mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-06-07 08:02:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

fix(agent): add qwen and deepseek to TOOL_USE_ENFORCEMENT_MODELS

Browse source 
Qwen3.x and DeepSeek-V3.x default to chatty/hallucinatory tool use without
enforcement steering — agents narrate "calling tool X" without actually
emitting a tool call, or run partial loops. Both model families fit the
same failure pattern TOOL_USE_ENFORCEMENT_GUIDANCE was already injected
for (gpt, codex, gemini, gemma, grok, glm).

Co-authored-by: briandevans <252620095+briandevans@users.noreply.github.com>

Squashed salvage of:
- 403e567ce fix(agent): add qwen and deepseek to TOOL_USE_ENFORCEMENT_MODELS
- 9433eabe7 test(agent): use realistic qwen-plus identifier in enforcement test

Fixes #28079.
This commit is contained in:
briandevans 2026-05-18 20:06:43 -07:00 • committed by Teknium
parent 4229facc01
commit 756900723a
3 changed files with 21 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
agent/prompt_builder.py
View file

@ -268,7 +268,7 @@ TOOL_USE_ENFORCEMENT_GUIDANCE = (
# Model name substrings that trigger tool-use enforcement guidance.
# Add new patterns here when a model family needs explicit steering.
TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma", "grok", "glm")
TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma", "grok", "glm", "qwen", "deepseek")
# OpenAI GPT/Codex-specific execution guidance. Addresses known failure modes
# where GPT models abandon work on partial results, skip prerequisite lookups,