f0
+    style HF fill:#d4edda
+```
+
+## 15. Workflow Timeline (Simplified)
+
+```mermaid
+gantt
+    title DeepCritical Magentic Workflow - Typical Execution
+    dateFormat mm:ss
+    axisFormat %M:%S
+
+    section Manager Planning
+    Initial planning         :p1, 00:00, 10s
+
+    section Hypothesis Agent
+    Generate hypotheses      :h1, after p1, 30s
+    Manager assessment       :h2, after h1, 5s
+
+    section Search Agent
+    Search hypothesis 1      :s1, after h2, 20s
+    Search hypothesis 2      :s2, after s1, 20s
+    Search hypothesis 3      :s3, after s2, 20s
+    RAG processing          :s4, after s3, 15s
+    Manager assessment      :s5, after s4, 5s
+
+    section Analysis Agent
+    Evidence extraction     :a1, after s5, 15s
+    Code generation        :a2, after a1, 20s
+    Code execution         :a3, after a2, 25s
+    Synthesis              :a4, after a3, 20s
+    Manager assessment     :a5, after a4, 5s
+
+    section Report Agent
+    Report assembly        :r1, after a5, 30s
+    Visualization          :r2, after r1, 15s
+    Formatting             :r3, after r2, 10s
+
+    section Manager Synthesis
+    Final synthesis        :f1, after r3, 10s
+```
+
+---
+
+## Key Differences from Original Design
+
+| Aspect | Original (Judge-in-Loop) | New (Magentic) |
+|--------|-------------------------|----------------|
+| **Control Flow** | Fixed sequential phases | Dynamic agent selection |
+| **Quality Control** | Separate Judge Agent | Manager assessment built-in |
+| **Retry Logic** | Phase-level with feedback | Agent-level with adaptation |
+| **Flexibility** | Rigid 4-phase pipeline | Adaptive workflow |
+| **Complexity** | 5 agents (including Judge) | 4 agents (no Judge) |
+| **Progress Tracking** | Manual state management | Built-in round/stall detection |
+| **Agent Coordination** | Sequential handoff | Manager-driven dynamic selection |
+| **Error Recovery** | Retry same phase | Try different agent or replan |
+
+---
+
+## Simplified Design Principles
+
+1. **Manager is Intelligent**: LLM-powered manager handles planning, selection, and quality assessment
+2. **No Separate Judge**: Manager's assessment phase replaces dedicated Judge Agent
+3. **Dynamic Workflow**: Agents can be called multiple times in any order based on need
+4. **Built-in Safety**: max_round_count (15) and max_stall_count (3) prevent infinite loops
+5. **Event-Driven UI**: Real-time streaming updates to Gradio interface
+6. **MCP-Powered Tools**: All external capabilities via Model Context Protocol
+7. **Shared Context**: Centralized state accessible to all agents
+8. **Progress Awareness**: Manager tracks what's been done and what's needed
+
+---
+
+## Legend
+
+- 🔴 **Red/Pink**: Manager, orchestration, decision-making
+- 🟡 **Yellow/Orange**: Specialist agents, processing
+- 🔵 **Blue**: Data, tools, MCP services
+- 🟣 **Purple/Pink**: Storage, databases, state
+- 🟢 **Green**: User interactions, final outputs
+- ⚪ **Gray**: External services, APIs
+
+---
+
+## Implementation Highlights
+
+**Simple 4-Agent Setup:**
+```python
+workflow = (
+    MagenticBuilder()
+    .participants(
+        hypothesis=HypothesisAgent(tools=[background_tool]),
+        search=SearchAgent(tools=[web_search, rag_tool]),
+        analysis=AnalysisAgent(tools=[code_execution]),
+        report=ReportAgent(tools=[code_execution, visualization])
+    )
+    .with_standard_manager(
+        chat_client=AnthropicClient(model="claude-sonnet-4"),
+        max_round_count=15,    # Prevent infinite loops
+        max_stall_count=3      # Detect stuck workflows
+    )
+    .build()
+)
+```
+
+**Manager handles quality assessment in its instructions:**
+- Checks hypothesis quality (testable, novel, clear)
+- Validates search results (relevant, authoritative, recent)
+- Assesses analysis soundness (methodology, evidence, conclusions)
+- Ensures report completeness (all sections, proper citations)
+
+No separate Judge Agent needed - manager does it all!
+
+---
+
+**Document Version**: 2.0 (Magentic Simplified)
+**Last Updated**: 2025-11-24
+**Architecture**: Microsoft Magentic Orchestration Pattern
+**Agents**: 4 (Hypothesis, Search, Analysis, Report) + 1 Manager
+**License**: MIT

