fix(kimi): send max_tokens, reasoning_effort, and thinking for Kimi/Moonshot

Kimi/Moonshot endpoints require explicit parameters that Hermes was not
sending, causing 'Response truncated due to output length limit' errors
and inconsistent reasoning behavior.

Root cause analysis against Kimi CLI source (MoonshotAI/kimi-cli,
packages/kosong/src/kosong/chat_provider/kimi.py):

1. max_tokens: Kimi's API defaults to a very low value when omitted.
   Reasoning tokens share the output budget — the model exhausts it on
   thinking alone.  Send 32000, matching Kimi CLI's generate() default.

2. reasoning_effort: Kimi CLI sends this as a top-level parameter (not
   inside extra_body).  Hermes was not sending it at all because
   _supports_reasoning_extra_body() returns False for non-OpenRouter
   endpoints.

3. extra_body.thinking: Kimi CLI uses with_thinking() which sets
   extra_body.thinking={"type":"enabled"} alongside reasoning_effort.
   This is a separate control from the OpenAI-style reasoning extra_body
   that Hermes sends for OpenRouter/GitHub.  Without it, the Kimi gateway
   may not activate reasoning mode correctly.

Covers api.kimi.com (Kimi Code) and api.moonshot.ai/cn (Moonshot).

Tests: 6 new test cases for max_tokens, reasoning_effort, and
extra_body.thinking under various configs.

tests/run_agent/test_run_agent.py

@@ -952,6 +952,84 @@ class TestBuildApiKwargs:
 
         assert "temperature" not in kwargs
 
+    def test_kimi_coding_endpoint_sends_max_tokens_and_reasoning(self, agent):
+        """Kimi endpoint should send max_tokens=32000 and reasoning_effort as
+        top-level params, matching Kimi CLI's default behavior."""
+        agent.base_url = "https://api.kimi.com/coding/v1"
+        agent._base_url_lower = agent.base_url.lower()
+        agent.model = "kimi-for-coding"
+        messages = [{"role": "user", "content": "hi"}]
+
+        kwargs = agent._build_api_kwargs(messages)
+
+        assert kwargs["max_tokens"] == 32000
+        assert kwargs["reasoning_effort"] == "medium"
+
+    def test_kimi_coding_endpoint_respects_custom_effort(self, agent):
+        """reasoning_effort should reflect reasoning_config.effort when set."""
+        agent.base_url = "https://api.kimi.com/coding/v1"
+        agent._base_url_lower = agent.base_url.lower()
+        agent.model = "kimi-for-coding"
+        agent.reasoning_config = {"enabled": True, "effort": "high"}
+        messages = [{"role": "user", "content": "hi"}]
+
+        kwargs = agent._build_api_kwargs(messages)
+
+        assert kwargs["reasoning_effort"] == "high"
+
+    def test_kimi_coding_endpoint_sends_thinking_extra_body(self, agent):
+        """Kimi endpoint should send extra_body.thinking={"type":"enabled"}
+        to activate reasoning mode, mirroring Kimi CLI's with_thinking()."""
+        agent.base_url = "https://api.kimi.com/coding/v1"
+        agent._base_url_lower = agent.base_url.lower()
+        agent.model = "kimi-for-coding"
+        messages = [{"role": "user", "content": "hi"}]
+
+        kwargs = agent._build_api_kwargs(messages)
+
+        assert kwargs["extra_body"]["thinking"] == {"type": "enabled"}
+
+    def test_kimi_coding_endpoint_disables_thinking(self, agent):
+        """When reasoning_config.enabled=False, thinking should be disabled
+        and reasoning_effort should be omitted entirely — mirroring Kimi
+        CLI's with_thinking("off") which maps to reasoning_effort=None."""
+        agent.base_url = "https://api.kimi.com/coding/v1"
+        agent._base_url_lower = agent.base_url.lower()
+        agent.model = "kimi-for-coding"
+        agent.reasoning_config = {"enabled": False}
+        messages = [{"role": "user", "content": "hi"}]
+
+        kwargs = agent._build_api_kwargs(messages)
+
+        assert kwargs["extra_body"]["thinking"] == {"type": "disabled"}
+        assert "reasoning_effort" not in kwargs
+
+    def test_moonshot_endpoint_sends_max_tokens_and_reasoning(self, agent):
+        """api.moonshot.ai should get the same Kimi-compatible params."""
+        agent.base_url = "https://api.moonshot.ai/v1"
+        agent._base_url_lower = agent.base_url.lower()
+        agent.model = "kimi-k2.5"
+        messages = [{"role": "user", "content": "hi"}]
+
+        kwargs = agent._build_api_kwargs(messages)
+
+        assert kwargs["max_tokens"] == 32000
+        assert kwargs["reasoning_effort"] == "medium"
+        assert kwargs["extra_body"]["thinking"] == {"type": "enabled"}
+
+    def test_moonshot_cn_endpoint_sends_max_tokens_and_reasoning(self, agent):
+        """api.moonshot.cn (China endpoint) should get the same params."""
+        agent.base_url = "https://api.moonshot.cn/v1"
+        agent._base_url_lower = agent.base_url.lower()
+        agent.model = "kimi-k2.5"
+        messages = [{"role": "user", "content": "hi"}]
+
+        kwargs = agent._build_api_kwargs(messages)
+
+        assert kwargs["max_tokens"] == 32000
+        assert kwargs["reasoning_effort"] == "medium"
+        assert kwargs["extra_body"]["thinking"] == {"type": "enabled"}
+
     def test_provider_preferences_injected(self, agent):
         agent.base_url = "https://openrouter.ai/api/v1"
         agent.providers_allowed = ["Anthropic"]