The replay takes the agent's record when it starts and writes a failure
into that record. Closing the agent drops it, so a replay that fails
afterwards no longer leaves an entry behind.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A replay whose hook threw or timed out ran again on every agent MCP
request, so each Paseo tool call waited on the broken plugin. The
runtime now remembers the instance that failed and replays it only
after the next restart.
The replay now arrives with reason "refresh", like the idle reopen the
same restart causes, so plugins no longer see "create" again.
An open waits until no replay is pending before it detaches, and a
replay that outlives its session detaches only the plugins it replayed.
Co-authored-by: Tom Gringauz <17593920+tomgrin10@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Give worktree teardown commands a shared one-minute deadline. Projects can override it with `worktree.teardownTimeoutMs` in `paseo.json`. Drain output so successful teardowns can exceed the old 1 MiB buffer. Bound the output retained for diagnostics.
At the deadline, try to terminate the command, close its output streams, and keep the worktree on disk. An exit status of zero in response to the stop signal still counts as a timeout.
Closes#9857.
Co-authored-by: Okan YILDIRIM <63511519+ragokan@users.noreply.github.com>
* fix(terminal): delete a stopped worker's copy on Windows
Windows keeps a just-exited worker's files open for a moment, so the
single rm in pruneTerminalWorkerRuntimes failed and left the copy until
the next daemon start. Retry the delete for up to 5.5s.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(terminal): bound the Windows retry of a worker copy delete
rm's maxRetries repeats at every directory level, so a file that stays
locked deep in node-pty would hold daemon start and stop far past the
intended window. Retry one rm per attempt for up to 3s instead.
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(workspaces): preserve commits when archiving worktrees
A removed worktree can be the only reference to its HEAD. Keep that commit before deletion and record the checkout so detached workspaces restore at the same commit.
Co-authored-by: Okan YILDIRIM <63511519+ragokan@users.noreply.github.com>
* fix(workspaces): restore saved checkouts through one git path
Keep existing archive and deletion behavior when Git cannot read a worktree HEAD, and record every readable checkout for a common restore path.
* fix(workspaces): preserve git HEAD identity through restore
Record Git’s full HEAD ref or commit so restore can pass branch and detached checkouts to Git without guessing from a short name.
* fix(workspaces): scope saved HEAD to each archive
An archive with no readable checkout must not retain the HEAD saved by an earlier archive.
* test(workspaces): verify detached checkout after restore
Update the browser journey for detached restore and allow the daemon restart test enough time on Windows runners.
---------
Co-authored-by: Okan YILDIRIM <63511519+ragokan@users.noreply.github.com>
* Let a steer wait out a Claude compaction instead of cancelling it
While Claude compacted, the Claude session answered every steer with
"unavailable". The agent manager reads that as "replace the turn", so
it interrupted the turn and Claude Code printed "Compaction canceled.".
Claude Code already holds a `next`-priority message until compaction
finishes, so the session now accepts the steer during compaction.
Co-authored-by: NightMachinery <36224762+NightMachinery@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* Steer only while the compaction is still running in the real Claude test
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: NightMachinery <36224762+NightMachinery@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
The MCP agent tools serialized live agents without the background work
summary that the WebSocket snapshot carries, so a parent agent saw an
idle worker with a running background shell as plain idle. Both tools now
add the same summary the session adds, omitted when the agent has none.
Co-authored-by: Orcun Simsek <1612171+ortschun@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Changing the thinking level of a running Claude agent marked its query for a
restart. The next turn, mode change or model change then retired the Claude
process, which ended every background shell, workflow and subagent it ran with
"connection lost".
A move between two effort levels now goes to the running query through
applyFlagSettings({ effortLevel }), as Fast mode already does, and marks no
restart. Switching thinking off, to ultracode or back to the default still
restarts, because those change how the query is launched. If the running
process does not take the change, the old restart path runs, so the change is
never lost.
