github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12278] Assist with Ollama models does not execute delayed/scheduled commands #8162

New Issue
Closed
opened 2026-04-12 20:34:17 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 20:34:17 -05:00
Owner
Copy Link

Originally created by @viba1 on GitHub (Sep 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12278

What is the issue?

When using Assist in Home Assistant with different models (default or via Ollama with tools support such as gemma3 or granite3.3), simple and complex commands behave differently.

A simple command such as "turn on the lamp" executes correctly regardless of the engine used.

A complex command such as "turn on the lamp in 1 minute" only returns "command received" when using ollama/gemma3/granite3.3, but only Home Assistant's native assistant actually executes the scheduled action.

In other words, the intent is correctly understood by the alternative models, but the action is never actually triggered when it involves a delay or time-based logic.
Steps to reproduce

Install Home Assistant and enable Assist.

Configure Ollama with a model supporting tools (e.g., gemma3, granite3.3).

Issue the voice or text command: "turn on the lamp".

    Expected result: the lamp turns on (this works correctly).

Issue the voice or text command: "turn on the lamp in 1 minute".

    Expected result: the lamp turns on after 1 minute.

    Actual result: only the HA default assistant executes the task. With Ollama, the response is "command received" but the action never happens.

Expected behavior

All implementations of Assist (default or via Ollama + tools models) should correctly execute complex commands involving scheduling or delays.
Current behavior

Default Assist: executes both simple and complex commands correctly.

Ollama Assist (gemma3, granite3.3, etc.): executes only simple commands but does not trigger scheduled actions.

Additional information

Home Assistant version: 2025.9

Ollama version: 0.11.10

Models tested: gemma3, granite3.3

Relevant log output

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.11.10

Originally created by @viba1 on GitHub (Sep 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12278 ### What is the issue? When using Assist in Home Assistant with different models (default or via Ollama with tools support such as gemma3 or granite3.3), simple and complex commands behave differently. A simple command such as "turn on the lamp" executes correctly regardless of the engine used. A complex command such as "turn on the lamp in 1 minute" only returns "command received" when using ollama/gemma3/granite3.3, but only Home Assistant's native assistant actually executes the scheduled action. In other words, the intent is correctly understood by the alternative models, but the action is never actually triggered when it involves a delay or time-based logic. Steps to reproduce Install Home Assistant and enable Assist. Configure Ollama with a model supporting tools (e.g., gemma3, granite3.3). Issue the voice or text command: "turn on the lamp". Expected result: the lamp turns on (this works correctly). Issue the voice or text command: "turn on the lamp in 1 minute". Expected result: the lamp turns on after 1 minute. Actual result: only the HA default assistant executes the task. With Ollama, the response is "command received" but the action never happens. Expected behavior All implementations of Assist (default or via Ollama + tools models) should correctly execute complex commands involving scheduling or delays. Current behavior Default Assist: executes both simple and complex commands correctly. Ollama Assist (gemma3, granite3.3, etc.): executes only simple commands but does not trigger scheduled actions. Additional information Home Assistant version: 2025.9 Ollama version: 0.11.10 Models tested: gemma3, granite3.3 ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.11.10
GiteaMirror added the bug label 2026-04-12 20:34:17 -05:00
GiteaMirror commented 2026-04-12 20:34:24 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 12, 2025):

ollama doesn't have a clock. This is a HA/intent/tool issue, not an ollama issue.

<!-- gh-comment-id:3287015670 --> @rick-github commented on GitHub (Sep 12, 2025): ollama doesn't have a clock. This is a HA/intent/tool issue, not an ollama issue.
GiteaMirror commented 2026-04-12 20:34:28 -05:00
Author
Owner
Copy Link

@viba1 commented on GitHub (Sep 12, 2025):

My bad.
Thanx

<!-- gh-comment-id:3287029027 --> @viba1 commented on GitHub (Sep 12, 2025): My bad. Thanx
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#8162
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?