refactor: rename the application package to docsgpt

The backend import package is now docsgpt, the name it will carry on PyPI;
application was far too generic to install into anyone's site-packages.
git mv plus a mechanical rewrite of every import, dotted string and path
reference: 734 Python files, the compose files, Dockerfile, workflows, docs,
setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage
config, .gitignore. Behaviour is unchanged.

Kept for one release:
- A top-level application package whose meta-path finder resolves
  application.x.y to the already-imported docsgpt.x.y object, so old imports
  and entry points (celery -A application.app.celery,
  uvicorn application.asgi:asgi_app) keep working with a FutureWarning.
- Celery registers every application.* task name as an alias of its
  docsgpt.* task on start-up, so messages queued by the previous release still
  run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries
  the previous release wrote are left unread instead of firing twice.

The backend image builds from the repository root (docker build -f
docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore
allow-lists docsgpt/ and application/ and keeps caches, local data, .env
files, the sample index files and the Dockerfile out. Compose and the image
workflows point at the new context.
This commit is contained in:
Alex committed 2026-09-07 10:20:43 +01:00
1 parent 3e7f1f91b4
commit 574f96341e
984 files changed
+9847 -9682

No files matched your search

+12 -12
View File
@@ -1,4 +1,4 @@
"""Smoke tests for ``application.worker.remote_worker`` and ``sync_worker``.
"""Smoke tests for ``docsgpt.worker.remote_worker`` and ``sync_worker``.
``remote_worker`` in ``sync`` mode does one PG write: it bumps
``sources.date`` on the referenced source row to ``now()``. That's the
@@ -19,14 +19,14 @@ from unittest.mock import MagicMock
import pytest
from application.parser.schema.base import Document
from application.storage.db.repositories.sources import SourcesRepository
from docsgpt.parser.schema.base import Document
from docsgpt.storage.db.repositories.sources import SourcesRepository
@pytest.fixture
def _mock_remote_pipeline(monkeypatch):
"""Stub out the non-PG boundaries used by ``remote_worker``."""
from application import worker
from docsgpt import worker
fake_loader = MagicMock(name="remote_loader")
fake_loader.load_data.return_value = [
@@ -59,7 +59,7 @@ class TestRemoteWorkerSyncUpdatesDate:
monkeypatch,
_mock_remote_pipeline,
):
from application import worker
from docsgpt import worker
# Seed a source with a known old ``date`` we can compare against.
import datetime as dt
@@ -111,7 +111,7 @@ class TestSyncWorker:
each to ``sync``. We assert the seeded row is discovered and
forwarded with the right doc_id — the nested ``sync`` call is
stubbed so we don't re-run the whole remote pipeline here."""
from application import worker
from docsgpt import worker
src = SourcesRepository(pg_conn).create(
"weekly-feed",
@@ -157,7 +157,7 @@ class TestSyncWorker:
):
"""connector:* sources have no RemoteCreator loader — sync_worker
must skip them, not dispatch them into sync()."""
from application import worker
from docsgpt import worker
SourcesRepository(pg_conn).create(
"drive-folder",
@@ -194,7 +194,7 @@ class TestSyncWorker:
):
"""Regression: remote_data reads back as a dict; sync_worker must
hand the loader the URL string, not the raw dict."""
from application import worker
from docsgpt import worker
SourcesRepository(pg_conn).create(
"docs-crawl",
@@ -249,7 +249,7 @@ class TestSyncWorker:
):
"""A URL source whose remote_data dict has no URL key normalizes
to None — sync_worker must skip it, not dispatch a doomed sync()."""
from application import worker
from docsgpt import worker
SourcesRepository(pg_conn).create(
"broken-feed",
@@ -292,7 +292,7 @@ class TestRemoteWorkerPathTraversal:
monkeypatch,
_mock_remote_pipeline,
):
from application import worker
from docsgpt import worker
created_paths: list[str] = []
deleted_paths: list[str] = []
@@ -350,7 +350,7 @@ class TestRemoteWorkerDeterministicSourceId:
monkeypatch,
_mock_remote_pipeline,
):
from application import worker
from docsgpt import worker
captured: list[dict] = []
monkeypatch.setattr(
@@ -382,7 +382,7 @@ class TestRemoteWorkerDeterministicSourceId:
monkeypatch,
_mock_remote_pipeline,
):
from application import worker
from docsgpt import worker
captured: list[dict] = []
monkeypatch.setattr(