Keep agent identity and origin authority stable through disconnects, destination changes, and scoped disposal. Share the resolver with trusted daemon consumers and plugins, using ordinary sessions and per-admission permission ceilings. Expose MCP host discovery through that boundary as the first checkpoint toward durable fleet subagents.
Keep queuing, permission codes and reconnection independent of transport selection. Track submitted request outcomes generically while retaining connection error codes and structured causes.
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.
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.
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.
* 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