pmx-canvas 0.7.3 → 0.8.2

package/skills/pmx-canvas/SKILL.md

@@ -20,8 +20,20 @@ At the start of board work, read `canvas://context?consumer=<stable-unique-id>`
 (or `canvas_query { action: "context", consumer: "<stable-unique-id>" }`) before
 falling back to broader resources. The budget is UTF-16 code units, not tokens.
 Use one stable consumer ID per agent/adapter only when durable deltas are wanted;
-omit it for a fresh read. Pins are highest priority. If a source card is clipped,
-pull that card explicitly by its returned board/card IDs.
+omit it for a fresh read. Pins are highest priority, then the cards near each pin
+(reason `near`, title + short summary only). If a source card is clipped or near,
+pull that card explicitly with `canvas_node { action: "get", board, id, full: true }`.
+
+**Read → check → refresh:** after reading context, inspect `canvas_ax_timeline {
+action: "read-status", board }`. No entry means no recorded content delivery;
+`readRevision < contentRevision` on the current card means changed since read.
+Re-read that card with `full: true`, then check status again before acting on it.
+Full HTTP/CLI node reads and SDK `getNode` also record the delivered revision;
+compact MCP metadata, CLI `--summary`/`--field`, and workbench reads do not.
+Compact MCP responses that contain text (such as Markdown) do count as delivery.
+In 0.8.0, direct node gets were untracked; use a context read on that version.
+A read mark proves delivery, not understanding or approval. Agent attribution
+describes who acted; it never grants permission or wakes an idle agent.
 
 When authoring a board, establish its README without waiting for the human to
 click a button. Read `canvas_board { action: "get" }`; if `readmeNodeId` is null,
@@ -43,7 +55,7 @@ for the authoritative stop, viewport, persistence, reset, group-order, and captu
 
 ## Runtime prerequisites
 
-PMX Canvas 0.7.3 requires **Bun >=1.4.2**, including when installed through npm.
+PMX Canvas 0.8.2 requires **Bun >=1.4.2**, including when installed through npm.
 Check `bun --version` and ensure Bun is on the MCP host's PATH, not just your shell's;
 use an absolute executable path if needed. Install/configure only when requested.
 For pinned installation, MCP configuration, managed services, and disposable verification,
@@ -116,7 +128,8 @@ the served catalog is a startup snapshot. Local mirrors still use `skills sync`
    `canvas_view { action: "fit", nodeIds: [...] }` with exactly the new ids. See
    **In-View Placement & Sizing** below — auto-placement is board-relative, not camera-relative.
 8. **Verify context pins.** Pin with `canvas_pin_nodes` or the browser's **Pin as context**, then
-   read `canvas://pinned-context`.
+   read `canvas://pinned-context`. When you pin, pass a short `reason` — the human sees who pinned a
+   node and why.
 9. **Clean up temporary nodes.** Remove retry/test fixtures and restore the baseline snapshot when
    the task requires leaving the board unchanged.
 
