mirror of
https://github.com/imartinez/privateGPT.git
synced 2026-07-17 01:48:03 +00:00
* feat: add bundle to remove * fix: spaces * feat: add xml render as skill spec * feat: add skill volume root to cache * fix: deduplicate values * fix: change the mount path to skill_id * fix: use different paths * feat: add principal (cherry picked from commit 5db64fe721d5706440ce9f342b1388ffe742bc16) # Conflicts: # private_gpt/components/code_execution/base.py # private_gpt/components/code_execution/code_execution_component.py # private_gpt/components/code_execution/local.py # private_gpt/components/environment/manager.py # private_gpt/components/tools/builders/bash_tool_builder.py # private_gpt/components/tools/builders/text_editor_tool_builder.py # private_gpt/components/tools/processors/bash_processor.py * fix: mypy ... * fix: config * fix: sandbox config * feat: add forward cookies * fix: loop * feat: add present server * feat: add feature flag for tools * refactor: move principal to another better place * feat: add api key principal * docs: fix docs * docs: add present server * fix: principal * fix: mypy * fix: avoid to block the loop * fix: blocks in expansion * fix: remove maximum concurrent users ... * fix: multiplexer * fix: readers * fix: more fixes ... * fix: impl * feat: tool scheduler * feat: add adaptative * feat: add chat worker * fix: config * fix: max * feat: add chat/tools workers * fix: mypy * feat: add generic scheduler * fix: get result * feat: do serializable the tool executor * fix: tools * fix: config * fix: config * fix: args * fix: config * fix: serializer * Revert "fix: blocks in expansion" This reverts commita2110f94a8. * fix: unify all logic * feat: add ingestion scheduler * fix: settings * fix: config * feat: add arq worker to chat * fix: arq worker * fix: add nest * fix: mypy * fix: await * fix: script stress * fix: tokenizer * fix: chat scheduler * fix: mypy * fix: add async tokenizer * fix: improve condense * fix: tool scheduler * feat: add initial real async chat worker * fix: mypy * fix: do resumable local executor ... ... ... fix: revert usleess changes fix: remove parent chat job fix: refactor fix: loop ref: rename models fix: chat engine fix: mypy ... ... ... fix: fix deps * fix: tests * fix: tests * ... * fix: stream * fix: config * fix: scheduler * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Handle PGPT_WORKER_MODE=celery in health check worker status * fix: cancel * fix: arch * fix: test ingestion * fix: deserialization of chat messages * fix: broken results * fix: mypy * fix: test * fix: config * fix: remove arq tool worker * fix: output cls * fix: preserve early resumable tool callbacks * fix: preserve async tool result order * refactor: address worker PR review comments * fix: mypy * test: colocate ARQ chat enqueue coverage * fix: remove redis from tests * fix: mypy * fix: tests * test: isolate chat mocks and cancellation timing * fix: tests * fix: tests * fix: test (cherry picked from commitf8ee460af2) * fix: worker config * test: remove flaky chat cancellation assertion (cherry picked from commit1115ff2349) # Conflicts: # tests/server/chat/test_chat_routes.py * fix: emit chat pings from stream listeners * fix: don't duplciate the output * fix: rss memory ... * fix: pass the args * fix: threads * fix: websearch --------- Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
155 lines
5.3 KiB
Python
155 lines
5.3 KiB
Python
"""Direct router tests for POST/GET/DELETE /v1/files."""
|
|
|
|
import io
|
|
from pathlib import Path
|
|
from urllib.parse import quote
|
|
|
|
from fastapi.testclient import TestClient
|
|
|
|
from private_gpt.server.files.file_models import (
|
|
DeletedFile,
|
|
FileListResponse,
|
|
FileMetadata,
|
|
)
|
|
from private_gpt.server.files.file_service import _decode_file_id, _encode_file_id
|
|
from tests.server.files.conftest import (
|
|
_FILE_CONTENT,
|
|
_FILE_NAME,
|
|
_MIME_TYPE,
|
|
_SESSION_ID,
|
|
)
|
|
|
|
|
|
def _file_url(file_id: str, scope_id: str, suffix: str = "") -> str:
|
|
"""Build a URL for a file endpoint, URL-encoding the absolute path ID."""
