test(website): reproduce plugin search dropping a term typed before hydration

Typing in the plugin search box before the page's scripts run leaves the term in the box but not in React state, so Enter searches without it.
2026-10-17 06:42:40 +00:00 · 2026-10-07 09:25:30 +02:00
42 changed files with 153 additions and 1721 deletions
@@ -1,12 +1,12 @@
 # Changelog

-## 0.11.0 - 2026-10-07
+## 0.11.0-beta.5 - 2026-10-06

 ### Added

 - Added Muse Code as a provider, with model, approval mode, and reasoning effort controls ([#5719](https://github.com/getpaseo/paseo/pull/5719), [#5775](https://github.com/getpaseo/paseo/pull/5775) by [@millerben95](https://github.com/millerben95))
 - Added Antigravity as a provider that drives the installed `agy` CLI, always in Full access ([#5714](https://github.com/getpaseo/paseo/pull/5714), [#5795](https://github.com/getpaseo/paseo/pull/5795))
- Added Usage, opened from the sidebar footer as a dialog on desktop and a sheet on mobile, showing each subscription account's quota windows with Refresh ([#5465](https://github.com/getpaseo/paseo/pull/5465), [#5685](https://github.com/getpaseo/paseo/pull/5685), [#5786](https://github.com/getpaseo/paseo/pull/5786), [#5805](https://github.com/getpaseo/paseo/pull/5805), [#5921](https://github.com/getpaseo/paseo/pull/5921), [#6216](https://github.com/getpaseo/paseo/pull/6216))
+- Added a Usage screen, opened from the sidebar footer, showing each subscription account's quota windows with Refresh ([#5465](https://github.com/getpaseo/paseo/pull/5465), [#5685](https://github.com/getpaseo/paseo/pull/5685), [#5786](https://github.com/getpaseo/paseo/pull/5786), [#5805](https://github.com/getpaseo/paseo/pull/5805), [#5921](https://github.com/getpaseo/paseo/pull/5921))
 - Added an opt-in Usage summary to the sidebar footer that shows the windows you pin ([#5903](https://github.com/getpaseo/paseo/pull/5903), [#5975](https://github.com/getpaseo/paseo/pull/5975), [#6089](https://github.com/getpaseo/paseo/pull/6089))
 - Added Usage discovery of ChatGPT logins from Codex CLI, OpenCode, Pi, and OMP ([#5844](https://github.com/getpaseo/paseo/pull/5844))
 - Added Usage discovery of Claude logins from the Claude Code credential file, the macOS keychain, Pi, and OMP ([#5844](https://github.com/getpaseo/paseo/pull/5844))
@@ -16,12 +16,9 @@
 - Added Fast mode and an Auto thinking level to OMP ([#5550](https://github.com/getpaseo/paseo/pull/5550) by [@n24q02m](https://github.com/n24q02m), [@abhi-wan-kenobi](https://github.com/abhi-wan-kenobi))
 - Added MCP servers to OMP schedules and Hub runs ([#5550](https://github.com/getpaseo/paseo/pull/5550) by [@omercnet](https://github.com/omercnet))
 - Added a Content width setting for the maximum width of chat and Markdown files on wide screens ([#5680](https://github.com/getpaseo/paseo/pull/5680))
- Added syntax highlighting for Vue files ([#6205](https://github.com/getpaseo/paseo/pull/6205) by [@Davnn1](https://github.com/Davnn1))
 - Added `agents.providers.<id>.options` in `config.json` as default options for every provider, with per-agent overrides ([#5780](https://github.com/getpaseo/paseo/pull/5780))
 - Added the terminal key bar and Paste to terminal panes on iPad and Android tablets ([#5712](https://github.com/getpaseo/paseo/pull/5712) by [@lardissone](https://github.com/lardissone))
 - Added screens and sidebar header and footer items to the plugin SDK ([#5685](https://github.com/getpaseo/paseo/pull/5685))
- Added a display name, icon, screenshots, and videos to the plugin manifest ([#6263](https://github.com/getpaseo/paseo/pull/6263))
- Added an `OVERVIEW.md` template to `paseo plugin init` for plugin registry listings ([#6226](https://github.com/getpaseo/paseo/pull/6226))
 - Added usage sources to the plugin SDK ([#5465](https://github.com/getpaseo/paseo/pull/5465), [#5876](https://github.com/getpaseo/paseo/pull/5876))
 - Added `spawnProcess()`, `execCommand()`, and `terminateProcess()` to the plugin SDK for launching CLIs, including Windows `.cmd` and `.bat` scripts ([#6151](https://github.com/getpaseo/paseo/pull/6151))
 - Added `client.playAudio()` to the plugin SDK for playing audio on every client ([#5976](https://github.com/getpaseo/paseo/pull/5976))
@@ -30,9 +27,10 @@

 ### Changed

- Changed `paseo plugin add owner/slug` to install the reviewed plugin from the plugin registry, so local directories need a path such as `./slug` and direct GitHub installs need `github:owner/repo` ([#6224](https://github.com/getpaseo/paseo/pull/6224))
+- Enabled the plugin registry by default: `paseo plugin add owner/slug` installs a reviewed artifact even when a local directory matches; use explicit local paths (including `.`, `..`, and Windows drive or UNC paths), and use `github:owner/repository` for direct GitHub installs. Registry connection, missing-ID, and `--ref` errors include recovery steps.
+
 - Changed the context window details to show usage for the account the agent runs under, including custom `CLAUDE_CONFIG_DIR` and `CODEX_HOME` homes ([#5465](https://github.com/getpaseo/paseo/pull/5465))
- Changed the context window details on desktop to a hover card with Refresh ([#5975](https://github.com/getpaseo/paseo/pull/5975), [#6185](https://github.com/getpaseo/paseo/pull/6185))
+- Changed the context window details on desktop to a hover card with Refresh ([#5975](https://github.com/getpaseo/paseo/pull/5975))
 - Changed the context window meter to show before an agent's first turn ([#6089](https://github.com/getpaseo/paseo/pull/6089))
 - Changed Codex Fast to a Speed menu listing the Normal, Fast, and Ultrafast speeds each model offers, shown as a lightning bolt on desktop that turns yellow while Fast or Ultrafast is selected ([#5708](https://github.com/getpaseo/paseo/pull/5708), [#6152](https://github.com/getpaseo/paseo/pull/6152) by [@Nurshot](https://github.com/Nurshot))
 - Changed Explorer tabs to work like workspace tabs, with a + menu, drag and drop, and Close for Files and Changes ([#5942](https://github.com/getpaseo/paseo/pull/5942))
@@ -48,18 +46,12 @@
 ### Fixed

 - Fixed Claude agents never showing Thought rows on Claude Opus 4.7 and later ([#4355](https://github.com/getpaseo/paseo/pull/4355) by [@ThePharmer](https://github.com/ThePharmer))
- Fixed a Claude agent showing as running while only its background helpers worked, and a send or Stop killing those helpers ([#6295](https://github.com/getpaseo/paseo/pull/6295) by [@IsakPersson](https://github.com/IsakPersson))
- Fixed a Claude agent in Auto mode failing to switch modes when Claude Code uses Bedrock or Vertex ([#6272](https://github.com/getpaseo/paseo/pull/6272))
- Fixed a Claude subagent's auto-mode report showing as a raw SubagentHandback tool card instead of markdown ([#6248](https://github.com/getpaseo/paseo/pull/6248))
- Fixed background Claude subagent cards showing as a bare "Task" that stayed running, as "Agent" after a daemon restart, or unlabeled when two launch together ([#6067](https://github.com/getpaseo/paseo/pull/6067), [#6100](https://github.com/getpaseo/paseo/pull/6100), [#6268](https://github.com/getpaseo/paseo/pull/6268))
+- Fixed a background Claude subagent's card showing as a bare "Task" that stayed running, or as "Agent" after a daemon restart ([#6067](https://github.com/getpaseo/paseo/pull/6067), [#6100](https://github.com/getpaseo/paseo/pull/6100))
 - Fixed Claude Code terminals not showing as needing input when Claude is idle ([#6022](https://github.com/getpaseo/paseo/pull/6022))
 - Fixed Claude usage calling a rate-limited login again before its retry time ([#6089](https://github.com/getpaseo/paseo/pull/6089))
 - Fixed a Claude agent that entered plan mode on its own still showing and storing its previous mode ([#6074](https://github.com/getpaseo/paseo/pull/6074))
 - Fixed a resumed agent returning to its creation-time mode after its mode was changed in the session ([#5140](https://github.com/getpaseo/paseo/pull/5140) by [@ThePlenkov](https://github.com/ThePlenkov))
 - Fixed ACP plugin providers failing to launch a `.cmd` or `.bat` CLI on Windows ([#6151](https://github.com/getpaseo/paseo/pull/6151))
- Fixed ACP agents running on their default model when the configured model is one the agent does not advertise ([#6273](https://github.com/getpaseo/paseo/pull/6273))
- Fixed archiving an ACP agent leaving its provider running when the provider never answers close ([#6213](https://github.com/getpaseo/paseo/pull/6213) by [@apple-ouyang](https://github.com/apple-ouyang))
- Fixed an archived ACP agent showing an empty chat after its worktree was removed ([#6228](https://github.com/getpaseo/paseo/pull/6228))
 - Fixed ACP agents rejecting every following message after a turn failed with a permission request open ([#6045](https://github.com/getpaseo/paseo/pull/6045))
 - Fixed the context window meter never appearing for ACP agents that report context usage ([#4848](https://github.com/getpaseo/paseo/pull/4848) by [@apple-ouyang](https://github.com/apple-ouyang))
 - Fixed schedule runs and workspace metadata recording `[object Object]` when an ACP agent rejects a session setting ([#5765](https://github.com/getpaseo/paseo/pull/5765))
@@ -74,14 +66,12 @@
 - Fixed opening an archived OMP agent starting an `omp` process that stayed running ([#5550](https://github.com/getpaseo/paseo/pull/5550) by [@thomasvan](https://github.com/thomasvan))
 - Fixed an OMP turn staying running forever when the run contains a message Paseo does not show, such as an OMP rule reminder ([#6112](https://github.com/getpaseo/paseo/pull/6112))
 - Fixed a prompt OMP rejects, such as for a missing API key, ending as a completed turn with no error ([#6110](https://github.com/getpaseo/paseo/pull/6110), [#6115](https://github.com/getpaseo/paseo/pull/6115))
- Fixed reopened OMP chats showing "Custom message" rows for compactions and other entries OMP writes on its own ([#6198](https://github.com/getpaseo/paseo/pull/6198), [#6215](https://github.com/getpaseo/paseo/pull/6215))
 - Fixed Pi and OMP sessions whose model was removed failing to import or reopen ([#6061](https://github.com/getpaseo/paseo/pull/6061))
 - Fixed Pi agents on Pi 0.99 starting without Paseo's MCP servers when `pi-mcp-adapter` is not installed ([#5762](https://github.com/getpaseo/paseo/pull/5762) by [@ArietidsZ](https://github.com/ArietidsZ))
 - Fixed a running Pi subagent showing an empty transcript until it finished ([#5755](https://github.com/getpaseo/paseo/pull/5755))
 - Fixed a grouped Tintinweb pi-subagents completion marking only its first agent completed and leaving the rest on working ([#5826](https://github.com/getpaseo/paseo/pull/5826))
 - Fixed OpenCode `ask` rules for `paseo_*` tools running the tool without a prompt ([#5801](https://github.com/getpaseo/paseo/pull/5801) by [@ymarcus93](https://github.com/ymarcus93))
 - Fixed the first OpenCode prompt waiting for the event stream timeout when the OpenCode server was slow to become ready ([#5873](https://github.com/getpaseo/paseo/pull/5873) by [@axsuul](https://github.com/axsuul))
- Fixed OpenCode v2 agents staying running after a question is dismissed or a tool permission is denied ([#6177](https://github.com/getpaseo/paseo/pull/6177), [#6188](https://github.com/getpaseo/paseo/pull/6188))
 - Fixed the Nix packages failing to start the daemon and to open terminals ([#5523](https://github.com/getpaseo/paseo/pull/5523) by [@wongcallum](https://github.com/wongcallum))
 - Fixed OpenCode v2 agents failing to start on the Nix packages ([#5988](https://github.com/getpaseo/paseo/pull/5988))
 - Fixed each Paseo skill appearing twice in Codex's skill list ([#5827](https://github.com/getpaseo/paseo/pull/5827) by [@3ae3ae](https://github.com/3ae3ae))
@@ -95,18 +85,12 @@
 - Fixed Codex terminal rows reading only "Terminal" without the command on current Codex ([#5774](https://github.com/getpaseo/paseo/pull/5774))
 - Fixed the composer showing the catalog default thinking level instead of the one the agent runs on ([#5804](https://github.com/getpaseo/paseo/pull/5804))
 - Fixed the composer showing another model's label when the agent's model is missing from the loaded catalog ([#5796](https://github.com/getpaseo/paseo/pull/5796))
- Fixed the chat jumping back by several screens when scrolling up through older history on web and desktop ([#5945](https://github.com/getpaseo/paseo/pull/5945), [#5970](https://github.com/getpaseo/paseo/pull/5970), [#6172](https://github.com/getpaseo/paseo/pull/6172))
+- Fixed the chat jumping back by several screens when scrolling up through older history on web and desktop ([#5945](https://github.com/getpaseo/paseo/pull/5945), [#5970](https://github.com/getpaseo/paseo/pull/5970))
 - Fixed images in chat shifting the text below them when they finish loading ([#5970](https://github.com/getpaseo/paseo/pull/5970))
 - Fixed copying all the code in a chat code block sometimes including its ``` fence lines ([#6138](https://github.com/getpaseo/paseo/pull/6138))
 - Fixed copying across a code block nested in a numbered list item renumbering the next item ([#6158](https://github.com/getpaseo/paseo/pull/6158))
- Fixed copying a chat selection across an image losing its alt text and source, or including the image when the selection started below it ([#6181](https://github.com/getpaseo/paseo/pull/6181), [#6195](https://github.com/getpaseo/paseo/pull/6195))
 - Fixed relative `path:line` file links in chat opening at the first line referenced for that file ([#5653](https://github.com/getpaseo/paseo/pull/5653) by [@3ae3ae](https://github.com/3ae3ae))
 - Fixed PR comments with linked pictures showing raw HTML tags and losing the image link ([#5968](https://github.com/getpaseo/paseo/pull/5968))
- Fixed text typed by the browser tool appearing in your message box instead of the browser tab ([#6207](https://github.com/getpaseo/paseo/pull/6207))
- Fixed Astro expressions losing their colors after a nested template string ([#6219](https://github.com/getpaseo/paseo/pull/6219))
- Fixed downloading files whose names contain non-ASCII characters ([#6278](https://github.com/getpaseo/paseo/pull/6278), [#6281](https://github.com/getpaseo/paseo/pull/6281) by [@dillonzq](https://github.com/dillonzq), [@jasonhnd](https://github.com/jasonhnd))
- Fixed the PR panel, sidebar workspace status, and "Worked for" line showing English in other app languages ([#6196](https://github.com/getpaseo/paseo/pull/6196), [#6208](https://github.com/getpaseo/paseo/pull/6208), [#6225](https://github.com/getpaseo/paseo/pull/6225) by [@dillonzq](https://github.com/dillonzq))
- Fixed French translations that read as word-for-word machine translation ([#6004](https://github.com/getpaseo/paseo/pull/6004) by [@fxlelouarn](https://github.com/fxlelouarn))
 - Fixed the desktop window not dragging from the workspace header after scrolling a long chat ([#5233](https://github.com/getpaseo/paseo/pull/5233) by [@Zhou-Ruichen](https://github.com/Zhou-Ruichen))
 - Fixed opening an agent on a touch screen in the desktop layout raising the on-screen keyboard ([#5477](https://github.com/getpaseo/paseo/pull/5477) by [@dinhphieu](https://github.com/dinhphieu))
 - Fixed Option+arrow, Cmd+arrow, and Cmd+Backspace line editing in the macOS terminal ([#3339](https://github.com/getpaseo/paseo/pull/3339) by [@gpambrozio](https://github.com/gpambrozio))
@@ -114,16 +98,12 @@
 - Fixed a new worktree workspace being archived when its `paseo.json` cannot be parsed ([#6036](https://github.com/getpaseo/paseo/pull/6036) by [@3ae3ae](https://github.com/3ae3ae))
 - Fixed workspace script status not updating in other connected clients ([#6007](https://github.com/getpaseo/paseo/pull/6007) by [@swbiggart](https://github.com/swbiggart))
 - Fixed agents and terminals inheriting the voice library path, which truncated Git Bash's PATH on Windows ([#5987](https://github.com/getpaseo/paseo/pull/5987) by [@hanh9898](https://github.com/hanh9898))
- Fixed dictation failing until the model was deleted by hand when the daemon stopped while extracting a local speech model ([#6210](https://github.com/getpaseo/paseo/pull/6210) by [@3ae3ae](https://github.com/3ae3ae))
 - Fixed macOS hosts showing as `UNKNOWN` when the network supplies no hostname ([#5922](https://github.com/getpaseo/paseo/pull/5922))
- Fixed `paseo daemon status` reporting a daemon in a Linux VM as stopped after the host wakes from sleep ([#6279](https://github.com/getpaseo/paseo/pull/6279))
- Fixed relay reconnects being ignored after a relay connection stalled before its handshake ([#5648](https://github.com/getpaseo/paseo/pull/5648) by [@3ae3ae](https://github.com/3ae3ae))
 - Fixed `paseo daemon run` exiting with "Daemon failed to start" when the program that launched it stops reading its output ([#6117](https://github.com/getpaseo/paseo/pull/6117))
 - Fixed CLI commands crashing with `EPIPE`, and the Windows desktop app showing an error dialog, when their output stops being read ([#6097](https://github.com/getpaseo/paseo/pull/6097))
 - Fixed daemon self-update on a linked global install giving the wrong reason for refusing ([#6095](https://github.com/getpaseo/paseo/pull/6095))
 - Fixed daemon self-update failing for an npm install under a prefix other than npm's global prefix ([#5649](https://github.com/getpaseo/paseo/pull/5649) by [@3ae3ae](https://github.com/3ae3ae))
 - Fixed opening an archived agent whose worktree was removed showing "Workspace unavailable" when the workspace had no recorded branch ([#5694](https://github.com/getpaseo/paseo/pull/5694))
- Fixed a failed send to an archived agent whose directory was removed taking it out of History ([#6255](https://github.com/getpaseo/paseo/pull/6255))
 - Fixed a host's version staying stale on the host page after its daemon restarts ([#5351](https://github.com/getpaseo/paseo/pull/5351) by [@bashrusakh](https://github.com/bashrusakh))
 - Fixed Remote SSH hosts failing to connect to a password-protected daemon, with a new Daemon password field ([#6081](https://github.com/getpaseo/paseo/pull/6081) by [@royenheart](https://github.com/royenheart))
 - Fixed removing a host during its first connection attempt not stopping the connection ([#5722](https://github.com/getpaseo/paseo/pull/5722))
@@ -143,7 +123,6 @@
 - Fixed `paseo schedule update --no-max-runs` and `--no-expires-in` failing before reaching the daemon ([#5973](https://github.com/getpaseo/paseo/pull/5973) by [@Mar-garet](https://github.com/Mar-garet))
 - Fixed `daemon.log` saying nothing when a resumed Claude agent's transcript is missing or cannot be read ([#5818](https://github.com/getpaseo/paseo/pull/5818) by [@gabrielgiordan](https://github.com/gabrielgiordan))
 - Fixed reloading a plugin adding `[System Error] Provider connection closed` to finished chats on its provider ([#5579](https://github.com/getpaseo/paseo/pull/5579))
- Fixed `paseo plugin add .` looking for the plugin in the daemon's directory instead of the CLI's ([#6239](https://github.com/getpaseo/paseo/pull/6239))
 - Fixed plugin settings screens on desktop having no way back to the Plugins page ([#5620](https://github.com/getpaseo/paseo/pull/5620))
 - Fixed plugin client code failing to import npm packages that declare only `main` or `module` ([#5838](https://github.com/getpaseo/paseo/pull/5838))
 - Fixed the SDK's `send()` and `run()` rejecting `activeTurnBehavior` in TypeScript ([#5605](https://github.com/getpaseo/paseo/pull/5605) by [@wjxdy](https://github.com/wjxdy))
@@ -50,8 +50,6 @@ Paseo is a desktop, mobile, web, and CLI app for coding agents. Open the desktop
 - **Cross-device:** iOS, Android, desktop, web, and CLI. Start work at your desk, check in from your phone, script it from the terminal.
 - **Privacy-first:** Paseo doesn't have any telemetry, tracking, or forced log-ins.

