Fix useChat so already-rendered user/assistant messages no longer flicker away while an agent turn is actively streaming.
- useChat.ts: during an active streaming turn for the current session, treat stale/empty/cross-session loadMessages responses as append-only against the visible thread instead of replacing it, merging any genuinely new same-session messages in and skipping the session-cache write when the active thread is being preserved.
- ChatView.streaming-thread.test.tsx: add coverage asserting the rendered thread stays visible across mid-turn session-update/tool-call/stale-reload churn.
- useChat.test.ts: add hook-level regression tests for the append-only/merge/cache-skip behavior during active streaming.
- docs/architecture.md, docs/dashboard-guide.md: document the append-only mid-turn thread-stability behavior.
- Add changeset (patch) for @runfusion/fusion describing the user-facing fix.
Files changed:
.../fn-7853-chat-mid-turn-message-stability.md | 7 +
docs/architecture.md | 1 +
docs/dashboard-guide.md | 1 +
.../__tests__/ChatView.streaming-thread.test.tsx | 130 +++++++++++++
.../dashboard/app/hooks/__tests__/useChat.test.ts | 208 +++++++++++++++++++++
packages/dashboard/app/hooks/useChat.ts | 35 +++-
6 files changed, 380 insertions(+), 2 deletions(-)
Fusion-Task-Id: FN-7853
Fusion-Task-Lineage: d9909469-082c-4eeb-81fb-b36d1a9e4705
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Session skill merging (collectPluginSkillNames) previously ignored per-project
Skills view enable/disable toggles and only consulted each plugin's static
default, so a user disabling a plugin skill in the Skills view would still see
it merged into live agent sessions. Extracted the effective-enablement
resolver shared by dashboard discovery and engine session assembly into
@fusion/core so both surfaces stay in sync.
- Added packages/core/src/skill-settings.ts with computeSkillId/parseSkillId/
normalizeStoredSkillPath/getSkillSettingState/resolvePluginSkillEnabled,
exported from @fusion/core's index.
- packages/dashboard/src/skills-adapter.ts now re-exports and delegates to the
shared @fusion/core resolver instead of duplicating its own
getSkillSettingState/computeSkillId/parseSkillId implementations.
- packages/engine/src/session-skill-context.ts: collectPluginSkillNames now
accepts a projectRootDir, reads project settings via skill-resolver's newly
exported readProjectSettings/resolveProjectRoot, and calls
resolvePluginSkillEnabled instead of only checking the plugin's static
skill.enabled flag; mergePluginSkills passes projectRootDir through.
- packages/engine/src/skill-resolver.ts: exported readProjectSettings and
ProjectSkillSettings for reuse by session-skill-context.
- Updated docs/plugin-management.md to document that per-project Skills view
toggles now apply to runtime agent sessions, not just discovery.
- Added unit tests for the new core resolver and updated dashboard/engine
tests to cover per-project toggle overrides in session merging.
- Added a patch changeset for @runfusion/fusion.
Files changed:
.changeset/fn-7858-plugin-skill-session-toggle.md | 7 ++
docs/plugin-management.md | 4 +-
packages/core/src/__tests__/skill-settings.test.ts | 62 +++++++++
packages/core/src/index.ts | 8 ++
packages/core/src/skill-settings.ts | 102 +++++++++++++++
.../dashboard/src/__tests__/skills-adapter.test.ts | 60 ++++++++-
packages/dashboard/src/skills-adapter.ts | 107 +++-------------
.../src/__tests__/session-skill-context.test.ts | 140 ++++++++++++++++++++-
packages/engine/src/session-skill-context.ts | 23 +++-
packages/engine/src/skill-resolver.ts | 4 +-
10 files changed, 409 insertions(+), 108 deletions(-)
Fusion-Task-Id: FN-7858
Fusion-Task-Lineage: 90e44d24-e385-4a74-b8e4-3c864ec39a95
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Path-registered plugin reload/restart now refreshes persisted manifest metadata instead of leaving stale version/settingsSchema in the store.
- PluginLoader.loadPlugin/reloadPlugin call a new refreshPersistedManifestMetadata helper after each fresh module import, generalizing the previously bundled-only refresh to path-registered plugins
- Refresh is metadata-only (version, settingsSchema) via a stable-JSON comparison, preserving per-project enablement and saved setting values, and is a no-op when nothing changed
- PluginStore.PluginUpdateInput/updatePlugin gain a settingsSchema field (undefined = unchanged, null = explicitly clear) so updatePlugin can persist manifest schema changes independently of setting values
- Docs: add a "Updating path-registered plugins" section to docs/PLUGIN_AUTHORING.md describing the new reload/refresh loop
- Tests: add coverage in plugin-loader.test.ts and plugin-store.test.ts for manifest metadata refresh on load/reload and settingsSchema persistence
- Add a patch changeset for @runfusion/fusion
Files changed:
.changeset/fn-7855-plugin-manifest-refresh.md | 7 +
docs/PLUGIN_AUTHORING.md | 10 ++
packages/core/src/__tests__/plugin-loader.test.ts | 177 ++++++++++++++++++++++
packages/core/src/__tests__/plugin-store.test.ts | 42 +++++
packages/core/src/plugin-loader.ts | 53 +++++++
packages/core/src/plugin-store.ts | 10 ++
6 files changed, 299 insertions(+)
Fusion-Task-Id: FN-7855
Fusion-Task-Lineage: f4d94023-5a27-4059-a7a5-61f524c171b8
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Issue #2015: product-code executor tasks were repeatedly routed to a
liaison-only agent because every routing path gated only on the coarse
role field, and several binding primitives had no guard at all.
- Add runtimeConfig.assignmentPolicy ("auto" | "explicit-only" | "none");
"none" can never be bound to implementation tasks by ANY path — no
override bypasses it (the liaison guarantee)
- Route every binding surface through one shared evaluator
(evaluateImplementationTaskBind): claimTaskForAgent, the previously
unguarded checkoutTask/assignTask primitives, selectNextTaskForAgent
(including the in-progress re-selection loop), scheduler auto-assign
pool, heartbeat inbox/auto-claim, fn_delegate_task, CLI agent-id
validation, and dashboard assign/checkout/inbox routes
- Lock project isolation with a regression test: a foreign-project
agent id is rejected by every binding primitive
- Expose Assignment Policy in Agent Detail settings; document in
docs/agents.md; add changeset
Fusion-Task-Id: FN-7851
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Replace one-shot grok -p JSON with native grok agent stdio (ACP) for realtime
streaming, tool visibility, and multi-turn sessions. Vendor the ACP client
into fusion-plugin-grok-runtime, forward Fusion fn_* tools and operator MCP,
stage Fusion skills via --plugin-dir, authenticate per xAI headless docs, and
align project chat manager store resolution so Grok chat sessions can send.
Extend the dashboard's Task Documents tab to union each task's registered documents with its task-scoped artifacts, with an inline right-pane viewer for the added artifact types.