Row: app-built-from-one-set
Paseo: c6210e21-fc13-4dfa-adfc-43a050c7d75a
Co-authored-by: gilad-rubin <6134299+gilad-rubin@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
A force-cancel finalizes turn X in the daemon while the provider keeps
running it, so the next run can be bound to the same X. handleStreamEvent
dropped every terminal for a finalized turn id, including the synthetic
turn_canceled that cancelAgentRunNow dispatches for the tracked run and
the provider's own terminal. The run never settled, cancelAgentRunNow
waited on it forever, and every later cancel, reload and send queued
behind it until the daemon restarted.
A terminal for the tracked run's own turn id is no longer dropped.
Fixes#6355
Supersedes #8405
Co-authored-by: Dominic Anaeto <dominic.anaeto@gmail.com>
On web and desktop, Download over a direct connection now fetches the file and saves it from a blob instead of navigating the window to the host URL. A rejected or unreachable download shows an error in the download toast and the app stays on the workspace. The daemon's HTTP CORS check uses the same origin rule as the WebSocket upgrade.
Closes#9895
Co-authored-by: panta82 <4291324+panta82@users.noreply.github.com>
Brings in the shipped 0.16.1 CHANGELOG.md and CHANGELOG.zh-CN.md entries
exactly as tagged, the 0.16.1 version in every package.json and
package-lock.json, and the F-Droid changelog files for version codes
160011-160014.
* fix(server): treat canceled Codex starts as interruptions
* fix(server): report a replaced pending start as undelivered to its sender
waitForAgentRunStart followed the agent rather than the sender's run, so a
send canceled by a replacement before reaching Codex resolved once the
replacement started. Keep the sender's own pending run and reject when it is
cleared before its turn starts.
The canceled-start tests drain streamAgent, because a fresh Codex agent has no
session handle before its first turn (#8393).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(server): keep a sender's start wait across a stale-session retry
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(server): expect the start options passed to a foreground run
Session create and scheduled prompts now pass the sender's start options,
so the two call-argument assertions include them.
Co-authored-by: 3ae3ae <3ae3ae@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(server): keep a Codex message canceled before it starts in history
A Stop or replacing send during Codex preparation settled the run as
canceled without recording the sender's prompt, so the message vanished
from history after a reload and on other clients. Record it as a
rejected attempt, as the start-failure branch already does, so it stays
in history without being delivered.
Co-authored-by: 3ae3ae <3ae3ae@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(server): return each send's start from dispatch
A send waited for its turn by looking up the agent's pending run when the
wait began. When a provider plugin's session was stale, the first start
failed and its run was cleared before the sender started waiting, so the
send rejected with "has no pending run" while the retry answered it.
startAgentRun now returns the start of the prompt it dispatched. Every run
created for that prompt, including the stale-session retry, is bound to
it, so the send resolves when its own turn starts and rejects when its own
run ends unstarted. This replaces the retry hand-off between runs in the
agent manager.
Co-authored-by: 3ae3ae <3ae3ae@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: 3ae3ae <ogyshjsm@naver.com>
Co-authored-by: Bae Seongmin <83870598+3ae3ae@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: bot <bot@localhost>
Co-authored-by: paseo-bot[bot] <paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: 3ae3ae <3ae3ae@users.noreply.github.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
In Bypass, Claude agents again show a permission card for asks from the user's permissions.ask rules (including managed policy), PreToolUse hooks that return ask, compound and piped commands that hit an ask rule, permissions.blockReadsOutsideWorkingDirectories, an organization's ask limit, and sandbox overrides. Claude's own checks are still approved without a card. Upgrades @anthropic-ai/claude-agent-sdk to 0.3.326, which passes the ask's source to canUseTool.
Closes#9916
* fix(server): move updatedAt when archiving an agent that is only in storage
Archiving a loaded agent sets its updatedAt to the archive time
(markRecordArchived). Archiving an agent that is only in storage, which
is also how a parent's archive reaches its children, kept the old
updatedAt. Lists sorted by updated_at, such as History, then left a
just-archived agent where its last turn put it, sometimes days back, and
clients paging such a list by time never reached it.
archiveSnapshotUnlocked now records the archive time as updatedAt too.
