ci: add pre-commit hook and fix linting issues (#545)

* style: deactivate PLC0415 only on part that it's ok

+ re-run pre-commit run --all

* ci: add pre-commit hook

* build: move from yarn to pnpm

* build: move from yarn to pnpm

* build: fix node-version

* ci: install pnpm prior node (?)

* build: update deps and pnpm trying to fix vercel build

* feat: docker www corepack

* style: pre-commit

---------

Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com>

server/migrations/versions/0bc0f3ff0111_add_webvtt_field_to_transcript.py

@@ -5,23 +5,21 @@ Revises: b7df9609542c
 Create Date: 2025-08-05 19:36:41.740957
 
 """
+
 from typing import Sequence, Union
 
-from alembic import op
 import sqlalchemy as sa
+from alembic import op
 
-
-revision: str = '0bc0f3ff0111'
-down_revision: Union[str, None] = 'b7df9609542c'
+revision: str = "0bc0f3ff0111"
+down_revision: Union[str, None] = "b7df9609542c"
 branch_labels: Union[str, Sequence[str], None] = None
 depends_on: Union[str, Sequence[str], None] = None
 
 
 def upgrade() -> None:
-    op.add_column('transcript',
-        sa.Column('webvtt', sa.Text(), nullable=True)
-    )
+    op.add_column("transcript", sa.Column("webvtt", sa.Text(), nullable=True))
 
 
 def downgrade() -> None:
-    op.drop_column('transcript', 'webvtt')
+    op.drop_column("transcript", "webvtt")

server/migrations/versions/116b2f287eab_add_full_text_search.py

@@ -5,43 +5,42 @@ Revises: 0bc0f3ff0111
 Create Date: 2025-08-07 11:27:38.473517
 
 """
+
 from typing import Sequence, Union
 
 from alembic import op
-import sqlalchemy as sa
 
-
-revision: str = '116b2f287eab'
-down_revision: Union[str, None] = '0bc0f3ff0111'
+revision: str = "116b2f287eab"
+down_revision: Union[str, None] = "0bc0f3ff0111"
 branch_labels: Union[str, Sequence[str], None] = None
 depends_on: Union[str, Sequence[str], None] = None
 
 
 def upgrade() -> None:
     conn = op.get_bind()
-    if conn.dialect.name != 'postgresql':
+    if conn.dialect.name != "postgresql":
         return
-    
+
     op.execute("""
-        ALTER TABLE transcript ADD COLUMN search_vector_en tsvector 
+        ALTER TABLE transcript ADD COLUMN search_vector_en tsvector
         GENERATED ALWAYS AS (
             setweight(to_tsvector('english', coalesce(title, '')), 'A') ||
             setweight(to_tsvector('english', coalesce(webvtt, '')), 'B')
         ) STORED
     """)
-    
+
     op.create_index(
-        'idx_transcript_search_vector_en',
-        'transcript',
-        ['search_vector_en'],
-        postgresql_using='gin'
+        "idx_transcript_search_vector_en",
+        "transcript",
+        ["search_vector_en"],
+        postgresql_using="gin",
     )
 
 
 def downgrade() -> None:
     conn = op.get_bind()
-    if conn.dialect.name != 'postgresql':
+    if conn.dialect.name != "postgresql":
         return
-    
-    op.drop_index('idx_transcript_search_vector_en', table_name='transcript')
-    op.drop_column('transcript', 'search_vector_en')
+
+    op.drop_index("idx_transcript_search_vector_en", table_name="transcript")
+    op.drop_column("transcript", "search_vector_en")

server/migrations/versions/8120ebc75366_populate_webvtt_from_topics.py

@@ -5,17 +5,16 @@ Revises: 116b2f287eab
 Create Date: 2025-08-11 19:11:01.316947
 
 """
+
 import json
 from typing import Sequence, Union
 
 from alembic import op
-import sqlalchemy as sa
 from sqlalchemy import text
 
-
 # revision identifiers, used by Alembic.
-revision: str = '8120ebc75366'
-down_revision: Union[str, None] = '116b2f287eab'
+revision: str = "8120ebc75366"
+down_revision: Union[str, None] = "116b2f287eab"
 branch_labels: Union[str, Sequence[str], None] = None
 depends_on: Union[str, Sequence[str], None] = None
 
@@ -88,7 +87,7 @@ def upgrade() -> None:
                 # Update the webvtt field
                 connection.execute(
                     text("UPDATE transcript SET webvtt = :webvtt WHERE id = :id"),
-                    {"webvtt": webvtt_content, "id": transcript_id}
+                    {"webvtt": webvtt_content, "id": transcript_id},
                 )
                 updated_count += 1
                 print(f"✓ Updated transcript {transcript_id}")
@@ -104,6 +103,4 @@ def upgrade() -> None:
 
 def downgrade() -> None:
     """Clear WebVTT field for all transcripts."""
-    op.execute(
-        text("UPDATE transcript SET webvtt = NULL")
-    )
+    op.execute(text("UPDATE transcript SET webvtt = NULL"))

server/pyproject.toml

@@ -104,3 +104,7 @@ select = [
 
 [tool.ruff.lint.per-file-ignores]
 "reflector/processors/summary/summary_builder.py" = ["E501"]
+"gpu/**.py" = ["PLC0415"]
+"reflector/tools/**.py" = ["PLC0415"]
+"migrations/versions/**.py" = ["PLC0415"]
+"tests/**.py" = ["PLC0415"]

server/reflector/db/transcripts.py

@@ -21,7 +21,7 @@ from reflector.db.rooms import rooms
 from reflector.db.utils import is_postgresql
 from reflector.processors.types import Word as ProcessorWord
 from reflector.settings import settings
-from reflector.storage import get_transcripts_storage, get_recordings_storage
+from reflector.storage import get_recordings_storage, get_transcripts_storage
 from reflector.utils import generate_uuid4
 from reflector.utils.webvtt import topics_to_webvtt
 

server/reflector/storage/__init__.py

@@ -3,6 +3,7 @@ from reflector.settings import settings
 
 
 def get_transcripts_storage() -> Storage:
+    assert settings.TRANSCRIPT_STORAGE_BACKEND
     return Storage.get_instance(
         name=settings.TRANSCRIPT_STORAGE_BACKEND,
         settings_prefix="TRANSCRIPT_STORAGE_",

server/reflector/views/_range_requests_response.py

@@ -44,8 +44,6 @@ def range_requests_response(
     """Returns StreamingResponse using Range Requests of a given file"""
 
     if not os.path.exists(file_path):
-        from fastapi import HTTPException
-
         raise HTTPException(status_code=404, detail="File not found")
 
     file_size = os.stat(file_path).st_size

server/reflector/views/transcripts_webrtc.py

@@ -26,7 +26,7 @@ async def transcript_record_webrtc(
         raise HTTPException(status_code=400, detail="Transcript is locked")
 
     # create a pipeline runner
-    from reflector.pipelines.main_live_pipeline import PipelineMainLive
+    from reflector.pipelines.main_live_pipeline import PipelineMainLive  # noqa: PLC0415
 
     pipeline_runner = PipelineMainLive(transcript_id=transcript_id)