Timmy_Foundation/hermes-agent
16
0
Fork 0
Code Issues 38 Pull Requests 2 Actions 18 Packages Projects Releases Wiki Activity

Fix context overrun crash with local LLM backends (fixes #348)

Browse Source 
Local backends (LM Studio, Ollama, llama.cpp) return HTTP 400
with messages like "Context size has been exceeded" when the
context window is full. The error phrase list did not include
"context size" or "context window", so these errors fell through
to the generic 4xx abort handler instead of triggering compression.

Changes:
- Move context-length check above generic 4xx handler so it runs
  first (same pattern as the existing 413 check)
- Add "context size" and "context window" to the phrase list
- Guard 4xx handler with `not is_context_length_error` to prevent
  context-related 400s from being treated as non-retryable
This commit is contained in:
Vicaversa
2026-03-05 01:12:34 +03:00
parent ffec21236d
commit e9ab711b66
1 changed files with 40 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
run_agent.py
View File

@@ -3286,13 +3286,49 @@ class AIAgent:
"partial": True
}
# Check for context-length errors BEFORE generic 4xx handler.
# 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', '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
else:
# Can't compress further
print(f"{self.log_prefix}❌ Context length exceeded and cannot compress further.")
print(f"{self.log_prefix} 💡 The conversation has accumulated too much content.")
logging.error(f"{self.log_prefix}Context length exceeded: {approx_tokens:,} tokens. Cannot compress further.")
self._persist_session(messages, conversation_history)
return {
"messages": messages,
"completed": False,
"api_calls": api_call_count,
"error": f"Context length exceeded ({approx_tokens:,} tokens). Cannot compress further.",
"partial": True
}
# 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 is excluded — it's 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',
is_client_error = (is_client_status_error and not is_context_length_error) or any(phrase in error_msg for phrase in [
'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',
@@ -3315,39 +3351,7 @@ class AIAgent:
"failed": True,
"error": str(api_error),
}
# Check for non-retryable errors (context length exceeded)
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',
'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
else:
# Can't compress further
print(f"{self.log_prefix}❌ Context length exceeded and cannot compress further.")
print(f"{self.log_prefix} 💡 The conversation has accumulated too much content.")
logging.error(f"{self.log_prefix}Context length exceeded: {approx_tokens:,} tokens. Cannot compress further.")
self._persist_session(messages, conversation_history)
return {
"messages": messages,
"completed": False,
"api_calls": api_call_count,
"error": f"Context length exceeded ({approx_tokens:,} tokens). Cannot compress further.",
"partial": True
}
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}")