Dev to main

.dockerignore

@@ -7,4 +7,3 @@ __pycache__
 data
 docs
 tests
-

.github/workflows/ci.yml

@@ -2,9 +2,9 @@ name: CI
 
 on:
   push:
-    branches: [main]
+    branches: [main, dev]
   pull_request:
-    branches: [main]
+    branches: [main, dev]
 
 jobs:
   python:

.gitignore

@@ -193,9 +193,9 @@ cython_debug/
 .abstra/
 
 # Visual Studio Code
-#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
 #   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   and can be added to the global gitignore or merged into this file. However, if you prefer,
 #   you could uncomment the following to ignore the entire vscode folder
 # .vscode/
 # Temporary file for partial code execution

.pre-commit-config.yaml

@@ -0,0 +1,38 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.10
+    hooks:
+      - id: ruff
+        args: [ --fix ]
+      - id: ruff-format
+
+  - repo: local
+    hooks:
+      - id: frontend-prettier
+        name: Frontend Prettier
+        entry: npm --prefix frontend run format
+        language: system
+        files: ^frontend/.*\.([jt]sx?|css|json)$
+        pass_filenames: false
+
+      - id: frontend-eslint
+        name: Frontend ESLint
+        entry: npm --prefix frontend run lint
+        language: system
+        files: ^frontend/.*\.([jt]sx?)$
+        pass_filenames: false
+
+      - id: mypy
+        name: mypy
+        entry: uv run mypy src/awaaz
+        language: system
+        files: ^src/awaaz/.*\.py$
+        pass_filenames: false

alembic/env.py

@@ -7,6 +7,7 @@
 calling code may pass an existing connection via ``config.attributes[
 "connection"]`` to share a single transaction.
 """
+
 import asyncio
 from logging.config import fileConfig
 

alembic/versions/9cbf7db8429b_initial_schema.py

@@ -1,10 +1,11 @@
 """initial schema
 
 Revision ID: 9cbf7db8429b
-Revises: 
+Revises:
 Create Date: 2026-06-27 20:22:36.367761
 
 """
+
 from collections.abc import Sequence
 
 import sqlalchemy as sa
@@ -13,113 +14,118 @@
 from alembic import op
 
 # revision identifiers, used by Alembic.
-revision: str = '9cbf7db8429b'
+revision: str = "9cbf7db8429b"
 down_revision: str | None = None
 branch_labels: str | Sequence[str] | None = None
 depends_on: str | Sequence[str] | None = None
 
