- Add eval score category types and exports in core with store support and coverage
- Implement engine evaluator evidence extraction and persistence with dedicated tests
- Update evaluator flow and cron wiring to record evidence alongside eval runs
- Refresh architecture, storage, and eval docs for evidence and categorization behavior
Fusion-Task-Id: FN-3391
This merge implements FN-3603, adding jump-to-latest controls for the chat view and improving mobile bubble width layout, with corresponding CSS updates in ChatView and QuickChatFAB components. It also includes documentation for the new mobile chat controls, a fix for workspace lint regex escaping,
Fusion-Task-Id: FN-3603
Merges five commits implementing centralized runtime skill forwarding that preserves Fusion context across the Hermes runtime layer. The engine's `agent-runtime` and `agent-session-helpers` were updated to forward skills at runtime, with `runtime-adapter.ts` and its types extended to carry context.
Fusion-Task-Id: FN-3612
Merged FN-3597 feature branch adds two-step protection against malformed columns in the board and list views: Step 1 normalizes malformed column data at the core level, and Step 2 hardens the Board and ListView grouping logic to gracefully handle edge cases. The changeset covers test isolation impro
Fusion-Task-Id: FN-3597
Fusion-Task-Id: FN-3607
Two cuts to wasted work in the merge verification loop:
1. After the in-merge fix agent runs, fingerprint the working tree
(`git diff HEAD` + `git status --porcelain`, sha256). If the post-fix
fingerprint matches pre-fix and is non-empty, the agent didn't actually
change anything — re-running the same failing command can only yield
the same failure, so log and report the attempt as unsuccessful without
paying the test/build cost. Empty fingerprints (snapshot tooling failed)
fall through to the existing re-run path so we never silently swallow a
real fix.
2. Inside `syncDependenciesForMerge`, hash the active lockfile and compare
against `node_modules/.fusion-install-marker` (written after each
successful install). When they match, skip `pnpm install
--frozen-lockfile` even if `package.json` is staged. Covers the common
case where `package.json` changes but the lockfile doesn't, and
amortizes install across auto-recovery re-enqueues that hit the same
worktree.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The /_perf/dashboard-load server route no longer exists, so every
reportDashboardPerf() call was a silently-swallowed 404. Remove the helper
in legacy.ts plus its five call sites in App.tsx / useProjects.ts (the
companion console.log lines stay), and drop the dashboard-perf.log entry
from the test-isolation runtime ignore list since nothing writes that file
anymore.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Live fusion instances running on a shared HOME write to tasks/, messages/,
memory-insights.md, test-cache.json, HEARTBEAT.md, kb.db.backup-*, and
fusion.db.pre-* snapshots; none were in the runtime ignore list, so the
script flagged them as test-driven mutations and failed merge build
verification. Recursion in collectFusionSignature only filters via top-level
matches, so adding these top-level patterns short-circuits descent into
live-app dirs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Expand test-changed coverage and shard selection assertions for CI workflows
- Improve vitest worker temp-directory utilities and related core/CLI tests
- Refine test isolation guardrails and runtime ignore handling for live .fusion noise
- Update contributing guidance and root test script usage for the verified workflow
Fusion-Task-Id: FN-3607
This merge introduces eval score categorization with a new `eval-scoring.ts` module (FN-3601, FN-3390), hardened bundled plugin entry resolution to prioritize workspace source over installed copies (FN-3590), and documented reply-link threading behavior in the mailbox (FN-3598). It also adds mobile
Fusion-Task-Id: FN-3590
This merge lands eval score categorization and evaluator hardening in core/engine, mobile mission CTA improvements with documented behavior, reply-link threading documentation, and a test-isolation fix that tolerates runtime noise on shared HOME directories. Dashboard components affected include Mai
Fusion-Task-Id: FN-3601
Exported the eval score category type from `@fusion/core` and added a defensive guard in the evaluator to prevent edge-case failures in the score evaluation switch.
