mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
- Add openai/openai-codex -> openai mapping to PROVIDER_TO_MODELS_DEV so context-length lookups use models.dev data instead of 128k fallback. Fixes #8161. - Set api_mode from custom_providers entry when switching via hermes model, and clear stale api_mode when the entry has none. Also extract api_mode in _named_custom_provider_map(). Fixes #8181. - Convert OpenAI image_url content blocks to Anthropic image blocks when the endpoint is Anthropic-compatible (MiniMax, MiniMax-CN, or any URL containing /anthropic). Fixes #8147.
This commit is contained in:
Teknium
GitHub
parent
b1f13a8c5f
commit
078dba015d
6 changed files with 214 additions and 1 deletions
|
|
@ -2112,6 +2112,75 @@ def _get_task_timeout(task: str, default: float = _DEFAULT_AUX_TIMEOUT) -> float
|
|||
return default
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Anthropic-compatible endpoint detection + image block conversion
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Providers that use Anthropic-compatible endpoints (via OpenAI SDK wrapper).
|
||||
# Their image content blocks must use Anthropic format, not OpenAI format.
|
||||
_ANTHROPIC_COMPAT_PROVIDERS = frozenset({"minimax", "minimax-cn"})
|
||||
|
||||
|
||||
def _is_anthropic_compat_endpoint(provider: str, base_url: str) -> bool:
|
||||
"""Detect if an endpoint expects Anthropic-format content blocks.
|
||||
|
||||
Returns True for known Anthropic-compatible providers (MiniMax) and
|
||||
any endpoint whose URL contains ``/anthropic`` in the path.
|
||||
"""
|
||||
if provider in _ANTHROPIC_COMPAT_PROVIDERS:
|
||||
return True
|
||||
url_lower = (base_url or "").lower()
|
||||
return "/anthropic" in url_lower
|
||||
|
||||
|
||||
def _convert_openai_images_to_anthropic(messages: list) -> list:
|
||||
"""Convert OpenAI ``image_url`` content blocks to Anthropic ``image`` blocks.
|
||||
|
||||
Only touches messages that have list-type content with ``image_url`` blocks;
|
||||
plain text messages pass through unchanged.
|
||||
"""
|
||||
converted = []
|
||||
for msg in messages:
|
||||
content = msg.get("content")
|
||||
if not isinstance(content, list):
|
||||
converted.append(msg)
|
||||
continue
|
||||
new_content = []
|
||||
changed = False
|
||||
for block in content:
|
||||
if block.get("type") == "image_url":
|
||||
image_url_val = (block.get("image_url") or {}).get("url", "")
|
||||
if image_url_val.startswith("data:"):
|
||||
# Parse data URI: data:<media_type>;base64,<data>
|
||||
header, _, b64data = image_url_val.partition(",")
|
||||
media_type = "image/png"
|
||||
if ":" in header and ";" in header:
|
||||
media_type = header.split(":", 1)[1].split(";", 1)[0]
|
||||
new_content.append({
|
||||
"type": "image",
|
||||
"source": {
|
||||
"type": "base64",
|
||||
"media_type": media_type,
|
||||
"data": b64data,
|
||||
},
|
||||
})
|
||||
else:
|
||||
# URL-based image
|
||||
new_content.append({
|
||||
"type": "image",
|
||||
"source": {
|
||||
"type": "url",
|
||||
"url": image_url_val,
|
||||
},
|
||||
})
|
||||
changed = True
|
||||
else:
|
||||
new_content.append(block)
|
||||
converted.append({**msg, "content": new_content} if changed else msg)
|
||||
return converted
|
||||
|
||||
|
||||
|
||||
def _build_call_kwargs(
|
||||
provider: str,
|
||||
model: str,
|
||||
|
|
@ -2304,6 +2373,11 @@ def call_llm(
|
|||
tools=tools, timeout=effective_timeout, extra_body=extra_body,
|
||||
base_url=resolved_base_url)
|
||||
|
||||
# Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
|
||||
_client_base = str(getattr(client, "base_url", "") or "")
|
||||
if _is_anthropic_compat_endpoint(resolved_provider, _client_base):
|
||||
kwargs["messages"] = _convert_openai_images_to_anthropic(kwargs["messages"])
|
||||
|
||||
# Handle max_tokens vs max_completion_tokens retry, then payment fallback.
|
||||
try:
|
||||
return _validate_llm_response(
|
||||
|
|
@ -2492,6 +2566,11 @@ async def async_call_llm(
|
|||
tools=tools, timeout=effective_timeout, extra_body=extra_body,
|
||||
base_url=resolved_base_url)
|
||||
|
||||
# Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
|
||||
_client_base = str(getattr(client, "base_url", "") or "")
|
||||
if _is_anthropic_compat_endpoint(resolved_provider, _client_base):
|
||||
kwargs["messages"] = _convert_openai_images_to_anthropic(kwargs["messages"])
|
||||
|
||||
try:
|
||||
return _validate_llm_response(
|
||||
await client.chat.completions.create(**kwargs), task)
|
||||
|
|
|
|||
|
|
@ -144,6 +144,8 @@ class ProviderInfo:
|
|||
PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
|
||||
"openrouter": "openrouter",
|
||||
"anthropic": "anthropic",
|
||||
"openai": "openai",
|
||||
"openai-codex": "openai",
|
||||
"zai": "zai",
|
||||
"kimi-coding": "kimi-for-coding",
|
||||
"minimax": "minimax",
|
||||
|
|
|
|||
|
|
@ -1107,6 +1107,7 @@ def select_provider_and_model(args=None):
|
|||
"base_url": base_url,
|
||||
"api_key": entry.get("api_key", ""),
|
||||
"model": entry.get("model", ""),
|
||||
"api_mode": entry.get("api_mode", ""),
|
||||
}
|
||||
return custom_provider_map
|
||||
|
||||
|
|
@ -1955,6 +1956,12 @@ def _model_flow_named_custom(config, provider_info):
|
|||
model["base_url"] = base_url
|
||||
if api_key:
|
||||
model["api_key"] = api_key
|
||||
# Apply api_mode from custom_providers entry, or clear stale value
|
||||
custom_api_mode = provider_info.get("api_mode", "")
|
||||
if custom_api_mode:
|
||||
model["api_mode"] = custom_api_mode
|
||||
else:
|
||||
model.pop("api_mode", None) # let runtime auto-detect from URL
|
||||
save_config(cfg)
|
||||
deactivate_provider()
|
||||
|
||||
|
|
|
|||
|
|
@ -1628,3 +1628,74 @@ class TestStaleBaseUrlWarning:
|
|||
|
||||
assert not any("OPENAI_BASE_URL is set" in rec.message for rec in caplog.records), \
|
||||
"Warning should not fire a second time"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Anthropic-compatible image block conversion
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestAnthropicCompatImageConversion:
|
||||
"""Tests for _is_anthropic_compat_endpoint and _convert_openai_images_to_anthropic."""
|
||||
|
||||
def test_known_providers_detected(self):
|
||||
from agent.auxiliary_client import _is_anthropic_compat_endpoint
|
||||
assert _is_anthropic_compat_endpoint("minimax", "")
|
||||
assert _is_anthropic_compat_endpoint("minimax-cn", "")
|
||||
|
||||
def test_openrouter_not_detected(self):
|
||||
from agent.auxiliary_client import _is_anthropic_compat_endpoint
|
||||
assert not _is_anthropic_compat_endpoint("openrouter", "")
|
||||
assert not _is_anthropic_compat_endpoint("anthropic", "")
|
||||
|
||||
def test_url_based_detection(self):
|
||||
from agent.auxiliary_client import _is_anthropic_compat_endpoint
|
||||
assert _is_anthropic_compat_endpoint("custom", "https://api.minimax.io/anthropic")
|
||||
assert _is_anthropic_compat_endpoint("custom", "https://example.com/anthropic/v1")
|
||||
assert not _is_anthropic_compat_endpoint("custom", "https://api.openai.com/v1")
|
||||
|
||||
def test_base64_image_converted(self):
|
||||
from agent.auxiliary_client import _convert_openai_images_to_anthropic
|
||||
messages = [{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": "describe"},
|
||||
{"type": "image_url", "image_url": {"url": "data:image/png;base64,iVBOR="}}
|
||||
]
|
||||
}]
|
||||
result = _convert_openai_images_to_anthropic(messages)
|
||||
img_block = result[0]["content"][1]
|
||||
assert img_block["type"] == "image"
|
||||
assert img_block["source"]["type"] == "base64"
|
||||
assert img_block["source"]["media_type"] == "image/png"
|
||||
assert img_block["source"]["data"] == "iVBOR="
|
||||
|
||||
def test_url_image_converted(self):
|
||||