-[Run parallel tasks in Paseo](https://paseo.sh/docs/parallel-development): start agents in separate worktrees, review their diffs, run each app, and check it in the built-in browser.
-
 ## Plugins

 Plugins run on the daemon and show up in every client you connect, with the same UI on desktop, web,
@@ -197,11 +197,10 @@ Claude Code announces subagent lifecycle on the SDK stream (`task_started` / `ta

 - **Not every announced task belongs in the track.** Task subagents announce as `local_agent` and workflows as `local_workflow`; a backgrounded shell announces as `local_bash` with the same `tool_use_id` shape, and ambient housekeeping sets `skip_transcript`. The Claude provider normalizes a workflow to a generic provider-subagent descriptor titled `Workflow`, using Claude's summary as its description and timeline opener. Shared storage, protocol, and UI do not distinguish it from another provider subagent.
 - **A task that was never declared gets no descriptor, by any route.** Filtered tasks still emit `task_notification`s carrying a `tool_use_id`, and still emit frames carrying `parent_tool_use_id`. Attributing either produces a descriptor with no identity and a defaulted `running` status — a nameless row that never finishes. Status, presentation updates, and sidechain frames all route through the declaration table.
- **Task ids are session-scoped, not turn-scoped.** Cancelling a turn must not clear the routing table: a backgrounded child settles after the interrupt and needs its descriptor to still exist. Cancellation instead terminalizes the declared children that were running in the foreground, and a later `task_notification` is free to correct that guess. Backgrounded children are identified by `is_backgrounded` on `task_started` (set at spawn; a resumed subagent is always background) or, when moved there later, on `task_updated.patch`.
+- **Task ids are session-scoped, not turn-scoped.** Cancelling a turn must not clear the routing table: a backgrounded child settles after the interrupt and needs its descriptor to still exist. Cancellation instead terminalizes the declared children that were running in the foreground, and a later `task_notification` is free to correct that guess. Backgrounded children are identified by `task_updated.patch.is_backgrounded`.
 - **A resumed task can be announced again with a new `tool_use_id`.** The first Task tool id remains the canonical descriptor and later ids are routing aliases for the same session-scoped task. The resumed prompt is added to that child timeline.
 - **Effort is only reachable through hooks.** It appears nowhere on the message stream at any depth, and the level Paseo requests is not necessarily the level that runs — a model that does not support it is silently downgraded. A hook firing inside a subagent reports the active post-downgrade level next to its `agent_id`, which is the same id `task_started` calls `task_id`.
 - **Backgrounded subagents emit no frames carrying `parent_tool_use_id` at all.** Everything keyed off that field sees nothing for one; they are visible only because the task protocol announces them.
- **Only `system/init` and `result` bracket a main-session turn.** Background subagents emit neither on the main stream, while their task frames, their own background jobs' `task_notification`, and `rate_limit_event` arrive with no `parent_tool_use_id`, the same shape as main-session work. `session_state_changed` stays `running` for as long as any background subagent lives (Claude Code 2.1.280), so it cannot open a turn; its `idle` can close one.
 - **Nested ownership comes from the launching sidechain, not `spawn_depth` alone.** A sidechain's Agent or Bash tool call records the direct owner of that `tool_use_id`; the following `task_started` inherits it. This routes a grandchild descriptor and child-owned background notifications without relying on labels or flattening them into the managed parent.
 - **On replay, `<session>/subagents/` holds every descendant beside the root.** Resolve the tree one proven generation at a time: the root transcript admits direct children, then each admitted sidechain transcript admits its children by `toolUseId`. `spawnDepth` orders candidates but does not establish ownership. Unresolved sidecars remain excluded as ambient or unrelated work.
 - **Replay `totalTokens` is a context-size reading, not cumulative spend.** Claude Code finalizes a subagent by summing the _last_ assistant message's usage block and shipping that as `usage.total_tokens`. Summing per-entry usage instead multiplies the cached prefix by the turn count and reports a number several times larger than the live path.
@@ -103,7 +103,7 @@ OpenCode owns user message IDs. Do not pass Paseo-generated IDs to OpenCode prom

 Active-turn steering is an optional `AgentSession.steerActiveTurn` operation. The manager owns admission against its exact foreground turn, canonical user-message creation, echo reconciliation, and falls back to the normal interrupt-and-replace path only when the adapter reports `unavailable`. An adapter error leaves the steer's fate ambiguous and must surface without an interrupt or retry. Codex calls `turn/steer` with the native expected turn and Paseo client user-message ID. Claude pushes an admitted steer into the exact active SDK query input; isolated control commands remain unavailable. OpenCode calls `session/prompt_async` with an OpenCode-generated message ID; the server queues the prompt while busy and the next LLM call in the same Paseo turn includes it. Pi sends its native `steer` RPC, which queues the message for delivery after the in-flight assistant turn's tool calls. Slash-command inputs report `unavailable` because pi rejects extension commands on the steer path, and echo identity is correlated by message text because pi's steer RPC takes no message ID. A missing session reports `unavailable` and uses the normal interrupt fallback.

-A steering adapter also owes its interrupt: stopping a turn must discard the steers the provider has not read yet, or one of them resumes the turn the user just stopped. Codex clears pending input when it aborts a turn; Claude does not, so its adapter cancels the SDK messages it queued before calling `query.interrupt()`. It calls `query.interrupt()` only while a main-session turn is in flight (between `system/init` and that turn's `result`): with the main session idle, an interrupt reaches only background subagents and no result follows it, so the adapter withdraws its unstarted messages and stops there. The adapter also declares `perTaskStopAffordance`, because without it the CLI kills every background subagent on interrupt. Pi requires `clear_queue` before `abort`; older binaries without that RPC retain their native queue behavior until the pi compatibility floor reaches 0.84.4.
+A steering adapter also owes its interrupt: stopping a turn must discard the steers the provider has not read yet, or one of them resumes the turn the user just stopped. Codex clears pending input when it aborts a turn; Claude does not, so its adapter cancels the SDK messages it queued before calling `query.interrupt()`. Pi requires `clear_queue` before `abort`; older binaries without that RPC retain their native queue behavior until the pi compatibility floor reaches 0.84.4.

 `SteerActiveTurnOptions.clearPendingPermissions` makes permission release part of the provider contract. A provider that accepts such a steer queues it first, denies permissions blocking its delivery, and stops once the steer is read. Steers without the flag leave permissions open. A denied plan remains in the timeline because the pending card was the only other copy of its text.

@@ -1,7 +0,0 @@
-Added
- Added Muse Code as a provider, with model, approval mode, and reasoning effort controls
- Added Antigravity as a provider that drives the installed agy CLI, always in Full access
- Added Usage, opened from the sidebar footer as a dialog on desktop and a sheet on mobile, showing each subscription account's quota windows with Refresh
- Added an opt-in Usage summary to the sidebar footer that shows the windows you pin
-
-Full notes: https://paseo.sh/changelog
@@ -1,7 +0,0 @@
-Added
- Added Muse Code as a provider, with model, approval mode, and reasoning effort controls
- Added Antigravity as a provider that drives the installed agy CLI, always in Full access
- Added Usage, opened from the sidebar footer as a dialog on desktop and a sheet on mobile, showing each subscription account's quota windows with Refresh
- Added an opt-in Usage summary to the sidebar footer that shows the windows you pin
-
-Full notes: https://paseo.sh/changelog
@@ -1,7 +0,0 @@
-Added
- Added Muse Code as a provider, with model, approval mode, and reasoning effort controls
- Added Antigravity as a provider that drives the installed agy CLI, always in Full access
- Added Usage, opened from the sidebar footer as a dialog on desktop and a sheet on mobile, showing each subscription account's quota windows with Refresh
- Added an opt-in Usage summary to the sidebar footer that shows the windows you pin
-
-Full notes: https://paseo.sh/changelog
@@ -1,7 +0,0 @@
-Added
- Added Muse Code as a provider, with model, approval mode, and reasoning effort controls
- Added Antigravity as a provider that drives the installed agy CLI, always in Full access
- Added Usage, opened from the sidebar footer as a dialog on desktop and a sheet on mobile, showing each subscription account's quota windows with Refresh
- Added an opt-in Usage summary to the sidebar footer that shows the windows you pin
-
-Full notes: https://paseo.sh/changelog
@@ -1,12 +1,12 @@
 {
  "name": "paseo",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "paseo",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "hasInstallScript": true,
      "license": "Apache-2.0",
      "workspaces": [
@@ -36413,7 +36413,7 @@
    },
    "packages/app": {
      "name": "@getpaseo/app",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "@codemirror/commands": "6.10.4",
        "@codemirror/language": "6.12.4",
@@ -37496,12 +37496,12 @@
    },
    "packages/cli": {
      "name": "@getpaseo/cli",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "@clack/prompts": "^1.0.0",
-        "@getpaseo/client": "0.11.0",
-        "@getpaseo/protocol": "0.11.0",
-        "@getpaseo/server": "0.11.0",
+        "@getpaseo/client": "0.11.0-beta.5",
+        "@getpaseo/protocol": "0.11.0-beta.5",
+        "@getpaseo/server": "0.11.0-beta.5",
        "chalk": "^5.3.0",
        "commander": "^12.0.0",
        "mime-types": "^2.1.35",
@@ -37748,10 +37748,10 @@
    },
    "packages/client": {
      "name": "@getpaseo/client",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
-        "@getpaseo/protocol": "0.11.0",
-        "@getpaseo/relay": "0.11.0",
+        "@getpaseo/protocol": "0.11.0-beta.5",
+        "@getpaseo/relay": "0.11.0-beta.5",
        "zod": "^4.4.3"
      },
      "devDependencies": {
@@ -37762,7 +37762,7 @@
    },
    "packages/desktop": {
      "name": "@getpaseo/desktop",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "license": "Apache-2.0",
      "dependencies": {
        "@getpaseo/cli": "*",
@@ -38006,7 +38006,7 @@
    },
    "packages/expo-two-way-audio": {
      "name": "@getpaseo/expo-two-way-audio",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "license": "MIT",
      "devDependencies": {
        "@types/jest": "^29.5.14",
@@ -38902,7 +38902,7 @@
    },
    "packages/highlight": {
      "name": "@getpaseo/highlight",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "@codemirror/language": "6.12.4",
        "@codemirror/legacy-modes": "^6.5.3",
@@ -38931,14 +38931,14 @@
    },
    "packages/plugin": {
      "name": "@getpaseo/plugin",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "@agentclientprotocol/sdk": "^1.4.0",
        "use-sync-external-store": "^1.6.0"
      },
      "devDependencies": {
-        "@getpaseo/client": "0.11.0",
-        "@getpaseo/protocol": "0.11.0",
+        "@getpaseo/client": "0.11.0-beta.5",
+        "@getpaseo/protocol": "0.11.0-beta.5",
        "@types/node": "^20.9.0",
        "@types/react": "~19.2.0",
        "react": "19.1.0",
@@ -38948,8 +38948,8 @@
        "zod": "^4.4.3"
      },
      "peerDependencies": {
-        "@getpaseo/client": "0.11.0",
-        "@getpaseo/protocol": "0.11.0",
+        "@getpaseo/client": "0.11.0-beta.5",
+        "@getpaseo/protocol": "0.11.0-beta.5",
        "react": "~19.1.0",
        "react-native": ">=0.81.5",
        "zod": "^4.4.3"
@@ -38971,7 +38971,7 @@
    },
    "packages/protocol": {
      "name": "@getpaseo/protocol",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "semver": "^7.8.5",
        "zod": "^4.4.3"
@@ -38998,7 +38998,7 @@
    },
    "packages/relay": {
      "name": "@getpaseo/relay",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "base64-js": "^1.5.1",
        "tweetnacl": "^1.0.3",
@@ -39216,16 +39216,16 @@
    },
    "packages/server": {
      "name": "@getpaseo/server",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "@agentclientprotocol/sdk": "^0.17.1",
        "@anthropic-ai/claude-agent-sdk": "0.3.246",
        "@anthropic-ai/sdk": "^0.104.2",
-        "@getpaseo/client": "0.11.0",
-        "@getpaseo/highlight": "0.11.0",
-        "@getpaseo/plugin": "0.11.0",
-        "@getpaseo/protocol": "0.11.0",
-        "@getpaseo/relay": "0.11.0",
+        "@getpaseo/client": "0.11.0-beta.5",
+        "@getpaseo/highlight": "0.11.0-beta.5",
+        "@getpaseo/plugin": "0.11.0-beta.5",
+        "@getpaseo/protocol": "0.11.0-beta.5",
+        "@getpaseo/relay": "0.11.0-beta.5",
        "@isaacs/ttlcache": "^2.1.4",
        "@modelcontextprotocol/sdk": "1.29.0",
        "@opencode-ai/sdk": "1.14.46",
@@ -40146,7 +40146,7 @@
    },
    "packages/website": {
      "name": "@getpaseo/website",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "@cloudflare/vite-plugin": "^1.29.1",
        "@cloudflare/workers-types": "^4.20260317.1",
@@ -41754,7 +41754,7 @@
    },
    "plugins": {
      "name": "@getpaseo/builtin-plugins",
-      "version": "0.11.0",
+      "version": "0.11.0-beta.5",
      "dependencies": {
        "@getpaseo/plugin": "*",
        "zod": "^4.4.3"
@@ -1,6 +1,6 @@
 {
  "name": "paseo",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "private": true,
  "description": "Paseo: voice-controlled development environment for local AI coding agents",
  "keywords": [
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/app",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "private": true,
  "main": "index.ts",
  "scripts": {
@@ -3047,34 +3047,6 @@ describe("HostRuntimeStore", () => {
    useSessionStore.getState().clearSession(host.serverId);
  });

