diff --git a/agent/anthropic_adapter.py b/agent/anthropic_adapter.py
index ff1d536b1753a..088f84c33411a 100644
--- a/agent/anthropic_adapter.py
+++ b/agent/anthropic_adapter.py
@@ -266,6 +266,14 @@ def _is_third_party_anthropic_endpoint(base_url: str | None) -> bool:
     return True  # Any other endpoint is a third-party proxy
 
 
+def _is_kimi_coding_endpoint(base_url: str | None) -> bool:
+    """Return True for Kimi's /coding endpoint that requires claude-code UA."""
+    normalized = _normalize_base_url_text(base_url)
+    if not normalized:
+        return False
+    return normalized.rstrip("/").lower().startswith("https://api.kimi.com/coding")
+
+
 def _requires_bearer_auth(base_url: str | None) -> bool:
     """Return True for Anthropic-compatible providers that require Bearer auth.
 
@@ -323,9 +331,18 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
         kwargs["base_url"] = normalized_base_url
     common_betas = _common_betas_for_base_url(normalized_base_url)
 
-    if _requires_bearer_auth(normalized_base_url):
+    if _is_kimi_coding_endpoint(base_url):
+        # Kimi's /coding endpoint requires User-Agent: claude-code/0.1.0
+        # to be recognized as a valid Coding Agent. Without it, returns 403.
+        # Check this BEFORE _requires_bearer_auth since both match api.kimi.com/coding.
+        kwargs["api_key"] = api_key
+        kwargs["default_headers"] = {
+            "User-Agent": "claude-code/0.1.0",
+            **( {"anthropic-beta": ",".join(common_betas)} if common_betas else {} )
+        }
+    elif _requires_bearer_auth(normalized_base_url):
         # Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
-        # Authorization: Bearer even for regular API keys. Route those endpoints
+        # Authorization: Bearer *** for regular API keys. Route those endpoints
         # through auth_token so the SDK sends Bearer auth instead of x-api-key.
         # Check this before OAuth token shape detection because MiniMax secrets do
         # not use Anthropic's sk-ant-api prefix and would otherwise be misread as
diff --git a/agent/auxiliary_client.py b/agent/auxiliary_client.py
index 5195b09520891..f738c8c0f937e 100644
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -845,7 +845,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
                     return GeminiNativeClient(api_key=api_key, base_url=base_url), model
             extra = {}
             if base_url_host_matches(base_url, "api.kimi.com"):
-                extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+                extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
             elif base_url_host_matches(base_url, "api.githubcopilot.com"):
                 from hermes_cli.models import copilot_default_headers
 
@@ -871,7 +871,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
                 return GeminiNativeClient(api_key=api_key, base_url=base_url), model
         extra = {}
         if base_url_host_matches(base_url, "api.kimi.com"):
-            extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+            extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
         elif base_url_host_matches(base_url, "api.githubcopilot.com"):
             from hermes_cli.models import copilot_default_headers
 
@@ -1487,7 +1487,7 @@ def _to_async_client(sync_client, model: str):
 
         async_kwargs["default_headers"] = copilot_default_headers()
     elif base_url_host_matches(sync_base_url, "api.kimi.com"):
-        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+        async_kwargs["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
     return AsyncOpenAI(**async_kwargs), model
 
 
@@ -1674,7 +1674,7 @@ def _wrap_if_needed(client_obj, final_model_str: str, base_url_str: str = ""):
             )
             extra = {}
             if base_url_host_matches(custom_base, "api.kimi.com"):
-                extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+                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()
@@ -1781,7 +1781,7 @@ def _wrap_if_needed(client_obj, final_model_str: str, base_url_str: str = ""):
         # Provider-specific headers
         headers = {}
         if base_url_host_matches(base_url, "api.kimi.com"):
-            headers["User-Agent"] = "KimiCLI/1.30.0"
+            headers["User-Agent"] = "claude-code/0.1.0"
         elif base_url_host_matches(base_url, "api.githubcopilot.com"):
             from hermes_cli.models import copilot_default_headers
 
