Local LLM using LM Studio fails to test and add models

[IAmSaeve]

Hi there 🙂

Thunderbolt locally using Docker Compose with a LM Studio instance for local models does not seem to work.
When trying to pick a model from the list from LM Studio I get all the models, as expected, but pressing "Test Model" and "Add model" fails.

Logs from Docker gives me this result:

backend-1    | {"level":30,"time":1781208638333,"pid":1,"hostname":"5f7077265e9b","event":"proxy_request","method":"POST","target_host":"localhost","status":400,"duration_ms":2,"bytes_in":0,"bytes_out":0,"user_id":"FNU1tnhElgpycSl4yIbjaIPg9tSv4RFS","request_id":"af50457f-0c3b-4e17-8368-6524f9e4302a","error_type":"ssrf"}
frontend-1   | 172.19.0.1 - - [11/Jun/2026:20:10:38 +0000] "POST /v1/proxy HTTP/1.1" 400 68 "http://localhost:3000/settings/models" "Mozilla/5.0 (X11; Linux x86_64; rv:151.0) Gecko/20100101 Firefox/151.0" "-"

The API is clearly reachable since all models are pulled in correctly, but none can be added or used.

Tested both LM Studio endpoint /api/v1/ and OpenAI /v1/

Details

Provider URL: http://localhost:1234/v1

Commit: f95c9cd
OS: Linux
Docker Compose Version: 5.1.4
Docker Version:

Client:
 Version:           29.5.2
 API version:       1.54
 Go version:        go1.26.3-X:nodwarf5
 Git commit:        79eb04c7d8
 Built:             Mon Jun  1 15:47:11 2026
 OS/Arch:           linux/amd64
 Context:           default

Server:
 Engine:
  Version:          29.5.2
  API version:      1.54 (minimum version 1.40)
  Go version:       go1.26.3-X:nodwarf5
  Git commit:       568f755ebe
  Built:            Mon Jun  1 15:47:11 2026
  OS/Arch:          linux/amd64
  Experimental:     false
 containerd:
  Version:          v2.3.1
  GitCommit:        64b425cf570b3b8dd1d4cc46da7c1fce65c6651a.m
 runc:
  Version:          1.4.2
  GitCommit:        
 docker-init:
  Version:          0.19.0
  GitCommit:        de40ad0

Screenshots