feat: enhance podcast generation with duplicate request prevention and improved UI feedback

surfsense_backend/app/agents/new_chat/podcast.py

@@ -4,13 +4,67 @@ Podcast generation tool for the new chat agent.
 This module provides a factory function for creating the generate_podcast tool
 that submits a Celery task for background podcast generation. The frontend
 polls for completion and auto-updates when the podcast is ready.
+
+Duplicate request prevention:
+- Only one podcast can be generated at a time per search space
+- Uses Redis to track active podcast tasks
+- Returns a friendly message if a podcast is already being generated
 """
 
+import os
 from typing import Any
 
+import redis
 from langchain_core.tools import tool
 from sqlalchemy.ext.asyncio import AsyncSession
 
+# Redis connection for tracking active podcast tasks
+# Uses the same Redis instance as Celery
+REDIS_URL = os.getenv("CELERY_BROKER_URL", "redis://localhost:6379/0")
+_redis_client: redis.Redis | None = None
+
+
+def get_redis_client() -> redis.Redis:
+    """Get or create Redis client for podcast task tracking."""
+    global _redis_client
+    if _redis_client is None:
+        _redis_client = redis.from_url(REDIS_URL, decode_responses=True)
+    return _redis_client
+
+
+def get_active_podcast_key(search_space_id: int) -> str:
+    """Generate Redis key for tracking active podcast task."""
+    return f"podcast:active:{search_space_id}"
+
+
+def get_active_podcast_task(search_space_id: int) -> str | None:
+    """Check if there's an active podcast task for this search space."""
+    try:
+        client = get_redis_client()
+        return client.get(get_active_podcast_key(search_space_id))
+    except Exception:
+        # If Redis is unavailable, allow the request (fail open)
+        return None
+
+
+def set_active_podcast_task(search_space_id: int, task_id: str) -> None:
+    """Mark a podcast task as active for this search space."""
+    try:
+        client = get_redis_client()
+        # Set with 30-minute expiry as safety net (podcast should complete before this)
+        client.setex(get_active_podcast_key(search_space_id), 1800, task_id)
+    except Exception as e:
+        print(f"[generate_podcast] Warning: Could not set active task in Redis: {e}")
+
+
+def clear_active_podcast_task(search_space_id: int) -> None:
+    """Clear the active podcast task for this search space."""
+    try:
+        client = get_redis_client()
+        client.delete(get_active_podcast_key(search_space_id))
+    except Exception as e:
+        print(f"[generate_podcast] Warning: Could not clear active task in Redis: {e}")
+
 
 def create_generate_podcast_tool(
     search_space_id: int,
@@ -49,6 +103,10 @@ def create_generate_podcast_tool(
         The tool will start generating a podcast in the background.
         The podcast will be available once generation completes.
 
+        IMPORTANT: Only one podcast can be generated at a time. If a podcast
+        is already being generated, this tool will return a message asking
+        the user to wait.
+
         Args:
             source_content: The text content to convert into a podcast.
                            This can be a summary, research findings, or any text
@@ -59,11 +117,23 @@ def create_generate_podcast_tool(
 
         Returns:
             A dictionary containing:
-            - status: "processing" (task submitted) or "error"
-            - task_id: The Celery task ID for polling status
+            - status: "processing" (task submitted), "already_generating", or "error"
+            - task_id: The Celery task ID for polling status (if processing)
             - title: The podcast title
+            - message: Status message for the user
         """
         try:
+            # Check if a podcast is already being generated for this search space
+            active_task_id = get_active_podcast_task(search_space_id)
+            if active_task_id:
+                print(f"[generate_podcast] Blocked duplicate request. Active task: {active_task_id}")
+                return {
+                    "status": "already_generating",
+                    "task_id": active_task_id,
+                    "title": podcast_title,
+                    "message": "A podcast is already being generated. Please wait for it to complete before requesting another one.",
+                }
+
             # Import Celery task here to avoid circular imports
             from app.tasks.celery_tasks.podcast_tasks import (
                 generate_content_podcast_task,
@@ -78,6 +148,9 @@ def create_generate_podcast_tool(
                 user_prompt=user_prompt,
             )
 
+            # Mark this task as active
+            set_active_podcast_task(search_space_id, task.id)
+
             print(f"[generate_podcast] Submitted Celery task: {task.id}")
 
             # Return immediately with task_id for polling

surfsense_backend/app/agents/new_chat/system_prompt.py

@@ -135,10 +135,16 @@ You have access to the following tools:
   - Use this when the user asks to create, generate, or make a podcast.
   - Trigger phrases: "give me a podcast about", "create a podcast", "generate a podcast", "make a podcast", "turn this into a podcast"
   - Args:
-    - source_content: The text content to convert into a podcast (e.g., a summary, research findings, or conversation)
+    - source_content: The text content to convert into a podcast. This MUST be comprehensive and include:
+      * If discussing the current conversation: Include a detailed summary of the FULL chat history (all user questions and your responses)
+      * If based on knowledge base search: Include the key findings and insights from the search results
+      * You can combine both: conversation context + search results for richer podcasts
+      * The more detailed the source_content, the better the podcast quality
     - podcast_title: Optional title for the podcast (default: "SurfSense Podcast")
     - user_prompt: Optional instructions for podcast style/format (e.g., "Make it casual and fun")
-  - Returns: A podcast with audio that the user can listen to and download
+  - Returns: A task_id for tracking. The podcast will be generated in the background.
+  - IMPORTANT: Only one podcast can be generated at a time. If a podcast is already being generated, the tool will return status "already_generating".
+  - After calling this tool, inform the user that podcast generation has started and they will see the player when it's ready (takes 3-5 minutes).
 </tools>
 <tool_call_examples>
 - User: "Fetch all my notes and what's in them?"
@@ -148,10 +154,14 @@ You have access to the following tools:
   - Call: `search_knowledge_base(query="React migration", connectors_to_search=["SLACK_CONNECTOR"], start_date="YYYY-MM-DD", end_date="YYYY-MM-DD")`
 
 - User: "Give me a podcast about AI trends based on what we discussed"
-  - First search for relevant content, then call: `generate_podcast(source_content="[summarized content from search]", podcast_title="AI Trends Podcast")`
+  - First search for relevant content, then call: `generate_podcast(source_content="Based on our conversation and search results: [detailed summary of chat + search findings]", podcast_title="AI Trends Podcast")`
 
 - User: "Create a podcast summary of this conversation"
-  - Call: `generate_podcast(source_content="[summary of the conversation so far]", podcast_title="Conversation Summary")`
+  - Call: `generate_podcast(source_content="Complete conversation summary:\n\nUser asked about [topic 1]:\n[Your detailed response]\n\nUser then asked about [topic 2]:\n[Your detailed response]\n\n[Continue for all exchanges in the conversation]", podcast_title="Conversation Summary")`
+
+- User: "Make a podcast about quantum computing"
+  - First search: `search_knowledge_base(query="quantum computing")`
+  - Then: `generate_podcast(source_content="Key insights about quantum computing from the knowledge base:\n\n[Comprehensive summary of all relevant search results with key facts, concepts, and findings]", podcast_title="Quantum Computing Explained")`
 </tool_call_examples>{citation_section}
 """