fix(kimi): resolve Kimi Code API 403 errors and User-Agent restrictions (#3549)

* fix(kimi): resolve Kimi Code API 403 errors and User-Agent restrictions

Kimi Code subscription keys require a whitelisted coding-agent User-Agent to avoid access_terminated_error 403s. This adds User-Agent probing and caching for Kimi Code endpoints.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(kimi): omit temperature for kimi-for-coding API calls

Kimi Code rejects any non-default temperature with HTTP 400, which broke deep research probes and low-temp LLM rounds.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
KYDNO
2026-06-15 02:56:54 -04:00
committed by GitHub
parent 674457384a
commit 955455b797
10 changed files with 289 additions and 9 deletions
+12 -1
View File
@@ -248,6 +248,9 @@ _PROVIDER_CURATED = {
"zai-coding": [
"glm-5.1", "glm-5v-turbo", "glm-5-turbo", "glm-4.7", "glm-4.5-air",
],
"kimi-code": [
"kimi-for-coding",
],
"deepseek": [
"deepseek-chat", "deepseek-reasoner",
],
@@ -315,6 +318,8 @@ def _match_provider_curated(base_url: str, provider: str) -> str:
parsed = urlparse(base_url)
if _host_match(base_url, "z.ai") and "/api/coding" in (parsed.path or ""):
return "zai-coding"
if _host_match(base_url, "kimi.com") and "/coding" in (parsed.path or ""):
return "kimi-code"
for domain, key in _HOST_TO_CURATED:
if _host_match(base_url, domain):
return key
@@ -703,6 +708,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
"""Probe a base URL's /models endpoint and return list of model IDs.
For Anthropic, queries their /v1/models API, falling back to hardcoded list."""
from src.endpoint_resolver import resolve_url
from src.llm_core import httpx_get_kimi_aware
base = resolve_url(_normalize_base(base_url))
provider = _safe_detect_provider(base)
if provider == "chatgpt-subscription":
@@ -738,7 +744,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
url = _safe_build_models_url(base)
headers = _safe_build_headers(api_key, base)
try:
r = httpx.get(url, headers=headers, timeout=timeout, verify=llm_verify())
r = httpx_get_kimi_aware(url, headers, timeout=timeout, verify=llm_verify())
r.raise_for_status()
data = r.json()
# OpenAI format: {"data": [{"id": "model-name"}]}
@@ -754,6 +760,11 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
for _e in _PROVIDER_CURATED.get(_ck, []):
if _e not in set(models) and not any(m.startswith(_e) for m in models):
models.append(_e)
if _host_match(base, "kimi.com") and "/coding" in (urlparse(base).path or ""):
_ck = _match_provider_curated(base, None)
for _e in _PROVIDER_CURATED.get(_ck, []):
if _e not in set(models) and not any(m.startswith(_e) for m in models):
models.append(_e)
return [m for m in models if _is_chat_model(m)]
except httpx.HTTPStatusError as e:
if api_key:
+4
View File
@@ -198,6 +198,8 @@ def setup_webhook_routes(
"opencode-go": "https://opencode.ai/zen/go/v1",
"fireworks": "https://api.fireworks.ai/inference/v1",
"venice": "https://api.venice.ai/api/v1",
"kimi-code": "https://api.kimi.com/coding/v1",
"kimicode": "https://api.kimi.com/coding/v1",
}
# Model prefix → provider mapping for auto-detection
@@ -210,6 +212,8 @@ def setup_webhook_routes(
"mistral": "mistral",
"llama": "groq",
"mixtral": "groq",
"kimi-for-coding": "kimi-code",
"kimi": "kimi-code",
}
def _resolve_base_url(model: Optional[str], provider: Optional[str]) -> Optional[str]: