feat(ui): force dark mode for api key input and enhance synthesis error handling

src/app.py

@@ -257,10 +257,25 @@ def create_demo() -> tuple[gr.ChatInterface, gr.Accordion]:
         "**MCP Server Active**: Connect Claude Desktop to `/gradio_api/mcp/`"
     )
 
+    # CSS to force dark mode on API key input
+    custom_css = """
+    .api-key-input input {
+        background-color: #1f2937 !important;
+        color: white !important;
+        border-color: #374151 !important;
+    }
+    .api-key-input input:focus {
+        background-color: #1f2937 !important;
+        color: white !important;
+        border-color: #e879f9 !important;
+    }
+    """
+
     demo = gr.ChatInterface(
         fn=research_agent,
         title="🍆 DeepBoner",
         description=description,
+        css=custom_css,
         examples=[
             [
                 "What drugs improve female libido post-menopause?",
@@ -304,6 +319,7 @@ def create_demo() -> tuple[gr.ChatInterface, gr.Accordion]:
                 placeholder="sk-... (OpenAI) or sk-ant-... (Anthropic)",
                 type="password",
                 info="Leave empty for free tier. Auto-detects provider from key prefix.",
+                elem_classes=["api-key-input"],
             ),
             api_key_state,  # Hidden state component for persistence
         ],

src/orchestrators/simple.py

@@ -541,11 +541,13 @@ class Orchestrator:
 
             from src.agent_factory.judges import get_model
 
-            # Create synthesis agent (string output, not structured)
+            # Create synthesis agent with retries (matching Judge agent pattern)
+            # Without retries, transient errors immediately trigger fallback
             agent: Agent[None, str] = Agent(
                 model=get_model(),
                 output_type=str,
                 system_prompt=system_prompt,
+                retries=3,  # Match Judge agent - retry on transient errors
             )
             result = await agent.run(user_prompt)
             narrative = result.output
@@ -554,14 +556,22 @@ class Orchestrator:
 
         except Exception as e:
             # Fallback to template synthesis if LLM fails
-            # This is intentionally broad - LLM can fail many ways (API, parsing, etc.)
+            # Log error details for debugging
             logger.warning(
                 "LLM synthesis failed, using template fallback",
                 error=str(e),
                 exc_type=type(e).__name__,
                 evidence_count=len(evidence),
             )
-            return self._generate_template_synthesis(query, evidence, assessment)
+            # Surface the error to user (MS Agent Framework pattern)
+            # Don't silently fall back - let user know synthesis degraded
+            error_note = (
+                f"\n\n> ⚠️ **Note**: AI narrative synthesis unavailable. "
+                f"Showing structured summary.\n"
+                f"> _Error: {type(e).__name__}_\n"
+            )
+            template = self._generate_template_synthesis(query, evidence, assessment)
+            return f"{error_note}\n{template}"
 
         # Add full citation list footer
         citations = "\n".join(

tests/unit/orchestrators/test_simple_synthesis.py

@@ -130,12 +130,12 @@ Long-term safety data is limited.
             assert "Evidence Synthesis" in result
 
     @pytest.mark.asyncio
-    async def test_falls_back_on_llm_error(
+    async def test_falls_back_on_llm_error_with_notice(
         self,
         sample_evidence: list[Evidence],
         sample_assessment: JudgeAssessment,
     ) -> None:
-        """Synthesis should fall back to template if LLM fails."""
+        """Synthesis should fall back to template if LLM fails, WITH error notice."""
         mock_search = MagicMock()
         mock_judge = MagicMock()
 
@@ -155,7 +155,11 @@ Long-term safety data is limited.
                 assessment=sample_assessment,
             )
 
-            # Should return template fallback (has Assessment section)
+            # Should surface error to user (MS Agent Framework pattern)
+            assert "AI narrative synthesis unavailable" in result
+            assert "Error" in result
+
+            # Should still include template content
             assert "Assessment" in result or "Drug Candidates" in result
             assert "Testosterone" in result  # Drug candidate should be present