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

feat(delegation): bump default child_timeout_seconds to 600s (#14809)

Browse source 
The 300s default was too tight for high-reasoning models on non-trivial
delegated tasks — e.g. gpt-5.5 xhigh reviewing 12 files would burn >5min
on reasoning tokens before issuing its first tool call, tripping the
hard wall-clock timeout with 0 api_calls logged.

- tools/delegate_tool.py: DEFAULT_CHILD_TIMEOUT 300 -> 600
- hermes_cli/config.py: surface delegation.child_timeout_seconds in
  DEFAULT_CONFIG so it's discoverable (previously the key was read by
  _get_child_timeout() but absent from the default config schema)

Users can still override via config.yaml delegation.child_timeout_seconds
or DELEGATION_CHILD_TIMEOUT_SECONDS env var (floor 30s, no ceiling).
This commit is contained in:
Teknium 2026-04-23 16:14:55 -07:00 • committed by GitHub
parent e26c4f0e34
commit 50d97edbe1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 6 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
hermes_cli/config.py
View file

@ -739,6 +739,10 @@ DEFAULT_CONFIG = {
"inherit_mcp_toolsets": True, "inherit_mcp_toolsets": True,
"max_iterations": 50, # per-subagent iteration cap (each subagent gets its own budget, "max_iterations": 50, # per-subagent iteration cap (each subagent gets its own budget,
# independent of the parent's max_iterations) # independent of the parent's max_iterations)
"child_timeout_seconds": 600, # wall-clock timeout for each child agent (floor 30s,
# no ceiling). High-reasoning models on large tasks
# (e.g. gpt-5.5 xhigh, opus-4.6) need generous budgets;
# raise if children time out before producing output.
"reasoning_effort": "", # reasoning effort for subagents: "xhigh", "high", "medium", "reasoning_effort": "", # reasoning effort for subagents: "xhigh", "high", "medium",
# "low", "minimal", "none" (empty = inherit parent's level) # "low", "minimal", "none" (empty = inherit parent's level)
"max_concurrent_children": 3, # max parallel children per batch; floor of 1 enforced, no ceiling "max_concurrent_children": 3, # max parallel children per batch; floor of 1 enforced, no ceiling

4
tools/delegate_tool.py
View file

@ -298,7 +298,7 @@ def _get_child_timeout() -> float:
"""Read delegation.child_timeout_seconds from config. """Read delegation.child_timeout_seconds from config.
Returns the number of seconds a single child agent is allowed to run Returns the number of seconds a single child agent is allowed to run
before being considered stuck. Default: 300 s (5 minutes). before being considered stuck. Default: 600 s (10 minutes).
""" """
cfg = _load_config() cfg = _load_config()
val = cfg.get("child_timeout_seconds") val = cfg.get("child_timeout_seconds")
@ -409,7 +409,7 @@ def _preserve_parent_mcp_toolsets(
DEFAULT_MAX_ITERATIONS = 50 DEFAULT_MAX_ITERATIONS = 50
DEFAULT_CHILD_TIMEOUT = 300 # seconds before a child agent is considered stuck DEFAULT_CHILD_TIMEOUT = 600 # seconds before a child agent is considered stuck
_HEARTBEAT_INTERVAL = 30 # seconds between parent activity heartbeats during delegation _HEARTBEAT_INTERVAL = 30 # seconds between parent activity heartbeats during delegation
_HEARTBEAT_STALE_CYCLES = ( _HEARTBEAT_STALE_CYCLES = (
5 # mark child stale after this many heartbeats with no iteration progress 5 # mark child stale after this many heartbeats with no iteration progress