mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-31 19:16:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix(timeouts): add claude-fable to reasoning stale-timeout floor table

Browse source 
claude-fable-5 is a Mythos-class reasoning model (1M context, 128K output,
adaptive thinking per anthropic_adapter.py) but was missing from the
_REASONING_STALE_TIMEOUT_FLOORS table. Without a floor entry it got the
default 180s stale timeout (300s with context scaling), which is too short
for fable-5's thinking phase on large contexts.

Each stale kill bumped the cross-turn circuit breaker streak; after 5
consecutive kills _check_stale_giveup() fired immediately (elapsed: 0.00s),
aborting all calls with "Provider has been unresponsive for 5 consecutive
stale attempts." Users with 191K-token contexts hit this reliably.

Add ("claude-fable", 600) — deep-reasoning tier alongside o1/deepseek-r1/
nemotron-3-ultra. The claude-fable slug matches claude-fable-5 and future
variants via the existing right-anchor regex.
This commit is contained in:
kshitijk4poor 2026-07-27 22:45:24 +05:00
parent c2e45b555f
commit 29abaeb98f
2 changed files with 14 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
agent/reasoning_timeouts.py
View file

@ -106,6 +106,14 @@ _REASONING_STALE_TIMEOUT_FLOORS: tuple[tuple[str, int], ...] = (
("claude-sonnet-5", 180),
("claude-sonnet-4.5", 180),
("claude-sonnet-4.6", 180),
# Anthropic Mythos-class named reasoning models (claude-fable-5, …).
# 1M context + 128K output — heavier thinking phase than the
# numbered Claude line, so the floor is in the deep-reasoning tier
# alongside o1 / deepseek-r1 / nemotron-3-ultra. Without this
# entry the stale-stream detector kills fable-5's thinking phase
# at the default 180s (300s with context scaling), tripping the
# cross-turn circuit breaker after 5 consecutive stale kills.
("claude-fable", 600),
# xAI Grok reasoning variants. Explicit reasoning-only keys
# plus one for the ``non-reasoning`` variant so users picking
# the fast variant don't get the 300s floor. Bare ``grok-3``,
@ -207,6 +215,8 @@ def get_reasoning_stale_timeout_floor(model: object) -> Optional[float]:
300.0
>>> get_reasoning_stale_timeout_floor("anthropic/claude-opus-4-6")
240.0
>>> get_reasoning_stale_timeout_floor("anthropic/claude-fable-5")
600.0
>>> get_reasoning_stale_timeout_floor("gpt-4o") is None
True
>>> get_reasoning_stale_timeout_floor("olmo-1") is None

4
tests/agent/test_reasoning_stale_timeout_floor.py
View file

@ -74,6 +74,10 @@ import pytest
("anthropic/claude-opus-4-20250514", 240.0),
("anthropic/claude-sonnet-4.5", 180.0),
("anthropic/claude-sonnet-4.6", 180.0),
# Anthropic Mythos-class named reasoning models — deep-reasoning tier.
("anthropic/claude-fable-5", 600.0),
("claude-fable-5", 600.0),
("claude-fable", 600.0),
# xAI Grok reasoning variants — explicit, not bare `grok`.
("x-ai/grok-4-fast-reasoning", 300.0),
("x-ai/grok-4.20-reasoning", 300.0),