diff --git a/hermes_cli/auth.py b/hermes_cli/auth.py
index c82bad3f02fcf..9f3b3cae94b32 100644
--- a/hermes_cli/auth.py
+++ b/hermes_cli/auth.py
@@ -168,8 +168,11 @@ class ProviderConfig:
         id="kimi-coding",
         name="Kimi / Moonshot",
         auth_type="api_key",
+        # Legacy platform.moonshot.ai keys use this endpoint (OpenAI-compat).
+        # sk-kimi- (Kimi Code) keys are auto-redirected to api.kimi.com/coding
+        # by _resolve_kimi_base_url() below.
         inference_base_url="https://api.moonshot.ai/v1",
-        api_key_env_vars=("KIMI_API_KEY",),
+        api_key_env_vars=("KIMI_API_KEY", "KIMI_CODING_API_KEY"),
         base_url_env_var="KIMI_BASE_URL",
     ),
     "kimi-coding-cn": ProviderConfig(
@@ -340,10 +343,16 @@ def get_anthropic_key() -> str:
 # =============================================================================
 
 # Kimi Code (kimi.com/code) issues keys prefixed "sk-kimi-" that only work
-# on api.kimi.com/coding/v1.  Legacy keys from platform.moonshot.ai work on
-# api.moonshot.ai/v1 (the default).  Auto-detect when user hasn't set
+# on api.kimi.com/coding.  Legacy keys from platform.moonshot.ai work on
+# api.moonshot.ai/v1 (the old default).  Auto-detect when user hasn't set
 # KIMI_BASE_URL explicitly.
-KIMI_CODE_BASE_URL = "https://api.kimi.com/coding/v1"
+#
+# Note: the base URL intentionally has NO /v1 suffix.  The /coding endpoint
+# speaks the Anthropic Messages protocol, and the anthropic SDK appends
+# "/v1/messages" internally — so "/coding" + SDK suffix → "/coding/v1/messages"
+# (the correct target). Using "/coding/v1" here would produce
+# "/coding/v1/v1/messages" (a 404).
+KIMI_CODE_BASE_URL = "https://api.kimi.com/coding"
 
 
 def _resolve_kimi_base_url(api_key: str, default_url: str, env_override: str) -> str:
diff --git a/hermes_cli/doctor.py b/hermes_cli/doctor.py
index e16f0bf5e64b5..2fc50321f68a6 100644
--- a/hermes_cli/doctor.py
+++ b/hermes_cli/doctor.py
@@ -943,18 +943,22 @@ def run_doctor(args):
             try:
                 import httpx
                 _base = os.getenv(_base_env, "") if _base_env else ""
-                # Auto-detect Kimi Code keys (sk-kimi-) → api.kimi.com
+                # Auto-detect Kimi Code keys (sk-kimi-) → api.kimi.com/coding/v1
+                # (OpenAI-compat surface, which exposes /models for health check).
                 if not _base and _key.startswith("sk-kimi-"):
                     _base = "https://api.kimi.com/coding/v1"
-                # Anthropic-compat endpoints (/anthropic) don't support /models.
-                # Rewrite to the OpenAI-compat /v1 surface for health checks.
+                # Anthropic-compat endpoints (/anthropic, api.kimi.com/coding
+                # with no /v1) don't support /models.  Rewrite to the OpenAI-compat
+                # /v1 surface for health checks.
                 if _base and _base.rstrip("/").endswith("/anthropic"):
                     from agent.auxiliary_client import _to_openai_base_url
                     _base = _to_openai_base_url(_base)
+                if base_url_host_matches(_base, "api.kimi.com") and _base.rstrip("/").endswith("/coding"):
+                    _base = _base.rstrip("/") + "/v1"
                 _url = (_base.rstrip("/") + "/models") if _base else _default_url
                 _headers = {"Authorization": f"Bearer {_key}"}
                 if base_url_host_matches(_base, "api.kimi.com"):
-                    _headers["User-Agent"] = "KimiCLI/1.30.0"
+                    _headers["User-Agent"] = "claude-code/0.1.0"
                 _resp = httpx.get(
                     _url,
                     headers=_headers,
diff --git a/hermes_cli/model_switch.py b/hermes_cli/model_switch.py
index 22721f9a42733..5b26f5b8b5f7c 100644
--- a/hermes_cli/model_switch.py
+++ b/hermes_cli/model_switch.py
@@ -678,6 +678,7 @@ def switch_model(
         _da = DIRECT_ALIASES.get(resolved_alias)
         if _da is not None and _da.base_url:
             base_url = _da.base_url
+            api_mode = ""  # clear so determine_api_mode re-detects from URL
             if not api_key:
                 api_key = "no-key-required"
 
