github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15029] /v1/chat/completions not support think:true #9654

New Issue
Closed
opened 2026-04-12 22:32:41 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 22:32:41 -05:00
Owner
Copy Link

Originally created by @dallisx on GitHub (Mar 24, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15029

What is the issue?

When invoking the deepseek-r1 model via the /v1/chat/completions endpoint, enabling the "think" feature is not possible. In the ollama source code, it is explicitly defined that "think" cannot be set to true, whereas the deepseek-r1 model exclusively supports "think=true". The relevant ollama source code is as follows:
var think *api.ThinkValue
var effort string

if r.Reasoning != nil {
	effort = r.Reasoning.Effort
} else if r.ReasoningEffort != nil {
	effort = *r.ReasoningEffort
}

if effort != "" {
	if !slices.Contains([]string{"high", "medium", "low", "none"}, effort) {
		return nil, fmt.Errorf("invalid reasoning value: '%s' (must be \"high\", \"medium\", \"low\", or \"none\")", effort)
	}

	if effort == "none" {
		think = &api.ThinkValue{Value: false}
	} else {
		think = &api.ThinkValue{Value: effort}
	}
}

return &api.ChatRequest{
	Model:           r.Model,
	Messages:        messages,
	Format:          format,
	Options:         options,
	Stream:          &r.Stream,
	Tools:           r.Tools,
	Think:           think,
	Logprobs:        r.Logprobs != nil && *r.Logprobs,
	TopLogprobs:     r.TopLogprobs,
	DebugRenderOnly: r.DebugRenderOnly,
}, nil

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @dallisx on GitHub (Mar 24, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15029 ### What is the issue? When invoking the deepseek-r1 model via the /v1/chat/completions endpoint, enabling the "think" feature is not possible. In the ollama source code, it is explicitly defined that "think" cannot be set to true, whereas the deepseek-r1 model exclusively supports "think=true". The relevant ollama source code is as follows: var think *api.ThinkValue var effort string if r.Reasoning != nil { effort = r.Reasoning.Effort } else if r.ReasoningEffort != nil { effort = *r.ReasoningEffort } if effort != "" { if !slices.Contains([]string{"high", "medium", "low", "none"}, effort) { return nil, fmt.Errorf("invalid reasoning value: '%s' (must be \"high\", \"medium\", \"low\", or \"none\")", effort) } if effort == "none" { think = &api.ThinkValue{Value: false} } else { think = &api.ThinkValue{Value: effort} } } return &api.ChatRequest{ Model: r.Model, Messages: messages, Format: format, Options: options, Stream: &r.Stream, Tools: r.Tools, Think: think, Logprobs: r.Logprobs != nil && *r.Logprobs, TopLogprobs: r.TopLogprobs, DebugRenderOnly: r.DebugRenderOnly, }, nil ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 22:32:41 -05:00
GiteaMirror commented 2026-04-12 22:32:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 24, 2026):

"true" is not a supported value in the OpenAI API for reasoning_effort. Instead, use one of "low", "medium" or "high", which will enable reasoning. Note that thinking is enabled by default, so explictly enabling thinking (think:true or reasoning_effort:medium) is not necessary for models that support thinking.

$ for t in none low medium high ; do r="$(curl -s localhost:11434/v1/chat/completions -d '{"model":"deepseek-r1","messages":[{"role":"user","content":"why is the sky blue"}],"reasoning_effort":"'$t'","stream":false,"seed":0}' | jq -r '.choices[0].message.reasoning//""')" ; printf "%-7s %4d %s\n" $t ${#r} "${r::100}" ; done
none       0 
low     3497 Okay, the user is asking "why is the sky blue." This is a classic question that people often wonder 
medium  3497 Okay, the user is asking "why is the sky blue." This is a classic question that people often wonder 
high    3497 Okay, the user is asking "why is the sky blue." This is a classic question that people often wonder
<!-- gh-comment-id:4117890232 --> @rick-github commented on GitHub (Mar 24, 2026): "true" is not a supported value in the [OpenAI API](https://developers.openai.com/api/docs/guides/reasoning#:~:text=to%20medium.-,Effort,-Start%20here%20when) for `reasoning_effort`. Instead, use one of "low", "medium" or "high", which will enable reasoning. Note that thinking is enabled by default, so explictly enabling thinking (`think:true` or `reasoning_effort:medium`) is not necessary for models that support thinking. ```console $ for t in none low medium high ; do r="$(curl -s localhost:11434/v1/chat/completions -d '{"model":"deepseek-r1","messages":[{"role":"user","content":"why is the sky blue"}],"reasoning_effort":"'$t'","stream":false,"seed":0}' | jq -r '.choices[0].message.reasoning//""')" ; printf "%-7s %4d %s\n" $t ${#r} "${r::100}" ; done none 0 low 3497 Okay, the user is asking "why is the sky blue." This is a classic question that people often wonder medium 3497 Okay, the user is asking "why is the sky blue." This is a classic question that people often wonder high 3497 Okay, the user is asking "why is the sky blue." This is a classic question that people often wonder ```
GiteaMirror commented 2026-04-12 22:32:42 -05:00
Author
Owner
Copy Link

@dallisx commented on GitHub (Mar 24, 2026):

这是来自QQ邮箱的假期自动回复邮件。
 
您好，我最近正在休假中，无法亲自回复您的邮件。我将在假期结束后，尽快给您回复。

<!-- gh-comment-id:4117894305 --> @dallisx commented on GitHub (Mar 24, 2026): 这是来自QQ邮箱的假期自动回复邮件。   您好，我最近正在休假中，无法亲自回复您的邮件。我将在假期结束后，尽快给您回复。
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#9654
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?