hermes-agent/tests/plugins/image_gen/test_openai_provider.py
Teknium 6b81590c55
test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions
Systematic prune per AGENTS.md test policy, one pass over every major
test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli,
cron, tui_gateway, honcho/openviking, root-level):

- DELETE: source-reading tests (read_text/getsource on prod files),
  change-detector tests (exact catalog counts, model-name snapshots,
  config version literals), mock-echo tests (assert a mock returns what
  it was told), assertion-free/trivial tests, near-duplicate
  parametrizations (boundaries + one representative kept), async/sync
  twin duplicates, cosmetic within-file variations.
- KEEP (mandatory): security/redaction/approval guards, message-role
  alternation invariants, prompt-caching/deterministic-call-id
  invariants, issue-number regression tests (deduped), E2E tests.
- 6 test files deleted outright (script-style/no-assert or fully
  redundant); conftest.py, fakes/, fixtures/ untouched.
- tests/acp/conftest.py added: autouse fixture stubs the live
  models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server
  tests performed on every session create — test_server.py 147s → 3.4s,
  and the tests are now genuinely hermetic.
- Sleep-based slowness shrunk where safe (codex_ttfb_watchdog,
  compression_concurrent_fork, etc.); no wall-clock assertion tightened.

Verification: full hermetic suite via scripts/run_tests.sh —
2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall
(baseline: 583s wall, 13,564s subprocess CPU).
2026-07-29 13:10:23 -07:00

