Update Groq model to openai/gpt-oss-120b

output/gaia_results_20260104_222540.json

@@ -0,0 +1,63 @@
+{
+  "metadata": {
+    "generated": "2026-01-04 22:25:40",
+    "timestamp": "20260104_222540",
+    "total_questions": 8,
+    "execution_time_seconds": 57.18,
+    "execution_time_formatted": "0m 57s",
+    "score_percent": 5.0,
+    "correct_count": 1,
+    "total_attempted": 8
+  },
+  "submission_status": "Submission Successful!\nUser: mangoobee\nOverall Score: 5.0% (1/8 correct)\nMessage: Score calculated successfully: 1/20 total questions answered correctly (8 valid tasks attempted). Score did not improve previous record, leaderboard not updated.",
+  "results": [
+    {
+      "task_id": "a1e91b78-d3d8-4675-bb8d-62741b4b68a6",
+      "question": "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?",
+      "submitted_answer": "ERROR: No evidence collected. Details: Tool vision failed: Exception: Vision analysis failed - Gemini and Claude both failed",
+      "correct": false
+    },
+    {
+      "task_id": "cca530fc-4052-43b2-b130-b30968d8aa44",
+      "question": "Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.",
+      "submitted_answer": "ERROR: No evidence collected. Details: Tool vision failed: Exception: Vision analysis failed - Gemini and Claude both failed",
+      "correct": false
+    },
+    {
+      "task_id": "2d83110e-a098-4ebb-9987-066c06fa42d0",
+      "question": ".rewsna eht sa \"tfel\" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI",
+      "submitted_answer": "right",
+      "correct": true
+    },
+    {
+      "task_id": "9d191bce-651d-4746-be2d-7ef8ecadb9c2",
+      "question": "Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.\n\nWhat does Teal'c say in response to the question \"Isn't that hot?\"",
+      "submitted_answer": "ERROR: No evidence collected. Details: Tool vision failed: Exception: Vision analysis failed - Gemini and Claude both failed",
+      "correct": false
+    },
+    {
+      "task_id": "cabe07ed-9eca-40ea-8ead-410ef5e83f91",
+      "question": "What is the surname of the equine veterinarian mentioned in 1.E Exercises from the chemistry materials licensed by Marisa Alviar-Agnew & Henry Agnew under the CK-12 license in LibreText's Introductory Chemistry materials as compiled 08/21/2023?",
+      "submitted_answer": "Unable to answer",
+      "correct": false
+    },
+    {
+      "task_id": "6f37996b-2ac7-44b0-8e68-6d28256631b4",
+      "question": "Given this table defining * on the set S = {a, b, c, d, e}\n\n|*|a|b|c|d|e|\n|---|---|---|---|---|---|\n|a|a|b|c|b|d|\n|b|b|c|a|e|c|\n|c|c|a|b|b|a|\n|d|b|e|b|e|d|\n|e|d|b|a|d|c|\n\nprovide the subset of S involved in any possible counter-examples that prove * is not commutative. Provide your answer as a comma separated list of the elements in the set in alphabetical order.",
+      "submitted_answer": "ERROR: No evidence collected. Details: Tool parse_file failed: FileNotFoundError: Text file not found: path/to/operation_table.csv",
+      "correct": false
+    },
+    {
+      "task_id": "8e867cd7-cff9-4e6c-867a-ff5ddc2550be",
+      "question": "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia.",
+      "submitted_answer": "Unable to answer",
+      "correct": false
+    },
+    {
+      "task_id": "4fc2f1ae-8625-45b5-ab34-ad4433bc21f8",
+      "question": "Who nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted in November 2016?",
+      "submitted_answer": "Unable to answer",
+      "correct": false
+    }
+  ]
+}

src/agent/llm_client.py

@@ -38,7 +38,7 @@ HF_MODEL = "Qwen/Qwen2.5-72B-Instruct"  # Excellent for function calling and rea
 # Alternatives: "meta-llama/Llama-3.1-70B-Instruct", "NousResearch/Hermes-3-Llama-3.1-70B"
 
 # Groq Configuration
-GROQ_MODEL = "qwen/qwen3-32b"  # Free tier: 60 req/min, fast inference
+GROQ_MODEL = "openai/gpt-oss-120b"
 # Alternatives: "llama-3.1-8b-instant", "mixtral-8x7b-32768"
 
 # Shared Configuration
@@ -184,7 +184,9 @@ def _call_with_fallback(function_name: str, *args, **kwargs) -> Any:
         logger.info(f"[{function_name}] Using primary provider: {primary_provider}")
         return retry_with_backoff(lambda: primary_func(*args, **kwargs))
     except Exception as primary_error:
-        logger.warning(f"[{function_name}] Primary provider {primary_provider} failed: {primary_error}")
+        logger.warning(
+            f"[{function_name}] Primary provider {primary_provider} failed: {primary_error}"
+        )
 
         # If fallback disabled, raise immediately
         if not enable_fallback:
@@ -199,11 +201,15 @@ def _call_with_fallback(function_name: str, *args, **kwargs) -> Any:
         for fallback_provider in fallback_providers:
             try:
                 fallback_func = _get_provider_function(function_name, fallback_provider)
-                logger.info(f"[{function_name}] Trying fallback provider: {fallback_provider}")
+                logger.info(
+                    f"[{function_name}] Trying fallback provider: {fallback_provider}"
+                )
                 return retry_with_backoff(lambda: fallback_func(*args, **kwargs))
             except Exception as fallback_error:
                 errors[fallback_provider] = fallback_error
-                logger.warning(f"[{function_name}] Fallback provider {fallback_provider} failed: {fallback_error}")
+                logger.warning(
+                    f"[{function_name}] Fallback provider {fallback_provider} failed: {fallback_error}"
+                )
                 continue
 
         # All providers failed