engine: reviewer subagents previously kept running after the parent task
was moved out of in-progress, paused, or globally paused — they spawn
their own AgentSession outside `activeSessions`/`activeStepExecutors`,
so the existing kill paths never reached them. Track them in a per-task
`activeSubagentSessions` map (mirrored in TriageProcessor) and dispose
on the same triggers as the main session. ReviewOptions gains
`onSessionCreated` / `onSessionEnded` callbacks the executor and triage
processor wire to register/unregister.
droid-cli: probe timeouts (`validateCliPresence`, `validateCliAuth`,
`runDroidProbe`) raised from 5s to 45s — observed cold-start is ~20s,
so 5s reported the binary as missing even when present. Provider gains
a `FIRST_LINE_TIMEOUT_MS` (60s) cold-start guard so a hung droid binary
is reported with an actionable error instead of being indistinguishable
from a slow-thinking turn. Fix the await race in `streamViaCli`: when
SIGKILL destroys stdout mid-buffer, `rl` may never emit "close", so the
promise also resolves on `proc.close` and forces `rl.close()` — prevents
the engine's "executor did not unwind within 60s — hung subprocess".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Plugin runtimes (openclaw, hermes, paperclip) wrap external CLIs and may not
propagate JS customTools to the underlying agent, so fn_identity could be
unreachable on those runtimes. Embedding the agent's identity (role, soul,
instructions, memory previews) directly in every execution prompt guarantees
the agent always sees what loaded for the tick — fn_identity remains as an
optional richer read for runtimes that do support custom tools.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merges the FN-2997 research CLI feature (275-line `research` command with routing, error handling, and docs), a droid CLI provider card for onboarding, a consolidated mock helpers module shared across CLI/dashboard/engine, the SSE architecture reference documentation, and the droid CLI probe module
Fusion-Task-Id: FN-2997
Adds a new Droid CLI provider card to the onboarding flow, including a dedicated provider icon, simplified card CSS, and token fallback fixes for droid provider authentication. The changes wire the card into the ModelOnboardingModal and add test coverage for the card component, icon, and onboarding
Fusion-Task-Id: FN-2980
The merge consolidates mock helpers across packages by creating a new shared `mockCoreEngine.ts` in the CLI package and strengthening the core/engine helpers, then migrating both CLI command tests and the dashboard's `AgentsView` tests to use the canonical helpers. It also publishes SSE architecture
Fusion-Task-Id: FN-3053
Published a canonical SSE architecture reference, with a major rewrite of the real-time dashboard documentation and a new contributing guideline for SSE patterns (FN-3054).
Fusion-Task-Id: FN-3054
The merge introduces a new `droid-cli-probe` module (148 lines) for node diagnostics, adds the corresponding runtime registration routes, and updates the `AgentDetailView` dashboard component to surface probe data. The agent heartbeat system is expanded with enhanced logging (agent-logger +125 lines
Fusion-Task-Id: FN-3052
Added a new `droid-cli-probe` module to the dashboard package with test coverage, implementing a CLI probe capability for the droid system.
Fusion-Task-Id: FN-2979
This merge introduces a new `packages/droid-cli` package that bridges AI agent execution as a subprocess, including process management, event streaming, tool mapping, MCP configuration, and thinking-mode support. It also adds the `DroidCliProviderCard` dashboard UI component with onboarding flows an
Fusion-Task-Id: FN-2978
The merge strengthens task recovery logic to prevent in-review tasks from entering merge-recovery loops and preserves failed review tasks during retry sweeps instead of incorrectly resetting them. It adds targeted test coverage for these edge cases in the self-healing and project engine modules.
Fusion-Task-Id: FN-3050
This merge implements a recoverable pending-login auth flow (FN-3047) across three phases: cancellable in-progress auth routes in the API, an extended auth client contract, and updated ModelOnboardingModal/SettingsModal UI with proper cancel-button visibility during logout. It also adds `dashboard-r
Fusion-Task-Id: FN-3047
Adds a new `dashboard-realtime.md` documentation file covering the SSE lifecycle and scoping behavior, plus minor cross-references in the README and architecture docs.
Fusion-Task-Id: FN-3048
This merge introduces canonical mock helper modules across the dashboard and engine packages, and migrates representative test suites to use them for consistency. The changes add four new mock helpers (`mockApi.ts`, `mockLucide.ts`, `mockCore.ts`, `mockCoreEngine.ts`) and harden the API mock proxy's
Fusion-Task-Id: FN-3044
Research settings sections in the SettingsModal are now gated behind the feature flag, with docs updated to document the gating behavior. Tests cover both desktop and mobile settings views for the new gating logic.
