mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
OpenAI-compatible clients (Open WebUI, LobeChat, etc.) can now send vision
requests to the API server. Both endpoints accept the canonical OpenAI
multimodal shape:
Chat Completions: {type: text|image_url, image_url: {url, detail?}}
Responses: {type: input_text|input_image, image_url: <str>, detail?}
The server validates and converts both into a single internal shape that the
existing agent pipeline already handles (Anthropic adapter converts,
OpenAI-wire providers pass through). Remote http(s) URLs and data:image/*
URLs are supported.
Uploaded files (file, input_file, file_id) and non-image data: URLs are
rejected with 400 unsupported_content_type.
Changes:
- gateway/platforms/api_server.py
- _normalize_multimodal_content(): validates + normalizes both Chat and
Responses content shapes. Returns a plain string for text-only content
(preserves prompt-cache behavior on existing callers) or a canonical
[{type:text|image_url,...}] list when images are present.
- _content_has_visible_payload(): replaces the bare truthy check so a
user turn with only an image no longer rejects as 'No user message'.
- _handle_chat_completions and _handle_responses both call the new helper
for user/assistant content; system messages continue to flatten to text.
- Codex conversation_history, input[], and inline history paths all share
the same validator. No duplicated normalizers.
- run_agent.py
- _summarize_user_message_for_log(): produces a short string summary
('[1 image] describe this') from list content for logging, spinner
previews, and trajectory writes. Fixes AttributeError when list
user_message hit user_message[:80] + '...' / .replace().
- _chat_content_to_responses_parts(): module-level helper that converts
chat-style multimodal content to Responses 'input_text'/'input_image'
parts. Used in _chat_messages_to_responses_input for Codex routing.
- _preflight_codex_input_items() now validates and passes through list
content parts for user/assistant messages instead of stringifying.
- tests/gateway/test_api_server_multimodal.py (new, 38 tests)
- Unit coverage for _normalize_multimodal_content, including both part
formats, data URL gating, and all reject paths.
- Real aiohttp HTTP integration on /v1/chat/completions and /v1/responses
verifying multimodal payloads reach _run_agent intact.
- 400 coverage for file / input_file / non-image data URL.
- tests/run_agent/test_run_agent_multimodal_prologue.py (new)
- Regression coverage for the prologue no-crash contract.
- _chat_content_to_responses_parts round-trip coverage.
- website/docs/user-guide/features/api-server.md
- Inline image examples for both endpoints.
- Updated Limitations: files still unsupported, images now supported.
Validated live against openrouter/anthropic/claude-opus-4.6:
POST /v1/chat/completions → 200, vision-accurate description
POST /v1/responses → 200, same image, clean output_text
POST /v1/chat/completions [file] → 400 unsupported_content_type
POST /v1/responses [input_file] → 400 unsupported_content_type
POST /v1/responses [non-image data URL] → 400 unsupported_content_type
Closes #5621, #8253, #4046, #6632.
Co-authored-by: Paul Bergeron <paul@gamma.app>
Co-authored-by: zhangxicen <zhangxicen@example.com>
Co-authored-by: Manuel Schipper <manuelschipper@users.noreply.github.com>
Co-authored-by: pradeep7127 <pradeep7127@users.noreply.github.com>
308 lines
12 KiB
Python
308 lines
12 KiB
Python
"""End-to-end tests for inline image inputs on /v1/chat/completions and /v1/responses.
|
|
|
|
Covers the multimodal normalization path added to the API server. Unlike the
|
|
adapter-level tests that patch ``_run_agent``, these tests patch
|
|
``AIAgent.run_conversation`` instead so the adapter's full request-handling
|
|
path (including the ``run_agent`` prologue that used to crash on list content)
|
|
executes against a real aiohttp app.
|
|
"""
|
|
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
from aiohttp import web
|
|
from aiohttp.test_utils import TestClient, TestServer
|
|
|
|
from gateway.config import PlatformConfig
|
|
from gateway.platforms.api_server import (
|
|
APIServerAdapter,
|
|
_content_has_visible_payload,
|
|
_normalize_multimodal_content,
|
|
cors_middleware,
|
|
security_headers_middleware,
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Pure-function tests for _normalize_multimodal_content
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestNormalizeMultimodalContent:
|
|
def test_string_passthrough(self):
|
|
assert _normalize_multimodal_content("hello") == "hello"
|
|
|
|
def test_none_returns_empty_string(self):
|
|
assert _normalize_multimodal_content(None) == ""
|
|
|
|
def test_text_only_list_collapses_to_string(self):
|
|
content = [{"type": "text", "text": "hi"}, {"type": "text", "text": "there"}]
|
|
assert _normalize_multimodal_content(content) == "hi\nthere"
|
|
|
|
def test_responses_input_text_canonicalized(self):
|
|
content = [{"type": "input_text", "text": "hello"}]
|
|
assert _normalize_multimodal_content(content) == "hello"
|
|
|
|
def test_image_url_preserved_with_text(self):
|
|
content = [
|
|
{"type": "text", "text": "describe this"},
|
|
{"type": "image_url", "image_url": {"url": "https://example.com/cat.png", "detail": "high"}},
|
|
]
|
|
out = _normalize_multimodal_content(content)
|
|
assert isinstance(out, list)
|
|
assert out == [
|
|
{"type": "text", "text": "describe this"},
|
|
{"type": "image_url", "image_url": {"url": "https://example.com/cat.png", "detail": "high"}},
|
|
]
|
|
|
|
def test_input_image_converted_to_canonical_shape(self):
|
|
content = [
|
|
{"type": "input_text", "text": "hi"},
|
|
{"type": "input_image", "image_url": "https://example.com/cat.png"},
|
|
]
|
|
out = _normalize_multimodal_content(content)
|
|
assert out == [
|
|
{"type": "text", "text": "hi"},
|
|
{"type": "image_url", "image_url": {"url": "https://example.com/cat.png"}},
|
|
]
|
|
|
|
def test_data_image_url_accepted(self):
|
|
content = [{"type": "image_url", "image_url": {"url": "data:image/png;base64,AAAA"}}]
|
|
out = _normalize_multimodal_content(content)
|
|
assert out == [{"type": "image_url", "image_url": {"url": "data:image/png;base64,AAAA"}}]
|
|
|
|
def test_non_image_data_url_rejected(self):
|
|
content = [{"type": "image_url", "image_url": {"url": "data:text/plain;base64,SGVsbG8="}}]
|
|
with pytest.raises(ValueError) as exc:
|
|
_normalize_multimodal_content(content)
|
|
assert str(exc.value).startswith("unsupported_content_type:")
|
|
|
|
def test_file_part_rejected(self):
|
|
with pytest.raises(ValueError) as exc:
|
|
_normalize_multimodal_content([{"type": "file", "file": {"file_id": "f_1"}}])
|
|
assert str(exc.value).startswith("unsupported_content_type:")
|
|
|
|
def test_input_file_part_rejected(self):
|
|
with pytest.raises(ValueError) as exc:
|
|
_normalize_multimodal_content([{"type": "input_file", "file_id": "f_1"}])
|
|
assert str(exc.value).startswith("unsupported_content_type:")
|
|
|
|
def test_missing_url_rejected(self):
|
|
with pytest.raises(ValueError) as exc:
|
|
_normalize_multimodal_content([{"type": "image_url", "image_url": {}}])
|
|
assert str(exc.value).startswith("invalid_image_url:")
|
|
|
|
def test_bad_scheme_rejected(self):
|
|
with pytest.raises(ValueError) as exc:
|
|
_normalize_multimodal_content([{"type": "image_url", "image_url": {"url": "ftp://example.com/x.png"}}])
|
|
assert str(exc.value).startswith("invalid_image_url:")
|
|
|
|
def test_unknown_part_type_rejected(self):
|
|
with pytest.raises(ValueError) as exc:
|
|
_normalize_multimodal_content([{"type": "audio", "audio": {}}])
|
|
assert str(exc.value).startswith("unsupported_content_type:")
|
|
|
|
|
|
class TestContentHasVisiblePayload:
|
|
def test_non_empty_string(self):
|
|
assert _content_has_visible_payload("hello")
|
|
|
|
def test_whitespace_only_string(self):
|
|
assert not _content_has_visible_payload(" ")
|
|
|
|
def test_list_with_image_only(self):
|
|
assert _content_has_visible_payload([{"type": "image_url", "image_url": {"url": "x"}}])
|
|
|
|
def test_list_with_only_empty_text(self):
|
|
assert not _content_has_visible_payload([{"type": "text", "text": ""}])
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# HTTP integration — real aiohttp client hitting the adapter handlers
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def _make_adapter() -> APIServerAdapter:
|
|
return APIServerAdapter(PlatformConfig(enabled=True))
|
|
|
|
|
|
def _create_app(adapter: APIServerAdapter) -> web.Application:
|
|
mws = [mw for mw in (cors_middleware, security_headers_middleware) if mw is not None]
|
|
app = web.Application(middlewares=mws)
|
|
app["api_server_adapter"] = adapter
|
|
app.router.add_post("/v1/chat/completions", adapter._handle_chat_completions)
|
|
app.router.add_post("/v1/responses", adapter._handle_responses)
|
|
app.router.add_get("/v1/responses/{response_id}", adapter._handle_get_response)
|
|
return app
|
|
|
|
|
|
@pytest.fixture
|
|
def adapter():
|
|
return _make_adapter()
|
|
|
|
|
|
class TestChatCompletionsMultimodalHTTP:
|
|
@pytest.mark.asyncio
|
|
async def test_inline_image_preserved_to_run_agent(self, adapter):
|
|
"""Multimodal user content reaches _run_agent as a list of parts."""
