Brennan Benson 520033b0e1 fix(native-chat): fold thoughts and tool calls between replies into one row (#26048)
* fix(native-chat): fold thoughts and tool calls between replies into one row

A model that thinks before every tool call drew a 'Thought for Ns' row between
each call, and each thought also stopped the calls from merging, so a turn read
as dozens of alternating rows. The transcript now draws an unbroken stretch of
tool calls and thoughts within a turn as one tool run; thoughts read in order
inside it when opened and are not counted in its label.

* fix(native-chat): keep work runs whole while a turn edits files

A live turn that had edited a file kept splitting its newest call or
thought off the run (the row carrying the turn's diff rollup could not
join), so a lone "Thought for Ns" row came back at the bottom.

- Run boundaries are now one pure pass in src/shared
  (nativeChatWorkRunSpans), applied over the built transcript slots.
  Section heads end runs by sitting between rows, and rows inside an
  expanded subagent section are grouped the same way.
- The row carrying the turn's diff rollup joins as the run's last
  member; the run takes the rollup from it and the bar from its head.
- A collapsed run reserves one tool row plus a lead's words, not every
  thought's text.
- Lone rows and runs draw through the same MessageRow, with one flat
  keyed line list, so a row becoming a run no longer remounts (a
  revealed diff card no longer re-fires its scroll).
- A run opens by default while the reader holds one of its thoughts
  open; the run's own choice still wins.
- A drawn thought with no visible text joins a run instead of
  splitting it.

* fix(native-chat): pair each row's result with its own call; keep open thoughts out of runs

- A structured journal row's call and result now share one id (the
  provider's call id, else the row's own id), so a diff or output can no
  longer pair with an earlier unanswered call in the same work run or
  folded message. A quiet command followed by edits now shows each diff
  card under its own call, and the rollup's reveal lands on it.
- A thought still being thought, while its turn or subagent works, keeps
  its own row after the run and joins once it ends.
- Removed the rule that opened a run because a thought inside it was
  open; a thought keeps its own open state inside its run.

* fix(native-chat): an open thought the live line lets go of joins its run

Only a subagent section keeps a still-running thought out of its run.
At the top level the live line owns the open thought; when it lets go
(a Stop in flight, a prompt waiting on the reader) the thought now joins
the run at once instead of flashing as its own row until the turn ends.

* test(native-chat): guard the run row memo; name the slot post-pass test after it

Settled work runs must not rebuild their lines and thoughts on every stream
frame of the live run. Renames the slot-level run test so it no longer
shares a name with the shared span test.
2026-10-07 03:35:08 -07:00
2026-09-26 20:50:46 +00:00
2026-05-04 20:42:03 -07:00
2026-03-16 22:27:51 -07:00
2026-03-28 10:19:14 -07:00

Orca Orca

GitHub stars Total downloads across all releases License: MIT Join the Orca Discord Follow Orca on X Supported platforms: macOS, Windows, and Linux

中文 · 日本語 · 한국어 · Español · Français · Português

The AI Orchestrator for 100x builders.
Run Codex, ClaudeCode, OpenCode or Pi side-by-side — each in its own worktree, tracked in one place.

Download Orca

Orca desktop app running agents in parallel worktrees, with the Orca mobile companion app in the corner

Features

Mobile Companion

Monitor and steer your agents from your phone — get notified when an agent finishes and send follow-ups from anywhere.

iOS App Store · Android APK 0.0.52 · Docs →

Orca desktop with the mobile companion app

Parallel Worktrees

Fan one prompt across five agents, each in its own isolated git worktree — compare the results and merge the winner.

Docs →

Parallel worktree orchestration

Terminal Splits

Ghostty-class terminals with WebGL rendering, infinite splits, and scrollback that survives restarts.

Docs →

Terminal splits

Design Mode

Click any UI element in a real Chromium window to send its HTML, CSS, and a cropped screenshot straight into your agent's prompt.

Docs →

Embedded browser and Design Mode

GitHub & Linear, Native

Browse PRs, issues, and project boards in-app — open a worktree from any task and review without a context switch.

