fix: repair Gradio accordion bug and cleanup env vars

- Unwrapped ChatInterface from gr.Blocks to fix settings accordion state (fixes P1_GRADIO_SETTINGS_CLEANUP).
- Updated .env.example with missing variables and removed dead ones.
- Updated documentation for the fix.

.env.example

@@ -8,8 +8,16 @@ OPENAI_API_KEY=sk-your-key-here
 ANTHROPIC_API_KEY=sk-ant-your-key-here
 
 # Model names (optional - sensible defaults)
-OPENAI_MODEL=gpt-5.1
-ANTHROPIC_MODEL=claude-sonnet-4-5-20250929
+OPENAI_MODEL=gpt-4-turbo
+ANTHROPIC_MODEL=claude-3-5-sonnet-20240620
+
+# ============== 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) ==============
 
@@ -20,7 +28,7 @@ ANTHROPIC_MODEL=claude-sonnet-4-5-20250929
 # WITH HF_TOKEN: Uses Llama 3.1 8B Instruct (requires accepting license)
 #
 # For HuggingFace Spaces deployment:
-#   Set this as a "Secret" in Space Settings → Variables and secrets
+#   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
@@ -36,9 +44,5 @@ LOG_LEVEL=INFO
 # PubMed (optional - higher rate limits)
 NCBI_API_KEY=your-ncbi-key-here
 
-# Modal Sandbox (optional - for secure code execution)
-MODAL_TOKEN_ID=ak-your-modal-token-id-here
-MODAL_TOKEN_SECRET=your-modal-token-secret-here
-
 # Vector Database (optional - for LlamaIndex RAG)
 CHROMA_DB_PATH=./chroma_db

docs/brainstorming/01_PUBMED_IMPROVEMENTS.md

@@ -0,0 +1,125 @@
+# PubMed Tool: Current State & Future Improvements
+
+**Status**: Currently Implemented
+**Priority**: High (Core Data Source)
+
+---
+
+## Current Implementation
+
+### What We Have (`src/tools/pubmed.py`)
+
+- Basic E-utilities search via `esearch.fcgi` and `efetch.fcgi`
+- Query preprocessing (strips question words, expands synonyms)
+- Returns: title, abstract, authors, journal, PMID
+- Rate limiting: None implemented (relying on NCBI defaults)
+
+### Current Limitations
+
+1. **No Full-Text Access**: Only retrieves abstracts, not full paper text
+2. **No Rate Limiting**: Risk of being blocked by NCBI
+3. **No BioC Format**: Missing structured full-text extraction
+4. **No Figure Retrieval**: No supplementary materials access
+5. **No PMC Integration**: Missing open-access full-text via PMC
+
+---
+
+## Reference Implementation (DeepCritical Reference Repo)
+
+The reference repo at `reference_repos/DeepCritical/DeepResearch/src/tools/bioinformatics_tools.py` has a more sophisticated implementation:
+
+### Features We're Missing
+
+```python
+# Rate limiting (lines 47-50)
+from limits import parse
+from limits.storage import MemoryStorage
+from limits.strategies import MovingWindowRateLimiter
+
+storage = MemoryStorage()
+limiter = MovingWindowRateLimiter(storage)
+rate_limit = parse("3/second")  # NCBI allows 3/sec without API key, 10/sec with
+
+# Full-text via BioC format (lines 108-120)
+def _get_fulltext(pmid: int) -> dict[str, Any] | None:
+    pmid_url = f"https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/{pmid}/unicode"
+    # Returns structured JSON with full text for open-access papers
+
+# Figure retrieval via Europe PMC (lines 123-149)
+def _get_figures(pmcid: str) -> dict[str, str]:
+    suppl_url = f"https://www.ebi.ac.uk/europepmc/webservices/rest/{pmcid}/supplementaryFiles"
+    # Returns base64-encoded images from supplementary materials
+```
+
+---
+
+## Recommended Improvements
+
+### Phase 1: Rate Limiting (Critical)
+
+```python
+# Add to src/tools/pubmed.py
+from limits import parse
+from limits.storage import MemoryStorage
+from limits.strategies import MovingWindowRateLimiter
+
+storage = MemoryStorage()
+limiter = MovingWindowRateLimiter(storage)
+
+# With NCBI_API_KEY: 10/sec, without: 3/sec
+def get_rate_limit():
+    if settings.ncbi_api_key:
+        return parse("10/second")
+    return parse("3/second")
+```
+
+**Dependencies**: `pip install limits`
+
+### Phase 2: Full-Text Retrieval
+
+```python
+async def get_fulltext(pmid: str) -> str | None:
+    """Get full text for open-access papers via BioC API."""
+    url = f"https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/{pmid}/unicode"
+    # Only works for PMC papers (open access)
+```
+
+### Phase 3: PMC ID Resolution
+
+```python
+async def get_pmc_id(pmid: str) -> str | None:
+    """Convert PMID to PMCID for full-text access."""
+    url = f"https://www.ncbi.nlm.nih.gov/pmc/utils/idconv/v1.0/?ids={pmid}&format=json"
+```
+
+---
+
+## Python Libraries to Consider
+
+| Library | Purpose | Notes |
+|---------|---------|-------|
+| [Biopython](https://biopython.org/) | `Bio.Entrez` module | Official, well-maintained |
+| [PyMed](https://pypi.org/project/pymed/) | PubMed wrapper | Simpler API, less control |
+| [metapub](https://pypi.org/project/metapub/) | Full-featured | Tested on 1/3 of PubMed |
+| [limits](https://pypi.org/project/limits/) | Rate limiting | Used by reference repo |
+
+---
+
+## API Endpoints Reference
+
+| Endpoint | Purpose | Rate Limit |
+|----------|---------|------------|
+| `esearch.fcgi` | Search for PMIDs | 3/sec (10 with key) |
+| `efetch.fcgi` | Fetch metadata | 3/sec (10 with key) |
+| `esummary.fcgi` | Quick metadata | 3/sec (10 with key) |
+| `pmcoa.cgi/BioC_json` | Full text (PMC only) | Unknown |
+| `idconv/v1.0` | PMID ↔ PMCID | Unknown |
+
+---
+
+## Sources
+
+- [PubMed E-utilities Documentation](https://www.ncbi.nlm.nih.gov/books/NBK25501/)
+- [NCBI BioC API](https://www.ncbi.nlm.nih.gov/research/bionlp/APIs/)
+- [Searching PubMed with Python](https://marcobonzanini.com/2015/01/12/searching-pubmed-with-python/)
+- [PyMed on PyPI](https://pypi.org/project/pymed/)

docs/bugs/P1_GRADIO_SETTINGS_CLEANUP.md

@@ -3,131 +3,79 @@
 **Priority**: P1 (UX Bug)
 **Status**: OPEN
 **Date**: 2025-11-27
+**Target Component**: `src/app.py`
 
 ---
 
-## Bug Description
+## 1. Problem Description
 
-The "Settings" accordion in the Gradio UI does not collapse/hide its content. Even when the accordion arrow shows "collapsed" state, all settings (Orchestrator Mode, API Key, API Provider) remain visible.
+The "Settings" accordion in the Gradio UI (containing Orchestrator Mode, API Key, Provider) fails to collapse, even when configured with `open=False`. It remains permanently expanded, cluttering the interface and obscuring the chat history.
 
----
-
-## Root Cause
+### Symptoms
+- Accordion arrow toggles visually, but content remains visible.
+- Occurs in both local development (`uv run src/app.py`) and HuggingFace Spaces.
 
-**Known Gradio Bug**: `additional_inputs_accordion` does not work correctly when `ChatInterface` is used inside `gr.Blocks()`.
+---
 
-**GitHub Issue**: [gradio-app/gradio#8861](https://github.com/gradio-app/gradio/issues/8861)
-> "Is there any subsequent plan to support gr.ChatInterface inheritance under gr.Block()? Currently using accordion is not working well."
+## 2. Root Cause Analysis
 
-**Our Code** (`src/app.py` lines 196-250):
-```python
-with gr.Blocks(...) as demo:  # <-- Using gr.Blocks wrapper
-    gr.ChatInterface(
-        ...
-        additional_inputs_accordion=gr.Accordion(label="⚙️ Settings", open=False),
-        additional_inputs=[...],
-    )
-```
+**Definitive Cause**: Nested `Blocks` Context Bug.
+`gr.ChatInterface` is itself a high-level abstraction that creates a `gr.Blocks` context. Wrapping `gr.ChatInterface` inside an external `with gr.Blocks():` context causes event listener conflicts, specifically breaking the JavaScript state management for `additional_inputs_accordion`.
 
-The `additional_inputs_accordion` parameter is designed for standalone `ChatInterface`, but breaks when wrapped in `gr.Blocks()`.
+**Reference**: [Gradio Issue #8861](https://github.com/gradio-app/gradio/issues/8861) confirms that `additional_inputs_accordion` malfunctions when `ChatInterface` is not the top-level block.
 