- DocumentsView Task Documents tab now merges task documents and task-scoped artifacts per task group, sorted/grouped consistently
- Adds an inline right-pane artifact viewer (image/video/audio/pdf/inline-doc/other) reusing getArtifactCategory + artifactMediaUrl/fetchArtifact
- Selection state is a discriminated document|artifact union kept separate from Project Files selection; the standalone Artifacts gallery tab is unchanged
- Updates dashboard-guide.md to describe the merged Task Documents behavior (grouping, search, and preview now cover both documents and artifacts)
- Adds a minor changeset for @runfusion/fusion documenting the artifact-in-Task-Documents feature
- Expands DocumentsView test coverage for the new union/selection/preview behavior
Files changed:
.changeset/fn-7845-task-documents-artifacts.md | 7 +
docs/dashboard-guide.md | 6 +-
.../dashboard/app/components/DocumentsView.css | 142 +++++++-
.../dashboard/app/components/DocumentsView.tsx | 389 ++++++++++++++++++---
.../components/__tests__/DocumentsView.test.tsx | 290 ++++++++++++++-
5 files changed, 780 insertions(+), 54 deletions(-)
Fusion-Task-Id: FN-7845
Fusion-Task-Lineage: 32bbe6dc-4c02-449c-a13f-38abb8fd727d
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Unifies the two independent durable-agent error-recovery paths (heartbeat timer and self-healing sweep) so they share one retry budget, eligibility check, and audit surface instead of racing separate counters.
- Share the heartbeatErrorRecovery attempt budget between HeartbeatMonitor's timer-entry recovery and SelfHealingManager.recoverOrphanedAgents(), with self-healing's legacy durableErrorRecovery metadata folded into the same counter via readHeartbeatErrorRetryCount().
- Add isHeartbeatErrorRecoverable() as the single transient/non-operator-actionable eligibility check, used by both the heartbeat timer and self-healing paths (self-healing additionally allows stale-worktree module-resolution errors).
- resetHeartbeatErrorRecoveryMetadata() now strips the legacy durableErrorRecovery field so recovered agents don't retain stale sweep bookkeeping.
- Self-healing emits the shared agent:auto-recover-error-state / agent:error-retry-exhausted run-audit events with source:"self-healing", and parks the agent paused with pauseReason:"error-retry-exhausted" on budget exhaustion, matching the heartbeat-timer behavior.
- Update AGENTS.md, docs/architecture.md, and docs/agents.md to describe the consolidated recovery budget and audit surface.
- Add a patch changeset documenting the fix for @runfusion/fusion.
Files changed:
.changeset/fn-7844-error-recovery-coordination.md | 7 ++
AGENTS.md | 2 +-
docs/agents.md | 14 ++--
docs/architecture.md | 2 +-
packages/engine/src/__tests__/heartbeat-error-recovery.test.ts | 13 +++-
packages/engine/src/__tests__/self-healing.test.ts | 58 ++++++++++++++-
packages/engine/src/agent-heartbeat.ts | 35 ++++++---
packages/engine/src/self-healing.ts | 85 ++++++++++++++++++----
8 files changed, 180 insertions(+), 36 deletions(-)
Fusion-Task-Id: FN-7844
Fusion-Task-Lineage: b70dcba5-56b6-412c-8be2-ef827bee9964
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Heartbeat-managed durable agents that land in state:"error" now self-recover on the next heartbeat instead of staying stuck until an operator intervenes.
- HeartbeatTriggerScheduler keeps timers armed for durable heartbeat-managed agents in error state when the last error is transient and not operator-actionable (credential/quota/model-access/permanent-config failures stay parked).
- executeHeartbeat clears recoverable errors at run entry (error → active, clears lastError), bounded by MAX_HEARTBEAT_ERROR_RECOVERY_ATTEMPTS (settings-overridable); a successful run resets the counter.
- On budget exhaustion, the agent is parked paused with pauseReason:"error-retry-exhausted".
- Emits new run-audit events agent:auto-recover-error-state and agent:error-retry-exhausted (added to DatabaseMutationType).
- Adds heartbeat-error-recovery.test.ts and extends heartbeat-scheduler.test.ts to cover the recovery/exhaustion paths.
- Adds changeset and documents the new behavior in AGENTS.md and docs/architecture.md.
Files changed:
.changeset/fn-7835-agent-error-auto-recovery.md | 7 +
AGENTS.md | 1 +
docs/architecture.md | 2 +
.../src/__tests__/heartbeat-error-recovery.test.ts | 323 +++++++++++++++++++++
.../src/__tests__/heartbeat-scheduler.test.ts | 89 +++++-
packages/engine/src/agent-heartbeat.ts | 209 ++++++++++++-
packages/engine/src/run-audit.ts | 2 +
7 files changed, 618 insertions(+), 15 deletions(-)
Fusion-Task-Id: FN-7835
Fusion-Task-Lineage: 1bbb28a3-8eb9-40e3-8177-6658ec5dae40
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds a shared urgency color source to priorityIndicator and wires it into every priority-glyph surface so low/normal/high/urgent read consistently by color, not just icon shape.
- priorityIndicator.tsx: add colorVar (low=info/blue, normal=muted, high=warning/amber, urgent=error/red) and new getPriorityColorVar() export as the single source of truth
- QuickEntryBox: tint the icon-only priority trigger and each option row in the priority picker with the matching urgency color
- TaskForm: tint the New Task inline priority glyph using the same color source
- TaskCard: render a colored priority glyph alongside the existing text label in the card-priority-badge (kept the non-normal visibility gate and badge geometry via a small CSS gap addition)
- Updated/added tests for QuickEntryBox, TaskCard (badge, badge-height, badge-wrap), and priorityIndicator to assert the new colors; added a patch changeset and a dashboard-guide.md doc update
Files changed:
.changeset/fn-7842-priority-color-coding.md | 7 +++++
docs/dashboard-guide.md | 7 +++--
.../dashboard/app/components/QuickEntryBox.tsx | 7 +++--
packages/dashboard/app/components/TaskCard.css | 2 ++
packages/dashboard/app/components/TaskCard.tsx | 6 +++-
packages/dashboard/app/components/TaskForm.tsx | 7 +++--
.../components/__tests__/QuickEntryBox.test.tsx | 17 +++++++++--
.../__tests__/TaskCard.badge-height.test.tsx | 5 ++++
.../__tests__/TaskCard.badge-wrap.test.tsx | 5 ++++
.../app/components/__tests__/TaskCard.test.tsx | 33 +++++++++++++++++++++-
.../app/utils/__tests__/priorityIndicator.test.tsx | 13 +++++----
packages/dashboard/app/utils/priorityIndicator.tsx | 16 ++++++++---
12 files changed, 103 insertions(+), 22 deletions(-)
Fusion-Task-Id: FN-7842
Fusion-Task-Lineage: 0b2d0d15-6e61-45fc-9378-bc09002bef55
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Raises Grok and Droid CLI cold-start timeout defaults from 60s to 120s and lets operators override them via environment variables.
- Grok runtime adapter: new GROK_CLI_FIRST_OUTPUT_TIMEOUT_MS env override for the first-output cold-start guard; default raised 60000ms → 120000ms; invalid/non-positive values fall back to the default
- Droid provider: new PI_DROID_CLI_FIRST_LINE_TIMEOUT_MS env override for the first-line cold-start guard; default raised 60000ms → 120000ms; invalid/non-positive values fall back to the default
- 30-minute inactivity safety net left unchanged on both adapters
- Added/updated unit tests covering the new env-driven timeout resolution and fallback behavior for both plugins
- Documented the new settings in docs/settings-reference.md and both plugin READMEs
- Added a minor changeset for @runfusion/fusion
Files changed:
.changeset/fn-7838-cli-timeout-configurable.md | 7 ++
docs/settings-reference.md | 13 ++-
plugins/fusion-plugin-droid-runtime/README.md | 8 ++
.../src/__tests__/provider.test.ts | 97 +++++++++++++++++++++-
.../fusion-plugin-droid-runtime/src/provider.ts | 26 ++++--
plugins/fusion-plugin-grok-runtime/README.md | 8 ++
.../src/__tests__/runtime-adapter.test.ts | 52 +++++++++++-
.../src/runtime-adapter.ts | 23 ++++-
8 files changed, 222 insertions(+), 12 deletions(-)
Fusion-Task-Id: FN-7838
Fusion-Task-Lineage: 7aad4470-b28f-42bd-be01-8363a1dd05e5
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Gives the Artifacts view's Task Documents sidebar a distinct card-per-task look with more breathing room between task groups, replacing the flat bordered-row list.
- Restyle .documents-task-sidebar-group into a bordered, rounded card with shadow and inter-group gap instead of a bottom-border-only divider
- Strengthen the group header (bolder task id/title, tinted background) so it reads as a container rather than a peer row
- Add hover/selected background treatment and left-indent to .documents-task-document-item entries, scoped under .documents-task-documents-sidebar so Project Files and Artifacts stay unaffected
- Add a regression test asserting group headers remain non-selectable containers distinct from selectable document rows
- Update dashboard-guide.md wording to describe the new distinct task-card grouping
- Add changeset (patch) documenting the sidebar restyle
Files changed:
.changeset/fn-7834-task-documents-grouping.md | 7 +++
docs/dashboard-guide.md | 2 +-
.../dashboard/app/components/DocumentsView.css | 38 +++++++++++++---
.../components/__tests__/DocumentsView.test.tsx | 50 ++++++++++++++++++++++
4 files changed, 90 insertions(+), 7 deletions(-)
Fusion-Task-Id: FN-7834
Fusion-Task-Lineage: 9bac7666-19ba-410b-81dc-d9201a61d0b5
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Reworks the Task Detail terminal experience: the embedded Terminal tab now sits between Comments and Cost, its workspace picker defaults to the task's worktree, and the mobile terminal panel is shorter.
- Move the Terminal tab in Task Detail's tab strip to sit right after Comments and before Cost (previously Cost was earlier and Terminal was near the Session tab)
- TerminalModal now defaults its workspace picker to the useWorkspaces entry whose worktree matches the passed defaultCwd, but only until the operator manually changes the selection; the footer/global terminal still defaults to Project Root since it doesn't pass defaultCwd
- Reduce `.detail-section--worktree-terminal`'s mobile min-height from min(65dvh, 14 * --space-2xl) to min(50dvh, 11 * --space-2xl) so tab context and controls stay reachable above the fold
- Update docs/dashboard-guide.md to describe the new Comments → Terminal → Cost tab order and the worktree-matching picker default
- Add regression tests covering the new tab order and the default terminal workspace selection behavior
- Add a patch changeset describing the user-facing change
Files changed:
.changeset/FN-7832-task-terminal-picker-and-tab-order.md | 7 +++
docs/dashboard-guide.md | 9 +--
packages/dashboard/app/components/TaskDetailModal.css | 5 +-
packages/dashboard/app/components/TaskDetailModal.tsx | 30 +++++-----
packages/dashboard/app/components/TerminalModal.tsx | 19 +++++++
packages/dashboard/app/components/__tests__/TaskDetailModal.attachments-and-tabs.test.tsx | 15 ++---
packages/dashboard/app/components/__tests__/TaskDetailModal.worktree-terminal.test.tsx | 12 ++++
packages/dashboard/app/components/__tests__/TerminalModal.test.tsx | 64 ++++++++++++++++++++++
8 files changed, 134 insertions(+), 27 deletions(-)
Fusion-Task-Id: FN-7832
Fusion-Task-Lineage: 4ee67a65-8564-49c9-b93c-8c3eab05c073
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Relocates the shared terminal action-control cluster into the bottom status-bar footer at every breakpoint and replaces the fixed tablet-viewport tab collapse with a container-width overflow check.
- Move font-size, Clear, Shortcuts, Preferences, connection status, pin, and pop-out controls out of the desktop header into the `.terminal-status-bar` footer at all widths (desktop/tablet/mobile/floating/docked/pinned/embedded), replacing the prior viewport-tier-based split.
- Replace `isTerminalTabletViewport()` with `evaluateTabsOverflow()`, a container-size (ResizeObserver-driven) check with hysteresis that swaps the `.terminal-tabs` strip for the existing mobile-style `.terminal-mobile-tabs` dropdown whenever the tab strip doesn't fit, independent of viewport breakpoint.
- Update TerminalModal.css to match the new footer-first layout and drop now-unused tablet-tier header rules.
- Update dashboard-guide.md terminal usage steps to describe the new always-footer control location and the width-based (not tablet-only) tab dropdown fallback.
- Expand TerminalModal.test.tsx coverage for the overflow-driven tab collapse/expand behavior and footer control placement.
- Add changeset fn-7829-terminal-shortcuts-footer.md (patch, feature) documenting the footer/tab-dropdown change; resolve an add/add conflict on the pre-existing artifacts-doc-editing-and-comment-fix.md changeset by keeping fusion/fn-7829's summary wording.
Files changed:
.../artifacts-doc-editing-and-comment-fix.md | 2 +-
.changeset/fn-7829-terminal-shortcuts-footer.md | 7 +
docs/dashboard-guide.md | 9 +-
.../dashboard/app/components/TerminalModal.css | 121 +++-----
.../dashboard/app/components/TerminalModal.tsx | 336 +++++++++++----------
.../components/__tests__/TerminalModal.test.tsx | 185 ++++++++----
6 files changed, 351 insertions(+), 309 deletions(-)
Fusion-Task-Id: FN-7829
Fusion-Task-Lineage: 443c6e69-8946-4307-8a1a-f4f90681a054
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
- scope session collections to the active project\n- clean up runtime stage registration in discovery tests\n- model brainstorms and plans as repeatable artifact collections\n- compact the singleton Strategy presentation
Terminal WebSocket sessions now retry with capped backoff through cold-start failures instead of giving up and requiring a manual Reconnect click.
