Lataa Orca 1.4.204

Thank you so much for using Orca and for your continued support! ❤️
Please note: It usually takes 48–72 hours for a landed PR to be released (except P0+ fixes). We have many more exciting PRs and features coming in later versions!
The short version
Agents & chat: Native chat adds file drag-and-drop and provider-aware Fast mode, resumes structured chats cleanly after restart, hides idle activity, and fixes tail-read cursor and Claude-turn reopening; Grok completion/hook attribution and Claude SessionEnd handling are more correct, and agent status keys rows by agent instead of pane.
Workspaces & mobile: Workspaces re-seed after agent selection, recover from activation failures, and retire orphaned chat tabs; mobile continues the typed-RPC migration across settings, source-control, and workspace creation while preserving delivery and fixing streaming jumps.
Performance: Orca batches terminal file-link checks, dispatches browser input in-process, avoids repeated remote capability probes, skips redundant persistence flushes, and bounds WSL skill discovery.

Product experience
Workspaces, tabs & browser
Safer workspace recovery, more responsive browser input, and clearer project views.
- fix(worktrees): retire the chat tab of a chat with no child when its workspace goes by @brennanb2025 in https://github.com/stablyai/orca/pull/19970
- fix(browser): press keys through a US-layout CDP key table instead of a subprocess per keystroke by @atreidesend in https://github.com/stablyai/orca/pull/15310
- fix(workspaces): re-seed a gate-reported empty workspace after an agent selection by @brennanb2025 in https://github.com/stablyai/orca/pull/20182
- fix(workspaces): recover a real terminal when activation throws for a planless agent create by @brennanb2025 in https://github.com/stablyai/orca/pull/20190
- fix(github): name an unfiltered empty project view instead of blaming a filter by @nwparker in https://github.com/stablyai/orca/pull/20588
Agents & workflow
Agent reliability & native chat
Chat adds drag-and-drop and Fast mode, recovers more gracefully, and reports agent state more accurately.
- fix(native-chat): wait for the runtime capability probe before resolving the creation launch route by @brennanb2025 in https://github.com/stablyai/orca/pull/19819
- feat(ai-vault-search): public session search contract and transports by @Jinwoo-H in https://github.com/stablyai/orca/pull/20277
- fix(tasks): preserve repository results under GitHub search quota by @OrcaWin in https://github.com/stablyai/orca/pull/20460
- fix(ai-vault): stream oversized remote session transcripts by @OrcaWin in https://github.com/stablyai/orca/pull/20455
- fix(grok): stop replayed Claude/Cursor hooks reporting Grok panes as Claude by @brennanb2025 in https://github.com/stablyai/orca/pull/20507
- feat(native-chat): support file drag and drop by @brennanb2025 in https://github.com/stablyai/orca/pull/20494
- refactor(attention): move the agent attention boundary off terminal panes by @brennanb2025 in https://github.com/stablyai/orca/pull/20525
- fix(grok): defer managed hook pane guard expansion to shell by @brennanb2025 in https://github.com/stablyai/orca/pull/20534
- refactor(orchestration): derive delivery eligibility from messages by @Jinwoo-H in https://github.com/stablyai/orca/pull/19837
- fix(grok): announce a completion once, when Grok is actually finished by @brennanb2025 in https://github.com/stablyai/orca/pull/20523
- feat(native-chat): add provider-aware Fast mode by @brennanb2025 in https://github.com/stablyai/orca/pull/20506
- fix(claude): subscribe to SessionEnd on capable versions, and correct a false comment by @brennanb2025 in https://github.com/stablyai/orca/pull/20530
- feat(agent-status): run-identity types for keying rows by agent instead of pane by @brennanb2025 in https://github.com/stablyai/orca/pull/20531
- fix(hooks): report a timed-out hook as unverifiable and terminate its process tree by @nwparker in https://github.com/stablyai/orca/pull/20559
- fix(session-search): read oversized numeric file IDs on Windows by @OrcaWin in https://github.com/stablyai/orca/pull/20551
- feat(native-chat): show a drop target on the whole chat pane by @brennanb2025 in https://github.com/stablyai/orca/pull/20561
- fix(native-chat): let the provider reopen a Claude turn it resumed itself by @brennanb2025 in https://github.com/stablyai/orca/pull/20518
- fix(native-chat): resume structured chats cleanly after restart by @brennanb2025 in https://github.com/stablyai/orca/pull/20509
- fix(ai-vault): ignore non-absolute env overrides for agent scan roots by @manuaudio in https://github.com/stablyai/orca/pull/13118
- fix(grok): stop SessionStart orca-status hook hanging for 10s by @bjornrun in https://github.com/stablyai/orca/pull/20090
- fix(native-chat): stop a bounded tail read from moving the chat cursor past unapplied rows by @brennanb2025 in https://github.com/stablyai/orca/pull/20581
- feat(ai-vault-search): construct the session search indexer in the scanner service behind a setting by @Jinwoo-H in https://github.com/stablyai/orca/pull/20516
- fix(native-chat): hide activity while awaiting input by @brennanb2025 in https://github.com/stablyai/orca/pull/20496
Mobile
Mobile continues its typed-RPC migration while keeping delivery and streaming stable.