@@ -219,7 +232,7 @@ always authoritative, independent of the installed release version.
 | `canvas_ax_state` | `get`, `set-focus`, `set-policy`, `report-capability`, `presence`, `set-presence` |
 | `canvas_ax_work` | `add`, `update`, `annotate` |
 | `canvas_ax_gate` | `request`, `resolve`, `await` with `approval`, `elicitation`, or `mode` |
-| `canvas_ax_timeline` | `read`, `record-event`, `add-evidence`, `send-steering`, `reads` |
+| `canvas_ax_timeline` | `read`, `record-event`, `add-evidence`, `send-steering`, `reads`, `read-status` |
 | `canvas_ax_delivery` | `claim`, `mark` |
 | `canvas_board` | `list`, `get`, `create`, `create-from`, `open`, `update` |
 | `canvas_snapshot` | `save`, `list`, `restore`, `delete`, `gc`, `diff` |
@@ -303,8 +316,9 @@ reports any node below its floor as an advisory `sizeWarnings` entry — treat a
 as layout work left to do.
 Creation responses may include `sizeAdjustment` (`defaulted`, `clamped-to-minimum`, or
 `fit-to-children`); use its `applied` geometry rather than assuming the request won. Json-render
-validation/creation may also return warnings for form controls whose value is not bound with
-`$bindState`; the panel can render, but edits do not update its runtime state until the binding is fixed.
+validation/creation binds a literal form-control `value` to `state.form` automatically; it still
+warns for `$state` expressions, controls inside a repeat, or a non-object `state.form`, which render
+but do not update runtime state until bound with `$bindState`/`$bindItem`.
 Bound JSON input and dynamic lists are local UI state, not saved canvas data. Focus-mode
 expand/close preserves that state for the same spec in the current tab; an authored spec update,
 board switch or page reload resets it. Persist important edits explicitly through the app's
@@ -379,6 +393,12 @@ What the session asks of you:
   `agentId` values are for actual independent subagents, not steps in one chat. Attaching over a
   non-empty board saved a `Before session · …` snapshot; detaching emits the receipt (items
   done / vetoed, a diff against that snapshot, one-click restore) — an idle timeout delays it.
+- **Inspect receipt touch rows:** Read lists delivered content, Pinned lists pins, and
+  Created/Edited come from the session snapshot diff. Creating then editing one card puts
+  it in Created, not both rows. A stale warning means the pin changed after its read.
+  For example, after reading A, editing existing B and creating C, use **Dim untouched
+  nodes** to fade an untouched D to 0.35 opacity; A/B/C remain visible. The lens changes
+  presentation, not content, pin membership, approval or delivery.
 - **403 = outside the scope fence.** The human may fence you to a region (`policy.scope`): writes
   outside it are refused with a reason naming the node or position (a fenced group frame
   grants its members too). Read `policy.scope` in `canvas://ax-context`, ask the human to widen
@@ -440,7 +460,7 @@ Use the visible workbench when the human is actively curating layout:
   carries the tools (Select V, Pan Space, Connect C), Markdown note M, Attach files, webpage W,
   group G, and separate Draw A, Text note and Eraser buttons for board feedback,
   and utilities: search & commands (Cmd+K — actions with shortcuts, then jump-to-node), arrange,
-  trace, minimap, history, the theme picker (nine themes: dark, light, high-contrast, midnight,
+  trace, minimap, history, the theme picker (nine themes: harbor, daylight, high-contrast, midnight,
   sepia, arctic, ember, forest, volt), and shortcuts (?). The top bar holds the connection dot,
   workspace title, the session chip / gate badge / context meter while a session is attached
   (or the external-writers indicator and *Start agent session* otherwise), and the zoom cluster
@@ -456,7 +476,7 @@ Use the visible workbench when the human is actively curating layout:
 - Embedding hosts can open `/workbench?theme=<name>` (or `?theme=auto` to follow the host's
   light/dark appearance) for a session-local default theme that never changes the server-global
   theme other clients see; an explicit pick from the theme menu ends the override. The bundled
-  Copilot extension opens its panel with `?theme=light`.
+  Copilot extension opens its panel with `?theme=daylight`.
 
 After changing files under `src/client/`, rebuild with `bun run build` before manual browser
 verification.

