mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-02 02:01:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(auxiliary): pass raw base_url to _maybe_wrap_anthropic for correct transport detection (#17467)

Browse source 
Fixes HTTP 404 errors when using Anthropic-compatible providers (Kimi Coding, MiniMax, MiniMax-CN) for auxiliary tasks.

Root cause: `_to_openai_base_url()` rewrites `/anthropic` → `/v1` so the OpenAI SDK hits the right endpoint. But the rewritten URL was then passed to `_maybe_wrap_anthropic`, whose `_endpoint_speaks_anthropic_messages` detector only fires on `/anthropic` or `api.kimi.com/coding`. Detector saw `/v1` → returned False → no Anthropic wrap → 404 on every aux call.

Fix: preserve the raw base_url before rewriting and pass it to `_maybe_wrap_anthropic` for transport detection, while still giving the rewritten URL to the OpenAI client constructor.

Closes #17705, #17413, #17086, #10469.

Co-authored-by: oak <chengoak@users.noreply.github.com>
This commit is contained in:
oak 2026-05-01 01:18:42 +08:00 • committed by GitHub
parent d954d6fbcf
commit 4e296dcdda
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 19 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

32
agent/auxiliary_client.py
View file

@ -355,6 +355,13 @@ def _to_openai_base_url(base_url: str) -> str:
rewritten = url[: -len("/anthropic")] + "/v1"
logger.debug("Auxiliary client: rewrote base URL %s → %s", url, rewritten)
return rewritten
if "api.kimi.com" in url and url.endswith("/coding"):
# Kimi Code uses /coding/v1/messages for Anthropic SDK (appends /v1/messages)
# but /coding/v1/chat/completions for OpenAI SDK (appends /chat/completions)
# Without /v1 here, OpenAI SDK hits /coding/chat/completions — a 404.
rewritten = url + "/v1"
logger.debug("Auxiliary client: rewrote Kimi base URL %s → %s", url, rewritten)
return rewritten
return url
@ -1086,9 +1093,8 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
if not api_key:
continue
base_url = _to_openai_base_url(
_pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
)
raw_base_url = _pool_runtime_base_url(entry, pconfig.inference_base_url) or pconfig.inference_base_url
base_url = _to_openai_base_url(raw_base_url)
model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id)
if model is None:
continue # skip provider if we don't know a valid aux model
@ -1106,7 +1112,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
extra["default_headers"] = copilot_default_headers()
_client = OpenAI(api_key=api_key, base_url=base_url, **extra)
_client = _maybe_wrap_anthropic(_client, model, api_key, base_url)
_client = _maybe_wrap_anthropic(_client, model, api_key, raw_base_url)
return _client, model
creds = resolve_api_key_provider_credentials(provider_id)
@ -1114,9 +1120,8 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
if not api_key:
continue
base_url = _to_openai_base_url(
str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
)
raw_base_url = str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
base_url = _to_openai_base_url(raw_base_url)
model = _API_KEY_PROVIDER_AUX_MODELS.get(provider_id)
if model is None:
continue # skip provider if we don't know a valid aux model
@ -1134,7 +1139,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
extra["default_headers"] = copilot_default_headers()
_client = OpenAI(api_key=api_key, base_url=base_url, **extra)
_client = _maybe_wrap_anthropic(_client, model, api_key, base_url)
_client = _maybe_wrap_anthropic(_client, model, api_key, raw_base_url)
return _client, model
return None, None
@ -2184,8 +2189,10 @@ def resolve_provider_client(
# Anthropic fallback SDK still sees the original URL.
if entry_api_mode == "anthropic_messages":
openai_base = custom_base
raw_base_for_wrap = custom_base
else:
openai_base = _to_openai_base_url(custom_base)
raw_base_for_wrap = custom_base
_clean_base2, _dq2 = _extract_url_query_params(openai_base)
_extra2 = {"default_query": _dq2} if _dq2 else {}
logger.debug(
@ -2229,7 +2236,7 @@ def resolve_provider_client(
):
client = CodexAuxiliaryClient(client, final_model)
else:
client = _wrap_if_needed(client, final_model, openai_base, custom_key)
client = _wrap_if_needed(client, final_model, raw_base_for_wrap, custom_key)
return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode
else (client, final_model))
logger.warning(
@ -2275,9 +2282,8 @@ def resolve_provider_client(
provider, ", ".join(tried_sources))
return None, None
base_url = _to_openai_base_url(
str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
)
raw_base_url = str(creds.get("base_url", "")).strip().rstrip("/") or pconfig.inference_base_url
base_url = _to_openai_base_url(raw_base_url)
default_model = _API_KEY_PROVIDER_AUX_MODELS.get(provider, "")
final_model = _normalize_resolved_model(model or default_model, provider)
@ -2326,7 +2332,7 @@ def resolve_provider_client(
# Anthropic-wire endpoints (Kimi Coding Plan api.kimi.com/coding,
# /anthropic-suffixed gateways) so named providers like kimi-coding
# land on the right transport without needing per-provider branches.
client = _wrap_if_needed(client, final_model, base_url, api_key)
client = _wrap_if_needed(client, final_model, raw_base_url, api_key)
logger.debug("resolve_provider_client: %s (%s)", provider, final_model)
return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode