Files
Claw3D/docs/whiteboard-spec.md
GordoCursor AgentLuke The DevElias PfefferClaude Sonnet 4.6copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>Greg Clarkiamlukethedev
4e552967d9 [PRIORITY][FEAT] merge runtime profiles, office systems, doctor, and vera lane convergence (#109)
* fix: include kanbanImmersive in immersiveOverlayActive calculation

When Kanban board is open, HUD elements (camera preset buttons, edit toolbar, overlays) should be suppressed. The kanbanImmersive flag was defined but not included in the immersiveOverlayActive condition, causing HUD elements to remain visible.

This fix adds kanbanImmersive to the immersiveOverlayActive calculation so HUD elements are properly hidden when the Kanban board is open.

Co-authored-by: Luke The Dev <iamlukethedev@users.noreply.github.com>

* Fix: Hide mini status bar when Kanban immersive overlay is open

Wraps the bottom-left mini status bar (showing agent stats, vibe score, and
control hints) with !immersiveOverlayActive check to match the behavior of
other HUD elements like camera controls and toolbar.

This ensures the status bar is properly hidden when the Kanban board or any
other immersive overlay is active, maintaining a clean immersive experience.

Co-authored-by: Luke The Dev <iamlukethedev@users.noreply.github.com>

* chore: drop unrelated package-lock line from branch

Co-authored-by: Luke The Dev <iamlukethedev@users.noreply.github.com>

* universal-backend-plan

* backend-neutral runtime seam

* package.json update

* feat: add Hermes gateway adapter as alternative to OpenClaw

Adds a WebSocket adapter that lets Claw3D connect to a Hermes AI agent
runtime without any changes to the frontend. The adapter implements the
full Claw3D gateway protocol and bridges it to the Hermes HTTP API.

Changes:
- server/hermes-gateway-adapter.js: WebSocket bridge implementing the
  Claw3D gateway protocol against the Hermes HTTP API. Supports all
  core methods (agents, sessions, chat streaming, cron, config, files,
  approvals) and multi-agent orchestration via spawn_agent/delegate_task
  tools. Persists conversation history to ~/.hermes/clawd3d-history.json.
- scripts/clawd3d-start.sh: All-in-one startup script that launches
  Hermes, the adapter, and the Next.js dev server with auto port
  conflict resolution. Alias as `claw3d` for convenience.
- src/features/office/hooks/useCronAgents.ts: Hook that polls the
  gateway for cron-scheduled agents and surfaces them in the 3D office.
- package.json: adds `hermes-adapter` npm script
- .env.example: documents Hermes config vars
- docs/hermes-gateway.md: setup guide and protocol reference

Usage:
  npm run hermes-adapter   # start adapter (connect to http://localhost:8642)
  npm run dev              # start Claw3D, point browser at localhost:3000
  # or: bash scripts/clawd3d-start.sh  (starts everything automatically)

Both OpenClaw and Hermes are supported simultaneously — the gateway URL
in NEXT_PUBLIC_GATEWAY_URL determines which backend Claw3D connects to.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat: add read_agent_context tool for cross-agent coordination

Agents can now read each other's conversation history via the
read_agent_context tool, enabling the orchestrator to check what
a sub-agent has done before re-delegating work.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat: wire Hermes office UX and role-aware runtime updates

* feature update - demomode & hermes adapter

* fix lint blockers

* lintfix #2

* fix: stabilize retro office camera preset callbacks

* Initial plan

* fix: stabilize retro office overview preset hooks

Agent-Logs-Url: https://github.com/gsknnft/Claw3D/sessions/9cc71555-591e-44cf-aec4-25affbdcb405

Co-authored-by: gsknnft <123185582+gsknnft@users.noreply.github.com>

* feat: add truthful backend selection, Hermes adapter hardening, and demo gateway mode

* fix: address bugbot review and finalize backend selection

* fixed - onboarding and hermes calls

* office systems roadmap

* feat specs in docs

* specs ready

* feat: continue custom runtime seam and gateway alignment

* custom lane wired

* feat: add custom runtime provider path and office runtime alignment

* office_sys prep

* tighten multi-floor runtime spec

* multi-floor v1 implementation

* moved floor nav

* runtime architecture specs

* claw3doctor specs

* feat: add first pass claw3doctor diagnostics

* docs: align roadmap with runtime profiles and office systems priorities

* feat: expand claw3doctor provider diagnostics and json output

* feat: improve claw3doctor formatting and multi-runtime diagnostics

* feat: formalize runtime profile resolution

* feat: expand claw3doctor profile health diagnostics

* feat: polish claw3doctor output and tunnel remediation

* feat: add claw3doctor profile scoping and failure classification

* docs: define claw3doctor v1 boundary and v2 backlog

* test: fix stale claw3doctor branch expectations

* test: fix stale expectations on claw3doctor branch

* fix(claw3doctor): scope provider-specific checks to --profile / --all-profiles flags

