Repository navigation
Replies: 20 comments
|
+1 |
|
+1 |
|
+1 |
|
+1 |
|
+1 |
|
+1 |
|
We need this badly |
|
+1 |
|
+1 |
|
+1 |
|
+1 |
|
+1 |
|
V2 has now landed, giving this topic some love, even opencode has an internal /btw slash command for a similar purpose. Would be nice to have |
|
+1, still very much want this. PR #18243 looks like the current attempt, would love to see it land. |
|
+1, i was using this all the time in cc would be immensly helpful |
|
+1, this is after a few days of very happy T3 Code usage the only really missing feature |
|
+1 please add |
|
I opened #24476 to bring Claude Code’s existing |
|
Happy to see there is such a need for this feature. I've built this on top of V2 and want to confirm direction and scope before I open it upstream. Working demo (all providers, web + desktop): jballo#1 What it does: How it's built: a side question is an ordinary V2 thread with a Proposed scope:
Question for maintainers: is this direction and scope OK to open as a PR? If you'd rather have it smaller, I'm happy to drop parts, e.g. the shortcut, or leave it Claude only first. |
|
+1, i prefer the tab-based solution from codex gui - ideal for complex questions / multiple turns |
Uh oh!
There was an error while loading. Please reload this page.
Problem
T3 Code has Steer and Queue for messages sent while an agent is working, but neither covers a different workflow:
Claude Code now exposes this as
/btw; Codex has the same general idea as/side.This is especially useful in long-running agent sessions. While an agent is working, I may want to ask things like:
Today the choices are all imperfect:
Desired behavior
Add a lightweight Side Chat / BTW action, available from the composer or command palette, with semantics roughly like:
If the parent is currently running, using the latest stable forkable boundary is fine. The important property is context-aware isolation, not necessarily access to partially streamed tokens.
A slash command such as
/btw//sidewould be nice, but a first-class UI action is equally good.Why this is worth revisiting after Orchestrator V2
This was already explored before V2:
/side/ SideChat request.The maintainer closure on #9436/#9437 explicitly said the orchestration/provider layers were being rewritten for V2 and invited a fresh PR/request once V2 landed.
V2 has now landed via #2829, and current
mainalready has much of the foundation that the old SideChat implementation had to build itself:thread.forkThreadForkServicethread.merge_backt3_thread_forkThere is even current user-facing fork/merge-back behavior, e.g. #15063.
So this request is intentionally not asking to revive the old orchestration implementation. It is asking whether the new V2 fork/context-transfer primitives can now be surfaced as a lightweight ephemeral SideChat workflow.
Relationship to Steer / Queue
This is intentionally a third semantic:
That distinction is the feature.
Possible minimal V1
A small first version could be:
Merge-back, multiple side tabs, mobile polish, and provider-specific shortcuts could come later.
The old #9437 UX is useful prior art, but the implementation should target the current V2 architecture.
All reactions