-  it("drains a queued message as a steer so a turn the agent just started is not interrupted", async () => {
-    const host = makeHost({ serverId: "srv_steer_queue_drain" });
-    const fakeClient = new FakeDaemonClient();
-    const store = new HostRuntimeStore({
-      deps: {
-        createClient: () => fakeClient as unknown as DaemonClient,
-        connectToDaemon: async () => ({
-          client: fakeClient as unknown as DaemonClient,
-          serverId: host.serverId,
-          hostname: null,
-        }),
-        getClientId: async () => "cid_steer_queue_drain",
-      },
-    });
-    const sessionStore = useSessionStore.getState();
-    sessionStore.initializeSession(host.serverId, fakeClient as unknown as DaemonClient, 1);
-    sessionStore.setQueuedMessages(
-      host.serverId,
-      new Map([["agent", [{ id: "queued", text: "next task", attachments: [] }]]]),
-    );
-
-    store.drainQueuedAgentMessage(host.serverId, "agent");
-    await fakeClient.waitForSentMessages(1);
-
-    expect(fakeClient.sentAgentMessages[0]?.[2]?.activeTurnBehavior).toBe("steer");
-    sessionStore.clearSession(host.serverId);
-  });
-
  it("uses legacy GitHub attachments when draining a queue for an old daemon", async () => {
    const host = makeHost({ serverId: "srv_legacy_queue_attachment" });
    const fakeClient = new FakeDaemonClient();
@@ -2426,11 +2426,6 @@ export class HostRuntimeStore {
          }),
          encodeImages,
          submission: createMessageSubmissionWriter(serverId),
-          // The queue drains when the agent goes idle, but the agent can start a turn of its own
-          // in that same moment (a wake-up after background work). Steering folds the message
-          // into that turn instead of interrupting it; with no turn running, the daemon starts
-          // a normal one.
-          activeTurnBehavior: "steer",
        });
      },
    })
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/cli",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "description": "Paseo CLI - control your AI coding agents from the command line",
  "bin": {
    "paseo": "bin/paseo"
@@ -28,9 +28,9 @@
  },
  "dependencies": {
    "@clack/prompts": "^1.0.0",
-    "@getpaseo/client": "0.11.0",
-    "@getpaseo/protocol": "0.11.0",
-    "@getpaseo/server": "0.11.0",
+    "@getpaseo/client": "0.11.0-beta.5",
+    "@getpaseo/protocol": "0.11.0-beta.5",
+    "@getpaseo/server": "0.11.0-beta.5",
    "chalk": "^5.3.0",
    "commander": "^12.0.0",
    "mime-types": "^2.1.35",
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/client",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "description": "Paseo client SDK package",
  "files": [
    "dist",
@@ -39,8 +39,8 @@
    "test": "vitest run"
  },
  "dependencies": {
-    "@getpaseo/protocol": "0.11.0",
-    "@getpaseo/relay": "0.11.0",
+    "@getpaseo/protocol": "0.11.0-beta.5",
+    "@getpaseo/relay": "0.11.0-beta.5",
    "zod": "^4.4.3"
  },
  "devDependencies": {
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/desktop",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "private": true,
  "description": "Paseo desktop app (Electron wrapper)",
  "homepage": "https://paseo.sh",
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/expo-two-way-audio",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "description": "Native module for two way audio streaming",
  "keywords": [
    "ExpoTwoWayAudio",
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/highlight",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "files": [
    "dist",
    "!dist/**/*.map",
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/plugin",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "description": "Paseo plugin SDK package",
  "files": [
    "dist",
@@ -70,8 +70,8 @@
    "use-sync-external-store": "^1.6.0"
  },
  "devDependencies": {
-    "@getpaseo/client": "0.11.0",
-    "@getpaseo/protocol": "0.11.0",
+    "@getpaseo/client": "0.11.0-beta.5",
+    "@getpaseo/protocol": "0.11.0-beta.5",
    "@types/node": "^20.9.0",
    "@types/react": "~19.2.0",
    "react": "19.1.0",
@@ -81,8 +81,8 @@
    "zod": "^4.4.3"
  },
  "peerDependencies": {
-    "@getpaseo/client": "0.11.0",
-    "@getpaseo/protocol": "0.11.0",
+    "@getpaseo/client": "0.11.0-beta.5",
+    "@getpaseo/protocol": "0.11.0-beta.5",
    "react": "~19.1.0",
    "react-native": ">=0.81.5",
    "zod": "^4.4.3"
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/protocol",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "description": "Paseo shared protocol schemas and wire types",
  "files": [
    "dist",
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/relay",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "description": "Paseo relay for bridging daemon and client connections",
  "files": [
    "dist",
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/server",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "description": "Paseo backend server",
  "files": [
    "dist/server",
@@ -107,11 +107,11 @@
    "@agentclientprotocol/sdk": "^0.17.1",
    "@anthropic-ai/claude-agent-sdk": "0.3.246",
    "@anthropic-ai/sdk": "^0.104.2",
-    "@getpaseo/client": "0.11.0",
-    "@getpaseo/highlight": "0.11.0",
-    "@getpaseo/plugin": "0.11.0",
-    "@getpaseo/protocol": "0.11.0",
-    "@getpaseo/relay": "0.11.0",
+    "@getpaseo/client": "0.11.0-beta.5",
+    "@getpaseo/highlight": "0.11.0-beta.5",
+    "@getpaseo/plugin": "0.11.0-beta.5",
+    "@getpaseo/protocol": "0.11.0-beta.5",
+    "@getpaseo/relay": "0.11.0-beta.5",
    "@isaacs/ttlcache": "^2.1.4",
    "@modelcontextprotocol/sdk": "1.29.0",
    "@opencode-ai/sdk": "1.14.46",
@@ -31,7 +31,6 @@ function createQueryMock(events: unknown[]): Query {
 describe("Claude SDK env", () => {
  test("forwards launch-context env through Claude process env", async () => {
    let capturedEnv: Record<string, string | undefined> | undefined;
-    let capturedPerTaskStopAffordance: boolean | undefined;
    const launchContext: AgentLaunchContext = {
      env: {
        PASEO_AGENT_ID: "00000000-0000-4000-8000-000000000201",
@@ -40,7 +39,6 @@ describe("Claude SDK env", () => {
    };
    const queryFactory = vi.fn(({ options }: ClaudeQueryInput) => {
      capturedEnv = options.env;
-      capturedPerTaskStopAffordance = options.perTaskStopAffordance;
      return createQueryMock([
        {
          type: "system",
@@ -93,10 +91,6 @@ describe("Claude SDK env", () => {
      expect(capturedEnv?.MCP_TIMEOUT).toBe("claude-startup-timeout");
      expect(capturedEnv?.MCP_TOOL_TIMEOUT).toBe("claude-tool-timeout");
      expect(session.usageSession?.()?.env).toBe(capturedEnv);
-      // Paseo reads session_state_changed to know when an autonomous turn is over.
-      expect(capturedEnv?.CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS).toBe("1");
-      // Without it, Stop and replace kill every background subagent along with the turn.
-      expect(capturedPerTaskStopAffordance).toBe(true);
    } finally {
      await session.close();
      expect(session.usageSession?.()).toBeNull();
@@ -91,17 +91,6 @@ function buildUsage() {
  };
 }

-/** Claude opening a turn of its own. Every main-session turn starts with one. */
-function buildTurnInit(sessionId: string) {
-  return {
-    type: "system",
-    subtype: "init",
-    session_id: sessionId,
-    permissionMode: "default",
-    model: "opus",
-  };
-}
-
 function buildSuccessResult(sessionId: string) {
  return {
    type: "result",
@@ -164,7 +153,13 @@ function createScriptedQuery(params: {
    },
  } satisfies ScriptedQuery;

-  scriptedQuery.emit(buildTurnInit(params.sessionId));
+  scriptedQuery.emit({
+    type: "system",
+    subtype: "init",
+    session_id: params.sessionId,
+    permissionMode: "default",
+    model: "opus",
+  });

  void (async () => {
    for await (const prompt of params.prompt) {
@@ -257,21 +252,6 @@ async function waitFor(
  }
 }

-/**
- * Paseo interrupts Claude only while a main-session turn is in flight, which it learns from the
- * init. The pump asks for its next frame only after routing the last one, so a second next() call
- * proves the init was read.
- */
-async function waitForInitRouted(
-  query: () => { next: ReturnType<typeof vi.fn> } | null | undefined,
-) {
-  await waitFor(() => (query()?.next.mock.calls.length ?? 0) >= 2);
-}
-
-function buildCommandLifecycle(commandUuid: string | null | undefined, state: string) {
-  return { type: "command_lifecycle", command_uuid: commandUuid, state };
-}
-
 afterEach(() => {
  queryFactory.mockReset();
 });
@@ -302,7 +282,6 @@ test("interrupt only calls query.interrupt and leaves the query open", async ()
  const firstTurn = streamSession(session, "first prompt");
  await firstTurn.next();
  await waitFor(() => queries[0]?.prompts.length === 1);
-  await waitForInitRouted(() => queries[0]);

  await session.interrupt();
  await waitFor(() => queries[0]?.interrupt.mock.calls.length === 1);
@@ -343,7 +322,6 @@ async function startSteeredTurn(sessionId: string): Promise<{
    throw new Error("Expected the original Claude turn to start");
  }
  await waitFor(() => query?.prompts.length === 1);
-  await waitForInitRouted(() => query);

  const steered = await session.steerActiveTurn!("queued steer", {
    expectedTurnId: start.value.turnId,
@@ -393,8 +371,11 @@ test("interrupt still stops the turn when Claude has already dequeued the steer"
 test("a steer Claude has already read is no longer discardable on interrupt", async () => {
  const { session, query, turn } = await startSteeredTurn("queued-steer-completed-session");

-  query()?.emit(buildCommandLifecycle(query()?.prompts[0]?.uuid, "started"));
-  query()?.emit(buildCommandLifecycle(query()?.prompts[1]?.uuid, "completed"));
+  query()?.emit({
+    type: "command_lifecycle",
+    command_uuid: query()?.prompts[1]?.uuid,
+    state: "completed",
+  });
  // Frames are translated in order, so the marker landing proves the lifecycle frame was read.
  query()?.emit({ type: "assistant", message: { content: "STEER_READ" } });
  await consumeUntil(turn, (event) => collectAssistantText([event]).includes("STEER_READ"));
@@ -407,23 +388,6 @@ test("a steer Claude has already read is no longer discardable on interrupt", as
  await session.close();
 });

-test("a steer Claude cancelled is no longer withdrawn on interrupt", async () => {
-  const { session, query, turn } = await startSteeredTurn("queued-steer-cancelled-session");
-
-  query()?.emit(buildCommandLifecycle(query()?.prompts[0]?.uuid, "started"));
-  // "cancelled" is terminal: API errors, interrupts and "now" pre-emption all end a message.
-  query()?.emit(buildCommandLifecycle(query()?.prompts[1]?.uuid, "cancelled"));
-  query()?.emit({ type: "assistant", message: { content: "STEER_CANCELLED" } });
-  await consumeUntil(turn, (event) => collectAssistantText([event]).includes("STEER_CANCELLED"));
-
-  await session.interrupt();
-  await waitFor(() => query()?.interrupt.mock.calls.length === 1);
-
-  expect(query()?.cancelAsyncMessage).not.toHaveBeenCalled();
-  await collectUntilTerminal(turn);
-  await session.close();
-});
-
 function buildStoppedTaskNotification(sessionId: string) {
  return {
    type: "system",
@@ -509,7 +473,6 @@ async function startInterruptedToolTurn(sessionId: string): Promise<{
  const turn = streamSession(session, "run the slow tool");
  await turn.next();
  await waitFor(() => query?.prompts.length === 1);
-  await waitForInitRouted(() => query);

  await session.interrupt();
  await collectUntilTerminal(turn);
@@ -560,7 +523,6 @@ test("Claude can still wake into an autonomous turn once the interrupted request

  query()?.emit(buildStoppedTaskNotification(sessionId));
  query()?.emit(buildAbortedResult(sessionId));
-  query()?.emit(buildTurnInit(sessionId));
  query()?.emit({
    type: "assistant",
    message: { content: "AUTONOMOUS_WAKE_RESPONSE" },
@@ -617,7 +579,6 @@ test("reuses the existing query after interrupt before starting the next prompt"
  const firstTurn = streamSession(session, "first prompt");
  await firstTurn.next();
  await waitFor(() => queries[0]?.prompts.length === 1);
-  await waitForInitRouted(() => queries[0]);

  await session.interrupt();
  await collectUntilTerminal(firstTurn);
@@ -691,7 +652,6 @@ test("recovers when the query pump sees a single interrupt abort before the next
  const output = createAsyncQueue<Record<string, unknown>>();
  const prompts: PromptRecord[] = [];
  let throwAbortOnNext = false;
-  let queryRef: Pick<ScriptedQuery, "next"> | null = null;

  queryFactory.mockImplementation(({ prompt }: { prompt: AsyncIterable<unknown> }) => {
    const scriptedQuery = {
@@ -725,8 +685,13 @@ test("recovers when the query pump sees a single interrupt abort before the next
      },
    } satisfies ScriptedQuery;

-    queryRef = scriptedQuery;
-    scriptedQuery.emit(buildTurnInit("interrupt-abort-recovery-session"));
+    scriptedQuery.emit({
+      type: "system",
+      subtype: "init",
+      session_id: "interrupt-abort-recovery-session",
+      permissionMode: "default",
+      model: "opus",
+    });

    void (async () => {
      for await (const promptMessage of prompt) {
@@ -765,7 +730,6 @@ test("recovers when the query pump sees a single interrupt abort before the next

  const firstTurn = streamSession(session, "first prompt");
  await firstTurn.next();
-  await waitForInitRouted(() => queryRef);
  await session.interrupt();
  await collectUntilTerminal(firstTurn);

@@ -804,7 +768,6 @@ test("stale abort result after replacement start does not poison the new foregro
  const firstTurn = streamSession(session, "first prompt");
  const firstStarted = await firstTurn.next();
  await waitFor(() => queryRef?.prompts.length === 1);
-  await waitForInitRouted(() => queryRef);

  await session.interrupt();
  const firstTurnEvents = [firstStarted.value!, ...(await collectUntilTerminal(firstTurn))];
@@ -849,7 +812,7 @@ test("stale abort result after replacement start does not poison the new foregro
  await session.close();
 });

-test("creates an autonomous live turn when Claude starts a turn without a foreground run", async () => {
+test("creates an autonomous live turn when assistant output arrives without a foreground run", async () => {
  const logger = createTestLogger();
  let queryRef: ScriptedQuery | null = null;

