* fix(server): skip Claude request-journal records when loading history
Claude Code 2.1.304+ journals each API request into the transcript as
api-request-blob records. They carry a message with a role and content,
so the history loader rendered them as assistant messages: restored
timelines gained the session's system context, including SessionStart
hook output and skill and tool listings.
Only user and assistant records are conversation turns once the system
record handling has run, so short-circuit every other type.
Closes#7102
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(claude): keep request context out of restored chats
Claude request-journal records contain message-shaped tool context. Only conversation records should enter the ordinary history mapper, after compaction and background task notifications are handled.
Co-authored-by: Kheva Mann <khevamann@users.noreply.github.com>
Co-authored-by: rogerluan <rogerluan@users.noreply.github.com>
---------
Co-authored-by: Roger Oba <rogerluan.oba@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: Kheva Mann <khevamann@users.noreply.github.com>
Co-authored-by: rogerluan <rogerluan@users.noreply.github.com>
* fix(server): close stale agent status after daemon restart
Repair persisted active statuses before serving clients. Let Claude process-tree cleanup run immediately after SDK close rather than waiting on an already closed control channel.
* test(app): expect closed agent status after daemon restart
* feat(git): default review to all branch changes
Keep the selected comparison stable while agents edit and commit so reviewing the complete result does not require switching scopes or interrupt unfinished comments.
* test(git): release Windows checkout handles during cleanup
Allow transient filesystem handles from subscription teardown to close before removing the test repository.
* fix(server): batch agent reports and completion notifications
Admit agent-originated messages immediately so a child can report and finish before one recipient-owned delivery. Keep human prompts direct, retain individual provenance through replay, and complete send receipts only after provider dispatch.
* test(server): wire queued delivery into bridge integration fixture
* test(server): resolve batching CLI fixture independently of cwd
Workspace CI runs from packages/server, while the original regression was verified from the repository root. Resolve the CLI entrypoint relative to this test file in both contexts.
* test(server): run batching CLI fixture with source exports
Server integration CI builds only the client dependency stack. Match the existing CLI subprocess fixtures so the send regression exercises workspace sources without requiring compiled server output.
* test(server): await persisted batch receipts within integration deadline
The provider-start callback precedes asynchronous receipt commits. Use the same explicit integration deadline as dispatch instead of the matcher default of one second on Windows CI.
* feat(hosts): connect to saved hosts through a daemon
* fix(hosts): validate safe targets and verify encrypted relay routes
* test(hosts): include relay coverage in existing CI contracts
* fix(cli): preserve validated addresses in daemon command hints
* fix(hosts): share daemon links across isolated routed sessions
Multiplex logical sessions over the monitored daemon connection and wrap original binary bytes in routing headers. Admit channels under their authenticated parent and current grants; preserve scoped delivery and physical send completion.
* fix(hosts): bound encrypted overload and initial acquisition
Check encrypted wire capacity before the async channel converts a resource limit into a physical connection error. Bound initial routed acquisition with the existing client timeout, then enable reconnect after admission.
* fix(hosts): keep compact row actions clear of host labels
Give compact connected-host rows separate text and action widths so long names and producer labels cannot compete with primary controls.
* refactor(hosts): remove management settings UI from phase one
Keep connected-host management in the CLI and shared SDK while preserving app saved connections and plugin access.
* test(hosts): control physical write backpressure across platforms
Hold real TCP writes until assertions finish instead of assuming a paused receiver exhausts every platform receive buffer. Preserve physical send settlement, byte identity, capacity and sibling checks.
* refactor(hosts): use the ordinary client contract over channel transports
Keep queuing, permission codes and reconnection independent of transport selection. Track submitted request outcomes generically while retaining connection error codes and structured causes.
* test(e2e): keep transient developer toasts from stalling checks
Concurrent locator handlers can wait for a dismiss button another handler removed. Dismiss existing toast DOM at document lifetime, including its open shadow root, without intercepting app actions.
* Create, prompt, and monitor agents across connected hosts (#7507)
* feat(hosts): delegate agents across connected hosts
Resolve MCP host operations through in-process commands for self and the existing routed client transport for other destinations. Keep ordinary parent labels, app sessions and idle finish notifications.
