* refactor(ai-vault): group scanner modules by defining owner
* refactor(ai-vault): consolidate owner imports and isolate path absence
* Preserve mobile CI triggers for extracted absence predicate
Select each child's workflow state in the issue detail query and render
a colored state dot plus the state name on every sub-issue row. Rows
without a state (older servers, sub-issues created locally before a
refetch) render as before.
Fixes#41348
* fix(computer): stop echoing written text and secure read-backs in action results
* fix(computer): treat a truncated set-value read-back as unverifiable
* fix(computer): accept code-point truncated read-backs as unverifiable
* fix(workspace-cleanup): warn before deleting a workspace's ignored local files
git worktree remove deletes ignored files such as .env and local config,
and git status never reports them, so cleanup showed "Clean git" and the
delete dialog said nothing. Read them with a bounded ls-files listing,
skip regenerable output, symlinks and byte-identical copies of the main
checkout, and surface the rest as an approval-only cleanup blocker and a
warning in the delete confirmation.
* fix(workspace-cleanup): show an unchecked warning when the ignored-files check fails
* style(workspace-cleanup): format merged fact status list
The cleanup scan ran only in desktop main over its own saved repos, so
workspaces on a paired server or an SSH host's orcad never showed up, and an
SSH host's retained source rows showed as "Remote unavailable" even while its
orcad served them.
Each host now runs the same scan over the repos it owns through a new
workspaceCleanup.scan RPC. The dialog merges every known host's answer,
names remote rows by this window's runtime host id so removal goes through
the existing worktree.rm route, cancels remote legs with their scan id, and
builds "Remote unavailable" rows from its catalog only when a host can't be
reached. Desktop main scans only the repos it shows.
* feat(plugins): Featured and Newly added rows in the plugin catalog
Featured shows the most installed plugin per category; Newly added lists plugins
by the catalog's new entry-level addedAt (hidden when no catalog dates entries),
with a New badge for 24h and an Added this week filter. Snapshots move to a v3
cache key so older builds never read addedAt.
* feat(plugins): derive Newly added dates from release dates, as the website does
Drops the catalog-level addedAt field (schema, docs, v3 snapshot key). Main now
estimates a listing date for each non-official plugin from its oldest dated
release, and the Newly added row, New badge and This week filter read it through
shared helpers that mirror orca-site's pluginNew.ts: 30-day window, newest first,
dates more than an hour in the future ignored, "just now / N hours ago / N days ago".
* feat(plugins): show nine Newly added plugins, drop the counts release dates inflate
Listing dates come from each community plugin's oldest kept release, and
catalogs keep only recent releases, so almost every plugin looks new: 181
of 182 fall in the 30-day window and 142 count as this week. Remove what
that inflates rather than flag it: the "N this week" count and its See all,
the This week filter, and the 24h New badge.
The Newly added row now offers the website's nine in the catalog's normal
wrapping grid, the same columns and card widths as the catalog groups.
* fix(plugins): pick Featured winners by every kind a plugin belongs to
Featured used only a plugin's first filter kind, while the category filters
count every kind, so category order could change winners or drop a kind's only
candidate. Each plugin, walked by installs with a key tie-break, now fills one
unfilled kind it belongs to (the one with the fewest candidates left, then by
name). Also note why Featured is a capped one-row teaser and pin the cap.
* fix(plugins): hide Featured when Newly added is empty
Without Newly added, Featured sat directly on the Official catalog, whose
leading cards are the same popular plugins in the same columns, so back-to-back
rows repeated and read as a render bug. Featured now shows only alongside
Newly added. Leaving featured plugins out of their catalog instead would move a
card into the catalog the moment it's installed and skew the catalog's N of M.
Adds a PluginManager test that no plugin card shows twice in the empty state,
and page-level fixtures (390, 600, 1440, empty 1440) for screenshots.
* fix(plugins): cap Newly added at two full rows of the current columns
At phone width nine stacked cards pushed the catalogs about 3.5 screens
down. The grid now shows two full rows of its container-query column
count (8 at four columns, 4 at two, 2 at one), hides a partial last row,
and the pick renders at most eight. Hidden plugins stay listed in their
catalog group, so there's no See all.