242 lines
9.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""Tests for the bundled OpenAI image_gen plugin (gpt-image-2, three tiers)."""
from __future__ import annotations
from pathlib import Path
from types import SimpleNamespace
from unittest.mock import MagicMock, patch
import pytest
import plugins.image_gen.openai as openai_plugin
# 1×1 transparent PNG — valid bytes for save_b64_image()
_PNG_HEX = (
"89504e470d0a1a0a0000000d49484452000000010000000108060000001f15c4"
"890000000d49444154789c6300010000000500010d0a2db40000000049454e44"
"ae426082"
)
def _b64_png() -> str:
import base64
return base64.b64encode(bytes.fromhex(_PNG_HEX)).decode()
def _fake_response(*, b64=None, url=None, revised_prompt=None):
item = SimpleNamespace(b64_json=b64, url=url, revised_prompt=revised_prompt)
return SimpleNamespace(data=[item])
@pytest.fixture(autouse=True)
def _tmp_hermes_home(tmp_path, monkeypatch):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
yield tmp_path
@pytest.fixture
def provider(monkeypatch):
monkeypatch.setenv("OPENAI_API_KEY", "test-key")
return openai_plugin.OpenAIImageGenProvider()
def _patched_openai(fake_client: MagicMock):
fake_openai = MagicMock()
fake_openai.OpenAI.return_value = fake_client
return patch.dict("sys.modules", {"openai": fake_openai})
# ── Metadata ────────────────────────────────────────────────────────────────
class TestMetadata:
def test_name(self, provider):
assert provider.name == "openai"
def test_default_model(self, provider):
assert provider.default_model() == "gpt-image-2-medium"
def test_list_models_three_tiers(self, provider):
ids = [m["id"] for m in provider.list_models()]
assert ids == ["gpt-image-2-low", "gpt-image-2-medium", "gpt-image-2-high"]
def test_catalog_entries_have_display_speed_strengths(self, provider):
for entry in provider.list_models():
assert entry["display"].startswith("GPT Image 2")
assert entry["speed"]
assert entry["strengths"]
# ── Availability ────────────────────────────────────────────────────────────
class TestAvailability:
def test_no_api_key_unavailable(self, monkeypatch):
monkeypatch.delenv("OPENAI_API_KEY", raising=False)
assert openai_plugin.OpenAIImageGenProvider().is_available() is False
def test_api_key_set_available(self, monkeypatch):
monkeypatch.setenv("OPENAI_API_KEY", "test")
assert openai_plugin.OpenAIImageGenProvider().is_available() is True
# ── Model resolution ────────────────────────────────────────────────────────
class TestModelResolution:
def test_env_var_override(self, monkeypatch):
monkeypatch.setenv("OPENAI_IMAGE_MODEL", "gpt-image-2-high")
model_id, meta = openai_plugin._resolve_model()
assert model_id == "gpt-image-2-high"
assert meta["quality"] == "high"
def test_config_openai_model(self, tmp_path):
import yaml
(tmp_path / "config.yaml").write_text(
yaml.safe_dump({"image_gen": {"openai": {"model": "gpt-image-2-low"}}})
)
model_id, meta = openai_plugin._resolve_model()
assert model_id == "gpt-image-2-low"
assert meta["quality"] == "low"
# ── Generate ────────────────────────────────────────────────────────────────
class TestSourceImageLoading:
def test_load_image_bytes_blocks_credential_store(self, tmp_path, monkeypatch):
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
auth_json = hermes_home / "auth.json"
auth_json.write_text('{"api_key":"sk-secret"}', encoding="utf-8")
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
with pytest.raises(ValueError, match="credential store"):
openai_plugin._load_image_bytes(str(auth_json))
def test_load_image_bytes_allows_legit_local_image(self, tmp_path, monkeypatch):
"""Negative control: a legitimate local image path is NOT blocked and
loads normally — proves the guard doesn't over-fire on everything."""
hermes_home = tmp_path / ".hermes"
hermes_home.mkdir()
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
img = tmp_path / "pic.png"
img.write_bytes(b"\x89PNG\r\n\x1a\nfake-image-bytes")
data, name = openai_plugin._load_image_bytes(str(img))
assert data == b"\x89PNG\r\n\x1a\nfake-image-bytes"
assert name == "pic.png"
class TestGenerate:
def test_empty_prompt_rejected(self, provider):
result = provider.generate("", aspect_ratio="square")
assert result["success"] is False
assert result["error_type"] == "invalid_argument"
def test_missing_api_key(self, monkeypatch):
monkeypatch.delenv("OPENAI_API_KEY", raising=False)
result = openai_plugin.OpenAIImageGenProvider().generate("a cat")
assert result["success"] is False
assert result["error_type"] == "auth_required"
def test_b64_saves_to_cache(self, provider, tmp_path):
png_bytes = bytes.fromhex(_PNG_HEX)
fake_client = MagicMock()
fake_client.images.generate.return_value = _fake_response(b64=_b64_png())
with _patched_openai(fake_client):
result = provider.generate("a cat", aspect_ratio="landscape")
assert result["success"] is True
assert result["model"] == "gpt-image-2-medium"
assert result["aspect_ratio"] == "landscape"
assert result["provider"] == "openai"
assert result["quality"] == "medium"
saved = Path(result["image"])
assert saved.exists()
assert saved.parent == tmp_path / "cache" / "images"
assert saved.read_bytes() == png_bytes
call_kwargs = fake_client.images.generate.call_args.kwargs
# All tiers hit the single underlying API model.
assert call_kwargs["model"] == "gpt-image-2"
assert call_kwargs["quality"] == "medium"
assert call_kwargs["size"] == "1536x1024"
# gpt-image-2 rejects response_format — we must NOT send it.
assert "response_format" not in call_kwargs
@pytest.mark.parametrize("tier,expected_quality", [
("gpt-image-2-low", "low"),
("gpt-image-2-medium", "medium"),
("gpt-image-2-high", "high"),
])
def test_tier_maps_to_quality(self, provider, monkeypatch, tier, expected_quality):
monkeypatch.setenv("OPENAI_IMAGE_MODEL", tier)
fake_client = MagicMock()
fake_client.images.generate.return_value = _fake_response(b64=_b64_png())
with _patched_openai(fake_client):
result = provider.generate("a cat")
assert result["model"] == tier
assert result["quality"] == expected_quality
assert fake_client.images.generate.call_args.kwargs["quality"] == expected_quality
# Always the same underlying API model regardless of tier.
assert fake_client.images.generate.call_args.kwargs["model"] == "gpt-image-2"
@pytest.mark.parametrize("aspect,expected_size", [
("landscape", "1536x1024"),
("square", "1024x1024"),
("portrait", "1024x1536"),
])
def test_aspect_ratio_mapping(self, provider, aspect, expected_size):
fake_client = MagicMock()
fake_client.images.generate.return_value = _fake_response(b64=_b64_png())
with _patched_openai(fake_client):
provider.generate("a cat", aspect_ratio=aspect)
assert fake_client.images.generate.call_args.kwargs["size"] == expected_size
def test_revised_prompt_passed_through(self, provider):
fake_client = MagicMock()
fake_client.images.generate.return_value = _fake_response(
b64=_b64_png(), revised_prompt="A photo of a cat",
)
with _patched_openai(fake_client):
result = provider.generate("a cat")
assert result["revised_prompt"] == "A photo of a cat"
def test_url_response_is_cached_locally(self, provider):
"""OpenAI URL response (if API ever returns one) is cached locally.
Pre-fix this asserted the bare URL passed through; symmetric to the
xAI #26942 fix. Even though gpt-image-2 returns b64 today, every
``image_gen`` provider must guarantee the gateway gets a stable
file path so ephemeral signed URLs can't expire mid-flight.
"""
fake_client = MagicMock()
fake_client.images.generate.return_value = _fake_response(
b64=None, url="https://example.com/img.png",
)
with _patched_openai(fake_client), patch(
"plugins.image_gen.openai.save_url_image",
return_value=Path("/tmp/openai_gpt-image-2_20260524_000000_deadbeef.png"),
) as mock_save_url:
result = provider.generate("a cat")
assert result["success"] is True
assert result["image"].startswith("/")
assert "example.com" not in result["image"]
mock_save_url.assert_called_once()