Co-authored-by: RoundRedDot <roundreddot@gmail.com>
* fix(server): keep updatedAt from moving back when an archive is restored
Archiving a stored-only agent now sets updatedAt to the archive time.
When the archive time is earlier than the record's updatedAt, as when a
failed send or resume puts an agent's original archive back after
unarchiving it, updatedAt stays where it is. Clients drop agent updates
that are older than the one they hold, so moving it back left them
showing the agent active.
Co-authored-by: luke <luopeihuan@gmail.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(server): keep updatedAt from moving back when a loaded agent's archive is restored
The rule that archiving never moves updatedAt backwards now lives in
buildArchivedAgentRecord, which both archive paths use. A failed send
that resumed the agent before a later loading step failed puts its
original archive back through the loaded path, which had the same
backwards move.
The workspace archive stamp test now uses stamps taken after the
agents' activity, as real archive stamps are.
Co-authored-by: luke <luopeihuan@gmail.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(server): require the archive time when building an archived agent
buildArchivedAgentRecord no longer accepts an archive that leaves
updatedAt unset, the gap #9920 came through, and its tests now assert
the rule: a later archive time moves updatedAt, an earlier one keeps it.
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: RoundRedDot <roundreddot@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>
With the default send setting, a message sent while an OpenCode agent
waits on a question steers the turn, and Paseo rejects the question in
OpenCode. The OpenCode session dropped the question from its own list
without reporting it resolved, so the agent manager and the app kept
showing it. Answering or dismissing it then failed with "No pending
permission request", and the prompt could not be closed.
The session now reports permission_resolved whenever OpenCode accepts a
reply, rejection, or answer, as the other providers do.
Fixes#9879
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
macOS FSEvents can replay the file's pre-subscription write as a create
after the observer starts. The test read the first event for the path,
so it stayed on that create after the delete arrived in a later batch.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
A Codex session opened to read history reads the thread and disposes its
app-server right away, but canStopRuntime() vetoed it because it had no
client. Idle cleanup then kept every such chat loaded in the daemon.
Closes#9804
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Spencer Shulem <1703265+Spshulem@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* Let Claude model discovery finish a token refresh instead of killing it
Model discovery stopped waiting after 5 s by aborting the SDK query and
tree-killing the CLI. A CLI that is still refreshing an expired OAuth
token at that moment has already rotated the refresh token, so the kill
leaves only the revoked token on disk and logs the user out.
The 5 s limit now only bounds the wait. A CLI that has not answered gets
its input ended and exits on its own; it is tree-killed only after a
60 s grace period or when the daemon shuts down.
Fixes#9314
* fix(server): let Claude model discovery finish a token refresh after it answers
Claude Code answers the model list before its startup token refresh has
saved the rotated refresh token. Discovery killed the CLI right after the
answer, so a refresh still in flight left the revoked token on disk and
every later Claude session failed until /login. Discovery now ends the
CLI's input and lets it exit on its own whether or not it answered, with
the existing grace period and shutdown kill as the bound.
Co-authored-by: daysun-k <8309193+daysun-k@users.noreply.github.com>
---------
Co-authored-by: daysun-k <8309193+daysun-k@users.noreply.github.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
After a daemon restart, an agent's timeline is rebuilt from provider
history, and those rows have no turn id. A reply the agent starts on its
own, such as Claude waking after a background subagent, follows the
previous reply with no user message between them, so the last assistant
message lookup joined the two and wait results and finish notifications
returned the old reply with the new one appended.
The timeline projection already treats a message id change as a new
message. Share that rule with the lookup, so both decide which rows are
chunks of one message the same way.
Closes#9814
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat(plugins): append agent instructions on session open
Recompute plugin instructions for each launch so changes apply on reopen without changing saved agent configuration.
