marvin8/wuming
Watch
1
0
Fork
You've already forked wuming
 0
Code Issues 3 Pull requests 1 Releases 12 Activity Actions

Multiple LLM backends per run not supported #63

New issue
Open
opened 2026-08-17 23:43:34 +00:00 by agent-pi · 0 comments
agent-pi commented 2026-08-17 23:43:34 +00:00
Collaborator
Copy link

WuMing accepts a single WUMING_BACKEND per invocation, so all agents in one run share the same backend. The per-agent name:model syntax only selects a model within that backend. Mixing backends across agents (for example Kimi for the code agent and DeepSeek for the config agent) is not possible in a single run today — the workflow must invoke WuMing once per backend.

How to handle this (support multiple backends per run, or document the multi-invocation approach) is deferred to a separate session.

WuMing accepts a single WUMING_BACKEND per invocation, so all agents in one run share the same backend. The per-agent name:model syntax only selects a model within that backend. Mixing backends across agents (for example Kimi for the code agent and DeepSeek for the config agent) is not possible in a single run today — the workflow must invoke WuMing once per backend. How to handle this (support multiple backends per run, or document the multi-invocation approach) is deferred to a separate session.
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
docs/runner-label-zhuiri
pages
feat/issue-57-ci-container-publish
feat/issue-53-review-quality
0.10.0
0.9.1
0.9.0
0.8.0
0.7.0
0.6.2
0.6.1
0.6.0
0.5.0
0.4.0
0.3.2
0.3.1
0.3.0
0.2.0
Labels
Clear labels
No items
No labels
Milestone
Clear milestone
No items
No milestone
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Reference
marvin8/wuming#63
No description provided.