PR #101 finding:
- Medium: --profile <adapter> and --all-profiles only scoped the profile health
  probe loop; OpenClaw/Hermes/Demo/Custom check blocks still ran based on the
  selected adapter type in runtimeContext, making CLI output misleading.

Fix: introduce adapterInScope(adapterType, defaultBehavior) helper in main().
  - --profile <adapter>  -> only that adapter's checks run
  - --all-profiles       -> all adapter checks run
  - no flag              -> falls back to existing shouldRun* predicate (unchanged)

Also:
- Export parseDoctorArgs from claw3doctor-core.mjs (removed duplicate in script)
- Add test suites: parseDoctorArgs flag parsing (6 cases) and
  adapterInScope scoping semantics (4 cases) — 10 new tests, all green

* fix(office): persist per-floor selectedAgentId on focusLocalAgent + wire officeFloors runtime state

PR #96 findings:
- Medium #1: focusLocalAgent now writes selectedAgentId back to floorRosterCache
  so handleSelectFloor restores the agent the user last picked on each floor
  rather than snapping back to the hydration-time suggestion.
- Medium #2: Add useEffect that calls settingsCoordinator.schedulePatch with
  officeFloors[activeFloorId] patch on every status/gatewayUrl change, writing
  status, gatewayUrl, lastKnownGoodAt, lastErrorCode, and lastErrorMessage so
  the persisted floor runtime state actually tracks live connection transitions.

* fix unkept changes

* fix audit findings - cross-floor misattribution & officefloors silent drops

* pushed changes

* multi-agentic runtime & chat bubble fix

* partial parity with office-sys-next

* claw3doctor parity

* partial parity with v_lane

* merged feat/office-systems-next -> merge_sys

* parity across PR branches

* rm *.orig postmerge

* full parity across unmerged PRs & main

* fix lukes findings

* fix findings - bigger chatbox

* real local upload path

* fixed file upload, MIME integgration

* minor fix

* fix lukess findings

* deleted *.orig

* three bugs fixed - gatewayclient, coord, claw3doctor

* address findings

* fix lukes findings

* fix findings #2

* fix: ignore temporary skill-agent names during identity recovery

* fix: preserve stable identity names during temp-name recovery

* fix(gateway): correct disconnect race and token-blanking on adapter switch

- disconnect() now checks actual connection status rather than selectedAdapterType,
  which may already reflect the target adapter when the effect fires. Prevents stale
  WebSocket clients from persisting after switching to local/claw3d/custom backends.
- setSelectedAdapterType() falls back to loadedGatewaySettings.current.profiles token
  when the in-memory adapterProfiles entry has an empty token (sanitized API form).
  Prevents saved tokens from being cleared when switching between backends.

Closes Luke findings: High (stale gateway on floor switch), Medium (token blanking).

Authored-By: GSKNNFT

* feat(gateway): loopback bypass, control-ui remap, operator.read scope, 75ms connect

Cherry-picked clean additions from pr/gsknnft-2 (fix/reduce-gateway-connect-delay):

- proxy-url.ts: resolveStudioProxyGatewayUrl() now accepts optional upstreamGatewayUrl;
  loopback hosts (localhost/127.0.0.1/::1) bypass the Studio proxy and connect directly
- gateway-proxy.js: remap unauthenticated openclaw-control-ui connections to webchat-ui
  client ID so OpenClaw doesn't reject them as unknown clients
- GatewayBrowserClient.ts + nodeGatewayClient.ts: add operator.read scope to both
  browser and Node gateway clients for expanded access control
- GatewayBrowserClient.ts: reduce socket open→connect delay from 750ms to 75ms

GatewayClient.ts rewrites from that PR were intentionally excluded — they would
regress our disconnect-race fix, token-blanking fix, broken-regex fix, local/claw3d
adapter support, adapterProfiles type export, and private envelope path.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(floor-nav): show only available floors per active adapter; block hang on unconfigured runtime

