Update

CHANGELOG.md

@@ -25,9 +25,11 @@
 - **app.py**
   - Updated `check_api_keys()` - Added HF_TOKEN status display in Test & Debug tab
   - UI now shows: "HF_TOKEN (HuggingFace): ✓ SET" or "✗ MISSING"
-  - Added `export_results_to_markdown(results_log, submission_status)` - Export evaluation results to markdown file
-  - Updated `run_and_submit_all()` - ALL return paths now export results to ~/Downloads/gaia_results_TIMESTAMP.md
-  - Added export_output UI component - Displays exported file path to user
+  - Added `export_results_to_markdown(results_log, submission_status)` - Export evaluation results with environment detection
+    - Local: Saves to ~/Downloads/gaia_results_TIMESTAMP.md
+    - HF Spaces: Saves to ./exports/gaia_results_TIMESTAMP.md (fixes cloud deployment issue)
+  - Updated `run_and_submit_all()` - ALL return paths now export results
+  - Added gr.File download button - Users can directly download results (better UX than textbox)
   - Updated run_button click handler - Now outputs 3 values (status, table, export_path)
 
 - **src/tools/__init__.py** (Fixed earlier in session)

app.py

@@ -35,13 +35,26 @@ def check_api_keys():
 
 
 def export_results_to_markdown(results_log: list, submission_status: str) -> str:
-    """Export evaluation results to markdown file in Downloads folder."""
+    """Export evaluation results to markdown file.
+
+    - Local: Saves to ~/Downloads
+    - HF Spaces: Saves to ./exports/ (for Gradio file download)
+    """
     from datetime import datetime
 
     timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-    downloads_dir = os.path.expanduser("~/Downloads")
     filename = f"gaia_results_{timestamp}.md"
-    filepath = os.path.join(downloads_dir, filename)
+
+    # Detect environment: HF Spaces or local
+    if os.getenv("SPACE_ID"):
+        # HF Spaces: save to local exports directory for Gradio to serve
+        export_dir = os.path.join(os.getcwd(), "exports")
+        os.makedirs(export_dir, exist_ok=True)
+        filepath = os.path.join(export_dir, filename)
+    else:
+        # Local: save to Downloads folder
+        downloads_dir = os.path.expanduser("~/Downloads")
+        filepath = os.path.join(downloads_dir, filename)
 
     with open(filepath, 'w') as f:
         # Header
@@ -414,10 +427,9 @@ with gr.Blocks() as demo:
             # Removed max_rows=10 from DataFrame constructor
             results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
-            export_output = gr.Textbox(
-                label="Exported Results",
-                placeholder="Results will be exported to markdown file in ~/Downloads",
-                interactive=False
+            export_output = gr.File(
+                label="Download Results",
+                type="filepath"
             )
 
             run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table, export_output])

dev/{dev_260103_16_huggingface_integration.md → dev_260103_16_huggingface_llm_integration.md}

@@ -1,4 +1,4 @@
-# [dev_260103_16] HuggingFace Inference API Integration
+# [dev_260103_16] HuggingFace LLM API Integration
 
 **Date:** 2026-01-03
 **Type:** Development
@@ -27,7 +27,7 @@
 
 ## Key Decisions
 
-### **Decision 1: HuggingFace Inference API over Ollama (local LLMs)**
+### **Decision 1: HuggingFace LLM API over Ollama (local LLMs)**
 
 **Why chosen:**
 
@@ -50,7 +50,7 @@
 
 - ✅ Excellent function calling capabilities (OpenAI-compatible tools format)
 - ✅ Strong reasoning performance (competitive with GPT-4 on benchmarks)
-- ✅ Free on HuggingFace Inference API
+- ✅ Free on HuggingFace LLM API
 - ✅ 72B parameters - sufficient intelligence for GAIA tasks
 
 **Considered alternatives:**
@@ -102,7 +102,7 @@
 
 ## Outcome
 
-Successfully integrated HuggingFace Inference API as free LLM fallback tier, completing Stage 4 MVP with robust multi-tier resilience.
+Successfully integrated HuggingFace LLM API as free LLM fallback tier, completing Stage 4 MVP with robust multi-tier resilience.
 
 **Deliverables:**
 

exports/gaia_results_20260104_005516.md

@@ -0,0 +1,35 @@
+# GAIA Agent Evaluation Results
+
+**Generated:** 2026-01-04 00:55:16
+
+## Submission Status
+
+Submission Successful!
+User: mangoobee
+Overall Score: 0.0% (0/20 correct)
+Message: Score calculated successfully: 0/20 total questions answered correctly (20 valid tasks attempted). Score did not improve previous record, leaderboard not updated.
+
+## Questions and Answers
+
+| Task ID | Question | Submitted Answer |
+|---------|----------|------------------|
+| 8e867cd7-cff9-4e6c-867a-ff5ddc2550be | How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can ... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| a1e91b78-d3d8-4675-bb8d-62741b4b68a6 | In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird spec... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 2d83110e-a098-4ebb-9987-066c06fa42d0 | .rewsna eht sa "tfel" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| cca530fc-4052-43b2-b130-b30968d8aa44 | Review the chess position provided in the image. It is black's turn. Provide the correct next mov... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 4fc2f1ae-8625-45b5-ab34-ad4433bc21f8 | Who nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted i... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 6f37996b-2ac7-44b0-8e68-6d28256631b4 | Given this table defining * on the set S = {a, b, c, d, e}  \|*\|a\|b\|c\|d\|e\| \|---\|---\|---\... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 9d191bce-651d-4746-be2d-7ef8ecadb9c2 | Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.  What does Teal'c say in respon... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| cabe07ed-9eca-40ea-8ead-410ef5e83f91 | What is the surname of the equine veterinarian mentioned in 1.E Exercises from the chemistry mate... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 3cef3a44-215e-4aed-8e3b-b1e3f08063b7 | I'm making a grocery list for my mom, but she's a professor of botany and she's a real stickler w... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3 | Hi, I'm making a pie but I could use some help with my shopping list. I have everything I need fo... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 305ac316-eef6-4446-960a-92d80d542f82 | Who did the actor who played Ray in the Polish-language version of Everybody Loves Raymond play i... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| f918266a-b3e0-4914-865d-4faa564f1aef | What is the final numeric output from the attached Python code? | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 3f57289b-8c60-48be-bd80-01f8099ca449 | How many at bats did the Yankee with the most walks in the 1977 regular season have that same sea... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 1f975693-876d-457b-a649-393859e79bf3 | Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study fo... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 840bfca7-4f7b-481a-8794-c560c340185d | On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This art... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| bda648d7-d618-4883-88f4-3466eabd860e | Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| cf106601-ab4f-4af9-b045-5295fe67b37d | What country had the least number of athletes at the 1928 Summer Olympics? If there's a tie for a... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| a0c07678-e491-4bbc-8f0b-07405144218f | Who are the pitchers with the number before and after Taishō Tamai's number as of July 2023? Give... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 7bd855d8-463d-4ed5-93ca-5fe35145f733 | The attached Excel file contains the sales of menu items for a local fast-food chain. What were t... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 5a0c1adf-205e-4841-a666-7c3ef95def9d | What is the first name of the only Malko Competition recipient from the 20th Century (after 1977)... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |

exports/gaia_results_20260104_005610.md

@@ -0,0 +1,35 @@
+# GAIA Agent Evaluation Results
+
+**Generated:** 2026-01-04 00:56:10
+
+## Submission Status
+
+Submission Successful!
+User: mangoobee
+Overall Score: 0.0% (0/20 correct)
+Message: Score calculated successfully: 0/20 total questions answered correctly (20 valid tasks attempted). Score did not improve previous record, leaderboard not updated.
+
+## Questions and Answers
+
+| Task ID | Question | Submitted Answer |
+|---------|----------|------------------|
+| 8e867cd7-cff9-4e6c-867a-ff5ddc2550be | How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can ... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| a1e91b78-d3d8-4675-bb8d-62741b4b68a6 | In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird spec... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 2d83110e-a098-4ebb-9987-066c06fa42d0 | .rewsna eht sa "tfel" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| cca530fc-4052-43b2-b130-b30968d8aa44 | Review the chess position provided in the image. It is black's turn. Provide the correct next mov... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 4fc2f1ae-8625-45b5-ab34-ad4433bc21f8 | Who nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted i... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 6f37996b-2ac7-44b0-8e68-6d28256631b4 | Given this table defining * on the set S = {a, b, c, d, e}  \|*\|a\|b\|c\|d\|e\| \|---\|---\|---\... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 9d191bce-651d-4746-be2d-7ef8ecadb9c2 | Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.  What does Teal'c say in respon... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| cabe07ed-9eca-40ea-8ead-410ef5e83f91 | What is the surname of the equine veterinarian mentioned in 1.E Exercises from the chemistry mate... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 3cef3a44-215e-4aed-8e3b-b1e3f08063b7 | I'm making a grocery list for my mom, but she's a professor of botany and she's a real stickler w... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3 | Hi, I'm making a pie but I could use some help with my shopping list. I have everything I need fo... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 305ac316-eef6-4446-960a-92d80d542f82 | Who did the actor who played Ray in the Polish-language version of Everybody Loves Raymond play i... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| f918266a-b3e0-4914-865d-4faa564f1aef | What is the final numeric output from the attached Python code? | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 3f57289b-8c60-48be-bd80-01f8099ca449 | How many at bats did the Yankee with the most walks in the 1977 regular season have that same sea... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 1f975693-876d-457b-a649-393859e79bf3 | Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study fo... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 840bfca7-4f7b-481a-8794-c560c340185d | On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This art... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| bda648d7-d618-4883-88f4-3466eabd860e | Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| cf106601-ab4f-4af9-b045-5295fe67b37d | What country had the least number of athletes at the 1928 Summer Olympics? If there's a tie for a... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| a0c07678-e491-4bbc-8f0b-07405144218f | Who are the pitchers with the number before and after Taishō Tamai's number as of July 2023? Give... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 7bd855d8-463d-4ed5-93ca-5fe35145f733 | The attached Excel file contains the sales of menu items for a local fast-food chain. What were t... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |
+| 5a0c1adf-205e-4841-a666-7c3ef95def9d | What is the first name of the only Malko Competition recipient from the 20th Century (after 1977)... | ERROR: No evidence collected. Details: Planning error: Exception: Planning failed with all LLMs. ... |