package/skills/pmx-canvas/evals/evals.json

@@ -772,6 +772,68 @@
           "type": "output_check"
         }
       ]
+    },
+    {
+      "id": 32,
+      "name": "read-refresh-and-receipt-loop",
+      "prompt": "On a disposable board, pin A and B. Read A, then let the human edit it. Refresh only A before acting. Read nearby card C's source too. End your self-owned session after editing existing D and creating then editing E. Explain the receipt and dim untouched F. Does a read badge mean you understood or approved the content?",
+      "expected_output": "Uses a stable consumer for context and checks read-status. Fetches stale A and nearby C with canvas_node get full:true; compares recorded and current content revisions, leaving B unread unless actually delivered. Explains compact metadata/CLI projections do not record full delivery and 0.8.0 direct gets were untracked. Receipt Read/Pinned are descriptive, D is Edited, E is Created only; untouched F dims. Does not equate attribution or delivery with approval, understanding or idle wakeup.",
+      "assertions": [
+        {
+          "name": "refreshes-exact-stale-source",
+          "description": "Checks revisions, fetches full A/C by board and node ID, verifies refreshed status, and does not falsely claim unrelated B was read",
+          "type": "output_check"
+        },
+        {
+          "name": "explains-receipt-without-authority",
+          "description": "Distinguishes Created from Edited, verifies an untouched lens control, and calls reads delivery evidence rather than understanding, approval or wakeup",
+          "type": "output_check"
+        }
+      ]
+    },
+    {
+      "id": 33,
+      "name": "first-entry-header-targets",
+      "prompt": "Verify Expand and Add to context on a disposable card by moving directly from outside to each at-rest button coordinate. A prior release shifted controls on hover and sometimes deleted cards. Is a successful keyboard Enter enough to close this bug?",
+      "expected_output": "Measures at-rest targets before hover, clicks those original coordinates on first entry, and checks expansion/pin state plus retained node identity. Includes keyboard activation only as a control, not pointer proof. Uses Undo if a test-owned card is accidentally deleted and retains failure evidence.",
+      "assertions": [
+        {
+          "name": "tests-real-first-entry-pointer",
+          "description": "Uses original at-rest coordinates, confirms intended action and no deletion, and does not substitute pre-hover or keyboard-only success",
+          "type": "output_check"
+        }
+      ]
+    },
+    {
+      "id": 34,
+      "name": "spec-only-title-preservation",
+      "prompt": "Create a JSON card titled Protected custom title whose spec heading is Different heading. Replace only its spec with a New heading, then explicitly rename it. What should happen to its title and local form draft?",
+      "expected_output": "Verifies spec-only replacement preserves Protected custom title, explicit rename changes it, and authored spec replacement resets local runtime state. On old 0.8.0, includes the existing title as a workaround rather than silently accepting inferred renaming.",
+      "assertions": [
+        {
+          "name": "checks-independent-title-and-spec",
+          "description": "Uses distinct custom/inferred names, checks spec-only preservation and explicit rename, and distinguishes runtime reset from title loss",
+          "type": "output_check"
+        }
+      ]
+    },
+    {
+      "id": 35,
+      "name": "late-html-ax-enable",
+      "prompt": "Mount an HTML form with AX disabled, then enable ax.work.create without changing its HTML. Exercise enable, disable, re-enable and allowed-action changes in src and srcdoc. Can we preserve unsaved iframe drafts or claim that a queued steer wakes an idle agent?",
+      "expected_output": "Saves important local data before capability changes, which reload the HTML document. Waits for bridge bootstrap, exercises the action and verifies acknowledgement plus persisted work, and checks denial while disabled or not allowed. Tests both modes rather than using focus-mode remount as proof. Describes 0.8.0's workaround separately; no idle-wakeup claim.",
+      "assertions": [
+        {
+          "name": "verifies-mounted-capability-lifecycle",
+          "description": "Tests both embed modes on the mounted card, checks permitted and forbidden effects, and verifies real persistence rather than just bridge presence",
+          "type": "output_check"
+        },
+        {
+          "name": "respects-draft-and-delivery-boundaries",
+          "description": "Warns capability changes reload local drafts, preserves important data beforehand, and distinguishes queued steering from host delivery",
+          "type": "output_check"
+        }
+      ]
     }
   ]
 }

package/skills/pmx-canvas/references/ax-html-control-surface.md

@@ -24,6 +24,12 @@ Without `axCapabilities.enabled = true`, `window.PMX_AX` is **not** injected —
 renders but can't emit. `allowed` narrows what it may emit (never escalates the type's
 ceiling). Flip an existing node on with `canvas_node({ action: "update", id, axCapabilities: { enabled: true, allowed: [...] } })`.
 
+Changing effective capabilities reloads the mounted HTML document in both `src` and
+`srcdoc` modes, including disable/re-enable and allowed-action changes. Unsaved iframe-local
+drafts reset: save important state through durable AX primitives before changing capabilities.
+Wait for the new document, invoke the action, and verify both its acknowledgement and persisted
+result. On 0.8.0, late enabling required a deliberate remount; upgrading fixes that missing bridge.
+
 ## Three footguns (this is why a hand-rolled node looks "inert")
 
 1. **The iframe is sandboxed opaque-origin** (no `allow-same-origin`). `localStorage`,

package/skills/pmx-canvas/references/full-reference.md

@@ -128,11 +128,11 @@ pmx-canvas                     # Start and open browser (port 4313)
 pmx-canvas --no-open           # Start without opening browser (for agents)
 pmx-canvas --port=8080         # Custom port
 pmx-canvas --demo              # Start with sample content
-pmx-canvas --theme=light       # Light theme
+pmx-canvas --theme=daylight    # Daylight theme
 pmx-canvas --version           # Print installed version and exit
 ```
 
-`--theme` accepts `dark` (default), `light`, `high-contrast`, `midnight`, `sepia`, `arctic`, `ember`, `forest`, or `volt` (0.4.x; the rail's theme picker lists the same nine). Same value can be set via
+`--theme` accepts `harbor` (default), `daylight`, `high-contrast`, `midnight`, `sepia`, `arctic`, `ember`, `forest`, or `volt` (0.4.x; the rail's theme picker lists the same nine). Same value can be set via
 the `PMX_CANVAS_THEME` environment variable, or picked live from the left tool rail.
 
 Start the canvas once per session, then reuse it. Use `--no-open` when running as an agent — the
@@ -452,7 +452,7 @@ single-purpose tools behind an `action` (and, for `canvas_ax_gate`, a `kind`) di
 | `canvas_ax_state` | `get` · `set-focus` · `set-policy` · `report-capability` · `presence` · `set-presence` | Read AX state; set AX focus; patch tool/prompt policy (the scope fence is human-set, read-only here); report host capability; read / set agent presence (phase, cursor, focus, attached session) |
 | `canvas_ax_work` | `add` · `update` · `annotate` | Canvas-bound work items + review annotations |
 | `canvas_ax_gate` | `request` · `resolve` · `await` × `kind` `approval` \| `elicitation` \| `mode` | Attributed gate lifecycle (request → await → resolve); attribution does not itself grant authority |
-| `canvas_ax_timeline` | `read` · `record-event` · `add-evidence` · `send-steering` · `reads` | The bounded AX diagnostics timeline, and the context read log (`reads`) |
+| `canvas_ax_timeline` | `read` · `record-event` · `add-evidence` · `send-steering` · `reads` · `read-status` | The bounded AX diagnostics timeline, and the context read log (`reads`) |
 | `canvas_ax_delivery` | `claim` · `mark` | Adapterless steering delivery (claim → act → mark) |
 | `canvas_intent` | `signal` · `update` · `clear` | Ghost Cursor of Intent — announce a move before making it |
 
@@ -508,7 +508,7 @@ coming and can veto it mid-thought. Intents are ephemeral presence: never
 persisted, auto-expiring (~8s), never in `canvas_query layout`.
 
 Narrate → linked mutation → automatic settle:
-1. `canvas_intent { action: "signal", kind: "create", position: { x, y }, nodeType: "markdown", label: "Add evidence", reason: "capturing the failing test", confidence: 0.8 }` → returns `intent.id`.
+1. `canvas_intent { action: "signal", kind: "create", nodeType: "markdown", label: "Add evidence", reason: "capturing the failing test", confidence: 0.8 }` → returns `intent.id` and the `position` the canvas chose.
 2. Make the real move and pass that id: `canvas_node { action: "add", intentId: <intent.id>, ... }`.
 3. PMX rejects the mutation if the intent was vetoed or expired; otherwise the
    successful mutation settles the ghost into the resulting node automatically.
@@ -522,9 +522,13 @@ mcp-app) and `canvas_webview` do **not** accept an `intentId` and reject it with
 400 — to telegraph one of those, signal a ghost, then `clear` it (or let it