* test(app): normalize subagent fixtures through snapshots
* docs(protocol): clarify same-host parent labels
* fix(hosts): resolve subagents through destination sessions
A child address identifies its destination regardless of the connection used. Reuse the existing host candidate selection for discovered routes and direct connections, and keep navigation and row actions independent of the parent transport.
* fix(hosts): keep routed destinations distinct during discovery
A routed candidate names only the origin daemon. Match it within the named destination profile so two destinations discovered through the same origin retain separate identities and connections, including existing saved routes.
* feat(hosts): prompt and query agents on selected hosts
Extend the existing MCP host operation boundary with prompt, status, activity and list operations. Local calls retain their handlers and notification owner; selected destinations use ordinary client RPCs and the existing idle finish wait.
* test(e2e): preserve toast coverage with CSS hiding
* docs(hosts): translate connected host references
* perf(workspaces): stop duplicating setup output in progress snapshots
Keep the required combined log field empty for setup clients, which display per-command output. Preserve concatenation only for legacy agent bootstrap timeline cards whose released renderers still read it directly.
* refactor(workspaces): own setup exclusively at the workspace boundary
Preserve keyed modern agent worktree creation while retiring legacy placement that selected an agent-owned setup lifecycle. Keep output in per-command workspace snapshots and retain empty strings required by existing wire schemas.
* fix(server): avoid duplicate cwd in worktree provisioning request
* test(e2e): keep developer toasts out of concurrent app assertions
Concurrent layout measurements could invoke the same Playwright locator handler before its first dismissal finished, leaving checks waiting for a removed button. Hide only the Expo toast host through test styling while retaining console error capture.
* feat(website): serve paseo.sh in Simplified Chinese
Every page of the website now has a Simplified Chinese version under
/zh-CN: the interface, docs, blog posts, comparison pages, legal pages,
all changelog releases and the homepage mockup. English URLs are unchanged.
The URL alone decides the language. There is no browser-language redirect
and no stored preference, because either would have to redirect the
unprefixed English URLs that people share and search engines index.
Internal links carry the page's language instead, and hreflang alternates
point Chinese search results at /zh-CN.
Translated headings pin the English anchor with {#id}, so section links
work in both languages. content-translations.test.ts fails when a page
has no translation or a translation's headings drift from the English.
Changelog releases and plugin listings without a translation render
whole in English under a notice, so a release never waits on one.
Plugin manifests and the registry gain optional translations and
OVERVIEW.zh-CN.md fields; older clients and registries ignore them.
* feat(website): replace the native language select with an EN/ZH menu
The header showed an OS-native select whose popup did not match the site.
The trigger now shows the language abbreviated (EN, ZH) and opens a menu in
the app's dropdown style that names each language in itself, with its name
in the page language underneath. Rows are real links to the same page in
that language; arrows, Escape, outside presses and taps behave as a menu
button, and the menu keeps itself on screen when a narrow header pushes the
trigger toward an edge.
Also drops the stray space after the full-width comma in the Chinese
homepage subtitle.
* docs(website): translate main's new docs and 0.12.0 release notes
Main added Keep run workspaces to the schedules docs, rewrote plugin icons
around inline SVG, and promoted 0.12.0 with new entries. Bring the Chinese
pages and changelog in line so no section falls back to English.
* fix(server): leave plugin listing translations to the registry
The daemon rejected manifests whose translations the registry would refuse,
so a plugin main installs could fail to load here. Paseo never reads
translations; the registry validates them at publish. Docs now say which
checks are automated at publish and which are human review.
* docs(plugins): describe the registry's final overview translation discovery
* style(server): format manifest test
* test(app): measure sidebar rows one at a time
After a reload the developer error toast appears while expectVerticalOrder
measures every row at once. Each concurrent boundingBox runs the toast
locator handler, and only one of them resumes, so the poll timed out on
every attempt since #7424. Measuring sequentially keeps one action in flight.
* test(app): return sidebar row measuring to main
#7480 hides the developer toast instead of running a locator handler, so
measuring the rows concurrently no longer races it. Reverts 41ac23016.
* test(app): wait for the compact shell before opening compact Changes
The shell survives the breakpoint, so right after the resize the wide
Explorer could still be visible: the test skipped the Explorer toggle and
the tab then disappeared, or toggled at the wrong time. Wait for the
compact-shell marker, as the composer helpers do since #7424.