docs/configuration/CONFIGURATION.md

@@ -0,0 +1,743 @@
+# Configuration Guide
+
+## Overview
+
+DeepCritical uses **Pydantic Settings** for centralized configuration management. All settings are defined in the `Settings` class in `src/utils/config.py` and can be configured via environment variables or a `.env` file.
+
+The configuration system provides:
+
+- **Type Safety**: Strongly-typed fields with Pydantic validation
+- **Environment File Support**: Automatically loads from `.env` file (if present)
+- **Case-Insensitive**: Environment variables are case-insensitive
+- **Singleton Pattern**: Global `settings` instance for easy access throughout the codebase
+- **Validation**: Automatic validation on load with helpful error messages
+
+## Quick Start
+
+1. Create a `.env` file in the project root
+2. Set at least one LLM API key (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `HF_TOKEN`)
+3. Optionally configure other services as needed
+4. The application will automatically load and validate your configuration
+
+## Configuration System Architecture
+
+### Settings Class
+
+The `Settings` class extends `BaseSettings` from `pydantic_settings` and defines all application configuration:
+
+```13:21:src/utils/config.py
+class Settings(BaseSettings):
+    """Strongly-typed application settings."""
+
+    model_config = SettingsConfigDict(
+        env_file=".env",
+        env_file_encoding="utf-8",
+        case_sensitive=False,
+        extra="ignore",
+    )
+```
+
+### Singleton Instance
+
+A global `settings` instance is available for import:
+
+```234:235:src/utils/config.py
+# Singleton for easy import
+settings = get_settings()
+```
+
+### Usage Pattern
+
+Access configuration throughout the codebase:
+
+```python
+from src.utils.config import settings
+
+# Check if API keys are available
+if settings.has_openai_key:
+    # Use OpenAI
+    pass
+
+# Access configuration values
+max_iterations = settings.max_iterations
+web_search_provider = settings.web_search_provider
+```
+
+## Required Configuration
+
+### LLM Provider
+
+You must configure at least one LLM provider. The system supports:
+
+- **OpenAI**: Requires `OPENAI_API_KEY`
+- **Anthropic**: Requires `ANTHROPIC_API_KEY`
+- **HuggingFace**: Optional `HF_TOKEN` or `HUGGINGFACE_API_KEY` (can work without key for public models)
+
+#### OpenAI Configuration
+
+```bash
+LLM_PROVIDER=openai
+OPENAI_API_KEY=your_openai_api_key_here
+OPENAI_MODEL=gpt-5.1
+```
+
+The default model is defined in the `Settings` class:
+
+```29:29:src/utils/config.py
+    openai_model: str = Field(default="gpt-5.1", description="OpenAI model name")
+```
+
+#### Anthropic Configuration
+
+```bash
+LLM_PROVIDER=anthropic
+ANTHROPIC_API_KEY=your_anthropic_api_key_here
+ANTHROPIC_MODEL=claude-sonnet-4-5-20250929
+```
+
+The default model is defined in the `Settings` class:
+
+```30:32:src/utils/config.py
+    anthropic_model: str = Field(
+        default="claude-sonnet-4-5-20250929", description="Anthropic model"
+    )
+```
+
+#### HuggingFace Configuration
+
+HuggingFace can work without an API key for public models, but an API key provides higher rate limits:
+
+```bash
+# Option 1: Using HF_TOKEN (preferred)
+HF_TOKEN=your_huggingface_token_here
+
+# Option 2: Using HUGGINGFACE_API_KEY (alternative)
+HUGGINGFACE_API_KEY=your_huggingface_api_key_here
+
+# Default model
+HUGGINGFACE_MODEL=meta-llama/Llama-3.1-8B-Instruct
+```
+
+The HuggingFace token can be set via either environment variable:
+
+```33:35:src/utils/config.py
+    hf_token: str | None = Field(
+        default=None, alias="HF_TOKEN", description="HuggingFace API token"
+    )
+```
+
+```57:59:src/utils/config.py
+    huggingface_api_key: str | None = Field(
+        default=None, description="HuggingFace API token (HF_TOKEN or HUGGINGFACE_API_KEY)"
+    )
+```
+
+## Optional Configuration
+
+### Embedding Configuration
+
+DeepCritical supports multiple embedding providers for semantic search and RAG:
+
+```bash
+# Embedding Provider: "openai", "local", or "huggingface"
+EMBEDDING_PROVIDER=local
+
+# OpenAI Embedding Model (used by LlamaIndex RAG)
+OPENAI_EMBEDDING_MODEL=text-embedding-3-small
+
+# Local Embedding Model (sentence-transformers, used by EmbeddingService)
+LOCAL_EMBEDDING_MODEL=all-MiniLM-L6-v2
+
+# HuggingFace Embedding Model
+HUGGINGFACE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
+```
+
+The embedding provider configuration:
+
+```47:50:src/utils/config.py
+    embedding_provider: Literal["openai", "local", "huggingface"] = Field(
+        default="local",
+        description="Embedding provider to use",
+    )
+```
+
+**Note**: OpenAI embeddings require `OPENAI_API_KEY`. The local provider (default) uses sentence-transformers and requires no API key.
+
+### Web Search Configuration
+
+DeepCritical supports multiple web search providers:
+
+```bash
+# Web Search Provider: "serper", "searchxng", "brave", "tavily", or "duckduckgo"
+# Default: "duckduckgo" (no API key required)
+WEB_SEARCH_PROVIDER=duckduckgo
+
+# Serper API Key (for Google search via Serper)
+SERPER_API_KEY=your_serper_api_key_here
+
+# SearchXNG Host URL (for self-hosted search)
+SEARCHXNG_HOST=http://localhost:8080
+
+# Brave Search API Key
+BRAVE_API_KEY=your_brave_api_key_here
+
+# Tavily API Key
+TAVILY_API_KEY=your_tavily_api_key_here
+```
+
+The web search provider configuration:
+
+```71:74:src/utils/config.py
+    web_search_provider: Literal["serper", "searchxng", "brave", "tavily", "duckduckgo"] = Field(
+        default="duckduckgo",
+        description="Web search provider to use",
+    )
+```
+
+**Note**: DuckDuckGo is the default and requires no API key, making it ideal for development and testing.
+
+### PubMed Configuration
+
+PubMed search supports optional NCBI API key for higher rate limits:
+
+```bash
+# NCBI API Key (optional, for higher rate limits: 10 req/sec vs 3 req/sec)
+NCBI_API_KEY=your_ncbi_api_key_here
+```
+
+The PubMed tool uses this configuration:
+
+```22:29:src/tools/pubmed.py
+    def __init__(self, api_key: str | None = None) -> None:
+        self.api_key = api_key or settings.ncbi_api_key
+        # Ignore placeholder values from .env.example
+        if self.api_key == "your-ncbi-key-here":
+            self.api_key = None
+
+        # Use shared rate limiter
+        self._limiter = get_pubmed_limiter(self.api_key)
+```
+
+### Agent Configuration
+
+Control agent behavior and research loop execution:
+
+```bash
+# Maximum iterations per research loop (1-50, default: 10)
+MAX_ITERATIONS=10
+
+# Search timeout in seconds
+SEARCH_TIMEOUT=30
+
+# Use graph-based execution for research flows
+USE_GRAPH_EXECUTION=false
+```
+
+The agent configuration fields:
+
+```80:85:src/utils/config.py
+    # Agent Configuration
+    max_iterations: int = Field(default=10, ge=1, le=50)
+    search_timeout: int = Field(default=30, description="Seconds to wait for search")
+    use_graph_execution: bool = Field(
+        default=False, description="Use graph-based execution for research flows"
+    )
+```
+
+### Budget & Rate Limiting Configuration
+
+Control resource limits for research loops:
+
+```bash
+# Default token budget per research loop (1000-1000000, default: 100000)
+DEFAULT_TOKEN_LIMIT=100000
+
+# Default time limit per research loop in minutes (1-120, default: 10)
+DEFAULT_TIME_LIMIT_MINUTES=10
+
+# Default iterations limit per research loop (1-50, default: 10)
+DEFAULT_ITERATIONS_LIMIT=10
+```
+
+The budget configuration with validation:
+
+```87:105:src/utils/config.py
+    # Budget & Rate Limiting Configuration
+    default_token_limit: int = Field(
+        default=100000,
+        ge=1000,
+        le=1000000,
+        description="Default token budget per research loop",
+    )
+    default_time_limit_minutes: int = Field(
+        default=10,
+        ge=1,
+        le=120,
+        description="Default time limit per research loop (minutes)",
+    )
+    default_iterations_limit: int = Field(
+        default=10,
+        ge=1,
+        le=50,
+        description="Default iterations limit per research loop",
+    )
+```
+
+### RAG Service Configuration
+
+Configure the Retrieval-Augmented Generation service:
+
+```bash
+# ChromaDB collection name for RAG
+RAG_COLLECTION_NAME=deepcritical_evidence
+
+# Number of top results to retrieve from RAG (1-50, default: 5)
+RAG_SIMILARITY_TOP_K=5
+
+# Automatically ingest evidence into RAG
+RAG_AUTO_INGEST=true
+```
+
+The RAG configuration:
+
+```127:141:src/utils/config.py
+    # RAG Service Configuration
+    rag_collection_name: str = Field(
+        default="deepcritical_evidence",
+        description="ChromaDB collection name for RAG",
+    )
+    rag_similarity_top_k: int = Field(
+        default=5,
+        ge=1,
+        le=50,
+        description="Number of top results to retrieve from RAG",
+    )
+    rag_auto_ingest: bool = Field(
+        default=True,
+        description="Automatically ingest evidence into RAG",
+    )
+```
+
+### ChromaDB Configuration
+
+Configure the vector database for embeddings and RAG:
+
+```bash
+# ChromaDB storage path
+CHROMA_DB_PATH=./chroma_db
+
+# Whether to persist ChromaDB to disk
+CHROMA_DB_PERSIST=true
+
+# ChromaDB server host (for remote ChromaDB, optional)
+CHROMA_DB_HOST=localhost
+
+# ChromaDB server port (for remote ChromaDB, optional)
+CHROMA_DB_PORT=8000
+```
+
+The ChromaDB configuration:
+
+```113:125:src/utils/config.py
+    chroma_db_path: str = Field(default="./chroma_db", description="ChromaDB storage path")
+    chroma_db_persist: bool = Field(
+        default=True,
+        description="Whether to persist ChromaDB to disk",
+    )
+    chroma_db_host: str | None = Field(
+        default=None,
+        description="ChromaDB server host (for remote ChromaDB)",
+    )
+    chroma_db_port: int | None = Field(
+        default=None,
+        description="ChromaDB server port (for remote ChromaDB)",
+    )
+```
+
+### External Services
+
+#### Modal Configuration
+
+Modal is used for secure sandbox execution of statistical analysis:
+
+```bash
+# Modal Token ID (for Modal sandbox execution)
+MODAL_TOKEN_ID=your_modal_token_id_here
+
+# Modal Token Secret
+MODAL_TOKEN_SECRET=your_modal_token_secret_here
+```
+
+The Modal configuration:
+
+```110:112:src/utils/config.py
+    # External Services
+    modal_token_id: str | None = Field(default=None, description="Modal token ID")
+    modal_token_secret: str | None = Field(default=None, description="Modal token secret")
+```
+
+### Logging Configuration
+
+Configure structured logging:
+
+```bash
+# Log Level: "DEBUG", "INFO", "WARNING", or "ERROR"
+LOG_LEVEL=INFO
+```
+
+The logging configuration:
+
+```107:108:src/utils/config.py
+    # Logging
+    log_level: Literal["DEBUG", "INFO", "WARNING", "ERROR"] = "INFO"
+```
+
+Logging is configured via the `configure_logging()` function:
+
+```212:231:src/utils/config.py
+def configure_logging(settings: Settings) -> None:
+    """Configure structured logging with the configured log level."""
+    # Set stdlib logging level from settings
+    logging.basicConfig(
+        level=getattr(logging, settings.log_level),
+        format="%(message)s",
+    )
+
+    structlog.configure(
+        processors=[
+            structlog.stdlib.filter_by_level,
+            structlog.stdlib.add_logger_name,
+            structlog.stdlib.add_log_level,
+            structlog.processors.TimeStamper(fmt="iso"),
+            structlog.processors.JSONRenderer(),
+        ],
+        wrapper_class=structlog.stdlib.BoundLogger,
+        context_class=dict,
+        logger_factory=structlog.stdlib.LoggerFactory(),
+    )
+```
+
+## Configuration Properties
+
+The `Settings` class provides helpful properties for checking configuration state:
+
+### API Key Availability
+
+Check which API keys are available:
+
+```171:189:src/utils/config.py
+    @property
+    def has_openai_key(self) -> bool:
+        """Check if OpenAI API key is available."""
+        return bool(self.openai_api_key)
+
+    @property
+    def has_anthropic_key(self) -> bool:
+        """Check if Anthropic API key is available."""
+        return bool(self.anthropic_api_key)
+
+    @property
+    def has_huggingface_key(self) -> bool:
+        """Check if HuggingFace API key is available."""
+        return bool(self.huggingface_api_key or self.hf_token)
+
+    @property
+    def has_any_llm_key(self) -> bool:
+        """Check if any LLM API key is available."""
+        return self.has_openai_key or self.has_anthropic_key or self.has_huggingface_key
+```
+
+**Usage:**
+
+```python
+from src.utils.config import settings
+
+# Check API key availability
+if settings.has_openai_key:
+    # Use OpenAI
+    pass
+
+if settings.has_anthropic_key:
+    # Use Anthropic
+    pass
+
+if settings.has_huggingface_key:
+    # Use HuggingFace
+    pass
+
+if settings.has_any_llm_key:
+    # At least one LLM is available
+    pass
+```
+
+### Service Availability
+
+Check if external services are configured:
+
+```143:146:src/utils/config.py
+    @property
+    def modal_available(self) -> bool:
+        """Check if Modal credentials are configured."""
+        return bool(self.modal_token_id and self.modal_token_secret)
+```
+
+```191:204:src/utils/config.py
+    @property
+    def web_search_available(self) -> bool:
+        """Check if web search is available (either no-key provider or API key present)."""
+        if self.web_search_provider == "duckduckgo":
+            return True  # No API key required
+        if self.web_search_provider == "serper":
+            return bool(self.serper_api_key)
+        if self.web_search_provider == "searchxng":
+            return bool(self.searchxng_host)
+        if self.web_search_provider == "brave":
+            return bool(self.brave_api_key)
+        if self.web_search_provider == "tavily":
+            return bool(self.tavily_api_key)
+        return False
+```
+
+**Usage:**
+
+```python
+from src.utils.config import settings
+
+# Check service availability
+if settings.modal_available:
+    # Use Modal sandbox
+    pass
+
+if settings.web_search_available:
+    # Web search is configured
+    pass
+```
+
+### API Key Retrieval
+
+Get the API key for the configured provider:
+
+```148:160:src/utils/config.py
+    def get_api_key(self) -> str:
+        """Get the API key for the configured provider."""
+        if self.llm_provider == "openai":
+            if not self.openai_api_key:
+                raise ConfigurationError("OPENAI_API_KEY not set")
+            return self.openai_api_key
+
+        if self.llm_provider == "anthropic":
+            if not self.anthropic_api_key:
+                raise ConfigurationError("ANTHROPIC_API_KEY not set")
+            return self.anthropic_api_key
+
+        raise ConfigurationError(f"Unknown LLM provider: {self.llm_provider}")
+```
+
+For OpenAI-specific operations (e.g., Magentic mode):
+
+```162:169:src/utils/config.py
+    def get_openai_api_key(self) -> str:
+        """Get OpenAI API key (required for Magentic function calling)."""
+        if not self.openai_api_key:
+            raise ConfigurationError(
+                "OPENAI_API_KEY not set. Magentic mode requires OpenAI for function calling. "
+                "Use mode='simple' for other providers."
+            )
+        return self.openai_api_key
+```
+
+## Configuration Usage in Codebase
+
+The configuration system is used throughout the codebase:
+
+### LLM Factory
+
+The LLM factory uses settings to create appropriate models:
+
+```129:144:src/utils/llm_factory.py
+    if settings.llm_provider == "huggingface":
+        model_name = settings.huggingface_model or "meta-llama/Llama-3.1-8B-Instruct"
+        hf_provider = HuggingFaceProvider(api_key=settings.hf_token)
+        return HuggingFaceModel(model_name, provider=hf_provider)
+
+    if settings.llm_provider == "openai":
+        if not settings.openai_api_key:
+            raise ConfigurationError("OPENAI_API_KEY not set for pydantic-ai")
+        provider = OpenAIProvider(api_key=settings.openai_api_key)
+        return OpenAIModel(settings.openai_model, provider=provider)
+
+    if settings.llm_provider == "anthropic":
+        if not settings.anthropic_api_key:
+            raise ConfigurationError("ANTHROPIC_API_KEY not set for pydantic-ai")
+        anthropic_provider = AnthropicProvider(api_key=settings.anthropic_api_key)
+        return AnthropicModel(settings.anthropic_model, provider=anthropic_provider)
+```
+
+### Embedding Service
+
+The embedding service uses local embedding model configuration:
+
+```29:31:src/services/embeddings.py
+    def __init__(self, model_name: str | None = None):
+        self._model_name = model_name or settings.local_embedding_model
+        self._model = SentenceTransformer(self._model_name)
+```
+
+### Orchestrator Factory
+
+The orchestrator factory uses settings to determine mode:
+
+```69:80:src/orchestrator_factory.py
+def _determine_mode(explicit_mode: str | None) -> str:
+    """Determine which mode to use."""
+    if explicit_mode:
+        if explicit_mode in ("magentic", "advanced"):
+            return "advanced"
+        return "simple"
+
+    # Auto-detect: advanced if paid API key available
+    if settings.has_openai_key:
+        return "advanced"
+
+    return "simple"
+```
+
+## Environment Variables Reference
+
+### Required (at least one LLM)
+
+- `OPENAI_API_KEY` - OpenAI API key (required for OpenAI provider)
+- `ANTHROPIC_API_KEY` - Anthropic API key (required for Anthropic provider)
+- `HF_TOKEN` or `HUGGINGFACE_API_KEY` - HuggingFace API token (optional, can work without for public models)
+
+#### LLM Configuration Variables
+
+- `LLM_PROVIDER` - Provider to use: `"openai"`, `"anthropic"`, or `"huggingface"` (default: `"huggingface"`)
+- `OPENAI_MODEL` - OpenAI model name (default: `"gpt-5.1"`)
+- `ANTHROPIC_MODEL` - Anthropic model name (default: `"claude-sonnet-4-5-20250929"`)
+- `HUGGINGFACE_MODEL` - HuggingFace model ID (default: `"meta-llama/Llama-3.1-8B-Instruct"`)
+
+#### Embedding Configuration Variables
+
+- `EMBEDDING_PROVIDER` - Provider: `"openai"`, `"local"`, or `"huggingface"` (default: `"local"`)
+- `OPENAI_EMBEDDING_MODEL` - OpenAI embedding model (default: `"text-embedding-3-small"`)
+- `LOCAL_EMBEDDING_MODEL` - Local sentence-transformers model (default: `"all-MiniLM-L6-v2"`)
+- `HUGGINGFACE_EMBEDDING_MODEL` - HuggingFace embedding model (default: `"sentence-transformers/all-MiniLM-L6-v2"`)
+
+#### Web Search Configuration Variables
+
+- `WEB_SEARCH_PROVIDER` - Provider: `"serper"`, `"searchxng"`, `"brave"`, `"tavily"`, or `"duckduckgo"` (default: `"duckduckgo"`)
+- `SERPER_API_KEY` - Serper API key (required for Serper provider)
+- `SEARCHXNG_HOST` - SearchXNG host URL (required for SearchXNG provider)
+- `BRAVE_API_KEY` - Brave Search API key (required for Brave provider)
+- `TAVILY_API_KEY` - Tavily API key (required for Tavily provider)
+
+#### PubMed Configuration Variables
+
+- `NCBI_API_KEY` - NCBI API key (optional, increases rate limit from 3 to 10 req/sec)
+
+#### Agent Configuration Variables
+
+- `MAX_ITERATIONS` - Maximum iterations per research loop (1-50, default: `10`)
+- `SEARCH_TIMEOUT` - Search timeout in seconds (default: `30`)
+- `USE_GRAPH_EXECUTION` - Use graph-based execution (default: `false`)
+
+#### Budget Configuration Variables
+
+- `DEFAULT_TOKEN_LIMIT` - Default token budget per research loop (1000-1000000, default: `100000`)
+- `DEFAULT_TIME_LIMIT_MINUTES` - Default time limit in minutes (1-120, default: `10`)
+- `DEFAULT_ITERATIONS_LIMIT` - Default iterations limit (1-50, default: `10`)
+
+#### RAG Configuration Variables
+
+- `RAG_COLLECTION_NAME` - ChromaDB collection name (default: `"deepcritical_evidence"`)
+- `RAG_SIMILARITY_TOP_K` - Number of top results to retrieve (1-50, default: `5`)
+- `RAG_AUTO_INGEST` - Automatically ingest evidence into RAG (default: `true`)
+
+#### ChromaDB Configuration Variables
+
+- `CHROMA_DB_PATH` - ChromaDB storage path (default: `"./chroma_db"`)
+- `CHROMA_DB_PERSIST` - Whether to persist ChromaDB to disk (default: `true`)
+- `CHROMA_DB_HOST` - ChromaDB server host (optional, for remote ChromaDB)
+- `CHROMA_DB_PORT` - ChromaDB server port (optional, for remote ChromaDB)
+
+#### External Services Variables
+
+- `MODAL_TOKEN_ID` - Modal token ID (optional, for Modal sandbox execution)
+- `MODAL_TOKEN_SECRET` - Modal token secret (optional, for Modal sandbox execution)
+
+#### Logging Configuration Variables
+
+- `LOG_LEVEL` - Log level: `"DEBUG"`, `"INFO"`, `"WARNING"`, or `"ERROR"` (default: `"INFO"`)
+
+## Validation
+
+Settings are validated on load using Pydantic validation:
+
+- **Type Checking**: All fields are strongly typed
+- **Range Validation**: Numeric fields have min/max constraints (e.g., `ge=1, le=50` for `max_iterations`)
+- **Literal Validation**: Enum fields only accept specific values (e.g., `Literal["openai", "anthropic", "huggingface"]`)
+- **Required Fields**: API keys are checked when accessed via `get_api_key()` or `get_openai_api_key()`
+
+### Validation Examples
+
+The `max_iterations` field has range validation:
+
+```81:81:src/utils/config.py
+    max_iterations: int = Field(default=10, ge=1, le=50)
+```
+
+The `llm_provider` field has literal validation:
+
+```26:28:src/utils/config.py
+    llm_provider: Literal["openai", "anthropic", "huggingface"] = Field(
+        default="openai", description="Which LLM provider to use"
+    )
+```
+
+## Error Handling
+
+Configuration errors raise `ConfigurationError` from `src/utils/exceptions.py`:
+
+```22:25:src/utils/exceptions.py
+class ConfigurationError(DeepCriticalError):
+    """Raised when configuration is invalid."""
+
+    pass
+```
+
+### Error Handling Example
+
+```python
+from src.utils.config import settings
+from src.utils.exceptions import ConfigurationError
+
+try:
+    api_key = settings.get_api_key()
+except ConfigurationError as e:
+    print(f"Configuration error: {e}")
+```
+
+### Common Configuration Errors
+
+1. **Missing API Key**: When `get_api_key()` is called but the required API key is not set
+2. **Invalid Provider**: When `llm_provider` is set to an unsupported value
+3. **Out of Range**: When numeric values exceed their min/max constraints
+4. **Invalid Literal**: When enum fields receive unsupported values
+
+## Configuration Best Practices
+
+1. **Use `.env` File**: Store sensitive keys in `.env` file (add to `.gitignore`)
+2. **Check Availability**: Use properties like `has_openai_key` before accessing API keys
+3. **Handle Errors**: Always catch `ConfigurationError` when calling `get_api_key()`
+4. **Validate Early**: Configuration is validated on import, so errors surface immediately
+5. **Use Defaults**: Leverage sensible defaults for optional configuration
+
+## Future Enhancements
+
+The following configurations are planned for future phases:
+
+1. **Additional LLM Providers**: DeepSeek, OpenRouter, Gemini, Perplexity, Azure OpenAI, Local models
+2. **Model Selection**: Reasoning/main/fast model configuration
+3. **Service Integration**: Additional service integrations and configurations
+

