anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 18:25:32 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

option to hide command prompt #2130

New Issue
Open
opened 2026-02-16 17:34:17 -05:00 by yindo · 6 comments
yindo commented 2026-02-16 17:34:17 -05:00
Owner
Copy Link
Copy Source

Originally created by @ferrao on GitHub (Oct 16, 2025).

Originally assigned to: @thdxr on GitHub.

I have created some commands that load context from files through shell output and file references.
Some of this additional context is long and I would like to avoid polluting the conversation with the agent with it.

Is there a way to achieve this, like with do with /details that shows and hides tool details.
Would be nice to use it to show/hide command details as well.

Originally created by @ferrao on GitHub (Oct 16, 2025). Originally assigned to: @thdxr on GitHub. I have created some commands that load context from files through shell output and file references. Some of this additional context is long and I would like to avoid polluting the conversation with the agent with it. Is there a way to achieve this, like with do with `/details` that shows and hides tool details. Would be nice to use it to show/hide command details as well.
yindo commented 2026-02-16 17:34:18 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 16, 2025):

Some of this additional context is long and I would like to avoid polluting the conversation with the agent with it.

Are you just wanting to visually hide the context or do you want it to be reduced for agent as well?

You can trigger a command as a subagent if the agent specified is a subagent or if you add:

subtask: true

to the command definition

That would address both visual and contextual pollution?

@rekram1-node commented on GitHub (Oct 16, 2025): > Some of this additional context is long and I would like to avoid polluting the conversation with the agent with it. Are you just wanting to visually hide the context or do you want it to be reduced for agent as well? You can trigger a command as a subagent if the agent specified is a subagent or if you add: subtask: true to the command definition That would address both visual and contextual pollution?
yindo commented 2026-02-16 17:34:18 -05:00
Author
Owner
Copy Link
Copy Source

@ferrao commented on GitHub (Oct 16, 2025):

Some of this additional context is long and I would like to avoid polluting the conversation with the agent with it.
Are you just wanting to visually hide the context or do you want it to be reduced for agent as well?

I just want to visually hide the context.

You can trigger a command as a subagent if the agent specified is a subagent or if you add:
subtask: true
to the command definition

That would address both visual and contextual pollution?

That was my initial setup, but had to give up on it, because that would force me to switch to the sub-agent session to maintain an interactive conversation with it.

@ferrao commented on GitHub (Oct 16, 2025): > > Some of this additional context is long and I would like to avoid polluting the conversation with the agent with it. > Are you just wanting to visually hide the context or do you want it to be reduced for agent as well? I just want to visually hide the context. > You can trigger a command as a subagent if the agent specified is a subagent or if you add: > subtask: true > to the command definition > > That would address both visual and contextual pollution? That was my initial setup, but had to give up on it, because that would force me to switch to the sub-agent session to maintain an interactive conversation with it.
yindo commented 2026-02-16 17:34:18 -05:00
Author
Owner
Copy Link
Copy Source

@ferrao commented on GitHub (Oct 16, 2025):

@rekram1-node perhaps if explain my use case better will help.

I want to invoke a command like /research <some topic to research>, which will trigger a bunch of context loading and involve a researcher agent in the conversation that will ask me a bunch of questions, that I will respond one at a time and eventually write the research output into a file.

@ferrao commented on GitHub (Oct 16, 2025): @rekram1-node perhaps if explain my use case better will help. I want to invoke a command like `/research <some topic to research>`, which will trigger a bunch of context loading and involve a `researcher` agent in the conversation that will ask me a bunch of questions, that I will respond one at a time and eventually write the research output into a file.
yindo commented 2026-02-16 17:34:18 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 16, 2025):

Okay gotcha just wanted to clarify, I understand now

@rekram1-node commented on GitHub (Oct 16, 2025): Okay gotcha just wanted to clarify, I understand now
yindo commented 2026-02-16 17:34:18 -05:00
Author
Owner
Copy Link
Copy Source

@ferrao commented on GitHub (Oct 16, 2025):

Okay gotcha just wanted to clarify, I understand now

For reference, I also opened #3222 regarding the interactive conversation with the agent.

@ferrao commented on GitHub (Oct 16, 2025): > Okay gotcha just wanted to clarify, I understand now For reference, I also opened #3222 regarding the interactive conversation with the agent.
yindo commented 2026-02-16 17:34:18 -05:00
Author
Owner
Copy Link
Copy Source

@V4G4X commented on GitHub (Jan 13, 2026):

Waiting for this since a long time!

@V4G4X commented on GitHub (Jan 13, 2026): Waiting for this since a long time!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#2130
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?