* Correct plugin catalog fixture evidence
* Make plugin highlight tests match observable behavior
* fix(sidebar): keep the session name first on a monitoring agent row
Leading with "Monitoring background tasks" made every monitoring row in a
narrow sidebar truncate to the same text. The row's dot already draws the
monitoring glyph, so the status can trail the name like every other state.
* fix(agents): keep a monitoring child row's name first too
Sub-agent rows (desktop sidebar, chat strip and mobile) share one lead/trail
rule that also put "Monitoring background tasks" before the name.
Monaco falls back to brackets for auto-closing, so a plugin bracket up to 128
characters was typed into the file as you type. The shared schema now fills in
autoClosingPairs with the brackets that pass the 8-character typed-pair rule.
* feat(workspace-cleanup): mark merged and unchanged workspaces from git evidence
Squash-merged branches whose remote was deleted were flagged as unpushed
and needed a forced delete. The scan now reads what HEAD holds beyond the
workspace's base (ancestor, Git's squash proof, or a cached merged PR) and
reports merged/unchanged reasons; landed commits no longer count as at risk.
A gone upstream no longer hides unpushed commits. Renames idle-clean to
inactive and drops the dead tier, selectedByDefault and volatile-local-context.
* fix(workspace-cleanup): read HEAD once, skip a reused branch as its own base
Merge evidence now compares the cached PR and the base against the HEAD it
reads, not the listing's possibly stale one; a workspace opened on an
existing branch no longer counts that branch as its base; the proof
wrapper settles the WSL route before building its caches; a visit keeps
merged/unchanged reasons; landed rows stop sorting as unpushed.
* fix(workspace-cleanup): qualify base refs and trust the branch proof only for HEAD
Base refs resolve through the worktree base-ref qualifier so a tag cannot
shadow them and only the branch's own family is skipped, including the
repo default; SHA-256 pinned commits are not bases; the squash proof runs
only while the branch ref is the HEAD just read; expanded details stop
counting landed commits as unpushed.
* test(workspace-cleanup): build the repo fixture without a cast
* fix(workspace-cleanup): never take a tag as a workspace's base
* fix(agent-hooks): keep the Claude session model on later hook status
SessionStart reports the model, but the Claude handler dropped it, so the
mobile composer chip stayed on "Model". Publish that model and retain it
when later lead and child events omit it.
* fix(agent-hooks): keep the Claude model across an Orca restart
Claude reports its model only on SessionStart. After a restart the listener's
lead state is empty, so the next hook dropped the saved model from the row.
* test: run the Claude model restart test in the node pool
* fix(agent-hooks): keep the Claude model when a terminal status row lands first
* refactor(agent-hooks): read the Claude lead model once to keep claude-events under the line limit
---------
Co-authored-by: Kelvin Amoaba <97001695+AmoabaKelvin@users.noreply.github.com>
* feat(agent-picker): fold legacy models the same way in every model picker
Claude aliases whose versioned model is listed, and Codex models superseded
in their family or by a newer major line, fold under Legacy models in the
agent launch picker, text-generation pickers, and native chat on desktop and
mobile. The default and current model always stay listed.
* feat(agent-picker): expand legacy models in place instead of a separate list
* feat(source-control): fold legacy models in the action model menu
* fix(agent-picker): keep model rows keyed across sections; let launch search find legacy models
* fix(agent-picker): keep rows in place while picking; classify each model catalog once
Legacy membership no longer depends on the selected model; a picker opens the
legacy section when the current model is in it. Classification is one pass and
cached per catalog, so streamed chat renders don't reclassify an unchanged list.
Typing on a closed Select no longer swallows its next close.
* fix(agent-picker): reopen menus with the current legacy model shown; PTY chats classify their discovered list
* test(agent-picker): wait on the menu instead of sleeping
* fix(agent-picker): keep the Legacy models row last, expanding older models above it
* fix(agent-picker): label the folded section More models, matching mobile
* perf(orchestration): read released worker output from its original instead of a saved copy
* fix(orchestration): keep refusal codes on released chat reads and locate legacy remote transcripts
* test(orchestration): prune flaky-pattern baseline for removed archive tests; guard a cursor read
* fix(orchestration): keep locator fields when stripping copies; never let the optional receipt page block remote release
* test(orchestration): drop removed archive tests from the node-runtime test list
* refactor(orchestration): drop the background strip; old rows keep their saved copy and its reader
* fix(orchestration): give reference rows the empty copy fields older Orca reads, with a note
* test(orchestration): give the slow-exit release mock a stored archive body
* fix(orchestration): record a transcript reference only for agents the reader can open
Liquid's {% comment %} / {% endcomment %} were dropped by hosts and refused by
validate:plugin. Comment markers are only inserted by Toggle Comment, so they
share the 128-character printable one-line rule with brackets; typed pairs keep 8.
* feat(wsl): turn WSL hosts on by default; ORCA_INTERNAL_WSL_HOSTS=0, false, off or no turns them off
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(wsl): review follow-ups for WSL hosts on by default
- Off words also match when quoted (cmd.exe's set NAME="0" keeps the quotes).
- The refusal now says WSL hosts are turned off for this launch, not missing from the build.
- New preload test pins when the renderer gets the WSL hosts API.
- Unit tests no longer inherit the gate state an Orca terminal publishes.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Two merges each added lines to global-settings-types.ts and pushed it past
the 300-line cap on main. Move workspaceCleanupPolicy into a group owned by
the workspace cleanup policy module, composed through GlobalSettingsBase like
the other feature settings. No behaviour change.
The site now lives at orca.dev; the old onorca.dev and www.onorca.dev hosts
redirect there. Linking to orca.dev directly skips that redirect.
Only page links change. Service hosts, sign-in and relay endpoints stay as they are.
* chore(endpoints): call orca.dev for feedback, plugin lists and update notes
The site moved to orca.dev. Feedback, connection diagnostics, plugin install
stats, the plugin kill list, update nudges and the changelog feed now use
orca.dev, as do the diagnostics token URL baked into builds and the release
download mirror (downloads.orca.dev). The old hosts serve the same paths,
so released builds keep working.
Skill share links on share.orca.dev are accepted, and the mobile scanner
recognizes the orca.dev Android download code. The old hosts stay accepted.
* chore(ci): leave the release JavaScript benchmark workflow unchanged
Editing it triggers the benchmark, whose parity check currently fails on
arm64 because max-quality brotli output for the mobile page differs by
architecture. The benchmark only needs some diagnostics URL, and the old
host still serves it.
The Agents list titled a thread with the tab's generated title, the first
prompt that tab saw. After `claude --resume` in a new tab, that is the
message sent after the resume, so the list kept a status note as the
thread's name while the tab and the agent row showed the session's own
name. Rank a named provider title of the pane's own session above the
generated title, as resolveTabNameSource does, and share the session
ownership check with the agent row.
Adds off-by-default workspace cleanup rules (merged, unchanged, inactive,
automation runs, orchestration workers, keep-when) to global settings and
an inherit/off/custom override on each repo. resolveWorkspaceCleanupPolicy
is the single source of truth for the coming background runner, and the
rules are exposed to paired clients through settings.get/settings.update.
No UI and no behaviour change yet.
* feat(orchestration): let coordinators approve worker permission prompts when the user turns it on
One setting on the orchestration page, off by default. When on, the
escalation offers orchestration approve and deny, both with a reason, and
the user still sees Allow/Deny: the first answer wins. A prompt the
worker's agent lets only a person approve is refused and stays with the
user. The machine running the worker enforces its own setting.
* fix(native-chat): a worker approval's receipt shows the command, not its tool input as JSON
* test(orchestration): list every worker-side case in the coordinator approval table
* chore(i18n): ship the coordinator approval setting's search keywords in the runtime catalog
* fix(orchestration): a reasonless allow keeps the person's refusal, and terminal checks no hook may approve are person-only
* fix(orchestration): address review on coordinator approvals
- A person-only chat prompt answered meanwhile reports as closed.
- A terminal allow reads Claude's warning from the screen it checks, so a
late-painted person-only warning still refuses before the hook is used.
- The receipt keeps a chat worker's whole command.
- orchestration approve prints the reason it sent.
* fix(native-chat): read the receipt's command through a parsed shape, not Reflect
* docs(skills): drop worker permission prompt guidance; the escalation carries it
Pi 1.5.1+ shrinks every image it is sent, including mid-turn ones; older Pi
sends steered images as given, so it keeps a 3.75 MiB (5 MB base64) cap.
Part of #37005
* fix(orchestration): label follow-up worker cards, gate remote-owned start cards on ready
A send that continues a finished or closed worker starts a follow-up Dispatch,
and the coordinator's chat showed it as "Started worker". The agent-start item
now carries the Dispatch it followed and whether the conversation reopened, and
the card reads "Reopened worker" or "Sent follow-up to worker".
worker-start --on a server that owns its workers wrote the card for any parsed
answer, with no agent kind. It now passes the started agent and writes the
card only once the server readied the worker, as local and attached starts do.
* test(native-chat): assert follow-up heading kind, not its copy
* feat(settings): move Remove project to a confirmed row at the bottom of Project Settings
* chore(i18n): sync protected copy keys for the remove-project dialog
* fix(settings): use primitive variants in the remove-project disclosure and dialog
* fix(settings): keep remove-project row off the per-write store path
The terminal count now lives in a dialog-only component, and the VM-recipe check is
memoized on worktree/runtime identity. Checkouts are grouped by host id, SSH labels
resolve through the setup's runtime owner, and a runtime missing from the catalog
shows as Unknown host instead of its raw id.
* fix(settings): select only the removed repos' worktree lists
Selecting the whole worktreesByRepo map re-rendered the remove-project row on every
other repo's worktree write. Also drop the orphaned terminalCount catalog keys.
* fix(settings): count remove-project terminals once on open; hide raw SSH ids
The dialog's terminal warning reads the count when Remove… is clicked instead of
subscribing, so no store write walks tabs. An SSH host with no label now shows as
Unknown host like an unlisted runtime, since generated target ids mean nothing to users.
* fix(settings): re-check terminal count before removing a project
A terminal opened from another client while the confirm dialog is up would close
without warning. Confirm now re-reads the count and, if it grew, updates the warning
and waits for a second confirm.
* test(settings): build remove-project fixture setups without a type assertion
* test(settings): cover the remove-project confirm holding for new terminals
* test(settings): drop the copy assertion from the remove-project confirm test
Agent reload treated did-fail-load as success, so it returned ok while the page showed a network error page; it now reports the page's load error like goto. A restored page stopped before its first commit holds only Chromium's initial empty entry, so native reload did nothing: the Reload button now navigates to the saved URL, and agent reload fails fast instead of waiting 10s and claiming success.
* fix(runtime): hold tui-idle until a cold-starting Claude has painted (STA-2380)
A shell auto-title (oh-my-zsh preexec) names the pane `claude` the moment
the command execs. Claude's `idle_title` rule counts that bare name as weak
idle once output has been quiet for 3s, so a Claude that took >3s to draw
its first frame settled `terminal wait --for tui-idle` on a blank screen.
`dispatch --inject` then pasted into a TUI that had not mounted yet and the
prompt was lost.
Name-only idle lanes (agent rule verdicts that require quiet, and the
sustained-title lane) now also require that the running command has painted
something since the shell's OSC 133;C command-start marker. Shells without
the marker keep today's behavior.
* fix(runtime): corroborate Claude's name-only idle with its own composer marker (STA-2380, C1 F1)
Orca's zsh OSC 133;C hook is first in preexec_functions, so a later user or
framework preexec hook (zsh-you-should-use, a custom echo) prints after the
command-start marker and before Claude runs. The any-visible-byte paint latch
counted that text as Claude's paint, so a silent cold start under such a hook
still settled tui-idle ready-weak on the shell's bare `claude` title.
For agents whose worker start already trusts their composer marker (Claude),
"painted" now means that marker (`❯`+NBSP after DECSET 2031, which no shell
sends) arrived since the command started. Other agents keep any-byte paint;
markerless shells and output gaps keep the permissive default.
Evidence: a real-zsh live-shell test under the production wrapper with
oh-my-zsh title-only, p10k/starship-style silent, and you-should-use-style
printing hooks, replayed through the real wait; runtime tests for the hook
text, a boot banner, the positive bare-title + composer path, and worker-start
readiness plus brief delivery timing.
