Handle blank Codex transport errors

nanobot/providers/openai_codex_provider.py

@@ -84,9 +84,21 @@ class OpenAICodexProvider(LLMProvider):
                 )
             return LLMResponse(content=content, tool_calls=tool_calls, finish_reason=finish_reason)
         except Exception as e:
-            msg = f"Error calling Codex: {e}"
-            retry_after = getattr(e, "retry_after", None) or self._extract_retry_after(msg)
-            return LLMResponse(content=msg, finish_reason="error", retry_after=retry_after)
+            response = _codex_error_response(e)
+            exc_type = "CodexHTTPError" if isinstance(e, _CodexHTTPError) else type(e).__name__
+            logger.warning(
+                "Codex API request failed: type={} kind={} retryable={} status={} "
+                "error_type={} error_code={} retry_after={} summary={}",
+                exc_type,
+                response.error_kind,
+                response.error_should_retry,
+                response.error_status_code,
+                response.error_type,
+                response.error_code,
+                response.retry_after,
+                _codex_log_summary(exc_type, response),
+            )
+            return response
 
     async def chat(
         self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
@@ -139,9 +151,22 @@ def _build_headers(account_id: str, token: str) -> dict[str, str]:
 
 
 class _CodexHTTPError(RuntimeError):
-    def __init__(self, message: str, retry_after: float | None = None):
+    def __init__(
+        self,
+        message: str,
+        *,
+        status_code: int | None = None,
+        retry_after: float | None = None,
+        error_type: str | None = None,
+        error_code: str | None = None,
+        should_retry: bool | None = None,
+    ):
         super().__init__(message)
+        self.status_code = status_code
         self.retry_after = retry_after
+        self.error_type = error_type
+        self.error_code = error_code
+        self.should_retry = should_retry
 
 
 async def _request_codex(
@@ -156,10 +181,16 @@ async def _request_codex(
         async with client.stream("POST", url, headers=headers, json=body) as response:
             if response.status_code != 200:
                 text = await response.aread()
+                raw = text.decode("utf-8", "ignore")
                 retry_after = LLMProvider._extract_retry_after_from_headers(response.headers)
+                error_type, error_code = LLMProvider._extract_error_type_code(raw)
                 raise _CodexHTTPError(
-                    _friendly_error(response.status_code, text.decode("utf-8", "ignore")),
+                    _friendly_error(response.status_code, raw),
+                    status_code=response.status_code,
                     retry_after=retry_after,
+                    error_type=error_type,
+                    error_code=error_code,
+                    should_retry=_should_retry_status(response.status_code, error_type, error_code, raw),
                 )
             return await consume_sse(response, on_content_delta, on_tool_call_delta)
 
@@ -170,6 +201,94 @@ def _prompt_cache_key(messages: list[dict[str, Any]]) -> str:
 
 
 def _friendly_error(status_code: int, raw: str) -> str:
+    _ = raw
     if status_code == 429:
         return "ChatGPT usage quota exceeded or rate limit triggered. Please try again later."
-    return f"HTTP {status_code}: {raw}"
+    return f"HTTP {status_code}: Codex API request failed"
+
+
+def _codex_error_response(exc: Exception) -> LLMResponse:
+    """Convert Codex transport/API failures into actionable, retryable metadata."""
+    exc_type = "CodexHTTPError" if isinstance(exc, _CodexHTTPError) else type(exc).__name__
+    detail = str(exc).strip()
+
+    status_code = getattr(exc, "status_code", None)
+    error_kind: str | None = None
+    default_detail: str | None = None
+    should_retry: bool | None = getattr(exc, "should_retry", None)
+
+    if isinstance(exc, (httpx.TimeoutException, asyncio.TimeoutError)):
+        error_kind = "timeout"
+        default_detail = "timed out waiting for response"
+        should_retry = True if should_retry is None else should_retry
+    elif isinstance(exc, httpx.RemoteProtocolError):
+        error_kind = "connection"
+        default_detail = "network protocol error while reading response"
+        should_retry = True if should_retry is None else should_retry
+    elif isinstance(exc, (httpx.NetworkError, httpx.TransportError)):
+        error_kind = "connection"
+        default_detail = "network connection failed"
+        should_retry = True if should_retry is None else should_retry
+    elif isinstance(exc, _CodexHTTPError):
+        error_kind = "http"
+        default_detail = "HTTP request failed"
+
+    if status_code is not None and should_retry is None:
+        retry_content = None if int(status_code) == 429 and isinstance(exc, _CodexHTTPError) else detail
+        should_retry = _should_retry_status(
+            int(status_code),
+            getattr(exc, "error_type", None),
+            getattr(exc, "error_code", None),
+            retry_content,
+        )
+
+    detail = detail or default_detail or "unexpected error"
+    message = f"Error calling Codex ({exc_type}): {detail}"
+    retry_after = getattr(exc, "retry_after", None) or LLMProvider._extract_retry_after(message)
+    return LLMResponse(
+        content=message,
+        finish_reason="error",
+        retry_after=retry_after,
+        error_status_code=int(status_code) if status_code is not None else None,
+        error_kind=error_kind,
+        error_type=getattr(exc, "error_type", None),
+        error_code=getattr(exc, "error_code", None),
+        error_retry_after_s=retry_after,
+        error_should_retry=should_retry,
+    )
+
+
+def _codex_log_summary(exc_type: str, response: LLMResponse) -> str:
+    """Return a bounded diagnostic summary without request body or raw upstream payload."""
+    if response.error_status_code is not None:
+        parts = [f"HTTP {response.error_status_code}"]
+        if response.error_type:
+            parts.append(f"type={response.error_type}")
+        if response.error_code:
+            parts.append(f"code={response.error_code}")
+        return " ".join(parts)
+
+    kind = (response.error_kind or "").strip()
+    if kind:
+        return f"{exc_type} {kind}"
+
+    return exc_type
+
+
+def _should_retry_status(
+    status_code: int,
+    error_type: str | None,
+    error_code: str | None,
+    content: str | None,
+) -> bool:
+    if status_code == 429:
+        return LLMProvider._is_retryable_429_response(
+            LLMResponse(
+                content=content or "",
+                finish_reason="error",
+                error_status_code=status_code,
+                error_type=error_type,
+                error_code=error_code,
+            )
+        )
+    return status_code in LLMProvider._RETRYABLE_STATUS_CODES or status_code >= 500