Fusion-Task-Id: FN-3045
Completes Step 2 of FN-3042 by scaling board typography styles across TaskCard and QuickEntryBox components, adding a new CustomModelDropdown stylesheet, and introducing keyboard focus-visible styles for theme selector controls. The merge includes new regression tests for board font scaling, resolve
Fusion-Task-Id: FN-3042
- Replace implicit theme swatch rendering with explicit sample definitions in the custom model dropdown styling
- Add ThemeSelectorSwatchContract regression tests to lock the swatch contract and prevent visual drift
- Restore workspace lint/typecheck gate behavior in onboarding-related settings flows
- Document the explicit swatch sample contract in dashboard README and related onboarding prompt/context updates
Fusion-Task-Id: FN-3043
The mobile QuickChat panel was unusable on iOS Safari: the input bar
rendered off-screen, the soft keyboard often did not open on FAB tap,
the panel slid up out of view on the second input focus, and the
header pill overflowed when the model name was long.
- The FAB JSX no longer emits inline right/bottom styles on mobile,
and the mobile media query pins every edge with !important so the
panel cannot be dragged off-screen by the desktop draggable hook.
- Body scroll is locked while the panel is open via overflow:hidden
on <html> and <body>, and the document is reset to scroll 0 on
open. This prevents iOS from leaking residual scroll into the
fixed-positioned panel between opens.
- An always-mounted, offscreen stealth input claims the iOS soft
keyboard inside the FAB click gesture (the real composer input is
initially `disabled` waiting for the chat session, and iOS will
not open the keyboard for a disabled input). Focus is transferred
synchronously to the real input once it becomes enabled.
- The composer input intercepts touchstart on mobile and re-focuses
with `preventScroll: true`, suppressing iOS's default focus-and-
scroll behavior that was shifting visualViewport.offsetTop and
sliding the panel up off-screen on a refocus.
- A useLayoutEffect mirrors visualViewport.height onto the panel as
--vv-height directly via the DOM, bypassing React state to avoid
the per-event reconciliation lag that read as visual jank during
the keyboard slide-in. On blur, the variable is cleared and a
short suppress window (~450ms) prevents iOS's mid-dismiss reports
from clobbering the regrowth, so the panel snaps back to full
height immediately while the keyboard finishes sliding down on
top of it.
- The model-tag pill in the header collapses to the provider icon
when the tag would otherwise exceed ~12 characters on mobile.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Previously the mobile terminal header used flex-wrap to stack tabs and
the action cluster on separate rows. The actions now stay pinned to the
right edge of the header row while the tab bar flexes to fill remaining
width and remains horizontally scrollable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add backend onboarding session service and legacy API routes for start, state, and import/export generation
- Introduce experimental AgentOnboardingModal UI with stream-state handling, model selector wiring, and onboarding launch flow in AgentsView
- Add onboarding gating via prompt overrides/store updates and include search behavior fix for partial-match filtering
- Expand dashboard/core tests for onboarding API, modal behavior, agents/settings integration, and prompt override handling
Fusion-Task-Id: FN-3025
- useTasks debounced effect bailed when searchQuery transitioned back to
undefined (App passes `searchQuery || undefined`), so clearing the
input never refetched the unfiltered list. Track previous value via
ref and only skip the initial mount.
- FTS5 search used bare tokens (exact term match), so "frob" did not
match "frobnicator". Append `*` to each token (and to quoted tokens)
for prefix matching. LIKE fallback already did substring matching.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This merge brings multiple substantial features: new research extension tools wired through the AI engine (with full test coverage and documentation), legacy routines agentId backward compatibility with migration paths, migration of experimental remote settings to the global scope, Nerd Font glyph a
Fusion-Task-Id: FN-2996
Merges FN-3009 (remote settings migrated to global scope with updated schema and docs), FN-3034 (legacy routines compatibility layer: agentId backfill on load and schema validation for old format), and FN-3039 (Nerd Font glyph asset bundled into the terminal with CSS prioritization). Core settings s
Fusion-Task-Id: FN-3034
This merge migrates Fusion's settings architecture to a unified global scope (FN-3009), consolidating settings types, defaults, merge semantics, updater logic, and routing into a centralized system that aligns dashboard remote settings with global configuration. Secondary changes include adding the
Fusion-Task-Id: FN-3009
Merges two features: FN-3039 bundles a 2.5MB Nerd Font glyph asset into the dashboard and updates the terminal to prioritize the bundled font, improving icon rendering across environments; FN-3035 tightens insight tool type definitions and adds corresponding tests. The CLI extension gains new tools
Fusion-Task-Id: FN-3039
This merge adds an AgentLogViewer component, improves the NewAgentDialog and QuickChatFAB with mobile keyboard awareness and custom model dropdowns, and introduces insight tools in the CLI extension with tightened typing and comprehensive test coverage. The theme system receives enhancements in `use
Fusion-Task-Id: FN-3041
Fixes the insight tool filter typing in the CLI extension to use stricter types, preventing incorrect filter values from being passed through.