 ---
 
-## Evidence
+## 3. Solution Strategy: "The Unwrap Fix"
 
-- Accordion arrow toggles (visual feedback works)
-- Content does NOT hide when collapsed
-- Same behavior in local dev and HuggingFace Spaces
-
----
+We will remove the redundant `gr.Blocks` wrapper. This restores the native behavior of `ChatInterface`, ensuring the accordion respects `open=False`.
 
-## Possible Fixes
+### Implementation Plan
 
-### Option 1: Remove gr.Blocks Wrapper (Recommended)
+**Refactor `src/app.py` / `create_demo()`**:
 
-If we don't need the header/footer markdown, use standalone `ChatInterface`:
+1.  **Remove** the `with gr.Blocks() as demo:` context manager.
+2.  **Instantiate** `gr.ChatInterface` directly as the `demo` object.
+3.  **Migrate UI Elements**:
+    *   **Header**: Move the H1/Title text into the `title` parameter of `ChatInterface`.
+    *   **Footer**: Move the footer text ("MCP Server Active...") into the `description` parameter. `ChatInterface` supports Markdown in `description`, making it the ideal place for static info below the title but above the chat.
 
+### Before (Buggy)
 ```python
-# Instead of gr.Blocks wrapper
-demo = gr.ChatInterface(
-    fn=research_agent,
-    title="🧬 DeepCritical",
-    description="AI-Powered Drug Repurposing Agent",
-    additional_inputs_accordion=gr.Accordion(label="⚙️ Settings", open=False),
-    additional_inputs=[...],
-)
+def create_demo():
+    with gr.Blocks() as demo:  # <--- CAUSE OF BUG
+        gr.Markdown("# Title")
+        gr.ChatInterface(..., additional_inputs_accordion=gr.Accordion(open=False))
+        gr.Markdown("Footer")
+    return demo
 ```
 
-**Pros**: Accordion should work correctly
-**Cons**: Less control over layout, no custom header/footer
-
-### Option 2: Manual Accordion Outside ChatInterface
-
-Move settings outside `ChatInterface` into a proper `gr.Accordion`:
-
+### After (Correct)
 ```python
-with gr.Blocks() as demo:
-    gr.Markdown("# 🧬 DeepCritical")
-
-    with gr.Accordion("⚙️ Settings", open=False):
-        mode = gr.Radio(choices=["simple", "magentic"], value="simple", label="Mode")
-        api_key = gr.Textbox(label="API Key", type="password")
-        provider = gr.Radio(choices=["openai", "anthropic"], value="openai", label="Provider")
-
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox(label="Ask a research question")
-
-    msg.submit(research_agent, [msg, chatbot, mode, api_key, provider], chatbot)
-```
-
-**Pros**: Full control, accordion works
-**Cons**: More code, lose ChatInterface conveniences (examples, etc.)
-
-### Option 3: Wait for Gradio Fix
-
-Gradio added `.expand()` and `.collapse()` events in recent versions. Upgrading might help.
-
-**Check current version**:
-```bash
-pip show gradio | grep Version
-```
-
-**Upgrade**:
-```bash
-pip install --upgrade gradio
+def create_demo():
+    return gr.ChatInterface(   # <--- FIX: Top-level component
+        ...,
+        title="🧬 DeepCritical",
+        description="*AI-Powered Drug Repurposing Agent...*\n\n---\n**MCP Server Active**...",
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Settings", open=False)
+    )
 ```
 
 ---
 
-## Recommendation
-
-**Option 1** (Remove gr.Blocks) is cleanest if we can live without custom header/footer.
-
-If header/footer needed, **Option 2** gives working accordion at cost of more code.
-
----
-
-## Files to Modify
-
-| File | Change |
-|------|--------|
-| `src/app.py` | Restructure UI per chosen option |
-| `pyproject.toml` | Possibly upgrade Gradio version |
-
----
-
-## Test Plan
+## 4. Validation
 
-1. Run locally: `uv run python -m src.app`
-2. Click Settings accordion to collapse
-3. Verify content hides when collapsed
-4. Verify content shows when expanded
-5. Test on HuggingFace Spaces after deploy
+1.  **Run**: `uv run python src/app.py`
+2.  **Check**: Open `http://localhost:7860`
+3.  **Verify**:
+    *   Settings accordion starts **COLLAPSED**.
+    *   Header title ("DeepCritical") is visible.
+    *   Footer text ("MCP Server Active") is visible in the description area.
+    *   Chat functionality works (Magentic/Simple modes).
 
