Permanent agents now run heartbeats regardless of bound-task block state.
The prior queued+blockedBy early-exit and its state-tracking machinery are
removed; HEARTBEAT_SYSTEM_PROMPT is rewritten to scope heartbeats to
ambient coordination (messaging, memory, finding work, delegation,
surfacing/chasing blockers, status). Task body work continues via the
executor path. Ephemeral agents are unchanged.
New allowParallelExecution flag (default true, permanent agents only) on
AgentHeartbeatConfig. When false, heartbeat and executor paths serialize
symmetrically: a heartbeat will not start while the agent's bound task
has an active executor session, and an executor session will not start
while the agent has an active heartbeat run. Either side re-dispatches
the other's deferred work on completion. UI toggle surfaces in the
agent's Heartbeat Settings tab.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a "Tools: On/Off" toggle next to the existing markdown toggle in
AgentLogViewer (used by both agent logs and task agent logs). When tool
output is off, tool/tool_result/tool_error entries are filtered before
grouping so only agent text and thinking render. Both toggles persist
globally across sessions via localStorage (fn-agent-log-markdown,
fn-agent-log-tool-output).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Removes no-op `agents.filter((a) => true)` calls (a leftover from the
terminated AgentState refactor) flagged by eslint and updates affected
tests and fixtures so `terminated` is no longer referenced. Also:
- Deletes the duplicate `state === "paused"` render branch in
AgentListModal list view that produced two "Resume" buttons.
- Updates the AgentDetailView help text to reflect the current
deletable states ("idle or paused").
- Aligns the bundled-plugin-install test with the new auto-load
behavior for already-installed enabled plugins.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the engine boots, if an agent has the new
runMissedHeartbeatOnStartup flag enabled and lastHeartbeatAt is older
than its interval, fire one catch-up heartbeat through the existing
executeHeartbeat path. Default is off, so existing agents are
unchanged. Toggle exposed in the agent's Heartbeat Settings tab.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Only running shows green and error shows red; idle/active/paused share
the neutral gray border and badge across the agent list, board, and
org-chart views.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drops "terminated" from AGENT_STATES. The agent lifecycle now runs through
idle | active | running | paused | error. paused (carrying a pauseReason)
absorbs every former terminated use case — manual stop, heartbeat run
termination, spawned-child cleanup. Run status (agentRuns.status) is
unchanged: "terminated" stays a valid run-status value.
AGENT_VALID_TRANSITIONS allows direct any→idle transitions so resetAgent
no longer needs the intermediate hop.
Stack-wide:
- core/agent-store: lastError clearing + resetAgent simplified.
- engine/agent-heartbeat, executor, in-process-runtime: terminated state
writes → paused; halt-state listener fires on paused/error.
- dashboard: AgentsView/AgentListModal/AgentDetailView lose the Terminated
badge/option/state-block; agent pickers no longer filter terminated;
agentHealth drops the Terminated branch; routes/state cast widened to
the new AgentState union.
Tests across core and engine updated to assert paused for AgentState and
left "terminated" intact for run-status assertions.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Run Now now optimistically stamps the agent's state to "running" before
the startAgentRun API call so the card reacts immediately. Rolls back on
error, mirroring the handleStateChange pattern.
- Whole .agent-card body is clickable (role=button, Enter/Space, focus ring)
and bails when the click landed on an action button, select, or the
role-icon so those keep their dedicated behaviors.
- Renamed the card's "View Details" button to "Details" and switched
.agent-card-actions to flex-wrap: nowrap so Run Now / Pause / Details
stay on one row regardless of card width.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add AgentErrorDetailsModal and wire agent list/detail views to open full error diagnostics while keeping inline errors compact
- Add line-number gutter toggle in FileEditor and Files modal with dashboard persistence coverage
- Align project memory scope guidance across core logic, CLI tool docs, and dashboard docs
- Add regression coverage for runtime plugin alias behavior and update related engine/heartbeat tests
- Include changesets for FN-3530 UI improvements and FN-3485 memory guidance updates
Fusion-Task-Id: FN-3530
This merge adds a line-number toggle to the Files modal with persisted preference, introduces an AgentAvatar component with server-side avatar storage routes, and adds documentation for both the toggle and avatar storage. It also includes a regression test for runtime plugin alias behavior and updat
Fusion-Task-Id: FN-3528
Six new tests covering the three bugs fixed in the previous commit:
- Retry limit: stops showing toasts after 3 consecutive failures,
resets counter on success
- Skip flag: startFreshSession sets/clears skipNextSessionInitRef,
creates new session even when existing one exists
- Ref stability: switchSession reads activeSession from ref so it
correctly detects "same session" and skips re-initialization
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three interacting bugs caused "Failed to initialize chat" toast spam and
prevented fresh session creation:
1. Race condition in handleCreateFreshSession — setting chatMode/
selectedAgentId before startFreshSession triggered the session-init
useEffect, which called switchSession and resumed the old session
instead of creating a new one. Fixed with skipNextSessionInitRef.