* docs(website): translate main's plugin file panel docs
* test(app): edit the code font size after the font family remount
A committed appearance change remounts the settings screen through
AppearanceStyleBoundary, and the new form starts from the stored size.
Filling the size before that remount lost the edit in CI.
* docs(website): translate main's client/ui import docs
Follows #7474: one /client/ui entry, StreamedText instead of useRevealedText,
SettingsGroup dropped from the settings table, and the new
'UI imports in v0.13' migration section.
* test(app): wait for the previous layout's file panel picker to leave
After a resize the old layout's picker animates out while the new one is
already mounted, so the Use button matched two elements and the strict
locator failed. Wait for the shell's layout and a single picker first.
* fix(files): report document MIME types for binary files
File reads now carry the document's MIME type for binary files, so a file panel can
hand the bytes to a viewer that needs the real type (application/pdf).
* feat(plugins): file panels
Plugins contribute file panels with addFilePanel. A file tab hosts the panels that claim the
file: the built-in Markdown, HTML and image panels, plugin panels, and Source, Paseo's editor,
which claims every text file and is always the last candidate. The panel is the tab body;
the bar shows the document's status and a switcher between the file's panels (side by side
up to three, two on a phone, a menu beyond that).
Paseo asks which panel opens a file only when a plugin panel is among several candidates,
once per open, and remembers the answer per extension or exact filename when told to. Open
with in the tab menu and the switcher change the tab's panel; Always use remembers it.
Opening a file at a line switches the tab to Source.
Panels read and write the host's document, so dirty state, autosave and conflicts stay
Paseo's. DocumentFrame shows bytes documents such as PDFs in the browser's viewer.
Replaces the file tab's Preview/Source mode toggle.
* feat(file-panels): choose and forget file panels in Settings > Files
Settings > Files lists each extension or filename where a plugin panel competes with
another candidate, or that has a remembered panel. Each row chooses the panel that opens
it, or Ask every time; Ask again forgets the choice. Source appears as a candidate for
text files. Panels no connected host offers can be forgotten but not chosen.
* docs(plugins): file panel examples and author reference
Adds the pdf-panel and markdown-panel examples, the File panels section of the plugin
reference, and an e2e spec that installs both examples, opens a PDF in the browser
viewer, and edits Markdown through Paseo's document across the switcher, Source,
autosave and conflicts.
* feat(file-panels): panels read and write through a file handle
The file tab stats the file and mounts its panel without reading it. Every
panel, built-in or plugin, gets a PluginFile handle: readText, readBytes, url,
version-checked writeText/writeBytes (PluginFileConflictError unless force),
and watch. useFileText, useFileBytes and useFileUrl read through it, and
Loading joins @getpaseo/plugin/client/ui. Panels own their loading state.
The host document pipeline, the explorer preview cache and the preview
lifecycle are deleted. The daemon classifies a file version from a bounded
sniff and writes base64 content as bytes behind fileByteWrites.
A deleted file keeps its panel mounted; a read confirms the deletion first,
so a remove-and-rewrite is not reported as one. Native Source decodes with
builtins and highlights in idle-time slices, the lines around the opening
line first, so a large file no longer blocks the JS thread.
* fix(file-panels): Settings offers Source where the picker does, and review follow-ups
- Settings > Files offers Source on every key except those a built-in panel of
another kind (Image) claims, so a plugin that alone claims a text extension
shows the same choices as the picker.
- Delete the unused isSourceFilePanel.
- The Markdown example warns with the file name when its unmount write fails,
rather than dropping the edit silently.
- Document that PluginFile stat fields are read at render time and that watch
or the read hooks are how a panel learns they changed.
* refactor(plugin): consolidate the client UI entrypoint
* fix(files): report document MIME types for binary files
File reads now carry the document's MIME type for binary files, so a file panel can
hand the bytes to a viewer that needs the real type (application/pdf).
* feat(plugins): file panels
Plugins contribute file panels with addFilePanel. A file tab hosts the panels that claim the
file: the built-in Markdown, HTML and image panels, plugin panels, and Source, Paseo's editor,
which claims every text file and is always the last candidate. The panel is the tab body;
the bar shows the document's status and a switcher between the file's panels (side by side
up to three, two on a phone, a menu beyond that).
