Implement MVP podcast generation

.env.example

@@ -1,53 +1,68 @@
-# Domain
-# This would be set to the production domain with an env var on deployment
-# used by Traefik to transmit traffic and aqcuire TLS certificates
-DOMAIN=localhost
-# To test the local Traefik config
-# DOMAIN=localhost.tiangolo.com
-
-# Used by the backend to generate links in emails to the frontend
-# In staging and production, set this env var to the frontend host, e.g.
-# FRONTEND_HOST=https://dashboard.example.com
-
-# Environment: local, staging, production
-ENVIRONMENT=local
-
-PROJECT_NAME="Study Companion Project"
-STACK_NAME=study-companion-project
-
-# Backend
-BACKEND_CORS_ORIGINS="http://localhost,http://localhost:5173,http://localhost:3000,http://localhost:3001,https://localhost,https://localhost:5173,http://localhost.tiangolo.com"
-SECRET_KEY=changethis
-FIRST_SUPERUSER=admin@example.com
-FIRST_SUPERUSER_PASSWORD=changethis
-
-# Emails
-SMTP_HOST=
-SMTP_USER=
-SMTP_PASSWORD=
-EMAILS_FROM_EMAIL=info@example.com
-SMTP_TLS=True
-SMTP_SSL=False
-SMTP_PORT=587
-
-# Postgres
-POSTGRES_SERVER=localhost
-POSTGRES_PORT=5432
-POSTGRES_DB=app
-POSTGRES_USER=postgres
-POSTGRES_PASSWORD=changethis
-
-SENTRY_DSN=
-
-# Configure these with your own Docker registry images
-DOCKER_IMAGE_BACKEND=backend
-DOCKER_IMAGE_NEXT_APP=frontend
-
-NEXT_PUBLIC_API_URL=http://localhost:8000
-
-
-PINECONE_API_KEY=changethis
-
-OPENAI_API_KEY=changethis
-
-NEXT_PUBLIC_BACKEND_BASE_URL=http://localhost:8000
+# Domain
+# This would be set to the production domain with an env var on deployment
+# used by Traefik to transmit traffic and aqcuire TLS certificates
+DOMAIN=localhost
+# To test the local Traefik config
+# DOMAIN=localhost.tiangolo.com
+
+# Used by the backend to generate links in emails to the frontend
+# In staging and production, set this env var to the frontend host, e.g.
+# FRONTEND_HOST=https://dashboard.example.com
+
+# Environment: local, staging, production
+ENVIRONMENT=local
+
+PROJECT_NAME="Study Companion Project"
+STACK_NAME=study-companion-project
+
+# Backend
+BACKEND_CORS_ORIGINS="http://localhost,http://localhost:5173,http://localhost:3000,http://localhost:3001,https://localhost,https://localhost:5173,http://localhost.tiangolo.com"
+SECRET_KEY=changethis
+FIRST_SUPERUSER=admin@example.com
+FIRST_SUPERUSER_PASSWORD=changethis
+
+# Emails
+SMTP_HOST=
+SMTP_USER=
+SMTP_PASSWORD=
+EMAILS_FROM_EMAIL=info@example.com
+SMTP_TLS=True
+SMTP_SSL=False
+SMTP_PORT=587
+
+# Postgres
+POSTGRES_SERVER=localhost
+POSTGRES_PORT=5432
+POSTGRES_DB=app
+POSTGRES_USER=postgres
+POSTGRES_PASSWORD=changethis
+
+SENTRY_DSN=
+
+# Configure these with your own Docker registry images
+DOCKER_IMAGE_BACKEND=backend
+DOCKER_IMAGE_NEXT_APP=frontend
+
+NEXT_PUBLIC_API_URL=http://localhost:8000
+
+
+PINECONE_API_KEY=changethis
+
+OPENAI_API_KEY=changethis
+
+NEXT_PUBLIC_BACKEND_BASE_URL=http://localhost:8000
+
+NEXT_INTERNAL_BACKEND_BASE_URL=http://backend:8000
+
+# Podcast storage configuration
+# "local" will store files under backend container at /app/podcasts
+# "s3" will upload to an S3 bucket using the credentials below
+PODCAST_STORAGE=local
+PODCAST_LOCAL_DIR=/app/podcasts
+AWS_ACCESS_KEY_ID=AKIA...
+AWS_SECRET_ACCESS_KEY=ieb...
+AWS_REGION=changethis
+S3_BUCKET_NAME=changethis
+S3_PREFIX=podcasts/
+PODCAST_TEACHER_VOICE=coral
+PODCAST_STUDENT_VOICE=alloy

.gitignore

@@ -1,8 +1,8 @@
-.DS_Store
-htmlcov
-.env
-*.env
-.env*
-/.idea/
-frontend/.*
-.aider*
+.DS_Store
+htmlcov
+*.env
+/.idea/
+frontend/.*
+.aider*
+config.bat
+node_modules

backend/app/alembic/versions/10368f38610b_fix_delete_document_error.py

@@ -1,46 +1,46 @@
-"""Fix delete document error.
-
-Revision ID: 10368f38610b
-Revises: b5370243d0bc
-Create Date: 2025-10-02 07:06:36.831373
-
-"""
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy import inspect
-import sqlmodel.sql.sqltypes
-
-
-# revision identifiers, used by Alembic.
-revision = '10368f38610b'
-down_revision = 'b5370243d0bc'
-branch_labels = None
-depends_on = None
-
-
-def upgrade():
-    conn = op.get_bind()
-    inspector = inspect(conn)
-    if 'chat' not in inspector.get_table_names():
-        # ### commands auto generated by Alembic - please adjust! ###
-        op.create_table('chat',
-            sa.Column('message', sqlmodel.sql.sqltypes.AutoString(length=1024), nullable=True),
-            sa.Column('is_system', sa.Boolean(), nullable=False),
-            sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
-            sa.Column('updated_at', sa.DateTime(), nullable=False),
-            sa.Column('id', sa.Uuid(), nullable=False),
-            sa.Column('course_id', sa.Uuid(), nullable=False),
-            sa.ForeignKeyConstraint(['course_id'], ['course.id'], ondelete='CASCADE'),
-            sa.PrimaryKeyConstraint('id')
-        )
-        op.drop_constraint(op.f('quizattempt_quiz_id_fkey'), 'quizattempt', type_='foreignkey')
-        op.create_foreign_key(None, 'quizattempt', 'quiz', ['quiz_id'], ['id'], ondelete='CASCADE')
-        # ### end Alembic commands ###
-
-
-def downgrade():
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_constraint(None, 'quizattempt', type_='foreignkey')
-    op.create_foreign_key(op.f('quizattempt_quiz_id_fkey'), 'quizattempt', 'quiz', ['quiz_id'], ['id'])
-    op.drop_table('chat')
-    # ### end Alembic commands ###
+"""Fix delete document error.
+
+Revision ID: 10368f38610b
+Revises: b5370243d0bc
+Create Date: 2025-10-02 07:06:36.831373
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy import inspect
+import sqlmodel.sql.sqltypes
+
+
+# revision identifiers, used by Alembic.
+revision = '10368f38610b'
+down_revision = 'b5370243d0bc'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    if 'chat' not in inspector.get_table_names():
+        # ### commands auto generated by Alembic - please adjust! ###
+        op.create_table('chat',
+            sa.Column('message', sqlmodel.sql.sqltypes.AutoString(length=1024), nullable=True),
+            sa.Column('is_system', sa.Boolean(), nullable=False),
+            sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
+            sa.Column('updated_at', sa.DateTime(), nullable=False),
+            sa.Column('id', sa.Uuid(), nullable=False),
+            sa.Column('course_id', sa.Uuid(), nullable=False),
+            sa.ForeignKeyConstraint(['course_id'], ['course.id'], ondelete='CASCADE'),
+            sa.PrimaryKeyConstraint('id')
+        )
+        op.drop_constraint(op.f('quizattempt_quiz_id_fkey'), 'quizattempt', type_='foreignkey')
+        op.create_foreign_key(None, 'quizattempt', 'quiz', ['quiz_id'], ['id'], ondelete='CASCADE')
+        # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_constraint(None, 'quizattempt', type_='foreignkey')
+    op.create_foreign_key(op.f('quizattempt_quiz_id_fkey'), 'quizattempt', 'quiz', ['quiz_id'], ['id'])
+    op.drop_table('chat')
+    # ### end Alembic commands ###

backend/app/alembic/versions/2042a1f0c0a1_add_podcast_table.py

@@ -0,0 +1,38 @@
+"""add podcast table
+
+Revision ID: 2042a1f0c0a1
+Revises: 10368f38610b
+Create Date: 2025-10-05 06:00:00.000000
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel.sql.sqltypes
+
+
+# revision identifiers, used by Alembic.
+revision = '2042a1f0c0a1'
+down_revision = '2cde6f094a4e'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.create_table(
+        'podcast',
+        sa.Column('id', sa.Uuid(), nullable=False),
+        sa.Column('course_id', sa.Uuid(), nullable=False),
+        sa.Column('title', sqlmodel.sql.sqltypes.AutoString(length=255), nullable=False),
+        sa.Column('transcript', sa.Text(), nullable=False),
+        sa.Column('audio_path', sqlmodel.sql.sqltypes.AutoString(length=1024), nullable=False),
+        sa.Column('storage_backend', sqlmodel.sql.sqltypes.AutoString(length=50), nullable=False),
+        sa.Column('duration_seconds', sa.Float(), nullable=True),
+        sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
+        sa.Column('updated_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['course_id'], ['course.id'], ondelete='CASCADE'),
+        sa.PrimaryKeyConstraint('id')
+    )
+
+
+def downgrade():
+    op.drop_table('podcast')

