[agent] cleanup: remove orphaned submodule and fix script organization

.gitignore

@@ -44,7 +44,6 @@ Thumbs.db
 __pycache__/
 *.py[cod]
 *$py.class
-uv.lock
 
 # C extensions
 *.so

backend/.gitignore

@@ -2,7 +2,6 @@
 __pycache__/
 *.py[cod]
 *$py.class
-uv.lock
 
 # C extensions
 *.so

backend/pyproject.toml

@@ -35,6 +35,7 @@ dependencies = [
     "langfuse",
     "numpy<2.0.0",
     "pycares<5.0.0",
+    "aiofiles>=25.1.0",
 ]
 
 

backend/scripts/benchmark.py

@@ -1,22 +1,24 @@
 """Benchmark Orchestration Script
 
-This script runs the agent against a dataset of questions and evaluates performance 
+This script runs the agent against a dataset of questions and evaluates performance
 using the evaluators defined in backend/tests/evaluators.py.
 """
 
 import asyncio
-import logging
 import json
+import logging
 import os
-from typing import List, Dict, Any
+from typing import Any, Dict, List
+
 from dotenv import load_dotenv
 
 # Load env vars before importing evaluators or agent components
 load_dotenv()
 
 from agent.graph import graph
+
 try:
-    from tests.evaluators import eval_quality, eval_groundedness
+    from tests.evaluators import eval_groundedness, eval_quality
 except ImportError:
     # This might happen if running script directly without module context
     # But usually handled by running as `python -m scripts.benchmark`
@@ -28,6 +30,7 @@
 # Path relative to backend root
 DATASET_PATH = os.path.join("tests", "data", "benchmark_questions.json")
 
+
 def load_dataset(path: str) -> List[Dict[str, Any]]:
     """Load questions from a JSON file."""
     if not os.path.exists(path):
@@ -41,12 +44,13 @@
             return []
 
     try:
-        with open(path, "r", encoding="utf-8") as f:
+        with open(path, encoding="utf-8") as f:
             return json.load(f)
     except Exception as e:
         logger.error(f"Failed to load dataset: {e}")
         return []
 
+
 async def run_benchmark():
     """Run evaluation for all questions."""
     questions = load_dataset(DATASET_PATH)
@@ -71,12 +75,13 @@
             # For automation, we assume the graph can run autonomously or we'd need to mock input.
             # Increase recursion limit to handle multi-step research plans (default is 25)
             # Disable planning confirmation to allow automated execution
-            response = await graph.ainvoke({
-                "messages": [("user", question)]
-            }, config={
-                "recursion_limit": 100,
-                "configurable": {"require_planning_confirmation": False}
-            })
+            response = await graph.ainvoke(
+                {"messages": [("user", question)]},
+                config={
+                    "recursion_limit": 100,
+                    "configurable": {"require_planning_confirmation": False},
+                },
+            )
 
             # Extract final answer from the last message content
             messages = response.get("messages", [])
@@ -113,17 +118,25 @@
                 "question": question,
                 "expected_topics": expected_topics,
                 "quality_score": quality_result.get("score", 0),
-                "quality_reasoning": quality_result.get("metadata", {}).get("reasoning", "No reasoning provided"),
+                "quality_reasoning": quality_result.get("metadata", {}).get(
+                    "reasoning", "No reasoning provided"
+                ),
                 "groundedness_score": groundedness_result.get("score", 0),
-                "groundedness_reasoning": groundedness_result.get("metadata", {}).get("reasoning", "No reasoning provided"),
-                "final_answer_snippet": (final_content[:200] + "...") if final_content else "No content"
+                "groundedness_reasoning": groundedness_result.get("metadata", {}).get(
+                    "reasoning", "No reasoning provided"
+                ),
+                "final_answer_snippet": (final_content[:200] + "...")
+                if final_content
+                else "No content",
             }
             results.append(result_entry)
 
-            logger.info(f"Result for '{question}': Q={result_entry['quality_score']}, G={result_entry['groundedness_score']}")
+            logger.info(
+                f"Result Q={result_entry['quality_score']}, G={result_entry['groundedness_score']} for question"
+            )
 
         except Exception as e:
-            logger.error(f"Agent failed for '{question}': {e}", exc_info=True)
+            logger.error("Agent failed for question", exc_info=True)
             continue
 
     # Report Generation
@@ -141,12 +154,12 @@
 """
         for r in results:
             report += f"""
-### {r['question']}
-- **Quality:** {r['quality_score']}
-  - *Reasoning:* {r['quality_reasoning']}
-- **Groundedness:** {r['groundedness_score']}
-  - *Reasoning:* {r['groundedness_reasoning']}
-- **Snippet:** {r['final_answer_snippet']}
+### {r["question"]}
+- **Quality:** {r["quality_score"]}
+  - *Reasoning:* {r["quality_reasoning"]}
+- **Groundedness:** {r["groundedness_score"]}
+  - *Reasoning:* {r["groundedness_reasoning"]}
+- **Snippet:** {r["final_answer_snippet"]}
 """
         print(report)
 
@@ -157,5 +170,6 @@
     else:
         logger.warning("No results to report.")
 