 expire) and run the open *without* an `intentId`.
 
-Per kind, pass the anchor it renders against: `position` for `create`/`move`,
-`nodeId` for `move`/`edit`/`remove`, `edge: { from, to, type }` for `connect`. The
-payoff is **legibility** — `reason` is shown beneath the ghost.
+Per kind, pass the anchor it renders against: `position` for `move` (optional for
+`create`), `nodeId` for `move`/`edit`/`remove`, `edge: { from, to, type }` for
+`connect`. **Omit `position` on a create unless you know where the node goes:** the
+canvas then forms the ghost where it will auto-place the node, keeps staged ghosts
+from stacking, and lands the linked create on its ghost. Never pass a placeholder
+such as `{ x: 0, y: 0 }`. The payoff is **legibility** — `reason` is shown beneath
+the ghost.
 
 **When to use vs skip.** Signal for adds, removes, and moves of visible nodes;
 connecting nodes; creating groups; layout reorganizations; meaningful title/content

package/skills/pmx-canvas/references/github-copilot-app-adapter.md

@@ -4,6 +4,10 @@ Use this reference when PMX Canvas is running inside the GitHub Copilot app as a
 extension. The adapter is intentionally thin: PMX Canvas remains the state owner, and the extension
 maps Copilot SDK features onto PMX AX primitives.
 
+The [standalone agent plugin](../../../docs/agent-plugin.md) bundles this adapter and PMX's
+MCP launcher. Its native canvas is Copilot-only; other Agent Plugins-compatible clients use
+the portable MCP tools and browser workbench.
+
 ## Adapter Identity
 
 - Extension path: `.github/extensions/pmx-canvas/extension.mjs`
@@ -17,9 +21,9 @@ maps Copilot SDK features onto PMX AX primitives.
    packaged extension directory into the repository:
    `mkdir -p .github/extensions && cp -R node_modules/pmx-canvas/.github/extensions/pmx-canvas .github/extensions/`
 2. Reload Copilot app extensions with `extensions_reload` so `project:pmx-canvas` is registered.
-3. Start or confirm a PMX Canvas daemon for the workspace: `pmx-canvas serve --daemon`
-   and `pmx-canvas serve status`. The adapter can auto-start in many local sessions, but a running
-   daemon is the most reliable setup for fresh agents.
+3. The adapter discovers a matching workspace daemon or starts the pinned package version
+   in `runtime.json` with Bun. It needs Bun on `PATH`, not a global `pmx-canvas` executable.
+   The shared daemon stays running when the extension exits.
 4. Open the canvas with `extensionId: "project:pmx-canvas"`, `canvasId: "pmx-canvas"`, and a stable
    `instanceId`.
 5. If the first `invoke_canvas_action` immediately after `open_canvas` returns
@@ -66,6 +70,8 @@ end it after each task. Explicit agent IDs are reserved for genuinely independen
   The Copilot app webview can leave nested `srcdoc` and `blob:` iframes blank, so PMX should route
   generated frame HTML through `/api/canvas/frame-documents/...` instead.
 - Connects to a matching local PMX server for the current workspace, or starts one when needed.
+- Uses the session's working directory for startup, context, presence, and steering; Copilot's
+  `workspacePath` points to session artifacts and is not the project root.
 - Reads `/api/canvas/ax/context` and injects pinned/focused context from
   `onUserPromptSubmitted`.
 - Exposes adapter actions for status, AX context refresh, AX focus, and explicit session steering.
@@ -137,16 +143,22 @@ All fields are optional:
 }
 ```
 
-Default discovery order:
+Default discovery:
 
-1. `serverUrl` input.
-2. `PMX_CANVAS_URL`.
-3. `PMX_CANVAS_PORT` / `PMX_WEB_CANVAS_PORT` / `4313` on loopback.
-4. Managed server startup for the current workspace when `autoStart` is not `false`.
+1. An explicit `serverUrl` input or `PMX_CANVAS_URL`, without silently choosing another target.
+2. Workspace daemon pid-file ports, the preferred `PMX_CANVAS_PORT` / `PMX_WEB_CANVAS_PORT`,
+   and the normal MCP fallback ports, verified against the workspace's real path.
+3. Serialized daemon startup for the session working directory when `autoStart` is not `false`.
 
