molecule-ai/hermes-agent
36
0
Fork 0
Code Issues 4 Pull Requests 5 Actions 104 Packages Projects Releases Wiki Activity

fix: improve gateway error handling for 429 usage limits and 500 context overflow (#1839)

Browse Source 
fix: improve gateway error handling for 429 usage limits and 500 context overflow
This commit is contained in:
Teknium 2026-03-17 16:32:20 -07:00 committed by GitHub
commit 37dceb043e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 24 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
gateway/run.py
View File

@ -2122,23 +2122,41 @@ class GatewayRunner:
error_detail = str(e)[:300] if str(e) else "no details available"
status_hint = ""
status_code = getattr(e, "status_code", None)
_hist_len = len(history) if 'history' in locals() else 0
if status_code == 401:
status_hint = " Check your API key or run `claude /login` to refresh OAuth credentials."
elif status_code == 429:
status_hint = " You are being rate-limited. Please wait a moment and try again."
# Check if this is a plan usage limit (resets on a schedule) vs a transient rate limit
_err_body = getattr(e, "response", None)
_err_json = {}
try:
if _err_body is not None:
_err_json = _err_body.json().get("error", {})
except Exception:
pass
if _err_json.get("type") == "usage_limit_reached":
_resets_in = _err_json.get("resets_in_seconds")
if _resets_in and _resets_in > 0:
import math
_hours = math.ceil(_resets_in / 3600)
status_hint = f" Your plan's usage limit has been reached. It resets in ~{_hours}h."
else:
status_hint = " Your plan's usage limit has been reached. Please wait until it resets."
else:
status_hint = " You are being rate-limited. Please wait a moment and try again."
elif status_code == 529:
status_hint = " The API is temporarily overloaded. Please try again shortly."
elif status_code == 400:
# 400 with a large session is almost always a context overflow.
# Give specific guidance instead of a generic error. (#1630)
_hist_len = len(history) if 'history' in locals() else 0
elif status_code in (400, 500):
# 400 with a large session is context overflow.
# 500 with a large session often means the payload is too large
# for the API to process — treat it the same way.
if _hist_len > 50:
return (
"⚠️ Session too large for the model's context window.\n"
"Use /compact to compress the conversation, or "
"/reset to start fresh."
)
else:
elif status_code == 400:
status_hint = " The request was rejected by the API."
return (
f"Sorry, I encountered an error ({error_type}).\n"