 ---
 
-## Sources
+## 5. Constraints & Notes
 
-- [Gradio Issue #8861 - Accordion not working in Blocks](https://github.com/gradio-app/gradio/issues/8861)
-- [Gradio ChatInterface Docs](https://www.gradio.app/docs/gradio/chatinterface)
-- [Gradio Accordion Docs](https://www.gradio.app/docs/gradio/accordion)
+- **Layout**: We lose the ability to place arbitrary elements *below* the chat box (footer will move to top, under title), but this is an acceptable trade-off for a working UI.
+- **CSS**: `ChatInterface` handles its own CSS; any custom class styling from the previous footer will be standardized to the description text style.

src/app.py

@@ -193,71 +193,59 @@ def create_demo() -> Any:
     Returns:
         Configured Gradio Blocks interface with MCP server enabled
     """
-    with gr.Blocks(
-        title="DeepCritical - Drug Repurposing Research Agent",
-    ) as demo:
-        # 1. Minimal Header (Option A: 2 lines max)
-        gr.Markdown(
-            "# 🧬 DeepCritical\n"
-            "*AI-Powered Drug Repurposing Agent — searches PubMed, ClinicalTrials.gov & Europe PMC*"
-        )
-
-        # 2. Main Chat Interface
-        # Config inputs will be in a collapsed accordion below the chat input
-        gr.ChatInterface(
-            fn=research_agent,
-            examples=[
-                [
-                    "What drugs could be repurposed for Alzheimer's disease?",
-                    "simple",
-                    "",
-                    "openai",
-                ],
-                [
-                    "Is metformin effective for treating cancer?",
-                    "simple",
-                    "",
-                    "openai",
-                ],
-                [
-                    "What medications show promise for Long COVID treatment?",
-                    "simple",
-                    "",
-                    "openai",
-                ],
+    # 1. Unwrapped ChatInterface (Fixes Accordion Bug)
+    demo = gr.ChatInterface(
+        fn=research_agent,
+        title="🧬 DeepCritical",
+        description=(
+            "*AI-Powered Drug Repurposing Agent — searches PubMed, "
+            "ClinicalTrials.gov & Europe PMC*\n\n"
+            "---\n"
+            "*Research tool only — not for medical advice.*  \n"
+            "**MCP Server Active**: Connect Claude Desktop to `/gradio_api/mcp/`"
+        ),
+        examples=[
+            [
+                "What drugs could be repurposed for Alzheimer's disease?",
+                "simple",
+                "",
+                "openai",
             ],
-            additional_inputs_accordion=gr.Accordion(label="⚙️ Settings", open=False),
-            additional_inputs=[
-                gr.Radio(
-                    choices=["simple", "magentic"],
-                    value="simple",
-                    label="Orchestrator Mode",
-                    info="Simple: Linear | Magentic: Multi-Agent (OpenAI)",
-                ),
-                gr.Textbox(
-                    label="🔑 API Key (Optional - BYOK)",
-                    placeholder="sk-... or sk-ant-...",
-                    type="password",
-                    info="Enter your own API key. Never stored.",
-                ),
-                gr.Radio(
-                    choices=["openai", "anthropic"],
-                    value="openai",
-                    label="API Provider",
-                    info="Select the provider for your API key",
-                ),
+            [
+                "Is metformin effective for treating cancer?",
+                "simple",
+                "",
+                "openai",
             ],
-        )
-
-        # 3. Minimal Footer (Option C: Remove MCP Tabs, keep info)
-        gr.Markdown(
-            """
-            ---
-            *Research tool only — not for medical advice.*
-            **MCP Server Active**: Connect Claude Desktop to `/gradio_api/mcp/`
-            """,
-            elem_classes=["footer"],
-        )
+            [
+                "What medications show promise for Long COVID treatment?",
+                "simple",
+                "",
+                "openai",
+            ],
+        ],
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Settings", open=False),
+        additional_inputs=[
+            gr.Radio(
+                choices=["simple", "magentic"],
+                value="simple",
+                label="Orchestrator Mode",
+                info="Simple: Linear | Magentic: Multi-Agent (OpenAI)",
+            ),
+            gr.Textbox(
+                label="🔑 API Key (Optional - BYOK)",
+                placeholder="sk-... or sk-ant-...",
+                type="password",
+                info="Enter your own API key. Never stored.",
+            ),
+            gr.Radio(
+                choices=["openai", "anthropic"],
+                value="openai",
+                label="API Provider",
+                info="Select the provider for your API key",
+            ),
+        ],
+    )
 
     return demo