@@ -885,7 +848,6 @@ test("creates an autonomous live turn when Claude starts a turn without a foregr
  await collectUntilTerminal(streamSession(session, "seed prompt"));

  const subscribedEvents = subscribeToEvents(session);
-  queryRef?.emit(buildTurnInit("autonomous-live-session"));
  queryRef?.emit({
    type: "assistant",
    message: { content: "AUTONOMOUS_WAKE_RESPONSE" },
@@ -954,7 +916,6 @@ test("steers an autonomous turn through its existing query without restarting it

  await collectUntilTerminal(streamSession(session, "seed prompt"));
  const autonomousEvents = subscribeToEvents(session);
-  queryRef?.emit(buildTurnInit("autonomous-steer-session"));
  queryRef?.emit({
    type: "assistant",
    message: { content: "AUTONOMOUS_RESPONSE" },
@@ -1038,7 +999,6 @@ test("auto-completes an open autonomous turn when a foreground prompt starts", a
  await collectUntilTerminal(streamSession(session, "seed prompt"));

  const subscribedEvents = subscribeToEvents(session);
-  queryRef?.emit(buildTurnInit("autonomous-handoff-session"));
  queryRef?.emit({
    type: "assistant",
    message: { content: "BACKGROUND_ONLY_RESPONSE" },
@@ -486,7 +486,6 @@ test("interruptActiveTurn only interrupts the active query without info logs", a
    } | null;
    input: { end: () => void } | null;
    queryRestartNeeded: boolean;
-    mainTurnInFlight: boolean;
    interruptActiveTurn: () => Promise<void>;
  } = asInternals(session);
  const interrupt = vi.fn(async () => undefined);
@@ -499,7 +498,6 @@ test("interruptActiveTurn only interrupts the active query without info logs", a
  };
  internal.input = { end };
  internal.queryRestartNeeded = false;
-  internal.mainTurnInFlight = true;

  try {
    await internal.interruptActiveTurn();
@@ -1193,7 +1191,6 @@ test("reuses one autonomous run for unbound stream_event bursts with no foregrou
  const queryMock = createBaseQueryMock(vi.fn(async () => ({ done: true, value: undefined })));

  internal.turnState = "idle";
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
  await internal.routeSdkMessageFromPump(
    {
      type: "stream_event",
@@ -1236,468 +1233,6 @@ test("reuses one autonomous run for unbound stream_event bursts with no foregrou
  await session.close();
 });

-interface SessionStateInternals {
-  turnState: "idle" | "foreground" | "autonomous";
-  routeSdkMessageFromPump: (
-    message: Record<string, unknown>,
-    activeQuery: QueryMock,
-  ) => Promise<void>;
-  autonomousTurn: { id: string } | null;
-  activeForegroundTurnId: string | null;
-}
-
-function sessionState(state: "idle" | "running" | "requires_action") {
-  return {
-    type: "system",
-    subtype: "session_state_changed",
-    state,
-    uuid: `state-${state}`,
-    session_id: "sess-1",
-  };
-}
-
-/** Claude opening a turn of its own. Every main-session turn starts with one. */
-function claudeTurnInit() {
-  return {
-    type: "system",
-    subtype: "init",
-    session_id: "sess-1",
-    permissionMode: "default",
-    model: "opus",
-  };
-}
-
-function successResult() {
-  return { type: "result", subtype: "success", usage: buildUsage(), total_cost_usd: 0 };
-}
-
-function commandLifecycle(
-  commandUuid: string,
-  state: "queued" | "started" | "completed" | "cancelled",
-) {
-  return { type: "command_lifecycle", command_uuid: commandUuid, state };
-}
-
-function unboundTextDelta(text: string) {
-  return {
-    type: "stream_event",
-    parent_tool_use_id: null,
-    event: { type: "content_block_delta", delta: { type: "text_delta", text } },
-  };
-}
-
-// What a background subagent emits on the main stream with no parent tool use id, so by frame
-// shape alone each looks like main-session work. Verified on the wire: none arrives inside a turn
-// Claude opened, and no result follows any of them.
-const helperTaskStarted = {
-  type: "system",
-  subtype: "task_started",
-  task_id: "helper-task",
-  tool_use_id: "toolu_helper",
-  task_type: "local_agent",
-  subagent_type: "general-purpose",
-  description: "Background helper",
-  is_backgrounded: true,
-  uuid: "uuid-task-started",
-  session_id: "sess-1",
-};
-const helperTaskProgress = {
-  type: "system",
-  subtype: "task_progress",
-  task_id: "helper-task",
-  tool_use_id: "toolu_helper",
-  description: "Background helper",
-  usage: { total_tokens: 1200, tool_uses: 3, duration_ms: 900 },
-  last_tool_name: "Bash",
-  uuid: "uuid-task-progress",
-  session_id: "sess-1",
-};
-// A subagent's own background Bash job completing.
-const subagentOwnedTaskNotification = {
-  type: "system",
-  subtype: "task_notification",
-  task_id: "bg-job-of-subagent",
-  tool_use_id: "toolu_subagent_bash",
-  status: "completed",
-  summary: "Background command completed",
-  output_file: "/tmp/bg-job-of-subagent.output",
-  uuid: "uuid-task-notification",
-  session_id: "sess-1",
-};
-const helperCompleted = {
-  type: "system",
-  subtype: "task_notification",
-  task_id: "helper-task",
-  tool_use_id: "toolu_helper",
-  status: "completed",
-  summary: "Background helper finished",
-  output_file: "/tmp/helper-task.output",
-  uuid: "uuid-helper-completed",
-  session_id: "sess-1",
-};
-const rateLimitEvent = {
-  type: "rate_limit_event",
-  rate_limit_info: { status: "allowed" },
-  uuid: "uuid-rate-limit",
-  session_id: "sess-1",
-};
-
-function createPendingQueryMock(): QueryMock {
-  return createBaseQueryMock(vi.fn(() => new Promise<never>(() => {})));
-}
-
-test("a main-session frame opens no turn until Claude starts one", async () => {
-  const session = await createSession();
-  const internal: SessionStateInternals = asInternals(session);
-  const queryMock = createPendingQueryMock();
-
-  // Main-session output only ever arrives inside a turn Claude opened with system/init, so a
-  // stray unbound frame is not the start of one.
-  await internal.routeSdkMessageFromPump(unboundTextDelta("stray"), queryMock);
-  expect(internal.autonomousTurn).toBeNull();
-
-  // The wake-up case autonomous turns exist for: a completed background subagent makes the main
-  // session start a turn of its own, with no prompt from the user.
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-  await internal.routeSdkMessageFromPump(unboundTextDelta("picking this up"), queryMock);
-  expect(internal.autonomousTurn?.id).toBe("autonomous-turn-1");
-
-  await internal.routeSdkMessageFromPump(successResult(), queryMock);
-  expect(internal.autonomousTurn).toBeNull();
-
-  await session.close();
-});
-
-test("a background subagent's frames never open a turn while the main session is idle", async () => {
-  sdkQueryFactory.mockImplementation(() => createPendingQueryMock());
-  const session = await createSession();
-  const internal: SessionStateInternals = asInternals(session);
-  const queryMock = createPendingQueryMock();
-
-  // Claude Code 2.1.280 reports "running" for as long as any background subagent is alive.
-  await internal.routeSdkMessageFromPump(sessionState("running"), queryMock);
-  for (const frame of [
-    helperTaskStarted,
-    helperTaskProgress,
-    subagentOwnedTaskNotification,
-    rateLimitEvent,
-    helperCompleted,
-  ]) {
-    await internal.routeSdkMessageFromPump(frame, queryMock);
-    expect(internal.autonomousTurn).toBeNull();
-    expect(internal.turnState).toBe("idle");
-  }
-
-  // The next user message starts its own foreground turn rather than landing on a phantom one.
-  const { turnId } = await session.startTurn("PING");
-  expect(internal.activeForegroundTurnId).toBe(turnId);
-  expect(internal.autonomousTurn).toBeNull();
-  expect(internal.turnState).toBe("foreground");
-
-  await session.close();
-});
-
-test("Claude waking up after a helper finishes gets an autonomous turn that its result closes", async () => {
-  const session = await createSession();
-  const internal: SessionStateInternals = asInternals(session);
-  const queryMock = createPendingQueryMock();
-  const events: AgentStreamEvent[] = [];
-  session.subscribe((event) => events.push(event));
-
-  // The helper's completion arrives outside any turn. Claude then starts one to react to it.
-  await internal.routeSdkMessageFromPump(helperTaskStarted, queryMock);
-  await internal.routeSdkMessageFromPump(helperCompleted, queryMock);
-  expect(internal.autonomousTurn).toBeNull();
-
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-  expect(internal.autonomousTurn?.id).toBe("autonomous-turn-1");
-  expect(internal.turnState).toBe("autonomous");
-
-  await internal.routeSdkMessageFromPump(unboundTextDelta("the helper is done"), queryMock);
-  await internal.routeSdkMessageFromPump(successResult(), queryMock);
-  expect(internal.autonomousTurn).toBeNull();
-  expect(internal.turnState).toBe("idle");
-  expect(events.filter((event) => event.type === "turn_started")).toHaveLength(1);
-  expect(events.filter((event) => event.type === "turn_completed")).toHaveLength(1);
-
-  await session.close();
-});
-
-test("a steer folded into a turn keeps one turn, and a turn Claude starts after it gets its own", async () => {
-  sdkQueryFactory.mockImplementation(() => createPendingQueryMock());
-  const session = await createSession();
-  const internal: SessionStateInternals = asInternals(session);
-  const queryMock = createPendingQueryMock();
-  const events: AgentStreamEvent[] = [];
-  session.subscribe((event) => events.push(event));
-
-  const { turnId } = await session.startTurn("hello");
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-  // A message pushed mid-turn is folded in at the next tool boundary: Claude acknowledges it, but
-  // starts no new turn.
-  await internal.routeSdkMessageFromPump(commandLifecycle("folded-steer", "queued"), queryMock);
-  await internal.routeSdkMessageFromPump(commandLifecycle("folded-steer", "started"), queryMock);
-  expect(internal.activeForegroundTurnId).toBe(turnId);
-  expect(internal.autonomousTurn).toBeNull();
-
-  await internal.routeSdkMessageFromPump(successResult(), queryMock);
-  expect(internal.activeForegroundTurnId).toBeNull();
-  expect(internal.turnState).toBe("idle");
-
-  // A message that arrived while Claude wrote its final answer runs as a turn of its own.
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-  expect(internal.autonomousTurn?.id).toBe("autonomous-turn-2");
-  await internal.routeSdkMessageFromPump(successResult(), queryMock);
-  expect(internal.autonomousTurn).toBeNull();
-  expect(internal.turnState).toBe("idle");
-  expect(events.filter((event) => event.type === "turn_started")).toHaveLength(2);
-  expect(events.filter((event) => event.type === "turn_completed")).toHaveLength(2);
-
-  await session.close();
-});
-
-test("session state never opens a turn", async () => {
-  const session = await createSession();
-  const internal: SessionStateInternals = asInternals(session);
-  const queryMock = createPendingQueryMock();
-  const events: AgentStreamEvent[] = [];
-  session.subscribe((event) => events.push(event));
-
-  // "running" covers background subagents too, so it says nothing about the main session.
-  for (const state of ["idle", "running", "requires_action", "idle"] as const) {
-    await internal.routeSdkMessageFromPump(sessionState(state), queryMock);
-    expect(internal.autonomousTurn).toBeNull();
-    expect(internal.turnState).toBe("idle");
-  }
-  // State frames are bookkeeping, never timeline content.
-  expect(events).toEqual([]);
-
-  await session.close();
-});
-
-test("an idle session state closes an autonomous turn that no result closed", async () => {
-  const session = await createSession();
-  const internal: SessionStateInternals = asInternals(session);
-  const queryMock = createPendingQueryMock();
-  const events: AgentStreamEvent[] = [];
-  session.subscribe((event) => events.push(event));
-
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-  expect(internal.autonomousTurn?.id).toBe("autonomous-turn-1");
-
-  // Safety net: Claude says nothing at all is running any more.
-  await internal.routeSdkMessageFromPump(sessionState("idle"), queryMock);
-  expect(internal.autonomousTurn).toBeNull();
-  expect(internal.turnState).toBe("idle");
-  expect(events.filter((event) => event.type === "turn_completed")).toHaveLength(1);
-
-  await session.close();
-});
-
-test("session state never opens or closes a foreground turn", async () => {
-  sdkQueryFactory.mockImplementation(() => createPendingQueryMock());
-  const session = await createSession();
-  const internal: SessionStateInternals = asInternals(session);
-  const queryMock = createPendingQueryMock();
-
-  await internal.routeSdkMessageFromPump(sessionState("idle"), queryMock);
-  const { turnId } = await session.startTurn("hello");
-
-  // The send's own running, then an idle that trails the previous turn and lands late.
-  await internal.routeSdkMessageFromPump(sessionState("running"), queryMock);
-  await internal.routeSdkMessageFromPump(sessionState("idle"), queryMock);
-  expect(internal.activeForegroundTurnId).toBe(turnId);
-  expect(internal.autonomousTurn).toBeNull();
-  expect(internal.turnState).toBe("foreground");
-
-  await internal.routeSdkMessageFromPump(
-    { type: "result", subtype: "success", usage: buildUsage(), total_cost_usd: 0 },
-    queryMock,
-  );
-  expect(internal.activeForegroundTurnId).toBeNull();
-  expect(internal.turnState).toBe("idle");
-
-  await session.close();
-});
-
-interface InterruptInternals extends SessionStateInternals {
-  pendingInterruptAbort: boolean;
-}
-
-type InterruptibleQueryMock = QueryMock & { cancelAsyncMessage: ReturnType<typeof vi.fn> };
-
-function createInterruptibleQueryMock(): InterruptibleQueryMock {
-  return Object.assign(createPendingQueryMock(), {
-    cancelAsyncMessage: vi.fn(async () => true),
-  });
-}
-
-/** The uuid Paseo stamped on the first message it pushed into the SDK input. */
-async function readFirstPromptUuid(): Promise<string | null> {
-  const input = sdkQueryFactory.mock.calls[0]?.[0] as { prompt: AsyncIterable<unknown> };
-  return await createPromptUuidReader(input.prompt)();
-}
-
-function abortedResult() {
-  return {
-    type: "result",
-    subtype: "error_during_execution",
-    errors: [],
-    usage: buildUsage(),
-    total_cost_usd: 0,
-  };
-}
-
-test("an interrupt before Claude starts the message withdraws it instead of interrupting", async () => {
-  const queryMock = createInterruptibleQueryMock();
-  sdkQueryFactory.mockImplementation(() => queryMock);
-  const session = await createSession();
-  const internal: InterruptInternals = asInternals(session);
-  const events: AgentStreamEvent[] = [];
-  session.subscribe((event) => events.push(event));
-
-  await session.startTurn("hello");
-  // Claude has not acknowledged the message yet: no init, no command_lifecycle "started".
-  await session.interrupt();
-
-  await vi.waitFor(() => expect(queryMock.cancelAsyncMessage).toHaveBeenCalledTimes(1));
-  expect(queryMock.cancelAsyncMessage).toHaveBeenCalledWith(await readFirstPromptUuid());
-  expect(queryMock.interrupt).not.toHaveBeenCalled();
-  // No result follows an interrupt that never happened, so no flag may wait for one.
-  expect(internal.pendingInterruptAbort).toBe(false);
-  expect(events.filter((event) => event.type === "turn_canceled")).toHaveLength(1);
-
-  await session.close();
-});
-
-test("an interrupt after Claude took the message but before it started stops it", async () => {
-  const queryMock = createInterruptibleQueryMock();
-  // Claude has dequeued the message for its next turn, so withdrawing it is a no-op.
-  queryMock.cancelAsyncMessage.mockImplementation(async () => false);
-  sdkQueryFactory.mockImplementation(() => queryMock);
-  const session = await createSession();
-  const internal: InterruptInternals = asInternals(session);
-
-  await session.startTurn("hello");
-  // No command_lifecycle "started" or init has reached Paseo yet.
-  await session.interrupt();
-
-  await vi.waitFor(() => expect(queryMock.interrupt).toHaveBeenCalledTimes(1));
-  expect(queryMock.cancelAsyncMessage).toHaveBeenCalledWith(await readFirstPromptUuid());
-  expect(internal.pendingInterruptAbort).toBe(true);
-
-  await session.close();
-});
-
-test("a prompt sent while a stopped prompt is being withdrawn is not withdrawn too", async () => {
-  const queryMock = createInterruptibleQueryMock();
-  let settleWithdrawal: (cancelled: boolean) => void = () => {};
-  queryMock.cancelAsyncMessage.mockImplementationOnce(
-    () => new Promise<boolean>((resolve) => (settleWithdrawal = resolve)),
-  );
-  sdkQueryFactory.mockImplementation(() => queryMock);
-  const session = await createSession();
-
-  await session.startTurn("first");
-  const firstUuid = await readFirstPromptUuid();
-  await session.interrupt();
-  await vi.waitFor(() => expect(queryMock.cancelAsyncMessage).toHaveBeenCalledTimes(1));
-
-  await session.startTurn("second");
-  settleWithdrawal(false);
-
-  await vi.waitFor(() => expect(queryMock.interrupt).toHaveBeenCalledTimes(1));
-  expect(queryMock.cancelAsyncMessage).toHaveBeenCalledTimes(1);
-  expect(queryMock.cancelAsyncMessage).toHaveBeenCalledWith(firstUuid);
-
-  await session.close();
-});
-
-test("an interrupt while only background subagents run never reaches Claude", async () => {
-  const queryMock = createInterruptibleQueryMock();
-  sdkQueryFactory.mockImplementation(() => queryMock);
-  const session = await createSession();
-  const internal: InterruptInternals = asInternals(session);
-
-  await session.startTurn("delegate to a helper");
-  const promptUuid = await readFirstPromptUuid();
-  await internal.routeSdkMessageFromPump(commandLifecycle(promptUuid ?? "", "started"), queryMock);
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-  await internal.routeSdkMessageFromPump(helperTaskStarted, queryMock);
-  await internal.routeSdkMessageFromPump(successResult(), queryMock);
-  // The main session is done; its helper keeps working.
-  await internal.routeSdkMessageFromPump(sessionState("running"), queryMock);
-  await internal.routeSdkMessageFromPump(helperTaskProgress, queryMock);
-
-  // Without perTaskStopAffordance, an interrupt here kills every running helper.
-  await session.interrupt();
-
-  expect(queryMock.interrupt).not.toHaveBeenCalled();
-  expect(queryMock.cancelAsyncMessage).not.toHaveBeenCalled();
-  expect(internal.pendingInterruptAbort).toBe(false);
-
-  await session.close();
-});
-
-test("an interrupt during a main turn interrupts Claude once and drops the aborted result", async () => {
-  const queryMock = createInterruptibleQueryMock();
-  sdkQueryFactory.mockImplementation(() => queryMock);
-  const session = await createSession();
-  const internal: InterruptInternals = asInternals(session);
-  const events: AgentStreamEvent[] = [];
-  session.subscribe((event) => events.push(event));
-
-  await session.startTurn("long task");
-  const promptUuid = await readFirstPromptUuid();
-  await internal.routeSdkMessageFromPump(commandLifecycle(promptUuid ?? "", "started"), queryMock);
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-
-  await session.interrupt();
-  await vi.waitFor(() => expect(queryMock.interrupt).toHaveBeenCalledTimes(1));
-  // Claude already started the message, so there is nothing to withdraw.
-  expect(queryMock.cancelAsyncMessage).not.toHaveBeenCalled();
-  expect(internal.pendingInterruptAbort).toBe(true);
-
-  // A replacement starts before the aborted turn reports its result.
-  const { turnId } = await session.startTurn("replacement");
-  await internal.routeSdkMessageFromPump(abortedResult(), queryMock);
-  expect(internal.activeForegroundTurnId).toBe(turnId);
-  expect(internal.pendingInterruptAbort).toBe(false);
-  expect(events.filter((event) => event.type === "turn_failed")).toHaveLength(0);
-
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-  await internal.routeSdkMessageFromPump(successResult(), queryMock);
-  expect(internal.activeForegroundTurnId).toBeNull();
-  expect(queryMock.interrupt).toHaveBeenCalledTimes(1);
-
-  await session.close();
-});
-
-test("a new turn clears an interrupt flag no result will consume", async () => {
-  const session = await createSession();
-  const internal: InterruptInternals = asInternals(session);
-  const queryMock = createPendingQueryMock();
-  const events: AgentStreamEvent[] = [];
-  session.subscribe((event) => events.push(event));
-
-  // An interrupt that landed just after its turn had ended: Claude emits no result for it.
-  internal.pendingInterruptAbort = true;
-
-  await internal.routeSdkMessageFromPump(claudeTurnInit(), queryMock);
-  expect(internal.pendingInterruptAbort).toBe(false);
-  expect(internal.autonomousTurn?.id).toBe("autonomous-turn-1");
-
-  // This turn's own failure is reported, not swallowed as the interrupted turn's leftover.
-  await internal.routeSdkMessageFromPump(
-    { ...abortedResult(), errors: ["API Error: 500 upstream failure"] },
-    queryMock,
-  );
-  expect(events.filter((event) => event.type === "turn_failed")).toHaveLength(1);
-  expect(internal.autonomousTurn).toBeNull();
-
-  await session.close();
-});
-
 test("tracks run lifecycle transitions for success, error, and interrupt", async () => {
  const session = await createSession();
  let streamCase: "success" | "error" | "interrupt" = "success";
@@ -78,7 +78,7 @@ describe("subagent lifecycle across an interrupt", () => {
    queryFactory.mockReset();
  });

