common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix: preserve URL query params for Azure OpenAI and custom endpoints

Browse Source 
Azure OpenAI requires an `api-version` query parameter on every request.
When users include it in the base_url (e.g. `?api-version=2025-04-01-preview`),
the OpenAI SDK silently drops it during URL construction, causing 404 errors.

Extract query params from base_url and pass them via `default_query` so the
SDK appends them to every request. This is a generic solution that works for
any custom endpoint requiring query parameters, not just Azure.

No-op for URLs without query params — fully backward compatible.
This commit is contained in:
pein892
2026-04-13 11:13:46 +08:00
committed by Teknium
parent c15064fa37
commit 24b4b24d79
2 changed files with 42 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
agent/auxiliary_client.py
View File

@@ -42,6 +42,7 @@ import time
from pathlib import Path # noqa: F401 — used by test mocks
from types import SimpleNamespace
from typing import Any, Dict, List, Optional, Tuple
from urllib.parse import urlparse, parse_qs, urlunparse
from openai import OpenAI
@@ -52,6 +53,17 @@ from utils import base_url_host_matches, base_url_hostname, normalize_proxy_env_
logger = logging.getLogger(__name__)
def _extract_url_query_params(url: str):
"""Extract query params from URL, return (clean_url, default_query dict or None)."""
parsed = urlparse(url)
if parsed.query:
clean = urlunparse(parsed._replace(query=""))
params = {k: v[0] for k, v in parse_qs(parsed.query).items()}
return clean, params
return url, None
# Module-level flag: only warn once per process about stale OPENAI_BASE_URL.
_stale_base_url_warned = False
@@ -1157,8 +1169,10 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
return None, None
model = _read_main_model() or "gpt-4o-mini"
logger.debug("Auxiliary client: custom endpoint (%s, api_mode=%s)", model, custom_mode or "chat_completions")
_clean_base, _dq = _extract_url_query_params(custom_base)
_extra = {"default_query": _dq} if _dq else {}
if custom_mode == "codex_responses":
real_client = OpenAI(api_key=custom_key, base_url=custom_base)
real_client = OpenAI(api_key=custom_key, base_url=_clean_base, **_extra)
return CodexAuxiliaryClient(real_client, model), model
if custom_mode == "anthropic_messages":
# Third-party Anthropic-compatible gateway (MiniMax, Zhipu GLM,
@@ -1172,12 +1186,12 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
"Custom endpoint declares api_mode=anthropic_messages but the "
"anthropic SDK is not installed — falling back to OpenAI-wire."
)
return OpenAI(api_key=custom_key, base_url=custom_base), model
return OpenAI(api_key=custom_key, base_url=_clean_base, **_extra), model
return (
AnthropicAuxiliaryClient(real_client, model, custom_key, custom_base, is_oauth=False),
model,
)
return OpenAI(api_key=custom_key, base_url=custom_base), model
return OpenAI(api_key=custom_key, base_url=_clean_base, **_extra), model
def _try_codex() -> Tuple[Optional[Any], Optional[str]]:
@@ -1825,12 +1839,15 @@ def resolve_provider_client(
provider,
)
extra = {}
_clean_base, _dq = _extract_url_query_params(custom_base)
if _dq:
extra["default_query"] = _dq
if base_url_host_matches(custom_base, "api.kimi.com"):
extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
elif base_url_host_matches(custom_base, "api.githubcopilot.com"):
from hermes_cli.models import copilot_default_headers
extra["default_headers"] = copilot_default_headers()
client = OpenAI(api_key=custom_key, base_url=custom_base, **extra)
client = OpenAI(api_key=custom_key, base_url=_clean_base, **extra)
client = _wrap_if_needed(client, final_model, custom_base)
return (_to_async_client(client, final_model) if async_mode
else (client, final_model))
@@ -1867,6 +1884,8 @@ def resolve_provider_client(
model or custom_entry.get("model") or _read_main_model() or "gpt-4o-mini",
provider,
)
_clean_base2, _dq2 = _extract_url_query_params(custom_base)
_extra2 = {"default_query": _dq2} if _dq2 else {}
logger.debug(
"resolve_provider_client: named custom provider %r (%s, api_mode=%s)",
provider, final_model, entry_api_mode or "chat_completions")
@@ -1884,7 +1903,7 @@ def resolve_provider_client(
"installed — falling back to OpenAI-wire.",
provider,
)
client = OpenAI(api_key=custom_key, base_url=custom_base)
client = OpenAI(api_key=custom_key, base_url=_clean_base2, **_extra2)
return (_to_async_client(client, final_model) if async_mode
else (client, final_model))
sync_anthropic = AnthropicAuxiliaryClient(
@@ -1893,7 +1912,7 @@ def resolve_provider_client(
if async_mode:
return AsyncAnthropicAuxiliaryClient(sync_anthropic), final_model
return sync_anthropic, final_model
client = OpenAI(api_key=custom_key, base_url=custom_base)
client = OpenAI(api_key=custom_key, base_url=_clean_base2, **_extra2)
# codex_responses or inherited auto-detect (via _wrap_if_needed).
# _wrap_if_needed reads the closed-over `api_mode` (the task-level
# override). Named-provider entry api_mode=codex_responses also