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>
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
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
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 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
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
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
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
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>
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>
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
Add recoverGhostReviewTasks as a final-fallback scan in the maintenance
loop. Catches any in-review task that fell through every more-specific
recovery scan and has been idle past taskStuckTimeoutMs, kicks it back
to todo with transient status cleared. Worktree state is intentionally
ignored — the executor recreates as needed. Preserves human-handoff and
active-merge statuses; rate-limited naturally by updatedAt refresh.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replace bare `feat(FN-XXXX): merge fusion/fn-XXXX` subjects with an
AI-generated summary describing what landed (e.g. `feat(FN-XXXX): add
webhook handler`). Calls the existing `summarizeCommitSubject` lane
alongside the body summarizer; falls back to `merge <branch>` when the
summarizer is disabled, unavailable, or returns nothing.
Default for `useAiMergeCommitSummary` flips to true so existing
projects without an explicit override pick up the new behavior. The
Settings UI already exposes the toggle.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
RoutineStore's constructor appends ".fusion" to its rootDir argument,
but InProcessRuntime was passing taskStore.getFusionDir() (already the
.fusion path), producing <projectRoot>/.fusion/.fusion/fusion.db. Pass
the project root instead, matching AutomationStore's construction.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The `as const` annotation narrowed column to "in-progress" only, breaking
tsc build when the moveTask mock assigned "todo".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Each agent now gets its own .fusion/agents/<id>/HEARTBEAT.md procedure
file instead of sharing a single project-wide file. A one-shot
migration in AgentStore.init() re-points existing agents off the legacy
shared path and copies the legacy file's contents into each agent's
new per-agent location so operator edits are preserved.
The HeartbeatTriggerScheduler now phase-aligns the first tick to
lastHeartbeatAt + intervalMs so a process restart resumes each agent's
existing schedule rather than waiting up to a full interval before
firing again. Overdue ticks fire promptly within a small jitter window
to avoid a thundering herd at boot.
Also fixes three pre-existing QuickChatFAB test failures introduced by
ad4db8243: auto-select default model now switches to model mode whether
or not agents are present, the model tag only renders in model mode,
and one test scopes its option lookup to role="option" to disambiguate
the in-header tag from the dropdown entry.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The merge commit message was built from `commitLog`/`diffStat` computed
against `merge-base(branch, main)`. Under squash-merge workflows, when an
earlier task is squash-merged onto main first, branches that forked off
the pre-squash main no longer share ancestry with it — `merge-base`
resolves to a point before the earlier task, and the message describes
work already merged via the prior squash. FN-2952's commit body claimed
11 files / 557 insertions when the actual diff was 2 files / 55 lines.
Subject was also a generic `merge <branch>` regardless of content.
- packages/engine/src/merger.ts: new `computeActualMergeCommitContext`
helper that derives commitLog/diffStat from the actual integration
delta (`git diff --cached <integrationTarget> --stat`), filtering
branch commits by patch-id against the target's recent history to
drop already-squashed siblings. Wired into both commit-finalization
sites (`commitOrAmendMergeWithFixes` uses `preAttemptHeadSha`; the
final amend in `runMergeAttempt` uses `HEAD~1`). Agent-context use of
the wide range is unchanged.
- packages/engine/src/merger.ts: `buildDeterministicMergeMessage` now
generates subject and body in parallel via `Promise.all`. Subject is
composed as `feat(taskId): <ai summary>`, capped at 72 chars, with
fallback to the legacy `merge <branch>` form on any AI failure.
- packages/core/src/ai-summarize.ts: new `summarizeCommitSubject` and
`sanitizeCommitSubject` mirroring the body summarizer's structure.
Same title-summarizer lane, 15s timeout. Sanitizer strips quotes,
bullets, re-added conventional-commit prefixes, and trailing periods;
hard-caps at 60 chars.