docs/configuration/index.md

@@ -0,0 +1,746 @@
+# Configuration Guide
+
+## Overview
+
+DeepCritical uses **Pydantic Settings** for centralized configuration management. All settings are defined in the `Settings` class in `src/utils/config.py` and can be configured via environment variables or a `.env` file.
+
+The configuration system provides:
+
+- **Type Safety**: Strongly-typed fields with Pydantic validation
+- **Environment File Support**: Automatically loads from `.env` file (if present)
+- **Case-Insensitive**: Environment variables are case-insensitive
+- **Singleton Pattern**: Global `settings` instance for easy access throughout the codebase
+- **Validation**: Automatic validation on load with helpful error messages
+
+## Quick Start
+
+1. Create a `.env` file in the project root
+2. Set at least one LLM API key (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `HF_TOKEN`)
+3. Optionally configure other services as needed
+4. The application will automatically load and validate your configuration
+
+## Configuration System Architecture
+
+### Settings Class
+
+The [`Settings`][settings-class] class extends `BaseSettings` from `pydantic_settings` and defines all application configuration:
+
+```13:21:src/utils/config.py
+class Settings(BaseSettings):
+    """Strongly-typed application settings."""
+
+    model_config = SettingsConfigDict(
+        env_file=".env",
+        env_file_encoding="utf-8",
+        case_sensitive=False,
+        extra="ignore",
+    )
+```
+
+[View source](https://github.com/DeepCritical/GradioDemo/blob/main/src/utils/config.py#L13-L21)
+
+### Singleton Instance
+
+A global `settings` instance is available for import:
+
+```234:235:src/utils/config.py
+# Singleton for easy import
+settings = get_settings()
+```
+
+[View source](https://github.com/DeepCritical/GradioDemo/blob/main/src/utils/config.py#L234-L235)
+
+### Usage Pattern
+
+Access configuration throughout the codebase:
+
+```python
+from src.utils.config import settings
+
+# Check if API keys are available
+if settings.has_openai_key:
+    # Use OpenAI
+    pass
+
+# Access configuration values
+max_iterations = settings.max_iterations
+web_search_provider = settings.web_search_provider
+```
+
+## Required Configuration
+
+### LLM Provider
+
+You must configure at least one LLM provider. The system supports:
+
+- **OpenAI**: Requires `OPENAI_API_KEY`
+- **Anthropic**: Requires `ANTHROPIC_API_KEY`
+- **HuggingFace**: Optional `HF_TOKEN` or `HUGGINGFACE_API_KEY` (can work without key for public models)
+
+#### OpenAI Configuration
+
+```bash
+LLM_PROVIDER=openai
+OPENAI_API_KEY=your_openai_api_key_here
+OPENAI_MODEL=gpt-5.1
+```
+
+The default model is defined in the `Settings` class:
+
+```29:29:src/utils/config.py
+    openai_model: str = Field(default="gpt-5.1", description="OpenAI model name")
+```
+
+#### Anthropic Configuration
+
+```bash
+LLM_PROVIDER=anthropic
+ANTHROPIC_API_KEY=your_anthropic_api_key_here
+ANTHROPIC_MODEL=claude-sonnet-4-5-20250929
+```
+
+The default model is defined in the `Settings` class:
+
+```30:32:src/utils/config.py
+    anthropic_model: str = Field(
+        default="claude-sonnet-4-5-20250929", description="Anthropic model"
+    )
+```
+
+#### HuggingFace Configuration
+
+HuggingFace can work without an API key for public models, but an API key provides higher rate limits:
+
+```bash
+# Option 1: Using HF_TOKEN (preferred)
+HF_TOKEN=your_huggingface_token_here
+
+# Option 2: Using HUGGINGFACE_API_KEY (alternative)
+HUGGINGFACE_API_KEY=your_huggingface_api_key_here
+
+# Default model
+HUGGINGFACE_MODEL=meta-llama/Llama-3.1-8B-Instruct
+```
+
+The HuggingFace token can be set via either environment variable:
+
+```33:35:src/utils/config.py
+    hf_token: str | None = Field(
+        default=None, alias="HF_TOKEN", description="HuggingFace API token"
+    )
+```
+
+```57:59:src/utils/config.py
+    huggingface_api_key: str | None = Field(
+        default=None, description="HuggingFace API token (HF_TOKEN or HUGGINGFACE_API_KEY)"
+    )
+```
+
+## Optional Configuration
+
+### Embedding Configuration
+
+DeepCritical supports multiple embedding providers for semantic search and RAG:
+
+```bash
+# Embedding Provider: "openai", "local", or "huggingface"
+EMBEDDING_PROVIDER=local
+
+# OpenAI Embedding Model (used by LlamaIndex RAG)
+OPENAI_EMBEDDING_MODEL=text-embedding-3-small
+
+# Local Embedding Model (sentence-transformers, used by EmbeddingService)
+LOCAL_EMBEDDING_MODEL=all-MiniLM-L6-v2
+
+# HuggingFace Embedding Model
+HUGGINGFACE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
+```
+
+The embedding provider configuration:
+
+```47:50:src/utils/config.py
+    embedding_provider: Literal["openai", "local", "huggingface"] = Field(
+        default="local",
+        description="Embedding provider to use",
+    )
+```
+
+**Note**: OpenAI embeddings require `OPENAI_API_KEY`. The local provider (default) uses sentence-transformers and requires no API key.
+
+### Web Search Configuration
+
+DeepCritical supports multiple web search providers:
+
+```bash
+# Web Search Provider: "serper", "searchxng", "brave", "tavily", or "duckduckgo"
+# Default: "duckduckgo" (no API key required)
+WEB_SEARCH_PROVIDER=duckduckgo
+
+# Serper API Key (for Google search via Serper)
+SERPER_API_KEY=your_serper_api_key_here
+
+# SearchXNG Host URL (for self-hosted search)
+SEARCHXNG_HOST=http://localhost:8080
+
+# Brave Search API Key
+BRAVE_API_KEY=your_brave_api_key_here
+
+# Tavily API Key
+TAVILY_API_KEY=your_tavily_api_key_here
+```
+
+The web search provider configuration:
+
+```71:74:src/utils/config.py
+    web_search_provider: Literal["serper", "searchxng", "brave", "tavily", "duckduckgo"] = Field(
+        default="duckduckgo",
+        description="Web search provider to use",
+    )
+```
+
+**Note**: DuckDuckGo is the default and requires no API key, making it ideal for development and testing.
+
+### PubMed Configuration
+
+PubMed search supports optional NCBI API key for higher rate limits:
+
+```bash
+# NCBI API Key (optional, for higher rate limits: 10 req/sec vs 3 req/sec)
+NCBI_API_KEY=your_ncbi_api_key_here
+```
+
+The PubMed tool uses this configuration:
+
+```22:29:src/tools/pubmed.py
+    def __init__(self, api_key: str | None = None) -> None:
+        self.api_key = api_key or settings.ncbi_api_key
+        # Ignore placeholder values from .env.example
+        if self.api_key == "your-ncbi-key-here":
+            self.api_key = None
+
+        # Use shared rate limiter
+        self._limiter = get_pubmed_limiter(self.api_key)
+```
+
+### Agent Configuration
+
+Control agent behavior and research loop execution:
+
+```bash
+# Maximum iterations per research loop (1-50, default: 10)
+MAX_ITERATIONS=10
+
+# Search timeout in seconds
+SEARCH_TIMEOUT=30
+
+# Use graph-based execution for research flows
+USE_GRAPH_EXECUTION=false
+```
+
+The agent configuration fields:
+
+```80:85:src/utils/config.py
+    # Agent Configuration
+    max_iterations: int = Field(default=10, ge=1, le=50)
+    search_timeout: int = Field(default=30, description="Seconds to wait for search")
+    use_graph_execution: bool = Field(
+        default=False, description="Use graph-based execution for research flows"
+    )
+```
+
+### Budget & Rate Limiting Configuration
+
+Control resource limits for research loops:
+
+```bash
+# Default token budget per research loop (1000-1000000, default: 100000)
+DEFAULT_TOKEN_LIMIT=100000
+
+# Default time limit per research loop in minutes (1-120, default: 10)
+DEFAULT_TIME_LIMIT_MINUTES=10
+
+# Default iterations limit per research loop (1-50, default: 10)
+DEFAULT_ITERATIONS_LIMIT=10
+```
+
+The budget configuration with validation:
+
+```87:105:src/utils/config.py
+    # Budget & Rate Limiting Configuration
+    default_token_limit: int = Field(
+        default=100000,
+        ge=1000,
+        le=1000000,
+        description="Default token budget per research loop",
+    )
+    default_time_limit_minutes: int = Field(
+        default=10,
+        ge=1,
+        le=120,
+        description="Default time limit per research loop (minutes)",
+    )
+    default_iterations_limit: int = Field(
+        default=10,
+        ge=1,
+        le=50,
+        description="Default iterations limit per research loop",
+    )
+```
+
+### RAG Service Configuration
+
+Configure the Retrieval-Augmented Generation service:
+
+```bash
+# ChromaDB collection name for RAG
+RAG_COLLECTION_NAME=deepcritical_evidence
+
+# Number of top results to retrieve from RAG (1-50, default: 5)
+RAG_SIMILARITY_TOP_K=5
+
+# Automatically ingest evidence into RAG
+RAG_AUTO_INGEST=true
+```
+
+The RAG configuration:
+
+```127:141:src/utils/config.py
+    # RAG Service Configuration
+    rag_collection_name: str = Field(
+        default="deepcritical_evidence",
+        description="ChromaDB collection name for RAG",
+    )
+    rag_similarity_top_k: int = Field(
+        default=5,
+        ge=1,
+        le=50,
+        description="Number of top results to retrieve from RAG",
+    )
+    rag_auto_ingest: bool = Field(
+        default=True,
+        description="Automatically ingest evidence into RAG",
+    )
+```
+
+### ChromaDB Configuration
+
+Configure the vector database for embeddings and RAG:
+
+```bash
+# ChromaDB storage path
+CHROMA_DB_PATH=./chroma_db
+
+# Whether to persist ChromaDB to disk
+CHROMA_DB_PERSIST=true
+
+# ChromaDB server host (for remote ChromaDB, optional)
+CHROMA_DB_HOST=localhost
+
+# ChromaDB server port (for remote ChromaDB, optional)
+CHROMA_DB_PORT=8000
+```
+
+The ChromaDB configuration:
+
+```113:125:src/utils/config.py
+    chroma_db_path: str = Field(default="./chroma_db", description="ChromaDB storage path")
+    chroma_db_persist: bool = Field(
+        default=True,
+        description="Whether to persist ChromaDB to disk",
+    )
+    chroma_db_host: str | None = Field(
+        default=None,
+        description="ChromaDB server host (for remote ChromaDB)",
+    )
+    chroma_db_port: int | None = Field(
+        default=None,
+        description="ChromaDB server port (for remote ChromaDB)",
+    )
+```
+
+### External Services
+
+#### Modal Configuration
+
+Modal is used for secure sandbox execution of statistical analysis:
+
+```bash
+# Modal Token ID (for Modal sandbox execution)
+MODAL_TOKEN_ID=your_modal_token_id_here
+
+# Modal Token Secret
+MODAL_TOKEN_SECRET=your_modal_token_secret_here
+```
+
+The Modal configuration:
+
+```110:112:src/utils/config.py
+    # External Services
+    modal_token_id: str | None = Field(default=None, description="Modal token ID")
+    modal_token_secret: str | None = Field(default=None, description="Modal token secret")
+```
+
+### Logging Configuration
+
+Configure structured logging:
+
+```bash
+# Log Level: "DEBUG", "INFO", "WARNING", or "ERROR"
+LOG_LEVEL=INFO
+```
+
+The logging configuration:
+
+```107:108:src/utils/config.py
+    # Logging
+    log_level: Literal["DEBUG", "INFO", "WARNING", "ERROR"] = "INFO"
+```
+
+Logging is configured via the `configure_logging()` function:
+
+```212:231:src/utils/config.py
+def configure_logging(settings: Settings) -> None:
+    """Configure structured logging with the configured log level."""
+    # Set stdlib logging level from settings
+    logging.basicConfig(
+        level=getattr(logging, settings.log_level),
+        format="%(message)s",
+    )
+
+    structlog.configure(
+        processors=[
+            structlog.stdlib.filter_by_level,
+            structlog.stdlib.add_logger_name,
+            structlog.stdlib.add_log_level,
+            structlog.processors.TimeStamper(fmt="iso"),
+            structlog.processors.JSONRenderer(),
+        ],
+        wrapper_class=structlog.stdlib.BoundLogger,
+        context_class=dict,
+        logger_factory=structlog.stdlib.LoggerFactory(),
+    )
+```
+
+## Configuration Properties
+
+The `Settings` class provides helpful properties for checking configuration state:
+
+### API Key Availability
+
+Check which API keys are available:
+
+```171:189:src/utils/config.py
+    @property
+    def has_openai_key(self) -> bool:
+        """Check if OpenAI API key is available."""
+        return bool(self.openai_api_key)
+
+    @property
+    def has_anthropic_key(self) -> bool:
+        """Check if Anthropic API key is available."""
+        return bool(self.anthropic_api_key)
+
+    @property
+    def has_huggingface_key(self) -> bool:
+        """Check if HuggingFace API key is available."""
+        return bool(self.huggingface_api_key or self.hf_token)
+
+    @property
+    def has_any_llm_key(self) -> bool:
+        """Check if any LLM API key is available."""
+        return self.has_openai_key or self.has_anthropic_key or self.has_huggingface_key
+```
+
+**Usage:**
+
+```python
+from src.utils.config import settings
+
+# Check API key availability
+if settings.has_openai_key:
+    # Use OpenAI
+    pass
+
+if settings.has_anthropic_key:
+    # Use Anthropic
+    pass
+
+if settings.has_huggingface_key:
+    # Use HuggingFace
+    pass
+
+if settings.has_any_llm_key:
+    # At least one LLM is available
+    pass
+```
+
+### Service Availability
+
+Check if external services are configured:
+
+```143:146:src/utils/config.py
+    @property
+    def modal_available(self) -> bool:
+        """Check if Modal credentials are configured."""
+        return bool(self.modal_token_id and self.modal_token_secret)
+```
+
+```191:204:src/utils/config.py
+    @property
+    def web_search_available(self) -> bool:
+        """Check if web search is available (either no-key provider or API key present)."""
+        if self.web_search_provider == "duckduckgo":
+            return True  # No API key required
+        if self.web_search_provider == "serper":
+            return bool(self.serper_api_key)
+        if self.web_search_provider == "searchxng":
+            return bool(self.searchxng_host)
+        if self.web_search_provider == "brave":
+            return bool(self.brave_api_key)
+        if self.web_search_provider == "tavily":
+            return bool(self.tavily_api_key)
+        return False
+```
+
+**Usage:**
+
+```python
+from src.utils.config import settings
+
+# Check service availability
+if settings.modal_available:
+    # Use Modal sandbox
+    pass
+
+if settings.web_search_available:
+    # Web search is configured
+    pass
+```
+
+### API Key Retrieval
+
+Get the API key for the configured provider:
+
+```148:160:src/utils/config.py
+    def get_api_key(self) -> str:
+        """Get the API key for the configured provider."""
+        if self.llm_provider == "openai":
+            if not self.openai_api_key:
+                raise ConfigurationError("OPENAI_API_KEY not set")
+            return self.openai_api_key
+
+        if self.llm_provider == "anthropic":
+            if not self.anthropic_api_key:
+                raise ConfigurationError("ANTHROPIC_API_KEY not set")
+            return self.anthropic_api_key
+
+        raise ConfigurationError(f"Unknown LLM provider: {self.llm_provider}")
+```
+
+For OpenAI-specific operations (e.g., Magentic mode):
+
+```162:169:src/utils/config.py
+    def get_openai_api_key(self) -> str:
+        """Get OpenAI API key (required for Magentic function calling)."""
+        if not self.openai_api_key:
+            raise ConfigurationError(
+                "OPENAI_API_KEY not set. Magentic mode requires OpenAI for function calling. "
+                "Use mode='simple' for other providers."
+            )
+        return self.openai_api_key
+```
+
+## Configuration Usage in Codebase
+
+The configuration system is used throughout the codebase:
+
+### LLM Factory
+
+The LLM factory uses settings to create appropriate models:
+
+```129:144:src/utils/llm_factory.py
+    if settings.llm_provider == "huggingface":
+        model_name = settings.huggingface_model or "meta-llama/Llama-3.1-8B-Instruct"
+        hf_provider = HuggingFaceProvider(api_key=settings.hf_token)
+        return HuggingFaceModel(model_name, provider=hf_provider)
+
+    if settings.llm_provider == "openai":
+        if not settings.openai_api_key:
+            raise ConfigurationError("OPENAI_API_KEY not set for pydantic-ai")
+        provider = OpenAIProvider(api_key=settings.openai_api_key)
+        return OpenAIModel(settings.openai_model, provider=provider)
+
+    if settings.llm_provider == "anthropic":
+        if not settings.anthropic_api_key:
+            raise ConfigurationError("ANTHROPIC_API_KEY not set for pydantic-ai")
+        anthropic_provider = AnthropicProvider(api_key=settings.anthropic_api_key)
+        return AnthropicModel(settings.anthropic_model, provider=anthropic_provider)
+```
+
+### Embedding Service
+
+The embedding service uses local embedding model configuration:
+
+```29:31:src/services/embeddings.py
+    def __init__(self, model_name: str | None = None):
+        self._model_name = model_name or settings.local_embedding_model
+        self._model = SentenceTransformer(self._model_name)
+```
+
+### Orchestrator Factory
+
+The orchestrator factory uses settings to determine mode:
+
+```69:80:src/orchestrator_factory.py
+def _determine_mode(explicit_mode: str | None) -> str:
+    """Determine which mode to use."""
+    if explicit_mode:
+        if explicit_mode in ("magentic", "advanced"):
+            return "advanced"
+        return "simple"
+
+    # Auto-detect: advanced if paid API key available
+    if settings.has_openai_key:
+        return "advanced"
+
+    return "simple"
+```
+
+## Environment Variables Reference
+
+### Required (at least one LLM)
+
+- `OPENAI_API_KEY` - OpenAI API key (required for OpenAI provider)
+- `ANTHROPIC_API_KEY` - Anthropic API key (required for Anthropic provider)
+- `HF_TOKEN` or `HUGGINGFACE_API_KEY` - HuggingFace API token (optional, can work without for public models)
+
+#### LLM Configuration Variables
+
+- `LLM_PROVIDER` - Provider to use: `"openai"`, `"anthropic"`, or `"huggingface"` (default: `"huggingface"`)
+- `OPENAI_MODEL` - OpenAI model name (default: `"gpt-5.1"`)
+- `ANTHROPIC_MODEL` - Anthropic model name (default: `"claude-sonnet-4-5-20250929"`)
+- `HUGGINGFACE_MODEL` - HuggingFace model ID (default: `"meta-llama/Llama-3.1-8B-Instruct"`)
+
+#### Embedding Configuration Variables
+
+- `EMBEDDING_PROVIDER` - Provider: `"openai"`, `"local"`, or `"huggingface"` (default: `"local"`)
+- `OPENAI_EMBEDDING_MODEL` - OpenAI embedding model (default: `"text-embedding-3-small"`)
+- `LOCAL_EMBEDDING_MODEL` - Local sentence-transformers model (default: `"all-MiniLM-L6-v2"`)
+- `HUGGINGFACE_EMBEDDING_MODEL` - HuggingFace embedding model (default: `"sentence-transformers/all-MiniLM-L6-v2"`)
+
+#### Web Search Configuration Variables
+
+- `WEB_SEARCH_PROVIDER` - Provider: `"serper"`, `"searchxng"`, `"brave"`, `"tavily"`, or `"duckduckgo"` (default: `"duckduckgo"`)
+- `SERPER_API_KEY` - Serper API key (required for Serper provider)
+- `SEARCHXNG_HOST` - SearchXNG host URL (required for SearchXNG provider)
+- `BRAVE_API_KEY` - Brave Search API key (required for Brave provider)
+- `TAVILY_API_KEY` - Tavily API key (required for Tavily provider)
+
+#### PubMed Configuration Variables
+
+- `NCBI_API_KEY` - NCBI API key (optional, increases rate limit from 3 to 10 req/sec)
+
+#### Agent Configuration Variables
+
+- `MAX_ITERATIONS` - Maximum iterations per research loop (1-50, default: `10`)
+- `SEARCH_TIMEOUT` - Search timeout in seconds (default: `30`)
+- `USE_GRAPH_EXECUTION` - Use graph-based execution (default: `false`)
+
+#### Budget Configuration Variables
+
+- `DEFAULT_TOKEN_LIMIT` - Default token budget per research loop (1000-1000000, default: `100000`)
+- `DEFAULT_TIME_LIMIT_MINUTES` - Default time limit in minutes (1-120, default: `10`)
+- `DEFAULT_ITERATIONS_LIMIT` - Default iterations limit (1-50, default: `10`)
+
+#### RAG Configuration Variables
+
+- `RAG_COLLECTION_NAME` - ChromaDB collection name (default: `"deepcritical_evidence"`)
+- `RAG_SIMILARITY_TOP_K` - Number of top results to retrieve (1-50, default: `5`)
+- `RAG_AUTO_INGEST` - Automatically ingest evidence into RAG (default: `true`)
+
+#### ChromaDB Configuration Variables
+
+- `CHROMA_DB_PATH` - ChromaDB storage path (default: `"./chroma_db"`)
+- `CHROMA_DB_PERSIST` - Whether to persist ChromaDB to disk (default: `true`)
+- `CHROMA_DB_HOST` - ChromaDB server host (optional, for remote ChromaDB)
+- `CHROMA_DB_PORT` - ChromaDB server port (optional, for remote ChromaDB)
+
+#### External Services Variables
+
+- `MODAL_TOKEN_ID` - Modal token ID (optional, for Modal sandbox execution)
+- `MODAL_TOKEN_SECRET` - Modal token secret (optional, for Modal sandbox execution)
+
+#### Logging Configuration Variables
+
+- `LOG_LEVEL` - Log level: `"DEBUG"`, `"INFO"`, `"WARNING"`, or `"ERROR"` (default: `"INFO"`)
+
+## Validation
+
+Settings are validated on load using Pydantic validation:
+
+- **Type Checking**: All fields are strongly typed
+- **Range Validation**: Numeric fields have min/max constraints (e.g., `ge=1, le=50` for `max_iterations`)
+- **Literal Validation**: Enum fields only accept specific values (e.g., `Literal["openai", "anthropic", "huggingface"]`)
+- **Required Fields**: API keys are checked when accessed via `get_api_key()` or `get_openai_api_key()`
+
+### Validation Examples
+
+The `max_iterations` field has range validation:
+
+```81:81:src/utils/config.py
+    max_iterations: int = Field(default=10, ge=1, le=50)
+```
+
+The `llm_provider` field has literal validation:
+
+```26:28:src/utils/config.py
+    llm_provider: Literal["openai", "anthropic", "huggingface"] = Field(
+        default="openai", description="Which LLM provider to use"
+    )
+```
+
+## Error Handling
+
+Configuration errors raise `ConfigurationError` from `src/utils/exceptions.py`:
+
+```22:25:src/utils/exceptions.py
+class ConfigurationError(DeepCriticalError):
+    """Raised when configuration is invalid."""
+
+    pass
+```
+
+### Error Handling Example
+
+```python
+from src.utils.config import settings
+from src.utils.exceptions import ConfigurationError
+
+try:
+    api_key = settings.get_api_key()
+except ConfigurationError as e:
+    print(f"Configuration error: {e}")
+```
+
+### Common Configuration Errors
+
+1. **Missing API Key**: When `get_api_key()` is called but the required API key is not set
+2. **Invalid Provider**: When `llm_provider` is set to an unsupported value
+3. **Out of Range**: When numeric values exceed their min/max constraints
+4. **Invalid Literal**: When enum fields receive unsupported values
+
+## Configuration Best Practices
+
+1. **Use `.env` File**: Store sensitive keys in `.env` file (add to `.gitignore`)
+2. **Check Availability**: Use properties like `has_openai_key` before accessing API keys
+3. **Handle Errors**: Always catch `ConfigurationError` when calling `get_api_key()`
+4. **Validate Early**: Configuration is validated on import, so errors surface immediately
+5. **Use Defaults**: Leverage sensible defaults for optional configuration
+
+## Future Enhancements
+
+The following configurations are planned for future phases:
+
+1. **Additional LLM Providers**: DeepSeek, OpenRouter, Gemini, Perplexity, Azure OpenAI, Local models
+2. **Model Selection**: Reasoning/main/fast model configuration
+3. **Service Integration**: Additional service integrations and configurations