* test(providers): verify plugin instructions on reopen
* fix(codex): refresh instructions from restored collaboration mode
A resumed thread can retain its prior collaboration instructions when the mode catalog is unavailable. Rebuild those instructions from the current launch before the next turn.
* fix(plugins): keep launch instructions out of agent records
Provider persistence handles can contain launch configuration. Strip transient instructions before saving and projecting handles.
* fix(codex): preserve built-in collaboration instructions
Pass agent instructions through the thread configuration so Codex can apply its own Plan and Default mode instructions.
* fix(opencode): preserve instructions when reading history
History-only opens do not apply current plugin contributions, so they must not clear the native session instruction entry.
* fix(codex): retain instructions after rewinding
A rewind forks the native thread, which does not inherit its parent launch instructions. Pass the current instructions to the fork.
* Deliver updated instructions to Codex threads
* Cover Codex snapshots after rewind
* Persist provider state when reopening agents
* Limit resume persistence refresh to providers that need it
OMP model labels were built as `${provider}/${name}` and then cut at the
last `/`, so a free-text name such as "... ~60-70 tok/s on 0.2.10, 52/56)"
showed as "56)". Underscores were rewritten to spaces ("IQ3_S" -> "IQ3 S"),
and a colon inside the name cut everything before it.
Pi had the same bug, fixed in #9823. Move that label rule into a shared
model-label module and use it for both providers: free-text names are
kept, path-like names are shortened to their last segment, and a
"Vendor: " prefix is dropped only when it is a prefix.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Rahul Sharma <19687913+rms523@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
The private index snapshot behind index and All changes comparisons was a
fresh copy, newer than every entry, so Git skipped its same-timestamp
content check and a same-size save made right after staging read as
unchanged. The copy now keeps the source index's mtime, rounded down to
the second.
Closes#9827
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(server): abort timed-out watcher setups and back off their retries
A watcher subscription that missed WORKSPACE_GIT_WATCHER_SUBSCRIBE_TIMEOUT_MS
was abandoned but its startup scan kept walking the tree to completion, and
recovery retried every five minutes forever, repeating the full scan each
time. On a CPU-starved host that kept dozens of directories rescanning.
- FileObserver.subscribe accepts an abort signal that stops the startup scan
and rejects; WorkspaceGit aborts setups at the deadline and on dispose.
- Consecutive setup timeouts extend the recovery delay past the 5-minute
ladder cap, doubling up to one hour; an accepted subscription resets it.
Degraded polling keeps its 5-60 s cadence meanwhile.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(file-observer): keep an aborted observation's backend from starting
Aborting a subscription closes its observation, which can happen while
start() is still reading the root. The backend then started after its close
had finished, and the native backend opened a root watcher that nothing
would close.
Co-authored-by: Spencer Shulem <1703265+Spshulem@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(file-observer): abort a subscription mid-scan in the abort test
The test aborted before the backend started, so it passed with the abort
listener removed. A tree past the Linux directory limit makes a scan that
keeps walking fail on the limit instead of rejecting with the reason.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Spencer Shulem <spshulem@gmail.com>
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: Spencer Shulem <1703265+Spshulem@users.noreply.github.com>
* fix(server): queue agent messages until the current turn ends
Steering refusal could replace a running turn and cancel compaction. Hold agent-originated messages and notifications together until the recipient settles, retaining explicit interruption and acknowledging finish subscriptions only after dispatch succeeds.
* fix(server): wake queued delivery at turn and permission checkpoints
A pending follow-up must not hide the permission needed to finish the current turn. Wake ready batches on recipient state changes, let completion waits report permission checkpoints, and preserve admission order and session-mode boundaries when busy dispatches retry.
* fix(server): publish autonomous readiness after run settlement
Idle snapshots emitted while the autonomous run record still existed could not wake queued delivery. Publish terminal state after clearing that run, and keep already debounced busy retries ready for the next turn boundary.
