APEX/BrowserUse_and_ComputerUse_skills
5
0
Fork 0
Code Issues 4 Pull requests 1 Projects 1 Releases Packages Wiki Activity Actions

Merge PR #420: fix: respect OPENAI_BASE_URL when resolving API key priority

Browse source 
Authored by manuelschipper. Adds GLM-4.7 and GLM-5 context lengths (202752)
to model_metadata.py. The key priority fix (prefer OPENAI_API_KEY for
non-OpenRouter endpoints) was already applied in PR #295; merged the Z.ai
mention into the comment.
This commit is contained in:
teknium1 2026-03-06 18:43:13 -08:00
commit 3c6c11b7c9
2 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
agent/model_metadata.py
View file

@ -49,6 +49,8 @@ DEFAULT_CONTEXT_LENGTHS = {
"meta-llama/llama-3.3-70b-instruct": 131072, "meta-llama/llama-3.3-70b-instruct": 131072,
"deepseek/deepseek-chat-v3": 65536, "deepseek/deepseek-chat-v3": 65536,
"qwen/qwen-2.5-72b-instruct": 32768, "qwen/qwen-2.5-72b-instruct": 32768,
"glm-4.7": 202752,
"glm-5": 202752,
} }

5
hermes_cli/runtime_provider.py
View file

@ -74,8 +74,9 @@ def _resolve_openrouter_runtime(
# Choose API key based on whether the resolved base_url targets OpenRouter. # Choose API key based on whether the resolved base_url targets OpenRouter.
# When hitting OpenRouter, prefer OPENROUTER_API_KEY (issue #289). # When hitting OpenRouter, prefer OPENROUTER_API_KEY (issue #289).
# When hitting a custom endpoint, prefer OPENAI_API_KEY so the OpenRouter # When hitting a custom endpoint (e.g. Z.ai, local LLM), prefer
# key doesn't leak to an unrelated provider (issue #560). # OPENAI_API_KEY so the OpenRouter key doesn't leak to an unrelated
# provider (issues #420, #560).
_is_openrouter_url = "openrouter.ai" in base_url _is_openrouter_url = "openrouter.ai" in base_url
if _is_openrouter_url: if _is_openrouter_url:
api_key = ( api_key = (