diff --git a/run_agent.py b/run_agent.py
index 62d641b7b28..8df43d75002 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -3333,23 +3333,24 @@ class AIAgent:
                             }
 
                     # Check for context-length errors BEFORE generic 4xx handler.
-                    # OpenRouter returns 400 (not 413) for "maximum context length"
-                    # errors — if we let the generic 4xx handler catch those first,
-                    # it aborts immediately instead of attempting compression+retry.
+                    # Local backends (LM Studio, Ollama, llama.cpp) often return
+                    # HTTP 400 with messages like "Context size has been exceeded"
+                    # which must trigger compression, not an immediate abort.
                     is_context_length_error = any(phrase in error_msg for phrase in [
-                        'context length', 'maximum context', 'token limit',
-                        'too many tokens', 'reduce the length', 'exceeds the limit',
+                        'context length', 'context size', 'maximum context',
+                        'token limit', 'too many tokens', 'reduce the length',
+                        'exceeds the limit', 'context window',
                         'request entity too large',  # OpenRouter/Nous 413 safety net
                     ])
                     
                     if is_context_length_error:
                         print(f"{self.log_prefix}⚠️  Context length exceeded - attempting compression...")
-                        
+
                         original_len = len(messages)
                         messages, active_system_prompt = self._compress_context(
                             messages, system_message, approx_tokens=approx_tokens
                         )
-                        
+
                         if len(messages) < original_len:
                             print(f"{self.log_prefix}   🗜️  Compressed {original_len} → {len(messages)} messages, retrying...")
                             continue  # Retry with compressed messages
@@ -3370,11 +3371,10 @@ class AIAgent:
                     # Check for non-retryable client errors (4xx HTTP status codes).
                     # These indicate a problem with the request itself (bad model ID,
                     # invalid API key, forbidden, etc.) and will never succeed on retry.
-                    # Note: 413 and context-length errors are excluded — handled above
-                    # via compression.
+                    # Note: 413 and context-length errors are excluded — handled above.
                     is_client_status_error = isinstance(status_code, int) and 400 <= status_code < 500 and status_code != 413
                     is_client_error = (is_client_status_error or any(phrase in error_msg for phrase in [
-                        'error code: 400', 'error code: 401', 'error code: 403',
+                        'error code: 401', 'error code: 403',
                         'error code: 404', 'error code: 422',
                         'is not a valid model', 'invalid model', 'model not found',
                         'invalid api key', 'invalid_api_key', 'authentication',
@@ -3397,7 +3397,7 @@ class AIAgent:
                             "failed": True,
                             "error": str(api_error),
                         }
-                    
+
                     if retry_count >= max_retries:
                         print(f"{self.log_prefix}❌ Max retries ({max_retries}) exceeded. Giving up.")
                         logging.error(f"{self.log_prefix}API call failed after {max_retries} retries. Last error: {api_error}")