* fix(server): apply queued modes only after run admission
Preparing a later mode group could change the running turn before busy admission rejected it. Carry the requested mode into the reserved run and apply it immediately before provider startup, leaving earlier and concurrently started turns untouched.
* fix(server): keep later mode groups queued until turn end
Dispatching every mode group at once prepared later modes against the preceding turn. Keep later groups pending and reject busy sends before changing mode, leaving mode validation outside run startup.
* fix(server): deliver provider commands during queued turns
Offer waiting messages individually through the provider-owned out-of-band path while a recipient runs. Recognized commands retain their existing behavior, while ordinary messages keep waiting without starting their dispatch observers.
* fix(server): offer queued commands once while running
Remember provider declines so timer retries do not repeat side effects or reinterpret a waiting message after provider state changes.
* fix(server): defer commands that request a session mode
An explicit mode belongs to a later turn. Keep those commands on the normal idle dispatch path so an out-of-band offer cannot ignore the requested mode or change the running turn.
The reaper signals a worker only after its socket accepts. The two
"cannot be opened for a moment" tests spawned a listening worker and
reaped without waiting for the listen, so on a loaded runner the reaper
found no socket, left the worker alive, and the test failed after
waitUntilGone's 5s deadline. Spawn the worker through a helper that
resolves once the socket is listening, as the other socket tests in
this file already do.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(pi): keep slashes and underscores in model display names
Pi model labels were built as `${provider}/${name}` and then cut at the
last `/`, so a free-text name such as "... ~60-70 tok/s, 52/56)" was shown
as "56)". Underscores were also rewritten to spaces ("IQ3_S" -> "IQ3 S").
The compact model trigger in the app repeated the last-`/` cut.
Build the Pi label from the model's own `name`/`id`: shorten only
path-like values with no whitespace (OpenRouter reports names like
"google/gemini-2.5-flash-lite"), and keep free-text names intact. The
compact trigger now strips only a leading provider namespace.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test(pi): cover model labels through the catalog and drop stale ACP copies
acp-agent.test.ts still imported transformPiModels, which the Pi label
fix removed, so its modelTransformer test and a stale copy of the old
Pi label tests failed. The modelTransformer test now supplies its own
transformer, and the Pi label cases run through fetchCatalog with the
reported model names instead of an exported helper.
Co-authored-by: Rahul Sharma <19687913+rms523@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(pi): keep colons inside free-text model names
The vendor-prefix strip cut a free-text Pi name at its first ": ", so
"Qwen3 IQ3_S (tail skip: on, 52/56)" showed as "on, 52/56)". Strip only
when the text before ": " has no parenthesis or comma, which keeps
OpenRouter's "Vendor: Model" names shortened.
Co-authored-by: Rahul Sharma <19687913+rms523@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Rahul Sharma <19687913+rms523@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
A PASEO_HOME on AFS passes the socket directory checks, then refuses the
Unix socket bind with EPERM, and the terminal worker failed to start. The
worker now binds each eligible candidate in turn and moves on when the
filesystem refuses the socket (EPERM, EACCES, EOPNOTSUPP, ENOTSUP). Other
listen errors still fail the start.
Fixes#9213
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
A turn the provider starts on its own, such as Claude waking after a
background subagent, has no user message before its reply. The last
assistant message lookup joined every adjacent assistant row, so it
returned the previous turn's reply with the new one appended, and the
220-character notification preview showed only the old reply.
Stop the backward scan at the turn boundary so the lookup returns only
the newest turn's reply, while chunks of one turn are still joined.
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 daemon drops a dictation stream when its STT session errors and answers
every later chunk with dictation_stream_error. The app only listened for
acks, so finishing waited 30s and reported a generic timeout. The sender now
fails finish with the daemon's message, and the daemon logs the failure that
dropped the stream once instead of nothing.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* 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.
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>
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>
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>
* 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>
* 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>
* 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.
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(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