- packages/core/src/__tests__/ai-summarize.test.ts: 9 tests covering
the sanitizer's behavior.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Enforce unavailable-node routing policy in the scheduler and wire policy integration through engine startup
- Expand scheduler and node-routing policy test coverage for unavailable-node handling and policy integration behavior
- Hoist the Active Agents panel above the main agents list and display next-heartbeat ETA details
- Fix Active Agents panel UI issues by resolving stuck "Connecting..." cards and adding spacing adjustments
- Add changesets covering Active Agents panel hoist/heartbeat ETA and connecting-state fixes
Fusion-Task-Id: FN-2951
The periodic maintenance job `recover-mergeable-review` was silently merging
in-review tasks regardless of `autoMerge` and `mergeStrategy` settings,
defeating the PR-based review flow for users with `autoMerge: false` and
`mergeStrategy: "pull-request"`.
Gate the sweep on `settings.autoMerge` (and globalPause/enginePaused for
consistency with other merge entry points) and route through the engine's
merge queue via the existing `enqueueMerge` callback so `mergeStrategy ===
"pull-request"` is honored. Falls back to the direct `store.mergeTask` path
only when no enqueue callback is wired (standalone/tests).
Closes https://github.com/Runfusion/Fusion/issues/21
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Replace placeholder /remote/qr SVG (URL drawn as text) with real QR
rendered via the qrcode package; add format=terminal returning ASCII
QR for the TUI.
* Resolve the public tailscale funnel URL from captured CLI output
instead of constructing http://<hostname>:<port> from a configured
hostname label — that label was never used by `tailscale funnel` and
produced a non-public URL in the auth/QR link.
* Drop hostname requirement from engine + UI; only target port matters.
* Tighten tailscale parseReadiness to require a URL on the matched line
so the tunnel manager doesn't lock in `running` before the URL line.
* TUI: poll remote status, show ● tunnel indicator + URL in MainHeader,
bind Ctrl+Q to a global QR overlay (terminal ASCII), and switch the
in-Settings K shortcut to render the same ASCII QR.
* Auto-poll remote status in the dashboard while in `starting`/`stopping`
so the UI flips to running without reopening the modal.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
FN-2910 surfaced concurrent reviewer + merger activity on the same task.
Root cause: asymmetric in-flight guards let an unpause-resume kick off a
fresh executor session while a recovery path was already running, and the
auto-merge handoff fired before the executor's finally block finished
cleanup. This sweeps the surrounding lifecycle paths for similar races and
tightens the reviewer pause gate against TOCTOU through runtime setup.
- Symmetric in-flight tracking across `executing`, `recoveringCompleted`,
and `resumingUnpaused`; `recoverCompletedTask` bails when any are set.
- Atomic claim of the recovery slot in the completed-task watchdog before
any awaited work.
- Workflow-rerun bounce returns "bounced" | "skipped-pending" so the
watchdog can no longer log a false-success retry when the original
bounce is still mid-flight.
- Self-healing's completed-task scan re-checks executing IDs inside the
loop instead of trusting a pre-await snapshot.
- 300ms grace period before auto-merge enqueue, giving the executor's
finally block (session disposal, child cleanup) time to drain and
eliminating the residual log-overlap symptom from FN-2910. Test uses
fake timers, no real sleep added.
- New AgentSemaphore.runNested for synchronously nested helper agents
(reviewers): bumps activeCount for honest observability while bypassing
the wait queue, preserving forward-progress fairness for the parent at
low maxConcurrent. Both createReviewStepTool and triage's
createReviewSpecTool now use it.
- New beforeSpawnSession hook on AgentRuntimeOptions/AgentOptions fired
inside createFnAgent immediately before createAgentSession, past every
awaited setup step. Reviewer wires a pause re-check that throws a
sentinel error converted to UNAVAILABLE, closing the TOCTOU window
where pause flipped during runtime resolution or resource loading.
All 2887 engine tests pass; engine + core + cli + dashboard + plugin-sdk
+ pi-claude-cli + desktop typecheck clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
