A budget-aborted keep-alive subagent's job row (job id == agent id) settles
failed and is retained ~5 min; executeCancel short-circuited to
already_completed for that window, leaving the zombie registration
unkillable exactly when the user wants it dead. Fall through to
cancelAgentRegistration for settled rows; keep already_completed when no
lingering registration exists.
Also stop wiring AgentLifecycleManager.global() onto SDK sessions created
with a caller-supplied agentRegistry: the global lifecycle releases through
AgentRegistry.global(), so it would report a cancel while releasing an
unrelated global ref. Without a lifecycle, cancel falls back to
dispose + unregister on the session's own registry.
Addresses both Codex P2 review findings on #6319.
A keep-alive subagent force-stopped for exceeding its soft request budget
is kept resumable (status idle, adopted by AgentLifecycleManager) so its
context can be salvaged, but its async job row settles and is reaped after
~5 min. After that, hub cancel <id> only reported "Background job not
found" because executeCancel consulted AsyncJobManager alone, leaving the
registration unkillable short of a broker restart.
hub cancel now falls through to the agent registration when no live job
matches: for a sub the caller spawned, it aborts any in-flight turn,
disposes the session, and releases it from the lifecycle. Cross-agent
kills stay impossible and Main/advisor refs are never targeted.
Fixes#6315
The model-facing start content reported when a process exited before readiness,
but launchRenderResult rebuilt the interactive result solely from structured
details and dropped that explanation. Mirror the terminal-without-readyAt
condition in the TUI start renderer and add a renderer contract test.
Fixes#6303
hub start and for:"ready" waits polled the live daemon state, so a process
that flipped starting→ready→exited within one 50ms poll interval was only
ever observed as "exited" and the wait blocked for the full readiness
timeout — despite #markReady durably recording readyAt. A pre-ready exit
had the same failure since terminal states only woke the wait during broker
shutdown.
Wake both waits on readyAt !== undefined || terminalState(state); readyTimedOut
= !ready then falls out. The start renderer reports "Process exited before
readiness was observed." for a pre-ready exit. Adds two regression tests that
hang to their caps on the old code.
Fixes#6303
clampTimeout resolved the per-tool default (bash 300s) whenever the agent
omitted `timeout` and only enforced the tool's own min/max, so the
tools.maxTimeout global ceiling — applied solely in sdk.ts on explicitly
numeric args — was bypassed on the common default-fallback path.
Thread maxTimeout into clampTimeout so the resolved effective timeout,
including the default path, is capped before the per-tool floor/ceiling
apply. Explicit values below the cap still win; maxTimeout <= 0 stays
no-cap. Applied at every call site (bash, eval, browser, debug, lsp,
fetch, and the session-level bash executor), and the bash clamp notice
now names the global ceiling when it is the binding limit.
Fixes#6294
- Exempted the handler-less conflict:// scheme from the URI-like guard so parseConflictUri still splices registered blocks.
- Extended the near-miss regression to assert conflict://1 reaches the resolver.
Fixes#6123
- Blocked malformed and unregistered URI-like paths before filesystem resolution.
- Suggested canonical xd:// spelling while preserving explicitly escaped local paths.
- Added regression coverage for xdt://, xd:/, and xd/ near misses.
Fixes#6123
Native combinators (AbortSignal.any, fetch) brand-check internal slots
that a Proxy cannot forward; return signals unwrapped from
bindBrowserRunFacade so tab.signal composes with native cancellation.
- Removed the once wrapper from Puppeteer's request emitter on first fire so it cannot leak into later runs.
- Added regression coverage asserting a fired once handler leaves zero residual request listeners.
Fixes#6004
- Removed run-scoped Puppeteer request handlers and disabled interception on every browser.run exit path.
- Recycled workers when bounded interception cleanup cannot restore the tab, with raw CDP recovery for held requests.
- Added live Chromium coverage for held requests, normal traffic restoration, and thrown setup calls.