CONTRIBUTING.md → docs/contributing.md

@@ -1,26 +1,24 @@
-# Contributing to The DETERMINATOR
+# Contributing to DeepCritical
 
-Thank you for your interest in contributing to The DETERMINATOR! This guide will help you get started.
+Thank you for your interest in contributing to DeepCritical! This guide will help you get started.
 
 ## Table of Contents
 
 - [Git Workflow](#git-workflow)
 - [Getting Started](#getting-started)
 - [Development Commands](#development-commands)
+- [Code Style & Conventions](#code-style--conventions)
+- [Type Safety](#type-safety)
+- [Error Handling & Logging](#error-handling--logging)
+- [Testing Requirements](#testing-requirements)
+- [Implementation Patterns](#implementation-patterns)
+- [Code Quality & Documentation](#code-quality--documentation)
+- [Prompt Engineering & Citation Validation](#prompt-engineering--citation-validation)
 - [MCP Integration](#mcp-integration)
 - [Common Pitfalls](#common-pitfalls)
 - [Key Principles](#key-principles)
 - [Pull Request Process](#pull-request-process)
 
-> **Note**: Additional sections (Code Style, Error Handling, Testing, Implementation Patterns, Code Quality, and Prompt Engineering) are available as separate pages in the [documentation](https://deepcritical.github.io/GradioDemo/contributing/).  
-> **Note on Project Names**: "The DETERMINATOR" is the product name, "DeepCritical" is the organization/project name, and "determinator" is the Python package name.
-
-## Repository Information
-
-- **GitHub Repository**: [`DeepCritical/GradioDemo`](https://github.com/DeepCritical/GradioDemo) (source of truth, PRs, code review)
-- **HuggingFace Space**: [`DataQuests/DeepCritical`](https://huggingface.co/spaces/DataQuests/DeepCritical) (deployment/demo)
-- **Package Name**: `determinator` (Python package name in `pyproject.toml`)
-
 ## Git Workflow
 
 - `main`: Production-ready (GitHub)
@@ -29,31 +27,9 @@ Thank you for your interest in contributing to The DETERMINATOR! This guide will
 - **NEVER** push directly to `main` or `dev` on HuggingFace
 - GitHub is source of truth; HuggingFace is for deployment
 
-### Dual Repository Setup
-
-This project uses a dual repository setup:
-
-- **GitHub (`DeepCritical/GradioDemo`)**: Source of truth for code, PRs, and code review
-- **HuggingFace (`DataQuests/DeepCritical`)**: Deployment target for the Gradio demo
-
-#### Remote Configuration
-
-When cloning, set up remotes as follows:
-
-```bash
-# Clone from GitHub
-git clone https://github.com/DeepCritical/GradioDemo.git
-cd GradioDemo
-
-# Add HuggingFace remote (optional, for deployment)
-git remote add huggingface-upstream https://huggingface.co/spaces/DataQuests/DeepCritical
-```
-
-**Important**: Never push directly to `main` or `dev` on HuggingFace. Always work through GitHub PRs. GitHub is the source of truth; HuggingFace is for deployment/demo only.
-
 ## Getting Started
 
-1. **Fork the repository** on GitHub: [`DeepCritical/GradioDemo`](https://github.com/DeepCritical/GradioDemo)
+1. **Fork the repository** on GitHub
 2. **Clone your fork**:
 
    ```bash
@@ -64,8 +40,7 @@ git remote add huggingface-upstream https://huggingface.co/spaces/DataQuests/Dee
 3. **Install dependencies**:
 
    ```bash
-   uv sync --all-extras
-   uv run pre-commit install
+   make install
    ```
 
 4. **Create a feature branch**:
@@ -78,9 +53,7 @@ git remote add huggingface-upstream https://huggingface.co/spaces/DataQuests/Dee
 6. **Run checks**:
 
    ```bash
-   uv run ruff check src tests
-   uv run mypy src
-   uv run pytest --cov=src --cov-report=term-missing tests/unit/ -v -m "not openai" -p no:logfire
+   make check
    ```
 
 7. **Commit and push**:
@@ -89,72 +62,22 @@ git remote add huggingface-upstream https://huggingface.co/spaces/DataQuests/Dee
    git commit -m "Description of changes"
    git push origin yourname-feature-name
    ```
-
 8. **Create a pull request** on GitHub
 
-## Package Manager
-
-This project uses [`uv`](https://github.com/astral-sh/uv) as the package manager. All commands should be prefixed with `uv run` to ensure they run in the correct environment.
-
-### Installation
-
-```bash
-# Install uv if you haven't already (recommended: standalone installer)
-# Unix/macOS/Linux:
-curl -LsSf https://astral.sh/uv/install.sh | sh
-
-# Windows (PowerShell):
-powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
-
-# Alternative: pipx install uv
-# Or: pip install uv
-
-# Sync all dependencies including dev extras
-uv sync --all-extras
-
-# Install pre-commit hooks
-uv run pre-commit install
-```
-
 ## Development Commands
 
 ```bash
-# Installation
-uv sync --all-extras              # Install all dependencies including dev
-uv run pre-commit install          # Install pre-commit hooks
-
-# Code Quality Checks (run all before committing)
-uv run ruff check src tests       # Lint with ruff
-uv run ruff format src tests      # Format with ruff
-uv run mypy src                   # Type checking
-uv run pytest --cov=src --cov-report=term-missing tests/unit/ -v -m "not openai" -p no:logfire  # Tests with coverage
-
-# Testing Commands
-uv run pytest tests/unit/ -v -m "not openai" -p no:logfire              # Run unit tests (excludes OpenAI tests)
-uv run pytest tests/ -v -m "huggingface" -p no:logfire                 # Run HuggingFace tests
-uv run pytest tests/ -v -p no:logfire                                  # Run all tests
-uv run pytest --cov=src --cov-report=term-missing tests/unit/ -v -m "not openai" -p no:logfire  # Tests with terminal coverage
-uv run pytest --cov=src --cov-report=html -p no:logfire                # Generate HTML coverage report (opens htmlcov/index.html)
-
-# Documentation Commands
-uv run mkdocs build                # Build documentation
-uv run mkdocs serve                # Serve documentation locally (http://127.0.0.1:8000)
+make install      # Install dependencies + pre-commit
+make check        # Lint + typecheck + test (MUST PASS)
+make test         # Run unit tests
+make lint         # Run ruff
+make format       # Format with ruff
+make typecheck    # Run mypy
+make test-cov     # Test with coverage
+make docs-build  # Build documentation
+make docs-serve  # Serve documentation locally
 ```
 
-### Test Markers
-
-The project uses pytest markers to categorize tests. See [Testing Guidelines](docs/contributing/testing.md) for details:
-
-- `unit`: Unit tests (mocked, fast)
-- `integration`: Integration tests (real APIs)
-- `slow`: Slow tests
-- `openai`: Tests requiring OpenAI API key
-- `huggingface`: Tests requiring HuggingFace API key
-- `embedding_provider`: Tests requiring API-based embedding providers
-- `local_embeddings`: Tests using local embeddings
-
-**Note**: The `-p no:logfire` flag disables the logfire plugin to avoid conflicts during testing.
-
 ## Code Style & Conventions
 
 ### Type Safety
@@ -163,9 +86,11 @@ The project uses pytest markers to categorize tests. See [Testing Guidelines](do
 - Use `mypy --strict` compliance (no `Any` unless absolutely necessary)
 - Use `TYPE_CHECKING` imports for circular dependencies:
 
-<!--codeinclude-->
-[TYPE_CHECKING Import Pattern](../src/utils/citation_validator.py) start_line:8 end_line:11
-<!--/codeinclude-->
+```python
+from typing import TYPE_CHECKING
+if TYPE_CHECKING:
+    from src.services.embeddings import EmbeddingService
+```
 
 ### Pydantic Models
 
@@ -200,10 +125,10 @@ result = await loop.run_in_executor(None, cpu_bound_function, args)
 
 ### Pre-commit
 
-- Pre-commit hooks run automatically on commit
+- Run `make check` before committing
 - Must pass: lint + typecheck + test-cov
-- Install hooks with: `uv run pre-commit install`
-- Note: `uv sync --all-extras` installs the pre-commit package, but you must run `uv run pre-commit install` separately to set up the git hooks
+- Pre-commit hooks installed via `make install`
+- **CRITICAL**: Make sure you run the full pre-commit checks before opening a PR (not draft), otherwise Obstacle is the Way will lose his mind
 
 ## Error Handling & Logging
 
@@ -211,9 +136,10 @@ result = await loop.run_in_executor(None, cpu_bound_function, args)
 
 Use custom exception hierarchy (`src/utils/exceptions.py`):
 
-<!--codeinclude-->
-[Exception Hierarchy](../src/utils/exceptions.py) start_line:4 end_line:31
-<!--/codeinclude-->
+- `DeepCriticalError` (base)
+- `SearchError` → `RateLimitError`
+- `JudgeError`
+- `ConfigurationError`
 
 ### Error Handling Rules
 
@@ -273,7 +199,7 @@ except httpx.HTTPError as e:
 1. Write failing test in `tests/unit/`
 2. Implement in `src/`
 3. Ensure test passes
-4. Run checks: `uv run ruff check src tests && uv run mypy src && uv run pytest --cov=src --cov-report=term-missing tests/unit/ -v -m "not openai" -p no:logfire`
+4. Run `make check` (lint + typecheck + test)
 
 ### Test Examples
 
@@ -294,8 +220,7 @@ async def test_real_pubmed_search():
 
 ### Test Coverage
 
-- Run `uv run pytest --cov=src --cov-report=term-missing tests/unit/ -v -m "not openai" -p no:logfire` for coverage report
-- Run `uv run pytest --cov=src --cov-report=html -p no:logfire` for HTML coverage report (opens `htmlcov/index.html`)
+- Run `make test-cov` for coverage report
 - Aim for >80% coverage on critical paths
 - Exclude: `__init__.py`, `TYPE_CHECKING` blocks
 
@@ -339,9 +264,11 @@ class MySearchTool:
 - Lazy initialization for optional dependencies (e.g., embeddings, Modal)
 - Check requirements before initialization:
 
-<!--codeinclude-->
-[Check Magentic Requirements](../src/utils/llm_factory.py) start_line:152 end_line:170
-<!--/codeinclude-->
+```python
+def check_magentic_requirements() -> None:
+    if not settings.has_openai_key:
+        raise ConfigurationError("Magentic requires OpenAI")
+```
 
 ### State Management
 
@@ -353,9 +280,11 @@ class MySearchTool:
 
 Use `@lru_cache(maxsize=1)` for singletons:
 
-<!--codeinclude-->
-[Singleton Pattern Example](../src/services/statistical_analyzer.py) start_line:252 end_line:255
-<!--/codeinclude-->
+```python
+@lru_cache(maxsize=1)
+def get_embedding_service() -> EmbeddingService:
+    return EmbeddingService()
+```
 
 - Lazy initialization to avoid requiring dependencies at import time
 
@@ -369,9 +298,22 @@ Use `@lru_cache(maxsize=1)` for singletons:
 
 Example:
 
-<!--codeinclude-->
-[Search Method Docstring Example](../src/tools/pubmed.py) start_line:51 end_line:58
-<!--/codeinclude-->
+```python
+async def search(self, query: str, max_results: int = 10) -> list[Evidence]:
+    """Search PubMed and return evidence.
+
+    Args:
+        query: The search query string
+        max_results: Maximum number of results to return
+
+    Returns:
+        List of Evidence objects
+
+    Raises:
+        SearchError: If the search fails
+        RateLimitError: If we hit rate limits
+    """
+```
 
 ### Code Comments
 
@@ -468,7 +410,7 @@ Example:
 
 ## Pull Request Process
 
-1. Ensure all checks pass: `uv run ruff check src tests && uv run mypy src && uv run pytest --cov=src --cov-report=term-missing tests/unit/ -v -m "not openai" -p no:logfire`
+1. Ensure all checks pass: `make check`
 2. Update documentation if needed
 3. Add tests for new features
 4. Update CHANGELOG if applicable
@@ -476,19 +418,11 @@ Example:
 6. Address review feedback
 7. Wait for approval before merging
 
-## Project Structure
-
-- `src/`: Main source code
-- `tests/`: Test files (`unit/` and `integration/`)
-- `docs/`: Documentation source files (MkDocs)
-- `examples/`: Example usage scripts
-- `pyproject.toml`: Project configuration and dependencies
-- `.pre-commit-config.yaml`: Pre-commit hook configuration
-
 ## Questions?
 