Paseo asks which panel opens a file only when a plugin panel is among several candidates,
once per open, and remembers the answer per extension or exact filename when told to. Open
with in the tab menu and the switcher change the tab's panel; Always use remembers it.
Opening a file at a line switches the tab to Source.
Panels read and write the host's document, so dirty state, autosave and conflicts stay
Paseo's. DocumentFrame shows bytes documents such as PDFs in the browser's viewer.
Replaces the file tab's Preview/Source mode toggle.
* feat(file-panels): choose and forget file panels in Settings > Files
Settings > Files lists each extension or filename where a plugin panel competes with
another candidate, or that has a remembered panel. Each row chooses the panel that opens
it, or Ask every time; Ask again forgets the choice. Source appears as a candidate for
text files. Panels no connected host offers can be forgotten but not chosen.
* docs(plugins): file panel examples and author reference
Adds the pdf-panel and markdown-panel examples, the File panels section of the plugin
reference, and an e2e spec that installs both examples, opens a PDF in the browser
viewer, and edits Markdown through Paseo's document across the switcher, Source,
autosave and conflicts.
* feat(file-panels): panels read and write through a file handle
The file tab stats the file and mounts its panel without reading it. Every
panel, built-in or plugin, gets a PluginFile handle: readText, readBytes, url,
version-checked writeText/writeBytes (PluginFileConflictError unless force),
and watch. useFileText, useFileBytes and useFileUrl read through it, and
Loading joins @getpaseo/plugin/client/ui. Panels own their loading state.
The host document pipeline, the explorer preview cache and the preview
lifecycle are deleted. The daemon classifies a file version from a bounded
sniff and writes base64 content as bytes behind fileByteWrites.
A deleted file keeps its panel mounted; a read confirms the deletion first,
so a remove-and-rewrite is not reported as one. Native Source decodes with
builtins and highlights in idle-time slices, the lines around the opening
line first, so a large file no longer blocks the JS thread.
* fix(file-panels): Settings offers Source where the picker does, and review follow-ups
- Settings > Files offers Source on every key except those a built-in panel of
another kind (Image) claims, so a plugin that alone claims a text extension
shows the same choices as the picker.
- Delete the unused isSourceFilePanel.
- The Markdown example warns with the file name when its unmount write fails,
rather than dropping the edit silently.
- Document that PluginFile stat fields are read at render time and that watch
or the read hooks are how a panel learns they changed.
* fix(plugins): file events are objects, deletion is a typed error, DocumentFrame owns its fallback
- watch listeners receive { type: "changed" } | { type: "deleted" }, so later
versions can add fields without breaking them.
- PluginFileDeletedError joins PluginFileConflictError. The read hooks report a
deleted file with it, and a write over a deleted file rejects with it; Source
shows that as the deleted notice. PluginFileConflictError now means only
"changed on disk".
- DocumentFrame on Android shows Paseo's "<TYPE> files can't be shown on this
device" message for documents its WebView cannot display, so the PDF example
is useFileUrl + Loading + DocumentFrame with no platform branch.
* test(file-panels): Settings offers Source for a remembered panel no host has
* test(e2e): hide the developer error toast instead of clicking it away
The locator handler that dismissed #error-toast could match a toast that closed before its
click, then wait on it until the test timed out (agent-timeline-resume.spec.ts:45 failed every
attempt on this branch). Hiding the toast with CSS keeps it off app actions with no race.
* test(e2e): desktop browser-tabs hides developer toasts on its attached page
* fix(server): report archived agents correctly over MCP
An archived agent is resumed back into memory whenever something reads its history:
agent-loading passes `{ purpose: "history" }` to resumeAgentFromPersistence exactly when
`record.archivedAt` is set. `list_agents` then sees it as a live ManagedAgent, which
carries no archive timestamp, so AgentDirectory's archive predicate passes it and the
stored record's timestamp never reaches the result:
- `list_agents` returns the agent with `archivedAt: null`, because
serializeSnapshotWithMetadata merges only the title from storage. A caller reconciling
ownership from that list concludes an archived agent is still running.