|
|
image_payload = [
|
|
{"type": "text", "text": "What's in this image?"},
|
|
{"type": "image_url", "image_url": {"url": "https://example.com/cat.png", "detail": "high"}},
|
|
]
|
|
|
|
app = _create_app(adapter)
|
|
async with TestClient(TestServer(app)) as cli:
|
|
with patch.object(
|
|
adapter,
|
|
"_run_agent",
|
|
new=MagicMock(),
|
|
) as mock_run:
|
|
async def _stub(**kwargs):
|
|
mock_run.captured = kwargs
|
|
return (
|
|
{"final_response": "A cat.", "messages": [], "api_calls": 1},
|
|
{"input_tokens": 0, "output_tokens": 0, "total_tokens": 0},
|
|
)
|
|
mock_run.side_effect = _stub
|
|
|
|
resp = await cli.post(
|
|
"/v1/chat/completions",
|
|
json={
|
|
"model": "hermes-agent",
|
|
"messages": [{"role": "user", "content": image_payload}],
|
|
},
|
|
)
|
|
|
|
assert resp.status == 200, await resp.text()
|
|
assert mock_run.captured["user_message"] == image_payload
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_text_only_array_collapses_to_string(self, adapter):
|
|
"""Text-only array becomes a plain string so logging stays unchanged."""
|
|
app = _create_app(adapter)
|
|
async with TestClient(TestServer(app)) as cli:
|
|
with patch.object(adapter, "_run_agent", new=MagicMock()) as mock_run:
|
|
async def _stub(**kwargs):
|
|
mock_run.captured = kwargs
|
|
return (
|
|
{"final_response": "ok", "messages": [], "api_calls": 1},
|
|
{"input_tokens": 0, "output_tokens": 0, "total_tokens": 0},
|
|
)
|
|
mock_run.side_effect = _stub
|
|
|
|
resp = await cli.post(
|
|
"/v1/chat/completions",
|
|
json={
|
|
"model": "hermes-agent",
|
|
"messages": [
|
|
{"role": "user", "content": [{"type": "text", "text": "hello"}]},
|
|
],
|
|
},
|
|
)
|
|
|
|
assert resp.status == 200, await resp.text()
|
|
assert mock_run.captured["user_message"] == "hello"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_file_part_returns_400(self, adapter):
|
|
app = _create_app(adapter)
|
|
async with TestClient(TestServer(app)) as cli:
|
|
resp = await cli.post(
|
|
"/v1/chat/completions",
|
|
json={
|
|
"model": "hermes-agent",
|
|
"messages": [
|
|
{"role": "user", "content": [{"type": "file", "file": {"file_id": "f_1"}}]},
|
|
],
|
|
},
|
|
)
|
|
assert resp.status == 400
|
|
body = await resp.json()
|
|
assert body["error"]["code"] == "unsupported_content_type"
|
|
assert body["error"]["param"] == "messages[0].content"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_non_image_data_url_returns_400(self, adapter):
|
|
app = _create_app(adapter)
|
|
async with TestClient(TestServer(app)) as cli:
|
|
resp = await cli.post(
|
|
"/v1/chat/completions",
|
|
json={
|
|
"model": "hermes-agent",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "image_url",
|
|
"image_url": {"url": "data:text/plain;base64,SGVsbG8="},
|
|
},
|
|
],
|
|
},
|
|
],
|
|
},
|
|
)
|
|
assert resp.status == 400
|
|
body = await resp.json()
|
|
assert body["error"]["code"] == "unsupported_content_type"
|
|
|
|
|
|
class TestResponsesMultimodalHTTP:
|
|
@pytest.mark.asyncio
|
|
async def test_input_image_canonicalized_and_forwarded(self, adapter):
|
|
app = _create_app(adapter)
|
|
async with TestClient(TestServer(app)) as cli:
|
|
with patch.object(adapter, "_run_agent", new=MagicMock()) as mock_run:
|
|
async def _stub(**kwargs):
|
|
mock_run.captured = kwargs
|
|
return (
|
|
{"final_response": "ok", "messages": [], "api_calls": 1},
|
|
{"input_tokens": 0, "output_tokens": 0, "total_tokens": 0},
|
|
)
|
|
mock_run.side_effect = _stub
|
|
|
|
resp = await cli.post(
|
|
"/v1/responses",
|
|
json={
|
|
"model": "hermes-agent",
|
|
"input": [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "input_text", "text": "Describe."},
|
|
{
|
|
"type": "input_image",
|
|
"image_url": "https://example.com/cat.png",
|
|
},
|
|
],
|
|
}
|
|
],
|
|
},
|
|
)
|
|
|
|
assert resp.status == 200, await resp.text()
|
|
expected = [
|
|
{"type": "text", "text": "Describe."},
|
|
{"type": "image_url", "image_url": {"url": "https://example.com/cat.png"}},
|
|
]
|
|
assert mock_run.captured["user_message"] == expected
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_input_file_returns_400(self, adapter):
|
|
app = _create_app(adapter)
|
|
async with TestClient(TestServer(app)) as cli:
|
|
resp = await cli.post(
|
|
"/v1/responses",
|
|
json={
|
|
"model": "hermes-agent",
|
|
"input": [
|
|
{
|
|
"role": "user",
|
|
"content": [{"type": "input_file", "file_id": "f_1"}],
|
|
}
|
|
],
|
|
},
|
|
)
|
|
assert resp.status == 400
|
|
body = await resp.json()
|
|
assert body["error"]["code"] == "unsupported_content_type"
|