* 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>
8.5 KiB
Meeting Room Workflow Spec
Third concrete office-system feature for Claw3D, building on existing standup support and extending it into a generalized meeting workflow model.
Goal
Turn the meeting room from a visual location into an operational workflow surface.
The meeting room should become the place where agents:
- gather
- present updates
- coordinate plans
- resolve blockers
- record decisions
- create follow-up actions
Product Position
The meeting room is not just a room.
It is a workflow type.
That means the system should support:
- visible in-world gathering
- structured meeting phases
- meeting outputs that affect the rest of the office
It should connect naturally to:
- standup
- whiteboard
- bulletin board
- task board
- QA/review systems later
Existing Foundation
Claw3D already has meaningful meeting-related pieces:
- a meeting room in the office layout
- standup meeting state and API routes
- participant arrival handling
- immersive standup board UI
- agent movement into the meeting area
This spec should treat standup as the first implemented meeting type, not as a special one-off.
Core Principle
Meetings should generate office state, not just temporary visuals.
Every meeting should be able to produce:
- summaries
- decisions
- blockers
- next actions
- linked whiteboard notes
- linked bulletin board items
That is what makes the office feel alive and useful.
Meeting Types
Recommended initial types:
standupplanningreviewincidentsync
Standup
Purpose:
- what each agent is working on
- blockers
- immediate next step visibility
Planning
Purpose:
- define approach
- compare options
- assign next actions
Review
Purpose:
- assess work completed
- gather feedback
- approve or reject next move
Incident
Purpose:
- coordinate under failure or urgency
- assign responsibilities
- capture current status and recovery path
Sync
Purpose:
- lightweight multi-agent coordination
- brief handoffs
- cross-team visibility
Workflow Model
Each meeting should have explicit phases.
Suggested phases:
scheduledgatheringin_progressdecisioncompletearchived
Scheduled
Meeting exists but has not started.
Gathering
Agents are walking to the meeting room or otherwise being assembled.
In Progress
Updates are being presented, questions asked, and information collected.
Decision
The meeting is converging:
- decisions recorded
- unresolved blockers identified
- next actions prepared
Complete
The outputs are finalized and written back into office systems.
Archived
Meeting is preserved in history but no longer active.
Suggested Data Model
V1 generalized meeting shape:
type MeetingType =
| "standup"
| "planning"
| "review"
| "incident"
| "sync";
type MeetingPhase =
| "scheduled"
| "gathering"
| "in_progress"
| "decision"
| "complete"
| "archived";
type MeetingActionItem = {
id: string;
text: string;
assignedAgentId?: string | null;
linkedTaskId?: string | null;
status: "open" | "done" | "dropped";
};
type MeetingDecision = {
id: string;
text: string;
authorType: "human" | "agent" | "system";
authorId?: string | null;
};
type OfficeMeeting = {
id: string;
type: MeetingType;
phase: MeetingPhase;
title: string;
startedAt?: string | null;
updatedAt: string;
participantAgentIds: string[];
arrivedAgentIds: string[];
currentSpeakerAgentId?: string | null;
summary?: string | null;
blockers: string[];
decisions: MeetingDecision[];
actionItems: MeetingActionItem[];
whiteboardDocumentId?: string | null;
bulletinCardIds?: string[];
};
Relationship To Standup
The current standup system should become the first meeting implementation under this model.
That means:
- keep standup behavior working
- preserve arrival and speaker sequencing
- treat standup as a specialized meeting workflow
- reuse the immersive standup screen as the first meeting immersive view
In practice:
- standup =
MeetingType: standup - existing standup cards become structured meeting inputs
- standup completion should emit durable outputs into whiteboard and bulletin board systems
Whiteboard Integration
Every meaningful meeting should have a whiteboard relationship.
Possible behaviors:
- auto-create whiteboard document when meeting starts
- write summary sections as the meeting progresses
- capture blockers, decisions, and next actions into whiteboard blocks
Suggested mapping:
- meeting discussion -> whiteboard notes
- decisions -> whiteboard decision blocks
- next actions -> whiteboard action blocks
The whiteboard is the drafting surface during the meeting.
Bulletin Board Integration
The bulletin board is the public output surface after the meeting.
Suggested mapping:
- important decision -> announcement card
- blocker -> blocker card
- action item with office-wide significance -> handoff card
- meeting completion -> meeting note card
The meeting room should feed the bulletin board, not bypass it.
Task Board Integration
Meetings should be able to seed or update tasks.
Examples:
- planning meeting creates task candidates
- review meeting marks work ready for QA
- incident meeting creates urgent recovery tasks
The task board remains the detailed execution layer.
The meeting room creates and updates intent.
Human Interaction Model
The human should be able to:
- start a meeting
- pick meeting type
- pick participants
- follow progress
- intervene during the meeting
- edit outcomes
- confirm or reject generated next steps
The user should not lose control over the outputs just because the meeting is agent-driven.
Agent Interaction Model
Agents should be able to:
- gather into the meeting room
- take speaking turns
- surface blockers
- suggest next steps
- add whiteboard content
- create meeting-derived outputs when allowed
Longer term, hierarchy may affect who can:
- call meetings
- approve decisions
- assign action items
Visual / Spatial Behavior
The meeting room should visibly change state during active meetings.
Possible signals:
- agents walk to seats
- current speaker highlighting
- board auto-opens or highlights
- room status banner
- meeting timer / phase indicator
The office should make it obvious that something coordinated is happening.
V1 Scope
V1 should focus on turning standup into the first generalized meeting flow.
Recommended V1 scope:
- meeting type abstraction for standup
- whiteboard output on meeting completion
- bulletin board output on meeting completion
- simple action-item capture
- immersive meeting screen improvements
Do not try to build all meeting types at once.
Out of Scope For V1
- voice/video simulation
- arbitrary meeting transcripts
- real-time collaborative editing by many actors at once
- department-specific meeting policies
- advanced approval chains
- multiplayer human facilitation
Implementation Strategy
Recommended order:
- Generalize standup data model into a broader meeting model.
- Keep standup UI working on top of that generalized model.
- Add whiteboard document creation/output for completed meetings.
- Add bulletin board output for decisions and blockers.
- Add action item seeding into task workflows.
- Introduce second meeting type, likely
planning.
Existing Code Seams
This work should likely align with:
src/features/office/hooks/useOfficeStandupController.tssrc/features/office/screens/StandupImmersiveScreen.tsxsrc/app/api/office/standup/*- retro office meeting-room positioning and agent movement
- office state persistence
This is important because Claw3D already has the skeleton of a meeting system.
The right path is to extend it, not replace it.
Success Criteria
V1 is successful if:
- standup remains functional
- standup now behaves like the first generalized meeting workflow
- meeting completion can write useful results into whiteboard and bulletin board systems
- users can see meeting outcomes affect the rest of the office
- the system remains backend-neutral
Future Extensions
Once the workflow model is stable, follow-up work can add:
- planning meetings
- review meetings
- incident rooms
- hierarchy-aware meeting permissions
- department-specific meeting rituals
- richer meeting summaries and archives
Summary
The meeting room should become the office’s coordination engine.
Standup is the starting point, but the real goal is a general workflow where meetings create durable plans, blockers, decisions, and next actions that shape the whole office.