2. Infinite retry loop — shouldRetrySessionInit retried indefinitely
when initializeSession failed, producing unbounded toast spam.
Fixed with a 3-retry cap (initRetryCountRef).
3. Cascading re-renders — switchSession depended on activeSession in
its closure, getting a new identity on every state change and
re-triggering the consumer's useEffect. Fixed by reading
activeSession from a ref instead.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When the local fn/fusion CLI is on the wrong version, the banner now
says "Update the Fusion CLI", shows installed vs expected versions,
and labels the action "Update with npm" instead of the generic install
copy.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The test clicked 'Medium' and 'Continue' synchronously without waiting
for the scope question options to fully render. Use findByText/findByRole
to wait for elements to appear before interacting, and add a timeout to
the final waitFor for the second question.
Previously the back button left the dashboard page entirely because
useNavigationHistory was only enabled for mobile viewports. Now it's
enabled for all viewports — desktop and mobile — so the browser back
button dismisses modals and reverts view changes within the SPA.
Changes:
- Enable useNavigationHistory for desktop (enabled: true instead of enabled: isMobile)
- Remove all isMobile ? historyAwareHandler : plainHandler ternaries
- Always use navigation-aware handlers (openDetailTask, openSettingsWithNav, etc.)
- Update JSDoc to reflect desktop support
The merge completes FN-3498 across three steps: adds ownership-aware done-task reconciliation to the merger, prevents branch-missing head SHA pollution during merge operations, and restores workspace typecheck compatibility. Core changes touch the merger (103 lines) and self-healing module (67 lines
Fusion-Task-Id: FN-3498
Merges FN-3470 in two steps: first, runtime plugins now prefer source path aliases over build artifacts, with hardening tests for vitest alias resolution and plugin view registry updates; second, a new `ensure-test-artifacts.mjs` bootstrap script guarantees required test files exist before test runs
Fusion-Task-Id: FN-3470
This merge introduces an eval automation domain store with persistence schema and a plugin dashboard view registry (FN-3512/FN-3513), adds scheduled eval batch architecture documentation (FN-3388), and includes substantial test coverage for Research routes and hooks (FN-3368 steps 1-3). The branch a
Fusion-Task-Id: FN-3368
This merge adds three major features: a new **eval domain store** (`eval-store.ts`, `eval-types.ts`) for AI evaluation data with persistence schema and a `PluginDashboardViewHost` for extensibility; a **plugin dashboard view registry** with navigation integration that lets plugins register custom vi
Fusion-Task-Id: FN-3512
Merged FN-3157 to add a plugin dashboard views system, including a plugin view registry with lazy loading, navigation integration for Header and MobileNavBar, a usePluginDashboardViews hook with cache and refetch support, and tests covering the no-loader path. Also added documentation in `docs/PLUGI
Fusion-Task-Id: FN-3157
The @keyframes spin and .animate-spin rules were incorrectly placed
inside the first :root {} block, which is invalid CSS — @keyframes
cannot be nested inside selector blocks. Browsers silently ignore
them in that position, so the spinners would still get stuck on pages
without component CSS loaded.
Moves the rules to the stylesheet top level between the two :root
blocks. Also fixes the mobile-css regression test that parses the
first :root block with a non-greedy regex.
Addresses review feedback from Greptile (P1) and CodeRabbit on PR #40.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The `.animate-spin` CSS utility class and `@keyframes spin` were only
defined in TaskCard.css but used by 25+ components (~60 instances).
On pages without a TaskCard rendered, the class didn't exist in the
stylesheet, causing all spinners to appear frozen.
Moves both the keyframes and utility class to the global styles.css
so they're available from the first paint regardless of which
components are loaded.
ClosesRunfusion/Fusion#39
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Merges fixes for the planning refine continuation flow (FN-3209) alongside a new local startup script for development environments. The changes include updates to `PlanningModeModal.tsx`, new and updated tests for the planning system, route handler improvements in `chat.ts` and `planning.ts`, and do
Fusion-Task-Id: FN-3209
Backend
- chat.ts now routes both regular chat and QuickChat through
createResolvedAgentSession instead of branching to createFnAgent for
the no-runtime-hint case. This removes the divergent path where
pi-ai's cleanupSessionResources(sessionId) could tear down resources
the next generation depends on.
- sendMessage's finally only disposes the agent if it still owns the
activeGenerations slot. A newer generation that has pre-empted us
cleans up its own agent in its own finally — disposing here would
yank the underlying CLI process out from under it.
