Why: Fast and slow channel cards duplicate across panes and completed replies hide process output.
Evidence: npm test; npm run build; 12 isolated Playwright scenarios with reload and responsive widths.
Impact: Preserve ordered folded process history, load durable run events, and give work cards one detailed pane.
Refs: Agent-System-Dev feature/work-companion-visibility UI1 UI2 UI3
Why: auditors need to generate and download a watermarked report from the overview, and that must not appear when the export commands are off or change whether the workspace itself opens.
Evidence: SELF npm test, 138 passed. Playwright download case is in e2e/rdm-audit.playwright.ts and runs under scripts/e2e.sh.
Impact: the overview shows type, generate, draft confirmation, watermark, sha256, expiry, and download only when the three export commands are enabled.
Refs: RDM pull request 301
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: the rdm-audit entry was an unconditional builtin, so on a plain base
without any rdm.inspect.* commands the workspace opened straight into a
rejected receipt (400) - diagnosed 2026-10-12. The page also rendered raw
receipt JSON instead of a readable error.
Evidence: vitest 23 files / 112 tests pass incl. the new contract matrix
(workspaces.test.ts, rdm-errors.test.ts) and design-guard; tsc -b &&
vite build pass; e2e plain-base scenario added (driven by dev-repo
scripts/e2e.sh phase 4).
Impact: audit entry shows only when GET /api/commands lists all seven
rdm.inspect.* commands enabled (store.rdmAuditAvailable, refreshed with
the workspace list); audit errors classify into capability-missing /
auth-expired / query-failed with the raw receipt kept in a Collapsible.
Refs: 2026-10-12 diagnostic report, increment 2.
Why: rdm.inspect.tree docs is two-level (parent=<docId> returns sections), but the U4 workspace only fetched level one - the tree showed bare documents, clicking a doc hit unsupported inspect.object kind, and the trace tab always showed no sections.
Evidence: tsc + design-guard green; scripts/e2e.sh full run in this task.
Impact: tree browsing expands documents into sections; trace entry lists sections aggregated per document.
Refs: U4/U3 read-service contract; task feature/rdm-e2e-acceptance.
Why: the master plan U4 requires a four-entry traceability audit workspace as a builtin Dev frontend workspace; U3 rdm.inspect.* commands are the server contract.
Evidence: SELF tsc --noEmit zero errors in new files; design guard compliance verified (tokens only, no raw colors, no inline fontSize, no details element); CI (GATE) will run full suite.
Impact: RdmAuditWorkspace.tsx (new, ~500 lines), api.ts (+rdmCommand), Workspaces.tsx (+rdm-audit dispatch), workspaces.ts (+builtin), styles.css (+rdm-audit-* using only @ui tokens).
Refs: Documents eb36571 master plan U4; U3 rdm.inspect.* contract
Why: The three-column workbench redesign converges entries and hierarchy:
project switching tops the left rail (identity shown once), sessions and
search stay centered, files/workspaces/account sink to the bottom. The
right column becomes a Work/Files third column that absorbs the preview
pane, which is no longer an independent fourth region; the artifacts
workspace overlay folds into the Files entry, and stop control
consolidates into the input area with a light fast/slow-lane status hint.
Evidence: make test-frontend NOT_RUN at commit time; the run and its
outcome are recorded in the Dev task card before integration.
Impact: App.tsx layout and divider width tiers (work 280-560, files with
open preview 420-1100); store UI state rightTab work/files plus filesView
with syncFilesEntry replacing syncPreviewRail; Workbench dual entry;
PreviewPane gains a back-to-list control; TaskSidebar project switcher;
TopBar drops project identity; Conversation drops the header stop button
and gains the input status line; workspaces.ts drops the artifacts builtin.
Refs: three-column workbench proposal (2026-10-11), DESIGN.md 6/9.3
revision follows in the Dev repo.
Why: .main { display: flex } overrides the UA [hidden] rule, so previewExpanded left the conversation column in the row and squeezed the preview.
Evidence: vitest test/previewfit.test.ts and test/design-guard.test.ts passed (10 tests). Headless Chromium at 1512x900: expanded .main is display:none and the preview slot is 1184px with the page centered (center delta 0); at 420px and 640px the wrapper stays column-width and the page stays left-aligned.
