github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #14660] server: apply format constraint when thinking is disabled #61469

New Issue
Open
opened 2026-04-29 16:33:37 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 16:33:37 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/14660
Author: @majiayu000
Created: 3/6/2026
Status: 🔄 Open

Base: main ← Head: fix/format-with-think-disabled

📝 Commits (1)

  • 9034842 server: apply format constraint when thinking is disabled

📊 Changes

2 files changed (+65 additions, -1 deletions)

View changed files

📝 server/routes.go (+2 -1)
📝 server/routes_generate_test.go (+63 -0)

📄 Description

Summary

  • Fix format/structured outputs being silently ignored when think=false on thinking-capable models (e.g. qwen3.5)

Problem

When sending think=false + format=json, the structured outputs logic still defers format masking (sets currentFormat = nil) because the condition only checks whether the model has a builtin parser or thinking capability, not whether thinking is actually enabled for the request. Since no thinking content is produced, the restart signal never fires, and format masking is never applied.

Fix

Add a thinkEnabled check so that format masking is only deferred when thinking will actually produce content.

Test plan

  • Added format applied when think disabled test to TestChatWithPromptEndingInThinkTag
  • Verifies that with think=false + format, the completion receives the format constraint directly (single call, format not nil)
  • All existing structured outputs tests pass (think=true behavior unchanged)

Fixes #14645

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/14660 **Author:** [@majiayu000](https://github.com/majiayu000) **Created:** 3/6/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `fix/format-with-think-disabled` --- ### 📝 Commits (1) - [`9034842`](https://github.com/ollama/ollama/commit/90348424c5bf11c300ced9c2a572a97f8df772f2) server: apply format constraint when thinking is disabled ### 📊 Changes **2 files changed** (+65 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `server/routes.go` (+2 -1) 📝 `server/routes_generate_test.go` (+63 -0) </details> ### 📄 Description ## Summary - Fix format/structured outputs being silently ignored when `think=false` on thinking-capable models (e.g. qwen3.5) ## Problem When sending `think=false` + `format=json`, the structured outputs logic still defers format masking (sets `currentFormat = nil`) because the condition only checks whether the model has a builtin parser or thinking capability, not whether thinking is actually enabled for the request. Since no thinking content is produced, the restart signal never fires, and format masking is never applied. ## Fix Add a `thinkEnabled` check so that format masking is only deferred when thinking will actually produce content. ## Test plan - Added `format applied when think disabled` test to `TestChatWithPromptEndingInThinkTag` - Verifies that with `think=false` + format, the completion receives the format constraint directly (single call, format not nil) - All existing structured outputs tests pass (think=true behavior unchanged) Fixes #14645 --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-29 16:33:37 -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 pull-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#61469
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?