-- Open an issue on [GitHub](https://github.com/DeepCritical/GradioDemo)
-- Check existing [documentation](https://deepcritical.github.io/GradioDemo/)
+- Open an issue on GitHub
+- Check existing documentation
 - Review code examples in the codebase
 
-Thank you for contributing to The DETERMINATOR!
+Thank you for contributing to DeepCritical!
+

docs/contributing/code-quality.md

@@ -0,0 +1,77 @@
+# Code Quality & Documentation
+
+This document outlines code quality standards and documentation requirements.
+
+## Linting
+
+- Ruff with 100-char line length
+- Ignore rules documented in `pyproject.toml`:
+  - `PLR0913`: Too many arguments (agents need many params)
+  - `PLR0912`: Too many branches (complex orchestrator logic)
+  - `PLR0911`: Too many return statements (complex agent logic)
+  - `PLR2004`: Magic values (statistical constants)
+  - `PLW0603`: Global statement (singleton pattern)
+  - `PLC0415`: Lazy imports for optional dependencies
+
+## Type Checking
+
+- `mypy --strict` compliance
+- `ignore_missing_imports = true` (for optional dependencies)
+- Exclude: `reference_repos/`, `examples/`
+- All functions must have complete type annotations
+
+## Pre-commit
+
+- Run `make check` before committing
+- Must pass: lint + typecheck + test-cov
+- Pre-commit hooks installed via `make install`
+
+## Documentation
+
+### Docstrings
+
+- Google-style docstrings for all public functions
+- Include Args, Returns, Raises sections
+- Use type hints in docstrings only if needed for clarity
+
+Example:
+
+```python
+async def search(self, query: str, max_results: int = 10) -> list[Evidence]:
+    """Search PubMed and return evidence.
+
+    Args:
+        query: The search query string
+        max_results: Maximum number of results to return
+
+    Returns:
+        List of Evidence objects
+
+    Raises:
+        SearchError: If the search fails
+        RateLimitError: If we hit rate limits
+    """
+```
+
+### Code Comments
+
+- Explain WHY, not WHAT
+- Document non-obvious patterns (e.g., why `requests` not `httpx` for ClinicalTrials)
+- Mark critical sections: `# CRITICAL: ...`
+- Document rate limiting rationale
+- Explain async patterns when non-obvious
+
+## See Also
+
+- [Code Style](code-style.md) - Code style guidelines
+- [Testing](testing.md) - Testing guidelines
+
+
+
+
+
+
+
+
+
+

docs/contributing/code-style.md

@@ -0,0 +1,57 @@
+# Code Style & Conventions
+
+This document outlines the code style and conventions for DeepCritical.
+
+## Type Safety
+
+- **ALWAYS** use type hints for all function parameters and return types
+- Use `mypy --strict` compliance (no `Any` unless absolutely necessary)
+- Use `TYPE_CHECKING` imports for circular dependencies:
+
+```python
+from typing import TYPE_CHECKING
+if TYPE_CHECKING:
+    from src.services.embeddings import EmbeddingService
+```
+
+## Pydantic Models
+
+- All data exchange uses Pydantic models (`src/utils/models.py`)
+- Models are frozen (`model_config = {"frozen": True}`) for immutability
+- Use `Field()` with descriptions for all model fields
+- Validate with `ge=`, `le=`, `min_length=`, `max_length=` constraints
+
+## Async Patterns
+
+- **ALL** I/O operations must be async (`async def`, `await`)
+- Use `asyncio.gather()` for parallel operations
+- CPU-bound work (embeddings, parsing) must use `run_in_executor()`:
+
+```python
+loop = asyncio.get_running_loop()
+result = await loop.run_in_executor(None, cpu_bound_function, args)
+```
+
+- Never block the event loop with synchronous I/O
+
+## Common Pitfalls
+
+1. **Blocking the event loop**: Never use sync I/O in async functions
+2. **Missing type hints**: All functions must have complete type annotations
+3. **Global mutable state**: Use ContextVar or pass via parameters
+4. **Import errors**: Lazy-load optional dependencies (magentic, modal, embeddings)
+
+## See Also
+
+- [Error Handling](error-handling.md) - Error handling guidelines
+- [Implementation Patterns](implementation-patterns.md) - Common patterns
+
+
+
+
+
+
+
+
+
+

docs/contributing/error-handling.md

@@ -0,0 +1,65 @@
+# Error Handling & Logging
+
+This document outlines error handling and logging conventions for DeepCritical.
+
+## Exception Hierarchy
+
+Use custom exception hierarchy (`src/utils/exceptions.py`):
+
+- `DeepCriticalError` (base)
+- `SearchError` → `RateLimitError`
+- `JudgeError`
+- `ConfigurationError`
+
+## Error Handling Rules
+
+- Always chain exceptions: `raise SearchError(...) from e`
+- Log errors with context using `structlog`:
+
+```python
+logger.error("Operation failed", error=str(e), context=value)
+```
+
+- Never silently swallow exceptions
+- Provide actionable error messages
+
+## Logging
+
+- Use `structlog` for all logging (NOT `print` or `logging`)
+- Import: `import structlog; logger = structlog.get_logger()`
+- Log with structured data: `logger.info("event", key=value)`
+- Use appropriate levels: DEBUG, INFO, WARNING, ERROR
+
+## Logging Examples
+
+```python
+logger.info("Starting search", query=query, tools=[t.name for t in tools])
+logger.warning("Search tool failed", tool=tool.name, error=str(result))
+logger.error("Assessment failed", error=str(e))
+```
+
+## Error Chaining
+
+Always preserve exception context:
+
+```python
+try:
+    result = await api_call()
+except httpx.HTTPError as e:
+    raise SearchError(f"API call failed: {e}") from e
+```
+
+## See Also
+
+- [Code Style](code-style.md) - Code style guidelines
+- [Testing](testing.md) - Testing guidelines
+
+
+
+
+
+
+
+
+
+

docs/contributing/implementation-patterns.md

@@ -0,0 +1,80 @@
+# Implementation Patterns
+
+This document outlines common implementation patterns used in DeepCritical.
+
+## Search Tools
+
+All tools implement `SearchTool` protocol (`src/tools/base.py`):
+
+- Must have `name` property
+- Must implement `async def search(query, max_results) -> list[Evidence]`
+- Use `@retry` decorator from tenacity for resilience
+- Rate limiting: Implement `_rate_limit()` for APIs with limits (e.g., PubMed)
+- Error handling: Raise `SearchError` or `RateLimitError` on failures
+
+Example pattern:
+
+```python
+class MySearchTool:
+    @property
+    def name(self) -> str:
+        return "mytool"
+    
+    @retry(stop=stop_after_attempt(3), wait=wait_exponential(...))
+    async def search(self, query: str, max_results: int = 10) -> list[Evidence]:
+        # Implementation
+        return evidence_list
+```
+
+## Judge Handlers
+
+- Implement `JudgeHandlerProtocol` (`async def assess(question, evidence) -> JudgeAssessment`)
+- Use pydantic-ai `Agent` with `output_type=JudgeAssessment`
+- System prompts in `src/prompts/judge.py`
+- Support fallback handlers: `MockJudgeHandler`, `HFInferenceJudgeHandler`
+- Always return valid `JudgeAssessment` (never raise exceptions)
+
+## Agent Factory Pattern
+
+- Use factory functions for creating agents (`src/agent_factory/`)
+- Lazy initialization for optional dependencies (e.g., embeddings, Modal)
+- Check requirements before initialization:
+
+```python
+def check_magentic_requirements() -> None:
+    if not settings.has_openai_key:
+        raise ConfigurationError("Magentic requires OpenAI")
+```
+
+## State Management
+
+- **Magentic Mode**: Use `ContextVar` for thread-safe state (`src/agents/state.py`)
+- **Simple Mode**: Pass state via function parameters
+- Never use global mutable state (except singletons via `@lru_cache`)
+
+## Singleton Pattern
+
+Use `@lru_cache(maxsize=1)` for singletons:
+
+```python
+@lru_cache(maxsize=1)
+def get_embedding_service() -> EmbeddingService:
+    return EmbeddingService()
+```
+
+- Lazy initialization to avoid requiring dependencies at import time
+
+## See Also
+
+- [Code Style](code-style.md) - Code style guidelines
+- [Error Handling](error-handling.md) - Error handling guidelines
+
+
+
+
+
+
+
+
+
+

docs/contributing/index.md

@@ -0,0 +1,159 @@
+# Contributing to DeepCritical
+
+Thank you for your interest in contributing to DeepCritical! This guide will help you get started.
+
+## Git Workflow
+
+- `main`: Production-ready (GitHub)
+- `dev`: Development integration (GitHub)
+- Use feature branches: `yourname-dev`
+- **NEVER** push directly to `main` or `dev` on HuggingFace
+- GitHub is source of truth; HuggingFace is for deployment
+
+## Development Commands
+
+```bash
+make install      # Install dependencies + pre-commit
+make check        # Lint + typecheck + test (MUST PASS)
+make test         # Run unit tests
+make lint         # Run ruff
+make format       # Format with ruff
+make typecheck    # Run mypy
+make test-cov     # Test with coverage
+```
+
+## Getting Started
+
+1. **Fork the repository** on GitHub
+2. **Clone your fork**:
+   ```bash
+   git clone https://github.com/yourusername/GradioDemo.git
+   cd GradioDemo
+   ```
+3. **Install dependencies**:
+   ```bash
+   make install
+   ```
+4. **Create a feature branch**:
+   ```bash
+   git checkout -b yourname-feature-name
+   ```
+5. **Make your changes** following the guidelines below
+6. **Run checks**:
+   ```bash
+   make check
+   ```
+7. **Commit and push**:
+   ```bash
+   git commit -m "Description of changes"
+   git push origin yourname-feature-name
+   ```
+8. **Create a pull request** on GitHub
+
+## Development Guidelines
+
+### Code Style
+
+- Follow [Code Style Guidelines](code-style.md)
+- All code must pass `mypy --strict`
+- Use `ruff` for linting and formatting
+- Line length: 100 characters
+
+### Error Handling
+
+- Follow [Error Handling Guidelines](error-handling.md)
+- Always chain exceptions: `raise SearchError(...) from e`
+- Use structured logging with `structlog`
+- Never silently swallow exceptions
+
+### Testing
+
+- Follow [Testing Guidelines](testing.md)
+- Write tests before implementation (TDD)
+- Aim for >80% coverage on critical paths
+- Use markers: `unit`, `integration`, `slow`
+
+### Implementation Patterns
+
+- Follow [Implementation Patterns](implementation-patterns.md)
+- Use factory functions for agent/tool creation
+- Implement protocols for extensibility
+- Use singleton pattern with `@lru_cache(maxsize=1)`
+
+### Prompt Engineering
+
+- Follow [Prompt Engineering Guidelines](prompt-engineering.md)
+- Always validate citations
+- Use diverse evidence selection
+- Never trust LLM-generated citations without validation
+
+### Code Quality
+
+- Follow [Code Quality Guidelines](code-quality.md)
+- Google-style docstrings for all public functions
+- Explain WHY, not WHAT in comments
+- Mark critical sections: `# CRITICAL: ...`
+
+## MCP Integration
+
+### MCP Tools
+
+- Functions in `src/mcp_tools.py` for Claude Desktop
+- Full type hints required
+- Google-style docstrings with Args/Returns sections
+- Formatted string returns (markdown)
+
+### Gradio MCP Server
+
+- Enable with `mcp_server=True` in `demo.launch()`
+- Endpoint: `/gradio_api/mcp/`
+- Use `ssr_mode=False` to fix hydration issues in HF Spaces
+
+## Common Pitfalls
+
+1. **Blocking the event loop**: Never use sync I/O in async functions
+2. **Missing type hints**: All functions must have complete type annotations
+3. **Hallucinated citations**: Always validate references
+4. **Global mutable state**: Use ContextVar or pass via parameters
+5. **Import errors**: Lazy-load optional dependencies (magentic, modal, embeddings)
+6. **Rate limiting**: Always implement for external APIs
+7. **Error chaining**: Always use `from e` when raising exceptions
+
+## Key Principles
+
+1. **Type Safety First**: All code must pass `mypy --strict`
+2. **Async Everything**: All I/O must be async
+3. **Test-Driven**: Write tests before implementation
+4. **No Hallucinations**: Validate all citations
+5. **Graceful Degradation**: Support free tier (HF Inference) when no API keys
+6. **Lazy Loading**: Don't require optional dependencies at import time
+7. **Structured Logging**: Use structlog, never print()
+8. **Error Chaining**: Always preserve exception context
+
+## Pull Request Process
+
+1. Ensure all checks pass: `make check`
+2. Update documentation if needed
+3. Add tests for new features
+4. Update CHANGELOG if applicable
+5. Request review from maintainers
+6. Address review feedback
+7. Wait for approval before merging
+
+## Questions?
+
+- Open an issue on GitHub
+- Check existing documentation
+- Review code examples in the codebase
+
+Thank you for contributing to DeepCritical!
+
+
+
+
+
+
+
+
+
+

