fix: integrate OpenAI Codex provider with new registry system

- Add OpenAI Codex ProviderSpec to registry.py
- Add openai_codex config field to ProvidersConfig in schema.py
- Mark Codex as OAuth-based (no API key required)
- Set appropriate default_api_base for Codex API

This integrates the Codex OAuth provider with the refactored
provider registry system introduced in upstream commit 299d8b3.

nanobot/config/schema.py

@@ -81,6 +81,7 @@ class ProvidersConfig(BaseModel):
     gemini: ProviderConfig = Field(default_factory=ProviderConfig)
     moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
     aihubmix: ProviderConfig = Field(default_factory=ProviderConfig)  # AiHubMix API gateway
+    openai_codex: ProviderConfig = Field(default_factory=ProviderConfig)  # OpenAI Codex (OAuth)  # AiHubMix API gateway
 
 
 class GatewayConfig(BaseModel):

nanobot/providers/registry.py

@@ -141,6 +141,24 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         model_overrides=(),
     ),
 
+    # OpenAI Codex: uses OAuth, not API key.
+    ProviderSpec(
+        name="openai_codex",
+        keywords=("openai-codex", "codex"),
+        env_key="",                         # OAuth-based, no API key
+        display_name="OpenAI Codex",
+        litellm_prefix="",                  # Not routed through LiteLLM
+        skip_prefixes=(),
+        env_extras=(),
+        is_gateway=False,
+        is_local=False,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="codex",
+        default_api_base="https://chatgpt.com/backend-api",
+        strip_model_prefix=False,
+        model_overrides=(),
+    ),
+
     # DeepSeek: needs "deepseek/" prefix for LiteLLM routing.
     ProviderSpec(
         name="deepseek",