diff --git a/hermes_cli/providers.py b/hermes_cli/providers.py
index 1764474aa9a5a..00c3f64bcf9e8 100644
--- a/hermes_cli/providers.py
+++ b/hermes_cli/providers.py
@@ -427,6 +427,16 @@ def determine_api_mode(provider: str, base_url: str = "") -> str:
     """
     pdef = get_provider(provider)
     if pdef is not None:
+        # Even for known providers, check URL heuristics for special endpoints
+        # (e.g. kimi /coding endpoint needs anthropic_messages even on 'custom')
+        if base_url:
+            url_lower = base_url.rstrip("/").lower()
+            if "api.kimi.com/coding" in url_lower:
+                return "anthropic_messages"
+            if url_lower.endswith("/anthropic") or "api.anthropic.com" in url_lower:
+                return "anthropic_messages"
+            if "api.openai.com" in url_lower:
+                return "codex_responses"
         return TRANSPORT_TO_API_MODE.get(pdef.transport, "chat_completions")
 
     # Direct provider checks for providers not in HERMES_OVERLAYS
@@ -439,6 +449,8 @@ def determine_api_mode(provider: str, base_url: str = "") -> str:
         hostname = base_url_hostname(base_url)
         if url_lower.endswith("/anthropic") or hostname == "api.anthropic.com":
             return "anthropic_messages"
+        if hostname == "api.kimi.com" and "/coding" in url_lower:
+            return "anthropic_messages"
         if hostname == "api.openai.com":
             return "codex_responses"
         if hostname.startswith("bedrock-runtime.") and base_url_host_matches(base_url, "amazonaws.com"):
diff --git a/hermes_cli/runtime_provider.py b/hermes_cli/runtime_provider.py
index 62f1407cc7a60..922946e2ad06d 100644
--- a/hermes_cli/runtime_provider.py
+++ b/hermes_cli/runtime_provider.py
@@ -46,6 +46,9 @@ def _detect_api_mode_for_url(base_url: str) -> Optional[str]:
       protocol under a ``/anthropic`` suffix — treat those as
       ``anthropic_messages`` transport instead of the default
       ``chat_completions``.
+    - Kimi Code's ``api.kimi.com/coding`` endpoint also speaks the
+      Anthropic Messages protocol (the /coding route accepts Claude
+      Code's native request shape).
     """
     normalized = (base_url or "").strip().lower().rstrip("/")
     hostname = base_url_hostname(base_url)
@@ -55,6 +58,8 @@ def _detect_api_mode_for_url(base_url: str) -> Optional[str]:
         return "codex_responses"
     if normalized.endswith("/anthropic"):
         return "anthropic_messages"
+    if hostname == "api.kimi.com" and "/coding" in normalized:
+        return "anthropic_messages"
     return None
 
