mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: enhance payload and context compression handling

Browse source 
Added logic to manage multiple compression attempts for large payloads and context length errors. Introduced limits on compression attempts to prevent infinite retries, with appropriate logging and error handling. This ensures better resilience and user feedback when facing compression issues during API calls.
This commit is contained in:
teknium1 2026-03-07 09:19:07 -08:00
parent 4d34427cc7
commit 5a711f32b1
1 changed files with 40 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

41
run_agent.py
View file

@ -3142,10 +3142,13 @@ class AIAgent:
api_start_time = time.time()
retry_count = 0
max_retries = 6 # Increased to allow longer backoff periods
compression_attempts = 0
max_compression_attempts = 3
codex_auth_retry_attempted = False
nous_auth_retry_attempted = False
finish_reason = "stop"
response = None # Guard against UnboundLocalError if all retries fail
while retry_count < max_retries:
try:
@ -3441,7 +3444,19 @@ class AIAgent:
)
if is_payload_too_large:
print(f"{self.log_prefix}⚠️ Request payload too large (413) - attempting compression...")
compression_attempts += 1
if compression_attempts > max_compression_attempts:
print(f"{self.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached for payload-too-large error.")
logging.error(f"{self.log_prefix}413 compression failed after {max_compression_attempts} attempts.")
self._persist_session(messages, conversation_history)
return {
"messages": messages,
"completed": False,
"api_calls": api_call_count,
"error": f"Request payload too large: max compression attempts ({max_compression_attempts}) reached.",
"partial": True
}
print(f"{self.log_prefix}⚠️ Request payload too large (413) — compression attempt {compression_attempts}/{max_compression_attempts}...")
original_len = len(messages)
messages, active_system_prompt = self._compress_context(
@ -3450,6 +3465,7 @@ class AIAgent:
if len(messages) < original_len:
print(f"{self.log_prefix} 🗜️ Compressed {original_len} → {len(messages)} messages, retrying...")
time.sleep(2) # Brief pause between compression retries
continue # Retry with compressed messages
else:
print(f"{self.log_prefix}❌ Payload too large and cannot compress further.")
@ -3495,6 +3511,20 @@ class AIAgent:
else:
print(f"{self.log_prefix}⚠️ Context length exceeded at minimum tier — attempting compression...")
compression_attempts += 1
if compression_attempts > max_compression_attempts:
print(f"{self.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached.")
logging.error(f"{self.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
self._persist_session(messages, conversation_history)
return {
"messages": messages,
"completed": False,
"api_calls": api_call_count,
"error": f"Context length exceeded: max compression attempts ({max_compression_attempts}) reached.",
"partial": True
}
print(f"{self.log_prefix} 🗜️ Context compression attempt {compression_attempts}/{max_compression_attempts}...")
original_len = len(messages)
messages, active_system_prompt = self._compress_context(
messages, system_message, approx_tokens=approx_tokens
@ -3503,6 +3533,7 @@ class AIAgent:
if len(messages) < original_len or new_ctx and new_ctx < old_ctx:
if len(messages) < original_len:
print(f"{self.log_prefix} 🗜️ Compressed {original_len} → {len(messages)} messages, retrying...")
time.sleep(2) # Brief pause between compression retries
continue # Retry with compressed messages or new tier
else:
# Can't compress further and already at minimum tier
@ -3581,6 +3612,14 @@ class AIAgent:
if interrupted:
break
# Guard: if all retries exhausted without a successful response
# (e.g. repeated context-length errors that exhausted retry_count),
# the `response` variable is still None. Break out cleanly.
if response is None:
print(f"{self.log_prefix}❌ All API retries exhausted with no successful response.")
self._persist_session(messages, conversation_history)
break
try:
if self.api_mode == "codex_responses":
assistant_message, finish_reason = self._normalize_codex_response(response)