- useTerminal tracks whether a socket has ever successfully opened via hasEverConnectedRef
- a never-connected initial connect ignores MAX_RECONNECT_ATTEMPTS and keeps retrying at capped backoff, staying in the reconnecting affordance until it opens
- mid-session drops (sockets that opened at least once) keep the existing bounded give-up behavior, and permanent 4000/4004 closes remain terminal
- context-change invalidation now uses a ref flag (contextChangedSinceLastEffectRef) consumed inside the effect instead of a transient boolean dependency, avoiding cleanup re-runs that tore down the replacement socket during context-switch/reconnect races
- manual reconnect() and context/session changes reset hasEverConnectedRef so cold-start behavior reapplies per session
- added a patch changeset and expanded useTerminal test coverage for first-launch reconnect vs. mid-session disconnect behavior
- documented the first-launch reconnect behavior in docs/dashboard-guide.md
Files changed:
.changeset/FN-7824-terminal-first-launch-autoreconnect.md | 7 +
docs/dashboard-guide.md | 3 +
packages/dashboard/app/hooks/__tests__/useTerminal.test.ts | 208 ++++++++++++++++++++-
packages/dashboard/app/hooks/useTerminal.ts | 34 +++-
4 files changed, 234 insertions(+), 18 deletions(-)
Fusion-Task-Id: FN-7824
Fusion-Task-Lineage: 7ed696d0-449e-4dc0-9be0-48b429b8c844
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Removes the hard divider between the Settings navigation rail and content, keeps section rows single-line with ellipsis overflow, and adds a draggable/keyboard-resizable handle that persists the rail's width in localStorage across the standalone modal and embedded Settings page.
- Add a resize handle (.settings-nav-resize-handle) between .settings-navigation and .settings-content, draggable via pointer events and resizable with ArrowLeft/ArrowRight when focused
- Persist chosen width to localStorage (fusion:settings-nav-width), clamped between 200px and 420px, defaulting to 248px; restore on mount
- Make .settings-navigation the sole owner of rail width via a --settings-nav-width CSS custom property instead of a fixed width, and drop the border-right divider
- Keep nav section labels on one line with white-space: nowrap + text-overflow: ellipsis in both the modal (SettingsModal.css) and embedded (styles.css) nav item styles
- Hide the resize handle on mobile; mobile keeps the stacked section picker unaffected
- Update docs/dashboard-guide.md to describe the new divider-less rail and resize behavior
- Add SettingsModal.navResize.test.tsx covering drag-resize, keyboard-resize, and width persistence
- Add changeset .changeset/fn-7825-settings-nav-resizable.md (minor)
Files changed:
.changeset/fn-7825-settings-nav-resizable.md | 7 +
docs/dashboard-guide.md | 3 +
packages/dashboard/app/components/SettingsModal.css | 56 ++++-
packages/dashboard/app/components/SettingsModal.tsx | 124 +++++++++-
packages/dashboard/app/components/__tests__/SettingsModal.navResize.test.tsx | 268 +++++++++++++++++++++
packages/dashboard/app/styles.css | 27 ++-
6 files changed, 467 insertions(+), 18 deletions(-)
Fusion-Task-Id: FN-7825
Fusion-Task-Lineage: 34b940b4-2698-46a4-b47c-cda0b0cac564
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Removes the single-worktree gate on the Task Detail Terminal tab so it renders for every task, defaulting its first shell to the task worktree when present and otherwise falling back to the project root.
- TaskDetailModal.tsx: showWorktreeTerminalTab is now always true (drops the isWorkspaceTask/single-worktree gate and its stale fallback effect); taskWorktreeCwd still feeds defaultCwd when a worktree is recorded, and the tab renders without requiring taskWorktreeCwd
- Adds a changeset documenting the behavior change (minor, feature) for @runfusion/fusion
- docs/dashboard-guide.md: updates the Terminal tab description to state it is always available, with worktree-or-project-root cwd fallback, including for multi-repo workspace tasks
- Expands TaskDetailModal.worktree-terminal.test.tsx coverage for the no-worktree and workspace-task cases now that the tab is always shown
Files changed:
.changeset/FN-7826-worktree-terminal-always-available.md | 7 +++
docs/dashboard-guide.md | 4 +-
packages/dashboard/app/components/TaskDetailModal.tsx | 12 ++---
.../TaskDetailModal.worktree-terminal.test.tsx | 57 +++++++++++++++++++---
4 files changed, 63 insertions(+), 17 deletions(-)
Fusion-Task-Id: FN-7826
Fusion-Task-Lineage: f87504fe-9330-4392-bdbe-33bba006d96c
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Aligns OAuthExpiryMonitor's ntfy push notifications with the /api/auth/status refresh-then-recheck logic that drives the in-app OAuthReloginBanner, so providers that silently auto-refresh (e.g. GitHub Copilot's ephemeral token) no longer trigger false "OAuth token expired" pushes with no matching banner.
- OAuthExpiryMonitor.check() now performs a best-effort authStorage.getApiKey() refresh and reloads/re-resolves the credential before dispatching oauth-token-expired, instead of relying solely on the stored expiry timestamp
- resolveEffectiveOAuthCredential() now also guards against non-finite expires values in addition to non-numeric ones
- Updated docs/dashboard-guide.md and docs/settings-reference.md to describe the refresh-then-recheck behavior generically (not just Claude/Anthropic) and documented the FN-7821 fix in FNXC provenance comments
- Added regression tests covering the refresh-then-recheck flow in oauth-expiry-monitor.test.ts
- Added a patch changeset describing the fix for release notes
Files changed:
.changeset/fn-7821-oauth-expiry-notification-banner-consistency.md | 7 +
docs/dashboard-guide.md | 6 +-
docs/settings-reference.md | 6 +-
packages/engine/src/notification/__tests__/oauth-expiry-monitor.test.ts | 146 ++++++++++++++++++++-
packages/engine/src/notification/oauth-expiry-monitor.ts | 48 ++++++-
5 files changed, 199 insertions(+), 14 deletions(-)
Fusion-Task-Id: FN-7821
Fusion-Task-Lineage: 5954592c-adda-4fd4-b205-265860eddf3d
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Consolidates Cursor Admin API key resolution onto one documented env var so the usage/admin credential path is reachable and unambiguous, replacing the prior dual CURSOR_ADMIN_API_KEY/CURSOR_API_KEY and multi-provider-id lookup.