- a default call (`includeArchived: false`) returns it anyway.
Storage stays the single owner of the timestamp. The MCP boundary merges the stored
record the same way the WebSocket path does in Session.enrichAgentPayload, reusing the
storage read it already makes for the title, and `archivedAt` becomes a projection option
beside `title`. `list_agents` filters archives after projection, where the timestamp is
known.
Copying the timestamp onto the managed agent was the other option and is worse:
unarchiveSnapshot clears only the stored record, so a managed copy would report an
unarchived agent as archived until it was reloaded.
The wire change is additive: `archivedAt` is already nullable and optional in the
protocol, and already populated on the stored path.
Fixes#4753
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(server): keep archived agents out of discovery after history reads
Apply archive filtering after stored metadata is projected in the shared directory. Exercise archive, history hydration, MCP discovery, WebSocket discovery and unarchive through a real daemon instead of mocked manager snapshots.
Co-authored-by: Thomas Van <minhthong@gmail.com>
---------
Co-authored-by: Thomas Van <minhthong@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>
* fix(server): notify the caller when a detached child finishes
`create_agent` with a detached relationship and `notifyOnFinish` arms a finish watcher
with `requireParentOwnership: true`. At fire time that guard checks that the child is
still labelled as the caller's, but resolveCreateAgentIntent strips the parent label from
a detached child on purpose, so the check can never pass and the caller never hears the
child it created finish.
The create path now requires parent ownership only for a child created with a parent.
The guard itself is unchanged: a parented child whose label later points elsewhere stays
silent, as agent-prompt.test.ts ("detaching a child ends its parent-owned finish
notification") requires. Only the create call knows the caller asked for a detached
child, which is why the fix lives there.
Tests drive the real finish watcher from createAgentCommand, with the finish published
as the manager publishes it: a detached child notifies its caller once, and a parented
child moved to another parent does not. Requiring ownership always fails the first;
never requiring it fails the second.
Fixes#6908
* test(server): verify detached completion through agent-scoped MCP
Exercise creation, stored parent labels, provider completion, and caller delivery
with the real daemon and injected provider clients. Cover detached and parented
creation and suppression after reparenting without replacing manager methods.
Co-authored-by: Thomas Van <minhthong@gmail.com>
---------
Co-authored-by: Thomas Van <minhthong@gmail.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Stop materializing and copying the entire conversation through lifecycle hooks. Keep the deprecated timeline field empty and direct plugins to bounded timeline reads.
* Upgrade to Expo 57 and unify Explorer across layouts
* feat(app): retain Explorer across layout and appearance changes
Keep one workspace Explorer host and destination-aware navigation so folding, theme updates and compact sheets preserve the current panel. Scope pull request discovery and timeline demand to active surfaces.
* fix(app): keep Explorer resize handles stretched through the dock
The shared frame moved the divider into an absolute column, leaving its horizontal handle without height. Restore the row so pointer drags reach it, preserving the existing resize and performance contract.
* fix(app): keep Explorer drag widths out of the shared stylesheet
Carry the existing inline sizing policy into the shared frame so pointer previews do not accumulate CSS rules.
* fix(test): align isolated test runtimes with Expo 57
Hoisted React consumers need the matching DOM renderer at the repository root. Automated Metro processes must not install native DevTools into disposable homes, and development toast overlays must not cover compact actions.
Keep Explorer journeys on the shared host and synchronize setup fixtures on daemon output rather than a one-second file-marker window. A delayed real child start reproduces the readiness failure on every platform.
* fix(test): await retained shell layout after composer resize
The gesture host now stays mounted across breakpoints, so its presence no longer identifies compact layout. Report the current layout on the retained host and synchronize composer journeys with that state.
* fix(app): preserve browser interactions in retained workspace hosts
Initially disabled gesture hosts still registered pointer and wheel listeners, while hover cards used window positions inside a workspace-local sheet portal. Respect initial gesture enablement and position cards relative to their measured floating host.
Keep developer-toast dismissal independent of pointer input and replacement toast visibility so modal, hover, and focus checks retain their input state.
* fix(test): share developer toast handling with Electron browser runs
The standalone Electron browser runner bypassed the browser fixture, allowing developer errors to cover Settings. Use the same non-pointer dismissal in both runners while retaining their console logs.