- __setCreateFnAgent test helper now mirrors its mock into the
createResolvedAgentSession slot so existing test setups still work
after the unification.
Frontend
- Extract createChatStreamHandlers (RAF coalescing, accumulators,
tool-call dedup, fallback handling) — useChat and useQuickChat were
duplicating ~85 LOC each. Both now compose the shared factory.
- Move shared chat types into chatTypes.ts. The hooks re-export them
for backward compatibility with existing consumers.
- Removed per-message Markdown/plain-text eye toggles. A single
thread-level toggle in the chat header now flips every assistant
bubble (including the streaming one) between rendered Markdown and
plain text.
- Model-only chats hide the per-message agent identity row entirely;
the model name is already in the thread header.
Tests
- Updated ChatView tests to reflect the new render-toggle contract
(single header toggle drives all bubbles) and the model-only avatar
suppression.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two related bugs left the Planning Mode modal stuck at partial height on
mobile. useModalResizePersist replayed desktop-saved pixel dimensions
that overrode the mobile 100dvh rule, and React reconciled removed CSS
custom properties to empty string rather than calling removeProperty(),
which on iOS Safari defeated the var() fallback after keyboard dismiss.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merges the documentation update for FN-3287, adding 2 lines to the dashboard README covering PR link visibility behavior. This completes Step 5 of the task.
Fusion-Task-Id: FN-3287
The merge adds expanded regression assertions for the org chart feature, covering agent CSS classes and mobile agents view components. The tests verify styling and layout behavior across both desktop and mobile contexts.
Fusion-Task-Id: FN-3472
This merge adds done-payload snapshot handling across the chat system (FN-3430), normalizing how final assistant messages are preserved and consumed in the dashboard hooks, plus it normalizes dashboard mailbox and user identity for inter-agent messaging (FN-3484) and introduces plugin workflow step
Fusion-Task-Id: FN-3430
Updates the restart integration test mock to account for plugin template behavior, keeping the test in sync with recent plugin template changes.
Fusion-Task-Id: FN-3096
The merge normalizes button utility classes in AgentsView, swapping 12 lines of CSS class references for their standardized counterparts for consistency and maintainability.
Fusion-Task-Id: FN-3448
This merge introduces autosave for agent and task detail settings in the dashboard (`TaskDetailModal.tsx`, `AgentDetailView.tsx`), adds an agent self-improvement service with heartbeat evaluation logic (`agent-self-improve.ts`, `agent-heartbeat.ts`), and expands agent tools for direct-report managem
Fusion-Task-Id: FN-3382
Adds deterministic split-pane refresh behavior to the Agents views (AgentsView and AgentDetailView), with comprehensive test coverage for the mutation refreshes in the detail pane and the agents hook.
Fusion-Task-Id: FN-3466
Merges two features: the org chart full-view mode (layout, controls, and documentation for FN-3461) and a QMD refresh fix that synchronizes the query memory database after agent dream writes, normalizing agent memory behavior. The AgentsView UI and agent-tools were updated alongside the new memory-b
Fusion-Task-Id: FN-3461
- Adjust llama.cpp provider card markup and CSS to keep compact spacing aligned with list view and workflow styling updates
- Add regression tests for compact llama.cpp card layout behavior in dashboard component tests
- Expand merge error recovery tests in the engine to validate deduped auto-merge retry handling and related project-engine flow changes
- Update architecture/task management docs and include changeset metadata for auto-merge recovery dedup work
Fusion-Task-Id: FN-3431
- Expand architecture documentation for git route and custom provider APIs
- Revise ListView styles to use updated design-token driven spacing and sizing
- Refresh WorkflowResultsTab styling to align with workflow token revisions
Added auto-claim setting UI to the Agent detail view with corresponding documentation in agents.md and test coverage for the new component behavior. The changeset marks this as a minor feature for the published `@runfusion/fusion` package.
Fusion-Task-Id: FN-3250
Merged two commits: relocated the new-task action button in ListView from the leading to trailing edge (FN-3486), and added a theme regression test for WorkflowResultsTab (FN-3462). Changes span ListView component and styles, WorkflowResultsTab CSS refactoring and tests, plus a dev-server-store upda
Fusion-Task-Id: FN-3486
Adds regression coverage for WorkflowResultsTab theme styling by moving a hardcoded box-shadow fallback into the global stylesheet and adding a test that validates the theme-specific status background renders correctly.
Fusion-Task-Id: FN-3462
Merged CSS changes that apply tokenized sizing and focus styles to InsightsView and DesktopModeChooser components, with the majority of changes in InsightsView.css.
Fusion-Task-Id: FN-3471