- Replace CURSOR_ADMIN_API_KEY (preferred) + CURSOR_API_KEY alias with a single CURSOR_API_KEY env var, mirroring the GROK_API_KEY precedent
- Simplify readCursorApiKey to check CURSOR_API_KEY then fall back to the single "cursor" authStorage entry via readConfiguredApiKey (drop the cursor/cursor-cli/cursor-agent provider-id loop)
- Export readCursorApiKey and fetchCursorUsage for direct test coverage
- Update the no-auth error message and settings-reference.md docs to reference only CURSOR_API_KEY, clarifying cursor-cli OAuth/session auth vs the separate Admin API usage-metering credential
- Add changeset (@runfusion/fusion: minor) documenting the credential-path change
- Add/adjust usage.test.ts coverage for readCursorApiKey precedence (env over authStorage) and the updated credential-absent error message
Files changed:
.changeset/fn-7817-cursor-api-key.md | 7 ++++
docs/settings-reference.md | 8 ++--
packages/dashboard/src/__tests__/usage.test.ts | 53 +++++++++++++++++++++++++-
packages/dashboard/src/usage.ts | 52 ++++++++-----------------
4 files changed, 77 insertions(+), 43 deletions(-)
Fusion-Task-Id: FN-7817
Fusion-Task-Lineage: 86ac3d47-8e80-4159-abee-6c41aae56407
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds a Cursor provider fetcher to the dashboard usage aggregator so operators with a Cursor Admin API key see spend-based usage alongside the other providers.
- usage.ts: add fetchCursorUsage() using the Cursor Admin API POST https://api.cursor.com/teams/spend with Basic auth (API key as username), resolving the key from CURSOR_ADMIN_API_KEY (preferred) or CURSOR_API_KEY, falling back to fusion-auth/pi-configured api keys; maps teamMemberSpend overallSpendCents/spendCents and hardLimitOverrideDollars/monthlyLimitDollars into a "Monthly spend" usage window with a reset derived from subscriptionCycleStart
- usage.ts: wire fetchCursorUsage into fetchAllProviderUsage's parallel provider fetch list (with withTimeout + no-auth demotion) and update the provider-list comment
- UsageIndicator.tsx: map the "Cursor" provider name to the existing cursor-cli icon token/SVG
- usage.test.ts: add CURSOR_ADMIN_API_KEY/CURSOR_API_KEY env stubbing and a full fetchCursorUsage regression suite (ok/zero-utilization/no-auth/error/expired-key/parse-failure cases)
- UsageIndicator.test.tsx: cover the Cursor icon mapping
- docs/settings-reference.md: document that the Usage dropdown Cursor card requires a Cursor Admin API key (session-only cursor-agent login is insufficient)
- add a minor changeset for @runfusion/fusion documenting the new Cursor usage card
Files changed:
.changeset/fn-7816-cursor-usage.md | 7 +
docs/settings-reference.md | 4 +
packages/dashboard/app/components/UsageIndicator.tsx | 7 +
packages/dashboard/app/components/__tests__/UsageIndicator.test.tsx | 26 +++
packages/dashboard/src/__tests__/usage.test.ts | 157 ++++++++++++++
packages/dashboard/src/usage.ts | 240 ++++++++++++++++++++-
6 files changed, 440 insertions(+), 1 deletion(-)
Fusion-Task-Id: FN-7816
Fusion-Task-Lineage: 4cec63d8-4ddc-40f3-8d16-5e4078da5eba
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Lifecycle warnings now recompute client-side from the live graph for
editable workflows, so the banner reflects edits immediately instead of
waiting for a save round-trip. The two deterministically fixable codes gain
one-click fixes in the banner (all view modes):
- missing-merge-region inserts a Merge boundary in front of end;
- missing-completion-summary inserts the canonical completion-summary node
(config from @fusion/core's completionSummaryNode) upstream of the merge
region when one exists, else in front of end.
"Fix all" on the collapsed summary line applies both in order, producing
start → summary → merge → end on a fresh workflow in one click. The other
three codes are structural judgment calls and stay manual.
analyzeWorkflowLifecycle + completionSummaryNode are pure and now re-export
through core's browser-safe types.ts alias entry.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- parseInsightsContent stripped bullet prefixes before filtering for them, so every
insights category rendered as one blob and counts were wrong (5 shown vs 84 real)
- drop dead GET /memory and GET /memory/stats mount fetches from useMemoryData and
stop refetching the file list on every file selection
- Memory view: full-width layout, accent tabs, 2-column Engines card grid, remove
duplicated capability badges, correct spacing-token-as-font-size rules
- Todos: single-row items with quiet inline action cluster (stacked on narrow/mobile)
- Insights: flat card list (no card-in-card), 28px/16px actions muted until hover
- Agent Memory tab: shared FileEditor (CodeMirror) for memory files, per-section save
actions, distinct inline-toggle aria-labels, fix {{date}} i18n interpolation
- PR screenshots under docs/assets/memory-ui-review-2026-07/
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Add an interactive, worktree-rooted, multi-tab Terminal tab to the Task Detail
view, distinct from the pre-existing CLI-agent Session tab.
- TaskDetailModal gains a new embedded Terminal tab (single non-workspace
task with one recorded worktree) that mounts TerminalModal in a new
`embedded` render mode, rooted at the task's worktree
- Rename the existing agent-session tab label to "Session" to disambiguate
it from the new Terminal tab
- useTerminalSessions gains task-scoped session storage and a `defaultCwd`
option so embedded terminal tabs persist separately from footer/global
project terminal tabs and start in the task worktree
- TerminalModal/CSS updated to support the embedded layout mode
- Update lazy-loaded-views docs test and AGENTS.md exclusion list to cover
the new `LazyTerminalModal` task-detail-internal surface
- Document the new Session/Terminal tab split in docs/dashboard-guide.md
- Add i18n strings for the new Terminal tab across all locales
- Add a changeset (minor) for @runfusion/fusion
Files changed:
.changeset/FN-7813-worktree-terminal-tab.md | 7 +
AGENTS.md | 2 +-
docs/dashboard-guide.md | 3 +
.../app/__tests__/lazy-loaded-views-docs.test.ts | 4 +-
.../dashboard/app/components/TaskDetailModal.css | 17 +++
.../dashboard/app/components/TaskDetailModal.tsx | 41 +++++-
.../dashboard/app/components/TerminalModal.css | 51 +++++++
.../dashboard/app/components/TerminalModal.tsx | 71 +++++++---
.../__tests__/TaskDetailModal.test-helpers.ts | 3 +
.../TaskDetailModal.worktree-terminal.test.tsx | 139 ++++++++++++++++++
.../components/__tests__/TerminalModal.test.tsx | 29 ++++
.../hooks/__tests__/useTerminalSessions.test.ts | 157 +++++++++++++++++++++
.../dashboard/app/hooks/useTerminalSessions.ts | 63 ++++++---
packages/i18n/locales/en/app.json | 3 +-
packages/i18n/locales/es/app.json | 3 +-
packages/i18n/locales/fr/app.json | 3 +-
packages/i18n/locales/ko/app.json | 3 +-
packages/i18n/locales/zh-CN/app.json | 3 +-
packages/i18n/locales/zh-TW/app.json | 3 +-
19 files changed, 550 insertions(+), 55 deletions(-)
Fusion-Task-Id: FN-7813
Fusion-Task-Lineage: 4ef86a15-347a-4862-b01c-5063d8004cb8
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds select-to-comment parity to the Task Documents right pane in the Artifacts view, reusing the existing Project Files selection-comment pattern (useSelectionComment/SelectionCommentPopover) so operators can highlight task-document content and send it to a new task.