docs/contributing/prompt-engineering.md

@@ -0,0 +1,65 @@
+# Prompt Engineering & Citation Validation
+
+This document outlines prompt engineering guidelines and citation validation rules.
+
+## Judge Prompts
+
+- System prompt in `src/prompts/judge.py`
+- Format evidence with truncation (1500 chars per item)
+- Handle empty evidence case separately
+- Always request structured JSON output
+- Use `format_user_prompt()` and `format_empty_evidence_prompt()` helpers
+
+## Hypothesis Prompts
+
+- Use diverse evidence selection (MMR algorithm)
+- Sentence-aware truncation (`truncate_at_sentence()`)
+- Format: Drug → Target → Pathway → Effect
+- System prompt emphasizes mechanistic reasoning
+- Use `format_hypothesis_prompt()` with embeddings for diversity
+
+## Report Prompts
+
+- Include full citation details for validation
+- Use diverse evidence selection (n=20)
+- **CRITICAL**: Emphasize citation validation rules
+- Format hypotheses with support/contradiction counts
+- System prompt includes explicit JSON structure requirements
+
+## Citation Validation
+
+- **ALWAYS** validate references before returning reports
+- Use `validate_references()` from `src/utils/citation_validator.py`
+- Remove hallucinated citations (URLs not in evidence)
+- Log warnings for removed citations
+- Never trust LLM-generated citations without validation
+
+## Citation Validation Rules
+
+1. Every reference URL must EXACTLY match a provided evidence URL
+2. Do NOT invent, fabricate, or hallucinate any references
+3. Do NOT modify paper titles, authors, dates, or URLs
+4. If unsure about a citation, OMIT it rather than guess
+5. Copy URLs exactly as provided - do not create similar-looking URLs
+
+## Evidence Selection
+
+- Use `select_diverse_evidence()` for MMR-based selection
+- Balance relevance vs diversity (lambda=0.7 default)
+- Sentence-aware truncation preserves meaning
+- Limit evidence per prompt to avoid context overflow
+
+## See Also
+
+- [Code Quality](code-quality.md) - Code quality guidelines
+- [Error Handling](error-handling.md) - Error handling guidelines
+
+
+
+
+
+
+
+
+
+

docs/contributing/testing.md

@@ -0,0 +1,61 @@
+# Testing Requirements
+
+This document outlines testing requirements and guidelines for DeepCritical.
+
+## Test Structure
+
+- Unit tests in `tests/unit/` (mocked, fast)
+- Integration tests in `tests/integration/` (real APIs, marked `@pytest.mark.integration`)
+- Use markers: `unit`, `integration`, `slow`
+
+## Mocking
+
+- Use `respx` for httpx mocking
+- Use `pytest-mock` for general mocking
+- Mock LLM calls in unit tests (use `MockJudgeHandler`)
+- Fixtures in `tests/conftest.py`: `mock_httpx_client`, `mock_llm_response`
+
+## TDD Workflow
+
+1. Write failing test in `tests/unit/`
+2. Implement in `src/`
+3. Ensure test passes
+4. Run `make check` (lint + typecheck + test)
+
+## Test Examples
+
+```python
+@pytest.mark.unit
+async def test_pubmed_search(mock_httpx_client):
+    tool = PubMedTool()
+    results = await tool.search("metformin", max_results=5)
+    assert len(results) > 0
+    assert all(isinstance(r, Evidence) for r in results)
+
+@pytest.mark.integration
+async def test_real_pubmed_search():
+    tool = PubMedTool()
+    results = await tool.search("metformin", max_results=3)
+    assert len(results) <= 3
+```
+
+## Test Coverage
+
+- Run `make test-cov` for coverage report
+- Aim for >80% coverage on critical paths
+- Exclude: `__init__.py`, `TYPE_CHECKING` blocks
+
+## See Also
+
+- [Code Style](code-style.md) - Code style guidelines
+- [Implementation Patterns](implementation-patterns.md) - Common patterns
+
+
+
+
+
+
+
+
+
+

docs/getting-started/examples.md

@@ -0,0 +1,205 @@
+# Examples
+
+This page provides examples of using DeepCritical for various research tasks.
+
+## Basic Research Query
+
+### Example 1: Drug Information
+
+**Query**:
+```
+What are the latest treatments for Alzheimer's disease?
+```
+
+**What DeepCritical Does**:
+1. Searches PubMed for recent papers
+2. Searches ClinicalTrials.gov for active trials
+3. Evaluates evidence quality
+4. Synthesizes findings into a comprehensive report
+
+### Example 2: Clinical Trial Search
+
+**Query**:
+```
+What clinical trials are investigating metformin for cancer prevention?
+```
+
+**What DeepCritical Does**:
+1. Searches ClinicalTrials.gov for relevant trials
+2. Searches PubMed for supporting literature
+3. Provides trial details and status
+4. Summarizes findings
+
+## Advanced Research Queries
+
+### Example 3: Comprehensive Review
+
+**Query**:
+```
+Review the evidence for using metformin as an anti-aging intervention, 
+including clinical trials, mechanisms of action, and safety profile.
+```
+
+**What DeepCritical Does**:
+1. Uses deep research mode (multi-section)
+2. Searches multiple sources in parallel
+3. Generates sections on:
+   - Clinical trials
+   - Mechanisms of action
+   - Safety profile
+4. Synthesizes comprehensive report
+
+### Example 4: Hypothesis Testing
+
+**Query**:
+```
+Test the hypothesis that regular exercise reduces Alzheimer's disease risk.
+```
+
+**What DeepCritical Does**:
+1. Generates testable hypotheses
+2. Searches for supporting/contradicting evidence
+3. Performs statistical analysis (if Modal configured)
+4. Provides verdict: SUPPORTED, REFUTED, or INCONCLUSIVE
+
+## MCP Tool Examples
+
+### Using search_pubmed
+
+```
+Search PubMed for "CRISPR gene editing cancer therapy"
+```
+
+### Using search_clinical_trials
+
+```
+Find active clinical trials for "diabetes type 2 treatment"
+```
+
+### Using search_all
+
+```
+Search all sources for "COVID-19 vaccine side effects"
+```
+
+### Using analyze_hypothesis
+
+```
+Analyze whether vitamin D supplementation reduces COVID-19 severity
+```
+
+## Code Examples
+
+### Python API Usage
+
+```python
+from src.orchestrator_factory import create_orchestrator
+from src.tools.search_handler import SearchHandler
+from src.agent_factory.judges import create_judge_handler
+
+# Create orchestrator
+search_handler = SearchHandler()
+judge_handler = create_judge_handler()
+orchestrator = create_orchestrator(
+    search_handler=search_handler,
+    judge_handler=judge_handler,
+    config={},
+    mode="advanced"
+)
+
+# Run research query
+query = "What are the latest treatments for Alzheimer's disease?"
+async for event in orchestrator.run(query):
+    print(f"Event: {event.type} - {event.data}")
+```
+
+### Gradio UI Integration
+
+```python
+import gradio as gr
+from src.app import create_research_interface
+
+# Create interface
+interface = create_research_interface()
+
+# Launch
+interface.launch(server_name="0.0.0.0", server_port=7860)
+```
+
+## Research Patterns
+
+### Iterative Research
+
+Single-loop research with search-judge-synthesize cycles:
+
+```python
+from src.orchestrator.research_flow import IterativeResearchFlow
+
+flow = IterativeResearchFlow(
+    search_handler=search_handler,
+    judge_handler=judge_handler,
+    use_graph=False
+)
+
+async for event in flow.run(query):
+    # Handle events
+    pass
+```
+
+### Deep Research
+
+Multi-section parallel research:
+
+```python
+from src.orchestrator.research_flow import DeepResearchFlow
+
+flow = DeepResearchFlow(
+    search_handler=search_handler,
+    judge_handler=judge_handler,
+    use_graph=True
+)
+
+async for event in flow.run(query):
+    # Handle events
+    pass
+```
+
+## Configuration Examples
+
+### Basic Configuration
+
+```bash
+# .env file
+LLM_PROVIDER=openai
+OPENAI_API_KEY=your_key_here
+MAX_ITERATIONS=10
+```
+
+### Advanced Configuration
+
+```bash
+# .env file
+LLM_PROVIDER=anthropic
+ANTHROPIC_API_KEY=your_key_here
+EMBEDDING_PROVIDER=local
+WEB_SEARCH_PROVIDER=duckduckgo
+MAX_ITERATIONS=20
+DEFAULT_TOKEN_LIMIT=200000
+USE_GRAPH_EXECUTION=true
+```
+
+## Next Steps
+
+- Read the [Configuration Guide](../configuration/index.md) for all options
+- Explore the [Architecture Documentation](../architecture/graph-orchestration.md)
+- Check out the [API Reference](../api/agents.md) for programmatic usage
+
+
+
+
+
+
+
+
+
+

docs/getting-started/installation.md

@@ -0,0 +1,144 @@
+# Installation
+
+This guide will help you install and set up DeepCritical on your system.
+
+## Prerequisites
+
+- Python 3.11 or higher
+- `uv` package manager (recommended) or `pip`
+- At least one LLM API key (OpenAI, Anthropic, or HuggingFace)
+
+## Installation Steps
+
+### 1. Install uv (Recommended)
+
+`uv` is a fast Python package installer and resolver. Install it with:
+
+```bash
+pip install uv
+```
+
+### 2. Clone the Repository
+
+```bash
+git clone https://github.com/DeepCritical/GradioDemo.git
+cd GradioDemo
+```
+
+### 3. Install Dependencies
+
+Using `uv` (recommended):
+
+```bash
+uv sync
+```
+
+Using `pip`:
+
+```bash
+pip install -e .
+```
+
+### 4. Install Optional Dependencies
+
+For embeddings support (local sentence-transformers):
+
+```bash
+uv sync --extra embeddings
+```
+
+For Modal sandbox execution:
+
+```bash
+uv sync --extra modal
+```
+
+For Magentic orchestration:
+
+```bash
+uv sync --extra magentic
+```
+
+Install all extras:
+
+```bash
+uv sync --all-extras
+```
+
+### 5. Configure Environment Variables
+
+Create a `.env` file in the project root:
+
+```bash
+# Required: At least one LLM provider
+LLM_PROVIDER=openai  # or "anthropic" or "huggingface"
+OPENAI_API_KEY=your_openai_api_key_here
+
+# Optional: Other services
+NCBI_API_KEY=your_ncbi_api_key_here  # For higher PubMed rate limits
+MODAL_TOKEN_ID=your_modal_token_id
+MODAL_TOKEN_SECRET=your_modal_token_secret
+```
+
+See the [Configuration Guide](../configuration/index.md) for all available options.
+
+### 6. Verify Installation
+
+Run the application:
+
+```bash
+uv run gradio run src/app.py
+```
+
+Open your browser to `http://localhost:7860` to verify the installation.
+
+## Development Setup
+
+For development, install dev dependencies:
+
+```bash
+uv sync --all-extras --dev
+```
+
+Install pre-commit hooks:
+
+```bash
+uv run pre-commit install
+```
+
+## Troubleshooting
+
+### Common Issues
+
+**Import Errors**:
+- Ensure you've installed all required dependencies
+- Check that Python 3.11+ is being used
+
+**API Key Errors**:
+- Verify your `.env` file is in the project root
+- Check that API keys are correctly formatted
+- Ensure at least one LLM provider is configured
+
+**Module Not Found**:
+- Run `uv sync` or `pip install -e .` again
+- Check that you're in the correct virtual environment
+
+**Port Already in Use**:
+- Change the port in `src/app.py` or use environment variable
+- Kill the process using port 7860
+
+## Next Steps
+
+- Read the [Quick Start Guide](quick-start.md)
+- Learn about [MCP Integration](mcp-integration.md)
+- Explore [Examples](examples.md)
+
+
+
+
+
+
+
+
+
+

docs/getting-started/mcp-integration.md

@@ -0,0 +1,211 @@
+# MCP Integration
+
+DeepCritical exposes a Model Context Protocol (MCP) server, allowing you to use its search tools directly from Claude Desktop or other MCP clients.
+
+## What is MCP?
+
+The Model Context Protocol (MCP) is a standard for connecting AI assistants to external tools and data sources. DeepCritical implements an MCP server that exposes its search capabilities as MCP tools.
+
+## MCP Server URL
+
+When running locally:
+
+```
+http://localhost:7860/gradio_api/mcp/
+```
+
+## Claude Desktop Configuration
+
+### 1. Locate Configuration File
+
+**macOS**:
+```
+~/Library/Application Support/Claude/claude_desktop_config.json
+```
+
+**Windows**:
+```
+%APPDATA%\Claude\claude_desktop_config.json
+```
+
+**Linux**:
+```
+~/.config/Claude/claude_desktop_config.json
+```
+
+### 2. Add DeepCritical Server
+
+Edit `claude_desktop_config.json` and add:
+
+```json
+{
+  "mcpServers": {
+    "deepcritical": {
+      "url": "http://localhost:7860/gradio_api/mcp/"
+    }
+  }
+}
+```
+
+### 3. Restart Claude Desktop
+
+Close and restart Claude Desktop for changes to take effect.
+
+### 4. Verify Connection
+
+In Claude Desktop, you should see DeepCritical tools available:
+- `search_pubmed`
+- `search_clinical_trials`
+- `search_biorxiv`
+- `search_all`
+- `analyze_hypothesis`
+
+## Available Tools
+
+### search_pubmed
+
+Search peer-reviewed biomedical literature from PubMed.
+
+**Parameters**:
+- `query` (string): Search query
+- `max_results` (integer, optional): Maximum number of results (default: 10)
+
+**Example**:
+```
+Search PubMed for "metformin diabetes"
+```
+
+### search_clinical_trials
+
+Search ClinicalTrials.gov for interventional studies.
+
+**Parameters**:
+- `query` (string): Search query
+- `max_results` (integer, optional): Maximum number of results (default: 10)
+
+**Example**:
+```
+Search clinical trials for "Alzheimer's disease treatment"
+```
+
+### search_biorxiv
+
+Search bioRxiv/medRxiv preprints via Europe PMC.
+
+**Parameters**:
+- `query` (string): Search query
+- `max_results` (integer, optional): Maximum number of results (default: 10)
+
+**Example**:
+```
+Search bioRxiv for "CRISPR gene editing"
+```
+
+### search_all
+
+Search all sources simultaneously (PubMed, ClinicalTrials.gov, Europe PMC).
+
+**Parameters**:
+- `query` (string): Search query
+- `max_results` (integer, optional): Maximum number of results per source (default: 10)
+
+**Example**:
+```
+Search all sources for "COVID-19 vaccine efficacy"
+```
+
+### analyze_hypothesis
+
+Perform secure statistical analysis using Modal sandboxes.
+
+**Parameters**:
+- `hypothesis` (string): Hypothesis to analyze
+- `data` (string, optional): Data description or code
+
+**Example**:
+```
+Analyze the hypothesis that metformin reduces cancer risk
+```
+
+## Using Tools in Claude Desktop
+
+Once configured, you can ask Claude to use DeepCritical tools:
+
+```
+Use DeepCritical to search PubMed for recent papers on Alzheimer's disease treatments.
+```
+
+Claude will automatically:
+1. Call the appropriate DeepCritical tool
+2. Retrieve results
+3. Use the results in its response
+
+## Troubleshooting
+
+### Connection Issues
+
+**Server Not Found**:
+- Ensure DeepCritical is running (`uv run gradio run src/app.py`)
+- Verify the URL in `claude_desktop_config.json` is correct
+- Check that port 7860 is not blocked by firewall
+
+**Tools Not Appearing**:
+- Restart Claude Desktop after configuration changes
+- Check Claude Desktop logs for errors
+- Verify MCP server is accessible at the configured URL
+
+### Authentication
+
+If DeepCritical requires authentication:
+- Configure API keys in DeepCritical settings
+- Use HuggingFace OAuth login
+- Ensure API keys are valid
+
+## Advanced Configuration
+
+### Custom Port
+
+If running on a different port, update the URL:
+
+```json
+{
+  "mcpServers": {
+    "deepcritical": {
+      "url": "http://localhost:8080/gradio_api/mcp/"
+    }
+  }
+}
+```
+
+### Multiple Instances
+
+You can configure multiple DeepCritical instances:
+
+```json
+{
+  "mcpServers": {
+    "deepcritical-local": {
+      "url": "http://localhost:7860/gradio_api/mcp/"
+    },
+    "deepcritical-remote": {
+      "url": "https://your-server.com/gradio_api/mcp/"
+    }
+  }
+}
+```
+
+## Next Steps
+
+- Learn about [Configuration](../configuration/index.md) for advanced settings
+- Explore [Examples](examples.md) for use cases
+- Read the [Architecture Documentation](../architecture/graph-orchestration.md)
+
+
+
+
+
+
+
+
+
+