Fusion-Task-Id: FN-3390
Local `pnpm test:isolated` was failing because a concurrently-running
fusion app continually mutates `~/.fusion` (databases, agent sessions,
memory, automations, plugins, logs). Filter those runtime-owned paths
from the protected-dir signature, widen the baseline-stability sampling
window, and re-sample on suspected violations so transient app activity
doesn't masquerade as test pollution.
Tests still cannot legitimately write into these paths — they're skipped
because the *running app* is expected to.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This merge restores the canonical agent lifecycle with termination scoped at the run level (FN-3580, 4 steps), adds sender-side wake recipient override for messages, and introduces test isolation CI enforcement with a stuck-requeue race fix. UI changes remove terminated-agent indicators from AgentDe
Fusion-Task-Id: FN-3580
Documents the live reviewer override behavior in the settings reference and task management guides, adding two lines to each file for a total of 4 lines of documentation.
Fusion-Task-Id: FN-3595
This merge lands five FN-3593 commits establishing a test isolation contract with a new `scripts/check-test-isolation.mjs` guard that scans for accidental `beforeEach`/`afterEach`/`beforeAll`/`afterAll` in setup helpers, plus per-package `setup-test-isolation.ts` bootstraps that canonicalize the pat
Fusion-Task-Id: FN-3593
Senders can now force the recipient agent to wake on receipt regardless
of the recipient's `messageResponseMode`. Surfaced as a "Wake recipient
immediately" checkbox in MessageComposer and as a `wake_recipient`
boolean param on the `fn_send_message` agent tool. Carried as
`metadata.wakeRecipient: true` on the message; the heartbeat hook
treats forced wakes as `message_received_urgent` in the wake delta so
agents can distinguish them from normal `messageResponseMode: immediate`
wakes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When SelfHealingManager.recoverCompletedTasks moved a task from
in-progress to in-review, the executor's stuck-kill cleanup running in
execute()'s finally block could fire 20s later, see a stale captured
task.column = "in-progress", and overwrite the recovery by tearing down
the worktree and moving the task back to todo with all step progress
reset. Both the outer-finally and step-session requeue blocks (and the
force-requeue setTimeout in markStuckAborted) now re-read the latest
column and skip cleanup entirely if the task has moved past
in-progress/todo.
Adds a new preserveProgressOnStuckRequeue setting (default: true,
toggle in Settings near the Stuck Task Timeout) so stuck-requeue passes
{ preserveProgress: true } to moveTask. Completed step statuses now
survive the bounce so the agent resumes from where it left off instead
of restarting every step from pending.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Update AgentErrorDetailsModal styles to improve mobile layout and avoid viewport overflow
- Add mobile regression tests for agent modal behavior in agent-modals-mobile coverage
- Extend core modal mobile test suite with AgentErrorDetailsModal safeguards
Fusion-Task-Id: FN-3587
The merge integrates five commits across the engine and dashboard: it fixes a quick chat icon-tag regression, ensures manual heartbeat runs respond immediately once a run record exists, splits the agents overview label into separate active vs running counts, prevents inbox messages from being auto-m
Fusion-Task-Id: FN-3586
POST /api/agents/:id/runs previously awaited resolvedMonitor.executeHeartbeat
end-to-end before sending the response. For real provider runs that take
tens of seconds to minutes, Safari (and intermediate proxies) drop the
client socket and the dashboard surfaces "Failed to start heartbeat run:
load failed" — the run is actually in flight, but the toast suggests it
failed to start.
The route now kicks off executeHeartbeat in the background, polls briefly
for the active-run record (created synchronously inside executeHeartbeat
→ startRun), and returns 201 with that record. Synchronous failures of
executeHeartbeat are still surfaced to the client; background failures
are logged via runtimeLogger.child("heartbeat"). The 409 active-run
conflict contract is preserved.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Overview dropdown previously rendered "X active · Y running" where
both X (stats.activeCount) and Y (activeAgents.length) counted agents
whose state was either "active" or "running" — so an agent that was
merely enabled but idle would still inflate the "running" tally. The
label now counts each state distinctly so "running" only reflects
agents that are mid-heartbeat. Adds AgentsOverviewBar.test.tsx to lock
in the new contract.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the dashboard user browses another agent's mailbox (e.g. the CEO's
inbox), opening a message no longer triggers POST /messages/:id/read.
