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

Custom commands with agents should(?) run in isolated sessions #1533

New Issue
Closed
opened 2026-02-16 17:31:25 -05:00 by yindo · 11 comments
yindo commented 2026-02-16 17:31:25 -05:00
Owner
Copy Link
Copy Source

Originally created by @audibleblink on GitHub (Aug 29, 2025).

Originally assigned to: @rekram1-node on GitHub.

Problem

When using a custom command that specifies an agent, the agent execution happens in the current context/session instead of running in isolation like when using @agent syntax.

Expected Behavior

A custom command like /commit with agent: git configured should behave the same as @git save my work - running the agent in its own isolated session without polluting the current context with tool output.

Current Behavior

The /commit command with agent: git executes everything in the current context/session, showing all git tool output and analysis in the main conversation.

Configuration

Command configuration (command/commit.md):

---
description: Commit using the current git state
agent: git
---

## Context

**Current git status**
!`git status`

**Current git diff (staged and unstaged changes)**
!`git diff --no-ext-diff HEAD | tr @ _`

**Recent commit format**
!`git log --oneline -10`

Agent configuration (agent/git.md):

---
description: Create well-formatted commits using the conventional commits style
mode: subagent
permission:
  bash:
    "git add *": "deny"
    "git stage *": "deny"
    "git reset *": "deny"
    "git restore *": "deny"
---
< git instructions here >

Impact

This makes custom commands with agents less useful since they clutter the main conversation instead of providing the clean, isolated execution that @agent syntax provides.

If this is the intended behavior, then perhaps an additional /command property like subtask: <boolean> could allow both behaviors

Originally created by @audibleblink on GitHub (Aug 29, 2025). Originally assigned to: @rekram1-node on GitHub. ## Problem When using a custom command that specifies an `agent`, the agent execution happens in the current context/session instead of running in isolation like when using `@agent` syntax. ## Expected Behavior A custom command like `/commit` with `agent: git` configured should behave the same as `@git save my work` - running the agent in its own isolated session without polluting the current context with tool output. ## Current Behavior The `/commit` command with `agent: git` executes everything in the current context/session, showing all git tool output and analysis in the main conversation. ## Configuration **Command configuration** (`command/commit.md`): ```markdown --- description: Commit using the current git state agent: git --- ## Context **Current git status** !`git status` **Current git diff (staged and unstaged changes)** !`git diff --no-ext-diff HEAD | tr @ _` **Recent commit format** !`git log --oneline -10` ``` **Agent configuration** (`agent/git.md`): ```markdown --- description: Create well-formatted commits using the conventional commits style mode: subagent permission: bash: "git add *": "deny" "git stage *": "deny" "git reset *": "deny" "git restore *": "deny" --- < git instructions here > ``` ## Impact This makes custom commands with agents less useful since they clutter the main conversation instead of providing the clean, isolated execution that `@agent` syntax provides. If this is the intended behavior, then perhaps an additional `/command` property like `subtask: <boolean>` could allow both behaviors
yindo closed this issue 2026-02-16 17:31:25 -05:00
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@NaikSoftware commented on GitHub (Sep 1, 2025):

It looks like subagent used under the hood. But not showed in the session title

@NaikSoftware commented on GitHub (Sep 1, 2025): It looks like subagent used under the hood. But not showed in the session title
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 1, 2025):

wdym? can you reword that

@rekram1-node commented on GitHub (Sep 1, 2025): wdym? can you reword that
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@NaikSoftware commented on GitHub (Sep 1, 2025):

I tried to ask which agent currently used and it responds with name of subagent

@NaikSoftware commented on GitHub (Sep 1, 2025): I tried to ask which agent currently used and it responds with name of subagent
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 1, 2025):

ah it is probably lying, the agent doesnt know its name but it does know the name of other subagents so it is just telling you the name of a subagent it can trigger

@rekram1-node commented on GitHub (Sep 1, 2025): ah it is probably lying, the agent doesnt know its name but it does know the name of other subagents so it is just telling you the name of a subagent it can trigger
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@arsham commented on GitHub (Sep 10, 2025):

You can test this behaviour by running the slash command and instruct it to do nothing and return back. Then in the current context ask questions about specific instructions in the slash command. Unfortunately my tests shows that the context is not isolated.

@arsham commented on GitHub (Sep 10, 2025): You can test this behaviour by running the slash command and instruct it to do nothing and return back. Then in the current context ask questions about specific instructions in the slash command. Unfortunately my tests shows that the context is not isolated.
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@NaikSoftware commented on GitHub (Sep 10, 2025):

It worked for me, because I copied slash commands from Claude Code. There I described at the beginning of the instructions which agent to use. I this case calling /my-command always switch to isolated agent, but this is a tricky 😄

@NaikSoftware commented on GitHub (Sep 10, 2025): It worked for me, because I copied slash commands from Claude Code. There I described at the beginning of the instructions which agent to use. I this case calling /my-command always switch to isolated agent, but this is a tricky 😄
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@arsham commented on GitHub (Sep 10, 2025):

I don't think that is what this issue is about, correct me if I'm wrong. You can delegate to agents in the instructions, but the issue is about the part in the front-matter:

---
description: Commit using the current git state
agent: git
---

In this setup, we expect the command to be run by the git agent and in isolation.

@arsham commented on GitHub (Sep 10, 2025): I don't think that is what this issue is about, correct me if I'm wrong. You can delegate to agents in the instructions, but the issue is about the part in the front-matter: ```yaml --- description: Commit using the current git state agent: git --- ``` In this setup, we expect the command to be run by the `git` agent and in isolation.
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 10, 2025):

if it is a subagent I think that makes a lot of sense, but what if it's a primary agent?

@rekram1-node commented on GitHub (Sep 10, 2025): if it is a subagent I think that makes a lot of sense, but what if it's a primary agent?
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@arsham commented on GitHub (Sep 10, 2025):

if it is a subagent I think that makes a lot of sense, but what if it's a primary agent?

I think it would be valuable to have both behave the same and in isolation. When we set this agent in a slash command, we intend to isolate it, otherwise we would omit the agent all together.

Another possibility would be in cases someone wants to run the command in the context of a certain primary agent. In that case we can document that they could use shift-tab to choose the primary agent and run the command with it.

@arsham commented on GitHub (Sep 10, 2025): > if it is a subagent I think that makes a lot of sense, but what if it's a primary agent? I think it would be valuable to have both behave the same and in isolation. When we set this `agent` in a slash command, we intend to isolate it, otherwise we would omit the `agent` all together. Another possibility would be in cases someone wants to run the command in the context of a certain primary agent. In that case we can document that they could use shift-tab to choose the primary agent and run the command with it.
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@audibleblink commented on GitHub (Sep 10, 2025):

If the slash command has no configured subagent, then I think it's a reasonable expectation for it to run in the currently selected agent and context.

In the event that someone wants the slash command to run with the currently active main agent, but as a subtask to strategically separate context, then a subtask frontmatter property seems valuable.

@audibleblink commented on GitHub (Sep 10, 2025): If the slash command has no configured subagent, then I think it's a reasonable expectation for it to run in the currently selected agent and context. In the event that someone wants the slash command to run with the currently active main agent, but as a subtask to strategically separate context, then a `subtask` frontmatter property seems valuable.
yindo commented 2026-02-16 17:31:25 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 13, 2025):

Will be in next release, will behave as @audibleblink said

@rekram1-node commented on GitHub (Sep 13, 2025): Will be in next release, will behave as @audibleblink said
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#1533
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?