From 1cbb1b5d66137ab4953248b4aca36ce3a7054ffd Mon Sep 17 00:00:00 2001
From: "DESKTOP-RTLN3BA\\$punk" <vermarohanfinal@gmail.com>
Date: Sun, 21 Dec 2025 23:31:11 -0800
Subject: [PATCH] refactor: remove chat-related fields and legacy podcast
 generation function

---
 .../50_remove_podcast_chat_columns.py         | 48 +++++++++++++++++++
 surfsense_backend/app/db.py                   |  4 --
 surfsense_backend/app/schemas/podcasts.py     |  2 -
 .../app/tasks/celery_tasks/podcast_tasks.py   |  5 +-
 surfsense_backend/app/tasks/podcast_tasks.py  | 11 +----
 5 files changed, 50 insertions(+), 20 deletions(-)
 create mode 100644 surfsense_backend/alembic/versions/50_remove_podcast_chat_columns.py

diff --git a/surfsense_backend/alembic/versions/50_remove_podcast_chat_columns.py b/surfsense_backend/alembic/versions/50_remove_podcast_chat_columns.py
new file mode 100644
index 000000000..c0c9e741b
--- /dev/null
+++ b/surfsense_backend/alembic/versions/50_remove_podcast_chat_columns.py
@@ -0,0 +1,48 @@
+"""50_remove_podcast_chat_columns
+
+Revision ID: 50
+Revises: 49
+Create Date: 2025-12-21
+
+Removes chat_id and chat_state_version columns from podcasts table.
+These columns were used for the old chat system podcast linking which
+has been replaced by the new-chat content-based podcast generation.
+"""
+
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from sqlalchemy import inspect
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "50"
+down_revision: str | None = "49"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    """Upgrade schema - Remove chat_id and chat_state_version from podcasts."""
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    columns = [col["name"] for col in inspector.get_columns("podcasts")]
+
+    if "chat_id" in columns:
+        op.drop_column("podcasts", "chat_id")
+
+    if "chat_state_version" in columns:
+        op.drop_column("podcasts", "chat_state_version")
+
+
+def downgrade() -> None:
+    """Downgrade schema - Re-add chat_id and chat_state_version to podcasts."""
+    op.add_column(
+        "podcasts",
+        sa.Column("chat_id", sa.Integer(), nullable=True),
+    )
+    op.add_column(
+        "podcasts",
+        sa.Column("chat_state_version", sa.String(100), nullable=True),
+    )
diff --git a/surfsense_backend/app/db.py b/surfsense_backend/app/db.py
index b563cd594..815115640 100644
--- a/surfsense_backend/app/db.py
+++ b/surfsense_backend/app/db.py
@@ -436,10 +436,6 @@ class Podcast(BaseModel, TimestampMixin):
     )
     search_space = relationship("SearchSpace", back_populates="podcasts")
 
-    # Optional: link to chat thread (null for content-based podcasts from new-chat)
-    chat_id = Column(Integer, nullable=True)
-    chat_state_version = Column(String(100), nullable=True)
-
 
 class SearchSpace(BaseModel, TimestampMixin):
     __tablename__ = "searchspaces"
diff --git a/surfsense_backend/app/schemas/podcasts.py b/surfsense_backend/app/schemas/podcasts.py
index bcf50a710..72c915d88 100644
--- a/surfsense_backend/app/schemas/podcasts.py
+++ b/surfsense_backend/app/schemas/podcasts.py
@@ -13,8 +13,6 @@ class PodcastBase(BaseModel):
     podcast_transcript: list[dict[str, Any]] | None = None
     file_location: str | None = None
     search_space_id: int
-    chat_id: int | None = None
-    chat_state_version: str | None = None
 
 
 class PodcastCreate(PodcastBase):
diff --git a/surfsense_backend/app/tasks/celery_tasks/podcast_tasks.py b/surfsense_backend/app/tasks/celery_tasks/podcast_tasks.py
index 7f67ba599..40fe21f0d 100644
--- a/surfsense_backend/app/tasks/celery_tasks/podcast_tasks.py
+++ b/surfsense_backend/app/tasks/celery_tasks/podcast_tasks.py
@@ -72,8 +72,7 @@ def generate_content_podcast_task(
     """
     Celery task to generate podcast from source content (for new-chat).
 
-    Unlike generate_chat_podcast which requires a chat_id, this task
-    generates a podcast directly from provided content.
+    This task generates a podcast directly from provided content.
 
     Args:
         source_content: The text content to convert into a podcast
@@ -164,8 +163,6 @@ async def _generate_content_podcast(
                 podcast_transcript=serializable_transcript,
                 file_location=file_path,
                 search_space_id=search_space_id,
-                chat_id=None,  # No chat_id for new-chat podcasts
-                chat_state_version=None,
             )
             session.add(podcast)
             await session.commit()
diff --git a/surfsense_backend/app/tasks/podcast_tasks.py b/surfsense_backend/app/tasks/podcast_tasks.py
index 21cd0d947..b3b01eb93 100644
--- a/surfsense_backend/app/tasks/podcast_tasks.py
+++ b/surfsense_backend/app/tasks/podcast_tasks.py
@@ -7,19 +7,10 @@ if called. Use generate_content_podcast_task in celery_tasks/podcast_tasks.py
 for new-chat podcast generation instead.
 """
 
-from sqlalchemy.ext.asyncio import AsyncSession
-
 from app.db import Podcast  # noqa: F401 - imported for backwards compatibility
 
 
-async def generate_chat_podcast(
-    session: AsyncSession,
-    chat_id: int,
-    search_space_id: int,
-    user_id: int,
-    podcast_title: str | None = None,
-    user_prompt: str | None = None,
-):
+async def generate_chat_podcast(*args, **kwargs):
     """
     Legacy function for generating podcasts from old chat system.