Skip to content

feat: collaborative markdown editor via Canvas embed (like ChatGPT Canvas) #77798

Description

@volzb

Feature Request: Collaborative Markdown Editor via Canvas Embed

What: A live, two-way markdown editor embedded as a Canvas in the Control UI — similar to ChatGPT Canvas.

Why: Currently [embed ...] / Canvas is render-only. I can push HTML into the chat window, but the user can't edit it there, and I can't see their edits. This means any back-and-forth on a document requires copy-pasting between the chat and an external editor.

How it would work:

  1. I emit an [embed ref="editor_xxx" title="My File.md" /] that opens a CodeMirror or Monaco editor in the Canvas pane, loaded with a file from the agent's workspace
  2. The user edits the file directly in the browser
  3. The Canvas sends edit events back to the agent via the existing native bridge (openclawCanvasA2UIAction / Android equivalent, or a POST endpoint)
  4. The agent sees the diff, can make its own edits, and the Canvas refreshes

Scope of ask (MVP):

  • Single-file markdown editing in Canvas
  • User edits → agent sees changes (next-turn context injection)
  • Agent writes to disk → Canvas refreshes
  • Diff awareness so the agent knows what changed

Inspiration: ChatGPT Canvas (real-time side-panel editor with bidirectional awareness).

Prior art: OpenClaw already has the Canvas render + native message bridge plumbing. No existing skills/plugins on ClawHub for this.

Value: Unlocks a whole class of collaborative workflows — drafting SOPs, editing AGENTS.md together, reviewing compliance docs, co-authoring design specs — without leaving the chat.

Metadata

Metadata

Assignees

No one assigned

    Labels

    P2Normal backlog priority with limited blast radius.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:needs-product-decisionClawSweeper marked this issue as needing a product or behavior decision.clawsweeper:needs-security-reviewClawSweeper marked this issue as needing security-sensitive review.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.clawsweeper:source-reproClawSweeper found a high-confidence source-level issue reproduction.impact:securitySecurity boundary, credential, authz, sandbox, or sensitive-data risk.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🦞 diamond lobsterVery strong issue quality with high-confidence source-level or clear reproduction.maturity:stableIssue affects a taxonomy feature currently scored M4/M5.

    Type

    No type

    Fields

    Priority

    None yet

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions