Publish the resolved replacement selection to the composer. iOS does not emit a native selection event for this edit, leaving autocomplete at the slash until the next keystroke.
* feat(app): browse, install and manage plugins from a built-in gallery
Settings → Host → Plugins becomes a gallery with two tabs. Installed lists
the host's plugins with on/off switches and pending updates. Browse lists the
plugin directory with featured cards, categories, sorting and search. Each
plugin has its own page with its screenshots, overview, details, install or
on/off controls, and its own settings screens inline.
Every install asks first, in a sheet naming the source and version, because
installing runs the plugin's code on the host. Uninstalling also asks first;
its confirm says what is deleted.
The daemon fetches the directory from its configured registry
(plugin.registry.list/get, gated by server_info.features.pluginRegistry). The
app never fetches from the registry itself, so a host with a private registry
shows that registry.
README overviews render with the registry's overview contract (the same one
the website uses): only https links and images work, and nothing is read as a
workspace file. Before this, a word like "Node.js" became a broken relative
link.
* fix(app): refresh plugin failures and leave Settings cleanly from a plugin page
The Installed row read the app-side evaluation error without subscribing to the
registry, so a plugin fixed by Reload kept its "failed" badge. Rows and the
plugin page now subscribe through usePluginEvaluationError.
Leaving Settings with no remembered workspace replaced only the top stack entry;
with a plugin page pushed on top, the Plugins list stayed mounted underneath and
reopening Settings stacked a second copy. Dismiss the Settings entries first.
* fix(app): keep Browse working as the registry grows, and test it end to end
Registry listings now reach apps through an open wire schema
(plugin.registry.list/get carry PluginListing*), and the daemon drops a listing
it cannot read instead of failing the whole index. A registry that adds an
artifact kind or bumps schemaVersion no longer breaks Browse on older apps.
The gallery picks its opening tab once, so installing the first plugin keeps
the user on Browse. README links open only https: the parser still autolinks
bare http, www and email text, so a press checks the URL again.
Adds a Browse e2e test against a local registry and Git repository: install
from a row through the confirm sheet, stay on Browse, open the listing page,
uninstall from it.
* test(server): give the oversized-sibling diff refresh the same time budget as its siblings
expect.poll defaults to one second, which a Windows git diff refresh can exceed.
* test(server): wait as long as the other observer tests for native watcher events
expect.poll defaults to one second; macOS FSEvents can deliver later than that on CI.
* fix(app): keep a listed plugin's page usable after uninstalling it, and fetch the directory less
An installed plugin's page finds its listing through the plugin, so uninstalling
a directory plugin from the Installed tab left "not installed or listed" with no
way back. The page now becomes the listing's page, offering Install again.
Updates are re-checked when the host's plugins change and after a failed update,
whose proposal named a revision that no longer exists. The directory, listing
and update queries refetch on mount only once stale, so opening a plugin's page
no longer refetches the whole directory and every update check.
* test(app): install the plugin before opening Plugins in the busy-queue reload test
Plugins opens on Browse when the host has no plugins and stays there after the first install, so a plugin installed through the daemon after the page opened never showed on Installed.
* test(website): wait for hydration before scrolling to the hero in a short window
The router resets the scroll position when the page hydrates. Scrolling to the mockup before that left it below the window, so its start line never came on screen and the opening scene never played. It failed 7 of 10 runs on webkit.
* fix(server): show the registry setup error on Browse instead of asking to retry
The registry's request headers were built inside the try around fetch, so a setup error such as credentials over plain HTTP came back as "Could not reach plugin registry. Retry later." Install already built them first.
* fix(app): show plugin errors without the request details meant for logs
A daemon RPC error's message ends with requestType=… code=…; the daemon's own text is in userMessage. Gallery alerts and toasts now show that text.
* fix(app): show why an update failed on the plugin's page
The update operation's failure was recorded under the plugin ID, but the page only read it to show the spinner, so a failed update looked as if nothing happened. The page now shows the error in its own alert, without the plugin's Failed badge, because the installed version keeps running. While an update is still available the button reads Retry.
* fix(app): show a plugin page's update error only while the update is offered
The failed update stayed in the operations store after the plugin was updated elsewhere or uninstalled, so the page kept saying the update failed. The page now shows it with the Update button it belongs to, as the Installed tab's Updates row does, and uninstalling forgets it.
On Android, a slow drag on a Usage card handle moved the sheet instead of the
card. A drop in the same slot left the sheet ignoring body swipes. A drop in a
new slot painted the original order for one or two frames.
The sheet gesture now registers a content drag as both a failure requirement
and a simultaneous relation, and the Gorhom patch spreads relation arrays into
RNGH, so the waiting sheet recognizer no longer cancels the card drag.
The old-order frames came from the list clearing its drag state before the
reordered data arrived. The sheet portal forwards changed children from an
effect, so the list committed old data with fresh transform hosts and a cleared
active key, and the new data about 200 ms later. The draggable-flatlist patch
now renews moved hosts and clears the active key in the render that receives
the reordered data. A same-slot drop resets explicitly because its data does
not change. Every native list that uses the patch gets the drop change.
Repro tooling for both device checks is in packages/app/e2e/mobile/usage-drag.
Approve Claude execution permission callbacks before creating or emitting permission events, preventing approval cards and transient waiting states in Bypass. Keep AskUserQuestion and ExitPlanMode interactive. Add regression coverage for silent approval and live mode changes.
timeline.append accepted any string as the row kind, but the app registers
renderer kinds with /^[a-z][a-z0-9-]*$/. A plugin that appended a kind such as
repro.card got a successful append, then its client setup threw in
addTimelineRenderer and the whole plugin client failed to load.
The daemon now rejects an append whose kind breaks that rule and names the rule
in the error. The wire schema stays a plain string. Document the rule in the
plugin docs.
Fixes#7326
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
ensureExplorerSidebar clicked the toggle only when no Explorer was
visible. Right after a resize to phone width one still is for a moment:
the wide layout until the app switches, then the closed phone overlay's
first frame. The helper skipped the click and the phone Explorer, which
starts closed, never opened.
The helper now decides from the toggle's aria-expanded, and the
Explorer spec waits for the app shell to switch layouts after resizing.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
The router scrolls the window back to the top when the page hydrates. The
hero tests scrolled to the mockup right after load, so in WebKit the reset
sometimes landed after the test's scroll and the opening scene never started.
The language button turns enabled in the render after that reset. The
changelog and plugins specs already waited on it with their own copies; the
wait now lives in the shared fixtures and the hero tests open the page with it.
Cleanup counts a worker gone once its socket refuses connections, and the
worker stops listening before its process exits. The test checked the
worker pid right after closeTerminals() resolved, so it failed whenever
the worker was still exiting. Wait for the pid to disappear, as the
adjacent shutdown tests do.
* fix(claude): keep an idle agent running while it has a session cron
Claude keeps session-only crons and /loop wakeups in its own process, so
stopping that process drops them. The idle runtime cleanup asked the Claude
session whether it could stop, and the session never knew about these jobs:
they appear nowhere on the message stream.
Claude lists them as session_crons on every Stop hook. The session now
records that list, and canStopRuntime() refuses while it is non-empty. The
next Stop after a fire, a CronDelete or an expiry updates the list.
Co-authored-by: KronixDev <35991992+KronixDev@users.noreply.github.com>
* refactor(claude): type the Stop hook with the SDK's hook input
Co-authored-by: KronixDev <35991992+KronixDev@users.noreply.github.com>
* fix(claude): hold the runtime after a cron tool call until the next Stop
Claude lists session crons only in the Stop hook, and runs Stop only for
turns that complete. A turn that called CronCreate and was interrupted or
failed left the count at zero, so idle cleanup could still stop the
process holding the cron. A CronCreate, CronDelete or ScheduleWakeup call
now marks the count unknown until the next Stop reports it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: KronixDev <35991992+KronixDev@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat(website): show orchestration and remote in an animated hero mockup
The homepage hero now has five scenes: Orchestration, Remote, Code review,
Pull requests, and Plugins. Orchestration and Remote were missing before,
and they are what separates Paseo from a single-machine agent app.
Orchestration, Code review, and Plugins play a script once the mockup is 60%
on screen, and again on every pill click. Each script is a list of beats
(wait, click, type, user, agent, tools, turnEnd, mark) laid end to end. A
non-React clock owns the time and components read one fact at a time, so
only the part that changed renders. A pointer clicks the composer, the
subagents pill, and the review controls. Reduced motion shows each finished
scene.
The right panel is 300px for the file tree and grows to 424px for the pull
request and the plugin. Picking a pill scrolls the pills and the mockup
into view.
* fix(website): keep a picked hero scene playing and scroll it into view the same in every browser
A pill click before the mockup was 60% on screen played its scene, and then
the visibility start played the same scene again from zero. The player now
starts the opening scene only when no scene has played, and the hero stops
the clock when it unmounts.
Picking a pill used scrollIntoView with `nearest`. For an element taller than
the window, each engine picks its own edge, and WebKit left the pill 25%
visible in a 1280x600 window. The hero now computes the scroll itself: the
least that shows the pills and the mockup, never past the pills at the top.
* fix(website): scroll a picked hero scene by where the hero settles, not where it slides
The hero slides up 40px as it enters. A pill clicked during the slide
measured the frame 40px low, so the scroll stopped with the pills 24px above
the window once the slide ended. This was the cause of the WebKit failure in
CI. The earlier explanation, that engines differ on scrollIntoView, was wrong.
The scroll now measures the frame from layout offsets, which ignore the slide.
The test holds the page clock so the slide stays at its first frame.
* test(website): hold the hero's slide-in still when a pill is picked during it
The test stopped the page timers but let time run, so it caught the bug only
when the click landed in the first second after load. It now pauses the clock
before the page loads and checks that the slide is still in progress at the
click.
* test(website): put the hero's 40px slide-in back by hand in the slide-in test
The test held the page clock to freeze the slide, but WebKit did not hold it,
so the test failed on its own precondition. It now waits for the slide to
end, puts the 40px offset on the container, picks a scene, and removes the
offset. Reduced motion makes the scroll instant, so the test asserts the
result without waiting for a scroll to settle.
* fix(website): start the opening hero scene in a window shorter than most of the mockup
The scene waited for 60% of the mockup to be on screen. A window shorter than
60% of the mockup, such as a wide browser with devtools docked at the bottom,
never reaches that, so the scene never started. It now starts when a line 60%
of the way down the mockup is on screen. That is the same moment in an
ordinary window, and a short window reaches it as the page scrolls past.
Archiving a worktree archives its record, then deletes the directory. A
reconciliation pass that listed the workspace before the archive went on
to read its checkout while the directory was being deleted, saw no Git
checkout, and wrote kind "directory" onto the archived record. Undo then
refused to recreate the worktree: "The archived workspace directory no
longer exists and cannot be recreated."
Reconciliation now skips a record that is archived when it re-reads it
and when it writes the update, as it already does when listing.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* Share the host menu row, a plain sheet subtitle, and settings rows on a menu's rail
- HostMenuItem: a host as a menu option (status dot, check), extracted from the
sidebar Display menu so other host pages reuse it.
- SheetHeaderSubtitle: one muted, truncating line under a sheet title.
- MenuSettingsRows: settings rows that share a menu surface with menu rows put
their labels on the menu rows' label rail (menuLabelInset).
* Pick the Usage host in Usage settings, and name it under the title
The host picker leaves the top of the Usage modal body. With more than one
connected host, the cog's options lead with a Host row showing the current
host; it opens a page of the same surface (a flyout when wide, an in-place page
with Back in the compact sheet), so no sheet opens over another. The modal
names the shown host in the header subtitle, muted and truncating, so a long
host name never crowds the title. With one host, neither shows.
Picking a host on a phone no longer dismisses Usage: only the body is keyed by
host, so the compact sheet no longer remounts (and dismisses) on a switch.
* A Usage host switch shows the new host loading, not the old host's cards
The host's reports list was read with a list shape, which keeps the previous
key's data while the next loads. Its key differs only by host, so after a
switch the old host's cards showed under the new host's name until its reports
arrived. Read it as a value. The title-row controls are keyed by host too, so a
failed setting change on one host never shows on another.
* Put menu settings rows on the menu's existing content rail
menuRowContentInset already names the menu row's label rail next to the style
it mirrors; drop the duplicate menuLabelInset.
* feat(app): open the project chooser with the new workspace shortcut
* fix(app): claim project shortcuts while projects load
* fix(app): keep project shortcuts owned by the focused screen
* client: recover routed hosts when their gateway reconnects
Assisted-By: OpenAI GPT-6.1 Sol high in omp/18.16.0
* client: wake routed clients before waiting for probes
Assisted-By: OpenAI GPT-6.1 Sol high in omp/18.18.9
* fix(server): clear attention without resuming closed agents
* fix(server): serialize attention clearing with reloads
* fix(server): keep cleared attention when a queued resume lands
Clearing attention on a closed agent no longer resumes its provider
session, so a resume that the loader queued behind the clear must not
restore the attention it read before the clear. Resume now reads
attention from the record inside the agent's lifecycle lane, as it
already does for metadata.
Adds a daemon regression test for a closed agent whose provider session
is gone: on main the clear_agent_attention request never gets a response
and the agent stays unread.
Co-authored-by: luke <luopeihuan@gmail.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: luke <luopeihuan@gmail.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(claude): state why a permission prompt appeared
### Linked issue
Closes #
No open issue tracks this. The behavior appeared in a live session on a
remote host.
### Type of change
- [x] Bug fix
- [ ] New feature
- [ ] Enhancement
- [ ] Refactor
- [ ] Docs
### Reasoning
A user selects Bypass and expects no prompts. A `permissions.ask` rule or a
`PreToolUse` hook outranks the mode, so the agent asks anyway, and the card
gives no cause. The user reads this as a broken mode.
Claude explains each prompt in `canUseTool`'s `decisionReason`. Paseo dropped
it. The card now shows that sentence, so a user can find the hook that owns
the rule instead of guessing.
Codex already puts its approval reason in `description`. Claude now matches,
so no new field and no protocol change are needed. `description` was unset on
every Claude permission request except `AskUserQuestion`, which keeps its own
summary because that spread still runs after this line.
### Goals
- The card shows the provider's reason when the provider sends one.
Acceptance: a hook-forced prompt in Bypass shows the hook's
`permissionDecisionReason`.
- A card without a reason looks exactly as it does today. Acceptance: no new
row, no layout shift.
- Claude and Codex carry an approval reason the same way. Acceptance: one
field, no provider-specific rendering.
### Non-goals
- Changing the CLI's precedence. A hook that asks still asks. Paseo shows
the cause; it does not overrule the hook.
- Auto-approving hook-forced tools in Bypass. `f998ee169` did that and was
reverted the same day. A blanket allow defeats a real safety hook.
### QA
Real Claude, web (browser), one live session in `bypassPermissions`, driven
through the app by Playwright.
```
npx playwright test --project=real-provider e2e/browser/permission-reason-card.real.spec.ts
1 passed (52.7s)
```
The run forces two prompts in the same session and captures both.
Forced by a `permissions.ask` rule, which sends no reason. This is the card
before this change:

Forced by a `PreToolUse` hook that returns a reason, same session:

The spec asserts both states, so the screenshots are not the only proof: the
hook's sentence is absent from the first card and visible on the second.
Both cards come from one session on this branch. The pair shows the two
render paths, with a reason and without. It is not an old build beside a new
one. A card without a reason renders exactly as it did before this change,
which is why the first shot stands in for the old card.
The spec lives at
`packages/app/e2e/browser/permission-reason-card.real.spec.ts`. It is not
part of this commit.
Unit:
```
npx vitest run packages/server/src/server/agent/providers/claude/agent.test.ts
Test Files 1 passed (1) Tests 75 passed (75)
```
Platforms: the daemon fills a field the card already rendered, so every
platform gets it through the existing path. Web verified above with real
Claude.
### Checklist
- [x] One focused change
- [x] `npm run typecheck` passes
- [x] `npm run lint` passes
- [x] `npm run format` passes
- [x] QA evidence
- [x] Tests added or updated where it made sense
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: preserve context for Claude permission reasons
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Mohamed Boudra <boudra.moha@gmail.com>
When New workspace hands its draft to the ready workspace's draft tab,
the text and setup move with it but the draft's plugin metadata did
not: it was cleared with the New workspace draft and never written to
the destination draft. A send after a failed first start then created
the agent without the metadata.
Copy the metadata into the destination draft at handoff, before the
New workspace draft is cleared.
Closes#9716
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Michael Wu <michaelmwu@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat(app): reorder and turn off usage cards
Usage cards default to alphabetical order. Drag a card by its handle to
reorder it; the handle shows on hover on web and is always visible on
native and compact layouts. A card's switch turns it off: the card
collapses to its header and its windows leave the sidebar summary. Order
and off state are device-local usage preferences.
Inside a native bottom sheet, a drag gesture can now keep the touch:
the sheet's content pan waits for the list's drag pan
(react-native-draggable-flatlist gains `dragGestureRef`), and the sheet
scroll stops while a drag is active.
* feat(app): one icon button for every sheet header
The sheet header's back arrow, close X and actions now render through
SheetHeaderIconButton, which takes the header island chrome CompactHeader
uses: 26pt frame and 16pt glyph on pointer, 44pt and 20pt on touch, muted
colour, hover fill and tooltip. Edge buttons hang into the row padding so
their glyphs sit on the content rail; the row keeps its 64pt height and the
trailing actions shrink before the title collapses.
Migrates the diagnostic, import session, model browser, changelog, plugin
logs and sheet pane actions, and moves the tool-call and tool-call overview
sheets onto SheetHeaderView. The Usage refresh and options buttons size
their glyph from the header scope. adaptive-modal-sheet and the migrated
sheets leave the raw-pressable burn-down list.
* feat(app): host picker trigger and Usage host placement
HostFilter renders the shared ComboboxTrigger, as in Settings, and
truncates long host names. Sessions, Schedules, plugin surfaces, the
labels manager and Usage pick this up together.
The Usage modal puts the host picker at the top of its body on every
form factor. The header is title, Refresh all, Settings, X, so the
title stays whole on a phone.
* feat(app): command center tabs, recent workspaces, and agents in workspace search
The command center gets All · Workspaces · Files · Actions tabs under the search
field. Tab and Shift+Tab rotate them on web, a tab keeps the query and starts at
its top, and Backspace on an empty field returns to All. ⌘P opens on Files in
place of the Files scope chip.
All leads with the three most recent workspaces other than the open one. Agent
rows are gone: an agent's title now finds its workspace, which shows the agent on
a third line and opens that agent's tab.
The selection now follows the first result until the user moves it, so rows that
load above it do not leave it on the row below.
* feat(app): archived workspaces in command center search
A query in All or Workspaces now also finds archived workspaces through
agent history, appended after the active matches. Archived rows show the
archive time and an Archived badge, and open the workspace's latest agent
where it can be unarchived. Hosts without history search contribute
nothing. History's archived badge moves into a shared ArchivedBadge.
* fix(app): put the command center divider between the field and the tabs
The tabs belong to the results, not the search field, so the rule now
separates the field from the tab bar. The tab-rotation test also pins the
list's top, since the tabs no longer live inside the header it measured.
* fix(app): rank agent matches by quality, keep background workspaces out of Recent, explain Files off-workspace
- Score each agent together with its workspace's title and subtitle, so a
query split across them ("payments login") finds the row, and pick the
workspace's own match only when it is as good as its best agent match.
Across workspaces, match quality now ranks before own-versus-agent.
- Carry the workspace's background flag through the project summary and
leave background workspaces out of Recent workspaces, as the sidebar
does. A query still finds them.
- The Files tab outside a workspace says "Open a workspace to search
files" instead of "No matches".
* fix(app): settle command center selection, name agents only for loose matches, drop Files off-workspace
- Name a workspace's agent only when the workspace's own text does not match
contiguously and the agent does; a change-request hit is always an own match.
- Follow the first row only until every source for the query and tab has
loaded, then keep the selection by ID so reorders do not move it.
- Projects stay loading until an online host's workspaces have arrived; the
agent directory reports ready first.
- Outside a workspace there is no Files tab and All lists no files; the All
placeholder names only what the available tabs search.
- The unqueried Workspaces list follows the sidebar's Show background setting.
* fix(app): keep Projects loading honest, rank own-name matches by their agents too, refresh archived search after archive
- The command center waits for online hosts' workspaces itself instead of
through useProjects. useProjects held isLoading until workspaces
hydrated, but a failed workspace request never hydrates, so the
Projects screen could spin forever.
- A workspace that matches on its own name is ranked by the better of
that match and its agents', so typing into an agent title shared with
another workspace no longer drops it below that workspace and back.
- Archiving a workspace marks agent history stale. Archived search reused
a cached page that still listed the agents as active, so a workspace
archived in the last 30 seconds matched in neither list.
* fix(app): decide command center agent matches by match class
One rule now picks both what a workspace row shows and how it ranks. A
match falls in a class: every word at a word boundary, a word inside a
word, or scattered/misspelled. A row names its agent only when the agent
matches in a closer class than the workspace's own text, never on a
change-request hit. Rows rank by class, then own text ahead of an agent,
then score, then recency.
The previous rules chose the ranking candidate and the displayed
candidate separately, so each fix moved the edge case: positional tier
gaps named agents mid-word, and ranking by a hidden agent let a mid-word
name outrank a word-boundary one with nothing on screen to explain it.
* style(app): format command center workspace search import
* fix(app): settle archived search when no history host is reachable
With no searchable host online, the history query is disabled under a new
key, and keepPreviousData kept serving the old key's rows as placeholder
data. Archived search read that as still waiting for results, so the
command center selection never settled and followed every re-rank.
Previous results now stand in only while the query can run.
* fix(server): resolve a full agent id only to the agent with that id
The daemon's agent lookup tries the exact id, then a unique id prefix,
then an exact title. A full id that matched no agent fell through to the
title step, so `paseo agent delete <id>` hard-deleted a different agent
whose title was that id, and inspect, stop, update, mode, logs and open
acted on it the same way. Stop at the exact-id step when the identifier
is a complete agent id.
Closes#9727
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore(cli): tag the full-agent-id guard as compatibility for older daemons
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore(cli): say which commands the full-agent-id compatibility guard covers
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(app): keep the command popover against the composer as it resizes
The popover lives in a portal and positioned itself from an asynchronous
copy of the composer's rect. Any composer layout change painted first: a
wrapped line overlapped the popover, cleared text left it floating above
the composer, and a window resize left it at the old width, for one frame
on web and up to seconds on Android under JS load.
The popover now follows the composer's live size between measurements.
Native reads the anchor's height on the UI thread every frame with a
Reanimated frame callback; web commits the placement from a
ResizeObserver with flushSync, before paint. The keyboard translate view
in the portal becomes host-sized and box-none, so the popover moves
inside it without leaving its parent's bounds (Android hit-testing).
* docs(app): state where the native popover's fixed-bottom tracking stops holding
The native frame follows only the composer's height so it never depends on whether iOS's native-driver keyboard lift has reached the shadow tree. The centered New workspace composer and width changes still wait for the rest measurement, as before.
* fix(app): stop the native popover frame measuring a composer that left the tree
When the composer unmounts with the popover open, the portal removes the frame a commit later. A busy JS thread holds that commit for many frames, and every failed measure() logged a Reanimated warning: 31 to 111 per layout swap on Android. A gate written from the anchor's ref callback arrives on the UI thread only after that same JS task, so the frame now stops on its first failed measure and falls back to the rest measurement.
* fix(app): close the autocomplete popover while its retained panel is hidden
A workspace stays mounted with display: none while another route shows, and the popover stayed open inside it. On native its frame then failed to measure the hidden composer, stopped tracking, and kept the stale placement after the user came back. The popover now closes with its panel and reopens with a fresh measurement.
* fix(app): open the autocomplete list where it rests, with only the rows it shows
The list mounted every result and then scrolled itself to the composer edge.
On Android the scroll command reaches the screen one or two frames after the
rows, so each open and each result change painted the far end of the list, or
the selection 8 px low, before the resting frame. Mounting 115 commands also
held the popover's first frame for 500 ms to 1 s.
The list is now an inverted, virtualized list: its resting scroll position is
the composer edge, and the first commit holds the rows that fill the popover.
Each result set gets its own list, so a result change starts at the composer
edge with the same bounded commit. Arrow-key selection is revealed through the
list's own viewability and scroll-to-index.
* fix(app): rest the autocomplete list at the far end when the selection wraps there
Wrapping the arrow-key selection from the best match to the far end of a long
list scrolled there over several frames, because the rows in between were not
mounted. The list now gets a scroller that rests at the end the selection
wrapped to, so the jump is one frame and mounts only the rows it shows.
* fix(app): keep the selected autocomplete row in view when the popover gets shorter
The row the arrow keys selected was brought into view once. A popover that then
lost height, because the composer grew or the window shrank, cut that row off
while Enter still chose it. The list checks the selected row again whenever its
height changes.
The test that counted scroll calls through patched Element prototypes now reads
the list's resting scroll position instead.
* fix(app): keep the autocomplete list when the same results arrive again
The composer hands the popover a new list on every keystroke and refetch, often
holding the results it already showed. The list started over for each one: a
second mount before the filtered results, and a list the user had scrolled
returned to its rest. A result set is now its options in order.
Tests import packages/*/dist at run time. On a cold cache each worker
transpiled the same files and wrote them into Playwright's shared
transform cache without locking, so a worker could read an entry
mid-write, load an empty module, and fail with "does not provide an
export named".
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(app): open the image preview without a flash
Opening an image preview showed "Couldn't load image", then the image
stretched to the whole window, then a blank frame, before the fitted image.
- The attachment preview URL hook returned null both while resolving and on
failure, so the lightbox showed the error while the URL resolved. It now
reports loading, ready, or failed.
- ZoomableImage rendered the image unfitted until its natural size arrived.
It now renders nothing until it can fit the image, and keeps it hidden until
it has loaded, so the image appears with its toolbar instead of after it.
- On Android, React Native lays a modal out at the screen minus the system
bars for its first frames, then grows it, so the backdrop snapped down; the
Modal wrapper sizes its content to the window from the first frame. The
lightbox's own SafeAreaProvider measured the dialog window, whose bottom
inset flips 24, 0, 24; it now reads the window insets via WindowSafeArea.
* fix(app): keep a reopened attachment preview from reading its released URL
Closing a preview releases its URL (revoked on web and desktop), but the hook kept the result for that attachment. Reopening the same attachment returned the revoked URL until the new lookup landed, so the image failed to load and "Couldn't load image" showed for a frame. The result is now dropped when its URL is released. The frame test also counts an image as visible only once it is painted, so a preview that never appears fails.
* test(app): wait for the stale file-link lookup to land before asserting
The test resolved the lookup and ended. React Query delivers the result on a timer, which could fire after jsdom was torn down ("window is not defined" failed app-tests in CI), and the no-open assertion could run before the stale result arrived at all.
* fix(app): show images the browser reports no natural size for
ZoomableImage waits for the image's size before painting it. React Native Web's Image.getSize never answers for an image that loads with a natural size of 0 (an SVG without width and height in some browsers), so the preview stayed blank with no error. The web build now measures the image itself and falls back to the browser's default replaced-element size, 300x150.
* fix(app): retry a reopened failed attachment preview from loading
The hook kept a failed result after its lookup was torn down, so reopening the same attachment showed "Couldn't load image" until the retry landed. Every cleanup now drops the result for its key.
* test(app): name the wait for a file-link lookup's delivery
Reanimated computes a style's first value when its hook first runs and sends
later values from an effect after the mounting commit, which native paints.
The popover's height bound lived in the component that renders while the
popover is closed, so it started at 0. Every open painted one frame with the
popover at its minimum height, hanging down over the composer, before the
measured bound arrived. The bound now lives in a frame that mounts only with
a measured anchor.
Browser tests could not apply animated style updates at all: Reanimated loads
its react-native-web style helpers with require, which Vite's ESM serving
lacks, so the first update after mount crashed the component.
A workspace opens on a New tab of its own, so waiting for the first
New tab to show passed before the Ctrl+T tab rendered. On a slow runner
the count was read too early, and the plus-menu check then saw the
shortcut's tab arrive as an extra one.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): fall back to fetchAgent in archive, reload, and detach (#9696)
* fix(cli): keep a full agent id exact when archive falls back to the daemon
The fallback added for agents missing from the listing asks the daemon
with fetch_agent, which tries the id, then an id prefix, then an exact
title. A full id that matches no agent could therefore resolve to a
different agent titled with that id, and archive, detach, or reload
acted on it. Accept the daemon's answer for a full id only when it is
that id, as the listing lookup already does since #9680.
Co-authored-by: xunWhale <2338923971@qq.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(cli): cover detach past the listing page and archive with a missing provider
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(cli): report a failed detach lookup as DETACH_FAILED
detach now asks the daemon when the listing has no match, and the
daemon rejects an ambiguous prefix. Wrap that failure in DETACH_FAILED
as archive and reload already do, instead of letting it out raw.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: xunWhale <2338923971@qq.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
The live-search test reset the row render counter after a fixed 600ms.
On a loaded runner FlatList was still mounting overscan rows after that,
and each late mount counted as a render of an unchanged row.
Reset the counter only after a quiet period with no row render.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(desktop): wait for an already-starting daemon to become ready
* test(desktop): cover a daemon stopping during startup
Keep incomplete host registration out of startup recovery when a delayed daemon exits before readiness.
Co-authored-by: magiclaw <930198090@qq.com>
---------
Co-authored-by: magiclaw <930198090@qq.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* 修复 ACP 模型档位按精确型号读取
Co-authored-by: Alfred <alfred@mkiio.com>
Alfred-Model: auto/gpt-6.1-sol
Alfred-Thinking-Effort: high
* fix(acp): keep shared thinking options for models without their own
A model that reports its own reasoning levels in its ACP metadata uses
them. A model that reports none keeps the session's thinking options, as
before, instead of losing its thinking picker.
Co-authored-by: sj <doskoi.panda@gmail.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: sj <doskoi.panda@gmail.com>
Co-authored-by: Alfred <alfred@mkiio.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
The "failed replacement cancellation preserves an autonomous running
state" test deleted its storage directory while the snapshot write for
the "running" state could still be in flight. Under CI load that write
lands during rmSync and fails the test with ENOTEMPTY. Flush the manager
and storage first, as the neighbouring cleanup tests do.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(server): keep a plugin child's canceled or failed turn on close
A plugin child that ended its turn as canceled or failed and then sent a
plain session.closed was upserted as completed. Remember the outcome of
the child's latest finished turn and use it when it closes without an
error.
* fix(server): clear plugin child outcomes when replaying a branch
Keep the close-status fix compatible with reused-child running updates and discard remembered outcomes when rewind replaces a binding. Cover terminal close states through the agent API and replay.
Co-authored-by: hadan8977 <zc-huang23@mails.tsinghua.edu.cn>
---------
Co-authored-by: hadan8977 <zc-huang23@mails.tsinghua.edu.cn>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Forking from a reply failed with "This checkpoint changed after it was
created" whenever a tool call started before that reply and finished
after it, the shape of background Bash, Monitor, Task and Codex
terminals. The projection keeps one row per tool call from its start to
its latest update, so the row spans the reply, and the fork refused any
copied row that spans the checkpoint.
Copy such a tool call into the fork marked running: its state at the
checkpoint can't be read back. Plugin cards that span the checkpoint
stay out, and a cursor from another epoch or a reply that is gone is
still refused.
* fix(archive): warn from fresh git state before removing a worktree
Archiving a worktree decided whether to warn from the sidebar row's cached git status. Until the
row received that status it was empty, so the archive removed uncommitted work and unpushed commits
without asking. Every archive that confirms now reads the worktree's checkout status from its host
first, and a failed read shows its error and keeps the worktree.
The host's dirty check ran bare `git status --porcelain`, which drops untracked files when the
repository sets `status.showUntrackedFiles=no`, so a worktree holding only new files read clean. It
now passes `--untracked-files=normal`.
* fix(archive): redirect from the current selection after the host answers
A worktree archive now waits for the host's checkout status before it starts. If you opened another
workspace meanwhile, the archive redirected from the selection captured at the click and replaced
the workspace you had just opened with /new. The redirect now runs the latest onArchiveStarted and
receives the workspace being archived, so the git actions controller compares that workspace with
the current selection instead of redirecting from whatever is open.
* fix(app): keep the Android chat still when a tap or long-press lands on its text
Chat text is selectable, and Android focuses selectable text when it is
touched. React Native's ReactScrollView.requestChildFocus scrolls a newly
focused child fully into view, so tapping a link or a word in a reply that
was partly off screen, or long-pressing it, scrolled the timeline by up to
a screen. The inverted timeline had a guard for this, but the guard
depended on the inversion (#4090, then #7131), and #8717 removed it with
the inversion.
PaseoScrollView now skips that reveal when the focused view is selectable,
non-editable text in touch mode. Inputs, and focus moved by a keyboard,
still scroll into view.
* test(app): assert the long press selects the word under the finger
* fix(app): keep the Android chat still when a tapped reply keeps streaming
Touched chat text keeps focus. When a streaming reply's text is replaced,
ArrowKeyMovementMethod collapses the selection to 0, and the focused text
view asks its scroll parent to reveal that line, which scrolled the
timeline back to the reply's first line. PaseoScrollView now drops
rectangle requests while touched read-only text holds focus with nothing
selected. A drag on a selection handle still reveals.
The input control test now makes its EditText selectable, as React
Native's TextInput does, so it covers the editor check.
* fix(app): keep the Android chat still when the timeline resizes after a tap
ScrollView.onSizeChanged scrolls the focused view into view when the
scroll view changes height. Touched chat text keeps focus, so a composer
change below the timeline (a queued message being sent, a send error
appearing) realigned the tapped reply. PaseoScrollView now skips that
reveal while touched read-only text holds focus.
* test(app): wait for the slash search to change before erasing it
"forgets an arrow-key choice once the search changes" waited for /help
after typing "h", but /help is already in the unfiltered list, so the
wait passed at once. On web the cursor reaches the slash search after
paint; a Backspace sent before that frame left the search at "" the
whole time, the /exit choice stood, and Enter archived the agent. The
test now waits for /tdd to leave the list, which only happens once the
search is "h".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(app): wait for the slash search to return before Enter
The input's value runs ahead of the slash list on web, so Enter could
still land on the list for "h". Wait for /tdd to come back first.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
When an archived or persisted agent is restored via resumeAgentFromPersistence, its managed record intentionally preserves the historical updatedAt timestamp so sidebar ordering and activity timestamps are not artificially bumped just by viewing or reopening the agent.
However, getRuntimeCleanupCandidates() previously used updatedAt.getTime() directly as lastActivityAt for idle runtime garbage collection. For any restored agent whose last conversation turn was older than the idle runtime threshold (default 60 minutes), the next periodic idle cleanup sweep (every 60s) immediately saw the newly spawned runtime as idle for >60m and terminated its live process.
Record openedAt on the per-session runtimeCleanupIdentities entry when a session is registered, and compute lastActivityAt in getRuntimeCleanupCandidates() as Math.max(updatedAt.getTime(), identity.openedAt) so a newly restored runtime gets a full idle window without mutating the agent's persisted updatedAt.
* fix(app): show the Android ripple on sidebar row presses
PressHighlight owns pressed feedback. Callers pass the pressed fill as
highlightStyle and stop painting it themselves. iOS and web paint the
fill; Android draws the platform ripple, clipped to the row's corners,
after Android's 100 ms tap timeout.
Rows that knock content out of the surface follow the fill through
onHighlightChange instead of tracking press state themselves.
Defaults borderWidth to 0 under clipped ripples: React Native 0.86 sends
NaN when a style drops borderWidth, and an overflow-hidden view then
stops painting (fixed upstream in facebook/react-native#57789).
* fix(app): let PressHighlight own file header press feedback
Changes-tree rows on Android painted their old flat pressed fill under the
new ripple. Lock the Android row's caller border and press handlers in a
test.
* fix(app): skip the sidebar row press fill while renaming
On web the row's pressable stays the responder for clicks inside the
inline rename field, so it painted the pressed fill while the title was
being edited. Drop highlightStyle while editing, as the press handlers
already are.
* fix(app): keep a press's fill and its report on the same edges
usePressFill painted from the live pressed state but reported only at
press-in and press-out, so the row fill and the badge ring could
disagree when highlightStyle appeared or went away mid-press. A press
now keeps the fill it started with; the paint and the report both come
from that one state.
* fix(app): drop a sidebar row without a wrong frame on native by remounting moved cells
draggable-flatlist moves a cell with a held drag translate. Reanimated re-applies a view's last animated transform to every React commit, so the reorder commit painted one frame of new order plus old translate. The drop now gives each moved cell a fresh transform host, keyed per cell, so the reorder commit mounts views with no animated transform to re-apply. Moved cells remount their row subtree on each drop.
* fix(app): keep a project's Show more reveal when a drop remounts it
The drop remounts each project block it moves, and the block held its
own reveal state, so a revealed project shrank back after a drop. The
project list now owns the reveal per project, and the group hook takes
it as input.
* docs(app): note that a native drop resets state held inside a moved row
* fix(app): render every row of a non-scrolling native list in its first commit
A drop remounts the nested workspace list of each project block it
moves. FlatList renders 10 rows on mount, so a moved project showing
more than 10 workspaces painted 10 rows and grew a commit later.
The sidebar list's bottom padding goes back to 16 and stays constant. The archive toast stays over the list's bottom edge, as on main, so nothing moves when it appears or leaves.
* fix(dev): keep seeded daemon homes from resuming agents
* fix(dev): accept BOM configs when seeding homes
* fix(dev): skip existing homes before reading seed config
* fix(dev): seed homes from symlinked checkout paths
* fix(dev): copy linked metadata into independent seed files
* fix(chat): preserve scroll offset when enabling virtualization
Reading older messages in a long web chat could jump to the first
message when older rows moved into the virtualized history section.
When the row virtualizer is enabled it scrolls to its remembered
offset, which falls back to initialOffset (0) the first time. Start
it from the scroll container's current position instead.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(chat): pass mountTimeline options as an object
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: luke <luopeihuan@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: paseo-bot[bot] <paseo-bot[bot]@users.noreply.github.com>
Observing the workspace starts a background git fetch of origin. The test's
origin is an SSH alias, so a real fetch runs ssh in the checkout and can still
be running after the service is disposed. On Windows that holds the folder
open and cleanup fails with EBUSY. The test now supplies a fetch that returns
no ref changes; the parent lookup and status poll it checks are unchanged.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(opencode): rebind a session when the previous bridge stops listening
A refused fetch proves the previous bridge is gone, but the check only
matched the Node shape (`cause.code`) and Bun's older spelling
(`code === "ConnectionRefused"`). OpenCode 2.2.5 runs on Bun 1.4.4,
which throws a TypeError with `code === "ECONNREFUSED"` and no
`cause`, so the error was rethrown, the stale binding was never
deleted, and every later bind for that session answered HTTP 500
(#8780).
Accept the code from either location. The narrow refusal check stays:
other connection failures remain inconclusive so two daemons cannot
take over the same session.
The probe is now classified by an exported predicate with the runtime
shapes as explicit cases, and the stale-binding test closes a real
listener instead of stubbing the network, so neither test patches a
global.
* test(opencode): bind the session on the restarted bridge before rebinding
The bridge now serves tools only for sessions it has bound, so the stale-binding
test registers the session on the restarted bridge, as a restarted daemon does
when it takes the agent back.
Co-authored-by: quickwind <wallacewei@live.cn>
---------
Co-authored-by: quickwind <wallacewei@live.cn>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(app): let the PR pane's Activity section collapse and resize
The PR pane was one ScrollView. Checks sat in a nested list capped at
268px, and the line above Activity was a plain 1px View. Collapsing
Activity only hid its body, so the checks stayed boxed with empty space
below, and nothing could be dragged.
The pane now splits like the Changes pane's docked Commits section. The
overview (header and checks) scrolls in its own region. While Activity is
open, a ResizeHandle between the two sets the overview's share. While it
is collapsed, the Activity row docks to the bottom and the overview fills
the rest.
* fix(app): keep the PR pane separator under the finger above the home indicator
The split measured the pane including its bottom safe-area padding, but
the overview's percentage height resolves against the box inside that
padding. On a phone with a home indicator the two heights differ, so a
drag jumped at the start and then lagged the finger (a 250px drag moved
the separator 212px on Android). The split is now measured inside the
padding, so the drag and the layout use the same height.
* fix(app): keep focus on the PR pane's Activity header when it toggles
The header moved between two parents as Activity opened and closed, so
React remounted the row and keyboard focus fell to the body. It now keeps
one slot in the split and only the timeline mounts. That also stops the
header shrinking into the space left by a large drag when the pane gets
short, since the header no longer sits in a min-height-0 wrapper.
The header exposes aria-expanded on web, which React Native Web does not
derive from accessibilityState. The Unistyles test stub now lets explicit
props override mapped ones, matching the library's merge order.
* test(app): fill unpinned test-theme tokens from the light theme
The Unistyles stub now runs uniProps mappings, and the markdown renderer's
mapping reads colors.terminal, which the hand-written test theme lacked.
Tokens a test does not pin now come from the real light theme.
* fix(app): save the PR pane separator where it is drawn
Dragging past the end of short checks left the separator at the content's
bottom but saved the pointer's share, so the separator jumped down when
more checks arrived. The saved share is now capped at the overview's
content height.
* fix(app): keep the PR pane's earlier share after a drag past short checks
Capping the saved share at the content height made any downward drag over
short checks pin the overview at that height, even a drag that visibly did
nothing. A drag that ends at or past the content's bottom now keeps the
larger of the current share and the content's, so growing checks return to
the share the overview had, and never to the pointer's position.
* fix(app): decide the PR pane's saved share when a drag ends
Drag previews wrote straight into the saved share, so a move above the end
of short checks during a drag replaced the share the overview had before
it, and a drag that ended back at the content's bottom left the overview
pinned there. Previews now live in their own drag state, and the saved
share is resolved once, on commit, against the share from before the drag.
Updating OpenCode from 1.x to 2.x while the daemon runs left it on the v1
client: the version probe result was cached for the client's lifetime and the
binary update does not change provider config, so the client was never rebuilt.
Once the old v1 server exited, every request failed with "Request is not
supported by this version of OpenCode Server (Server responded with
text/html)". Refresh and Reload did not recover; only a daemon restart did.
A forced catalog refresh now drops a cached v1 selection so the next call
re-probes the binary. A v2 selection owns live sessions and stays. A guard keeps
an overlapping forced refresh from discarding the selection the first one made.
Fixes#9583
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
A wheel listener can run before or after the browser applies the scroll it
causes. When the reader had already stopped following output and the last
notch landed exactly at the history start, the listener saw the pre-scroll
position, did not re-arm history-start pagination, and no older page was
requested. The upward scroll now re-arms loading itself.
The turn-collapse journey hung on this race until its 120s timeout; the
older-history page wait now fails with a message after the expect timeout.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix(server): let a message rejected before dispatch be retried
A send_agent_message_request with a messageId wrote its pending receipt
before loading the agent, setting its mode, and starting the run. When one
of those steps failed, nothing reached the provider, yet every retry with
the same messageId reported agent_request_outcome_unknown.
The pending receipt is now written at the dispatch boundary: the send
awaits beforeDispatch after the agent is loaded and its mode is set, just
before the prompt is handed to a run. A failure before that point leaves
no receipt, so the retry submits the message once. Failures after it stay
ambiguous, as before.
Closes#9297
Co-authored-by: tmad4000 <1430007+tmad4000@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(server): lock that a send failing after dispatch is never resubmitted
Scope the docs/hub.md retry sentence to direct sends: agent-sourced sends
still write their receipt before queueing.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(hub): scope the retry promise to failures before the run starts
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(hub): name run startup as the ambiguous boundary
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: tmad4000 <1430007+tmad4000@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>