mirror of
https://github.com/guillaumemeyer/watermarks-remover.git
synced 2026-08-22 13:11:57 +02:00
* feat: split skill from service, add HTTP API and Docker distribution The agent skill (skills/remove-ai-marks/) is now a code-free remote client: all implementation moved to service/scripts/ and runs behind a stdlib HTTP service (server.py) with /health, /capabilities, /inspect, /clean and a dynamically generated OpenAPI 3.0.3 spec at /openapi.json. - Move scripts/ and the backend Dockerfiles under service/ - server.py: JSON/base64 HTTP entrypoint with size caps, binary guard, atomic writes, loopback default, optional bearer auth - Core Dockerfile (exiftool/qpdf/c2patool preinstalled) and a GHCR publish workflow for the core/markllm/markdiffusion images - compose.yaml (wr-* services, harness/heavy profiles) + compose-check.sh to validate the running stack (exit code only) - Fix markllm image build (tokenizers 0.22.2, CPU-only torch) and ctrlregen build (python:3.11 base for the 2023-era research pins) - Fix markllm/markdiffusion harness images missing common.py at runtime * docs: add .env.example and service configuration guide * fix: disable chain-of-thought for openai-compatible Layer B rewrites deepseek-v4-flash is a reasoning model: a one-line paraphrase burned 9,894 reasoning tokens (~100s) and hit the default timeout. Send reasoning_effort=none by default for the openai-compatible backend (--reasoning-effort / WATERMARKS_REWRITE_REASONING_EFFORT; 'off' omits the parameter), cutting the same rewrite to ~1s / 12 tokens. Tested end-to-end against api.deepseek.com. * fix: sanitize client-supplied filename in HTTP service CodeQL 'uncontrolled data in path expression' (server.py): a name like '../../x' flowed into Path(tmpdir) / name, letting an upload escape the request temp dir on write. Sanitize name to its basename in _decode_input (_safe_name) and refuse any joined path whose parent is not the tmpdir at the write sites (_tmp_path). Tests cover traversal names. * chore: gitignore .env (contains local rewrite credentials) * chore: deny-by-default gitignore and dockerignore; document compose env config .gitignore and service/.dockerignore now exclude everything by default and explicitly allow only what is publishable/needed: tracked source, docs, tests, .github, and (for images) the service/scripts/ tree that every Dockerfile COPYs. Root .dockerignore documents that all builds use service/ as context. README Configuration section now covers .env setup for docker compose, host-side export for CLI runs, and the full variable table.
147 lines
4.1 KiB
Python
147 lines
4.1 KiB
Python
"""Tests for the optional reverse-SynthID scorer adapter."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import subprocess
|
|
import sys
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
SCRIPTS = ROOT / "service" / "scripts"
|
|
sys.path.insert(0, str(SCRIPTS))
|
|
|
|
import image_meta # noqa: E402
|
|
from image_meta import ImageInspectReport, run_synthid_score # noqa: E402
|
|
|
|
SCORE_SCRIPT = SCRIPTS / "score_synthid.py"
|
|
|
|
|
|
def test_score_synthid_cli_unavailable_without_upstream(
|
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
|
):
|
|
monkeypatch.delenv("REVERSE_SYNTHID_DIR", raising=False)
|
|
dummy = tmp_path / "img.png"
|
|
dummy.write_bytes(b"not really an image")
|
|
|
|
r = subprocess.run(
|
|
[sys.executable, str(SCORE_SCRIPT), str(dummy)],
|
|
