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(run_agent): refresh activity during streaming responses

Browse source 
Previously, long-running streamed responses could be incorrectly treated
as idle by the gateway/cron inactivity timeout even while tokens were
actively arriving. The _touch_activity() call (which feeds
get_activity_summary() polled by the external timeout) was either called
only on the first chunk (chat completions) or not at all (Anthropic,
Codex, Codex fallback).

Add _touch_activity() on every chunk/event in all four streaming paths
so the inactivity monitor knows data is still flowing.

Fixes #8760
This commit is contained in:
yongtenglei 2026-04-13 05:19:16 -07:00 • committed by Teknium
parent ba50fa3035
commit 2773b18b56
2 changed files with 184 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
run_agent.py
View file

@ -4318,6 +4318,7 @@ class AIAgent:
try:
with active_client.responses.stream(**api_kwargs) as stream:
for event in stream:
self._touch_activity("receiving stream response")
if self._interrupt_requested:
break
event_type = getattr(event, "type", "")
@ -4442,6 +4443,7 @@ class AIAgent:
collected_text_deltas: list = []
try:
for event in stream_or_response:
self._touch_activity("receiving stream response")
event_type = getattr(event, "type", None)
if not event_type and isinstance(event, dict):
event_type = event.get("type")
@ -5074,12 +5076,9 @@ class AIAgent:
role = "assistant"
reasoning_parts: list = []
usage_obj = None
_first_chunk_seen = False
for chunk in stream:
last_chunk_time["t"] = time.time()
if not _first_chunk_seen:
_first_chunk_seen = True
self._touch_activity("receiving stream response")
self._touch_activity("receiving stream response")
if self._interrupt_requested:
break
@ -5255,6 +5254,7 @@ class AIAgent:
# actively arriving (the chat_completions path
# already does this at the top of its chunk loop).
last_chunk_time["t"] = time.time()
self._touch_activity("receiving stream response")
if self._interrupt_requested:
break