Fusion-Task-Id: FN-3035
This merge adds research settings to the settings modal and dashboard (FN-2839, FN-3029), implements a dashboard font scale setting with persistence and documentation (FN-3027), refactors AgentDetailView with a new AgentLogViewer CSS module (FN-2839), and improves NewAgentDialog with custom model dr
Fusion-Task-Id: FN-3027
This merge brings several enhancements across the dashboard and engine. Research settings are now fully integrated into the settings modal and exported for alias builds, including a new schema and dedicated resolver. The AgentDetailView receives a heartbeat markdown viewer modal and expanded styling
Fusion-Task-Id: FN-3029
This merge adds a new **Research Settings** section to the settings modal and dashboard (ResearchView), including a new schema, types, and resolver exported for dashboard alias builds, along with comprehensive tests and documentation updates. It also makes task review step fields editable in the Tas
Fusion-Task-Id: FN-3031
Adds `focus-visible` styling to action buttons in the AgentLogViewer component, improving keyboard accessibility for interactive button elements.
Fusion-Task-Id: FN-3037
This merge introduces a research settings system including new resolver functions in `@fusion/core`, a dedicated ResearchView in the dashboard with a full SettingsModal integration, and corresponding TypeScript types and schemas. Comprehensive unit tests cover routing resolution, research settings,
Fusion-Task-Id: FN-2839
Exports the research settings resolver from `@fusion/core` types to fix dashboard alias builds, ensuring the resolver is available when imported through the dashboard's module alias configuration.
Fusion-Task-Id: FN-2995
Adds a heartbeat markdown viewer modal to the AgentDetailView (FN-3030) with styling, tests, and documentation for the feature, while also rendering multi-sample theme swatches in the ThemeSelector component (FN-3028).
Fusion-Task-Id: FN-3030
ThemeSelector now renders multi-sample theme swatches with richer styling; tests were updated to match and the swatch contract is documented in the dashboard README.
Fusion-Task-Id: FN-3028
The vitest child-process guard wrapped exec/execFile without preserving the
`[util.promisify.custom]` symbol, so awaited `execAsync` resolved to a raw
stdout string instead of `{stdout, stderr}`. That single regression cascaded
through ~60 "failing" tests across cli, core, engine, and dashboard whose
production code was actually correct. Also relax the AI-CLI blocklist for
cheap introspection (--version/--help/which …), give SIGTERM'd subprocesses a
brief grace period before being flagged as "left running", fix a few real
test-side bugs uncovered along the way (executor mock step transitions, iOS
last-resort keyboard path, mission SSE replay tests racing with the real AI
agent), and convert dashboard route tests' dynamic `await import("../server.js")`
to static imports so first-test timings drop from 2–5s to <200ms.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds Nerd Font as the terminal font stack default with a migration to update existing user settings, updates the terminal and settings modals to reflect the new font choice, and includes corresponding tests plus a patch changeset for `@runfusion/fusion`.
Fusion-Task-Id: FN-3026
Workflow-step REVISE retries, pause→todo handoffs, and the
context-overflow fresh-session requeue were all routing tasks back to
`todo` before returning to `in-progress`. The default reopen-to-todo
path reset every step to pending and rewrote PROMPT.md checkboxes, so
each retry restarted from step 0 even when earlier steps had already
been done — the symptom seen on FN-2978, where every workflow REVISE
or pause cycle wiped the task's progress.
- Add `preserveResumeState` to `TaskStore.moveTask`. When set, skip
`resetAllStepsToPending` + `resetPromptCheckboxes` and keep
`worktree` and `executionStartedAt` so the resumed run reattaches to
the same checkout. `status`, `error`, and `blockedBy` still clear.
- Use it on the workflow-rerun bounce, the three pause-graceful
handoffs, and the context-overflow requeue. The agent-terminated
pause path still discards (it nukes worktree+branch by design).
- Context-overflow requeue clears `sessionFile` synchronously in the
awaited `updateTask` immediately before `moveTask`, so the next
dispatch cannot reopen the saturated session via a stale pointer.
- `fn_task_update` no longer silently regresses `done`/`skipped` steps
to `in-progress`, no longer captures a stale rewind checkpoint when
it does, and tells the agent honestly when a regression is ignored.
- Mobile chat keyboard: ChatView/QuickChatFAB gate layout on the new
`keyboardOpen` flag so focused-input + viewport-shrink iOS cases
still adjust when the computed overlap is zero.