+
 if __name__ == "__main__":
     asyncio.run(run_benchmark())

backend/scripts/check_path.py

@@ -1,9 +1,10 @@
-
-import sys
 import os
+import sys
+
 print(sys.path)
 try:
     import agent
+
     print(f"Agent: {agent}")
 except ImportError as e:
     print(f"ImportError: {e}")

scripts/generate_sample_reports.py → backend/scripts/generate_sample_reports.py

@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
-import os
-import sys
 import asyncio
 import json
+import os
+import sys
 from datetime import datetime
 from pathlib import Path
 
@@ -13,9 +13,10 @@
 
 # Import Agent Components
 try:
-    from agent.graph import graph
-    from agent.configuration import Configuration
     from langchain_core.messages import HumanMessage
+
+    from agent.configuration import Configuration
+    from agent.graph import graph
 except ImportError as e:
     print(f"Error importing backend modules: {e}")
     sys.exit(1)
@@ -36,8 +37,8 @@
             "answer_model": "gemma-3-27b-it",
             "number_of_initial_queries": 2,
             "max_research_loops": 1,
-            "require_planning_confirmation": False
-        }
+            "require_planning_confirmation": False,
+        },
     },
     {
         "name": "02_solid_state_batteries_deep",
@@ -48,8 +49,8 @@
             "answer_model": "gemma-3-27b-it",
             "number_of_initial_queries": 4,
             "max_research_loops": 3,
-            "require_planning_confirmation": False
-        }
+            "require_planning_confirmation": False,
+        },
     },
     {
         "name": "03_remote_work_broad",
@@ -60,8 +61,8 @@
             "answer_model": "gemma-3-27b-it",
             "number_of_initial_queries": 6,
             "max_research_loops": 2,
-            "require_planning_confirmation": False
-        }
+            "require_planning_confirmation": False,
+        },
     },
     {
         "name": "04_rust_vs_cpp_technical",
@@ -72,14 +73,15 @@
             "answer_model": "gemma-3-27b-it",
             "number_of_initial_queries": 3,
             "max_research_loops": 2,
-            "require_planning_confirmation": False
-        }
-    }
+            "require_planning_confirmation": False,
+        },
+    },
 ]
 
 OUTPUT_DIR = REPO_ROOT / "docs" / "sample_reports"
 OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
 
+
 async def generate_report(run_config):
     name = run_config["name"]
     topic = run_config["topic"]
@@ -89,18 +91,16 @@ async def generate_report(run_config):
     print(f"Topic: {topic}")
     print(f"Config: {conf_dict}")
 
-    inputs = {
-        "messages": [HumanMessage(content=topic)]
-    }
+    inputs = {"messages": [HumanMessage(content=topic)]}
 
     # Configuration wrapper for LangGraph
     # We pass the Configuration object fields via 'configurable' dict
     runnable_config = {
         "configurable": {
             "thread_id": f"sample_report_{name}_{int(datetime.now().timestamp())}",
-            **conf_dict
+            **conf_dict,
         },
-        "recursion_limit": 100
+        "recursion_limit": 100,
     }
 
     report_content = ""
@@ -123,15 +123,16 @@ async def generate_report(run_config):
         duration = (datetime.now() - start_time).total_seconds()
         metadata = {
             "duration_seconds": duration,
-            "total_steps": len(final_state.get("messages", [])), # Proxy for steps
+            "total_steps": len(final_state.get("messages", [])),  # Proxy for steps
             "research_loops_performed": conf_dict.get("max_research_loops"),
-            "model": conf_dict.get("query_generator_model")
+            "model": conf_dict.get("query_generator_model"),
         }
 
     except Exception as e:
         print(f"Error generating report for {name}: {e}")
         report_content = f"Error generating report: {str(e)}"
         import traceback
+
         traceback.print_exc()
 
     # Save Artifacts
@@ -140,22 +141,27 @@ async def generate_report(run_config):
 
     header = f"""# Sample Report: {topic}
 > **Configuration**: {name}
-> **Model**: {conf_dict['query_generator_model']}
-> **Depth**: {conf_dict['max_research_loops']} Loops
-> **Breadth**: {conf_dict['number_of_initial_queries']} Initial Queries
-> **Duration**: {metadata.get('duration_seconds', 0):.2f}s
+> **Model**: {conf_dict["query_generator_model"]}
+> **Depth**: {conf_dict["max_research_loops"]} Loops
+> **Breadth**: {conf_dict["number_of_initial_queries"]} Initial Queries
+> **Duration**: {metadata.get("duration_seconds", 0):.2f}s
 
 ---
 
 """
-    with open(md_filename, "w", encoding="utf-8") as f:
-        f.write(header + report_content)
+    # SonarCloud: Use an asynchronous file API instead of synchronous open() in this async function.
+    import aiofiles
+
+    async with aiofiles.open(md_filename, "w", encoding="utf-8") as f:
+        await f.write(header + report_content)
 
     print(f"Saved report to {md_filename}")
     return metadata
 
+
 async def main():
     import argparse
+
     parser = argparse.ArgumentParser()
     parser.add_argument("--index", type=int, help="Index of config to run (0-3)")
     args = parser.parse_args()
@@ -175,5 +181,6 @@ async def main():
         print("\nAll runs complete.")
         print(json.dumps(results, indent=2))
 
+
 if __name__ == "__main__":
     asyncio.run(main())