github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15134] x/tools: add a no-op think tool for structured reasoning before action #56202

New Issue
Open
opened 2026-04-29 10:25:26 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 10:25:26 -05:00
Owner
Copy Link

Originally created by @harshitgavita-07 on GitHub (Mar 29, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15134

I'd like to propose a small addition to the agent/tooling layer: a built-in think
tool in x/tools that gives models a structured no-op reasoning step before taking
an external action.

Why

The current tool loop supports acting (bash, web/search-style tools, etc.), but
there doesn't appear to be a built-in reasoning primitive for cases where a model
should explicitly plan before choosing its next tool call.

For local/smaller models, this can help reduce bad tool selection and malformed
arguments by encouraging a plan-first pattern:

  1. think
  2. choose tool
  3. act

Proposed behavior

  • Tool name: think
  • Input schema: { "thought": string }
  • Execution: validates input and returns "ok"
  • Side effects: none
  • Optional opt-out via env var, e.g. OLLAMA_AGENT_DISABLE_THINK=1

Scope

This would be intentionally small:

  • x/tools/think.go
  • tests
  • registry wiring
  • human-readable display name in approval UI

If this direction fits the roadmap, I can open a focused PR with tests.
@jmorganca

Originally created by @harshitgavita-07 on GitHub (Mar 29, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15134 I'd like to propose a small addition to the agent/tooling layer: a built-in `think` tool in `x/tools` that gives models a structured no-op reasoning step before taking an external action. ## Why The current tool loop supports acting (`bash`, web/search-style tools, etc.), but there doesn't appear to be a built-in reasoning primitive for cases where a model should explicitly plan before choosing its next tool call. For local/smaller models, this can help reduce bad tool selection and malformed arguments by encouraging a plan-first pattern: 1. think 2. choose tool 3. act ## Proposed behavior - Tool name: `think` - Input schema: `{ "thought": string }` - Execution: validates input and returns `"ok"` - Side effects: none - Optional opt-out via env var, e.g. `OLLAMA_AGENT_DISABLE_THINK=1` ## Scope This would be intentionally small: - `x/tools/think.go` - tests - registry wiring - human-readable display name in approval UI If this direction fits the roadmap, I can open a focused PR with tests. @jmorganca
GiteaMirror added the feature request label 2026-04-29 10:25:27 -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 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#56202
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?