Offer Auto the same explicit resume action as Bypass and apply the saved mode before releasing plan approval. Ordinary Implement keeps selecting Accept File Edits.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
List snapshots do not subscribe modern clients to permission events. Activate that feed before both scenarios so the request assertion and auto-review absence assertion exercise delivery.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
A text-only refusal finishes successfully without identifying a child. Remove its provisional subagent row when the tool completes, while retaining the refusal in the tool timeline.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(workspaces): observe setup output only in the visible setup panel
Setup logs were requested for the whole session, including unrelated workspaces. Use directory status for discovery and source-owned workspace observations for details, preserving legacy delivery only for clients without the negotiated capability.
* fix(workspaces): publish external setup progress once per daemon
MCP and scheduled setup enter through the broadcast API. Publish them to the shared setup owner before session fanout so each observation gets one update and snapshots survive periods without connected clients. Keep the setup action available on older hosts to explain the required host update.
* fix(app): replace setup details with each observation snapshot
A host restart can return an empty setup snapshot. Apply that authoritative snapshot so an open panel does not retain output from the previous daemon. Assert setup membership requests as well as delivery in the browser lifecycle regression.
* test(workspaces): cover setup status catch-up after directory release
* test(workspaces): synchronize setup output and release fixture resources
Every contribution `icon` now takes a Lucide name, `{ svg }`, or a
component. Attachment sources take only the first two because composer
drafts persist the source icon.
The daemon's provider-icon check and the app's inline-SVG check are the
same function in the shared SDK root, so a plugin sees the same reasons
in both places. The app parses each icon once at registration and fails
the plugin with that reason. Rendering goes through one module that
turns any form into a component, so surfaces never branch on the form.
Startup inventories exceed the function argument limit when spread into push. Append each event individually in both benchmark collectors so large fixtures can reach their measurement summary.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Cursor discovery used one constant account key across all credential stores. Derive that key from the token subject in both discovery paths, and isolate unreadable identities by store, so host merging preserves each account while shared accounts still deduplicate.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(server): 正确编码 MCP 终端按键
send_terminal_keys 会将方向键、导航键和多数修饰键组合当作普通文字输入。
复用协议层编码器，并从终端前导序列恢复输入模式，保留 literal 和未知文本的原样发送行为。
补充 MCP 入口回归与真实 PTY 字节验证；MCP 文件 197 项测试通过，
最终终端回归 44 项通过，服务端类型、Lint 和格式检查通过。
Fixes#7337
* fix(terminal): keep MCP keys in the running program input mode
The worker mirror refreshed its input preamble only on snapshot reads, so MCP arrows used normal mode after an unattached program enabled application cursor keys. Carry the authoritative preamble with streamed worker messages before notifying consumers.
Co-authored-by: Aling33 <3489986145@qq.com>
---------
Co-authored-by: Aling33 <3489986145@qq.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
A Codex goal can start while thread/resume is still connecting, before the manager can subscribe. Retain those startup events until the first subscriber and apply them before registration returns, preserving run state and cancellation ownership.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: Hemanth <git@soni.im>
The runtime default cancels a pending IPv4 connect before slow routes complete, then fails immediately on unreachable IPv6. Give each relay address five seconds within the existing ten-second handshake deadline, covering both control and data sockets.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
A network path can swallow close notifications while the Hub socket remains open locally. Probe it with protocol ping/pong frames and feed stale sockets into the existing reconnect path.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
The crash-relaunch test waited with vi.waitFor's default one second for a
fresh runtime and MCP child to come up. On the Windows runner with three
workers that took longer once in six runs and failed main. The assertions
are unchanged; only the budget for the relaunch is realistic now.
Eight Playwright shards with two workers each, format/lint/relay/sdk combined into one routed quality job, Windows server integration in its own job, cancel-in-progress on every ref, one vitest start for the filtered integration files, no fan-in gate, and a deadline for the heap-bound directory search test that covers its 27,000-directory fixture on Windows.
First run on the Team plan: 19m48s from creation to last job with zero queue, all 21 jobs green, 224 runner-minutes. The same workflow under the old 20-job cap finished in 58 minutes with up to 40 minutes of queue per job.
