Jinwoo HongandOrca ea8ea08116 feat(orchestration): bundled improvements — check-wait, stale-base, preamble+ask, QoL (#1403)
* feat(orchestration): transport keepalive + delivered_at split for check --wait

Implements the four §3 fixes from the check-wait design doc:

- §3.1 Transport keepalive: long-poll RPCs (orchestration.check --wait) emit
  `{"_keepalive":true}` frames every 10s so neither server nor client tears
  the socket down on idle. A `longPoll` admission counter capped at 16 fails
  fast with `runtime_busy` when saturated; an AbortController wired through
  the RPC dispatcher cancels the inner waiter the moment the socket closes.
- §3.2 delivered_at split: push-on-idle now stamps `delivered_at` instead of
  flipping `read`, so the check caller remains the sole consumer of its
  queue. Adds a synchronous idempotent schema migration that hard-fails on
  error.
- §3.3 inbox/check parity: `orchestration inbox --terminal <handle>` and
  `orchestration check --all` agree on the same rows (sequence DESC, no
  mark-read). `check --unread=false` kept for one release as a compat shim.
- §3.4 CLI heartbeat: `orca orchestration check --wait` emits JSON heartbeat
  lines to stderr every 15s so Claude Code's Bash tool sees continuous
  output and doesn't auto-background the subprocess.

Tests: extends runtime-rpc, orca-runtime, envelope-schema, orchestration
method, and formatter suites; adds a subprocess test that spawns the built
CLI and verifies stderr line-flushing, heartbeat cadence, and stdout
cleanliness end-to-end.

Co-authored-by: Orca <help@stably.ai>

* feat(orchestration): preamble rules + heartbeat schema

- Preamble (#7, #15, #9): worker_done body ("3-sentence summary" + reportPath),
  BEHAVIOR RULE #1 forbidding AskUserQuestion, heartbeat every 5 minutes with
  taskId+dispatchId payload, AFTER YOU SEND grace window.
- Schema v2 migration: adds 'heartbeat' to messages.type CHECK, adds
  dispatch_contexts.last_heartbeat_at, gated by user_version PRAGMA with
  transactional rebuild + explicit CREATE INDEX to avoid silent perf regress.
- DB helpers: recordHeartbeat (dispatched-only), getStaleDispatches,
  getThreadMessagesFor (thread+handle scoped for ask).

Co-authored-by: Orca <help@stably.ai>

* feat(orchestration): coordinator heartbeat + stale detector

Handle incoming 'heartbeat' messages by calling recordHeartbeat keyed on
payload.dispatchId (strict — log-and-skip if missing, no taskId fallback so
a straggler heartbeat from a previously-failed dispatch cannot mask a hung
retry per §5.3.4). On every tick after the 10-minute threshold, emit one
log per stale dispatched row — no auto-fail.

Also threads dispatchId through buildDispatchPreamble so workers can
attribute their heartbeats back to the correct dispatch context.

Co-authored-by: Orca <help@stably.ai>

* feat(orchestration): orca orchestration ask verb

Adds a CLI verb that sends a decision_gate message and blocks on the
coordinator's reply, scoped to the outbound message's thread. Group
addresses (@all, @idle, …) are rejected — fan-out questions must use
send --type decision_gate explicitly.

--json emits bare single-line JSON (bypassing printResult) so workers can
pipe `orca orchestration ask … --json | jq -r .answer` without unwrapping
an RPC envelope; human mode prints just the answer. On timeout the verb
exits 1 and returns {answer: null, timedOut: true}.

This is the CLI surface BEHAVIOR RULE #1 in the dispatch preamble points
workers at instead of AskUserQuestion.

Co-authored-by: Orca <help@stably.ai>

* feat(orchestration): QoL bundle — preamble visibility, status enum, dispatch cross-ref, inbox --full

Addresses four items from ORCHESTRATOR_FEEDBACK:

- #5 preamble visibility: `dispatch-show --preamble` regenerates the preamble
  text for a task; `dispatch --inject --dry-run` previews without mutating
  state; `dispatch --return-preamble` echoes the injected preamble in the JSON
  response so coordinators can audit what a worker received.
- #6 status enum validation: CLI rejects unknown `task-update --status` values
  with `invalid status '<x>', expected one of: pending, ready, dispatched,
  completed, failed, blocked` before the RPC's generic Zod message. Valid
  statuses are listed under Notes in `task-update --help`.
- #13 task-list dispatch cross-ref: `task-list --json` now includes
  `assignee_handle` and `dispatch_id` for tasks in status=dispatched via a
  read-only LEFT JOIN on dispatch_contexts. Non-dispatched rows keep their
  legacy shape so existing consumers are unaffected.
- #14 inbox body visibility: `inbox --full` prints body + payload verbatim;
  default output is unchanged (id/from/to/subject only).

No DB migrations; join-only change on dispatch_contexts so the sibling
preamble PR's `last_heartbeat_at` column addition will not conflict.