-  async function startInterruptibleTurn(taskStarted: Record<string, unknown> = {}) {
+  async function startInterruptibleTurn() {
    const channel = buildOpenQueryMock();
    queryFactory.mockImplementation(() => channel.query);
    const session = await new ClaudeAgentClient({
@@ -107,7 +107,6 @@ describe("subagent lifecycle across an interrupt", () => {
      task_type: "local_agent",
      subagent_type: "general-purpose",
      description: "Reply with banana",
-      ...taskStarted,
    });
    await vi.waitFor(() => expect(subagentEvents.length).toBeGreaterThan(0));

@@ -170,31 +169,6 @@ describe("subagent lifecycle across an interrupt", () => {
    await session.close();
  });

-  test("a child spawned in the background is not canceled with the turn that spawned it", async () => {
-    // Claude announces a background spawn on task_started itself and sends no task_updated patch.
-    const { channel, session, subagentEvents } = await startInterruptibleTurn({
-      is_backgrounded: true,
-    });
-
-    await session.interrupt();
-    channel.push({
-      type: "system",
-      subtype: "task_notification",
-      task_id: TASK_ID,
-      tool_use_id: SUBAGENT_ID,
-      status: "completed",
-    });
-
-    await vi.waitFor(() =>
-      expect(subagentEvents).toContainEqual(
-        expect.objectContaining({ id: SUBAGENT_ID, status: "completed" }),
-      ),
-    );
-    expect(statuses(subagentEvents, SUBAGENT_ID)).toEqual(["running", "completed"]);
-
-    await session.close();
-  });
-
  test("a foreground child is canceled with the turn that spawned it", async () => {
    const { session, subagentEvents } = await startInterruptibleTurn();

@@ -3160,15 +3160,10 @@ describe("ClaudeAgentSession context window usage", () => {
  });

  test("a compaction abandoned in an autonomous turn does not suppress the next marker", async () => {
-    // Claude starts a turn of its own after the foreground result, which starts compacting and is
-    // then ended by the next foreground turn, never reaching a boundary.
+    // Trailing output after the foreground result opens an autonomous turn, which starts
+    // compacting and is then ended by the next foreground turn, never reaching a boundary.
    const session = await createSessionForTurns([
-      [
-        createSuccessResult(),
-        createInitMessage(),
-        createMessageStartEvent(),
-        createCompactingStatus(),
-      ],
+      [createSuccessResult(), createMessageStartEvent(), createCompactingStatus()],
      [createCompactingStatus(), createSuccessResult()],
    ]);

@@ -452,15 +452,6 @@ function errorToMessageString(error: unknown): string {
  return "";
 }

-/**
- * Claude opens every main-session turn with system/init and closes it with exactly one result:
- * a prompt, a wake-up after background work, a slash command, an API error. Background subagents
- * never emit either on the main stream.
- */
-function isClaudeTurnInit(message: SDKMessage): boolean {
-  return message.type === "system" && message.subtype === "init";
-}
-
 function firstStringField(
  input: Record<string, unknown>,
  primaryKey: string,
@@ -2079,12 +2070,11 @@ class ClaudeAgentSession implements AgentSession {
  private activeForegroundQuery: Query | null = null;
  private activeForegroundInput: AsyncMessageInput<SDKUserMessage> | null = null;
  /**
-   * Messages pushed into the live SDK input (steers, and a foreground turn's own prompt) whose
-   * command_lifecycle has not reached "started". Interrupting has to withdraw them, or the SDK
-   * dequeues one and resumes the turn we just stopped. SDK user UUIDs are provider-private; never
-   * let them escape the adapter boundary.
+   * Steers pushed into the live SDK input that Claude may not have read yet. Interrupting the turn
+   * has to discard them, or the SDK dequeues one and resumes the turn we just stopped. SDK user
+   * UUIDs are provider-private; never let them escape the adapter boundary.
   */
-  private readonly unstartedMessageUuids = new Set<string>();
+  private readonly queuedSteerUuids = new Set<string>();
  /** Human steers whose text has not reached Claude yet and therefore supersede blocking cards. */
  private readonly permissionClearingSteerUuids = new Set<string>();
  private claudeSessionId: string | null;
@@ -2136,12 +2126,6 @@ class ClaudeAgentSession implements AgentSession {
  private queryPumpPromise: Promise<void> | null = null;
  private queryRestartNeeded = false;
  private pendingInterruptAbort = false;
-  /**
-   * Whether Claude's main session is inside one of its own turns: set by system/init and by a
-   * pushed message's command_lifecycle "started" (/compact works for seconds before its init),
-   * cleared by the turn's result or an idle session state. See observeMainTurnBracket.
-   */
-  private mainTurnInFlight = false;
  private foregroundHasVisibleActivity = false;
  private activeTurnHasAssistantText = false;
  private readonly contextUsage: ClaudeContextUsageState;
@@ -2288,7 +2272,6 @@ class ClaudeAgentSession implements AgentSession {
    this.contextUsage.beginTurn();
    this.transitionTurnState("foreground", "foreground turn started");
    this.clearRecentStderr();
-    if (sdkUserMessageId) this.unstartedMessageUuids.add(sdkUserMessageId);

    let cancelIssued = false;
    const requestCancel = () => {
@@ -2299,18 +2282,13 @@ class ClaudeAgentSession implements AgentSession {
      if (this.cancelCurrentTurn === requestCancel) {
        this.cancelCurrentTurn = null;
      }
-      // Whether Claude has this message in hand. A late idle from the previous turn can clear
-      // mainTurnInFlight after Claude started it, so the message's own lifecycle counts too.
-      const claudeStartedTurn =
-        this.mainTurnInFlight ||
-        (sdkUserMessageId !== null && !this.unstartedMessageUuids.has(sdkUserMessageId));
      this.rejectAllPendingPermissions(new Error("Permission request canceled"));
      this.finishForegroundTurn({
        type: "turn_canceled",
        provider: "claude",
        reason: "Interrupted",
      });
-      void this.interruptActiveTurn(claudeStartedTurn).catch((error) => {
+      void this.interruptActiveTurn().catch((error) => {
        this.logger.warn({ err: error }, "Failed to interrupt during cancel");
      });
    };
@@ -2320,11 +2298,6 @@ class ClaudeAgentSession implements AgentSession {

    try {
      await this.ensureQuery();
-      if (cancelIssued) {
-        // Stopped while Claude was still starting up: withdrawn by never sending it.
-        if (sdkUserMessageId) this.unstartedMessageUuids.delete(sdkUserMessageId);
-        return { turnId };
-      }
      if (!this.input) {
        throw new Error("Claude session input stream not initialized");
      }
@@ -2338,7 +2311,6 @@ class ClaudeAgentSession implements AgentSession {
        }
      }, 0);
    } catch (error) {
-      if (sdkUserMessageId) this.unstartedMessageUuids.delete(sdkUserMessageId);
      this.finishForegroundTurn(
        this.buildTurnFailedEvent(error instanceof Error ? error.message : "Claude stream failed"),
      );
@@ -2387,7 +2359,7 @@ class ClaudeAgentSession implements AgentSession {
    clearPendingPermissions: boolean,
  ): void {
    const uuid = message.uuid;
-    if (uuid) this.unstartedMessageUuids.add(uuid);
+    if (uuid) this.queuedSteerUuids.add(uuid);
    if (uuid && clearPendingPermissions) {
      this.permissionClearingSteerUuids.add(uuid);
    }
@@ -2398,7 +2370,7 @@ class ClaudeAgentSession implements AgentSession {
      }
    } catch (error) {
      if (uuid) {
-        this.unstartedMessageUuids.delete(uuid);
+        this.queuedSteerUuids.delete(uuid);
        this.permissionClearingSteerUuids.delete(uuid);
      }
      throw error;
@@ -3210,8 +3182,6 @@ class ClaudeAgentSession implements AgentSession {
    const options = await this.buildOptions(launchMode);
    this.logger.debug({ options: summarizeClaudeOptionsForLog(options) }, "claude query");
    this.input = input;
-    // A fresh Claude process has no turn of its own in flight.
-    this.mainTurnInFlight = false;
    this.query = claudeQuery(
      { prompt: input.iterable, options },
      {
@@ -3331,12 +3301,7 @@ class ClaudeAgentSession implements AgentSession {
    return createProviderEnv({
      baseEnv: process.env,
      runtimeSettings: this.runtimeSettings,
-      overlays: [
-        this.launchEnv,
-        // Makes the CLI announce session_state_changed, whose "idle" is the safety net that closes
-        // an autonomous turn (see consumeSessionStateChange).
-        { CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS: "1" },
-      ],
+      overlays: [this.launchEnv],
    });
  }

@@ -3403,10 +3368,6 @@ class ClaudeAgentSession implements AgentSession {
      ...settingsOptions,
      // Provider subagent panes render the child's nested transcript.
      forwardSubagentText: true,
-      // Stop and replace abort only the main turn, like Esc in Claude Code, and background
-      // subagents keep running. Without this declaration an interrupt kills every one of them.
-      // Claude stops a helper itself with its TaskStop tool.
-      perTaskStopAffordance: true,
      hooks: this.buildSubagentEffortHooks(),
      ...(this.persistSession === undefined ? {} : { persistSession: this.persistSession }),
      env: sdkEnv,
@@ -3937,67 +3898,35 @@ class ClaudeAgentSession implements AgentSession {
    return false;
  }

+  private isAssistantishMessage(message: SDKMessage): boolean {
+    return (
+      message.type === "assistant" ||
+      message.type === "stream_event" ||
+      message.type === "tool_progress" ||
+      (message.type === "system" && message.subtype === "task_notification")
+    );
+  }
+
  /**
-   * Claude's account of whether anything in the session is working, which is not the same as the
-   * main session working: Claude Code 2.1.280 stays "running" for as long as any background
-   * subagent is alive. So "running" never opens a turn.
-   *
-   * "idle" means nothing at all is running, so it closes an autonomous turn whatever opened it.
-   * It never closes a foreground turn: an idle can trail the previous turn and land just after a
-   * new send, and it must not end that send.
-   *
-   * Returns true when the frame was a state change, which is bookkeeping and never reaches the
-   * timeline.
+   * Claude keeps talking about the request it was told to kill — the notification for the tool it
+   * just stopped, trailing assistant output. That is not new work, so it must not open a turn: the
+   * only message that would close that turn is the result shouldSuppressStaleResult drops, leaving
+   * the agent stuck reporting "running" forever.
   */
-  private consumeSessionStateChange(message: SDKMessage): boolean {
-    if (message.type !== "system" || message.subtype !== "session_state_changed") {
+  private shouldStartAutonomousTurn(message: SDKMessage): boolean {
+    if (this.activeForegroundTurnId || this.pendingInterruptAbort) {
      return false;
    }
-    if (message.state === "idle") {
-      this.mainTurnInFlight = false;
-      this.completeAutonomousTurn();
-    }
-    return true;
-  }
-
-  /** Tracks mainTurnInFlight from Claude's own turn brackets (isClaudeTurnInit). */
-  private observeMainTurnBracket(message: SDKMessage): void {
-    if (message.type === "result") {
-      this.mainTurnInFlight = false;
-      return;
-    }
-    if (isClaudeTurnInit(message)) {
-      this.mainTurnInFlight = true;
-      // A new turn has begun, so the interrupted one is over. An interrupt that landed after its
-      // turn had already ended gets no result, and the leftover flag would swallow this turn's.
-      this.pendingInterruptAbort = false;
-      return;
-    }
-    if (readClaudeCommandLifecycle(message)?.state === "started") {
-      this.mainTurnInFlight = true;
-    }
-  }
-
-  /**
-   * Only the main session's own turn start opens an autonomous turn. Everything a background
-   * subagent emits (its task frames, its own background jobs' notifications, rate limit events)
-   * arrives outside one, and no result would ever close a turn it opened.
-   */
-  private opensAutonomousTurn(message: SDKMessage): boolean {
-    return isClaudeTurnInit(message) && !this.activeForegroundTurnId;
+    return this.isAssistantishMessage(message);
  }

  private async routeSdkMessageFromPump(message: SDKMessage): Promise<void> {
-    if (this.consumeSessionStateChange(message)) {
-      return;
-    }
-    this.observeMainTurnBracket(message);
    if (this.shouldSuppressStaleResult(message)) {
      return;
    }

    const isForeground = Boolean(this.activeForegroundTurnId);
-    if (this.opensAutonomousTurn(message)) {
+    if (this.shouldStartAutonomousTurn(message)) {
      this.startAutonomousTurn();
    }
    if (!isForeground && !this.autonomousTurn && message.type === "result") {
@@ -4139,13 +4068,7 @@ class ClaudeAgentSession implements AgentSession {
    return true;
  }

