HOMELAB-236: fix(litellm): update stale Ollama model names #25

Merged
claude-agent merged 1 commit from plane/HOMELAB-236-litellm-model-fix into live 2026-03-23 01:53:11 +00:00
Owner

Fix stale model names blocking Ollama inference and Langfuse callback.

  • llama3.1:8b → llama3.2:1b-instruct-q4_0
  • qwen2.5-coder:14b → qwen2.5-coder:7b
Fix stale model names blocking Ollama inference and Langfuse callback. - llama3.1:8b → llama3.2:1b-instruct-q4_0 - qwen2.5-coder:14b → qwen2.5-coder:7b
HOMELAB-236: fix(litellm): update stale Ollama model names
Some checks failed
0/0 projects applied successfully.
CI Review / pr-title (pull_request) Successful in 0s
CI Review / helm-validate (pull_request) Failing after 3s
CI Review / ai-review (pull_request) Failing after 1s
Lint & Validate / terraform-validate (pull_request) Failing after 1s
Lint & Validate / yaml-lint (pull_request) Failing after 1s
Lint & Validate / shellcheck (pull_request) Failing after 1s
b1e475ea69
Model config referenced llama3.1:8b and qwen2.5-coder:14b but Ollama
has llama3.2:1b-instruct-q4_0 and qwen2.5-coder:7b. This blocked all
Ollama inference through LiteLLM, preventing the Langfuse callback from
capturing any generation data.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sign in to join this conversation.
No reviewers
No labels
No milestone
No project
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.

Dependencies

No dependencies set.

Reference
aaron/infra-core!25
No description provided.