 
 def upgrade() -> None:
     # ### commands auto generated by Alembic - please adjust! ###
-    op.create_table('collections',
-    sa.Column('id', sa.String(length=36), nullable=False),
-    sa.Column('name', sa.String(length=255), nullable=False),
-    sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
-    sa.Column('updated_at', sa.DateTime(timezone=True), nullable=False),
-    sa.PrimaryKeyConstraint('id')
+    op.create_table(
+        "collections",
+        sa.Column("id", sa.String(length=36), nullable=False),
+        sa.Column("name", sa.String(length=255), nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
     )
-    with op.batch_alter_table('collections', schema=None) as batch_op:
-        batch_op.create_index(batch_op.f('ix_collections_name'), ['name'], unique=True)
-
-    op.create_table('documents',
-    sa.Column('id', sa.String(length=36), nullable=False),
-    sa.Column('title', sa.String(length=255), nullable=False),
-    sa.Column('source_filename', sa.String(length=255), nullable=True),
-    sa.Column('text', sa.Text(), nullable=False),
-    sa.Column('revision', sa.Integer(), nullable=False),
-    sa.Column('author', sa.String(length=255), nullable=True),
-    sa.Column('series', sa.String(length=255), nullable=True),
-    sa.Column('tags', sa.String(length=500), nullable=True),
-    sa.Column('cover_path', sa.Text(), nullable=True),
-    sa.Column('metadata_json', sqlite.JSON(), nullable=True),
-    sa.Column('word_count', sa.Integer(), nullable=False),
-    sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
-    sa.Column('updated_at', sa.DateTime(timezone=True), nullable=False),
-    sa.PrimaryKeyConstraint('id')
+    with op.batch_alter_table("collections", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_collections_name"), ["name"], unique=True)
+
+    op.create_table(
+        "documents",
+        sa.Column("id", sa.String(length=36), nullable=False),
+        sa.Column("title", sa.String(length=255), nullable=False),
+        sa.Column("source_filename", sa.String(length=255), nullable=True),
+        sa.Column("text", sa.Text(), nullable=False),
+        sa.Column("revision", sa.Integer(), nullable=False),
+        sa.Column("author", sa.String(length=255), nullable=True),
+        sa.Column("series", sa.String(length=255), nullable=True),
+        sa.Column("tags", sa.String(length=500), nullable=True),
+        sa.Column("cover_path", sa.Text(), nullable=True),
+        sa.Column("metadata_json", sqlite.JSON(), nullable=True),
+        sa.Column("word_count", sa.Integer(), nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
     )
-    with op.batch_alter_table('documents', schema=None) as batch_op:
-        batch_op.create_index(batch_op.f('ix_documents_author'), ['author'], unique=False)
-        batch_op.create_index(batch_op.f('ix_documents_series'), ['series'], unique=False)
-
-    op.create_table('document_collections',
-    sa.Column('document_id', sa.String(length=36), nullable=False),
-    sa.Column('collection_id', sa.String(length=36), nullable=False),
-    sa.ForeignKeyConstraint(['collection_id'], ['collections.id'], ondelete='CASCADE'),
-    sa.ForeignKeyConstraint(['document_id'], ['documents.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('document_id', 'collection_id')
+    with op.batch_alter_table("documents", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_documents_author"), ["author"], unique=False)
+        batch_op.create_index(batch_op.f("ix_documents_series"), ["series"], unique=False)
+
+    op.create_table(
+        "document_collections",
+        sa.Column("document_id", sa.String(length=36), nullable=False),
+        sa.Column("collection_id", sa.String(length=36), nullable=False),
+        sa.ForeignKeyConstraint(["collection_id"], ["collections.id"], ondelete="CASCADE"),
+        sa.ForeignKeyConstraint(["document_id"], ["documents.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("document_id", "collection_id"),
     )
-    op.create_table('jobs',
-    sa.Column('id', sa.String(length=36), nullable=False),
-    sa.Column('document_id', sa.String(length=36), nullable=False),
-    sa.Column('document_revision', sa.Integer(), nullable=False),
-    sa.Column('status', sa.String(length=32), nullable=False),
-    sa.Column('backend', sa.String(length=32), nullable=False),
-    sa.Column('model', sa.String(length=255), nullable=False),
-    sa.Column('voice', sa.String(length=255), nullable=False),
-    sa.Column('speed', sa.Float(), nullable=False),
-    sa.Column('chunking_mode', sa.String(length=32), nullable=False),
-    sa.Column('character_limit', sa.Integer(), nullable=False),
-    sa.Column('error', sa.Text(), nullable=True),
-    sa.Column('output_path', sa.Text(), nullable=True),
-    sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
-    sa.Column('updated_at', sa.DateTime(timezone=True), nullable=False),
-    sa.ForeignKeyConstraint(['document_id'], ['documents.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('id')
+    op.create_table(
+        "jobs",
+        sa.Column("id", sa.String(length=36), nullable=False),
+        sa.Column("document_id", sa.String(length=36), nullable=False),
+        sa.Column("document_revision", sa.Integer(), nullable=False),
+        sa.Column("status", sa.String(length=32), nullable=False),
+        sa.Column("backend", sa.String(length=32), nullable=False),
+        sa.Column("model", sa.String(length=255), nullable=False),
+        sa.Column("voice", sa.String(length=255), nullable=False),
+        sa.Column("speed", sa.Float(), nullable=False),
+        sa.Column("chunking_mode", sa.String(length=32), nullable=False),
+        sa.Column("character_limit", sa.Integer(), nullable=False),
+        sa.Column("error", sa.Text(), nullable=True),
+        sa.Column("output_path", sa.Text(), nullable=True),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+        sa.ForeignKeyConstraint(["document_id"], ["documents.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
     )
-    with op.batch_alter_table('jobs', schema=None) as batch_op:
-        batch_op.create_index(batch_op.f('ix_jobs_status'), ['status'], unique=False)
-
-    op.create_table('chunks',
-    sa.Column('id', sa.String(length=36), nullable=False),
-    sa.Column('job_id', sa.String(length=36), nullable=False),
-    sa.Column('position', sa.Integer(), nullable=False),
-    sa.Column('text', sa.Text(), nullable=False),
-    sa.Column('status', sa.String(length=32), nullable=False),
-    sa.Column('attempts', sa.Integer(), nullable=False),
-    sa.Column('audio_path', sa.Text(), nullable=True),
-    sa.Column('error', sa.Text(), nullable=True),
-    sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
-    sa.Column('updated_at', sa.DateTime(timezone=True), nullable=False),
-    sa.ForeignKeyConstraint(['job_id'], ['jobs.id'], ondelete='CASCADE'),
-    sa.PrimaryKeyConstraint('id'),
-    sa.UniqueConstraint('job_id', 'position')
+    with op.batch_alter_table("jobs", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_jobs_status"), ["status"], unique=False)
+
+    op.create_table(
+        "chunks",
+        sa.Column("id", sa.String(length=36), nullable=False),
+        sa.Column("job_id", sa.String(length=36), nullable=False),
+        sa.Column("position", sa.Integer(), nullable=False),
+        sa.Column("text", sa.Text(), nullable=False),
+        sa.Column("status", sa.String(length=32), nullable=False),
+        sa.Column("attempts", sa.Integer(), nullable=False),
+        sa.Column("audio_path", sa.Text(), nullable=True),
+        sa.Column("error", sa.Text(), nullable=True),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
+        sa.ForeignKeyConstraint(["job_id"], ["jobs.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("job_id", "position"),
     )
-    with op.batch_alter_table('chunks', schema=None) as batch_op:
-        batch_op.create_index(batch_op.f('ix_chunks_job_id'), ['job_id'], unique=False)
-        batch_op.create_index(batch_op.f('ix_chunks_status'), ['status'], unique=False)
+    with op.batch_alter_table("chunks", schema=None) as batch_op:
+        batch_op.create_index(batch_op.f("ix_chunks_job_id"), ["job_id"], unique=False)
+        batch_op.create_index(batch_op.f("ix_chunks_status"), ["status"], unique=False)
 