capture_output=True,
|
|
text=True,
|
|
)
|
|
|
|
assert r.returncode == 3
|
|
assert "REVERSE_SYNTHID_DIR" in (r.stderr or "")
|
|
|
|
|
|
def test_run_synthid_score_unconfigured_returns_none(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
):
|
|
monkeypatch.delenv("REVERSE_SYNTHID_DIR", raising=False)
|
|
assert run_synthid_score(Path("x.png")) is None
|
|
|
|
|
|
def test_run_synthid_score_unavailable_returns_none(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
):
|
|
def fake_run(*args, **kwargs):
|
|
return SimpleNamespace(returncode=3, stdout="", stderr="unavailable")
|
|
|
|
monkeypatch.setattr(image_meta.subprocess, "run", fake_run)
|
|
assert run_synthid_score(Path("x.png"), upstream_dir="/tmp/upstream") is None
|
|
|
|
|
|
def test_run_synthid_score_parses_json(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
):
|
|
payload = {
|
|
"available": True,
|
|
"is_watermarked": True,
|
|
"confidence": 0.91,
|
|
"phase_match": 0.65,
|
|
}
|
|
captured: dict = {}
|
|
|
|
def fake_run(cmd, **kwargs):
|
|
captured["cmd"] = cmd
|
|
return SimpleNamespace(returncode=0, stdout=json.dumps(payload), stderr="")
|
|
|
|
monkeypatch.setattr(image_meta.subprocess, "run", fake_run)
|
|
result = run_synthid_score(Path("img.png"), upstream_dir="/tmp/upstream")
|
|
|
|
assert result == payload
|
|
assert "--json" in captured["cmd"]
|
|
assert "--upstream-dir" in captured["cmd"]
|
|
assert "/tmp/upstream" in captured["cmd"]
|
|
|
|
|
|
def test_run_synthid_score_runtime_error_is_reported(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
):
|
|
def fake_run(*args, **kwargs):
|
|
return SimpleNamespace(returncode=1, stdout="", stderr="boom")
|
|
|
|
monkeypatch.setattr(image_meta.subprocess, "run", fake_run)
|
|
result = run_synthid_score(Path("img.png"), upstream_dir="/tmp/upstream")
|
|
|
|
assert result is not None
|
|
assert result.get("available") is False
|
|
assert "boom" in result.get("error", "")
|
|
|
|
|
|
def test_inspect_image_cli_prints_synthid_score(
|
|
tmp_path: Path,
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
capsys: pytest.CaptureFixture[str],
|
|
):
|
|
import importlib.util
|
|
|
|
spec = importlib.util.spec_from_file_location(
|
|
"inspect_image_cli", str(SCRIPTS / "inspect_image.py")
|
|
)
|
|
assert spec and spec.loader
|
|
cli = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(cli)
|
|
|
|
report = ImageInspectReport(
|
|
path="shot.png",
|
|
format="png",
|
|
has_c2pa=False,
|
|
has_ai_metadata=False,
|
|
synthid={
|
|
"available": True,
|
|
"is_watermarked": True,
|
|
"confidence": 0.91,
|
|
},
|
|
)
|
|
img = tmp_path / "shot.png"
|
|
img.write_bytes(b"not really an image")
|
|
monkeypatch.setattr(cli, "inspect_image", lambda path, synthid_dir=None: report)
|
|
monkeypatch.setattr(sys, "argv", ["inspect_image.py", str(img)])
|
|
|
|
assert cli.main() == 0
|
|
out = capsys.readouterr().out
|
|
assert "SynthID score: confidence 0.910 (watermarked: yes)" in out
|
|
|
|
|
|
def test_inspect_report_to_dict_includes_synthid():
|
|
report = ImageInspectReport(
|
|
path="x.png",
|
|
format="png",
|
|
has_c2pa=False,
|
|
has_ai_metadata=False,
|
|
synthid={"available": True, "confidence": 0.8},
|
|
)
|
|
assert report.to_dict()["synthid"]["confidence"] == 0.8
|
|
|
|
empty = ImageInspectReport(
|
|
path="x.png",
|
|
format="png",
|
|
has_c2pa=False,
|
|
has_ai_metadata=False,
|
|
)
|
|
assert empty.to_dict()["synthid"] is None
|