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>
Prevent the terminal header's shortcut/status text and action controls from wrapping onto multiple lines when the floating or docked terminal panel is narrow at desktop breakpoints.
- Add white-space: nowrap to .terminal-shortcuts--header so header help text stays on one line
- Add white-space: nowrap to .terminal-connection-status to keep connection status text from wrapping
- Rely on existing .terminal-actions min-width: 0 + overflow-x: auto pattern for horizontal scrolling instead of wrapping
- Add regression test asserting the nowrap/scroll rules and that mobile still hides these elements
- Add changeset documenting the fix
Files changed:
.changeset/fn-7823-terminal-header-nowrap.md | 7 +++++++
packages/dashboard/app/components/TerminalModal.css | 9 +++++++++
.../app/components/__tests__/TerminalModal.test.tsx | 21 +++++++++++++++++++++
3 files changed, 37 insertions(+)
Fusion-Task-Id: FN-7823
Fusion-Task-Lineage: 36426985-a489-41ec-9d79-f8b02862d504
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>
Swap the hand-drawn Cursor CLI placeholder SVG for Cursor's official cube/arrow brand mark and ensure model-id-shaped provider strings resolve to it.
- Replace CursorCliIcon's placeholder rounded-square+badge SVG with Cursor's official cube/arrow brand mark path data
- Add cursor -> cursor-cli mapping in inferProviderIconKey so cursor, cursor-agent, and cursor/<model> strings resolve to the branded icon instead of falling through to the generic CPU icon
- Update ProviderIcon and providerIconKey tests to cover the new brand mark paths and provider-string inference
- Add a patch changeset documenting the fix
Files changed:
.changeset/fn-7818-cursor-logo.md | 7 +++++
packages/dashboard/app/components/ProviderIcon.tsx | 33 +++++++++++-----------
.../app/components/__tests__/ProviderIcon.test.tsx | 12 ++++++--
.../app/utils/__tests__/providerIconKey.test.ts | 4 +++
packages/dashboard/app/utils/providerIconKey.ts | 8 ++++++
5 files changed, 44 insertions(+), 20 deletions(-)
Fusion-Task-Id: FN-7818
Fusion-Task-Lineage: 73e85e18-e98a-4dc3-b89d-f831525620de
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>
- fix: fragments are hidden in the add-step dialog when the target edge is
inside a foreach/loop/optional-group (they expand to top-level subgraphs
and cannot splice into a template-child edge), and
spliceInsertedSubgraphOnEdge now refuses container-internal edges as a
second line of defense (Greptile P1 x2).
- test: add-step modal container-target hiding, multi-entry/exit splice
fan-out, internal-cycle entries fallback, ambiguous merge-inbound
lifecycle fallback, and edge-targeted "as optional group" wiring
(CodeRabbit nitpicks).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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>
- fix: edge-targeted fragment and "insert as optional group" picks from the
add-step dialog now splice the inserted subgraph into the targeted edge
(entries inherit the original routing condition, exits feed the old
target, subgraph moves into the source's column band) instead of dropping
disconnected fixed-position nodes (Greptile P1).
- feat: the lifecycle warnings banner is now a one-line collapsible
disclosure (count summary, details on expand) so it no longer dominates
the editor header.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Switching or creating a workflow could leave the simplified canvas fitted to
the previous graph's bounds (an apparently empty canvas after New workflow).
