github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.5k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11938] [Bug/Feature Request] JSON Parse Failure via Reverse Tunnel with Chunked HTTP Responses #69984

New Issue
Open
opened 2026-05-04 19:59:05 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-04 19:59:05 -05:00
Owner
Copy Link

Originally created by @ademirtug on GitHub (Aug 16, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11938

What is the issue?

Description:
I encountered an issue when using Ollama behind a reverse tunnel, where JSON responses fail to parse when Ollama switches from Content-Length responses to HTTP chunked transfer encoding.

Setup:

  • Remote Server: Runs the Open Web UI (port 9000) but does not have Ollama installed.
  • Local PC: Runs Ollama (localhost:11434) and is behind a CGNAT.
  • Tunnel: A reverse tunnel is used (either via a custom C# relay or ssh -R 11434:localhost:11434) to connect the server to the local Ollama instance.

Steps to Reproduce:

  1. Run Ollama locally on your PC.
  2. Connect the server’s Open Web UI to Ollama via the reverse tunnel.
  3. Request the list of models — this works correctly.
  4. Send a query, e.g., "hey".
  5. Ollama switches to HTTP chunked transfer encoding, and the Open Web UI fails with a JSON parse error.

Observed Behavior:

  • Content-Length responses are correctly parsed.
  • Chunked transfer responses break JSON parsing through the tunnel.

Expected Behavior:

  • JSON responses from Ollama should be correctly parsed regardless of transfer encoding.

Additional Notes:

  • This issue occurs both with my C# relay implementation and a standard SSH reverse tunnel (ssh -R).
  • The problem seems related to handling of chunked HTTP responses across a TCP relay.

Request:

  • A feature or flag to force Content-Length

Relevant log output

OS

Windows

GPU

AMD

CPU

AMD

Ollama version

0.11.5

Originally created by @ademirtug on GitHub (Aug 16, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11938 ### What is the issue? Description: I encountered an issue when using Ollama behind a reverse tunnel, where JSON responses fail to parse when Ollama switches from `Content-Length` responses to HTTP chunked transfer encoding. Setup: - Remote Server: Runs the Open Web UI (port 9000) but does not have Ollama installed. - Local PC: Runs Ollama (localhost:11434) and is behind a CGNAT. - Tunnel: A reverse tunnel is used (either via a custom C# relay or `ssh -R 11434:localhost:11434`) to connect the server to the local Ollama instance. Steps to Reproduce: 1. Run Ollama locally on your PC. 2. Connect the server’s Open Web UI to Ollama via the reverse tunnel. 3. Request the list of models — this works correctly. 4. Send a query, e.g., `"hey"`. 5. Ollama switches to HTTP chunked transfer encoding, and the Open Web UI fails with a JSON parse error. Observed Behavior: - `Content-Length` responses are correctly parsed. - Chunked transfer responses break JSON parsing through the tunnel. Expected Behavior: - JSON responses from Ollama should be correctly parsed regardless of transfer encoding. Additional Notes: - This issue occurs both with my C# relay implementation and a standard SSH reverse tunnel (`ssh -R`). - The problem seems related to handling of chunked HTTP responses across a TCP relay. Request: - A feature or flag to force `Content-Length` ### Relevant log output ```shell ``` ### OS Windows ### GPU AMD ### CPU AMD ### Ollama version 0.11.5
GiteaMirror added the bug label 2026-05-04 19:59:05 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#69984
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?