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

agent/auxiliary_client.py

@@ -922,6 +922,7 @@ def _resolve_forced_provider(forced: str) -> Tuple[Optional[OpenAI], Optional[st
 _AUTO_PROVIDER_LABELS = {
     "_try_openrouter": "openrouter",
     "_try_nous": "nous",
+    "_try_ollama": "ollama",
     "_try_custom_endpoint": "local/custom",
     "_try_codex": "openai-codex",
     "_resolve_api_key_provider": "api-key",
@@ -930,6 +931,18 @@ _AUTO_PROVIDER_LABELS = {
 _AGGREGATOR_PROVIDERS = frozenset({"openrouter", "nous"})
 
 
+def _try_ollama() -> Tuple[Optional[OpenAI], Optional[str]]:
+    """Detect and return an Ollama client if the server is reachable."""
+    base_url = (os.getenv("OLLAMA_BASE_URL", "") or "http://localhost:11434").strip().rstrip("/")
+    base_url = base_url + "/v1" if not base_url.endswith("/v1") else base_url
+    from agent.model_metadata import detect_local_server_type
+    if detect_local_server_type(base_url) != "ollama":
+        return None, None
+    api_key = (os.getenv("OLLAMA_API_KEY", "") or "ollama").strip()
+    model = _read_main_model() or "gemma4:12b"
+    return OpenAI(api_key=*** base_url=base_url), model
+
+
 def _get_provider_chain() -> List[tuple]:
     """Return the ordered provider detection chain.
 
@@ -939,6 +952,7 @@ def _get_provider_chain() -> List[tuple]:
     return [
         ("openrouter", _try_openrouter),
         ("nous", _try_nous),
+        ("ollama", _try_ollama),
         ("local/custom", _try_custom_endpoint),
         ("openai-codex", _try_codex),
         ("api-key", _resolve_api_key_provider),
@@ -988,6 +1002,7 @@ def _try_payment_fallback(
     # Map common resolved_provider values back to chain labels.
     _alias_to_label = {"openrouter": "openrouter", "nous": "nous",
                        "openai-codex": "openai-codex", "codex": "openai-codex",
+                       "ollama": "ollama",
                        "custom": "local/custom", "local/custom": "local/custom"}
     skip_chain_labels = {_alias_to_label.get(s, s) for s in skip_labels}
 
@@ -1195,6 +1210,15 @@ def resolve_provider_client(
         return (_to_async_client(client, final_model) if async_mode
                 else (client, final_model))
 
+    # ── Ollama (first-class local provider) ──────────────────────────
+    if provider == "ollama":
+        base_url = (explicit_base_url or os.getenv("OLLAMA_BASE_URL", "") or "http://localhost:11434").strip().rstrip("/")
+        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=*** 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) ───────────
     if provider == "custom":
         if explicit_base_url:
@@ -1335,6 +1359,7 @@ def get_async_text_auxiliary_client(task: str = ""):
 _VISION_AUTO_PROVIDER_ORDER = (
     "openrouter",
     "nous",
+    "ollama",
     "openai-codex",
     "anthropic",
     "custom",

agent/model_metadata.py

@@ -26,7 +26,7 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
     "gemini", "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
     "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
-    "custom", "local",
+    "ollama", "custom", "local",
     # Common aliases
     "google", "google-gemini", "google-ai-studio",
     "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
@@ -102,9 +102,12 @@ DEFAULT_CONTEXT_LENGTHS = {
     "gpt-4": 128000,
     # Google
     "gemini": 1048576,
-    # Gemma (open models served via AI Studio)
+    # Gemma (open models — Ollama / AI Studio)
     "gemma-4-31b": 256000,
     "gemma-4-26b": 256000,
+    "gemma-4-12b": 256000,
+    "gemma-4-4b": 256000,
+    "gemma-4-1b": 256000,
     "gemma-3": 131072,
     "gemma": 8192,  # fallback for older gemma models
     # DeepSeek
@@ -187,6 +190,8 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.githubcopilot.com": "copilot",
     "models.github.ai": "copilot",
     "api.fireworks.ai": "fireworks",
+    "localhost": "ollama",
+    "127.0.0.1": "ollama",
 }
 