- refactor(mobile): migrate settings reads to RpcOperation by @Jinwoo-H in https://github.com/stablyai/orca/pull/20499
- fix(mobile): give native chat one tail-follow owner so streaming stops jumping by @brennanb2025 in https://github.com/stablyai/orca/pull/20493
- fix(mobile): preserve delivery ambiguity across transport cutover by @Jinwoo-H in https://github.com/stablyai/orca/pull/20280
- test(mobile): consolidate the RPC migration's verification infrastructure by @Jinwoo-H in https://github.com/stablyai/orca/pull/20521
- refactor(mobile): send the source-control domain through typed RpcOperations by @Jinwoo-H in https://github.com/stablyai/orca/pull/20544
- fix(mobile): two known main bugs the RPC migration preserved by @Jinwoo-H in https://github.com/stablyai/orca/pull/20563
- test(mobile): pin each RPC golden to its own scenario input, not the whole manifest by @Jinwoo-H in https://github.com/stablyai/orca/pull/20562
- refactor(mobile): send the task workspace-creation domain through typed RpcOperations by @Jinwoo-H in https://github.com/stablyai/orca/pull/20568
Relay & cloud
Probes and identity validation have tighter bounds and failure handling.
- fix(rpc): validate provider-specific fields in TaskProviderIdentity by @Jinwoo-H in https://github.com/stablyai/orca/pull/20284
- fix(ssh): bound relay incumbent lsof probe by @kaluli123123 in https://github.com/stablyai/orca/pull/18304
Quality & delivery
Nothing here changes what you see — it changes how smoothly Orca behaves under real workloads. Expanded below if you want the detail.
Performance improvements
Targeted optimizations reduce unnecessary work across terminal, browser, remote, persistence, and skill-discovery paths.
Highlights include batched terminal file-link checks on their owning host, in-process browser pointer dispatch, fewer remote capability probes during file imports, skipped redundant whole-state flushes on terminal reattach, and bounded WSL skill discovery.
- perf(terminal): batch file-link checks on their owning host by @OrcaWin in https://github.com/stablyai/orca/pull/20463
- perf(skills): bound WSL installed skill discovery by @PPP-JH in https://github.com/stablyai/orca/pull/12314
- perf(remote): avoid repeated capability probes during file imports by @dngur6344 in https://github.com/stablyai/orca/pull/14555
- perf(persistence): skip redundant whole-state flushes on terminal reattach by @AmethystLiang in https://github.com/stablyai/orca/pull/20137
- perf(browser): dispatch coordinate pointer input in process instead of one subprocess per event by @nwparker in https://github.com/stablyai/orca/pull/20593
Reliability, tests & delivery
- fix(runtime): reject malformed file Base64 padding by @Jinwoo-H in https://github.com/stablyai/orca/pull/20283
- fix: show unexpected signout notice only once across versions by @Jinwoo-H in https://github.com/stablyai/orca/pull/20526
- fix(auth): report callback failures instead of cancellation by @Jinwoo-H in https://github.com/stablyai/orca/pull/20535
- fix(git): skip upstream remote probes when the remote is absent by @innocarpe in https://github.com/stablyai/orca/pull/18455
- fix(terminal): drop the agent gutter from copied selections (#19770) by @nwparker in https://github.com/stablyai/orca/pull/20545
- fix(pty): pace the EAGAIN write retry so a stalled reader can't saturate the daemon thread by @nireak in https://github.com/stablyai/orca/pull/15319
New contributors
- @atreidesend made their first contribution in https://github.com/stablyai/orca/pull/15310
- @PPP-JH made their first contribution in https://github.com/stablyai/orca/pull/12314
- @manuaudio made their first contribution in https://github.com/stablyai/orca/pull/13118
- @bjornrun made their first contribution in https://github.com/stablyai/orca/pull/20090
- @nireak made their first contribution in https://github.com/stablyai/orca/pull/15319
Full Changelog: https://github.com/stablyai/orca/compare/v1.4.203...v1.4.204