docs/getting-started/quick-start.md

@@ -0,0 +1,115 @@
+# Quick Start Guide
+
+Get up and running with DeepCritical in minutes.
+
+## Start the Application
+
+```bash
+uv run gradio run src/app.py
+```
+
+Open your browser to `http://localhost:7860`.
+
+## First Research Query
+
+1. **Enter a Research Question**
+
+   Type your research question in the chat interface, for example:
+   - "What are the latest treatments for Alzheimer's disease?"
+   - "Review the evidence for metformin in cancer prevention"
+   - "What clinical trials are investigating COVID-19 vaccines?"
+
+2. **Submit the Query**
+
+   Click "Submit" or press Enter. The system will:
+   - Generate observations about your query
+   - Identify knowledge gaps
+   - Search multiple sources (PubMed, ClinicalTrials.gov, Europe PMC)
+   - Evaluate evidence quality
+   - Synthesize findings into a report
+
+3. **Review Results**
+
+   Watch the real-time progress in the chat interface:
+   - Search operations and results
+   - Evidence evaluation
+   - Report generation
+   - Final research report with citations
+
+## Authentication
+
+### HuggingFace OAuth (Recommended)
+
+1. Click "Sign in with HuggingFace" at the top of the app
+2. Authorize the application
+3. Your HuggingFace API token will be automatically used
+4. No need to manually enter API keys
+
+### Manual API Key
+
+1. Open the Settings accordion
+2. Enter your API key:
+   - OpenAI API key
+   - Anthropic API key
+   - HuggingFace API key
+3. Click "Save Settings"
+4. Manual keys take priority over OAuth tokens
+
+## Understanding the Interface
+
+### Chat Interface
+
+- **Input**: Enter your research questions here
+- **Messages**: View conversation history and research progress
+- **Streaming**: Real-time updates as research progresses
+
+### Status Indicators
+
+- **Searching**: Active search operations
+- **Evaluating**: Evidence quality assessment
+- **Synthesizing**: Report generation
+- **Complete**: Research finished
+
+### Settings
+
+- **API Keys**: Configure LLM providers
+- **Research Mode**: Choose iterative or deep research
+- **Budget Limits**: Set token, time, and iteration limits
+
+## Example Queries
+
+### Simple Query
+
+```
+What are the side effects of metformin?
+```
+
+### Complex Query
+
+```
+Review the evidence for using metformin as an anti-aging intervention, 
+including clinical trials, mechanisms of action, and safety profile.
+```
+
+### Clinical Trial Query
+
+```
+What are the active clinical trials investigating Alzheimer's disease treatments?
+```
+
+## Next Steps
+
+- Learn about [MCP Integration](mcp-integration.md) to use DeepCritical from Claude Desktop
+- Explore [Examples](examples.md) for more use cases
+- Read the [Configuration Guide](../configuration/index.md) for advanced settings
+- Check out the [Architecture Documentation](../architecture/graph-orchestration.md) to understand how it works
+
+
+
+
+
+
+
+
+
+

docs/index.md

@@ -0,0 +1,63 @@
+# DeepCritical
+
+**AI-Native Drug Repurposing Research Agent**
+
+DeepCritical is a deep research agent system that uses iterative search-and-judge loops to comprehensively answer research questions. The system supports multiple orchestration patterns, graph-based execution, parallel research workflows, and long-running task management with real-time streaming.
+
+## Features
+
+- **Multi-Source Search**: PubMed, ClinicalTrials.gov, Europe PMC (includes bioRxiv/medRxiv)
+- **MCP Integration**: Use our tools from Claude Desktop or any MCP client
+- **HuggingFace OAuth**: Sign in with your HuggingFace account to automatically use your API token
+- **Modal Sandbox**: Secure execution of AI-generated statistical code
+- **LlamaIndex RAG**: Semantic search and evidence synthesis
+- **HuggingFace Inference**: Free tier support with automatic fallback
+- **Strongly Typed Composable Graphs**: Graph-based orchestration with Pydantic AI
+- **Specialized Research Teams of Agents**: Multi-agent coordination for complex research tasks
+
+## Quick Start
+
+```bash
+# Install uv if you haven't already
+pip install uv
+
+# Sync dependencies
+uv sync
+
+# Start the Gradio app
+uv run gradio run src/app.py
+```
+
+Open your browser to `http://localhost:7860`.
+
+For detailed installation and setup instructions, see the [Getting Started Guide](getting-started/installation.md).
+
+## Architecture
+
+DeepCritical uses a Vertical Slice Architecture:
+
+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
+
+The system supports three main research patterns:
+
+- **Iterative Research**: Single research loop with search-judge-synthesize cycles
+- **Deep Research**: Multi-section parallel research with planning and synthesis
+- **Research Team**: Multi-agent coordination using Magentic framework
+
+Learn more about the [Architecture](overview/architecture.md).
+
+## Documentation
+
+- [Overview](overview/architecture.md) - System architecture and design
+- [Getting Started](getting-started/installation.md) - Installation and setup
+- [Configuration](configuration/index.md) - Configuration guide
+- [API Reference](api/agents.md) - API documentation
+- [Contributing](contributing.md) - Development guidelines
+
+## Links
+
+- [GitHub Repository](https://github.com/DeepCritical/GradioDemo)
+- [HuggingFace Space](https://huggingface.co/spaces/DataQuests/DeepCritical)
+

LICENSE.md → docs/license.md

@@ -23,3 +23,13 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
+
+
+
+
+
+
+
+
+
+

docs/overview/architecture.md

@@ -0,0 +1,192 @@
+# Architecture Overview
+
+DeepCritical is a deep research agent system that uses iterative search-and-judge loops to comprehensively answer research questions. The system supports multiple orchestration patterns, graph-based execution, parallel research workflows, and long-running task management with real-time streaming.
+
+## Core Architecture
+
+### Orchestration Patterns
+
+1. **Graph Orchestrator** (`src/orchestrator/graph_orchestrator.py`):
+   - Graph-based execution using Pydantic AI agents as nodes
+   - Supports both iterative and deep research patterns
+   - Node types: Agent, State, Decision, Parallel
+   - Edge types: Sequential, Conditional, Parallel
+   - Conditional routing based on knowledge gaps, budget, and iterations
+   - Parallel execution for concurrent research loops
+   - Event streaming via `AsyncGenerator[AgentEvent]` for real-time UI updates
+   - Fallback to agent chains when graph execution is disabled
+
+2. **Deep Research Flow** (`src/orchestrator/research_flow.py`):
+   - **Pattern**: Planner → Parallel Iterative Loops (one per section) → Synthesis
+   - Uses `PlannerAgent` to break query into report sections
+   - Runs `IterativeResearchFlow` instances in parallel per section via `WorkflowManager`
+   - Synthesizes results using `LongWriterAgent` or `ProofreaderAgent`
+   - Supports both graph execution (`use_graph=True`) and agent chains (`use_graph=False`)
+   - Budget tracking per section and globally
+   - State synchronization across parallel loops
+
+3. **Iterative Research Flow** (`src/orchestrator/research_flow.py`):
+   - **Pattern**: Generate observations → Evaluate gaps → Select tools → Execute → Judge → Continue/Complete
+   - Uses `KnowledgeGapAgent`, `ToolSelectorAgent`, `ThinkingAgent`, `WriterAgent`
+   - `JudgeHandler` assesses evidence sufficiency
+   - Iterates until research complete or constraints met (iterations, time, tokens)
+   - Supports graph execution and agent chains
+
+4. **Magentic Orchestrator** (`src/orchestrator_magentic.py`):
+   - Multi-agent coordination using `agent-framework-core`
+   - ChatAgent pattern with internal LLMs per agent
+   - Uses `MagenticBuilder` with participants: searcher, hypothesizer, judge, reporter
+   - Manager orchestrates agents via `OpenAIChatClient`
+   - Requires OpenAI API key (function calling support)
+   - Event-driven: converts Magentic events to `AgentEvent` for UI streaming
+   - Supports long-running workflows with max rounds and stall/reset handling
+
+5. **Hierarchical Orchestrator** (`src/orchestrator_hierarchical.py`):
+   - Uses `SubIterationMiddleware` with `ResearchTeam` and `LLMSubIterationJudge`
+   - Adapts Magentic ChatAgent to `SubIterationTeam` protocol
+   - Event-driven via `asyncio.Queue` for coordination
+   - Supports sub-iteration patterns for complex research tasks
+
+6. **Legacy Simple Mode** (`src/legacy_orchestrator.py`):
+   - Linear search-judge-synthesize loop
+   - Uses `SearchHandlerProtocol` and `JudgeHandlerProtocol`
+   - Generator-based design yielding `AgentEvent` objects
+   - Backward compatibility for simple use cases
+
+## Long-Running Task Support
+
+The system is designed for long-running research tasks with comprehensive state management and streaming:
+
+1. **Event Streaming**:
+   - All orchestrators yield `AgentEvent` objects via `AsyncGenerator`
+   - Real-time UI updates through Gradio chat interface
+   - Event types: `started`, `searching`, `search_complete`, `judging`, `judge_complete`, `looping`, `synthesizing`, `hypothesizing`, `complete`, `error`
+   - Metadata includes iteration numbers, tool names, result counts, durations
+
+2. **Budget Tracking** (`src/middleware/budget_tracker.py`):
+   - Per-loop and global budget management
+   - Tracks: tokens, time (seconds), iterations
+   - Budget enforcement at decision nodes
+   - Token estimation (~4 chars per token)
+   - Early termination when budgets exceeded
+   - Budget summaries for monitoring
+
+3. **Workflow Manager** (`src/middleware/workflow_manager.py`):
+   - Coordinates parallel research loops
+   - Tracks loop status: `pending`, `running`, `completed`, `failed`, `cancelled`
+   - Synchronizes evidence between loops and global state
+   - Handles errors per loop (doesn't fail all if one fails)
+   - Supports loop cancellation and timeout handling
+   - Evidence deduplication across parallel loops
+
+4. **State Management** (`src/middleware/state_machine.py`):
+   - Thread-safe isolation using `ContextVar` for concurrent requests
+   - `WorkflowState` tracks: evidence, conversation history, embedding service
+   - Evidence deduplication by URL
+   - Semantic search via embedding service
+   - State persistence across long-running workflows
+   - Supports both iterative and deep research patterns
+
+5. **Gradio UI** (`src/app.py`):
+   - Real-time streaming of research progress
+   - Accordion-based UI for pending/done operations
+   - OAuth integration (HuggingFace)
+   - Multiple backend support (API keys, free tier)
+   - Handles long-running tasks with progress indicators
+   - Event accumulation for pending operations
+
+## Graph Architecture
+
+The graph orchestrator (`src/orchestrator/graph_orchestrator.py`) implements a flexible graph-based execution model:
+
+**Node Types**:
+
+- **Agent Nodes**: Execute Pydantic AI agents (e.g., `KnowledgeGapAgent`, `ToolSelectorAgent`)
+- **State Nodes**: Update or read workflow state (evidence, conversation)
+- **Decision Nodes**: Make routing decisions (research complete?, budget exceeded?)
+- **Parallel Nodes**: Execute multiple nodes concurrently (parallel research loops)
+
+**Edge Types**:
+
+- **Sequential Edges**: Always traversed (no condition)
+- **Conditional Edges**: Traversed based on condition (e.g., if research complete → writer, else → tool selector)
+- **Parallel Edges**: Used for parallel execution branches
+
+**Graph Patterns**:
+
+- **Iterative Graph**: `[Input] → [Thinking] → [Knowledge Gap] → [Decision: Complete?] → [Tool Selector] or [Writer]`
+- **Deep Research Graph**: `[Input] → [Planner] → [Parallel Iterative Loops] → [Synthesizer]`
+
+**Execution Flow**:
+
+1. Graph construction from nodes and edges
+2. Graph validation (no cycles, all nodes reachable)
+3. Graph execution from entry node
+4. Node execution based on type
+5. Edge evaluation for next node(s)
+6. Parallel execution via `asyncio.gather()`
+7. State updates at state nodes
+8. Event streaming for UI
+
+## Key Components
+
+- **Orchestrators**: Multiple orchestration patterns (`src/orchestrator/`, `src/orchestrator_*.py`)
+- **Research Flows**: Iterative and deep research patterns (`src/orchestrator/research_flow.py`)
+- **Graph Builder**: Graph construction utilities (`src/agent_factory/graph_builder.py`)
+- **Agents**: Pydantic AI agents (`src/agents/`, `src/agent_factory/agents.py`)
+- **Search Tools**: PubMed, ClinicalTrials.gov, Europe PMC, RAG (`src/tools/`)
+- **Judge Handler**: LLM-based evidence assessment (`src/agent_factory/judges.py`)
+- **Embeddings**: Semantic search & deduplication (`src/services/embeddings.py`)
+- **Statistical Analyzer**: Modal sandbox execution (`src/services/statistical_analyzer.py`)
+- **Middleware**: State management, budget tracking, workflow coordination (`src/middleware/`)
+- **MCP Tools**: Claude Desktop integration (`src/mcp_tools.py`)
+- **Gradio UI**: Web interface with MCP server and streaming (`src/app.py`)
+
+## Research Team & Parallel Execution
+
+The system supports complex research workflows through:
+
+1. **WorkflowManager**: Coordinates multiple parallel research loops
+   - Creates and tracks `ResearchLoop` instances
+   - Runs loops in parallel via `asyncio.gather()`
+   - Synchronizes evidence to global state
+   - Handles loop failures gracefully
+
+2. **Deep Research Pattern**: Breaks complex queries into sections
+   - Planner creates report outline with sections
+   - Each section runs as independent iterative research loop
+   - Loops execute in parallel
+   - Evidence shared across loops via global state
+   - Final synthesis combines all section results
+
+3. **State Synchronization**: Thread-safe evidence sharing
+   - Evidence deduplication by URL
+   - Global state accessible to all loops
+   - Semantic search across all collected evidence
+   - Conversation history tracking per iteration
+
+## Configuration & Modes
+
+- **Orchestrator Factory** (`src/orchestrator_factory.py`):
+  - Auto-detects mode: "advanced" if OpenAI key available, else "simple"
+  - Supports explicit mode selection: "simple", "magentic", "advanced"
+  - Lazy imports for optional dependencies
+
+- **Research Modes**:
+  - `iterative`: Single research loop
+  - `deep`: Multi-section parallel research
+  - `auto`: Auto-detect based on query complexity
+
+- **Execution Modes**:
+  - `use_graph=True`: Graph-based execution (parallel, conditional routing)
+  - `use_graph=False`: Agent chains (sequential, backward compatible)
+
+
+
+
+
+
+
+
+
+

