The mission interview route passed modelProvider/modelId from the request
body directly without resolving the configured default model from settings.
When "Use default" was selected, both values were undefined, causing
createFnAgent to use pi's internal fallback instead of the user's
configured default (e.g. zai/glm-5.1). This produced "AI returned no
valid JSON" errors.
Use resolvePlanningSettingsModel() to resolve the effective model from
the settings hierarchy (planning-specific → project → global defaults),
with explicit request overrides still taking precedence.
Closes#48
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
When a permanent agent has allowParallelExecution=false, TaskExecutor.execute()
defers if the agent has an active heartbeat run, and HeartbeatScheduler defers
a heartbeat if the agent's bound task has an active executor session. Each side
re-dispatches the other's deferred work on completion via resumeTaskForAgent
and the in-process runtime's onRunCompleted hook.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The CLI proxy already had a remove() trap, but the engine's
createFusionAuthStorage was missing it. Without this trap, calling
remove() on a provider would delete the credential from storage but
not add it to loggedOutProviders, allowing fallback credentials to
resurrect the provider on the next read.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reorder logout/set/remove traps so in-memory loggedOutProviders is only
updated after the underlying storage write succeeds. If target.logout()
or target.set() throws, the tombstone set now stays consistent with the
actual storage state.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The list() trap now applies a final filter against loggedOutProviders,
matching the defensive approach used in the CLI layer. While target.logout()
removes entries from underlying storage, this prevents any edge case where
a logged-out provider could appear in list() results.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- get() now returns undefined for logged-out providers instead of
delegating to target.get() which could bypass the guard
- getCredential() in provider-auth returns undefined for logged-out
providers instead of falling through to authStorage.get()
- getAll() skips logged-out providers at top of loop
- list() filters modelsJsonApiKeys against loggedOutProviders
- Added remove() trap in provider-auth for clearApiKey flow
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The logout flow had two bugs causing credentials to reappear immediately:
1. The codebase has two separate auth storage Proxy chains:
- createFusionAuthStorage (engine, for agents)
- mergeAuthStorageReads (CLI, for dashboard UI)
Neither had a logout trap, so supplemental credentials from
~/.claude/.credentials.json were never excluded after logout.
2. The upstream AuthStorage.hasAuth() checks environment variables
(ANTHROPIC_API_KEY), which always returns true regardless of logout.
Fix: Add loggedOutProviders tracking to both Proxy chains. All query
traps (has, hasAuth, get, getAll, list, getApiKey) return false/undefined
for logged-out providers instead of delegating to the underlying storage.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When rootDir is the developer's primary checkout, the merger stashes
uncommitted edits before its hard resets and applies them back at the
end. Previously a pop conflict logged a single warning and silently
left the stash in place — a subsequent merge would push another
autostash on top, burying the first. Recent FN-3299 work was lost this
way and surfaced two side-by-side fusion-merger-autostash entries in
the local stash list.
Three changes:
- AI auto-resolve on apply conflict. The new
runAiAgentForAutostashConflict spawns the same createResolvedAgentSession
path as the in-merge fix-agent, instructs it to clear conflict markers
in place without committing, and verifies markers are gone post-run.
On verified success the stash is dropped; on any failure or remaining
markers the stash is left intact for manual recovery.
- Outcome surfaced via new MergeResult.autostash (AutostashOutcome)
field so dashboard / CLI / daemon can show developers whether their
work was reapplied cleanly, AI-resolved, or needs manual recovery.
- Deterministic stash identity. Replaced `git stash push` + label-grep
(which races against concurrent stashing tools) with `git stash create`
+ `git stash store`, capturing SHA atomically with snapshot creation
and using it for apply / drop. Untracked files captured via `git add
-A` before create; cleanup via `git reset --hard` + `git clean -fd`.
Also surfaces orphaned `fusion-merger-autostash:*` entries from prior
runs at merge entry, so they can no longer be silently buried.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Hermes / OpenClaw / Paperclip runtime cards in Settings now lazily
register themselves on first Save instead of failing with `Plugin
"fusion-plugin-...-runtime" not found`. The CLI also bundles each
runtime plugin (with @fusion/plugin-sdk inlined via esbuild) into
dist/plugins/<id>/bundled.js so npm/npx-installed Fusion can load them
without the workspace SDK dependency.
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>
Two related leaks in the agent lifecycle plus a refactor:
- Governance-skip paths in executeHeartbeat (budget/global-pause/engine-paused)
were leaving agents permanently stuck in `running` because they ran startRun
first and then short-circuited with skipStateTransition: true. Removed the
flag from those four paths so they flow through running → active. Added
HeartbeatMonitor.reconcileOrphanedRunningAgents() on start to recover any
rows already trapped in this state.
- Ephemeral task-workers piled up across runtime restarts because taskAgentMap
was in-memory only and the startup sweep ignored ephemerals with no taskId.
Now: spawn dedup via findAgentByName before create, on-disk fallback in
finalize when the in-memory map is empty, and the sweep deletes any
ephemeral not bound to an in-progress task.
- Extracted the lifecycle into EphemeralWorkerManager
(packages/engine/src/ephemeral-worker-manager.ts). InProcessRuntime drops
~140 lines and delegates via onTaskStart/onTaskComplete/onTaskError/
attachStateChangeListener/reconcileOrphaned. ChildProcessRuntime and
RemoteNodeRuntime inherit the fix because they delegate execution to a
worker that runs InProcessRuntime.
Durable assigned agents now return to `active` after task completion (was
`terminated` in the old contract).
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
- Clarify task memory scope behavior across core types, project memory logic, engine tool prompts, and related docs
- Add regression coverage for memory scope and runtime plugin alias handling in core/dashboard/engine tests
- Add agent avatar API routes and dashboard UI support for avatar display and storage documentation
- Add line-number gutter toggle support in FileEditor and Files modal with accompanying component tests
- Include changeset for @runfusion/fusion documenting memory scope guidance update
Fusion-Task-Id: FN-3485
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
Adds a regression test for runtime plugin alias functionality (FN-3298 Step 3), covering 25 lines of test coverage for this feature.
Fusion-Task-Id: FN-3298
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
Up/Down arrows now cycle the focused panel on the Main page (mirroring
Left/Right), except on the Logs panel where they keep their existing
role of navigating log entries. Expanding a log entry with Enter now
also disables xterm mouse reporting so the user can click-drag to
select the message text; closing the expanded view restores wheel
scrolling.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
node-pty was previously only present transitively via the workspace
@fusion/dashboard devDependency, which is stripped at publish time. Fresh
users running `npx runfusion.ai` hit a 503 "PTY module could not be loaded"
when opening the dashboard terminal. Tightened the package-config guard so
this regression is caught next time.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Patch process.emitWarning in the shared vitest setup to drop the
"SQLite is an experimental feature" notice; align the test mock for
getQrPayload with the canonical RemoteQrPayload signature.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Raise checkForChanges slow-poll warn threshold from 100ms to 750ms so
warnings only fire when cycles approach the 1s poll interval, and route
skill-resolver info diagnostics through log() instead of warn().
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Documents the race called out in code review: when recovery samples a
stale run id and a fresh run is spawned for the same agent before
endHeartbeatRun() lands, only the sampled id is terminated — never the
freshly-spawned run.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the dashboard crashes mid-heartbeat, the agentRuns row is left in
status='active' forever. HeartbeatTriggerScheduler.onTimerTick treats
any active run as "still running" and skips every subsequent tick, so
agents go silent indefinitely (observed: 6+ hours). The existing
in-memory missed-heartbeat watchdog can't help — its trackedAgents map
is wiped on process restart.
SelfHealingManager.recoverStaleHeartbeatRuns now reconciles these on
startup and during periodic maintenance: terminates active runs whose
processPid does not match the current process, has no recorded pid, or
has been active for more than 6 hours.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The MissionLoop calls this.missionStore.listMissions() during startup
recovery, but the mock TaskStore's getMissionStore() return value didn't
include this method. When the runtime startup sequence raced ahead, it
would hit "listMissions is not a function" — making the test flaky.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
Merged four commits implementing comment-driven retriage: triage rules now respond to specific comment patterns (Step 1) and surface needs-replan feedback inputs in the UI (Step 2), with documentation for the new behavior and a bug fix restoring workspace typecheck defaults. Changes span the core ta
Fusion-Task-Id: FN-3502
