ollma

It run for few minute then it failed, when switched to other model it loop forever.

to continue the project what information needed to pass to you? a prompt or just project folder?

OpenAI-compatible chat request failed
endpoint: http://localhost:11434/v1/chat/completions
model: qwen3-coder:30b
auth: local endpoint (no auth)
status: 404 Not Found
response: {"error":{"message":"model 'qwen3-coder:30b' not found","type":"not_found_error","param":null,"code":null}}

Ollama hint: make sure ollama serve is running, the model is installed with ollama pull <model>, and run jcode with an installed model, for example jcode --provider ollama --model llama3.2 run 'hello'.

↪ Fallback available: press Ctrl+Y to switch to llama3.1:latest via api key (Ollama) and resend.

What failed: Ollama
Error: OpenAI-compatible chat request failed

↪ Switching to llama3.1:latest via api key (Ollama) and resending (was Ollama).

✓ Switched to model: llama3.1:latest

Start by reproducing the reported command with the Ollama provider and the qwen3-coder:30b model, after checking that ollama serve is running and the model is installed. Trace the failed OpenAI-compatible request and the fallback to llama3.1:latest; done should include a defined, non-looping response when the requested model is unavailable.