-  /**
-   * Interrupts Claude only when a turn of its main session is running. With nothing running there
-   * is nothing to stop but our own queued messages, so those are withdrawn instead: an interrupt
-   * would reach only background helpers (and kill them on a CLI that ignores
-   * perTaskStopAffordance), and no result would follow to consume pendingInterruptAbort.
-   */
-  private async interruptActiveTurn(claudeStartedTurn = this.mainTurnInFlight): Promise<void> {
+  private async interruptActiveTurn(): Promise<void> {
    const queryToInterrupt = this.query;
    if (!queryToInterrupt || typeof queryToInterrupt.interrupt !== "function") {
      this.logger.trace(
@@ -4159,16 +4082,8 @@ class ClaudeAgentSession implements AgentSession {
      );
      return;
    }
-    if (claudeStartedTurn) {
-      this.pendingInterruptAbort = true;
-      await this.withdrawUnstartedMessages(queryToInterrupt);
-    } else {
-      // Claude can dequeue a message for its next turn before announcing it started; withdrawing
-      // it is then a no-op, and only an interrupt stops it. Withdraw once: a prompt sent while
-      // this withdrawal was in flight belongs to the next turn.
-      if (await this.withdrawUnstartedMessages(queryToInterrupt)) return;
-      this.pendingInterruptAbort = true;
-    }
+    this.pendingInterruptAbort = true;
+    await this.discardQueuedSteers(queryToInterrupt);
    try {
      await this.awaitWithTimeout(
        queryToInterrupt.interrupt(),
@@ -4180,15 +4095,14 @@ class ClaudeAgentSession implements AgentSession {
  }

  /**
-   * Interrupt means interrupt: a message Claude never started dies with the turn instead of
-   * resuming it. One already dequeued cannot be recalled, and does not need to be, since the
-   * interrupt kills it. Returns whether Claude confirmed every message withdrawn.
+   * Interrupt means interrupt: a steer Claude never read dies with the turn instead of resuming it.
+   * A steer already dequeued cannot be recalled, and does not need to be — the interrupt kills it.
   */
-  private async withdrawUnstartedMessages(query: Query): Promise<boolean> {
-    const uuids = [...this.unstartedMessageUuids];
-    this.unstartedMessageUuids.clear();
+  private async discardQueuedSteers(query: Query): Promise<void> {
+    const uuids = [...this.queuedSteerUuids];
+    this.queuedSteerUuids.clear();
    this.permissionClearingSteerUuids.clear();
-    if (uuids.length === 0) return true;
+    if (uuids.length === 0) return;
    // The SDK runtime supports this, but its public Query type has not caught up. Keep the
    // compatibility escape hatch inside the Claude adapter.
    const cancelAsyncMessage = (
@@ -4196,17 +4110,14 @@ class ClaudeAgentSession implements AgentSession {
        cancelAsyncMessage?: (uuid: string) => Promise<boolean>;
      }
    ).cancelAsyncMessage;
-    if (!cancelAsyncMessage) return false;
-    let withdrewAll = true;
+    if (!cancelAsyncMessage) return;
    for (const uuid of uuids) {
      try {
-        if (!(await cancelAsyncMessage.call(query, uuid))) withdrewAll = false;
+        await cancelAsyncMessage.call(query, uuid);
      } catch (error) {
-        withdrewAll = false;
-        this.logger.warn({ err: error }, "Failed to withdraw a queued Claude message");
+        this.logger.warn({ err: error }, "Failed to discard a queued Claude steer");
      }
    }
-    return withdrewAll;
  }

  private translateMessageToEvents(
@@ -4255,7 +4166,7 @@ class ClaudeAgentSession implements AgentSession {
      }
    }

-    this.forgetStartedMessage(message);
+    this.forgetReadSteer(message);

    switch (message.type) {
      case "system":
@@ -4289,14 +4200,11 @@ class ClaudeAgentSession implements AgentSession {
    return events;
  }

-  /**
-   * Once Claude has started a message, or cancelled it, there is nothing left to withdraw on
-   * interrupt.
-   */
-  private forgetStartedMessage(message: unknown): void {
+  /** Once Claude has read a steer there is nothing left to discard on interrupt. */
+  private forgetReadSteer(message: unknown): void {
    const lifecycle = readClaudeCommandLifecycle(message);
    if (!lifecycle || lifecycle.state === "queued") return;
-    this.unstartedMessageUuids.delete(lifecycle.commandUuid);
+    this.queuedSteerUuids.delete(lifecycle.commandUuid);
    this.permissionClearingSteerUuids.delete(lifecycle.commandUuid);
  }

@@ -6611,8 +6519,7 @@ function extractClaudeUserText(messageRaw: unknown): string | null {

 interface ClaudeCommandLifecycle {
  commandUuid: string;
-  /** "cancelled" is terminal too: API errors, interrupts and "now" pre-emption end a message. */
-  state: "queued" | "started" | "completed" | "cancelled";
+  state: "queued" | "started" | "completed";
 }

 /** Runtime-only Claude frames are validated here because the SDK's public union omits them. */
@@ -6621,7 +6528,7 @@ function readClaudeCommandLifecycle(message: unknown): ClaudeCommandLifecycle |
  if (record?.type !== "command_lifecycle") return null;
  if (
    typeof record.command_uuid !== "string" ||
-    !["queued", "started", "completed", "cancelled"].includes(String(record.state))
+    !["queued", "started", "completed"].includes(String(record.state))
  ) {
    return null;
  }
@@ -511,33 +511,6 @@ describe("ClaudeTaskProtocolSource", () => {
    expect(source.cancelRunningForegroundTasks()).toEqual([]);
  });

-  it("does not cancel a subagent announced as backgrounded at spawn", () => {
-    // Claude sets is_backgrounded on task_started for a child spawned in the background, and
-    // sends no task_updated patch for it.
-    const source = new ClaudeTaskProtocolSource();
-    source.observe(taskStarted({ is_backgrounded: true }));
-
-    expect(source.cancelRunningForegroundTasks()).toEqual([]);
-  });
-
-  it("does not cancel a resumed subagent, which Claude always runs in the background", () => {
-    const source = new ClaudeTaskProtocolSource();
-    source.observe(taskStarted({ tool_use_id: "toolu_original", is_backgrounded: false }));
-    source.observe(taskUpdated("completed"));
-    source.observe(taskStarted({ tool_use_id: "toolu_resumed", is_backgrounded: true }));
-
-    expect(source.cancelRunningForegroundTasks()).toEqual([]);
-  });
-
-  it("still cancels a subagent announced in the foreground", () => {
-    const source = new ClaudeTaskProtocolSource();
-    source.observe(taskStarted({ is_backgrounded: false }));
-
-    expect(source.cancelRunningForegroundTasks()).toEqual([
-      { kind: "status", id: "toolu_01DgLoPMW9", status: "canceled" },
-    ]);
-  });
-
  it("still routes a backgrounded subagent that settles after the interrupt", () => {
    // The headline case: interrupt, continue, and the child that was told to outlive the turn
    // reports completion later. Wiping the routing table on cancel drops this on the floor and
@@ -16,8 +16,7 @@ import {
 *
 * Verified on the wire (Claude Code 2.1.220, Paseo's own query options):
 *
- *   task_started       task_id, tool_use_id, description, subagent_type, task_type,
- *                      is_backgrounded
+ *   task_started       task_id, tool_use_id, description, subagent_type, task_type
 *   task_updated       task_id, patch.status, patch.is_backgrounded
 *   task_notification  task_id, tool_use_id, status
 *
@@ -40,11 +39,6 @@ interface TaskStartedMessage {
  task_type?: string;
  prompt?: string;
  skip_transcript?: boolean;
-  /**
-   * Set at spawn: true for a task registered in the background. A resumed subagent is always
-   * registered in the background.
-   */
-  is_backgrounded?: boolean;
 }

 /** Task-tool subagents. Backgrounded shell commands announce as `local_bash`. */
@@ -77,8 +71,8 @@ interface TaskUpdatedMessage {
  task_id: string;
  /**
   * `is_backgrounded` is declared on `SDKTaskUpdatedMessage["patch"]`: it flips when a foreground
-   * task is moved to the background after `task_started`. Together with `task_started`'s own
-   * flag it separates a child that dies with its turn from one told to outlive it.
+   * task is backgrounded, which is the only signal that separates a child that dies with its turn
+   * from one that was explicitly told to outlive it.
   */
  patch?: { status?: string; is_backgrounded?: boolean };
 }
@@ -177,8 +171,8 @@ export class ClaudeTaskProtocolSource {
  /** Workflow invocations already own a real Workflow card in the parent timeline. */
  private readonly idsWithExistingParentToolCard = new Set<string>();
  /**
-   * Declared subagents running in the background, whether spawned there or moved there later.
-   * They outlive the turn that spawned them, so a turn ending is not evidence that they stopped.
+   * Declared subagents that were moved to the background. They outlive the turn that spawned
+   * them, so a turn ending is not evidence that they stopped.
   */
  private readonly backgroundedIds = new Set<string>();
  /** Last status emitted per subagent, so a redundant announcement is not re-broadcast. */
@@ -337,7 +331,6 @@ export class ClaudeTaskProtocolSource {

    this.sawTaskStarted = true;
    const existingId = this.subagentIdByTaskId.get(message.task_id);
-    this.recordBackgrounded(existingId ?? id, message.is_backgrounded);
    if (existingId) {
      return this.observeExistingTaskStart(message, id, existingId);
    }
@@ -421,15 +414,14 @@ export class ClaudeTaskProtocolSource {

  private observeTaskUpdated(message: TaskUpdatedMessage): SubagentObservation[] {
    const id = this.subagentIdByTaskId.get(message.task_id);
-    if (id) this.recordBackgrounded(id, message.patch?.is_backgrounded);
+    const backgrounded = message.patch?.is_backgrounded;
+    if (id && typeof backgrounded === "boolean") {
+      if (backgrounded) this.backgroundedIds.add(id);
+      else this.backgroundedIds.delete(id);
+    }
    return this.observeStatus(message.task_id, message.patch?.status);
  }

-  private recordBackgrounded(id: string, backgrounded: boolean | undefined): void {
-    if (backgrounded === true) this.backgroundedIds.add(id);
-    else if (backgrounded === false) this.backgroundedIds.delete(id);
-  }
-
  private observeTaskNotification(message: TaskNotificationMessage): SubagentObservation[] {
    const observations = this.observeWorkflowResult(message);
    observations.push(...this.observeUsage(message.task_id, message.usage));
@@ -304,166 +304,6 @@ async function waitForRunningClaudeSleep(
  );
 }

-// Explicit point-in-time polls of agent status, on top of (not instead of) the pushed
-// agent_update events the collector already records. A phantom "running" flip that starts and
-// ends between two polls would still be caught by the pushed-event scan the callers pair this
-// with; polling here additionally proves the daemon answers fetchAgent with "idle" throughout,
-// not just that it eventually pushes one.
-async function sampleAgentStatuses(
-  client: DaemonClient,
-  agentId: string,
-  samples: number,
-  intervalMs: number,
-): Promise<string[]> {
-  const statuses: string[] = [];
-  for (let i = 0; i < samples; i += 1) {
-    const snapshot = await client.fetchAgent({ agentId });
-    statuses.push(snapshot?.agent.status ?? "missing");
-    if (i < samples - 1) {
-      await sleep(intervalMs);
-    }
-  }
-  return statuses;
-}
-
-// NOTE: agent_stream events on the wire (AgentStreamEventPayloadSchema in
-// packages/protocol/src/messages.ts) do not include a "provider_subagent" variant. A backgrounded
-// subagent's descriptor updates are forwarded exclusively as separate "agent.provider_subagents.update"
-// messages (see forwardProviderSubagentUpdate in session.ts), and that push channel's delivery is
-// gated by capabilities this test's plain DaemonClient does not declare. list_provider_subagents is a
-// plain request/response RPC unaffected by that gating, so status history below polls it directly
-// instead of trying to reconstruct status transitions from the stream.
-type ProviderSubagentDescriptor = Awaited<
-  ReturnType<DaemonClient["listProviderSubagents"]>
->["subagents"][number];
-
-interface ProviderSubagentPoll {
-  subagent: ProviderSubagentDescriptor;
-  // Every status observed while polling, in order, so a transient cancel cannot hide behind a
-  // later "completed" read even though the store's status field is not expected to un-cancel.
-  history: string[];
-}
-
-// Polls agent.provider_subagents.list until the backgrounded helper is registered at all.
-// "Main's turn is running" (waitForAgentUpsert) fires on generic turn-start bookkeeping, which
-// can be true before Claude has actually issued the Agent tool call; canceling that early
-// cancels a turn with no helper launched yet, which is not what "Stop spares a helper" means to
-// test. This confirms the helper actually exists before the caller acts on it.
-async function waitForProviderSubagentToExist(
-  client: DaemonClient,
-  agentId: string,
-  timeoutMs = 60_000,
-): Promise<ProviderSubagentDescriptor> {
-  const deadline = Date.now() + timeoutMs;
-  while (Date.now() < deadline) {
-    const { subagents } = await client.listProviderSubagents(agentId);
-    if (subagents[0]) {
-      return subagents[0];
-    }
-    await sleep(300);
-  }
-  throw new Error(
-    `Timed out waiting for a background helper to be registered for agent ${agentId}`,
-  );
-}
-
-// Claude starts the wake-up turn a moment after the helper's completion lands (0.1 to 5 s in
-// recorded traces), so poll for it instead of checking the instant the helper reads completed.
-// The daemon announces an autonomous turn to subscribers as a pushed "running" agent_update,
-// not as an agent_stream turn_started (that stream reaches the client that started a run).
-async function waitForWakeTurn(
-  collector: ReturnType<typeof createMessageCollector>,
-  agentId: string,
-  fromIndex: number,
-  timeoutMs = 30_000,
-): Promise<boolean> {
-  const deadline = Date.now() + timeoutMs;
-  while (Date.now() < deadline) {
-    const window = collector.messages.slice(fromIndex);
-    const woke =
-      getAgentStatuses(window, agentId).includes("running") ||
-      window.some(
-        (message) =>
-          message.type === "agent_stream" &&
-          message.payload.agentId === agentId &&
-          message.payload.event.type === "turn_started",
-      );
-    if (woke) return true;
-    await sleep(500);
-  }
-  return false;
-}
-
-// The wake-up turn runs briefly after it opens, so the final state is read once it settles.
-async function waitForAgentStatus(
-  client: DaemonClient,
-  agentId: string,
-  status: string,
-  timeoutMs = 60_000,
-): Promise<string | undefined> {
-  const deadline = Date.now() + timeoutMs;
-  let last: string | undefined;
-  while (Date.now() < deadline) {
-    last = (await client.fetchAgent({ agentId }))?.agent.status;
-    if (last === status) return last;
-    await sleep(500);
-  }
-  return last;
-}
-
-// Polls agent.provider_subagents.list until the single backgrounded helper leaves "running".
-// Scenarios in this file always launch exactly one background helper, so subagents[0] is it.
-async function waitForProviderSubagentTerminal(
-  client: DaemonClient,
-  agentId: string,
-  timeoutMs = 90_000,
-): Promise<ProviderSubagentPoll> {
-  const deadline = Date.now() + timeoutMs;
-  const history: string[] = [];
-  let lastSeen: ProviderSubagentDescriptor[] = [];
-  while (Date.now() < deadline) {
-    const { subagents } = await client.listProviderSubagents(agentId);
-    lastSeen = subagents;
-    const subagent = subagents[0];
-    if (subagent) {
-      history.push(subagent.status);
-      if (subagent.status !== "running") {
-        return { subagent, history };
-      }
-    }
-    await sleep(1_000);
-  }
-  throw new Error(
-    `Timed out waiting for the background helper to leave "running". history=${JSON.stringify(history)} lastSeen=${JSON.stringify(lastSeen)}`,
-  );
-}
-
-// Pulls the main agent's own assistant text via fetchAgentTimeline rather than the push
-// collector. Assistant text delivery is paced (docs/agent-stream-performance.md), so checking
-// the collector immediately after waitForFinish resolves can still miss the final text; the
-// timeline fetch is authoritative and matches what the pre-existing tests in this file do.
-async function fetchAssistantTexts(
-  client: DaemonClient,
-  agentId: string,
-  limit = 100,
-): Promise<string[]> {
-  const timeline = await client.fetchAgentTimeline(agentId, { limit });
-  return timeline.entries
-    .filter((entry) => entry.item.type === "assistant_message")
-    .map((entry) => (entry.item as Extract<AgentTimelineItem, { type: "assistant_message" }>).text);
-}
-
-async function fetchSubagentAssistantTexts(
-  client: DaemonClient,
-  agentId: string,
-  subagentId: string,
-): Promise<string[]> {
-  const timeline = await client.fetchProviderSubagentTimeline(agentId, subagentId, { limit: 50 });
-  return timeline.rows
-    .filter((row) => row.item.type === "assistant_message")
-    .map((row) => (row.item as Extract<AgentTimelineItem, { type: "assistant_message" }>).text);
-}
-
 describe("daemon E2E (real claude) - send message during tool call", () => {
  let canRun = false;
  interface SteeringResources {
@@ -664,141 +504,6 @@ describe("daemon E2E (real claude) - send message during tool call", () => {
    }
  }, 210_000);

