Trying to use instinct I always get error: The operation was aborted

[stranger-games]

Hi,

When I set auto complete to most other models it works but only when I set it to instinct or continuedev-instinct as in the coonfig.yaml I always get the following error. Olama is setup in docker image but autocomplete works with other models like qwen2.5-coder-7b.

[@continuedev] error: The operation was aborted. {"context":"llm_fetch","url":"http://localhost:11434/api/chat","method":"POST","model":"nate/instinct","provider":"ollama"}
[@continuedev] error: The operation was aborted. {"context":"llm_stream_chat","model":"nate/instinct","provider":"ollama","useOpenAIAdapter":false,"streamEnabled":false,"templateMessages":false}

here's my config.yaml file

name: Local Agent
version: 1.0.0
schema: v1
models:
- name: qwen3:32b
  provider: ollama
  model: qwen3:32b
  roles:
    - apply
    - autocomplete
    - chat
    - edit
- name: Qwen3-Coder-30B-A3B_UD-Q4_K_XL
  provider: ollama
  model: hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:UD-Q4_K_XL
  roles:
    - apply
    - autocomplete
    - chat
    - edit
- name: qwen2.5-coder-7b
  provider: ollama
  model: qwen2.5-coder:7b
  roles:
    - autocomplete
- name: continuedev-instinct
  provider: ollama
  model: nate/instinct:latest
  roles:
    - autocomplete
  defaultCompletionOptions:
    temperature: 0
    stop:
      - <|im_end|>
- uses: continuedev/instinct

[stranger-games]

I checked the ollama docker log and noticed the error was 500. I updated the docker image for ollama, I also increased the Autocomplete Timeout. I still get the error below, however I noticed the error code changed on ollama side.
It's now 499

[GIN] 2025/10/12 - 07:18:43 | 499 | 12.947215152s | 172.19.0.1 | POST "/api/chat"

mainThreadExtensionService.ts:79 AbortError2: The operation was aborted.
at abort2 (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:137386:22)
at c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:137397:7
at new Promise ()
at fetch3 (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:137368:10)
at fetchwithRequestOptions (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:139872:24)
at async customFetch2 (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:243257:26)
at async withExponentialBackoff (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:239085:27)
at async _Ollama._streamChat (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:485417:26)
at async _Ollama.streamChat (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:243778:32)
at async _Ollama.chat (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:243664:26)
at async _NextEditProvider._handleCompletion (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:730894:21)
at async _NextEditProvider.provideInlineCompletionItems (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:730787:18)
at async ContinueCompletionProvider.provideInlineCompletionItems (c:\Users\Abdalla.vscode\extensions\continue.continue-1.2.8-win32-x64\out\extension.js:757890:25)
at async da.provideInlineCompletions (file:///c:/Users/Abdalla/AppData/Local/Programs/Microsoft%20VS%20Code/resources/app/out/vs/workbench/api/node/extensionHostProcess.js:142:145872)
log.ts:460 ERR An unknown error occurred. Please consult the log for more details.

[stranger-games]

After rechecking the ollama log I see the following. It seems that continue dev cancel the request even though I am setting the autocomplete timeout to 10000. So this probably means continue.dev just cancels for another reason.

time=2025-10-12T13:02:21.266Z level=INFO source=server.go:400 msg="starting runner" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-65eff06597c533456ac031479f31175e894e9e6ff79a562ed4d1f859f154af29 --port 38989"

time=2025-10-12T13:02:21.267Z level=INFO source=server.go:505 msg="system memory" total="29.4 GiB" free="27.9 GiB" free_swap="8.0 GiB"

time=2025-10-12T13:02:21.267Z level=INFO source=memory.go:36 msg="new model will fit in available VRAM across minimum required GPUs, loading" model=/root/.ollama/models/blobs/sha256-65eff06597c533456ac031479f31175e894e9e6ff79a562ed4d1f859f154af29 library=CUDA parallel=1 required="5.6 GiB" gpus=1

time=2025-10-12T13:02:21.267Z level=INFO source=server.go:545 msg=offload library=CUDA layers.requested=-1 layers.model=29 layers.offload=29 layers.split=[29] memory.available="[22.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="5.6 GiB" memory.required.kv="448.0 MiB" memory.required.allocations="[5.6 GiB]" memory.weights.total="4.1 GiB" memory.weights.repeating="3.7 GiB" memory.weights.nonrepeating="426.4 MiB" memory.graph.full="478.0 MiB" memory.graph.partial="730.4 MiB"

time=2025-10-12T13:02:21.268Z level=INFO source=sched.go:449 msg="Load failed" model=/root/.ollama/models/blobs/sha256-65eff06597c533456ac031479f31175e894e9e6ff79a562ed4d1f859f154af29 error="context canceled"

time=2025-10-12T13:02:21.280Z level=INFO source=runner.go:864 msg="starting go runner"

load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so

[GIN] 2025/10/12 - 13:02:21 | 499 | 1.115589223s | 172.19.0.1 | POST "/api/chat"