docs/overview/features.md

@@ -0,0 +1,144 @@
+# Features
+
+DeepCritical provides a comprehensive set of features for AI-assisted research:
+
+## Core Features
+
+### Multi-Source Search
+
+- **PubMed**: Search peer-reviewed biomedical literature via NCBI E-utilities
+- **ClinicalTrials.gov**: Search interventional clinical trials
+- **Europe PMC**: Search preprints and peer-reviewed articles (includes bioRxiv/medRxiv)
+- **RAG**: Semantic search within collected evidence using LlamaIndex
+
+### MCP Integration
+
+- **Model Context Protocol**: Expose search tools via MCP server
+- **Claude Desktop**: Use DeepCritical tools directly from Claude Desktop
+- **MCP Clients**: Compatible with any MCP-compatible client
+
+### Authentication
+
+- **HuggingFace OAuth**: Sign in with HuggingFace account for automatic API token usage
+- **Manual API Keys**: Support for OpenAI, Anthropic, and HuggingFace API keys
+- **Free Tier Support**: Automatic fallback to HuggingFace Inference API
+
+### Secure Code Execution
+
+- **Modal Sandbox**: Secure execution of AI-generated statistical code
+- **Isolated Environment**: Network isolation and package version pinning
+- **Safe Execution**: Prevents malicious code execution
+
+### Semantic Search & RAG
+
+- **LlamaIndex Integration**: Advanced RAG capabilities
+- **Vector Storage**: ChromaDB for embedding storage
+- **Semantic Deduplication**: Automatic detection of similar evidence
+- **Embedding Service**: Local sentence-transformers (no API key required)
+
+### Orchestration Patterns
+
+- **Graph-Based Execution**: Flexible graph orchestration with conditional routing
+- **Parallel Research Loops**: Run multiple research tasks concurrently
+- **Iterative Research**: Single-loop research with search-judge-synthesize cycles
+- **Deep Research**: Multi-section parallel research with planning and synthesis
+- **Magentic Orchestration**: Multi-agent coordination using Microsoft Agent Framework
+
+### Real-Time Streaming
+
+- **Event Streaming**: Real-time updates via `AsyncGenerator[AgentEvent]`
+- **Progress Tracking**: Monitor research progress with detailed event metadata
+- **UI Integration**: Seamless integration with Gradio chat interface
+
+### Budget Management
+
+- **Token Budget**: Track and limit LLM token usage
+- **Time Budget**: Enforce time limits per research loop
+- **Iteration Budget**: Limit maximum iterations
+- **Per-Loop Budgets**: Independent budgets for parallel research loops
+
+### State Management
+
+- **Thread-Safe Isolation**: ContextVar-based state management
+- **Evidence Deduplication**: Automatic URL-based deduplication
+- **Conversation History**: Track iteration history and agent interactions
+- **State Synchronization**: Share evidence across parallel loops
+
+## Advanced Features
+
+### Agent System
+
+- **Pydantic AI Agents**: Type-safe agent implementation
+- **Structured Output**: Pydantic models for agent responses
+- **Agent Factory**: Centralized agent creation with fallback support
+- **Specialized Agents**: Knowledge gap, tool selector, writer, proofreader, and more
+
+### Search Tools
+
+- **Rate Limiting**: Built-in rate limiting for external APIs
+- **Retry Logic**: Automatic retry with exponential backoff
+- **Query Preprocessing**: Automatic query enhancement and synonym expansion
+- **Evidence Conversion**: Automatic conversion to structured Evidence objects
+
+### Error Handling
+
+- **Custom Exceptions**: Hierarchical exception system
+- **Error Chaining**: Preserve exception context
+- **Structured Logging**: Comprehensive logging with structlog
+- **Graceful Degradation**: Fallback handlers for missing dependencies
+
+### Configuration
+
+- **Pydantic Settings**: Type-safe configuration management
+- **Environment Variables**: Support for `.env` files
+- **Validation**: Automatic configuration validation
+- **Flexible Providers**: Support for multiple LLM and embedding providers
+
+### Testing
+
+- **Unit Tests**: Comprehensive unit test coverage
+- **Integration Tests**: Real API integration tests
+- **Mock Support**: Extensive mocking utilities
+- **Coverage Reports**: Code coverage tracking
+
+## UI Features
+
+### Gradio Interface
+
+- **Real-Time Chat**: Interactive chat interface
+- **Streaming Updates**: Live progress updates
+- **Accordion UI**: Organized display of pending/done operations
+- **OAuth Integration**: Seamless HuggingFace authentication
+
+### MCP Server
+
+- **RESTful API**: HTTP-based MCP server
+- **Tool Discovery**: Automatic tool registration
+- **Request Handling**: Async request processing
+- **Error Responses**: Structured error responses
+
+## Development Features
+
+### Code Quality
+
+- **Type Safety**: Full type hints with mypy strict mode
+- **Linting**: Ruff for code quality
+- **Formatting**: Automatic code formatting
+- **Pre-commit Hooks**: Automated quality checks
+
+### Documentation
+
+- **Comprehensive Docs**: Detailed documentation for all components
+- **Code Examples**: Extensive code examples
+- **Architecture Diagrams**: Visual architecture documentation
+- **API Reference**: Complete API documentation
+
+
+
+
+
+
+
+
+
+

docs/overview/quick-start.md

@@ -0,0 +1,82 @@
+# Quick Start
+
+Get started with DeepCritical in minutes.
+
+## Installation
+
+```bash
+# Install uv if you haven't already
+pip install uv
+
+# Sync dependencies
+uv sync
+```
+
+## Run the UI
+
+```bash
+# Start the Gradio app
+uv run gradio run src/app.py
+```
+
+Open your browser to `http://localhost:7860`.
+
+## Basic Usage
+
+### 1. Authentication (Optional)
+
+**HuggingFace OAuth Login**:
+- Click the "Sign in with HuggingFace" button at the top of the app
+- Your HuggingFace API token will be automatically used for AI inference
+- No need to manually enter API keys when logged in
+
+**Manual API Key (BYOK)**:
+- Provide your own API key in the Settings accordion
+- Supports HuggingFace, OpenAI, or Anthropic API keys
+- Manual keys take priority over OAuth tokens
+
+### 2. Start a Research Query
+
+1. Enter your research question in the chat interface
+2. Click "Submit" or press Enter
+3. Watch the real-time progress as the system:
+   - Generates observations
+   - Identifies knowledge gaps
+   - Searches multiple sources
+   - Evaluates evidence
+   - Synthesizes findings
+4. Review the final research report
+
+### 3. MCP Integration (Optional)
+
+Connect DeepCritical to Claude Desktop:
+
+1. Add to your `claude_desktop_config.json`:
+```json
+{
+  "mcpServers": {
+    "deepcritical": {
+      "url": "http://localhost:7860/gradio_api/mcp/"
+    }
+  }
+}
+```
+
+2. Restart Claude Desktop
+3. Use DeepCritical tools directly from Claude Desktop
+
+## Available Tools
+
+- `search_pubmed`: Search peer-reviewed biomedical literature
+- `search_clinical_trials`: Search ClinicalTrials.gov
+- `search_biorxiv`: Search bioRxiv/medRxiv preprints
+- `search_all`: Search all sources simultaneously
+- `analyze_hypothesis`: Secure statistical analysis using Modal sandboxes
+
+## Next Steps
+
+- Read the [Installation Guide](../getting-started/installation.md) for detailed setup
+- Learn about [Configuration](../configuration/index.md)
+- Explore the [Architecture](../architecture/graph-orchestration.md)
+- Check out [Examples](../getting-started/examples.md)
+

docs/team.md

@@ -0,0 +1,40 @@
+# Team
+
+DeepCritical is developed by a team of researchers and developers working on AI-assisted research.
+
+## Team Members
+
+### The-Obstacle-Is-The-Way
+
+- GitHub: [The-Obstacle-Is-The-Way](https://github.com/The-Obstacle-Is-The-Way)
+
+### MarioAderman
+
+- GitHub: [MarioAderman](https://github.com/MarioAderman)
+
+### Josephrp
+
+- GitHub: [Josephrp](https://github.com/Josephrp)
+
+## About
+
+The DeepCritical team met online in the Alzheimer's Critical Literature Review Group in the Hugging Science initiative. We're building the agent framework we want to use for AI-assisted research to turn the vast amounts of clinical data into cures.
+
+## Contributing
+
+We welcome contributions! See the [Contributing Guide](contributing/index.md) for details.
+
+## Links
+
+- [GitHub Repository](https://github.com/DeepCritical/GradioDemo)
+- [HuggingFace Space](https://huggingface.co/spaces/DataQuests/DeepCritical)
+
+
+
+
+
+
+
+
+
+

examples/README.md

@@ -0,0 +1,184 @@
+# DeepCritical Examples
+
+**NO MOCKS. NO FAKE DATA. REAL SCIENCE.**
+
+These demos run the REAL drug repurposing research pipeline with actual API calls.
+
+---
+
+## Prerequisites
+
+You MUST have API keys configured:
+
+```bash
+# Copy the example and add your keys
+cp .env.example .env
+
+# Required (pick one):
+OPENAI_API_KEY=sk-...
+ANTHROPIC_API_KEY=sk-ant-...
+
+# Optional (higher PubMed rate limits):
+NCBI_API_KEY=your-key
+```
+
+---
+
+## Examples
+
+### 1. Search Demo (No LLM Required)
+
+Demonstrates REAL parallel search across PubMed, ClinicalTrials.gov, and Europe PMC.
+
+```bash
+uv run python examples/search_demo/run_search.py "metformin cancer"
+```
+
+**What's REAL:**
+- Actual NCBI E-utilities API calls (PubMed)
+- Actual ClinicalTrials.gov API calls
+- Actual Europe PMC API calls (includes preprints)
+- Real papers, real trials, real preprints
+
+---
+
+### 2. Embeddings Demo (No LLM Required)
+
+Demonstrates REAL semantic search and deduplication.
+
+```bash
+uv run python examples/embeddings_demo/run_embeddings.py
+```
+
+**What's REAL:**
+- Actual sentence-transformers model (all-MiniLM-L6-v2)
+- Actual ChromaDB vector storage
+- Real cosine similarity computations
+- Real semantic deduplication
+
+---
+
+### 3. Orchestrator Demo (LLM Required)
+
+Demonstrates the REAL search-judge-synthesize loop.
+
+```bash
+uv run python examples/orchestrator_demo/run_agent.py "metformin cancer"
+uv run python examples/orchestrator_demo/run_agent.py "aspirin alzheimer" --iterations 5
+```
+
+**What's REAL:**
+- Real PubMed + ClinicalTrials + Europe PMC searches
+- Real LLM judge evaluating evidence quality
+- Real iterative refinement based on LLM decisions
+- Real research synthesis
+
+---
+
+### 4. Magentic Demo (OpenAI Required)
+
+Demonstrates REAL multi-agent coordination using Microsoft Agent Framework.
+
+```bash
+# Requires OPENAI_API_KEY specifically
+uv run python examples/orchestrator_demo/run_magentic.py "metformin cancer"
+```
+
+**What's REAL:**
+- Real MagenticBuilder orchestration
+- Real SearchAgent, JudgeAgent, HypothesisAgent, ReportAgent
+- Real manager-based coordination
+
+---
+
+### 5. Hypothesis Demo (LLM Required)
+
+Demonstrates REAL mechanistic hypothesis generation.
+
+```bash
+uv run python examples/hypothesis_demo/run_hypothesis.py "metformin Alzheimer's"
+uv run python examples/hypothesis_demo/run_hypothesis.py "sildenafil heart failure"
+```
+
+**What's REAL:**
+- Real PubMed + Web search first
+- Real embedding-based deduplication
+- Real LLM generating Drug -> Target -> Pathway -> Effect chains
+- Real knowledge gap identification
+
+---
+
+### 6. Full-Stack Demo (LLM Required)
+
+**THE COMPLETE PIPELINE** - All phases working together.
+
+```bash
+uv run python examples/full_stack_demo/run_full.py "metformin Alzheimer's"
+uv run python examples/full_stack_demo/run_full.py "sildenafil heart failure" -i 3
+```
+
+**What's REAL:**
+1. Real PubMed + ClinicalTrials + Europe PMC evidence collection
+2. Real embedding-based semantic deduplication
+3. Real LLM mechanistic hypothesis generation
+4. Real LLM evidence quality assessment
+5. Real LLM structured scientific report generation
+
+Output: Publication-quality research report with validated citations.
+
+---
+
+## API Key Requirements
+
+| Example | LLM Required | Keys |
+|---------|--------------|------|
+| search_demo | No | Optional: `NCBI_API_KEY` |
+| embeddings_demo | No | None |
+| orchestrator_demo | Yes | `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` |
+| run_magentic | Yes | `OPENAI_API_KEY` (Magentic requires OpenAI) |
+| hypothesis_demo | Yes | `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` |
+| full_stack_demo | Yes | `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` |
+
+---
+
+## Architecture
+
+```text
+User Query
+    |
+    v
+[REAL Search] --> PubMed + ClinicalTrials + Europe PMC APIs
+    |
+    v
+[REAL Embeddings] --> Actual sentence-transformers
+    |
+    v
+[REAL Hypothesis] --> Actual LLM reasoning
+    |
+    v
+[REAL Judge] --> Actual LLM assessment
+    |
+    +---> Need more? --> Loop back to Search
+    |
+    +---> Sufficient --> Continue
+    |
+    v
+[REAL Report] --> Actual LLM synthesis
+    |
+    v
+Publication-Quality Research Report
+```
+
+---
+
+## Why No Mocks?
+
+> "Authenticity is the feature."
+
+Mocks belong in `tests/unit/`, not in demos. When you run these examples, you see:
+- Real papers from real databases
+- Real AI reasoning about real evidence
+- Real scientific hypotheses
+- Real research reports
+
+This is what DeepCritical actually does. No fake data. No canned responses.

examples/embeddings_demo/run_embeddings.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python3
+"""
+Demo: Semantic Search & Deduplication (Phase 6).
+
+This script demonstrates embedding-based capabilities using REAL data:
+- Fetches REAL abstracts from PubMed
+- Embeds text with sentence-transformers
+- Performs semantic deduplication on LIVE research data
+
+Usage:
+    uv run python examples/embeddings_demo/run_embeddings.py
+"""
+
+import asyncio
+
+from src.services.embeddings import EmbeddingService
+from src.tools.pubmed import PubMedTool
+
+
+def create_fresh_service(name_suffix: str = "") -> EmbeddingService:
+    """Create a fresh embedding service with unique collection name."""
+    import uuid
+
+    # Create service with unique collection by modifying the internal collection
+    service = EmbeddingService.__new__(EmbeddingService)
+    service._model = __import__("sentence_transformers").SentenceTransformer("all-MiniLM-L6-v2")
+    service._client = __import__("chromadb").Client()
+    collection_name = f"demo_{name_suffix}_{uuid.uuid4().hex[:8]}"
+    service._collection = service._client.create_collection(
+        name=collection_name, metadata={"hnsw:space": "cosine"}
+    )
+    return service
+
+
+async def demo_real_pipeline() -> None:
+    """Run the demo using REAL PubMed data."""
+    print("\n" + "=" * 60)
+    print("DeepCritical Embeddings Demo (REAL DATA)")
+    print("=" * 60)
+
+    # 1. Fetch Real Data
+    query = "metformin mechanism of action"
+    print(f"\n[1] Fetching real papers for: '{query}'...")
+    pubmed = PubMedTool()
+    # Fetch enough results to likely get some overlap/redundancy
+    evidence = await pubmed.search(query, max_results=10)
+
+    print(f"    Found {len(evidence)} papers.")
+    print("\n    Sample Titles:")
+    for i, e in enumerate(evidence[:3], 1):
+        print(f"    {i}. {e.citation.title[:80]}...")
+
+    # 2. Embed Data
+    print("\n[2] Embedding abstracts (sentence-transformers)...")
+    service = create_fresh_service("real_demo")
+
+    # 3. Semantic Search
+    print("\n[3] Semantic Search Demo")
+    print("    Indexing evidence...")
+    for e in evidence:
+        # Use URL as ID for uniqueness
+        await service.add_evidence(
+            evidence_id=e.citation.url,
+            content=e.content,
+            metadata={
+                "source": e.citation.source,
+                "title": e.citation.title,
+                "date": e.citation.date,
+            },
+        )
+
+    semantic_query = "activation of AMPK pathway"
+    print(f"    Searching for concept: '{semantic_query}'")
+    results = await service.search_similar(semantic_query, n_results=2)
+
+    print("    Top matches:")
+    for i, r in enumerate(results, 1):
+        similarity = 1 - r["distance"]
+        print(f"    {i}. [{similarity:.1%} match] {r['metadata']['title'][:70]}...")
+
+    # 4. Semantic Deduplication
+    print("\n[4] Semantic Deduplication Demo")
+    # Create a FRESH service for deduplication so we don't clash with Step 3's index
+    dedup_service = create_fresh_service("dedup_demo")
+
+    print("    Checking for redundant papers (threshold=0.85)...")
+
+    # To force a duplicate for demo purposes, let's double the evidence list
+    # simulating finding the same papers again or very similar ones
+    duplicated_evidence = evidence + evidence[:2]
+    print(f"    Input pool: {len(duplicated_evidence)} items (with artificial duplicates added)")
+
+    unique = await dedup_service.deduplicate(duplicated_evidence, threshold=0.85)
+
+    print(f"    Output pool: {len(unique)} unique items")
+    print(f"    Removed {len(duplicated_evidence) - len(unique)} duplicates.")
+
+    print("\n" + "=" * 60)
+    print("Demo complete! Verified with REAL PubMed data.")
+    print("=" * 60 + "\n")
+
+
+if __name__ == "__main__":
+    asyncio.run(demo_real_pipeline())