* fix(ci): route command-paint attribution sources to shell_contracts; attribute live-shell bytes by stream offset (STA-2380, C2 F1/F2)
- pr-shell-contract-prefixes: the live-shell test, terminal-command-paint.ts,
tui-idle-evidence-source.ts and draft-paste-ready-scanner.ts route to the
shell_contracts job; a routing test reads the job's step from pr.yml and
asserts every listed test routes there.
- tui-idle-zsh-preexec-hook-order.live-shell.test: locate the DECSET 2031
anchor by offset in the accumulated stream, split a straddling read, carry
pending escapes across the shell/agent halves, and assert attribution is
invariant under coalescing and 3-byte re-chunking.
- terminal-command-paint: disclose the accepted trade-off (a known Claude with
marker history but no supported composer signal times out; markerless shells
and output gaps still fail open; no version cutoff claimed).
* test(ci): stream-offset launch-order proof, route tui-idle-evidence.ts, parse the whole shell-contracts step (STA-2380, C3-1/2/3)
- live-shell test: assert the launch order on the joined bytes by stream
offset (133;C, then the user hook's output, then the agent's anchor and
composer); no read-boundary or timestamp assertions remain. Re-chunk
cases add a split anchor and a shell-tail/agent-start coalesced read.
- pr-shell-contract-prefixes: route tui-idle-evidence.ts, the readiness
evaluator the live-shell replay exercises.
- routing ratchet: read the step's run script through the YAML parser so
a blank line or later command cannot truncate it; cross-check against
the real-shell tests UNIT_EXCLUDE drops so a dropped entry fails rather
than a smaller count; fixture tests for blank line, exact list, missing
step.
* test(ci): answer compinit's insecure-directory prompt in the zsh preexec live-shell test (STA-2380)
Ubuntu's global zshrc runs a plain compinit, which on CI runners stops at
"Ignore insecure directories and continue [y] or abort compinit [n]?"
before zle exists, so the stand-in never launched and the shell-contracts
job failed with "no composer frame from the stand-in". Answer the prompt
with y as zsh-startup-hook-pty-harness.ts does. The prompt bytes precede
Orca's OSC 133;C marker, so stream-offset attribution is unchanged.
* Revert "Make chat wait check the chat's work state instead of reading its history every second (#41129)"
This reverts commit 9a10464bec.
* Revert "feat(cli): read, message and wait on agent chats with orca chat list/read/send/wait (#40836)"
This reverts commit c2e6ebbf0b.
* revert: worker permission approvals (#40756)
This reverts commit 818055fcbb.
The feature misbehaves in real use: an Allow on a worker's approval card
was recorded as closed without an answer, and closed approval cards render
at the bottom of the coordinator chat, below newer messages.
Removed: the Claude PermissionRequest hook hold and its 130 s timeout,
the approval card in the coordinator chat, `orchestration deny`, the
approval payload on stop escalations, and the held-delivery lines on send
receipts. Escalation text goes back to its pre-#40756 wording.
Kept from later commits:
- #40983 (lost-worker alerts): its `lost` reason, cause/leftover/settled
fields, turnStartedAt and the rejected-report check stay; only the
approval branches around them are removed.
- #41158 (owner moves) and the test cleanups (#41151, #41175, #41177)
only touched approval code that is now deleted.
* feat(orchestration): answer workers' permission prompts from the coordinator (re-land of #40756)
* fix(orchestration): credit an approval from Claude's own decision record and place each worker card at its time
- An Allow that Claude took is answered by the person even when the command then fails or is still running; a failed command's PostToolUseFailure counts as ran.
- Expired means the agent's own timeout only; a close Orca can't name is not an expiry, and reasonDelivered is true only with a reason.
- Escalations wait for the dialog to paint and read Claude's warning even when a long command hides the top of its box.
- Worker cards and receipts render after the message they followed in time, not after the whole conversation; the toast says what happened.
* fix(native-chat): place timed rows without a memo the compiler skips
* perf(orchestration): feed chat approvals from their own stream, pin open cards, close cards whose worker ended
Native chats no longer subscribe to the crew stream for worker approvals. A
narrow orchestration.workerApprovalsSubscribe stream per chat party wakes only
on that party's own mail and on Run/Dispatch changes, never on agent status,
and reads the crew only when the approval list itself changes. The pane no
longer redraws for approvals: the transcript receipts and the pinned stack
each hold the feed themselves.
Open worker prompts are pinned above the composer (above the chat's own
prompt), oldest first, in a bounded scrolling stack; the transcript keeps only
receipts, at the time the worker asked. The countdown ticks only for open
cards in a visible pane.
An approval whose Dispatch is no longer running reads as closed ("No longer
open · worker ended"); a hook that hangs up after its worker is gone closes as
worker-ended rather than "answer it in the terminal"; and a click that finds
the prompt or Dispatch already gone turns the card into its receipt at once.
Also carries over: a stop owes a closing line only to an approval whose
escalation went out.
* fix(native-chat): no toast when a worker approval answer lands; the card's receipt says it
* fix(native-chat): a worker approval card answers on click, as the chat's own prompt does
The card turns into 'Allowed by you' at once and Claude's confirmation runs behind it; only an answer
Claude did not take changes it to the real outcome, and a failure reopens the card.
* fix(orchestration): keep main's stop-report index for the open-approval sweep after the re-land
* fix(orchestration): final-review fixes for chat worker approvals
- A click that gets approval_not_open no longer hides the card: the host's list decides, so a
prompt the host still holds stays answerable. Only dispatch_inactive closes it locally.
- The approvals stream watches only the orchestration database's own changes (Runs, Dispatches,
mail), not terminal identity notices, so agent status and title changes cost it nothing in main.
- Receipts are the chat's history: no 30-minute window, bounded by 100 rows with still-open
prompts kept first.
- The pinned stack is capped against the pane and gives way first, so the chat's own prompt keeps
its room; a prompt that closes while shown stays pinned as its receipt for 4 s, and one only the
worker's terminal can answer stays pinned.
- A close no one named, after the worker's Dispatch ended, reads as worker-ended, and an
unanswered close of an ended worker sends the coordinator no second notice.
- The transcript's receipts keep one array until a receipt changes.
* refactor(native-chat): a worker approval card waits on the host after a click instead of answering ahead of it
Both buttons turn off and the clicked one shows a spinner until the answer returns; the host's list
then turns the card into its receipt. Drops the client-side close and its reconciliation.
* fix(native-chat): let the compiler memoize the worker approval answer handler
* perf(orchestration): stop coordinator check and worker-list from rescanning Run history
- check: the empty-check hint projects only workers that can still be running or owe an action
- worker-list: later pages reuse the first page's inventory counts from the cursor
- check: read completion reports for follow-ups in one query
- outstanding-delivery lookups and the worker seat-grab check use their indexes
- hot by-id lookups name their columns so prepared statements are cached
- stop-archive checks archive existence without reading the archive
* fix(orchestration): judge the check hint per worker-list page and tie carried counts to their filter
* fix(orchestration): reuse carried worker-list counts only for the same Run scope
* perf(orchestration): find empty-check hint candidates through indexes and refresh the stale delivery trigger
* perf(orchestration): read only the worker-list pages that hold hint candidates
* perf(orchestration): look up page owners through indexes instead of reading pages
* perf(orchestration): batch hint candidate positions and join pages that share no identity
* perf(orchestration): keep creator hand-back lookups on the creator index
* Move local usage services into a supervised backend process
* Own usage recovery and worker retirement lifetimes
* Preserve answered usage data during background refresh
* Run independent usage scans concurrently in the backend
* Limit backend startup paths to the delegated usage service
* Show usage failures through backend recovery
* Include usage failure strings in the English catalog
* Keep usage update details beside refresh failures
* Resolve usage freshness failure from the final producer snapshot
* Retain the forced refresh completion requirement
* Keep managed backend failures out of application crash reports
* Preserve usage recovery boundaries across backend reconnects
* Match the backend RPC cancellation signal in the usage seam proof
* Avoid serializing backend requests before port delivery
* Keep receiving request validation in the boundary schemas
* test: align usage transport coverage with renderer project
* fix: preserve unknown usage state and renderer retirement
* fix(usage): revalidate tracking before scan admission
* fix(usage): retry failed backend startup on demand
* test(usage): isolate stale backend ownership checks