-  test("a background subagent keeps running after a message is sent while it works", async () => {
-    // The scenario the rest of this file explicitly rules out: every other test here tells Claude
-    // "Do not use a background task", so steering during a backgrounded subagent was never
-    // covered. A subagent streams on the parent's channel, so a parent that mistakes the child's
-    // frames for its own work reports "running" after it has already finished, and the message
-    // sent into that window is refused, or delivered by cancelling the turn and taking the
-    // subagent with it. Both outcomes are user-visible, and both are what this asserts against.
-    const logger = pino({ level: "silent" });
-    const resources: SteeringResources = {
-      cwd: tmpCwd(),
-      daemon: null,
-      client: null,
-      collector: null,
-    };
-    try {
-      resources.daemon = await createTestPaseoDaemon({
-        agentClients: { claude: new ClaudeAgentClient({ logger }) },
-        logger,
-      });
-      resources.client = new DaemonClient({ url: `ws://127.0.0.1:${resources.daemon.port}/ws` });
-      const { client, cwd } = resources;
-      if (!client) throw new Error("Claude background-subagent test client was not created");
-      await within("connect background-subagent test client", 15_000, client.connect());
-      await within(
-        "subscribe background-subagent test client",
-        15_000,
-        client.fetchAgents({ subscribe: {} }),
-      );
-      const agent = await within(
-        "create background-subagent test agent",
-        30_000,
-        client.createAgent({
-          cwd: cwd ?? process.cwd(),
-          title: "claude-background-survives-send",
-          ...getRealProviderConfig("claude"),
-        }),
-      );
-      resources.collector = createMessageCollector(client);
-      await within(
-        "launch one background subagent and end the turn",
-        30_000,
-        client.sendAgentMessage(
-          agent.id,
-          [
-            "Use the Agent tool exactly once with run_in_background: true.",
-            "subagent_type: general-purpose.",
-            `description: "bg survivor".`,
-            `prompt: "Use the Bash tool with run_in_background: true to run exactly: sleep 40.`,
-            `Wait for its completion notification, then reply exactly: CHILD_DONE."`,
-            "Immediately after launching it, reply with the single word LAUNCHED and end your turn.",
-            "Do not wait for it. Do not call any other tools.",
-          ].join(" "),
-          { messageId: generateClientMessageId() },
-        ),
-      );
-
-      // The main session has ended its turn. It must read as idle even though the subagent it
-      // launched is still streaming on the shared channel.
-      const afterLaunch = await within(
-        "wait for the main session to go idle after launching the subagent",
-        120_000,
-        client.waitForFinish(agent.id, 110_000),
-      );
-      expect(
-        afterLaunch.status,
-        "a main session that finished its turn must not report busy because a subagent is running",
-      ).not.toBe("running");
-
-      // And a message sent in that window must be accepted rather than refused.
-      const followUpId = generateClientMessageId();
-      await within(
-        "send a message to the idle main session while the subagent runs",
-        30_000,
-        client.sendAgentMessage(agent.id, "Are you there? Reply exactly: MAIN_ALIVE.", {
-          messageId: followUpId,
-        }),
-      );
-      await within(
-        "wait for the main session to answer",
-        120_000,
-        client.waitForFinish(agent.id, 110_000),
-      );
-
-      const timeline = await within(
-        "fetch background-subagent timeline",
-        15_000,
-        client.fetchAgentTimeline(agent.id, { limit: 200 }),
-      );
-      const assistantText = timeline.entries
-        .filter((entry) => entry.item.type === "assistant_message")
-        .map(
-          (entry) => (entry.item as Extract<AgentTimelineItem, { type: "assistant_message" }>).text,
-        )
-        .join("\\n");
-      expect(
-        assistantText,
-        "the main session must be reachable while its background subagent still runs",
-      ).toContain("MAIN_ALIVE");
-
-      // The subagent must have survived the send rather than being cancelled with the turn. Its
-      // status is read from agent.provider_subagents.list (see the note above
-      // waitForProviderSubagentToExist): agent_stream carries no provider_subagent events.
-      const { subagents } = await within(
-        "list provider subagents after the send",
-        15_000,
-        client.listProviderSubagents(agent.id),
-      );
-      expect(subagents.length, "the background subagent must be tracked").toBeGreaterThan(0);
-      expect(
-        subagents.map((subagent) => subagent.status),
-        "a backgrounded subagent must not be canceled by a message sent to the main session",
-      ).not.toContain("canceled");
-      const { subagent, history } = await within(
-        "wait for the background subagent to finish",
-        90_000,
-        waitForProviderSubagentTerminal(client, agent.id, 80_000),
-      );
-      expect(subagent.status, "the helper must complete, not be canceled or fail").toBe(
-        "completed",
-      );
-      expect(history, "no status poll may read canceled").not.toContain("canceled");
-    } finally {
-      const cleanup = await Promise.allSettled([
-        Promise.resolve(resources.collector?.unsubscribe()),
-        resources.client?.close() ?? Promise.resolve(),
-        resources.daemon?.close() ?? Promise.resolve(),
-      ]);
-      if (resources.cwd) rmSync(resources.cwd, { recursive: true, force: true });
-      const failures = cleanup.flatMap((result) =>
-        result.status === "rejected" ? [result.reason] : [],
-      );
-      expect(failures, "Claude background-subagent E2E cleanup failures").toEqual([]);
-    }
-  }, 300_000);
-
  test("Stop cancels a queued Claude steer before it can resume the interrupted turn", async () => {
    const logger = pino({ level: "silent" });
    const cwd = tmpCwd();
@@ -973,430 +678,4 @@ describe("daemon E2E (real claude) - send message during tool call", () => {
      rmSync(cwd, { recursive: true, force: true });
    }
  }, 300_000);
-
-  test("a helper's own nested background job does not phantom-run the parent or kill the helper", async () => {
-    // The exact reported bug: main backgrounds a helper, the helper itself starts its OWN
-    // background job (a grandchild from main's perspective) and then keeps working in the
-    // foreground. The grandchild's completion is bookkeeping that belongs to the helper, not to
-    // main, and must not make main phantom-report "running" or get treated as busy.
-    const logger = pino({ level: "silent" });
-    const resources: SteeringResources = {
-      cwd: tmpCwd(),
-      daemon: null,
-      client: null,
-      collector: null,
-    };
-    try {
-      resources.daemon = await createTestPaseoDaemon({
-        agentClients: { claude: new ClaudeAgentClient({ logger }) },
-        logger,
-      });
-      resources.client = new DaemonClient({ url: `ws://127.0.0.1:${resources.daemon.port}/ws` });
-      const { client, cwd } = resources;
-      if (!client) throw new Error("nested background-job test client was not created");
-      await within("connect nested background-job test client", 15_000, client.connect());
-      await within(
-        "subscribe nested background-job test client",
-        15_000,
-        client.fetchAgents({ subscribe: {} }),
-      );
-      const agent = await within(
-        "create nested background-job test agent",
-        30_000,
-        client.createAgent({
-          cwd: cwd ?? process.cwd(),
-          title: "claude-nested-background-job",
-          ...getRealProviderConfig("claude"),
-        }),
-      );
-      resources.collector = createMessageCollector(client);
-
-      await within(
-        "launch a helper with its own nested background job and end the turn",
-        30_000,
-        client.sendAgentMessage(
-          agent.id,
-          [
-            "Use the Agent tool exactly once with run_in_background: true.",
-            "subagent_type: general-purpose.",
-            `description: "nested bg survivor".`,
-            `prompt: "Use the Bash tool with run_in_background: true to run exactly:`,
-            `python3 -c 'import time; time.sleep(5)'.`,
-            `Immediately after starting it, without waiting for it, use the Bash tool again`,
-            `in the foreground to run exactly: python3 -c 'import time; time.sleep(50)'.`,
-            `After that foreground command finishes, reply exactly: CHILD_DONE."`,
-            "Immediately after launching it, reply with the single word LAUNCHED and end your turn.",
-            "Do not wait for it. Do not call any other tools.",
-          ].join(" "),
-          { messageId: generateClientMessageId() },
-        ),
-      );
-
-      const afterLaunch = await within(
-        "wait for the main session to go idle after launching the nested-background helper",
-        120_000,
-        client.waitForFinish(agent.id, 110_000),
-      );
-      expect(afterLaunch.status, "the main session must be idle once it replied LAUNCHED").toBe(
-        "idle",
-      );
-
-      // The helper's own nested background job (5s) finishes while the helper is still busy
-      // in its unrelated foreground sleep (50s). Sample for 30s, well past the nested job's
-      // completion even when the helper is slow to start it,
-      // both by polling and by scanning every pushed agent_update in the window, so a brief
-      // phantom flip cannot slip between polls.
-      const sampleWindowStart = resources.collector.messages.length;
-      const polledStatuses = await sampleAgentStatuses(client, agent.id, 11, 3_000);
-      const pushedStatuses = getAgentStatuses(
-        resources.collector.messages.slice(sampleWindowStart),
-        agent.id,
-      );
-      const observedRunning = [...polledStatuses, ...pushedStatuses].filter(
-        (status) => status === "running",
-      );
-      expect(
-        observedRunning,
-        `the parent must stay idle across the nested job's completion; polled=${JSON.stringify(polledStatuses)} pushed=${JSON.stringify(pushedStatuses)}`,
-      ).toEqual([]);
-
-      // A message sent in that window must still be answered normally.
-      await within(
-        "send PONG request while the nested job settles",
-        30_000,
-        client.sendMessage(agent.id, "Reply with exactly PONG.", {
-          messageId: generateClientMessageId(),
-        }),
-      );
-      await within("wait for the PONG reply", 60_000, client.waitForFinish(agent.id, 50_000));
-      // Pulled via fetchAgentTimeline, not the push collector: assistant text delivery is paced
-      // (docs/agent-stream-performance.md) and can trail waitForFinish's own completion signal,
-      // so the collector can still be missing the final text the instant waitForFinish resolves.
-      const pongTexts = await within(
-        "fetch timeline for the PONG reply",
-        15_000,
-        fetchAssistantTexts(client, agent.id, 20),
-      );
-      expect(
-        pongTexts.join("\n"),
-        "the agent must answer PONG while the helper is still running",
-      ).toContain("PONG");
-
-      const messagesBeforeWake = resources.collector.messages.length;
-
-      // The helper itself must survive: never recorded canceled, and it eventually reports
-      // CHILD_DONE from its own foreground sleep finishing.
-      const { subagent, history } = await within(
-        "wait for the nested-background helper to finish",
-        90_000,
-        waitForProviderSubagentTerminal(client, agent.id, 80_000),
-      );
-      expect(subagent.status, "the helper must complete, not be canceled or fail").toBe(
-        "completed",
-      );
-      expect(
-        history,
-        `no provider subagent status poll may ever read canceled; history=${JSON.stringify(history)}`,
-      ).not.toContain("canceled");
-      const subagentTexts = await fetchSubagentAssistantTexts(client, agent.id, subagent.id);
-      expect(
-        subagentTexts.join("\n"),
-        "the helper's own transcript must contain its final CHILD_DONE reply",
-      ).toContain("CHILD_DONE");
-
-      // The helper's completion should wake the main session with a fresh turn (the
-      // session-state-driven autonomous turn), separate from the PONG exchange above.
-      const wokeMainAgent = await waitForWakeTurn(
-        resources.collector,
-        agent.id,
-        messagesBeforeWake,
-      );
-      if (!wokeMainAgent) {
-        const wakeWindowMessages = resources.collector.messages.slice(messagesBeforeWake);
-        const wakeWindowEventTypes = wakeWindowMessages
-          .filter(
-            (message) => message.type === "agent_stream" && message.payload.agentId === agent.id,
-          )
-          .map((message) =>
-            message.type === "agent_stream" ? message.payload.event.type : "unknown",
-          );
-        const timeline = await client
-          .fetchAgentTimeline(agent.id, { limit: 100 })
-          .catch(() => null);
-        throw new Error(
-          `the helper's completion must wake the main session with a new turn. ` +
-            `wakeWindowEventTypes=${JSON.stringify(wakeWindowEventTypes)} ` +
-            `recentTimeline=${JSON.stringify(timeline ? summarizeTimelineItems(timeline) : null)}`,
-        );
-      }
-
-      expect(await waitForAgentStatus(client, agent.id, "idle"), "the agent must end idle").toBe(
-        "idle",
-      );
-    } finally {
-      const cleanup = await Promise.allSettled([
-        Promise.resolve(resources.collector?.unsubscribe()),
-        resources.client?.close() ?? Promise.resolve(),
-        resources.daemon?.close() ?? Promise.resolve(),
-      ]);
-      if (resources.cwd) rmSync(resources.cwd, { recursive: true, force: true });
-      const failures = cleanup.flatMap((result) =>
-        result.status === "rejected" ? [result.reason] : [],
-      );
-      expect(failures, "nested background-job E2E cleanup failures").toEqual([]);
-    }
-  }, 300_000);
-
-  test("the app's default steer survives a backgrounded helper while the main session works", async () => {
-    // appSettings.sendBehavior defaults to "steer" (packages/app/src/hooks/use-settings/storage.ts),
-    // so this is what the app actually sends when a user replies while an agent looks busy.
-    const logger = pino({ level: "silent" });
-    const resources: SteeringResources = {
-      cwd: tmpCwd(),
-      daemon: null,
-      client: null,
-      collector: null,
-    };
-    try {
-      resources.daemon = await createTestPaseoDaemon({
-        agentClients: { claude: new ClaudeAgentClient({ logger }) },
-        logger,
-      });
-      resources.client = new DaemonClient({ url: `ws://127.0.0.1:${resources.daemon.port}/ws` });
-      const { client, cwd } = resources;
-      if (!client) throw new Error("default-steer background-helper test client was not created");
-      await within("connect default-steer test client", 15_000, client.connect());
-      await within(
-        "subscribe default-steer test client",
-        15_000,
-        client.fetchAgents({ subscribe: {} }),
-      );
-      const agent = await within(
-        "create default-steer test agent",
-        30_000,
-        client.createAgent({
-          cwd: cwd ?? process.cwd(),
-          title: "claude-default-steer-background-helper",
-          ...getRealProviderConfig("claude"),
-        }),
-      );
-      resources.collector = createMessageCollector(client);
-
-      await within(
-        "launch the background helper and start the main session's own foreground sleep",
-        30_000,
-        client.sendAgentMessage(
-          agent.id,
-          [
-            "Use the Agent tool exactly once with run_in_background: true.",
-            "subagent_type: general-purpose.",
-            `description: "bg survivor b".`,
-            `prompt: "Use the Bash tool in the foreground to run exactly:`,
-            `python3 -c 'import time; time.sleep(42)'. After it finishes, reply exactly: CHILD_DONE."`,
-            "Do not wait for that background helper to finish before continuing.",
-            "After launching it, use the Bash tool one more time yourself, WITHOUT run_in_background,",
-            "to run exactly: python3 -c 'import time; time.sleep(16)'.",
-            // Matching the proven pattern from the first test in this file: tell Claude to wait
-            // for a later message rather than relying on the sleep call itself to block, since a
-            // Bash call can resolve through Claude Code's own async task_notification path once a
-            // background subagent is already active instead of blocking the turn.
-            "Do not reply or finish your turn until a later user message arrives, no matter how",
-            "quickly that Bash command finishes. When that later message arrives, address it and",
-            "end your turn. Do not call any other tools.",
-          ].join(" "),
-          { messageId: generateClientMessageId() },
-        ),
-      );
-
-      // Confirm the daemon considers main's own turn active before steering it. This does not
-      // wait for a specific "sleep 16" shell call to show as running: Claude Code 2.1.280 can
-      // report a slower Bash call through its own async task_notification tool instead of a
-      // classic blocking call once a background subagent is already active, so pinning to a
-      // literal running shell tool_call is not reliable here. Busy at the daemon level is what
-      // "while main is busy with its own sleep" actually needs.
-      await within(
-        "confirm main's own turn is active before steering",
-        30_000,
-        client.waitForAgentUpsert(agent.id, (snapshot) => snapshot.status === "running", 25_000),
-      );
-      // The running status precedes the Agent tool call, so a steer sent on it alone can reach
-      // Claude before the helper exists and prove nothing about a helper surviving it.
-      await within(
-        "confirm the background helper is registered before steering",
-        60_000,
-        waitForProviderSubagentToExist(client, agent.id, 55_000),
-      );
-
-      await within(
-        "send the app's default steer while main is busy with its own sleep",
-        30_000,
-        client.sendMessage(agent.id, "Reply with exactly PONG.", {
-          messageId: generateClientMessageId(),
-          activeTurnBehavior: "steer",
-        }),
-      );
-
-      const finish = await within(
-        "wait for the main session to finish after the steer",
-        120_000,
-        client.waitForFinish(agent.id, 110_000),
-      );
-      expect(finish.status, "the main session must end idle after the steer").toBe("idle");
-      // Pulled via fetchAgentTimeline, not the push collector: see fetchAssistantTexts.
-      const postSteerTexts = await within(
-        "fetch timeline for the post-steer PONG reply",
-        15_000,
-        fetchAssistantTexts(client, agent.id, 20),
-      );
-      expect(postSteerTexts.join("\n"), "PONG must be answered after the steer").toContain("PONG");
-
-      const { subagent, history } = await within(
-        "wait for the background helper to finish",
-        90_000,
-        waitForProviderSubagentTerminal(client, agent.id, 80_000),
-      );
-      expect(subagent.status, "the helper must complete, not be canceled or fail").toBe(
-        "completed",
-      );
-      expect(
-        history,
-        `no provider subagent status poll may ever read canceled; history=${JSON.stringify(history)}`,
-      ).not.toContain("canceled");
-      const subagentTexts = await fetchSubagentAssistantTexts(client, agent.id, subagent.id);
-      expect(
-        subagentTexts.join("\n"),
-        "the helper's own transcript must contain its final CHILD_DONE reply",
-      ).toContain("CHILD_DONE");
-    } finally {
-      const cleanup = await Promise.allSettled([
-        Promise.resolve(resources.collector?.unsubscribe()),
-        resources.client?.close() ?? Promise.resolve(),
-        resources.daemon?.close() ?? Promise.resolve(),
-      ]);
-      if (resources.cwd) rmSync(resources.cwd, { recursive: true, force: true });
-      const failures = cleanup.flatMap((result) =>
-        result.status === "rejected" ? [result.reason] : [],
-      );
-      expect(failures, "default-steer background-helper E2E cleanup failures").toEqual([]);
-    }
-  }, 300_000);
-
-  test("Stop cancels the main session's own turn but spares its background helper", async () => {
-    const logger = pino({ level: "silent" });
-    const resources: SteeringResources = {
-      cwd: tmpCwd(),
-      daemon: null,
-      client: null,
-      collector: null,
-    };
-    try {
-      resources.daemon = await createTestPaseoDaemon({
-        agentClients: { claude: new ClaudeAgentClient({ logger }) },
-        logger,
-      });
-      resources.client = new DaemonClient({ url: `ws://127.0.0.1:${resources.daemon.port}/ws` });
-      const { client, cwd } = resources;
-      if (!client) throw new Error("Stop-spares-helper test client was not created");
-      await within("connect Stop-spares-helper test client", 15_000, client.connect());
-      await within(
-        "subscribe Stop-spares-helper test client",
-        15_000,
-        client.fetchAgents({ subscribe: {} }),
-      );
-      const agent = await within(
-        "create Stop-spares-helper test agent",
-        30_000,
-        client.createAgent({
-          cwd: cwd ?? process.cwd(),
-          title: "claude-stop-spares-helper",
-          ...getRealProviderConfig("claude"),
-        }),
-      );
-      resources.collector = createMessageCollector(client);
-
-      await within(
-        "launch the background helper and start the main session's own foreground sleep",
-        30_000,
-        client.sendAgentMessage(
-          agent.id,
-          [
-            "Use the Agent tool exactly once with run_in_background: true.",
-            "subagent_type: general-purpose.",
-            `description: "bg survivor c".`,
-            `prompt: "Use the Bash tool in the foreground to run exactly:`,
-            `python3 -c 'import time; time.sleep(43)'. After it finishes, reply exactly: CHILD_DONE."`,
-            "Do not wait for that background helper to finish before continuing.",
-            "After launching it, use the Bash tool one more time yourself, WITHOUT run_in_background,",
-            "to run exactly: python3 -c 'import time; time.sleep(23)'.",
-            "Do not call any other tools.",
-          ].join(" "),
-          { messageId: generateClientMessageId() },
-        ),
-      );
-
-      // Confirm the helper has actually been launched (registered) before Stop, not just that
-      // main's turn shows "running": that status can flip true on generic turn-start bookkeeping
-      // before Claude has issued the Agent tool call, and canceling that early cancels a turn
-      // with no helper to spare yet.
-      await within(
-        "confirm the background helper is registered before Stop",
-        60_000,
-        waitForProviderSubagentToExist(client, agent.id, 55_000),
-      );
-
-      const messagesBeforeStop = resources.collector.messages.length;
-      await within("Stop the main session's own turn", 30_000, client.cancelAgent(agent.id));
-      const afterStop = await within(
-        "wait for the agent to go idle after Stop",
-        60_000,
-        client.waitForFinish(agent.id, 50_000),
-      );
-      expect(afterStop.status, "Stop must leave the agent idle").toBe("idle");
-
-      // The helper must survive Stop: it keeps running and later reports CHILD_DONE, which
-      // wakes the main session with a fresh autonomous turn.
-      const { subagent, history } = await within(
-        "wait for the background helper to finish after Stop",
-        90_000,
-        waitForProviderSubagentTerminal(client, agent.id, 80_000),
-      );
-      expect(subagent.status, "Stop must not cancel or fail the background helper").toBe(
-        "completed",
-      );
-      expect(
-        history,
-        `no provider subagent status poll may ever read canceled; history=${JSON.stringify(history)}`,
-      ).not.toContain("canceled");
-      const subagentTexts = await fetchSubagentAssistantTexts(client, agent.id, subagent.id);
-      expect(
-        subagentTexts.join("\n"),
-        "the helper's own transcript must contain its final CHILD_DONE reply",
-      ).toContain("CHILD_DONE");
-
-      const wokeMainAgent = await waitForWakeTurn(
-        resources.collector,
-        agent.id,
-        messagesBeforeStop,
-      );
-      expect(
-        wokeMainAgent,
-        "the helper's completion after Stop must wake the main session with a new turn",
-      ).toBe(true);
-
-      expect(await waitForAgentStatus(client, agent.id, "idle"), "the agent must end idle").toBe(
-        "idle",
-      );
-    } finally {
-      const cleanup = await Promise.allSettled([
-        Promise.resolve(resources.collector?.unsubscribe()),
-        resources.client?.close() ?? Promise.resolve(),
-        resources.daemon?.close() ?? Promise.resolve(),
-      ]);
-      if (resources.cwd) rmSync(resources.cwd, { recursive: true, force: true });
-      const failures = cleanup.flatMap((result) =>
-        result.status === "rejected" ? [result.reason] : [],
-      );
-      expect(failures, "Stop-spares-helper E2E cleanup failures").toEqual([]);
-    }
-  }, 300_000);
 });
@@ -114,34 +114,21 @@ test("keeps the directory's ranking window when searching", async ({ page }) =>
 });

