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: budget-exhausted conversations now get a summary instead of empty response

Browse source 
The post-loop grace call mechanism was broken: it injected a user
message and set _budget_grace_call=True, but could never re-enter the
while loop (already exited).  Worse, the flag blocked the fallback
_handle_max_iterations from running, so final_response stayed None.

Users saw empty/no response when the agent hit max iterations.

Fix: remove the dead grace block and let _handle_max_iterations handle
it directly — it already injects a summary request and makes one extra
toolless API call.
This commit is contained in:
Teknium 2026-04-13 03:34:59 -07:00 • committed by Teknium
parent 3804556cd9
commit 934318ba3a
1 changed files with 5 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

24
run_agent.py
View file

@ -10189,17 +10189,11 @@ class AIAgent:
if final_response is None and (
api_call_count >= self.max_iterations
or self.iteration_budget.remaining <= 0
) and not self._budget_exhausted_injected:
# Budget exhausted but we haven't tried asking the model to
# summarise yet. Inject a user message and give it one grace
# API call to produce a text response.
self._budget_exhausted_injected = True
self._budget_grace_call = True
_grace_msg = (
"Your tool budget ran out. Please give me the information "
"or actions you've completed so far."
)
messages.append({"role": "user", "content": _grace_msg})
):
# Budget exhausted — ask the model for a summary via one extra
# API call with tools stripped. _handle_max_iterations injects a
# user message and makes a single toolless request.
_turn_exit_reason = f"max_iterations_reached({api_call_count}/{self.max_iterations})"
self._emit_status(
f"⚠️ Iteration budget exhausted ({api_call_count}/{self.max_iterations}) "
"— asking model to summarise"
@ -10209,14 +10203,6 @@ class AIAgent:
f"\n⚠️ Iteration budget exhausted ({api_call_count}/{self.max_iterations}) "
"— requesting summary..."
)
if final_response is None and (
api_call_count >= self.max_iterations
or self.iteration_budget.remaining <= 0
) and not self._budget_grace_call:
_turn_exit_reason = f"max_iterations_reached({api_call_count}/{self.max_iterations})"
if self.iteration_budget.remaining <= 0 and not self.quiet_mode:
print(f"\n⚠️ Iteration budget exhausted ({self.iteration_budget.used}/{self.iteration_budget.max_total} iterations used)")
final_response = self._handle_max_iterations(messages, api_call_count)
# Determine if conversation completed successfully