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>

tests/test_model_routes.py

@@ -205,6 +205,9 @@ class TestMatchProviderCurated:
     def test_ollama_url(self):
         assert _match_provider_curated("https://ollama.com/api", "openai") == "ollama"
 
+    def test_kimi_code_url(self):
+        assert _match_provider_curated("https://api.kimi.com/coding/v1", "openai") == "kimi-code"
+
     def test_no_url_match_returns_provider(self):
         assert _match_provider_curated("https://localhost:1234", "openai") == "openai"
 
@@ -312,6 +315,12 @@ class TestCurateModels:
         assert curated == models
         assert extra == []
 
+    def test_kimi_code_partitions(self):
+        models = ["kimi-for-coding", "other-model"]
+        curated, extra = _curate_models(models, "kimi-code")
+        assert "kimi-for-coding" in curated
+        assert "other-model" in extra
+
     def test_curated_sorted_by_priority(self):
         models = ["gpt-4o-mini", "gpt-4o", "o3"]
         curated, _ = _curate_models(models, "openai")