     # ### end Alembic commands ###
 
 
 def downgrade() -> None:
     # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table('chunks', schema=None) as batch_op:
-        batch_op.drop_index(batch_op.f('ix_chunks_status'))
-        batch_op.drop_index(batch_op.f('ix_chunks_job_id'))
+    with op.batch_alter_table("chunks", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_chunks_status"))
+        batch_op.drop_index(batch_op.f("ix_chunks_job_id"))
 
-    op.drop_table('chunks')
-    with op.batch_alter_table('jobs', schema=None) as batch_op:
-        batch_op.drop_index(batch_op.f('ix_jobs_status'))
+    op.drop_table("chunks")
+    with op.batch_alter_table("jobs", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_jobs_status"))
 
-    op.drop_table('jobs')
-    op.drop_table('document_collections')
-    with op.batch_alter_table('documents', schema=None) as batch_op:
-        batch_op.drop_index(batch_op.f('ix_documents_series'))
-        batch_op.drop_index(batch_op.f('ix_documents_author'))
+    op.drop_table("jobs")
+    op.drop_table("document_collections")
+    with op.batch_alter_table("documents", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_documents_series"))
+        batch_op.drop_index(batch_op.f("ix_documents_author"))
 
-    op.drop_table('documents')
-    with op.batch_alter_table('collections', schema=None) as batch_op:
-        batch_op.drop_index(batch_op.f('ix_collections_name'))
+    op.drop_table("documents")
+    with op.batch_alter_table("collections", schema=None) as batch_op:
+        batch_op.drop_index(batch_op.f("ix_collections_name"))
 
-    op.drop_table('collections')
+    op.drop_table("collections")
     # ### end Alembic commands ###

docs/architecture.md

@@ -20,4 +20,3 @@ input above configured backend limit.
 Job states: `queued`, `running`, `paused`, `failed`, `cancelled`, `completed`. Chunk states:
 `pending`, `processing`, `failed`, `completed`. Worker startup resets abandoned `processing`
 chunks to `pending`. Atomic file replacement prevents partial WAV checkpoints.
-

frontend/.dockerignore

@@ -1,4 +1,3 @@
 node_modules
 dist
 coverage
-

frontend/nginx.conf.template

@@ -50,4 +50,3 @@ server {
         try_files $uri $uri/ /index.html;
     }
 }
-