- Add markdown/plain preview refs and useSelectionComment hooks scoped to the selected Task Document, following the existing Plain/Markdown render toggle
- Gate the Task Documents selection popover on activeTab === "tasks" and the selected task document (separate from the Project Files popover, which stays gated on activeTab === "project") so tab switches never cross-render popovers
- Compose the New Task description source as `taskId/key` for task-document selections, mirroring the file-path convention used for Project Files
- Add regression tests covering plain/markdown task-document selection, empty-pane gating, tab isolation between Task Documents and Project Files popovers, and the mobile detail pane
- Update dashboard-guide.md to document select-to-comment support for Task Documents alongside Project Files
- Add a minor changeset for @runfusion/fusion documenting the feature (depends on FN-7811)
Files changed:
.changeset/fn-7812-task-documents-select-to-comment.md | 7 ++
docs/dashboard-guide.md | 4 +-
packages/dashboard/app/components/DocumentsView.tsx | 37 ++++++---
packages/dashboard/app/components/__tests__/DocumentsView.test.tsx | 93 ++++++++++++++++++++++
4 files changed, 130 insertions(+), 11 deletions(-)
Fusion-Task-Id: FN-7812
Fusion-Task-Lineage: ace10d70-35fd-42fe-8a4a-e2c2c7c7c27b
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Reworks the Artifacts view's Task Documents tab to reuse the Project Files left-sidebar/right-pane layout instead of expandable task-grouped cards, giving both tabs a consistent browsing pattern.
- Replace the collapsible TaskGroup/DocumentCard components with a documents-project-layout sidebar listing documents grouped by task (with revision metadata and task status badges) and a right pane rendering the selected document's content
- Add separate selectedTaskDocumentId selection state so tab switching never leaks Project Files content into Task Documents (and vice versa), with desktop/mobile gating matching the Project Files pattern
- Preserve the existing Plain/Markdown render toggle for task document content; select-to-comment stays Project-Files-only for this change (tracked as follow-up)
- Update DocumentsView.css for the new sidebar/right-pane structure and rewrite DocumentsView.test.tsx coverage for the new interaction model
- Update docs/dashboard-guide.md to describe the shared sidebar/right-pane browsing pattern for Task Documents
- Add changeset fn-7811-task-documents-sidebar.md (minor)
Files changed:
.changeset/fn-7811-task-documents-sidebar.md | 7 +
docs/dashboard-guide.md | 4 +-
.../dashboard/app/components/DocumentsView.css | 181 ++++--------
.../dashboard/app/components/DocumentsView.tsx | 308 ++++++++++-----------
.../components/__tests__/DocumentsView.test.tsx | 116 ++++++--
5 files changed, 299 insertions(+), 317 deletions(-)
Fusion-Task-Id: FN-7811
Fusion-Task-Lineage: e943ebf8-6e8e-4f5f-a55c-99c949be2624
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Fixes the List view's two-pane split layout clipping primary controls and the
expanded quick-add composer on tablet-width viewports (769-1024px) by
switching those widths to the same single-pane card/detail layout already
used on mobile.
- Add `useSinglePaneList` gate in ListView.tsx (`viewportMode === "mobile" || "tablet"`) driving split-vs-single-pane structure, detail routing, and resize-handle wiring, while touch-only long-press behavior stays on `isMobile`.
- Extend the mobile-only responsive CSS breakpoints in ListView.css from `max-width: 768px` to `max-width: 1024px` so tablet gets the same toolbar/card scaffolding as mobile, while desktop split rules remain unchanged above that tier.
- Add `list-view--single-pane` root class and route tablet clicks through the single-pane `onOpenDetail` path instead of the desktop split-pane selection.
- Update docs/dashboard-guide.md to describe the tablet single-pane behavior and add an FNXC:ListView comment recording the FN-7809 rationale.
- Add regression tests covering tablet single-pane rendering, tablet detail-open routing, and updated CSS-fixture assertions for the widened breakpoint.
- Add a patch changeset describing the fix for @runfusion/fusion release notes.
Files changed:
.changeset/fn-7809-list-tablet-single-pane.md | 7 +++
docs/dashboard-guide.md | 6 +-
packages/dashboard/app/components/ListView.css | 11 ++--
packages/dashboard/app/components/ListView.tsx | 49 ++++++++-------
.../app/components/__tests__/ListView.test.tsx | 69 +++++++++++++++++++++-
5 files changed, 112 insertions(+), 30 deletions(-)
Fusion-Task-Id: FN-7809
Fusion-Task-Lineage: 9e5f8bb7-13ee-4a58-81b1-eb5a9911bd4e
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
- contain fn_artifact_register path payloads: realpath-canonicalized
containment before stat/read — relative paths require and must stay
inside baseDir, absolute paths allowed only under baseDir or the OS
temp dir (deliberate allowance for browser/screenshot tooling);
the process.cwd() fallback is gone, symlink escapes rejected
- bind task-scoped heartbeat artifact registration to the acquired
worktree (baseDir: sessionCwd rebind after acquisition); no-task
heartbeat prompt now says to pass absolute temp-dir paths
- enforce exactly-one payload source (content/uri/dataBase64/path);
content+uri combos are now rejected to match the documented contract
- add FNXC rationale comments at both visual-artifact instruction sites
in the planning prompts (sync contract with the executor prompt)
- media route: statSync -> await stat from node:fs/promises
- range tests ride the in-memory MockSocket harness (TestResponse gains
binary-safe bodyBuffer; real-TCP helper deleted) and assert the full
206 Content-Range/Content-Length contract for every range form
- add PdfViewer coverage (iframe src/title) in DocumentsView tests
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- artifact viewers (image/video lightbox, PDF viewer, doc viewer) now host in
the shared FloatingWindow: draggable by the viewer header, resizable by
edge/corner handles, geometry persisted per viewer kind, closed by button
or Escape; FloatingWindow gains an ariaLabel prop so headerless windows
keep an accessible dialog name
- the Artifacts view leads with the Artifacts tab and always lands on it;
Project Files and Task Documents are secondary tabs (the old auto-select
effect is gone)
- mobile tab buttons rendered at mismatched heights (two-line "Project
Files"/"Task Documents" grew past 44px while one-line "Artifacts" stayed
at 44px); tabs now pin to the uniform 44px control height with
non-wrapping labels in a scrollable row
Verified live: window dragged (264,146 -> 144,164) and resized
(1024x720 -> 872x618) in a real browser; mobile 390x844 lands on Artifacts
with uniform tab buttons.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Video was registrable but effectively unusable, and HTML/PDF deliverables
had no first-class path from agents to the gallery.