Tests:
- New `preserveResumeState` coverage in store.test.ts; updated
workflow-rerun + pause-graceful assertions in executor.test.ts.
- Restructured the previously-flaky "routes exhausted prompt-mode
workflow hard failures" test to drive the bounce inline; passes in
isolation and in the wider workflow/pause/context sweep (59/59).
- Added regression tests in ChatView.test.tsx and QuickChatFAB.test.tsx
for the iOS last-resort `keyboardOpen=true, keyboardOverlap=0` case.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three coordinated fixes for the FN-2978 incident class — auto-requeues
that orphaned committed work and watchdog kills on long verification runs.
**Auto-requeue branch reuse** (executor.ts, worktree-pool.ts)
- executor.ts:1782 now uses `task.branch || fusion/<id>` so persisted
branches are honored on requeue. Previously the hardcoded fallback
always tried to re-create the original branch, hit a conflict with
the prior run's ref, and got suffix -2/-3. Other call sites already
honor task.branch — this aligns the worktree-acquisition path.
- worktree-pool.ts:181 prepareForTask now probes existing branches with
`git rev-parse --verify` and checks them out as-is. Falls through to
suffixed creation only when the branch is genuinely in use by another
live worktree. Previously force-reset with `checkout -B`, destroying
prior commits.
- New private reconcileStepsFromGitHistory walks `git log
baseCommitSha..HEAD` for `feat(FN-X): complete Step N` commits and
marks matching steps[] as done so resumes don't redo committed work.
**Manual reset endpoint + UI** (dashboard)
- POST /api/tasks/:id/reset (requires `confirm: true`) — clears worktree,
branch, all retry counters, resets steps[] to pending, moves to todo.
Distinct from /retry which is the soft-resume path.
- Reset button alongside Retry in TaskDetailModal with confirm dialog,
wired through useTasks → AppModals → API.
**fn_run_verification tool** (run-verification-tool.ts, executor.ts)
- New custom tool wrapping test/lint/build commands with a heartbeat
callback (per-line + 60s synthetic), 200KB head+tail output cap, hard
timeout with SIGTERM→SIGKILL escalation, and auto-bootstrap detection
for missing node_modules. Prevents the inactivity watchdog from
killing sessions during long compiles.
- Cross-platform via `shell: true` (Node picks /bin/sh on POSIX,
cmd.exe on Windows). Prompt section in EXECUTOR_SYSTEM_PROMPT and
EXECUTOR_PROMPT_TEXT instructs agents to prefer package-scoped
verification first and reserve workspace-scoped runs for final
integration.
**Tests** (64 passing)
- detect-pseudo-pause.test.ts (27 tests) — covers all 7 regex patterns,
structural fallback, FN-2978 regression text.
- reconcile-step-regex.test.ts (25 tests) — pins the commit-message
regex against a wide variant set.
- run-verification-command.test.ts (12 tests) — basic execution, output
capture, heartbeat callbacks, timeout, error handling. POSIX-specific
cases (multi-cmd `;`, `>&2`, `\$USER`) gated behind itPosix.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds vitest coverage for validateCliPresenceAsync and validateCliAuthAsync,
verifying success paths, spawn-error paths, non-zero exit codes, and that
auth failures emit the expected warning. Pairs with the async/memoized
validation refactor in f7df0d4e3 that unblocks the dashboard event loop
on every chat send.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Agents sometimes end turns by asking permission instead of calling tools.
Add turn-ending rules to both executor prompts and runtime detection via
detectPseudoPause() to identify these stalls and issue targeted retry
prompts that correct the behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The merge hardens the cloudflared installation backend with fallback logic and architecture detection, updates the SettingsModal UI with clearer manual installation guidance, and adds comprehensive test coverage for the remote access routes including the new memory-based settings registration flow.
Fusion-Task-Id: FN-2977
Merges external Tailscale funnel detection (FN-2976) — adds types, detection logic, status inclusion, kill flow, and a dedicated UI panel for funnel processes started outside Fusion — alongside custom AI providers API routes and a new settings UI section (FN-2965).
Fusion-Task-Id: FN-2976
Merged v0.9.4 bringing custom AI providers to the dashboard — SettingsModal now surfaces provider configuration with an onboarding disclosure flow, backed by new API routes (`/custom-providers`) and comprehensive test coverage. The engine adds self-healing with a ghost-review fallback recovery path,
Fusion-Task-Id: FN-2965
The merge adds an inline version refresh control to the Settings modal with improved touch targets for better mobile usability, replacing a separate duplicate-updates check button. Changes span the SettingsModal component, its CSS styling, and new test coverage for the control behavior.
Fusion-Task-Id: FN-2974
