fix(openai): route api.openai.com to Responses API for GPT-5.x

Based on PR #1859 by @magi-morph (too stale to cherry-pick, reimplemented).

GPT-5.x models reject tool calls + reasoning_effort on
/v1/chat/completions with a 400 error directing to /v1/responses.
This auto-detects api.openai.com in the base URL and switches to
codex_responses mode in three places:

- AIAgent.__init__: upgrades chat_completions → codex_responses
- _try_activate_fallback(): same routing for fallback model
- runtime_provider.py: _detect_api_mode_for_url() for both custom
  provider and openrouter runtime resolution paths

Also extracts _is_direct_openai_url() helper to replace the inline
check in _max_tokens_param().

hermes_cli/runtime_provider.py

@@ -24,6 +24,18 @@ def _normalize_custom_provider_name(value: str) -> str:
     return value.strip().lower().replace(" ", "-")
 
 
+def _detect_api_mode_for_url(base_url: str) -> Optional[str]:
+    """Auto-detect api_mode from the resolved base URL.
+
+    Direct api.openai.com endpoints need the Responses API for GPT-5.x
+    tool calls with reasoning (chat/completions returns 400).
+    """
+    normalized = (base_url or "").strip().lower().rstrip("/")
+    if "api.openai.com" in normalized and "openrouter" not in normalized:
+        return "codex_responses"
+    return None
+
+
 def _auto_detect_local_model(base_url: str) -> str:
     """Query a local server for its model name when only one model is loaded."""
     if not base_url:
@@ -185,7 +197,9 @@ def _resolve_named_custom_runtime(
 
     return {
         "provider": "openrouter",
-        "api_mode": custom_provider.get("api_mode", "chat_completions"),
+        "api_mode": custom_provider.get("api_mode")
+        or _detect_api_mode_for_url(base_url)
+        or "chat_completions",
         "base_url": base_url,
         "api_key": api_key,
         "source": f"custom_provider:{custom_provider.get('name', requested_provider)}",
@@ -263,7 +277,9 @@ def _resolve_openrouter_runtime(
 
     return {
         "provider": "openrouter",
-        "api_mode": _parse_api_mode(model_cfg.get("api_mode")) or "chat_completions",
+        "api_mode": _parse_api_mode(model_cfg.get("api_mode"))
+        or _detect_api_mode_for_url(base_url)
+        or "chat_completions",
         "base_url": base_url,
         "api_key": api_key,
         "source": source,

run_agent.py

@@ -501,6 +501,12 @@ class AIAgent:
         else:
             self.api_mode = "chat_completions"
 
+        # Direct OpenAI sessions use the Responses API path.  GPT-5.x tool
+        # calls with reasoning are rejected on /v1/chat/completions, and
+        # Hermes is a tool-using client by default.
+        if self.api_mode == "chat_completions" and self._is_direct_openai_url():
+            self.api_mode = "codex_responses"
+
         # Pre-warm OpenRouter model metadata cache in a background thread.
         # fetch_model_metadata() is cached for 1 hour; this avoids a blocking
         # HTTP request on the first API response when pricing is estimated.
@@ -1080,6 +1086,11 @@ class AIAgent:
             return
         self._safe_print(*args, **kwargs)
 
+    def _is_direct_openai_url(self, base_url: str = None) -> bool:
+        """Return True when a base URL targets OpenAI's native API."""
+        url = (base_url or self._base_url_lower).lower()
+        return "api.openai.com" in url and "openrouter" not in url
+
     def _max_tokens_param(self, value: int) -> dict:
         """Return the correct max tokens kwarg for the current provider.
         
@@ -1087,11 +1098,7 @@ class AIAgent:
         'max_completion_tokens'. OpenRouter, local models, and older
         OpenAI models use 'max_tokens'.
         """
-        _is_direct_openai = (
+        if self._is_direct_openai_url():
-            "api.openai.com" in self._base_url_lower
-            and "openrouter" not in self._base_url_lower
-        )
-        if _is_direct_openai:
             return {"max_completion_tokens": value}
         return {"max_tokens": value}
 
@@ -3553,13 +3560,15 @@ class AIAgent:
                     fb_provider)
                 return False
 
-            # Determine api_mode from provider
+            # Determine api_mode from provider / base URL
             fb_api_mode = "chat_completions"
             fb_base_url = str(fb_client.base_url)
             if fb_provider == "openai-codex":
                 fb_api_mode = "codex_responses"
             elif fb_provider == "anthropic" or fb_base_url.rstrip("/").lower().endswith("/anthropic"):
                 fb_api_mode = "anthropic_messages"
+            elif self._is_direct_openai_url(fb_base_url):
+                fb_api_mode = "codex_responses"
 
             old_model = self.model
             self.model = fb_model