- media route now serves HTTP byte ranges (Accept-Ranges, 206 +
Content-Range, 416 on unsatisfiable) so <video>/<audio> seeking works
and Safari plays media at all
- video attachments (mp4/webm/mov, 100MB cap vs 5MB for other types)
bridge into the artifact registry like images; multer transport ceiling
raised to 100MB with per-type caps enforced in the store
- fn_artifact_register path payloads are signature-validated for video
(ftyp box / EBML header) and PDF (%PDF- prefix), mirroring images
- HTML doc artifacts (mimeType text/html) render as live sandboxed
iframe previews by default in the doc viewer, with a Preview/Source
toggle and the same FileEditor edit mode
- executor/heartbeat/planning prompts and tool descriptions now cover
the full type matrix: images, videos, audio, HTML mockups, PDFs, and
markdown docs, each with the registration recipe
Verified live: range requests (200/206/416) via curl, an ffmpeg-generated
mp4 playing to completion in the gallery lightbox, and an interactive
HTML mockup rendering in the sandboxed preview.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Agents could never get screenshots/wireframes/mocks into the Artifacts view:
fn_artifact_register was gated on assignedAgentId (never set in default
ephemeral mode), the only image payload source was inline base64, and no
prompt ever told agents to register visual deliverables.
- always expose fn_artifact_register to executor sessions ("executor" author
fallback), resolve relative paths against the task worktree, and default
taskId to the executing task (heartbeat task lane too)
- add a `path` payload source: file read with 50MB cap, extension MIME
inference, PNG/JPEG/GIF/WebP signature + SVG sniff validation, persisted
through managed artifact storage
- executor/heartbeat/planning prompts + engine-tools reference now instruct
agents to register screenshots, wireframes, mockups, and recordings
- new ArtifactsGallery: Images/Docs/PDFs/Videos/Audio/Other category sections
and filter chips, visual tile grid + lightbox, embedded PDF viewer, audio
player rows, download rows; mobile-responsive down to the 768px breakpoint
- doc artifacts open a full viewer rendered as markdown by default with an
in-place edit mode using the shared CodeMirror FileEditor; persisted via new
GET/PATCH /api/artifacts/:id + TaskStore.updateArtifact and live-refreshed
through the new artifact:updated SSE event
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Replace the boolean isGitRepository() check with a tri-state Git detection so environmental git failures (dubious ownership, missing git binary, timeouts) are no longer misreported as "not a Git repository", which previously blocked all task execution in valid repos and survived engine restarts.
- Add detectGitRepository() in worktree-pool.ts returning repo / not-repo / error (with reason: dubious-ownership, git-missing, timeout, unknown), classified from git's stderr; bound the git rev-parse call with a 10s timeout and maxBuffer; keep isGitRepository() as a backward-compatible wrapper
- Route the executor dispatch preflight guard through detectGitRepository(): only emit the original "not a Git repository / run git init" fatal on a positive not-repo verdict; on error, throw a distinct accurate error naming the real git failure, including the safe.directory remedy for dubious ownership
- Route the in-process runtime startup warning through the same tri-state detection so it only warns "not a Git repository" on a positive not-repo verdict
- Add a regression test locking extractWorktreeConflictInfo() to NOT misclassify a dubious-ownership git worktree add failure as not-git-repo
- Add targeted tests across worktree-pool, executor-worktree, and in-process-runtime test suites covering repo/not-repo/dubious-ownership/git-missing/timeout classifications on Windows OneDrive-style and POSIX paths
- Add changeset and a docs/solutions/logic-errors write-up of the false-negative root cause and fix
Files changed:
.changeset/fn-7799-git-detection-false-negative.md | 7 +++
.../logic-errors/git-detection-false-not-repo.md | 54 ++++++++++++++++
.../engine/src/__tests__/executor-worktree.test.ts | 61 +++++++++++++++++++
.../engine/src/__tests__/worktree-pool.test.ts | 71 +++++++++++++++++++---
packages/engine/src/executor.ts | 38 +++++++++---
.../runtimes/__tests__/in-process-runtime.test.ts | 53 ++++++++++++++--
packages/engine/src/runtimes/in-process-runtime.ts | 16 ++++-
packages/engine/src/worktree-pool.ts | 66 ++++++++++++++++++--
8 files changed, 334 insertions(+), 32 deletions(-)
Fusion-Task-Id: FN-7799
Fusion-Task-Lineage: 25a84283-bf47-472b-8a98-a10bf7e494de
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Narrative: the streaming-json headless contract intermittently emitted only thought events then stopReason:Cancelled with zero text, leaving Chat replies silently empty; the adapter now spawns grok with --output-format json, buffers stdout, and parses the single JSON response on process close, with streaming-json parsing kept only as a diagnostic fallback.
- Change grok CLI invocation from --output-format streaming-json to --output-format json (cli-stream.ts)
- Add GrokCliJsonResponse type ({text, stopReason, sessionId, requestId, thought}) and parseJsonOutput() to stream-parser.ts, keeping legacy NDJSON line parsing for fallback/diagnostics
- Rework runtime-adapter.ts to buffer full stdout, parse it via parsePromptOutput (JSON object first, NDJSON fallback), and surface a formatTerminalNoTextDiagnostic when a non-EndTurn stopReason yields no assistant text
- Rename first-line/inactivity timeout bookkeeping from line-based to output/chunk-based (FIRST_OUTPUT_TIMEOUT_MS, firstOutputReceived, firstStdoutChunk) since stdout is no longer consumed via readline
- Update cli-stream/runtime-adapter/stream-parser tests to cover the JSON response path and the Cancelled/no-text diagnostic
- Update docs/grok-cli-contract.md and plugin README to document the json output-format contract and diagnostics
- Add changeset fn-7796-grok-cli-reliable-headless.md (patch, fix)
Files changed:
.changeset/fn-7796-grok-cli-reliable-headless.md | 7 +
docs/grok-cli-contract.md | 108 ++++++++-----
plugins/fusion-plugin-grok-runtime/README.md | 16 +-
.../src/__tests__/cli-stream.test.ts | 4 +-
.../src/__tests__/runtime-adapter.test.ts | 73 ++++++++-
.../src/__tests__/stream-parser.test.ts | 80 +++++----
.../fusion-plugin-grok-runtime/src/cli-stream.ts | 14 +-
.../src/runtime-adapter.ts | 180 ++++++++++++---------
.../src/stream-parser.ts | 65 ++++++--
plugins/fusion-plugin-grok-runtime/src/types.ts | 13 +-
10 files changed, 373 insertions(+), 187 deletions(-)
Fusion-Task-Id: FN-7796
Fusion-Task-Lineage: c920fcf0-98f8-42ec-867a-7f76c0aca1b7
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds a per-lane thinking-level selector to every fallback model picker across global, project, and workflow Settings surfaces, wiring them into the existing null-as-delete save paths.