Paseo tool rows put the variable part first ("QA messenger finished"), so
truncation hid the fixed part, and MCP calls showed only the humanized tool
name with no context. Every Paseo tool now has one catalog entry in
protocol/paseo-tool-presentation owning its fixed label, the input field
shown as context, and its detail layout. Agent-message events read
noun-first ("Agent finished" + sender) and use the Paseo icon; the app
ignored it before because the wire detail's legacy "bot" icon won.
Summaries are capped in code at 120 characters because prompts can be one
enormous line; the renderer is not trusted to clip them.
The activity curator behind `paseo logs` and get_agent_activity printed a
bare "[Agent message]" because the server tool-call type never declared the
agentMessage field the projection sets; it now prints the event, sender,
and body.
* fix(usage): retain last successful data when polls fail
Keep the latest poll outcome separate from its successful snapshot so errors remain visible without discarding known usage or advancing its freshness. Preserve attempt timestamps for response ordering and isolate retained values by scoped login set.
* fix(usage): preserve history through discovery failures
A failed account-store read does not confirm that an account was removed. Retain its existing host mapping until successful discovery replaces it, without carrying mappings across agent launch environments.
Late child frames were discarded after the launching turn ended, and parent completion cleared accumulated child actions. Keep card updates attached to the launching turn and release child actions on task completion.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(server): keep overlapping directory searches within their scan budget
Construct child paths and branch iterators as the round-robin walk consumes them. Eager sibling expansion retained hundreds of thousands of unvisited children per search and exhausted the heap when requests overlapped.
* test(server): stop directory-search children before fixture cleanup
---------
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Selecting Allow All now moves Copilot to Agent mode before enabling allow_all, so a session that was in Plan can implement the plan.
Closes#3855.
Co-authored-by: KiraPC <pasqualecarmine.carbone@gmail.com>
* Let agents steer a running turn from send_agent_prompt and paseo send
When an agent used the send_agent_prompt MCP tool on a target that was
mid-turn, sendPromptToAgent ran without activeTurnBehavior, so the
prompt path fell through to replaceAgentRun. That cancelled the target's
active turn and every provider subagent it had in flight. The web UI,
child finish notifications and schedules already pass "steer"; the MCP
tool and the CLI had no way to ask for it.
Add an optional activeTurnBehavior input to send_agent_prompt. It
defaults to "steer" for agent-scoped callers and to "interrupt" for
top-level callers, so existing top-level behaviour is unchanged. Add
--steer to paseo send. Document both and cover them with tests.
* fix(agents): retain finish notifications during steering acknowledgement
Observe completion before dispatch and hold delivery until acceptance. A replacement discards the displaced turn observation and starts a fresh listener before its iterator runs.
* fix(agents): preserve notification ownership when follow-ups fail
Keep the previous observation until dispatch succeeds and suppress duplicate delivery during acknowledgement. Decide whether to retain the running turn from the dispatch result, including side commands requested with interrupt.
* fix(agents): deduplicate notifications across overlapping follow-ups
---------
Co-authored-by: Mohamed Boudra <boudra.moha@gmail.com>
resolveClaudeCodeVersion() probes <configured command> --version and parsed any output with the generic fallback in parseClaudeCodeVersion. With a wrapper command (e.g. cux), that output is the wrapper's own version, which then failed every minimumClaudeCodeVersion gate and silently hid Opus 5.5, Opus 5, Fable 5, Sonnet 5.5 and Haiku 5.5. Only trust output that identifies itself as Claude Code (x.y.z (Claude Code)); anything else falls into the existing unknown-version path that does not gate models.
* fix(server): return actionable OpenCode bridge errors
* fix(server): surface OpenCode tool input errors
* fix(server): surface OpenCode v2 tool errors
* test(server): cover OpenCode v2 bridge errors
* fix(server): classify missing schedules as tool input
* fix(server): surface schedule state conflicts
* fix(server): validate schedule tool inputs
* fix(server): keep tool contracts while reporting OpenCode input errors
Preserve the removal of create_agent.background and keep legacy schedule fields hidden. Verify client errors through the real bridge, catalog, and schedule service rather than mocked schedule failures.