Co-authored-by: Orca <help@stably.ai>

* fix(worktree): prevent stale-base worktree creation and dispatch

Addresses feedback #16 per DESIGN_DOC_STALE_BASE_FIX.md §0. Four v1
components coordinated by a single shared fetch cache on the runtime:

1. Concurrent-fetch-with-gate in UI create path: `createLocalWorktree`
   fires `git fetch` BEFORE the suffix loop / PR probe / path
   resolution, then awaits right before `addWorktree` so the new branch
   always spawns from a fresh remote tip. Renderer sees a two-phase
   spinner via the new `createWorktree:progress` IPC event. The cache
   is a `Map<repoPath::remote, Promise<void>>` + 30s success-only
   timestamp on `OrcaRuntimeService` (§7.1 — shared with dispatch).
2. Dispatch pre-flight drift guard in `Coordinator.dispatchTask`:
   probes `rev-list --left-right --count` against the target worktree
   and silently returns (preserves `ready`, no circuit-breaker burn)
   when `behind > 20` unless the task spec carries
   `allow-stale-base: true`. Parsing strips the flag so it never leaks
   into the worker's `--- TASK ---` block.
3. Preamble drift section: populated only when dispatch detected drift.
   Workers see `--- BASE DRIFT ---` with the N-most-recent subjects
   they don't have, so they can pull them in before running.
4. §3.3 Lifecycle: `.finally()` evicts Map entries on BOTH success and
   rejection; timestamp is written ONLY on success. Prevents a single
   DNS hiccup from wedging every future create on the repo until
   restart, and keeps the freshness window honest.

Defers the DB `allow_stale_base` column (§0.2) and the create-time
warn toast; both can layer in later without migration.

Tests: 35 new/updated unit tests covering drift preamble, dispatch
refusal, spec-text flag parsing, fetch Map eviction after rejection,
freshness-window short-circuit, and concurrent-caller serialization.

Co-authored-by: Orca <help@stably.ai>

* test(orchestration): seed v2 DB in migration hard-fail test

After consolidating the schema bump, fresh DBs are initialized directly at
v3 via createTables(), so the v2→v3 ALTER TABLE is skipped on new installs
and the prior test's stub never fired. Seed a v2-shape file on disk so the
guarded ALTER actually runs and the "simulated migration failure" stub
propagates as intended.

Co-authored-by: Orca <help@stably.ai>

---------

Co-authored-by: Orca <help@stably.ai>
2026-05-04 12:10:53 -07:00
2026-04-06 23:32:45 -07:00
2026-03-16 22:27:51 -07:00
2026-03-28 10:19:14 -07:00

Orca Orca

Supported Platforms Discord Follow on X

English · 中文 · 日本語 · Español

The AI Orchestrator for 100x builders.
Run Claude Code, Codex, or OpenCode side-by-side across repos — each in its own worktree, tracked in one place.
Available for macOS, Windows, and Linux.

Download 🐋

Orca Screenshot

Supported Agents

Orca supports any CLI agent (not just this list).

Claude Code   Codex   Gemini   Pi   Hermes Agent   OpenCode   Goose   Amp   Auggie   Charm   Cline   Codebuff   Continue   Cursor   Droid   GitHub Copilot   Kilocode   Kimi   Kiro   Mistral Vibe   Qwen Code   Rovo Dev


Features

  • No login required — Bring your own Claude Code or Codex subscription.
  • Worktree-native — Every feature gets its own worktree. No stashing, no branch juggling. Spin up and switch instantly.
  • Multi-agent terminals — Run multiple AI agents side-by-side in tabs and panes. See which ones are active at a glance.
  • Built-in source control — Review AI-generated diffs, make quick edits, and commit without leaving Orca.
  • GitHub integration — PRs, issues, and Actions checks linked to each worktree automatically.
  • SSH support — Connect to remote machines and run agents on them directly from Orca.
  • Notifications — Know when an agent finishes or needs attention. Mark threads unread to come back later.

Install

Mac, Linux, Windows

Alternatively, install from a package manager:

macOS (Homebrew)

brew install --cask stablyai/orca/orca

Arch Linux (AUR)

# Precompiled binary
yay -S stably-orca-bin

# Build from GitHub source
yay -S stably-orca-git

[New] Annotate AI Diff

Comment directly on AI-generated diffs.

Annotate any line in an AI-generated diff with your feedback, then send it back to the agent to revise. Keep the review loop tight — no copying line numbers, no context switching.

Orca Annotate AI Diff — comment on AI-generated diffs and send feedback to the agent


[New] Hot Swap Codex Accounts

Multiple Codex accounts? Switch in one click.

If you run multiple Codex accounts to get the best token deal, Orca lets you hot-swap between them instantly — no re-login, no config files. Just pick an account and keep building.

Orca Codex Account Switcher — hot swap between multiple Codex accounts


[New] Per Worktree Browser & Design Mode

See your app. Click any element. Drop it into the chat.

Orca ships with a built-in browser right inside your worktree. Preview your app as you build, then switch to Design Mode — click any UI element and it lands directly in your AI chat as context. No screenshots, no copy-pasting selectors. Just point at what you want to change and tell the agent what to do.

Orca Design Mode — click any UI element and drop it into the chat


[New] Introducing the Orca CLI

Agent orchestration from your terminal.

Let your AI agent control your IDE. Use AI to add projects to your IDE, spin up worktrees, and update the current worktree's comment with meaningful progress checkpoints directly from the terminal. Ships with the Orca IDE (install under Settings).

npx skills add https://github.com/stablyai/orca --skill orca-cli

Community & Support

  • Discord: Join the community on Discord.
  • Twitter / X: Follow @orca_build for updates and announcements.
  • Feedback & Ideas: We ship fast. Missing something? Request a new feature.
  • Show Support: Star this repo to follow along with our daily ships.

Developing

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

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
1.5 GiB
Languages
TypeScript 95.1%
JavaScript 4.1%
Swift 0.2%
CSS 0.2%
HCL 0.1%