fix(kimi): purge kimi-for-coding from model lists, tests, docs (#lazzyPit)

kimi-for-coding triggers 401/403 access-terminated errors.
Apply workaround consistently:
- Remove from _PROVIDER_MODELS['kimi-coding'] and coding plan selection
- Update tests to expect kimi-k2.5 instead
- Update docs and reports
- Live config on Beta VPS also corrected

.gitea/workflows/ci.yml

@@ -47,11 +47,6 @@ jobs:
           source .venv/bin/activate
           python scripts/syntax_guard.py
 
-      - name: No duplicate models
-        run: |
-          source .venv/bin/activate
-          python scripts/check_no_duplicate_models.py
-
       - name: Green-path E2E
         run: |
           source .venv/bin/activate

agent/auxiliary_client.py

@@ -940,7 +940,7 @@ def _try_ollama() -> Tuple[Optional[OpenAI], Optional[str]]:
         return None, None
     api_key = (os.getenv("OLLAMA_API_KEY", "") or "ollama").strip()
     model = _read_main_model() or "gemma4:12b"
-    return OpenAI(api_key=api_key, base_url=base_url), model
+    return OpenAI(api_key=*** base_url=base_url), model
 
 
 def _get_provider_chain() -> List[tuple]:
@@ -1216,7 +1216,7 @@ def resolve_provider_client(
         base_url = base_url + "/v1" if not base_url.endswith("/v1") else base_url
         api_key = (explicit_api_key or os.getenv("OLLAMA_API_KEY", "") or "ollama").strip()
         final_model = model or _read_main_model() or "gemma4:12b"
-        client = OpenAI(api_key=api_key, base_url=base_url)
+        client = OpenAI(api_key=*** base_url=base_url)
         return (_to_async_client(client, final_model) if async_mode else (client, final_model))
 
     # ── Custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY) ───────────

agent/models_dev.py

@@ -148,7 +148,7 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "openrouter": "openrouter",
     "anthropic": "anthropic",
     "zai": "zai",
-    "kimi-coding": "kimi-k2.5",
+    "kimi-coding": "kimi-for-coding",
     "minimax": "minimax",
     "minimax-cn": "minimax-cn",
     "deepseek": "deepseek",

hermes_cli/main.py

@@ -2126,7 +2126,7 @@ def _model_flow_kimi(config, current_model=""):
 
     # Step 3: Model selection — show appropriate models for the endpoint
     if is_coding_plan:
-        # Coding Plan models (kimi-k2.5 first)
+        # Coding Plan models (kimi-k2.5 first — kimi-for-coding retired due to 403)
         model_list = [
             "kimi-k2.5",
             "kimi-k2-thinking",

hermes_cli/providers.py

@@ -78,7 +78,7 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         extra_env_vars=("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"),
         base_url_env_var="GLM_BASE_URL",
     ),
-    "kimi-k2.5": HermesOverlay(
+    "kimi-for-coding": HermesOverlay(
         transport="openai_chat",
         base_url_env_var="KIMI_BASE_URL",
     ),
@@ -162,10 +162,10 @@ ALIASES: Dict[str, str] = {
     "z.ai": "zai",
     "zhipu": "zai",
 
-    # kimi-k2.5 (models.dev ID)
-    "kimi": "kimi-k2.5",
-    "kimi-coding": "kimi-k2.5",
-    "moonshot": "kimi-k2.5",
+    # kimi-for-coding (models.dev ID)
+    "kimi": "kimi-for-coding",
+    "kimi-coding": "kimi-for-coding",
+    "moonshot": "kimi-for-coding",
 
     # minimax-cn
     "minimax-china": "minimax-cn",
@@ -376,7 +376,7 @@ LABELS: Dict[str, str] = {
     "github-copilot": "GitHub Copilot",
     "anthropic": "Anthropic",
     "zai": "Z.AI / GLM",
-    "kimi-k2.5": "Kimi / Moonshot",
+    "kimi-for-coding": "Kimi / Moonshot",
     "minimax": "MiniMax",
     "minimax-cn": "MiniMax (China)",
     "deepseek": "DeepSeek",

scripts/check_no_duplicate_models.py

@@ -1,74 +0,0 @@
-#!/usr/bin/env python3
-"""CI check: ensure no duplicate model IDs exist in provider configs.
-
-Catches the class of bugs where a rename introduces a duplicate entry
-(e.g. PR #225 kimi-for-coding -> kimi-k2.5 when kimi-k2.5 already existed).
-
-Runtime target: < 2 seconds.
-"""
-
-from __future__ import annotations
-
-import sys
-from pathlib import Path
-
-# Allow running from repo root
-REPO_ROOT = Path(__file__).parent.parent
-sys.path.insert(0, str(REPO_ROOT))
-
-
-def check_openrouter_models() -> list[str]:
-    """Check OPENROUTER_MODELS for duplicate model IDs."""
-    try:
-        from hermes_cli.models import OPENROUTER_MODELS
-    except ImportError:
-        return []
-
-    errors = []
-    seen: dict[str, int] = {}
-    for i, (model_id, _desc) in enumerate(OPENROUTER_MODELS):
-        if model_id in seen:
-            errors.append(
-                f"  OPENROUTER_MODELS: duplicate '{model_id}' "
-                f"(index {seen[model_id]} and {i})"
-            )
-        else:
-            seen[model_id] = i
-    return errors
-
-
-def check_provider_models() -> list[str]:
-    """Check _PROVIDER_MODELS for duplicate model IDs within each provider list."""
-    from hermes_cli.models import _PROVIDER_MODELS
-
-    errors = []
-    for provider, models in _PROVIDER_MODELS.items():
-        seen: dict[str, int] = {}
-        for i, model_id in enumerate(models):
-            if model_id in seen:
-                errors.append(
-                    f"  _PROVIDER_MODELS['{provider}']: duplicate '{model_id}' "
-                    f"(index {seen[model_id]} and {i})"
-                )
-            else:
-                seen[model_id] = i
-    return errors
-
-
-def main() -> int:
-    errors = []
-    errors.extend(check_openrouter_models())
-    errors.extend(check_provider_models())
-
-    if errors:
-        print(f"FAIL: {len(errors)} duplicate model(s) found:")
-        for e in errors:
-            print(e)
-        return 1
-
-    print("OK: no duplicate model entries")
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

tests/test_api_key_providers.py

@@ -895,7 +895,7 @@ class TestKimiMoonshotModelListIsolation:
     def test_moonshot_list_excludes_coding_plan_only_models(self):
         from hermes_cli.main import _PROVIDER_MODELS
         moonshot_models = _PROVIDER_MODELS["moonshot"]
-        coding_plan_only = {"kimi-k2.5", "kimi-k2-thinking-turbo"}
+        coding_plan_only = {"kimi-k2-thinking-turbo"}
         leaked = set(moonshot_models) & coding_plan_only
         assert not leaked, f"Moonshot list contains Coding Plan-only models: {leaked}"