github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14196] Delayed Constrained Decoding for Thinking with JSON/Structured Outputs #71311

New Issue
Open
opened 2026-05-05 01:11:10 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-05 01:11:10 -05:00
Owner
Copy Link

Originally created by @ardafincan on GitHub (Feb 10, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14196

Currently when using models with thinking ability alongside the format: parameter, the thinking process is entirely suppressed.

So I would like to propose a "Delayed Constrained Decoding" mechanism.

The inference engine should allow model to generate tokens unconstrained until it reaches the </think> token.
Only after that JSON/Schema should be forced on the remaining steps.

I am thinking of working on this one, what do you think?

Originally created by @ardafincan on GitHub (Feb 10, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14196 Currently when using models with `thinking` ability alongside the `format:` parameter, the thinking process is entirely suppressed. So I would like to propose a *"Delayed Constrained Decoding"* mechanism. The inference engine should allow model to generate tokens unconstrained until it reaches the `</think>` token. Only after that JSON/Schema should be forced on the remaining steps. I am thinking of working on this one, what do you think?
GiteaMirror added the feature request label 2026-05-05 01:11:10 -05:00
GiteaMirror commented 2026-05-05 01:11:12 -05:00
Author
Owner
Copy Link

@ardafincan commented on GitHub (Feb 14, 2026):

I am correcting this: the thinking ability gets suppressed when the request is sent to /api/generate someone solved the issue in /api/chat but it remains in generate endpoint. I am working on this.

<!-- gh-comment-id:3902006352 --> @ardafincan commented on GitHub (Feb 14, 2026): I am correcting this: the thinking ability gets suppressed when the request is sent to `/api/generate` someone solved the issue in `/api/chat` but it remains in generate endpoint. I am working on this.
GiteaMirror commented 2026-05-05 01:11:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 17, 2026):

FYI #14288

<!-- gh-comment-id:3912042578 --> @rick-github commented on GitHub (Feb 17, 2026): FYI #14288
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 feature request
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#71311
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?