docs(changelog): rewrite the last thirty releases for readers

Releases 1.13.1 through 1.22.1 are regrouped by what each change is
(New, Improvements, Fixes, Misc) and reworded in the voice the
changelog-authoring skill asks for: one or two plain sentences per
bullet, the symptom or the capability named, no mechanism. Packed
bullets were split, every fact and every contributor credit kept.
Older releases keep the mechanical grouping.

Claude-Session: https://claude.ai/code/session_01VqV56Hez25hTxXH4ipJfzH
This commit is contained in:
Bohdan Triapitsyn
2026-09-05 15:58:34 +03:00
parent d9b9c8edab
commit 9f78de9e89
33 changed files with 2714 additions and 2213 deletions
+9 -8
View File
@@ -6,21 +6,22 @@ date: 2026-06-29
## App
### New
- Chat: a new Follow-up behavior setting (Settings → Chat) controls what happens when you press Enter on a message while the agent is still responding — Steer inserts it into the agent's current turn, or Queue holds it until the turn finishes. Replaces the previous queue-mode toggle (thanks to @bashrusakh).
- **Chat: choose what Enter does mid-reply.** A Follow-up behavior setting in Settings → Chat either steers your message into the agent's current turn or queues it until the turn finishes. It takes over from the old queue-mode toggle (thanks to @bashrusakh).
### Improvements
- Sessions: deleting a worktree group from the sidebar, or permanently deleting an archived session that has subagent sessions, now removes those subagent sessions too instead of leaving them behind (thanks to @bashrusakh).
- Sessions: deleting a worktree group from the sidebar, or permanently deleting an archived session, now takes its subagent sessions with it (thanks to @bashrusakh).
### Fixes
- Startup: launching the app no longer hangs for around 20 seconds before you can open a session, load a diff, or send a message GitHub pull request status checks no longer tie up the connection to the server during startup.
- OpenCode: when a separate OpenCode is already running (the TUI, `opencode serve`, or a daemon on the default port 4096), the app now starts its own server instead of attaching to it. This fixes the "OpenChamber could not finish initialization" error and stops the app from opening or closing your separate OpenCode when it starts and quits. Connecting to an external OpenCode now requires setting `OPENCODE_HOST`, `OPENCODE_PORT`, or `OPENCODE_SKIP_START`.
- Sessions: clicking a session inside a worktree group no longer briefly jumps the selection to the project's first session while the sidebar data catches up (thanks to @bashrusakh).
- Sync: a connected but quiet session (for example an agent running a long tool call) no longer triggers repeated background refreshes every ~15 seconds (thanks to @tomzx).
- **Startup: the app is usable right away.** Launching it no longer hangs for around 20 seconds before you can open a session, load a diff, or send a message. GitHub pull request status checks were holding the connection to the server.
- **OpenCode: your own OpenCode is left alone.** When one is already running, whether the TUI, `opencode serve`, or a daemon on port 4096, the app starts its own server. This clears the "OpenChamber could not finish initialization" error and stops the app from opening or closing your OpenCode as it starts and quits.
- OpenCode: to connect to an external OpenCode on purpose, set `OPENCODE_HOST`, `OPENCODE_PORT`, or `OPENCODE_SKIP_START`.
- Sessions: clicking a session inside a worktree group keeps it selected, with no jump to the project's first session while the sidebar catches up (thanks to @bashrusakh).
- Sync: a connected but quiet session, say an agent running a long tool call, stops kicking off a background refresh every 15 seconds (thanks to @tomzx).
## VS Code
### New
- Chat: a new Follow-up behavior setting controls what happens when you press Enter on a message while the agent is still responding — Steer inserts it into the agent's current turn, or Queue holds it until the turn finishes. Replaces the previous queue-mode toggle (thanks to @bashrusakh).
- **Chat: choose what Enter does mid-reply.** A Follow-up behavior setting either steers your message into the agent's current turn or queues it until the turn finishes. It takes over from the old queue-mode toggle (thanks to @bashrusakh).
### Fixes
- Sync: a connected but quiet session (for example an agent running a long tool call) no longer triggers repeated background refreshes every ~15 seconds (thanks to @tomzx).
- Sync: a connected but quiet session, say an agent running a long tool call, stops kicking off a background refresh every 15 seconds (thanks to @tomzx).