from agent.auxiliary_client import _convert_openai_images_to_anthropic
|
||||
messages = [{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "image_url", "image_url": {"url": "https://example.com/img.jpg"}}
|
||||
]
|
||||
}]
|
||||
result = _convert_openai_images_to_anthropic(messages)
|
||||
img_block = result[0]["content"][0]
|
||||
assert img_block["type"] == "image"
|
||||
assert img_block["source"]["type"] == "url"
|
||||
assert img_block["source"]["url"] == "https://example.com/img.jpg"
|
||||
|
||||
def test_text_only_messages_unchanged(self):
|
||||
from agent.auxiliary_client import _convert_openai_images_to_anthropic
|
||||
messages = [{"role": "user", "content": "Hello"}]
|
||||
result = _convert_openai_images_to_anthropic(messages)
|
||||
assert result[0] is messages[0] # same object, not copied
|
||||
|
||||
def test_jpeg_media_type_parsed(self):
|
||||
from agent.auxiliary_client import _convert_openai_images_to_anthropic
|
||||
messages = [{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,/9j/="}}
|
||||
]
|
||||
}]
|
||||
result = _convert_openai_images_to_anthropic(messages)
|
||||
assert result[0]["content"][0]["source"]["media_type"] == "image/jpeg"
|
||||
|
|
|
|||
|
|
@ -87,7 +87,10 @@ class TestProviderMapping:
|
|||
|
||||
def test_unmapped_provider_not_in_dict(self):
|
||||
assert "nous" not in PROVIDER_TO_MODELS_DEV
|
||||
assert "openai-codex" not in PROVIDER_TO_MODELS_DEV
|
||||
|
||||
def test_openai_codex_mapped_to_openai(self):
|
||||
assert PROVIDER_TO_MODELS_DEV["openai"] == "openai"
|
||||
assert PROVIDER_TO_MODELS_DEV["openai-codex"] == "openai"
|
||||
|
||||
|
||||
class TestExtractContext:
|
||||
|
|
|
|||
|
|
@ -122,3 +122,54 @@ class TestCustomProviderModelSwitch:
|
|||
model = config.get("model")
|
||||
assert isinstance(model, dict)
|
||||
assert model["default"] == "model-X"
|
||||
|
||||
def test_api_mode_set_from_provider_info(self, config_home):
|
||||
"""When custom_providers entry has api_mode, it should be applied."""
|
||||
import yaml
|
||||
from hermes_cli.main import _model_flow_named_custom
|
||||
|
||||
provider_info = {
|
||||
"name": "Anthropic Proxy",
|
||||
"base_url": "https://proxy.example.com/anthropic",
|
||||
"api_key": "***",
|
||||
"model": "claude-3",
|
||||
"api_mode": "anthropic_messages",
|
||||
}
|
||||
|
||||
with patch("hermes_cli.models.fetch_api_models", return_value=["claude-3"]), \
|
||||
patch.dict("sys.modules", {"simple_term_menu": None}), \
|
||||
patch("builtins.input", return_value="1"), \
|
||||
patch("builtins.print"):
|
||||
_model_flow_named_custom({}, provider_info)
|
||||
|
||||
config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
|
||||
model = config.get("model")
|
||||
assert isinstance(model, dict)
|
||||
assert model.get("api_mode") == "anthropic_messages"
|
||||
|
||||
def test_api_mode_cleared_when_not_specified(self, config_home):
|
||||
"""When custom_providers entry has no api_mode, stale api_mode is removed."""
|
||||
import yaml
|
||||
from hermes_cli.main import _model_flow_named_custom
|
||||
|
||||
# Pre-seed a stale api_mode in config
|
||||
config_path = config_home / "config.yaml"
|
||||
config_path.write_text(yaml.dump({"model": {"api_mode": "anthropic_messages"}}))
|
||||
|
||||
provider_info = {
|
||||
"name": "My vLLM",
|
||||
"base_url": "https://vllm.example.com/v1",
|
||||
"api_key": "***",
|
||||
"model": "llama-3",
|
||||
}
|
||||
|
||||
with patch("hermes_cli.models.fetch_api_models", return_value=["llama-3"]), \
|
||||
patch.dict("sys.modules", {"simple_term_menu": None}), \
|
||||
patch("builtins.input", return_value="1"), \
|
||||
patch("builtins.print"):
|
||||
_model_flow_named_custom({}, provider_info)
|
||||
|
||||
config = yaml.safe_load((config_home / "config.yaml").read_text()) or {}
|
||||
model = config.get("model")
|
||||
assert isinstance(model, dict)
|
||||
assert "api_mode" not in model, "Stale api_mode should be removed"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue