adds youtube video

AUDIO_INPUT_FIX.md

@@ -91,3 +91,4 @@ If audio input still doesn't appear:
 
 
 
+

ERROR_FIXES_SUMMARY.md

@@ -153,3 +153,4 @@ Some MCP tools use `gr.State` inputs, which Gradio warns won't update between to
 
 
 
+

FILE_OUTPUT_IMPLEMENTATION_PLAN.md

@@ -238,3 +238,4 @@ Current implementation in `event_to_chat_message()` already handles this correct
 
 
 
+

FILE_OUTPUT_VERIFICATION.md

@@ -221,3 +221,4 @@ No reimplementation needed. All changes are present and correct.
 
 
 
+

FIX_SUMMARY.md

@@ -99,3 +99,4 @@ if isinstance(final_result, dict):
 - Better logging will help debug any future issues with result extraction
 
 
+

MULTIMODAL_SETTINGS_IMPLEMENTATION_PLAN.md

@@ -383,3 +383,4 @@ result["content"] = f"{content}\n\n{file_links}"
 
 
 
+

MULTIMODAL_SETTINGS_IMPLEMENTATION_SUMMARY.md

@@ -154,3 +154,4 @@
 
 
 
+

PDF_REPORT_INTEGRATION.md

@@ -131,3 +131,4 @@ PDF generation is automatically triggered when:
 - Batch PDF generation
 
 
+

README.md

@@ -43,7 +43,7 @@ tags:
 [![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)
-[![YouTube](https://img.shields.io/badge/YouTube-FF0000?style=for-the-badge&logo=youtube&logoColor=white&label=Watch%20Demo&labelColor=FF0000&color=FF0000)](https://www.youtube.com/watch?v=PLACEHOLDER)
+[![YouTube](https://img.shields.io/badge/YouTube-FF0000?style=for-the-badge&logo=youtube&logoColor=white&label=Watch%20Demo&labelColor=FF0000&color=FF0000)](https://www.youtube.com/watch?v=https://youtu.be/Mb0M83BqgOw)
 [![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) 
 
@@ -88,6 +88,16 @@ Please join us @ https://hf.co/spaces/DataQuests/DeepCritical where we will keep
 - 💖 made with love
 
 
+## What Can It Do ? 
+
+- long running tasks (potentially millions of tokens over hours and hours)
+- data processing and rendering
+- statistical analyses 
+- literature reviews 
+- websearch
+- synthetize complex information
+- find hard to find information
+
 ## Deep Critical In the Media 
 
 - Social Medial Posts about Deep Critical :
@@ -184,8 +194,9 @@ Please join us @ https://hf.co/spaces/DataQuests/DeepCritical where we will keep
 
 ## 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)
+[![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)
+[![YouTube](https://img.shields.io/badge/YouTube-FF0000?style=for-the-badge&logo=youtube&logoColor=white&label=Watch%20Demo&labelColor=FF0000&color=FF0000)](https://www.youtube.com/watch?v=https://youtu.be/Mb0M83BqgOw)
 [![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) 
+[![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/qdfnvSPcqP) 

REPORT_WRITING_AGENTS_ANALYSIS.md

@@ -186,3 +186,4 @@ The infrastructure to handle file outputs in Gradio is in place, but the agents
 
 
 
+

SERPER_WEBSEARCH_IMPLEMENTATION_PLAN.md

@@ -400,3 +400,4 @@ This plan details the implementation of SERPER-based web search by vendoring cod
 
 
 
+

dev/__init__.py

@@ -1,3 +1,4 @@
 """Development utilities and plugins."""
 
 
+

docs/api/agents.md

@@ -272,3 +272,4 @@ def create_input_parser_agent(model: Any | None = None) -> InputParserAgent
 
 
 
+

docs/api/models.md

@@ -250,3 +250,4 @@ class BudgetStatus(BaseModel):
 
 
 
+

docs/api/services.md

@@ -207,5 +207,6 @@ Analyzes a hypothesis using statistical methods.
 
 
 
+
 
 

docs/api/tools.md

@@ -237,3 +237,4 @@ Searches multiple tools in parallel.
 
 
 
+

docs/architecture/agents.md

@@ -194,3 +194,4 @@ Factory functions:
 
 
 
+

docs/contributing/code-quality.md

@@ -83,3 +83,4 @@ async def search(self, query: str, max_results: int = 10) -> list[Evidence]:
 
 
 
+

docs/contributing/code-style.md

@@ -63,3 +63,4 @@ result = await loop.run_in_executor(None, cpu_bound_function, args)
 
 
 
+

docs/contributing/error-handling.md

@@ -71,3 +71,4 @@ except httpx.HTTPError as e:
 
 
 
+

docs/contributing/implementation-patterns.md

@@ -86,3 +86,4 @@ def get_embedding_service() -> EmbeddingService:
 
 
 
+

docs/contributing/index.md

@@ -165,3 +165,4 @@ Thank you for contributing to DeepCritical!
 
 
 
+

docs/contributing/prompt-engineering.md

@@ -71,3 +71,4 @@ This document outlines prompt engineering guidelines and citation validation rul
 
 
 
+

docs/contributing/testing.md

@@ -75,3 +75,4 @@ async def test_real_pubmed_search():
 
 
 
+

docs/getting-started/installation.md

@@ -158,3 +158,4 @@ uv run pre-commit install
 
 
 
+

docs/implementation/IMPLEMENTATION_SUMMARY.md

@@ -185,3 +185,4 @@ Located in `src/app.py` lines 667-712:
 
 
 
+

docs/implementation/TTS_MODAL_IMPLEMENTATION.md

@@ -139,3 +139,4 @@ To test TTS:
 
 
 
+

docs/license.md

@@ -41,3 +41,4 @@ SOFTWARE.
 