Co-authored-by: Felipe Fidelix <felipe@fdx.is>
* fix(server): distinguish caller errors from stored data failures
Tag validation failures where tool arguments are parsed, so schema errors from persisted state remain internal failures. Preserve the missing-agent error at its producer and translate it for prompt delivery. Real HTTP regressions fail for both misclassifications before this change.
* fix(server): preserve messages for unclassified tool failures
Keep existing error messages on HTTP 500 responses so agents can correct failed tool calls. Exercise missing workspaces through the real script service and bridge route.
* fix(server): preserve clearing schedule names with blank strings
---------
Co-authored-by: Felipe Fidelix <felipe@fdx.is>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
A pending thinking change retired the live query when mode, model, or command controls requested it. Reuse the query owned by the current turn and apply pending launch settings after the turn finishes.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(server): run slash commands sent by another agent out of band again
* fix(omp): send /steer and /follow-up as prompts so an idle agent starts a run
* test(omp): verify idle follow-ups and parent notifications
Cover real daemon and MCP delivery, and keep the fake runtime tests independent of an installed OMP executable.
Co-authored-by: Hung Le <22406703+nhthung@users.noreply.github.com>
* fix(omp): report idle follow-up admission failures
Use the existing prompt lifecycle for an idle command so acknowledgements and late rejections settle the child and notify its caller. Keep busy commands on the streaming prompt path, and accept one runtime prompt input object.
---------
Co-authored-by: Hung Le <22406703+nhthung@users.noreply.github.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
* fix(claude): show a background subagent's action log on its card
Claude Code answers a background Agent call at launch and streams the
child's frames afterwards. Since #6067 the sidechain tracker stopped
emitting the parent card once the call had its result, so the card's
log stayed empty. The tracker now rebuilds the card from the settled
call, keeping its status, output, and label, and adds the child's
action log.
Closes#6157
* fix(claude): release a settled subagent call when the child finishes
* fix(claude): keep a background subagent's card in the turn that settled it
A background child often keeps streaming after the parent's turn ends. Its
frames then rebuilt the settled card in the next turn with an empty log, and
the projection showed it as a second card for the same call. The settled call
now rebuilds the card only within the turn that answered it.
* test(claude): model the turn boundary in background card coverage
---------
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Generated image Markdown was concatenated into the preceding paragraph and rendered at inline size. Preserve paragraph boundaries around image output while retaining intentional inline image behavior.
Cursor agents never showed plan usage cards under their context details.
ACP sessions had no usageSession(), and the Cursor usage source only ran
global discovery, so per-agent discovery always came back empty.
Cursor ACP sessions now report a usage session (provider "cursor" plus
their launch env). The Cursor usage source resolves the cursor-agent
auth.json for that env. Sessions on CURSOR_API_KEY or CURSOR_AUTH_TOKEN,
the in-memory store, or the macOS Keychain (the default there) report
no login.
* fix(server): open worktree.terminals when a workspace is created on its own
runWorktreeSetupInBackground only opened the paseo.json worktree.terminals
when its caller passed runAutoTerminals, and only the fork-PR "allow setup"
handler did. workspace.create, the request the New Workspace screen sends,
ran worktree.setup and then skipped the terminals.
Both callers want the terminals, so the flag goes away: terminals follow a
successful setup on a newly created worktree. Reused worktrees stay excluded
by shouldBootstrap, and the agent setup continuation never reaches this
function, so nothing opens twice.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* test(server): run automatic terminal regressions in CI
Include workspace creation in the existing integration command, and append to the terminal marker so repeated command execution fails the regression.
* test(server): make workspace fixtures portable on Windows
Run the setup fixture through a command accepted by PowerShell, await its readiness, and fix the fixture Git line-ending policy. Allow Windows directory locks to settle during cleanup.
* test(server): expose setup failures and await fixture cleanup
Check the public setup status before terminal startup so failures distinguish setup errors from terminal creation. Use asynchronous directory removal so Windows cleanup retries leave the event loop available.
* test(server): start the Windows setup service asynchronously
The Windows regression starts its service but setup stays running, so terminal bootstrap is never reached. Launch the fixture service explicitly with Start-Process and retain the readiness and setup-completion assertions.
---------
Co-authored-by: David Yang <9925+davidyang@users.noreply.github.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Mohamed Boudra