Impact: expanded preview fills the main row; docx pages center only when the column is wider than the page. Narrow-column fit scaling is unchanged. previewfit still returns 1 when available width is <= 0.
Refs: App.tsx hidden={previewExpanded}; styles.css .main and .docx-wrapper
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The pane pinned .ui-fp to the column height, and the docx fit host then clipped overflow, so the right-hand preview could not scroll. The fullscreen DocViewer was a second shell around the same FilePreview.
Evidence: npx vitest run (17 files, 82 tests) and npx tsc --noEmit passed. Headless Chromium laid out a 1400px docx host inside a 764px pane (body scrollHeight 1400) and a pdf iframe that filled that pane.
Impact: .preview-pane-body is the scroll owner. Docx refit also watches page height. The overlay viewer is gone; expand/restore and text edit/save live on the pane.
Refs: Agent-System-Dev#196, Agent-System-Frontend#44
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Headers, HITL details, tool lists, and status words used faint text, semantic colors were used as text, and the molv sidebar primary button matched the navy surface. There was no control for --ui-font-size.
Evidence: npx vitest run (17 files, 81 tests), npx tsc --noEmit, and knip unused exports 43 <= 43 passed in modules/frontend.
Impact: Content classes move to --text-dim or *-text. Sidebar active, focus, and the new-task button use the sidebar tokens. Settings gains 小/标准/大/特大, stored only in localStorage as ui.fontSize. Before: no font-size control and a 1:1 new-task button on molv. After: four local sizes and a light sidebar button.
Refs: feature/contrast-typography
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: An A4 page is wider than the preview column, and the page background followed the app theme, so body text disappeared in dark mode.
Evidence: npm test (17 files, 81 tests) and npx tsc -b passed in modules/frontend.
Impact: Docx pages stay on --paper with their own styles and shrink to fit the column. A column wider than the page, including fullscreen, keeps them at 100%. Before: section background var(--bg) and color var(--text). After: var(--paper) and var(--paper-ink).
Refs: feature/docx-paper-preview
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Keys must be added without writing masks back, and a turn needs copy, exclude, and regenerate without deleting history.
Evidence: npx tsc -b. Session notes and candidate switches call the new conversation and message routes.
Impact: Settings gains key, lore, and slash-template panels. Excluded messages stay visible and are dimmed.
Refs: docs/records/2026-10-04-sillytavern-review.md
Why: tracked workspace writes need a visible way to return files to the state before a user message.
Evidence: the confirm lists the files the rewind API would restore or skip.
Impact: the control only calls the new checkpoints and rewind endpoints. Usage may include the model that served.
Refs: feature/durable-rewind
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Plan, default, and auto-edit have to be visible where the user sends a message, and confirmation cards need to show the arguments.
Evidence: The mode control and card detail only use existing color, radius, and type tokens.
Impact: An empty mode still renders as 默认. Confirm cards use the wait color instead of the success color.
Refs: feature/permission-hooks
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The send button, stop button, and queued sends each looked at a different slice of run state, so a reconnect or a late assistant message could disagree.
Evidence: A depth-4 walk of send, HTTP results, SSE, reconnect, conversation switch, and flush keeps busy aligned with an in-flight run, hides the live bubble once an assistant message exists, and keeps one user message per request id.
Impact: The event listener list is exhaustive over the stream contract, including run.check. A disconnected stream shows 重连中.
Refs: feature/runstate-shell
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Deliverable cards appeared as soon as a file was registered, and the last draft was shown as the answer before the run had finished composing one.
Evidence: vitest run test/live.test.ts test/toolkind.test.ts test/messageparts.test.ts test/design-guard.test.ts
Impact: Cards wait until the run ends. A finalizing phase keeps earlier text in the process block, and check rows render there.
Refs: feature/final-reply-compose
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Streaming tool arguments looked like a frozen cursor, and a failed run folded the only narration into the collapsed process block.
Evidence: npx vitest run in modules/frontend, 13 files, 66 passed. npx tsc -b reports only a pre-existing missing docx-preview module.
Impact: Live tools move composing to running to done with arguments and output; finished runs lift the last narration; same-run errors and duplicate files collapse into the reply.
