hermes-agent

mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-28 15:01:34 +08:00

Files

LVT382009 f7af90e2da fix: wire _ephemeral_max_output_tokens into chat_completions and add NVIDIA NIM default

Based on #12152 by @LVT382009.

Two fixes to run_agent.py:

1. _ephemeral_max_output_tokens consumption in chat_completions path:
   The error-recovery ephemeral override was only consumed in the
   anthropic_messages branch of _build_api_kwargs.  All chat_completions
   providers (OpenRouter, NVIDIA NIM, Qwen, Alibaba, custom, etc.)
   silently ignored it.  Now consumed at highest priority, matching the
   anthropic pattern.

2. NVIDIA NIM max_tokens default (16384):
   NVIDIA NIM falls back to a very low internal default when max_tokens
   is omitted, causing models like GLM-4.7 to truncate immediately
   (thinking tokens exhaust the budget before the response starts).

3. Progressive length-continuation boost:
   When finish_reason='length' triggers a continuation retry, the output
   budget now grows progressively (2x base on retry 1, 3x on retry 2,
   capped at 32768) via _ephemeral_max_output_tokens.  Previously the
   retry loop just re-sent the same token limit on all 3 attempts.

2026-04-18 12:51:30 -07:00

lib

feat: lazy bootstrap node

2026-04-16 10:47:37 -05:00

whatsapp-bridge

security: supply chain hardening — CI pinning, dep pinning, and code fixes (#9801 )

2026-04-14 14:23:37 -07:00

build_skills_index.py

feat(skills): centralized skills index — eliminate GitHub API calls for search/install

2026-04-12 16:39:04 -07:00

contributor_audit.py

feat(ci): add contributor attribution check on PRs (#9376 )