The previous behavior silently consumed the agent's unread state, so the
agent's heartbeat never surfaced the message and fn_read_messages (which
defaults to unread_only=true) returned nothing. Auto-mark-read now only
fires on the dashboard user's own inbox tab. Adds regression tests in
MailboxView.test.tsx and MailboxModal.test.tsx.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The InProcessRuntime constructed its AgentStore with only `rootDir`, leaving
task-claim/checkout/release operations unconfigured. As a result, the
heartbeat auto-claim scan logged "TaskStore not configured for task-claim
operations" whenever a relevant todo was found. Pass the runtime's TaskStore
through to the AgentStore so claimTaskForAgent succeeds.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This merge introduces a memory file markdown preview feature (FN-3584) with corresponding documentation, refines the AgentDetailView and AgentLogViewer components in the dashboard, and adds defensive collision handling for worktree operations during manual task moves (FN-3583).
Fusion-Task-Id: FN-3584
The merge lands five commits: a fix (FN-3583) that preserves non-tool message boundaries when tools are hidden in CLI bundles, plus hardened test coverage for that regression and bundle asset bootstrapping; worktree collision prevention on manual task moves via a new `worktree-names.ts` module and s
Fusion-Task-Id: FN-3583
Two related bugs let two in-progress tasks share a single
.worktrees/<name> directory:
1. The dashboard POST /tasks/:id/move route promoted tasks to
in-progress without allocating a fresh worktree path, so a queued
task carrying a stale worktree field from a prior preserveResumeState
requeue could land in-progress on a directory already held by another
active task.
2. moveTask({preserveResumeState:true}) kept the worktree pointer on
requeue. When the on-disk checkout was later removed or reassigned,
the next dispatch collided with a worktree the scheduler had handed
to another task.
moveTask now releases the worktree pointer on every reopen-to-todo hop
(branch is kept so committed progress survives via git worktree add
<path> <branch>). A new preserveWorktree option opts internal bounces
out of the release. moveTask also accepts an allocateWorktree callback
that runs under a new cross-task allocation lock in TaskStore, so two
concurrent moves cannot pick the same name from a stale snapshot. Both
the manual-move route and the scheduler dispatch path flow through the
allocator and share the lock.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Convert the dynamic await import("./agent-session-helpers.js") and
await import("./session-skill-context.js") calls inside the heartbeat
executor to static top-level imports, matching the rationale of
38933c770 (which already made the sibling pi.js import static).
This surfaces ERR_MODULE_NOT_FOUND at engine load time rather than
mid-heartbeat when a worktree is on a branch missing the helpers.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This merge adds a new evaluation framework including signal collection (`eval-signal-collector.ts`), typed evaluation signals (`eval-types.ts`), and an evaluator engine module (`evaluator.ts`) with cron-runner integration for scheduled evaluation. It also establishes plugin contribution type constra
Fusion-Task-Id: FN-3102
Completes typing for the scheduled evaluator integration in the cron runner and project engine, with corresponding test updates in the evaluator test file.
Fusion-Task-Id: FN-3389
This merge adds a canonical in-dialog AI interview flow for agent onboarding (FN-3553), replacing the old wizard with a multi-step dialog that guides users through creating and reviewing agent prompts before spawning, plus tokenized typography fixes. It also introduces native shell connection handof
Fusion-Task-Id: FN-3553
This merge adds a complete plugin management system (FN-3565) with CLI commands, a loader, runner, and dashboard routes, along with project-scoped auth storage (FN-3544), native shell connection support for mobile (FN-3400) spanning onboarding, connection manager, and remote desktop handoff, and ref
Fusion-Task-Id: FN-3400
- Add project auth storage model and persistence wiring in core DB/store/types
- Expand core test coverage for DB migration, store behavior, and project auth store flows
- Update heartbeat agent, settings, dashboard, and storage documentation for the new behavior
- Replace hardcoded mobile touch-target sizing in dependency graph styles with token-based sizing
Fusion-Task-Id: FN-3544
This merge adds a complete plugin management system to Fusion: a new `fn plugin` CLI command for installing/removing plugins, a plugin loader in core, a plugin runner in engine, and dashboard routes for plugin management UI, along with a plugin management guide in docs. It also documents task evalua
Fusion-Task-Id: FN-3565
Merged branch removes the duplicate desktop "Todos" nav entry from the Header, syncs the `allowParallelExecution` runtime toggle into `AgentDetailView`, and updates the corresponding docs (agents.md, settings-reference.md, todo-view.md, dashboard-guide.md) to reflect the navigation change. Tests wer
Fusion-Task-Id: FN-3539
Fixes FN-3567 by synchronizing the `allowParallelExecution` runtime toggle in the AgentDetailView component, adding one line to keep the setting in sync.
Fusion-Task-Id: FN-3567
This merge completes the agent terminated state alignment (FN-3535), adding "running → terminated" transition support with consistent styling and lifecycle controls across the heartbeat engine, agent store, and dashboard UI, plus plugin author documentation improvements (FN-3537) and plugin loader t
Fusion-Task-Id: FN-3535
Merged FN-3566 work that audits local main divergence from origin and reconciles the branch, adding an audit trail document (`FN-3566-STEP1-AUDIT.md`) to track the divergence analysis and safeguards applied during the reconciliation process.
Fusion-Task-Id: FN-3566
Refactored plugin-loader tests and implementation to isolate plugin test contamination, improving test independence in `@fusion/core`.
Fusion-Task-Id: FN-3564
In a narrow resized sidebar the milestones / features / tasks counts ran
off the card edge because .mission-list__item-summary was a non-wrapping
flex row. Switch it to flex-wrap with split row/column gaps so the stats
reflow onto new lines instead of clipping.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Promote the sidebar "Plan New Mission" CTA to a btn-primary (matching the
chat sidebar's "New Chat") and drop the dashed icon buttons; full-width
progress bar and Activity row each get their own line in the card.
- Auto-select the first mission in the inline desktop view so users land
in detail rather than the empty placeholder. Skipped in mobile and the
standalone modal so existing flows and unit tests stay intact.
- Replace the bare "No missions yet" line with a richer empty state that
explains what missions are and offers an inline Plan New Mission CTA.
- Guard loadMissionDetail against malformed responses (missing milestones)
so racing fetch fallbacks don't crash the detail render.
- Update three MissionManager tests to match the new copy/structure.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
TriageProcessor.stop() previously only halted the polling loop, so
in-flight specify sessions and their reviewer subagents kept streaming
past shutdown. Extracted the existing global-pause teardown into
abortAndDisposeActiveSessions() and call it from stop() too.
aiMergeTask creates three sessions during a merge — autostash resolver,
in-merge verification fix agent, and pull-rebase conflict resolver — but
only the autostash one was registered via onSession. The other two are
now registered (with onSession threaded through pushToRemoteAfterMerge
into the rebase resolver chain), so ProjectEngine.stop() actually
disposes whichever merger session is running when shutdown lands.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Import button moved to the AgentsView header; its detail-view test
coverage no longer applies.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Recovers cleanups from stash@{2}/stash@{3} (FN-3530 merger autostashes)
that the merger never restored: 4 dead `[data-state="terminated"]`
selectors in AgentListModal.css, 3 CSS-class assertions in
agent-css-classes.test.ts targeting classes the runtime no longer emits,
and a `state: "terminated"` fixture in routes-agents.test.ts now flipped
to `paused` so the "invalid state transitions" test exercises a real
rejection (paused→paused is not in AGENT_VALID_TRANSITIONS).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