 
 
+

docs/team.md

@@ -46,3 +46,4 @@ We welcome contributions! See the [Contributing Guide](contributing/index.md) fo
 
 
 
+

new_env.txt

@@ -101,3 +101,4 @@ MODAL_TOKEN_SECRET=your_modal_token_secret_here
 
 
 
+

src/agents/long_writer.py

@@ -225,6 +225,36 @@ class LongWriterAgent:
             "Section writing failed after all attempts",
             error=str(last_exception) if last_exception else "Unknown error",
         )
+        
+        # Try to enhance fallback with evidence if available
+        try:
+            from src.middleware.state_machine import get_workflow_state
+            
+            state = get_workflow_state()
+            if state and state.evidence:
+                # Include evidence citations in fallback
+                evidence_refs: list[str] = []
+                for i, ev in enumerate(state.evidence[:10], 1):  # Limit to 10
+                    authors = ", ".join(ev.citation.authors[:2]) if ev.citation.authors else "Unknown"
+                    evidence_refs.append(
+                        f"[{i}] {authors}. *{ev.citation.title}*. {ev.citation.url}"
+                    )
+                
+                enhanced_draft = f"## {next_section_title}\n\n{next_section_draft}"
+                if evidence_refs:
+                    enhanced_draft += "\n\n### Sources\n\n" + "\n".join(evidence_refs)
+                
+                return LongWriterOutput(
+                    next_section_markdown=enhanced_draft,
+                    references=evidence_refs,
+                )
+        except Exception as e:
+            self.logger.warning(
+                "Failed to enhance fallback with evidence",
+                error=str(e),
+            )
+        
+        # Basic fallback
         return LongWriterOutput(
             next_section_markdown=f"## {next_section_title}\n\n{next_section_draft}",
             references=[],

src/agents/writer.py

@@ -175,6 +175,30 @@ FINDINGS:
             "Report writing failed after all attempts",
             error=str(last_exception) if last_exception else "Unknown error",
         )
+        
+        # Try to use evidence-based report generator for better fallback
+        try:
+            from src.middleware.state_machine import get_workflow_state
+            from src.utils.report_generator import generate_report_from_evidence
+            
+            state = get_workflow_state()
+            if state and state.evidence:
+                self.logger.info(
+                    "Using evidence-based report generator for fallback",
+                    evidence_count=len(state.evidence),
+                )
+                return generate_report_from_evidence(
+                    query=query,
+                    evidence=state.evidence,
+                    findings=findings,
+                )
+        except Exception as e:
+            self.logger.warning(
+                "Failed to use evidence-based report generator",
+                error=str(e),
+            )
+        
+        # Fallback to simple report if evidence generator fails
         # Truncate findings in fallback if too long
         fallback_findings = findings[:500] + "..." if len(findings) > 500 else findings
         return (

src/middleware/state_machine.py

@@ -129,3 +129,4 @@ def get_workflow_state() -> WorkflowState:
     return state
 
 
+

src/tools/searchxng_web_search.py

@@ -115,3 +115,4 @@ class SearchXNGWebSearchTool:
             raise SearchError(f"SearchXNG search failed: {e}") from e
 
 
+

src/tools/serper_web_search.py

@@ -115,3 +115,4 @@ class SerperWebSearchTool:
             raise SearchError(f"Serper search failed: {e}") from e
 
 
+

src/tools/vendored/crawl_website.py

@@ -127,3 +127,4 @@ async def crawl_website(starting_url: str) -> list[ScrapeResult] | str:
     return result
 
 
+

src/tools/vendored/searchxng_client.py

@@ -96,3 +96,4 @@ class SearchXNGClient:
             raise SearchError(f"SearchXNG search failed: {e}") from e
 
 
+

src/tools/vendored/serper_client.py

@@ -92,3 +92,4 @@ class SerperClient:
             raise SearchError(f"Serper search failed: {e}") from e
 
 
+

src/tools/vendored/web_search_core.py

@@ -201,3 +201,4 @@ def is_valid_url(url: str) -> bool:
     return True
 
 
+

src/tools/web_search_factory.py

@@ -68,3 +68,4 @@ def create_web_search_tool() -> SearchTool | None:
         return None
 
 
+

src/utils/markdown.css

@@ -6,3 +6,4 @@ body {
 }
 
 
+

src/utils/md_to_pdf.py

@@ -66,3 +66,4 @@ def md_to_pdf(md_text: str, pdf_file_path: str) -> None:
     logger.debug("PDF generated successfully", pdf_path=pdf_file_path)
 
 
+

src/utils/report_generator.py

@@ -169,3 +169,4 @@ def generate_report_from_evidence(
     return "".join(report_parts)
 
 
+

tests/unit/middleware/test_budget_tracker_phase7.py

@@ -177,5 +177,6 @@ class TestIterationTokenTracking:
 
 
 
+
 
 

tests/unit/middleware/test_state_machine.py

@@ -374,5 +374,6 @@ class TestContextVarIsolation:
 
 
 
+
 
 

tests/unit/middleware/test_workflow_manager.py

@@ -304,5 +304,6 @@ class TestWorkflowManager:
 
 
 
+