Upd user_id

legacy.py

@@ -791,7 +791,7 @@ Return only the variations, one per line, no numbering or extra text."""
         
         from utils.api.router import generate_answer_with_model
         selection = {"provider": "nvidia", "model": "meta/llama-3.1-8b-instruct"}
-        response = await generate_answer_with_model(selection, sys_prompt, user_prompt, None, nvidia_rotator)
+        response = await generate_answer_with_model(selection, sys_prompt, user_prompt, None, nvidia_rotator, user_id="system", context="legacy_analysis")
         
         # Parse variations
         variations = [line.strip() for line in response.split('\n') if line.strip()]

routes/reports.py

@@ -155,7 +155,7 @@ async def generate_report(
     # Step 2: Execute detailed subtasks based on CoT plan
     logger.info("[REPORT] Executing detailed subtasks")
     update_report_status(session_id, "processing", "Processing data...", 40)
-    detailed_analysis = await execute_detailed_subtasks(cot_plan, context_text, web_context_block, eff_name, nvidia_rotator, gemini_rotator)
+    detailed_analysis = await execute_detailed_subtasks(cot_plan, context_text, web_context_block, eff_name, nvidia_rotator, gemini_rotator, user_id)
     
     # Step 3: Synthesize comprehensive report from detailed analysis
     logger.info("[REPORT] Synthesizing comprehensive report")
@@ -453,7 +453,7 @@ Create a simple plan for this report."""
         }
 
 
-async def execute_detailed_subtasks(cot_plan: Dict[str, Any], context_text: str, web_context: str, filename: str, nvidia_rotator, gemini_rotator) -> Dict[str, Any]:
+async def execute_detailed_subtasks(cot_plan: Dict[str, Any], context_text: str, web_context: str, filename: str, nvidia_rotator, gemini_rotator, user_id: str = "") -> Dict[str, Any]:
     """Execute detailed analysis for each subtask with hierarchical section assignment and CoT references."""
     detailed_analysis = {}
     synthesis_strategy = cot_plan.get("synthesis_strategy", {})
@@ -1326,7 +1326,8 @@ Return the renumbered headings in the format: "level: new_number: heading_text"
 @app.post("/mermaid/fix")
 async def fix_mermaid_syntax(
     mermaid_code: str = Form(...),
-    error_message: str = Form("")
+    error_message: str = Form(""),
+    user_id: str = Form("system")
 ):
     """
     Fix Mermaid diagram syntax using AI for UI rendering.

utils/api/router.py

@@ -190,7 +190,7 @@ async def generate_answer_with_model(selection: Dict[str, Any], system_prompt: s
             # Fallback: Qwen → NVIDIA_SMALL
             logger.info("Falling back from Qwen to NVIDIA_SMALL")
             fallback_selection = {"provider": "nvidia", "model": NVIDIA_SMALL}
-            return await generate_answer_with_model(fallback_selection, system_prompt, user_prompt, gemini_rotator, nvidia_rotator)
+            return await generate_answer_with_model(fallback_selection, system_prompt, user_prompt, gemini_rotator, nvidia_rotator, user_id, context)
     elif provider == "nvidia_large":
         # Use NVIDIA Large (GPT-OSS) for hard/long context tasks with fallback
         try:
@@ -200,7 +200,7 @@ async def generate_answer_with_model(selection: Dict[str, Any], system_prompt: s
             # Fallback: NVIDIA_LARGE → NVIDIA_SMALL
             logger.info("Falling back from NVIDIA_LARGE to NVIDIA_SMALL")
             fallback_selection = {"provider": "nvidia", "model": NVIDIA_SMALL}
-            return await generate_answer_with_model(fallback_selection, system_prompt, user_prompt, gemini_rotator, nvidia_rotator)
+            return await generate_answer_with_model(fallback_selection, system_prompt, user_prompt, gemini_rotator, nvidia_rotator, user_id, context)
     elif provider == "nvidia_coder":
         # Use NVIDIA Coder for code generation tasks with fallback
         try:
@@ -211,7 +211,7 @@ async def generate_answer_with_model(selection: Dict[str, Any], system_prompt: s
             # Fallback: NVIDIA_CODER → NVIDIA_SMALL
             logger.info("Falling back from NVIDIA_CODER to NVIDIA_SMALL")
             fallback_selection = {"provider": "nvidia", "model": NVIDIA_SMALL}
-            return await generate_answer_with_model(fallback_selection, system_prompt, user_prompt, gemini_rotator, nvidia_rotator)
+            return await generate_answer_with_model(fallback_selection, system_prompt, user_prompt, gemini_rotator, nvidia_rotator, user_id, context)
 
     return "Unsupported provider."