Refs: feature/stream-display-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: The first S4 pass makes the project the navigation context, keeps deep views in one overlay, and leaves domain panels empty until a plugin declares them.
Evidence: npx tsc -b and npm test (61 passed) in modules/frontend.
Impact: Top bar, project sidebar, inbox all/todo filter, one-way scroll sync, drag-and-drop on the whole chat column, and local molv/system themes.
Refs: feature/s4-shell-overhaul
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: A background child should not look like the conversation is busy, and its completion note needs a compact row instead of a full assistant bubble.
Evidence: vitest run passed, including design-guard. tsc -b passed.
Impact: The stop button cancels the conversation run. System notices fold with the shared Collapsible.
Refs: feature/agent-harness-p3b
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Process output folded on every text delta, successful tool
results disappeared after refresh, and generated files stayed plain
text instead of a card that opens a closable preview.
Evidence: npx tsc -b --noEmit (clean); npx vitest run (51 passed).
Impact: Live work stays expanded until the run ends, then folds to
one worked-time line. File cards open a per-conversation preview pane.
docx renders page by page, with mammoth if that fails.
Refs: feature/chat-timeline-preview
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: a busy conversation rejected further input, and the file list lived
only behind the workspace overlay.
Evidence: npx tsc --noEmit and vitest 42 tests, including outbox
append/edit/promote. The queue uses Collapsible and design tokens.
The files tab reuses ArtifactsPanel.
Impact: while a run is active, Enter queues the draft (edit, delete, or
send-now). Finished and failed runs drain the queue. HTTP 409 also
enqueues instead of only toasting. Backend serialization is unchanged.
Refs: task feature/input-queue
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: tool artifacts were only reachable via the collapsed process
section or the artifacts workspace; users had to read model text to
learn a file existed. Deliverables should appear directly in the
conversation as an openable card (ZCode/Kimi pattern) that opens the
right-rail preview.
Evidence:
- Conversation.tsx artifact_ref renderer upgraded from a small chip to
a deliverable card (icon + name + kind/size meta + preview affordance
+ single download action); whole card click = rail preview (the one
preview placement, fullscreen still reachable from the rail header)
- live.ts projects artifact items as content parts pinned after the
reply text, isomorphic with the new llm.go persisted order; card is
visible while streaming
- styles: deliverable-card uses tokens only (radius-lg card, bg-raised,
hairline border, mk-rise-in entrance); design-guard suite green
- vitest 40/40 (live.test pinned-tail case updated, messageparts.test
covers new persisted order plus legacy inline order); tsc clean
Impact: every generated artifact (docx/pdf/image/…) now surfaces as an
in-chat card immediately, click-to-preview in the right rail with real
formatting for styled docx; workspace panel (⌘1) unchanged as the
file-system fallback.
Refs: task feature/deliverable-docx-r1 (backend: write_docx + pinned
artifact_ref)
Why: Keep the task branch on the shared baseline before acceptance.
The merged CF3 code carried a bare hex fallback (#d8d8d8) and off-scale
font size in .inbox-scope — the design guard caught it; fixed to tokens
(--border / --radius-full / --fs-ui-sm / --bg-hover) per DESIGN.md.
Evidence: clean ort merge; npx tsc -b clean; npm test -> 39 passed
(guard green after the fix); npm run build succeeds.
Impact: brings the project inbox dual view into the branch with its
styles brought onto the token system; no behavior changes.
Refs: task feature/ui-tokens-v3.
Why: Approved redesign phase 4: process folds, long-reply folds, thinking
blocks and context-observation fold move to the @ui Collapsible primitive
(two-layer height+fade animation, delayed unmount, open-state memory);
tool calls render as ToolBlock rows with running sweep and paired results;
the live bar gains the ZCode worked-time line with sweep; input placeholder
states the backend's honest busy semantics (serialized per conversation).
Evidence: npx tsc -b clean; npm test -> 39 passed (details-guard included);
npm run build succeeds; combined make test recorded in the Dev task card.
Impact: Conversation.tsx replaces all <details> usage (guard-enforced);
ProcessParts pairs tool_call with its trailing tool_result into ToolBlock;
styles.css rewrites fold selectors for the Collapsible structure and adds
message mount animation (mk-rise-in); no contract or API changes.
Refs: Agent-System-Dev task feature/ui-tokens-v3 (phase 4).
Why: D49/D51 — aggregated project view (project cards + other
conversations' pending) so todos survive conversation switches;
D50 — subscribe the project channel via scope=project.
Evidence: api endpoints (listProjectCards/cardToProject, card.* named
SSE events — also fixes live card events previously dropped);
store projectCards/inboxScope/applyProjectEvent/cardToProject with
badge combining both scopes; Workbench scope tabs + grouped ProjectInbox;
styles for scope control.
Impact: existing conversation inbox behavior unchanged; badge now counts
both scopes.
Refs: documents proposal 2026-09-30-card-stream-artifact-unify-project-inbox.md (D48-D51).
Why: Approved redesign phase 2 (IA): normal users run projects entirely
through conversation; system capabilities (user management, agent profiles,
plugin management, plugin-declared workspaces) belong behind a dedicated
admin entry, not in the user-facing sidebar or settings. The sidebar
workspace strip is removed; artifacts stay reachable via the right-rail
tab and conversation chips.
Evidence: npx tsc -b clean; npm test -> 38 passed (design-guard ratchet
still green). Full combined run recorded in the Dev task card.
Impact: new AdminZone full-screen view with a declarative section registry
(users/profiles/plugins/plugin-workspaces via UIRenderer); sections moved
out of SettingsModal (now personal preferences only) and AdminUsersModal
(now password change only); store ui.adminUsersOpen renamed adminZoneOpen;
workspaceEntries narrowed by role so plugin entries no longer take Cmd1-9
for regular users; theme toggle moved into the account menu.
Refs: Agent-System-Dev task feature/ui-tokens-v3 (phase 2).
Why: Phase 1 of the approved frontend redesign: re-skin the shell to the
Zai look (floating rounded panels on an inset base with 4px gutters),
invert primary buttons to the mono scheme, and move every font size onto
the --fs-ui-* scale. Also wires @ui/motion.css and replaces local
keyframes with mk-* utilities.
Evidence: npx tsc -b clean; npm test -> 38 passed (new host-side
design-guard ratchet); npm run build succeeds. Combined Dev make test
recorded in the Dev task card.
Impact: styles.css fully re-tokenized (panel borders/radius, primary
button color-mix hover, login brand panel in near-mono navy); inline
fontSize literals in components replaced with scale tokens except one
decorative glyph in the ratchet baseline. No component class names or
behavior changed.
Refs: Agent-System-Dev task feature/ui-tokens-v3; DESIGN.md (parent repo).
Why: the adjudicated plan (D1-D4) calls for office/link previews with
loaders injected from the host, right-rail light preview alongside the
overlay viewer, and artifact deletion kept as an API capability with no
UI entry.
Evidence: previewsetup.ts injects docx (mammoth), xlsx (SheetJS, sheet
tabs, 200-row cap), pptx (pptx-preview full-fidelity; pptx2html was
dropped for a broken module entry — tXml case mismatch breaks Linux
builds — per the D2 fallback clause), and the /api/url-preview fetcher,
all via dynamic import: the main entry grows ~12KB while xlsx (430KB),
pptx (1.2MB) and jszip (98KB) load on first preview. DocViewer becomes a
FilePreview container (keeps text-family editing); Workbench gains a
preview tab with rail-preview state (store.railPreview); artifact chips
and panel rows gain a rail-preview action; the panel delete button is
removed while api.deleteArtifact and DELETE /api/artifacts/{id} remain.
tsc clean; vitest 33 passed; production build succeeds.
Impact: previews work end to end for the whole format matrix; deletion
stays plugin-reachable only.
Refs: task feature/file-preview-caps; ui fb76239; core 4d29301; backend
6d4ccfd.
Why: AssistantMessage reordered a message's parts by the process flag,
so tool calls floated above the text that surrounded them instead of
appearing where they actually ran; live streams had the same defect via
a fixed template order and never showed artifacts mid-run. Generated
files (e.g. meeting-minutes docx) had no visible download path, the
artifacts panel was a bare list, DocViewer nested a modal inside the
overlay, and settings rows used a legacy grid with a floating save
button.
Evidence: messageparts.ts adds groupParts (order-preserving grouping of
consecutive process parts, unit-tested) plus humanSize/artifactIcon
helpers; Conversation renders blocks in original order and the artifact
chip becomes icon + open + download; LiveState.parts accumulates events
in arrival order including artifact_ref so live view matches the
persisted message; ArtifactsPanel gains search/kind filter/upload and
per-row preview/download/delete-confirm; DocViewer is a single-layer
OverlayHost with pdf iframe, csv/json monospace, and a binary info card
with a download CTA; SettingsModal migrates to @ui SettingRow with the
save button pinned in the shell actions bar; inbox cards receive the
docBridge so result cards can open artifacts. tsc clean, vitest 20
passed, production build succeeds.
Impact: message timelines read in true execution order during and after
runs; every artifact is previewable and downloadable from the message
chip, the workspace panel, and the viewer; settings render on the fixed
two-column shell.
Refs: task feature/chat-order-artifact-files (ui# c3e1f3b backend#
44b51fa).
Why: avatars, cards, and settings are base capabilities now (user
decision 2026-09-30); the host must eat its own dogfood so plugins get
the identical surfaces.
Evidence:
- Local icons.tsx removed; Icon/Avatar/BrandMark/primitives/Settings
Shell imported from @ui; message stream gains avatar columns (user
initial from /api/me name, assistant brand mark); SettingsModal
rebuilt on SettingsShell (side-nav sections with badges, EmptyState
for plugins, iconified actions); AdminUsersModal rows show shared
avatars.
- tsconfig paths pin react/react-dom types to the frontend copy — the
source-composed ui package otherwise resolves a second @types/react
through its own node_modules during make frontend (npm ci), which
breaks type identity (surfaced by SVGProps crossing the boundary);
vite dedupe already guarantees one runtime copy.
- Headless on the real binary: avatar columns render, settings shell
switches sections with badges, admin rows show avatars, zero console
errors; build + vitest green.
Impact: visual/structural only; no API or state changes.
Refs: Agent-System-Documents proposal 2026-09-30-ui-redesign-and-auth.md
Why: user feedback (2026-09-30) — the UI still lacked the polish and
modern feel of ZCode; per its design system (calm/dense/operational)
this is the R4 visual convergence pass.
Evidence:
- New icons.tsx: 32 Lucide-style linear SVG icons replacing every emoji/
glyph (grep for the old glyph set now returns 0 in components); brand
mark + workspace-icon mapping shared by sidebar, rail, login, menus.
- Login/change gates gain a wide-screen brand panel (gradient + radial
glows + feature list), segmented tabs, focus-ring inputs, glowing
submit; sidebar gets a solid accent New Task CTA, inline-icon search,
selected task with accent bar, hover-reveal row actions, account
footer chips; chat area gains floating rounded composer with focus
glow, calmer header/tool blocks, greener HITL confirmations, empty
state mark; modals gain backdrop blur + spring-in.
- Two headless review iterations on the real binary (--auth on, both
themes): fixed bubble padding, headline break, and lifted the panel
step for clearer three-column separation; final walk shows 21 SVGs,
zero leftover glyphs, zero console errors, build + vitest + full make
test green.
Impact: pure visual layer (CSS + icon components + class-level JSX);
no behavior, API, or state changes; both themes driven by the new token
scale in the ui repo.
Refs: Agent-System-Documents proposal 2026-09-30-ui-redesign-and-auth.md (R4)
Why: accounts are admin-issued (user decision 2026-09-30, no self
registration); initial and admin-reset passwords must force a change on
first login.
Evidence:
- LoginPage: password (primary) + API key tabs; ChangePasswordGate
blocks the app until the forced change completes (mismatch/length
validation inline); App auth state machine checking -> login ->
mustchange -> ok, session cookie flows through fetch automatically.
- Account menu gains change-password and admin-only user management;
AdminUsersModal: create account (random initial password generator,
admin checkbox), reset password, status table (ADMIN/USER, pending
change chips).
- Fixed a real bug found in the headless walk: menu toggles passed
e.currentTarget into the setState updater where React nulls it by
render time, so anchor was null and the menu never rendered; capture
the element before the updater.
- Headless journey on the real binary with --auth on: admin bootstrap
via CLI -> first-login forced change -> app; admin creates bob (bob
sees no user management); alice reset via CLI -> forced change on
next login; API-key tab login; logout; zero console errors. npm run
build + vitest green; make test full suite exit 0.
