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.
* 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.
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.
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>
Each streamed text or reasoning chunk was cut from the accumulated
message with slice, which can share the source string's storage. The
timeline store keeps every chunk, so a 128 KB reasoning part retained
about 128 MB: every chunk held the full message as it stood when the
chunk arrived. Long OpenCode v2 reasoning streams exhausted the daemon
worker's heap.
The timeline now emits an independent copy of each suffix, so retained
memory follows the length of the text.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Preserve the bundled Hoplite ACP adapter and provisioning transformer, activate it only after Add, and provide a searchable provider grid. Restore the contributor's original icon without the copyright mark.
Co-authored-by: Odin Glynn-Martin <odin.glynn@icloud.com>
Protocol contracts are available through the SDK peer dependency during development, but clean Git installs lack that dependency tree. Accept erased protocol type imports while retaining runtime dependency resolution and SDK ownership checks.
* fix: reject a question permission that would deliver no answer
Answering an `AskUserQuestion` permission in any shape but
`updatedInput.answers` keyed by one of its questions resolves as `allow` and
delivers nothing. The waiting agent is told "The user did not answer the
questions." — an affirmative falsehood rather than silence, so neither side can
see that anything failed. The responder sees success; the agent believes the
human declined and acts on that.
The field it is most natural to reach for cannot work. `selectedActionId` is
`z.string().optional()` with no membership check, and is read only for `plan`
kinds; a question advertises `actions: undefined`, so there is no action id to
name in the first place.
It is also unrecoverable. `respondToPermission` deletes the request from
`pendingPermissions` on entry, so the malformed answer consumes it and the retry
fails with "No pending permission request". The guard runs before that delete,
and `AgentManager` drops its own copy only once the call resolves, so both maps
survive the throw and the request stays answerable.
The answer contract is per provider, so the guard is in the Claude provider
rather than in `AgentManager`. Claude keeps an answer only when its key is a
question's full text or its header and its value is a non-empty string; Codex's
`mapCodexQuestionResponseByHeader` reads headers only and deliberately selects
each question's first option when nothing maps, which a shared guard would have
rejected; OpenCode reads headers only as well.
`resolveClaudeAskUserQuestionAnswers` is extracted from
`normalizeClaudeAskUserQuestionUpdatedInput` with no change in behaviour, and
both it and the guard now use it. So "would this deliver anything" is answered
by the code that does the delivering, rather than by a second copy of its rule —
which matters more than it looks, because that rule has two details easy to
restate wrongly: `readNonEmptyString` tests `value.trim()` for emptiness but
returns the *original* string, so a question named `" Which colour? "` is keyed
by that padding; and an empty `updatedInput.questions` array is a list that wins
over the request's own questions and maps nothing, not an absent one.
Verified on a live daemon over the MCP `respond_to_permission` path against a
seat whose question text is literally `" Which colour? "`: `selectedActionId`,
the trimmed key, an empty echoed question list and a numeric answer are each
rejected with the request still pending, and
`{"answers":{" Which colour? ":"Ochre"}}` then reaches the agent.
One known limit: the WebSocket path (`session.ts handleAgentPermissionResponse`)
catches the throw and emits an `activity_log` error rather than failing the
call, because a permission response is modelled as a notification. So
`paseo permit allow` still prints `allowed` and exits 0 for a rejected shape.
The destructive half is closed on every path — the request survives and the
agent is never told a falsehood — but closing the reporting half needs a
protocol change.
* test(claude): cover the question-answer-required retry path
A non-deliverable answer to an AskUserQuestion permission is rejected, but
the pending request survives it: a corrected retry against the same request
id is accepted, and the waiting agent receives the answer.
Mutation testing on a fork found that the existing suite does not pin this
ordering — moving the deliverability check to run after the request is
deleted from pendingPermissions still leaves every existing test green. This
test reds against that change.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
---------
Co-authored-by: Thomas Van <minhthong@gmail.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: paseo-bot <paseo-bot@users.noreply.github.com>
* fix(server): name an imported Claude agent after its /rename
Importing a Claude session named the agent after its first prompt even when the
session had been renamed in the CLI, so the name had to be set again by hand.
#4216 fixed the Import Session listing; the imported agent still kept the
prompt.
Read the last usable `custom-title` from the transcript and pass it as the
imported config title. The record is re-emitted on every save, so searching
backwards from the end of the file finds the current name without walking a
transcript that can reach tens of megabytes.
Only an explicit rename is carried over. Agents are named after their first
prompt line since #1563, so adopting the generated `ai-title` here would put
that LLM summary back.
Refs #2513
* refactor(server): drop unused generality from the Claude title reader
readLastClaudeTitle took content, type and field so it could read both
custom-title and ai-title records, which the listing needed before #4216 took
that over. Only the custom-title read is left, so the two extra parameters are
dead flexibility that also broke the single-object-parameter rule in
packages/server/CLAUDE.md.
Collapse it to readLastClaudeCustomTitle(content) and pull the record type into
a constant so the needle and the type check share one literal.
Hooks skipped: the repo-wide typecheck fails on two pre-existing Electron
typing errors in packages/desktop/src/main.ts that reproduce with this change
stashed. packages/server typecheck, lint and format all pass.
* test(server): drive the real resume path in the import title tests
The tests assigned an inline arrow function to client.resumeSession to keep
Claude Code from spawning. Importing replays the transcript from disk and never
starts a process, so the stub was never needed. Dropping it runs the real
resume path, which is what docs/testing.md asks for, and removes the arrow
assignment that docs/coding-standards.md rules out.
Hooks skipped: the repo-wide typecheck fails on two pre-existing Electron
typing errors in packages/desktop/src/main.ts that reproduce with this change
stashed. packages/server typecheck, lint, format and the 83 claude tests pass.
* fix(server): narrow the transcript read error instead of asserting it
The ENOENT check cast the caught value to NodeJS.ErrnoException to reach
`code`, which is the kind of assertion docs/coding-standards.md rules out:
narrow with `if`, do not silence the compiler. Add the same local type guard
pid-lock.ts already uses and test through it.
Behaviour is unchanged. A value that is not an Error still falls through to
the rethrow, exactly as reading `code` off the assertion did.
Hooks skipped: the repo-wide typecheck fails on two pre-existing Electron
typing errors in packages/desktop/src/main.ts that reproduce with this change
stashed. packages/server typecheck, lint, format and the 83 claude tests pass.
* fix(server): let claudeProjectDirSync resolve the Claude config dir
The import title reader built the config dir itself through os.homedir(),
but os is no longer imported here, so the fallback threw a ReferenceError
whenever CLAUDE_CONFIG_DIR was unset. claudeProjectDirSync already resolves
the same default.
* test(server): give the import title helpers object parameters
* fix(server): preserve imported session renames across history locations
The import title reader must use the same provider environment and transcript
lookup as history replay. Otherwise an imported session has its history but
loses its explicit name when its configuration directory or project changed.
Co-authored-by: platanus-kr <platanus.kr@gmail.com>
---------
Co-authored-by: platanus-kr <platanus.kr@gmail.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
ACP command updates discarded input hints before the autocomplete command list reached consumers. Preserve the advertised hint, retaining the empty hint for commands without input metadata.
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
Co-authored-by: bwestlund17 <brian.westlund@proton.me>
Mohamed Boudra