 
@@ -205,7 +210,8 @@ def _resolve_runtime_from_pool_entry(
             api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
         else:
             # Auto-detect Anthropic-compatible endpoints (/anthropic suffix,
-            # api.openai.com → codex_responses, api.x.ai → codex_responses).
+            # Kimi /coding, api.openai.com → codex_responses, api.x.ai →
+            # codex_responses).
             detected = _detect_api_mode_for_url(base_url)
             if detected:
                 api_mode = detected
@@ -660,7 +666,8 @@ def _resolve_explicit_runtime(
             if configured_mode:
                 api_mode = configured_mode
             else:
-                # Auto-detect Anthropic-compatible endpoints (/anthropic suffix).
+                # Auto-detect from URL (Anthropic /anthropic suffix,
+                # api.openai.com → Responses, Kimi /coding, etc.).
                 detected = _detect_api_mode_for_url(base_url)
                 if detected:
                     api_mode = detected
diff --git a/run_agent.py b/run_agent.py
index c5966a173706b..4f431bb6a96c3 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -1175,7 +1175,7 @@ def __init__(
                     client_kwargs["default_headers"] = copilot_default_headers()
                 elif base_url_host_matches(effective_base, "api.kimi.com"):
                     client_kwargs["default_headers"] = {
-                        "User-Agent": "KimiCLI/1.30.0",
+                        "User-Agent": "claude-code/0.1.0",
                     }
                 elif base_url_host_matches(effective_base, "portal.qwen.ai"):
                     client_kwargs["default_headers"] = _qwen_portal_headers()
@@ -5049,7 +5049,7 @@ def _apply_client_headers_for_base_url(self, base_url: str) -> None:
 
             self._client_kwargs["default_headers"] = copilot_default_headers()
         elif base_url_host_matches(base_url, "api.kimi.com"):
-            self._client_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+            self._client_kwargs["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
         elif base_url_host_matches(base_url, "portal.qwen.ai"):
             self._client_kwargs["default_headers"] = _qwen_portal_headers()
         elif base_url_host_matches(base_url, "chatgpt.com"):
diff --git a/scripts/release.py b/scripts/release.py
index f2a72ea0038d4..7050993137cf0 100755
--- a/scripts/release.py
+++ b/scripts/release.py
@@ -44,6 +44,7 @@
     "teknium@nousresearch.com": "teknium1",
     "127238744+teknium1@users.noreply.github.com": "teknium1",
     # contributors (from noreply pattern)
+    "wangqiang@wangqiangdeMac-mini.local": "xiaoqiang243",
     "snreynolds2506@gmail.com": "snreynolds",
     "35742124+0xbyt4@users.noreply.github.com": "0xbyt4",
     "71184274+MassiveMassimo@users.noreply.github.com": "MassiveMassimo",
diff --git a/tests/hermes_cli/test_api_key_providers.py b/tests/hermes_cli/test_api_key_providers.py
index 2af003ea08622..7d0674b038583 100644
--- a/tests/hermes_cli/test_api_key_providers.py
+++ b/tests/hermes_cli/test_api_key_providers.py
@@ -71,7 +71,11 @@ def test_copilot_env_vars(self):
 
     def test_kimi_env_vars(self):
         pconfig = PROVIDER_REGISTRY["kimi-coding"]
-        assert pconfig.api_key_env_vars == ("KIMI_API_KEY",)
+        # KIMI_API_KEY is the primary env var; KIMI_CODING_API_KEY is a
+        # secondary fallback for Kimi Code sk-kimi- keys so users don't
+        # have to overload the same variable.
+        assert "KIMI_API_KEY" in pconfig.api_key_env_vars
+        assert "KIMI_CODING_API_KEY" in pconfig.api_key_env_vars
         assert pconfig.base_url_env_var == "KIMI_BASE_URL"
 
     def test_minimax_env_vars(self):
diff --git a/tools/delegate_tool.py b/tools/delegate_tool.py
index 093be11c01663..ebf771d1598e7 100644
--- a/tools/delegate_tool.py
+++ b/tools/delegate_tool.py
@@ -1322,6 +1322,9 @@ def _resolve_delegation_credentials(cfg: dict, parent_agent) -> dict:
         elif base_url_hostname(configured_base_url) == "api.anthropic.com":
             provider = "anthropic"
             api_mode = "anthropic_messages"
+        elif "api.kimi.com/coding" in base_lower:
+            provider = "custom"
+            api_mode = "anthropic_messages"
 
         return {
             "model": configured_model,