Fixes#6004
- Added bare `eN`/`@eN` regex to `parseAriaRefSelector` so agents can copy refs straight from snapshot output.
- Applied ref resolution to `press`, `screenshot`, `drag`, `select`, and `uploadFile` action handlers.
- Fixed `#select` to assign the full option set first then read back, avoiding double-counting when unselecting mid-loop.
Resolved tool interruptibility from each call's raw arguments so mixed-operation tools can keep side-effecting calls non-interruptible.
Restricted the unified hub to interrupt passive waits and followed logs while preserving start, send, and lifecycle operation results.
Fixes#5995
Added TCP server transport for vscode-js-debug and recursively handled startDebugging requests, breakpoint synchronization, active child routing, and tree cleanup.
Fixes#5984
web_search is a discoverable built-in, so with tools.xdev defaulting to
true createTools mounted it under xd:// and dropped it from the top-level
toolset. Models that call web_search directly got "Tool web_search not
found" on default configs. Pin it in XDEV_KEEP_TOP_LEVEL so it stays a
direct-callable tool while other discoverable tools keep mounting.
Fixes#5973
- Replaced the losing Bun.sleep with an unrefed timeout cleared in a finally block.
- Added regression coverage that verifies prompt wheel acknowledgements leave no timer behind.
Fixes#5905
- Released tab.scroll after two seconds when a queued wheel event waits on a busy renderer acknowledgement.
- Preserved immediate dispatch failures and added regression coverage for both outcomes.
Fixes#5905
selectCollapsedTodos took the active-overflow branch at active.length >= cap, so exactly cap actives plus trailing pending returned the cap rows with an empty summary — the pending work vanished with no '… N more' indicator.
Use a strict '> cap' guard so equality falls through to the normal branch, which counts every hidden row.
Fixes#5873
The first pass anchored a slice on the active task, which still showed completed rows, kept the active item mid-window, and gave the two views divergent selection logic. Per reviewer, replace it with one shared policy both collapsed views run.
selectCollapsedTodos (todo.ts) omits completed/abandoned, pulls every active task (in_progress or subagent-matched pending) to the head in todo order, fills remaining rows with following pending tasks, and emits '… N more active todos' when active work alone exceeds the cap; it falls back to closed tasks for a settled phase so HUD persistence still renders. renderTreeList gains a trailingSummary primitive so item selection lives in the todo domain. The transient tool result reaches live subagent matches via setActiveTodoDescriptionsProvider, wired from interactive mode's observer registry, so both views share the active set.
Fixes#5873
Selecting an ask toolResult in /tree previously just repositioned the
leaf onto the stale answer without re-running the interactive picker
(issue #5642). navigateTree() now detects an ask toolResult target and
returns { reopenAsk: { toolCallId, questions } } recovered from the
original toolCall's persisted arguments, instead of mutating anything.
The TUI's tree selector re-opens the ask picker via a standalone
AskTool.execute() call (reusing the live tool-execution UI context),
then calls navigateTree() again with { reanswerAskResult } to branch a
*new* sibling toolResult off the same ask toolCall -- the original
answer's branch stays fully reachable. Non-ask toolResults, and ask
toolResults whose original arguments can't be recovered (legacy/
corrupted sessions), keep the existing plain leaf-move behavior.
This implements direction 2 from the issue's maintainer triage
(re-answer as a new sibling branch), not direction 1 (resuming the
agent turn) or direction 3 (docs-only).
Both collapsed todo renderers took fixed edge slices: the tool result kept the tail eight (truncateFrom start) and the HUD kept the head five (base.slice), so a mid-phase in_progress task fell in the omitted middle of both.
Add an anchorIndex option to renderTreeList that slides the collapsed window over the anchored item with two-sided '… N more' summaries, and anchor both call sites on the in_progress task (HUD falls back to the first subagent-matched pending task).
Fixes#5873
can1357