mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-05 02:31:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(delegation): pass target_model to resolve_runtime_provider in _resolve_delegation_credentials

Browse source 
When delegation.model differs from model.default and the provider is
opencode-go or opencode-zen, the wrong api_mode is computed because
resolve_runtime_provider falls back to model_cfg.get('default') — the
main model — instead of the configured delegation model.

For example, with model.default=minimax-m2.7 (anthropic_messages) and
delegation.model=glm-5.1 (chat_completions), subagents get
anthropic_messages, which strips /v1 from the base URL and causes a 404.

resolve_runtime_provider already accepts target_model for exactly this
purpose; _resolve_delegation_credentials just wasn't passing it.

Fixes #15319
Related: #13678
This commit is contained in:
Emilien Domenge 2026-04-24 22:05:40 +02:00 • committed by Teknium
parent e2211b2683
commit 83bbe9b458
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tools/delegate_tool.py
View file

@ -2299,7 +2299,7 @@ def _resolve_delegation_credentials(cfg: dict, parent_agent) -> dict:
try:
from hermes_cli.runtime_provider import resolve_runtime_provider
runtime = resolve_runtime_provider(requested=configured_provider)
runtime = resolve_runtime_provider(requested=configured_provider, target_model=configured_model)
except Exception as exc:
raise ValueError(
f"Cannot resolve delegation provider '{configured_provider}': {exc}. "