 test("searches for a term typed before the page finished loading", async ({ page }) => {
-  const loadScripts = await holdScripts(page);
+  let loadScripts!: () => void;
+  const scriptsHeld = new Promise<void>((resolve) => (loadScripts = resolve));
+  await page.route(/\.js($|\?)/, async (route) => {
+    await scriptsHeld;
+    await route.continue();
+  });
  await page.goto("/plugins?window=month", { waitUntil: "domcontentloaded" });
  await searchPlugins(page, "graphite");
-  await loadScripts();
+  loadScripts();
+  await page.waitForLoadState("load");
  await expect(page.getByRole("button", { name: "Clear search" })).toBeVisible();
  await page.keyboard.press("Enter");
  await expect(page).toHaveURL(/\/plugins\/all\?q=graphite&window=month$/);
 });

-test("filters browse results for a term typed before the page finished loading", async ({
-  page,
-}) => {
-  await page.goto("/");
-  const loadScripts = await holdScripts(page);
-  await page.goto("/plugins/all", { waitUntil: "domcontentloaded" });
-  const entries = await historyLength(page);
-  await searchPlugins(page, "gra");
-  await loadScripts();
-  await expect(page).toHaveURL(/\/plugins\/all\?q=gra$/);
-  await expect(page.getByRole("heading", { level: 1, name: /^Results for “gra”/ })).toBeVisible();
-  await expect(page.getByRole("link", { name: /Dracula/ })).toHaveCount(0);
-  expect(await historyLength(page)).toBe(entries + 1);
-
-  await page.goBack();
-  await expect(page).toHaveURL(/\/plugins\/all$/);
-  await expect(page.getByRole("heading", { level: 1, name: /^All plugins/ })).toBeVisible();
-});
-
 test("clears the search with the clear button", async ({ page }) => {
  await page.goto("/plugins/all");
  const searchbox = page.getByRole("searchbox", { name: "Search plugins" });
@@ -333,20 +320,6 @@ test.describe("search engine visits without JavaScript", () => {
  });
 });

-/** Holds the page's scripts so typing lands before hydration; the returned function loads them. */
-async function holdScripts(page: Page): Promise<() => Promise<void>> {
-  let release!: () => void;
-  const held = new Promise<void>((resolve) => (release = resolve));
-  await page.route(/\.js($|\?)/, async (route) => {
-    await held;
-    await route.continue();
-  });
-  return async () => {
-    release();
-    await page.waitForLoadState("load");
-  };
-}
-
 async function searchPlugins(page: Page, term: string) {
  await page.getByRole("searchbox", { name: "Search plugins" }).fill(term);
 }
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/website",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "private": true,
  "type": "module",
  "scripts": {
@@ -46,12 +46,6 @@ export function PluginSearch({
    },
    [live, show, term],
  );
-  // A term typed before the page hydrated is in the box but not in state; adopt it. Once hydrated,
-  // the box always matches state, so this does nothing.
-  useEffect(() => {
-    const typed = input.current?.value ?? "";
-    if (typed !== term) edit(typed);
-  }, [edit, term]);
  const handleChange = useCallback(
    (event: ChangeEvent<HTMLInputElement>) => edit(event.target.value),
    [edit],
@@ -1,6 +1,6 @@
 {
  "name": "@getpaseo/builtin-plugins",
-  "version": "0.11.0",
+  "version": "0.11.0-beta.5",
  "private": true,
  "type": "module",
  "scripts": {
@@ -141,7 +141,7 @@ Daemon logging uses separate console and file sinks by default:

 - Console: `info` and above
 - File (`$PASEO_HOME/daemon.log`): `trace` and above
- File rotation: `10m` max file size, `3` rotated files kept alongside the active file
+- File rotation: `10m` max file size, `2` retained files total (active + 1 rotated)

 ```json
 {
@@ -155,7 +155,7 @@ Daemon logging uses separate console and file sinks by default:
      "path": "daemon.log",
      "rotate": {
        "maxSize": "10m",
-        "maxFiles": 3
+        "maxFiles": 2
      }
    }
  }
@@ -71,7 +71,6 @@ The image runs the daemon and serves the bundled web UI. It does not bundle agen

 ## Where next

- [Run parallel tasks](/docs/parallel-development), use separate worktrees, review diffs, and test changes in the desktop app.
 - [Connectivity](/docs/connectivity), connect through the relay or Tailscale.
 - [Docker](/docs/docker), run the daemon and bundled web UI in a container.
 - [Workspaces](/docs/workspaces), the project, workspace, and session model Paseo is built around.
@@ -10,8 +10,6 @@ category: Orchestration

 Paseo lets your coding agents coordinate other agents, split work across providers and machines, and keep tasks moving automatically.

-You can also start and supervise each task yourself in the desktop app. [Run parallel tasks in separate worktrees](/docs/parallel-development), inspect their diffs, and test each app in a terminal and browser before choosing what to merge.
-
 ## What your agents can do

 - **Choose providers and models:** launch other agents using any provider and model configured on the host.
@@ -1,52 +0,0 @@
---
-title: Run parallel tasks
-description: Run coding agents in separate worktrees, review their diffs, and test each change with terminals and the built-in browser in Paseo.
-nav: Run parallel tasks
-order: 12
-category: Workspaces
---
-
-# Run parallel tasks
-
-Use Paseo's desktop app to give several coding agents independent tasks, review their changes, and run the results. Each task gets a workspace with its own git worktree and branch, with agents, files, diffs, terminals, and browser tabs together.
-
-Start with the [desktop app](/docs#desktop-app-recommended), a local git repository, and at least one [coding agent installed and authenticated](/docs/supported-providers). The examples below use a repository with an `origin/main` branch.
-
-## Start two tasks
-
-1. Open **New workspace** and select your project.
-2. Set **Isolation** to **New worktree** and choose `origin/main` as the starting ref.
-3. Choose an agent and model, then submit a task, for example: “Add filtering to the project list. Run the relevant tests.”
-4. Create a second workspace with **New worktree** from the same starting ref. Give its agent another task: “Add keyboard navigation to the settings page. Run the relevant tests.”
-
-Both agents run concurrently. Select either workspace in the sidebar to read progress or send a follow-up. Choose the same provider for both tasks or a different provider for each.
-
-Separate worktrees keep their file edits on separate branches. For two alternative implementations of the same feature, give both agents the same task and compare their results before choosing one.
-
-## Review each change
-
-Select a workspace and open **Changes** from the Command Center to inspect its diff. Open **Files** to browse and edit the source. Use split panes to keep the agent conversation beside the code you're reviewing.
-
-Send corrections to that workspace's agent. To get another opinion, use **New agent** in the same workspace and ask it to review the changes without editing files. Agents in the same workspace share its working directory.
-
-## Run and test the app
-
-In the selected workspace, use **New terminal** from the Command Center. Install dependencies and run your project's test or development command there.
-
-Each worktree has its own files, but processes still share the machine's network ports. Assign a different dev-server port to each running copy. For repeatable setup and service ports, configure [worktree setup and scripts](/docs/worktrees#paseojson).
-
-For a web app, use **New browser** and enter that workspace's dev-server URL. Exercise the changed flow, then switch workspaces to test the other implementation. Browser tabs run inside the desktop app.
-
-You can also ask the agent to check the app in those tabs. Enable [browser automation](/docs/browser#enabling), then give it the URL and concrete steps to verify, for example:
-
-> Open http://localhost:3001, filter the project list by name, and verify that clearing the filter restores the full list. Report any failures and take a screenshot of the result.
-
-## Choose what to merge
-
-Review the diff and test results for each workspace. Ask for any remaining changes before committing and opening a pull request for that branch, using your usual Git workflow in the workspace terminal or through its agent.
-
-For independent tasks, review and merge each branch. For competing implementations, choose the version you want to keep. Archive a workspace when you no longer need it; [worktree cleanup](/docs/worktrees#manage-the-workspace) removes the managed directory after its last workspace is archived.
-
-## Let an agent coordinate the tasks
-
-When you want an agent to create the workspaces, launch workers, and collect their results, use [orchestration](/docs/orchestration). The workers appear in Paseo so you can inspect their conversations and changes as they work.
@@ -8,9 +8,7 @@ category: Providers

 # Providers

-Paseo runs **existing coding agents you've installed and authenticated** in workspaces with an editor, terminals, diffs, and, on desktop, a browser. Run several agents in parallel, choose a provider for each task, and review their work in the same app. Your subscriptions, config, skills, and MCP servers stay intact.
-
-To try the workflow, [run parallel tasks in separate worktrees](/docs/parallel-development).
+Paseo doesn't ship its own coding agent. It launches and supervises **existing CLIs you've already installed and authenticated**, Claude Code, Codex, OpenCode, Antigravity, Muse Code, Cursor, Gemini, and the rest. Your subscriptions, your config, your skills, your MCP servers all stay intact. Paseo just gives you a UI, a CLI, a relay, and orchestration on top.

 ## Mental model

@@ -197,7 +197,7 @@ If you don't want to manage a reverse proxy or open ports, a tunnel gives you an
 - **Tailscale Serve** keeps it inside your tailnet, no public exposure, TLS handled for you:

  ```bash
-  tailscale serve --bg http://127.0.0.1:6767
+  tailscale serve https / http://127.0.0.1:6767
  ```

  Reach it at `https://<your-machine>.<tailnet>.ts.net/`. Only devices on your tailnet can connect.
@@ -48,8 +48,6 @@ The workspace is the product concept; a git worktree is one way to isolate its f

 ## Creating a workspace

-For a desktop walkthrough from starting parallel agents to reviewing and testing their changes, see [Run parallel tasks](/docs/parallel-development).
-
 You can create a workspace in the app or from the CLI:

 ```bash