- floors.ts: add paperclip to FloorProvider; add listAvailableFloorsForAdapter() —
  lobby always visible, runtime floors only shown when their provider matches the
  active adapter, so demo-only users only see Lobby
- OfficeFloorNav: accept activeAdapterType prop, filter floor list via
  listAvailableFloorsForAdapter(); fall back displayActiveFloorId to lobby if current
  floor is no longer in the available set
- OfficeScreen: pass selectedAdapterType to OfficeFloorNav; add guard in
  handleSelectFloor — bail back to lobby immediately when a runtime floor has no
  gateway URL configured, preventing the connect-hang limbo state

Authored-By: GSKNNFT

* hardening: drop unsafe-eval in production CSP; add TRUSTED_PROXY IP resolution

next.config.ts:
- unsafe-eval removed from production script-src (Next.js dev/HMR needs it, but
  production build does not; React and Three.js make no use of eval)
- connect-src intentionally kept broad with note: gateway URLs are user-configured
  at runtime, cannot be enumerated at build time

server/access-gate.js:
- Add resolveClientIp() helper: when TRUSTED_PROXY=1 env var is set, prefer the
  first value of X-Forwarded-For for rate-limiter keying (correct behavior behind
  nginx/Caddy/Vercel edge). Without the flag, remoteAddress is used (safe default
  for direct exposure — prevents X-Forwarded-For spoofing by untrusted clients).

Authored-By: GSKNNFT

* fix(security): remove upstream tokens from browser API; propagate abort to custom runtime

HIGH — /api/studio: strip gatewayPrivate and localGatewayDefaultsPrivate from GET and
PUT responses. Upstream tokens must not cross the browser API boundary. The Studio
proxy (server/gateway-proxy.js) already injects the server-side token into connect
frames when the browser sends an empty token, so the browser never needed raw tokens.
GatewayClient.ts and OfficeScreen.tsx updated to work from sanitized public settings only.

MEDIUM — /api/runtime/custom route: pass request.signal to the upstream fetch() call.
Client abort (e.g. hitting Stop) now cancels the upstream runtime request instead of
leaving it running after the browser fetch resolves.

Authored By: GSKNNFT

* fix(security): preserve stored token through empty-token UI state; handle non-JSON health responses

GatewayClient.ts — autosave effects no longer overwrite persisted gateway tokens with
empty strings. When the in-memory token is empty (proxy handles auth server-side),
the patch omits the token field (undefined) so mergeGatewaySettings/mergeGatewayProfiles
treats it as "leave unchanged". adapterProfiles updater also preserves the existing
stored token when the new token is empty, preventing floor-switch from erasing tokens.

runtime/custom/http.ts — requestCustomRuntime() checks the response Content-Type before
calling response.json(). Non-JSON responses (e.g. plain-text /health "OK") are returned
as-is instead of throwing a JSON parse error, making the custom/local/claw3d health
probe path reliable for runtimes that return plain text.

Authored By: GSKNNFT

* fix(bug): avoid overwriting stored tokens with an empty UI value

GatewayClient.ts:944 → token: "" || undefined = undefined → omitted from patch
mergeGatewayConnectionState: patch.token === undefined → patchedToken = undefined → nextToken = undefined || current?.token ?? "" = "abc123" ✓

scenarionn- user explicitly clears token (empty string patch):

mergeGatewayConnectionState: patchedToken = "" → nextToken = "" || current?.token ?? "" = falls back to existing stored token

Authored By: GSKNNFT

* fix ongoing findings issue

* test: update gateway connection persistence expectations

Co-authored-by: Luke The Dev <iamlukethedev@users.noreply.github.com>

* fix: tighten ts.net hostname matching in doctor

Co-authored-by: Luke The Dev <iamlukethedev@users.noreply.github.com>

* chore(release): prepare v0.1.4

Pin in-repo app version to 0.1.4 to match the planned GitHub release
tag, and document the convergence release in CHANGELOG.md with verified
0.1.3 and 0.1.4 entries covering runtime profiles, multi-floor offices,
remote messaging/handoffs, file uploads, security hardening, and the
claw3doctor diagnostics CLI.

Made-with: Cursor

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Luke The Dev <iamlukethedev@users.noreply.github.com>
Co-authored-by: Elias Pfeffer <eliaspfeffer@gmail.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Greg Clark <greg.clark@gmail.com>
Co-authored-by: iamlukethedev <lucas.guilherme@smartwayslfl.com>
2026-04-23 18:29:20 -05:00

9.4 KiB
Raw Permalink Blame History

Whiteboard Spec

Second concrete office-system feature for Claw3D, designed to work alongside the bulletin board.