backend/app/alembic/versions/98c65ba436bd_add_cascade_delete_to_quizsession_.py

@@ -1,47 +1,47 @@
-"""Add cascade delete to quizsession.course_id
-
-Revision ID: 98c65ba436bd
-Revises: 2cde6f094a4e
-Create Date: 2025-10-06 11:31:30.334302
-
-"""
-from alembic import op
-import sqlalchemy as sa
-import sqlmodel.sql.sqltypes
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision = '98c65ba436bd'
-down_revision = '2cde6f094a4e'
-branch_labels = None
-depends_on = None
-
-
-def upgrade():
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_index(op.f('ix_flashcardset_created_at'), table_name='flashcardset')
-    op.drop_index(op.f('ix_flashcardset_document_id'), table_name='flashcardset')
-    op.drop_index(op.f('ix_flashcardset_status'), table_name='flashcardset')
-    op.drop_index(op.f('ix_flashcardset_updated_at'), table_name='flashcardset')
-    op.drop_table('flashcardset')
-    # ### end Alembic commands ###
-
-
-def downgrade():
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.create_table('flashcardset',
-    sa.Column('content_json', postgresql.JSONB(astext_type=sa.Text()), autoincrement=False, nullable=True),
-    sa.Column('document_id', sa.UUID(), autoincrement=False, nullable=False),
-    sa.Column('status', sa.VARCHAR(), autoincrement=False, nullable=False),
-    sa.Column('error_message', sa.VARCHAR(length=512), autoincrement=False, nullable=True),
-    sa.Column('id', sa.UUID(), autoincrement=False, nullable=False),
-    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=False),
-    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=False),
-    sa.ForeignKeyConstraint(['document_id'], ['document.id'], name=op.f('flashcardset_document_id_fkey')),
-    sa.PrimaryKeyConstraint('id', name=op.f('flashcardset_pkey'))
-    )
-    op.create_index(op.f('ix_flashcardset_updated_at'), 'flashcardset', ['updated_at'], unique=False)
-    op.create_index(op.f('ix_flashcardset_status'), 'flashcardset', ['status'], unique=False)
-    op.create_index(op.f('ix_flashcardset_document_id'), 'flashcardset', ['document_id'], unique=False)
-    op.create_index(op.f('ix_flashcardset_created_at'), 'flashcardset', ['created_at'], unique=False)
-    # ### end Alembic commands ###
+"""Add cascade delete to quizsession.course_id
+
+Revision ID: 98c65ba436bd
+Revises: 2cde6f094a4e
+Create Date: 2025-10-06 11:31:30.334302
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel.sql.sqltypes
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = '98c65ba436bd'
+down_revision = '2cde6f094a4e'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_flashcardset_created_at'), table_name='flashcardset')
+    op.drop_index(op.f('ix_flashcardset_document_id'), table_name='flashcardset')
+    op.drop_index(op.f('ix_flashcardset_status'), table_name='flashcardset')
+    op.drop_index(op.f('ix_flashcardset_updated_at'), table_name='flashcardset')
+    op.drop_table('flashcardset')
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('flashcardset',
+    sa.Column('content_json', postgresql.JSONB(astext_type=sa.Text()), autoincrement=False, nullable=True),
+    sa.Column('document_id', sa.UUID(), autoincrement=False, nullable=False),
+    sa.Column('status', sa.VARCHAR(), autoincrement=False, nullable=False),
+    sa.Column('error_message', sa.VARCHAR(length=512), autoincrement=False, nullable=True),
+    sa.Column('id', sa.UUID(), autoincrement=False, nullable=False),
+    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=False),
+    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=False),
+    sa.ForeignKeyConstraint(['document_id'], ['document.id'], name=op.f('flashcardset_document_id_fkey')),
+    sa.PrimaryKeyConstraint('id', name=op.f('flashcardset_pkey'))
+    )
+    op.create_index(op.f('ix_flashcardset_updated_at'), 'flashcardset', ['updated_at'], unique=False)
+    op.create_index(op.f('ix_flashcardset_status'), 'flashcardset', ['status'], unique=False)
+    op.create_index(op.f('ix_flashcardset_document_id'), 'flashcardset', ['document_id'], unique=False)
+    op.create_index(op.f('ix_flashcardset_created_at'), 'flashcardset', ['created_at'], unique=False)
+    # ### end Alembic commands ###

backend/app/alembic/versions/a9b7c6d5e4f3_merge_heads_podcast_and_dev.py

@@ -0,0 +1,27 @@
+"""merge heads: podcast + dev
+
+Revision ID: a9b7c6d5e4f3
+Revises: ('2042a1f0c0a1', '64343f21e9a8')
+Create Date: 2025-10-06 00:00:00
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = 'a9b7c6d5e4f3'
+down_revision = ('2042a1f0c0a1', '64343f21e9a8')
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # Merge point: no-op
+    pass
+
+
+def downgrade():
+    # Merge point: no-op
+    pass
+