- Add inline thinking-level dropdowns to the global Fallback Model, workflow-declared planning/validator fallback lanes, and the project-scoped Title Summarizer fallback picker via CustomModelDropdown's `showThinkingLevel`.
- Route `planningFallbackThinkingLevel`/`validatorFallbackThinkingLevel` through workflow settings PATCH and `titleSummarizerFallbackThinkingLevel` through project settings save-split, both with null-as-delete semantics on reset.
- Move Title Summarizer fallback out of the workflow-declared model pairs into a dedicated project-scoped lane in ProjectModelsSection so its thinking companion isn't tied to workflow settings.
- Update WorkflowSettingsPanel to surface the new fallback thinking companion keys.
- Extend/adjust tests (settings-save-split, settings-sections, SettingsModal.models-auth, WorkflowSettingsPanel, core settings-migration) to cover the new selectors and save routing.
- Document the fallback thinking-level runtime behavior in docs/settings-reference.md and docs/dashboard-guide.md.
- Add a minor changeset describing the new fallback thinking-level selectors.
Files changed:
.changeset/fn-7795-fallback-thinking-selectors.md | 7 +
docs/dashboard-guide.md | 4 +-
docs/settings-reference.md | 10 +-
packages/core/src/__tests__/settings-migration.test.ts | 14 +-
packages/dashboard/app/__tests__/settings-save-split.test.ts | 35 +++++
packages/dashboard/app/__tests__/settings-sections.test.tsx | 163 ++++++++++++++++++++-
packages/dashboard/app/components/WorkflowSettingsPanel.tsx | 6 +-
packages/dashboard/app/components/__tests__/SettingsModal.models-auth.test.tsx | 11 +-
packages/dashboard/app/components/__tests__/WorkflowSettingsPanel.test.tsx | 38 +++++
packages/dashboard/app/components/settings/save-split.ts | 9 +-
packages/dashboard/app/components/settings/sections/GlobalModelsSection.tsx | 8 +-
packages/dashboard/app/components/settings/sections/ProjectModelsSection.tsx | 58 ++++++--
12 files changed, 328 insertions(+), 35 deletions(-)
Fusion-Task-Id: FN-7795
Fusion-Task-Lineage: ec990d47-defe-4717-993a-56988afe8d7d
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Adds fallbackThinkingLevel plumbing so, when Fusion swaps from a primary model to a configured fallback model (executor, validator/reviewer, merger, planning, title-summarizer, heartbeat, and workflow-step lanes), the fallback's own configured thinking level is applied instead of silently reusing the primary lane's level.
- Add fallbackThinkingLevel option to AgentRuntimeOptions (agent-runtime.ts), AgentOptions (pi.ts), and ReviewOptions (reviewer.ts)
- Add per-lane resolvers: resolveExecutorFallbackThinkingLevel, resolvePlanningFallbackThinkingLevel, resolveValidatorFallbackThinkingLevel, resolveTitleSummarizerFallbackThinkingLevel, resolveMergerFallbackThinkingLevel (agent-session-helpers.ts), each following fallback-provider precedence and falling back to the primary lane/default thinking level when unset
- Export new resolvers from packages/engine/src/index.ts
- Apply the resolved fallback thinking level in createFnAgent's applyThinkingLevelIfSupported once a session has swapped to the fallback model (pi.ts)
- Wire fallbackThinkingLevel through executor session creation (workflow-step, task validator, child-agent, and main executor session paths), merger session creation, and heartbeat session creation
- Promote the fallback thinking level alongside the fallback model/provider when the no-visible-key Grok CLI fallback is promoted to primary, so the cleared fallback pair doesn't leave the session on the superseded primary's thinking level
- Route workflow-step fallback thinking level by which fallback candidate (validatorFallback vs globalFallback) actually matched
- Document fallbackThinkingLevel runtime-swap behavior in docs/settings-reference.md
- Add minor changeset for @runfusion/fusion
- Add regression tests covering fallback thinking-level resolution and application (agent-session-helpers.test.ts, pi.test.ts) and a shared test helper (executor-test-helpers.ts)
Files changed:
.changeset/fn-7794-fallback-thinking-level.md | 7 ++
docs/settings-reference.md | 3 +
.../src/__tests__/agent-session-helpers.test.ts | 38 ++++++
.../engine/src/__tests__/executor-test-helpers.ts | 23 ++++
packages/engine/src/__tests__/pi.test.ts | 136 +++++++++++++++++++++
packages/engine/src/agent-heartbeat.ts | 3 +-
packages/engine/src/agent-runtime.ts | 5 +
packages/engine/src/agent-session-helpers.ts | 54 ++++++++
packages/engine/src/executor.ts | 31 ++++-
packages/engine/src/index.ts | 5 +
packages/engine/src/merger.ts | 7 +-
packages/engine/src/pi.ts | 16 ++-
packages/engine/src/reviewer.ts | 6 +
13 files changed, 327 insertions(+), 7 deletions(-)
Fusion-Task-Id: FN-7794
Fusion-Task-Lineage: c94d621a-ccbd-42b2-9fe6-cb619418ad90
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
Image attachments added via TaskStore.addAttachment now surface as first-class image artifacts, reusing the existing artifact listing/SSE/media pipeline instead of duplicating bytes.
- addAttachment() registers a URI-only "image" artifact (metadata.source: "attachment") pointing at the already-written attachments/<file> path whenever an image mimeType is attached; registration is best-effort and swallows the archived/soft-deleted-task rejection so addAttachment keeps its always-succeeds contract for valid images.
- deleteAttachment() now removes any bridged artifact rows for a filename before deleting the attachment file, so /api/artifacts/:id/media can never point at a deleted attachment.
- register-task-workflow-routes.ts's resolveArtifactMediaPath now accepts task-scoped attachments/<file> URIs (in addition to artifacts/<file>) so the media route can stream bridged image-attachment artifacts; task-less artifacts remain restricted to .fusion/artifacts/.
- docs/storage.md documents the attachment→artifact bridge behavior and the media route's accepted URI prefixes.
- Added a changeset (@runfusion/fusion: minor) describing the user-facing Artifacts view change.
- Extended store-attachments and artifacts-route-integration tests to cover the new bridging and deletion behavior.
Files changed:
.changeset/fn-7791-image-attachments-artifacts.md | 7 +++
docs/storage.md | 3 +-
packages/core/src/__tests__/store-attachments.test.ts | 59 +++++++++++++++++++++-
packages/core/src/store.ts | 58 ++++++++++++++++++++-
packages/dashboard/src/routes/__tests__/artifacts-route-integration.test.ts | 40 +++++++++++++++
packages/dashboard/src/routes/register-task-workflow-routes.ts | 9 +++-
6 files changed, 172 insertions(+), 4 deletions(-)
Fusion-Task-Id: FN-7791
Fusion-Task-Lineage: 4df47880-6161-4a8b-933a-2f6fc2fed953
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