Impact: replaces the old API-key-only LoginGate; embedded no-auth mode
unchanged (no login page shown).
Refs: proposal 2026-09-30-ui-redesign-and-auth.md section 5 (R2,
admin-issued variant)
Why: creation entries were split (project + at sidebar top-left, new
session at bottom-left) and the project tree forced per-project
navigation; the approved option A design makes one primary New Task
entry, organization a view mode, and identity always present.
Evidence:
- New TaskSidebar: single New Task split button (current-project context,
Cmd-N, secondary menu for new project / new task in project), project
<-> timeline organization with persisted collapse, pinned section,
archive view toggle, hover row actions, account footer fed by
/api/me (embedded mode shows local tenant; logout clears the key),
workspace icon strip retained (D25 shared list with Cmd-1..9).
- store: tasks = cross-project list via GET /api/conversations; openTask
switches project context; pin/archive optimistic + refresh; last
project context persisted; stale conversations field removed.
- tasklist.ts pure helpers + 6 vitest cases; npm run build passes;
headless walk on the real binary: cross-project open, pinned-first,
archive hide/show/restore, new-task flow, zero console errors.
Impact: ProjectNav removed; contracts.ts regenerated from core
(pinned/archived); no composer/right-pane changes (D25/D26/D31 intact).
Refs: Agent-System-Documents docs/proposals/2026-09-30-ui-redesign-and-auth.md
Why: during a run nothing was rendered (the assistant message only lands
at completion, so the LiveState projection never hit the screen), and
white-space:pre-wrap on .part-text turned marked's inter-block newlines
into blank lines, giving ordered lists a huge per-item gap. A latent
race also wiped thinking/tool/phase state that arrived before the send
POST resolved, and thinking text ran inline with the answer.
Evidence: headless playwright against the mock backend shows the live
bar, an expanded thinking panel, tool chips and incremental text with a
blinking cursor mid-run; list item gaps measure 2.1px with
white-space:normal; make test (frontend 9 tests) green.
Impact: users watch thinking, tool calls and the answer stream in real
time; markdown typography (lists, tables, quotes, headings) is compact;
terminal runs fold the process trail behind a summary.
Refs: feature/chat-live-quality task card.
Why: .chat is a column-flex item of .main without min-height:0, so its
content-based automatic minimum height grew past the viewport; .chat-body
never overflowed (never scrolled) and the input bar was pushed off-screen.
Evidence: headless Chromium on mock serve, 1024x620: before .chat=2130px
and input-bar bottom=717 (>viewport), chat-body scrollable=false; after
.chat=620, chat-body clientH 501 / scrollH 2011 with wheel scroll moving
600px up and back to bottom, input-bar bottom=620. Variants (empty
conversation, single short message, 1024x400, 720x600) keep the input
visible. Full combo make test green.
Impact: chat page was unusable beyond one screen of content; single CSS
rule chain, no behavior change elsewhere.
Refs: Agent-System-Dev task card feature/chat-scroll-fix.
Why: The schema renderer and design tokens moved to the new Agent-System-UI
repo (D29); Frontend becomes the first host consuming it through the @ui
source alias so future inbox/card/workspace components land in the shared
library instead of this repo.
Evidence: tsc+build clean with modules/ui materialized; vitest 9/9 pass;
combined CSS (tokens.css + ui.css + styles.css) verified rule-identical to
the pre-migration styles.css except comments and a collision-free block
relocation; doc-ref store access replaced by injected DocBridge at the two
call sites (plugin panels, card parts, HITL forms).
Impact: Requires sibling modules/ui checkout (Dev worktree provides it); vite
dedupe keeps single react/marked copies in the bundle.
Refs: Agent-System-Documents proposal 2026-09-30-ui-inbox-command-workspace (D29)
Details (original message):
Implement the three-column workbench frontend: resizable/collapsible nav with overshorthand collapse, streaming chat with part renderers and process collapse, HITL choice cards with impact display and free-input pivot, plan/todos/artifacts/agents tabs, subagent tracker modal, schema-driven settings center with effect badges and masked secrets, profile management with import/export, plugin panel rendering, doc viewer with edit-save; contract shape tests.
weichen