Docs →

GitHub and Linear task workflows in Orca

SSH Worktrees

Run agents on a beefy remote box with full file editing, git, and terminals — auto-reconnect and port forwarding included.

Docs →

Remote worktrees over SSH

Annotate AI Diffs

Drop comments on any diff line and ship them back to the agent — review, edit, and commit without leaving Orca.

Docs →

Annotate AI-generated diffs

Drag Files to Agents

VS Code's editor with autosave everywhere — drag files or images straight into an agent prompt.

Docs →

Drag files and images into an agent prompt

Orca CLI

Agents drive Orca too — script every workflow with orca worktree create, snapshot, click, and fill.

Docs →

Script Orca from the CLI

Also in the box:

  • Quick open — Search across worktrees, files, agents, commands, and repo context without leaving your flow.
  • Account switcher & usage tracking — See Claude and Codex usage and rate-limit resets, and hot-swap accounts without re-logging in.
  • Rich repo previews — Preview Markdown, images, PDFs, and repo docs in the workspace.
  • Computer Use — Let agents operate desktop apps and visible UI when a workflow needs real interaction.
  • Notifications and unread state — Know when an agent finishes or needs attention, then mark threads unread to come back later.
  • And many, many more — we ship daily, so this list is perpetually behind. The changelog is the real feature list.

Supported Agents

Works with any CLI agent — if it runs in a terminal, it runs in Orca.

Claude Code logo Claude Code   Codex logo Codex   Grok logo Grok   Cursor logo Cursor   GitHub Copilot logo GitHub Copilot   Muse logo Muse   DeepSeek Harness logo DeepSeek Harness   ZCode logo ZCode   OpenCode logo OpenCode   MiMo Code logo MiMo Code   Amp logo Amp   OpenClaude logo OpenClaude   Antigravity logo Antigravity   Pi logo Pi   oh-my-pi logo oh-my-pi   Hermes Agent logo Hermes Agent   Devin logo Devin   Goose logo Goose   Auggie logo Auggie   Autohand Code logo Autohand Code   Charm logo Charm   Cline logo Cline   CodeBuddy logo CodeBuddy   Codebuff logo Codebuff   Freebuff logo Freebuff   Command Code logo Command Code   Continue logo Continue   Droid logo Droid   Kilocode logo Kilocode   Kimi logo Kimi   Kiro logo Kiro   Mistral Vibe logo Mistral Vibe   Qwen Code logo Qwen Code   Rovo Dev logo Rovo Dev   + any CLI agent


Install

Desktop — macOS, Windows, Linux

Or via a package manager:

# macOS (Homebrew)
brew install --cask stablyai/orca/orca

# Arch Linux (AUR) — or stably-orca-git to build from source
yay -S stably-orca-bin

Mobile Companion — iOS, Android

Pair with your desktop app to monitor and steer your agents from your phone.


Community & Support

  • Discord: Join the community on Discord.

  • Twitter / X: Follow @orca_build for updates and announcements.

  • WeChat: Scan to join the Orca community WeChat group 11.

    WeChat group 11 QR code for the Orca community
  • Feedback & Ideas: We ship fast. Missing something? Request a new feature.

  • Privacy: See the privacy & telemetry docs for what anonymous usage data Orca collects and how to opt out.

  • Show Support: Star this repo to follow along with our daily ships.


Developing

Want to contribute or run locally? See our CONTRIBUTING.md guide.

The relay that pairs the mobile app with a desktop host is also in this repository under cloud/, with a separate pnpm workspace and setup guide.

Orca contributors

GitHub star history chart for stablyai/orca

Signed Builds

Windows code signing sponored/provided by SignPath.io, certificate by SignPath Foundation.

License

Orca is free and open source under the MIT License.

S
Description
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
Readme MIT
1.9 GiB
Languages
TypeScript 95.1%
JavaScript 4.1%
Swift 0.2%
HCL 0.2%
CSS 0.1%