 

config/fallback-config.yaml

@@ -6,7 +6,7 @@ model: anthropic/claude-opus-4.6
 # Fallback chain: Anthropic -> Kimi -> Ollama (local)
 fallback_providers:
   - provider: kimi-coding
-    model: kimi-for-coding
+    model: kimi-k2.5
     timeout: 60
     reason: "Primary fallback when Anthropic quota limited"
   

hermes_cli/auth.py

@@ -820,10 +820,11 @@ def resolve_provider(
         "hf": "huggingface", "hugging-face": "huggingface", "huggingface-hub": "huggingface",
         "go": "opencode-go", "opencode-go-sub": "opencode-go",
         "kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
-        # Local server aliases — route through the generic custom provider
+        # Local server aliases
         "lmstudio": "custom", "lm-studio": "custom", "lm_studio": "custom",
-        "ollama": "custom", "vllm": "custom", "llamacpp": "custom",
+        "vllm": "custom", "llamacpp": "custom",
         "llama.cpp": "custom", "llama-cpp": "custom",
+        "ollama": "ollama",
     }
     normalized = _PROVIDER_ALIASES.get(normalized, normalized)
 

hermes_cli/main.py

@@ -2126,9 +2126,8 @@ 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-for-coding first)
+        # Coding Plan models (kimi-k2.5 first — kimi-for-coding retired due to 403)
         model_list = [
-            "kimi-for-coding",
             "kimi-k2.5",
             "kimi-k2-thinking",
             "kimi-k2-thinking-turbo",
@@ -4206,7 +4205,7 @@ For more help on a command:
     )
     chat_parser.add_argument(
         "--provider",
-        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode"],
+        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "huggingface", "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "ollama"],
         default=None,
         help="Inference provider (default: auto)"
     )

hermes_cli/models.py

@@ -130,7 +130,6 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "glm-4.5-flash",
     ],
     "kimi-coding": [
-        "kimi-for-coding",
         "kimi-k2.5",
         "kimi-k2-thinking",
         "kimi-k2-thinking-turbo",
@@ -568,7 +567,7 @@ def list_available_providers() -> list[dict[str, str]]:
         "gemini", "huggingface",
         "zai", "kimi-coding", "minimax", "minimax-cn", "kilocode", "anthropic", "alibaba",
         "opencode-zen", "opencode-go",
-        "ai-gateway", "deepseek", "custom",
+        "ai-gateway", "deepseek", "ollama", "custom",
     ]
     # Build reverse alias map
     aliases_for: dict[str, list[str]] = {}

reports/ezra-quarterly-report-april-2026.md

@@ -235,7 +235,7 @@ The Hermes Agent framework serves as both the delivery platform and the portfoli
 
 | House | Host | Model / Provider | Gateway Status |
 |-------|------|------------------|----------------|
-| Ezra | Hermes VPS | `kimi-for-coding` (Kimi K2.5) | API `8658`, webhook `8648` — Active |
+| Ezra | Hermes VPS | `kimi-k2.5` (Kimi K2.5) | API `8658`, webhook `8648` — Active |
 | Bezalel | Hermes VPS | Claude Opus 4.6 (Anthropic) | Port `8645` — Active |
 | Allegro-Primus | Hermes VPS | Kimi K2.5 | Port `8644` — Requires restart |
 | Bilbo | External | Gemma 4B (local) | Telegram dual-mode — Active |

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-for-coding", "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}"
 
@@ -908,7 +908,7 @@ class TestKimiMoonshotModelListIsolation:
     def test_coding_plan_list_contains_plan_specific_models(self):
         from hermes_cli.main import _PROVIDER_MODELS
         coding_models = _PROVIDER_MODELS["kimi-coding"]
-        assert "kimi-for-coding" in coding_models
+        assert "kimi-k2.5" in coding_models
         assert "kimi-k2-thinking-turbo" in coding_models
 
 

website/docs/integrations/providers.md

@@ -142,7 +142,7 @@ hermes chat --provider zai --model glm-5
 # Requires: GLM_API_KEY in ~/.hermes/.env
 
 # Kimi / Moonshot AI
-hermes chat --provider kimi-coding --model kimi-for-coding
+hermes chat --provider kimi-coding --model kimi-k2.5
 # Requires: KIMI_API_KEY in ~/.hermes/.env
 
 # MiniMax (global endpoint)