|
|
encoded = quote(file_id, safe="")
|
|
return f"/v1/files/{encoded}{suffix}?scope_id={scope_id}"
|
|
|
|
|
|
def test_upload_returns_file_metadata(
|
|
files_client: TestClient, volume_root: Path
|
|
) -> None:
|
|
resp = files_client.post(
|
|
f"/v1/files?scope_id={_SESSION_ID}",
|
|
files={"file": (_FILE_NAME, io.BytesIO(_FILE_CONTENT), _MIME_TYPE)},
|
|
)
|
|
assert resp.status_code == 200
|
|
meta = FileMetadata.model_validate(resp.json())
|
|
assert meta.filename == _FILE_NAME
|
|
assert meta.size_bytes == len(_FILE_CONTENT)
|
|
assert meta.downloadable is False
|
|
assert meta.scope.id == _SESSION_ID
|
|
# ID is a base64-encoded canonical path pointing into uploads/
|
|
decoded = _decode_file_id(meta.id)
|
|
assert decoded.startswith("/")
|
|
assert "uploads" in decoded
|
|
assert decoded.endswith(_FILE_NAME)
|
|
|
|
|
|
def test_list_files_empty_session(files_client: TestClient) -> None:
|
|
resp = files_client.get(f"/v1/files?scope_id={_SESSION_ID}")
|
|
assert resp.status_code == 200
|
|
listing = FileListResponse.model_validate(resp.json())
|
|
assert listing.data == []
|
|
assert listing.has_more is False
|
|
|
|
|
|
def test_list_files_after_upload(files_client: TestClient) -> None:
|
|
files_client.post(
|
|
f"/v1/files?scope_id={_SESSION_ID}",
|
|
files={"file": (_FILE_NAME, io.BytesIO(_FILE_CONTENT), _MIME_TYPE)},
|
|
)
|
|
|
|
resp = files_client.get(f"/v1/files?scope_id={_SESSION_ID}")
|
|
assert resp.status_code == 200
|
|
listing = FileListResponse.model_validate(resp.json())
|
|
assert len(listing.data) == 1
|
|
assert listing.data[0].filename == _FILE_NAME
|
|
|
|
|
|
def test_get_file_metadata(files_client: TestClient) -> None:
|
|
upload_resp = files_client.post(
|
|
f"/v1/files?scope_id={_SESSION_ID}",
|
|
files={"file": (_FILE_NAME, io.BytesIO(_FILE_CONTENT), _MIME_TYPE)},
|
|
)
|
|
file_id = upload_resp.json()["id"]
|
|
|
|
resp = files_client.get(_file_url(file_id, _SESSION_ID))
|
|
assert resp.status_code == 200
|
|
meta = FileMetadata.model_validate(resp.json())
|
|
assert meta.id == file_id
|
|
assert meta.filename == _FILE_NAME
|
|
|
|
|
|
def test_get_file_metadata_not_found(files_client: TestClient) -> None:
|
|
encoded_id = _encode_file_id("/nonexistent/path/file.txt")
|
|
resp = files_client.get(_file_url(encoded_id, _SESSION_ID))
|
|
assert resp.status_code == 404
|
|
|
|
|
|
def test_download_uploaded_file(files_client: TestClient) -> None:
|
|
upload_resp = files_client.post(
|
|
f"/v1/files?scope_id={_SESSION_ID}",
|
|
files={"file": (_FILE_NAME, io.BytesIO(_FILE_CONTENT), _MIME_TYPE)},
|
|
)
|
|
file_id = upload_resp.json()["id"]
|
|
|
|
resp = files_client.get(_file_url(file_id, _SESSION_ID, suffix="/content"))
|
|
assert resp.status_code == 200
|
|
assert resp.content == _FILE_CONTENT
|
|
|
|
|
|
def test_download_output_file(files_client: TestClient, volume_root: Path) -> None:
|
|
"""A sandbox output file can be downloaded via its absolute path ID."""
|
|
output_path = volume_root / "outputs" / _SESSION_ID / "result.csv"
|
|
output_path.write_bytes(_FILE_CONTENT)
|
|
|
|
canonical = "/mnt/user-data/outputs/result.csv"
|
|
file_id = _encode_file_id(canonical)
|
|
|
|
resp = files_client.get(_file_url(file_id, _SESSION_ID, suffix="/content"))
|
|
assert resp.status_code == 200
|
|
assert resp.content == _FILE_CONTENT
|
|
|
|
|
|
def test_list_includes_outputs(files_client: TestClient, volume_root: Path) -> None:
|
|
output_path = volume_root / "outputs" / _SESSION_ID / "result.png"
|
|
output_path.write_bytes(b"\x89PNG")
|
|
|
|
canonical = "/mnt/user-data/outputs/result.png"
|
|
output_id = _encode_file_id(canonical)
|
|
|
|
resp = files_client.get(f"/v1/files?scope_id={_SESSION_ID}")
|
|
listing = FileListResponse.model_validate(resp.json())
|
|
ids = [f.id for f in listing.data]
|
|
assert output_id in ids
|
|
downloadable = {f.id: f.downloadable for f in listing.data}
|
|
assert downloadable[output_id] is True
|
|
|
|
|
|
def test_delete_uploaded_file(files_client: TestClient) -> None:
|
|
upload_resp = files_client.post(
|
|
f"/v1/files?scope_id={_SESSION_ID}",
|
|
files={"file": (_FILE_NAME, io.BytesIO(_FILE_CONTENT), _MIME_TYPE)},
|
|
)
|
|
file_id = upload_resp.json()["id"]
|
|
|
|
del_resp = files_client.delete(_file_url(file_id, _SESSION_ID))
|
|
assert del_resp.status_code == 200
|
|
deleted = DeletedFile.model_validate(del_resp.json())
|
|
assert deleted.id == file_id
|
|
assert deleted.type == "file_deleted"
|
|
|
|
assert files_client.get(_file_url(file_id, _SESSION_ID)).status_code == 404
|
|
|
|
|
|
def test_delete_output_returns_404(files_client: TestClient, volume_root: Path) -> None:
|
|
output_path = volume_root / "outputs" / _SESSION_ID / "result.csv"
|
|
output_path.write_bytes(b"a,b\n1,2")
|
|
|
|
canonical = "/mnt/user-data/outputs/result.csv"
|
|
output_id = _encode_file_id(canonical)
|
|
|
|
resp = files_client.delete(_file_url(output_id, _SESSION_ID))
|
|
assert resp.status_code == 404
|