Goal

Add a whiteboard system inside the office for collaborative planning, meeting notes, and draft idea shaping.

The whiteboard is where the office thinks.

The bulletin board is where the office posts what matters.

Product Position

The whiteboard should not duplicate the bulletin board.

Use the distinction:

  • bulletin board = visible office signals
  • whiteboard = active drafting and planning surface

The whiteboard is best for:

  • brainstorming
  • architecture outlines
  • meeting notes
  • draft task breakdowns
  • org planning
  • decision framing

It is not a Kanban replacement and not a polished document editor.

Why This Feature Matters

The office already has:

  • standup logic
  • meeting room space
  • whiteboard props in the retro office
  • task board and planning-adjacent systems

What is missing is a shared in-world planning surface.

The whiteboard creates that surface.

Primary Use Cases

Meeting Notes

Examples:

  • standup talking points
  • decisions made during a meeting
  • action items
  • unresolved questions

Brainstorming

Examples:

  • possible approaches to a feature
  • tradeoff comparisons
  • rough implementation ideas
  • product concept sketches in text form

Architecture Planning

Examples:

  • component breakdown
  • adapter/provider mapping
  • system boundaries
  • workflow diagrams in structured text

Org Planning

Examples:

  • team structure drafts
  • role definitions
  • department responsibilities
  • handoff chains

Session-to-Plan Bridge

Examples:

  • summarize an agent conversation into a board section
  • turn standup outputs into grouped notes
  • capture a working draft before turning it into bulletin board items or tasks

V1 Scope

V1 should be structured, not freehand.

That means:

  • text blocks
  • sections
  • cards / note clusters
  • ordering
  • lightweight templates

Do not start with arbitrary drawing tools.

Whiteboard Model

Suggested V1 shape:

type WhiteboardBlockType =
  | "heading"
  | "note"
  | "decision"
  | "question"
  | "action"
  | "group";

type WhiteboardBlock = {
  id: string;
  type: WhiteboardBlockType;
  title?: string;
  body?: string;
  createdAt: string;
  updatedAt: string;
  authorType: "human" | "agent" | "system";
  authorId?: string | null;
  authorName?: string | null;
  linkedAgentId?: string | null;
  linkedSessionKey?: string | null;
  linkedTaskId?: string | null;
  color?: string | null;
  collapsed?: boolean;
};

type WhiteboardDocument = {
  id: string;
  title: string;
  mode: "planning" | "meeting" | "architecture" | "org" | "freeform";
  createdAt: string;
  updatedAt: string;
  archived: boolean;
  blocks: WhiteboardBlock[];
};

V1 Interaction Model

V1 interactions:

  • create whiteboard
  • rename whiteboard
  • add/edit/delete blocks
  • reorder blocks
  • collapse/expand groups
  • link a block to an agent, task, or session
  • archive whiteboard
  • duplicate whiteboard

Optional but useful:

  • convert a block into a bulletin-board card
  • convert a block into a task seed

Templates

Templates are important because they make the feature useful immediately.

Recommended V1 templates:

  • Meeting Notes
  • Standup Review
  • Planning Session
  • Architecture Draft
  • Org Planning

Example: Meeting Notes Template

Sections:

  • attendees
  • current topic
  • decisions
  • blockers
  • next actions

Example: Planning Session Template

Sections:

  • problem
  • options
  • risks
  • chosen direction
  • tasks

Relationship To Existing Systems

The whiteboard should integrate with what Claw3D already has.

Standup

The standup controller already exists.

The whiteboard should support:

  • auto-creating a meeting notes board for an active standup
  • writing participant summaries to blocks
  • collecting blockers and next actions into dedicated sections

Bulletin Board

The whiteboard should feed the bulletin board, not replace it.

Examples:

  • convert a decision block into an announcement card
  • convert a blocker block into a blocker card
  • convert a next-action block into a handoff card

Task Board / Kanban

The whiteboard is where a plan is shaped before it becomes a tracked workflow.

Examples:

  • rough task breakdown on whiteboard
  • selected action blocks converted into actual task records
  • blocked tasks reflected back to the bulletin board

Company Builder / Org Planning

The whiteboard is a natural fit for:

  • team structure drafts
  • department planning
  • role relationship mapping

This is especially useful before company-builder output becomes actual agents.