Keying the canvas's ReactFlowProvider on the workflow id forces a fresh
measure + initial fitView per workflow; the in-place refit still handles
inserts/deletes within one workflow.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Adds a simplified graphical node editor as the workflow editor's default
view: a modern vertical auto-laid-out React Flow canvas with insert-on-edge
"+" affordances and a searchable, categorized add-step dialog (node kinds +
fragments + step templates). A segmented Simple/Advanced/List switch
(persisted in localStorage) keeps the full advanced canvas untouched and
retains the old compact row editor as the List fallback. Mobile's graph tab
gains the touch-friendly simplified canvas with the row list as fallback.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- parseInsightsContent: only top-level bullets (column 0 on the raw line) start
a new insight; indented sub-bullets stay inside their parent insight with
indentation preserved, so counts no longer inflate
- regression test for indented sub-bullets
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- parseInsightsContent: append continuation lines to the previous bullet so
multiline insights render in full instead of truncating after the first line
- .memory-insight-item: white-space: pre-wrap so continuation breaks display
- regression tests for per-bullet parsing, counts, and multiline continuations
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 a Grok (xAI) provider fetcher to the dashboard's usage aggregation so a Grok card now appears in the Usage dropdown when credentials are configured.
- Add fetchGrokUsage() in usage.ts: resolves the API key from GROK_API_KEY env, then ~/.grok/user-settings.json, then grok-cli auth storage, and validates it against GET https://api.x.ai/v1/api-key
- Since xAI exposes no subscription usage meter for inference keys, the card reports auth-validity status (ok/no-auth/error) with an empty usage-window list rather than fabricating quota data
- Surfaces clear error messages for expired/blocked keys and non-200 responses; omits the card entirely when no credentials are found
- Register fetchGrokUsage in fetchAllProviderUsage's parallel provider fetch list alongside Claude, Codex, Gemini, Minimax, Zai, and GitHub Copilot
- Add extensive test coverage in usage.test.ts for key-source precedence, ok/error/no-auth states, and blocked/expired key handling
- Add changeset (.changeset/fn-7814-grok-usage.md) documenting the new minor feature
Files changed:
.changeset/fn-7814-grok-usage.md | 7 ++
packages/dashboard/src/__tests__/usage.test.ts | 157 +++++++++++++++++++++++++
packages/dashboard/src/usage.ts | 95 ++++++++++++++-
3 files changed, 257 insertions(+), 2 deletions(-)
Fusion-Task-Id: FN-7814
Fusion-Task-Lineage: cac497a9-5a57-4ba5-a7ea-8a01b89a0cbd
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>
Replace the FileEditor's bounded self-echo Set with monotonic edit versions so trailing-newline edits (e.g. after a markdown header or at end-of-file) are never dropped when an older content prop races the live CodeMirror document.
- Track a monotonic localEditVersionRef and a contentEditVersionsRef map (content -> version) instead of a size-capped Set of echoed strings, avoiding eviction of stale values during long editing sessions.
- Compare a stale prop's known edit version against the live document's version and the last accepted prop version to decide if it is a stale self-echo, at any session length.
- Update FNXC:FileViewer comment to document the FN-7810 rationale for switching from bounded-Set self-echo detection to edit-version comparison.
- Add regression tests covering trailing markdown-header and plain-text newline edits across markdown/non-markdown file paths, and a long-session (20+ edit) case that previously could evict the self-echo tracking.
Files changed:
packages/dashboard/app/components/FileEditor.tsx | 32 +++++++----
.../app/components/__tests__/FileEditor.test.tsx | 64 +++++++++++++++++++++-
2 files changed, 83 insertions(+), 13 deletions(-)
Fusion-Task-Id: FN-7810
Fusion-Task-Lineage: 9dd68746-e772-4fa3-b648-6f3138d1e36e
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
A long-lived connection can go SQLITE_NOTADB ('file is not a database' on
every query) while the on-disk file stays intact — observed 2026-07-10 on the
live dashboard, which then failed every API request and poll cycle until the
process was restarted, because all corruption recovery ran at open time only.
The sqlite adapter now detects connection-corruption errors, closes the dead
handle, reopens the same path, replays connection-scoped PRAGMAs, verifies
with quick_check, and retries the failed operation once when outside an
explicit transaction. Prepared statements are generation-tracked and
re-prepare transparently after a reopen; a lost transaction's unwind is
absorbed so the original error propagates cleanly. Reopens are rate-limited,
and real on-disk corruption still defers to the open-time recovery machinery.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- 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>