In-World UX

The whiteboard should exist as a real office surface.

Recommended forms:

  • meeting-room whiteboard
  • wall-mounted planning board
  • design room / architecture board in future themes

Behavior:

  • clicking the board opens an immersive planning surface
  • active meetings can auto-focus or highlight the whiteboard
  • whiteboard state should feel like part of the room, not a random modal

Sidebar / Secondary Access

The user should also be able to open the whiteboard from a panel or shortcut.

Good options:

  • HQ sidebar tab
  • meeting controls
  • standup panel

This is especially important when users want direct access without camera movement.

Storage Model

Like the bulletin board, V1 should be persisted locally in office preferences.

Suggested shape:

type OfficePreference = {
  whiteboards?: {
    documents: WhiteboardDocument[];
    activeDocumentId?: string | null;
    updatedAt?: string;
  };
};

Storage should be keyed by gateway URL / office context so each connected office can keep its own working state.

JSON Canvas Compatibility

JSON Canvas is a good interoperability target for the whiteboard, but it should not define the product by itself.

Recommended stance:

  • use Claw3D's own whiteboard model as the primary domain model
  • support export/import to JSON Canvas as a compatibility layer
  • avoid turning the whiteboard into a generic infinite-canvas editor before the office workflow is proven

Why:

  • Claw3D needs stronger links to meetings, bulletin board items, tasks, agents, and sessions
  • the whiteboard is a workflow surface, not only a canvas
  • structured planning is more important than unconstrained canvas freedom in V1

Good use of JSON Canvas:

  • export planning boards
  • import external draft canvases
  • map blocks/groups into JSON Canvas nodes
  • preserve links where practical

Bad use of JSON Canvas:

  • letting a generic canvas model dictate the first product UX
  • replacing office-native planning behavior with a broad but shallow editor

Authoring Rules

Allowed authors:

  • human
  • agent
  • system

Recommended behavior:

  • human edits are fully editable
  • system-generated sections should remain editable but visibly marked
  • agent-authored blocks should show provenance

That balance keeps the board useful without feeling rigid.

V1 Automation

Useful automations:

  • create a whiteboard automatically when a standup meeting starts
  • seed a whiteboard from a planning command or meeting ritual
  • let an agent summarize a session into selected board blocks

Important:

  • automation should create structure, not spam content
  • the user should remain able to edit the board freely

Visual Structure

V1 should look like a structured planning board, not a blank canvas.

Possible presentation:

  • left column for sections
  • center canvas for block editing
  • right rail for linked agents/sessions/tasks

Or:

  • grouped lanes by section with text cards inside them

The design should prioritize clarity over novelty.

Out of Scope For V1

Do not include these initially:

  • freehand drawing tools
  • multiplayer cursor presence
  • arbitrary shapes/connectors
  • full diagramming toolkit
  • external document sync
  • rich media embedding
  • advanced permissions by department

Those can come later if the structured board proves valuable.

Implementation Strategy

Recommended order:

  1. Define whiteboard document and block schema.
  2. Add office preference persistence.
  3. Build a simple whiteboard panel UI with templates.
  4. Connect the in-world whiteboard object to open the panel.
  5. Add standup seeding / meeting integration.
  6. Add conversions into bulletin-board cards and task seeds.

Existing Code Seams

This feature should align with:

  • standup systems in src/features/office/hooks/useOfficeStandupController.ts
  • standup API routes under src/app/api/office/standup
  • retro office whiteboard objects and room interactions
  • office settings persistence
  • task board seeding concepts already present in office task flows

This reduces implementation risk and keeps the feature tied to real office mechanics.

Success Criteria

V1 is successful if:

  • the user can open a whiteboard from inside the office
  • a meeting or planning session can write structured notes to it
  • the board can link to agents, sessions, and tasks
  • users can turn whiteboard outputs into bulletin board items or task seeds
  • the system works independently of OpenClaw-specific behavior

Future Extensions

Once V1 is working, the whiteboard can evolve into:

  • diagram mode
  • relationship mapping
  • architecture views
  • agent collaboration sessions
  • department-specific whiteboards
  • persistent planning archives
  • richer visual theming by office skin

Summary

The whiteboard should become Claw3Ds active planning surface.

It is where meetings, drafts, and rough plans take shape before they become tasks, bulletin items, or office decisions.