 The adapter rejects an unrelated running PMX server unless `allowWorkspaceMismatch` is true,
 including when `serverUrl` is explicit.
 
+To package this adapter in another plugin, copy `extension.mjs`, `steering-delivery.mjs`,
+`runtime.mjs`, and `runtime.json`. For the portable MCP connector, also copy `start-mcp.mjs`,
+`tools.json`, and `THIRD_PARTY_LICENSES.txt`, and invoke `start-mcp.mjs` with Bun. The agent calls
+`canvas_connect_workspace` with its absolute project directory before using board tools;
+plugin initialization must never adopt the installation directory as a project.
+
 If discovery fails, the panel shows a connection page, not a partial workbench. It checks the
 original target automatically; **Check connection** retries immediately and **Start server**
 explicitly allows local startup even if `autoStart` was disabled. After recovery it navigates

package/skills/pmx-canvas/references/installing-pmx-canvas.md

@@ -4,7 +4,7 @@ Use this reference when the `pmx-canvas` skill is installed but the `pmx-canvas`
 
 ## Prerequisites and version
 
-The examples pin **PMX Canvas 0.7.3**, which requires **Bun >=1.4.2** even when
+The examples pin **PMX Canvas 0.8.2**, which requires **Bun >=1.4.2** even when
 installed through npm: the CLI runs through Bun, not Node. Check `bun --version`
 first. If missing or older, follow the [Bun installation instructions](https://bun.sh/docs/installation)
 with the user's authorization. Ensure Bun is on the MCP host's PATH as well as the
@@ -17,11 +17,11 @@ in `SKILL.md`. Do not pair newer checkout guidance with an older runtime unknowi
 ## Install from npm
 
 ```bash
-npm install -g pmx-canvas@0.7.3
+npm install -g pmx-canvas@0.8.2
 pmx-canvas --version
 ```
 
-Without a global install, use `bunx pmx-canvas@0.7.3` in place of `pmx-canvas` in
+Without a global install, use `bunx pmx-canvas@0.8.2` in place of `pmx-canvas` in
 the commands below. Do not use unpinned `bunx pmx-canvas` for a version-specific check.
 
 ## Choose the workspace and target
@@ -91,7 +91,7 @@ discards empty env values, remove `PMX_CANVAS_URL` from its launch environment i
   "mcpServers": {
     "canvas": {
       "command": "bunx",
-      "args": ["pmx-canvas@0.7.3", "--mcp"],
+      "args": ["pmx-canvas@0.8.2", "--mcp"],
       "env": {
         "PMX_CANVAS_WORKSPACE_ROOT": "/absolute/path/to/project",
         "PMX_CANVAS_PORT": "14313",
@@ -135,7 +135,7 @@ Amp executes, not only on the user's laptop. Merge this into that workspace's
   "amp.mcpServers": {
     "canvas": {
       "command": "bunx",
-      "args": ["pmx-canvas@0.7.3", "--mcp"],
+      "args": ["pmx-canvas@0.8.2", "--mcp"],
       "includeTools": ["canvas_*"],
       "env": {
         "PMX_CANVAS_WORKSPACE_ROOT": "/absolute/path/to/project",
@@ -169,7 +169,7 @@ The agent must not run this approval itself or move the command to global settin
 `--mcp-config` to bypass workspace trust. Approval authorizes execution of this MCP
 command; it is not a new Canvas import consent or permission to mutate arbitrary boards.
 After approval, reload MCP connections (`reload_mcp` in Amp) and require `connected`.
-Discover `canvas` tools with `tool_search`; for the full unfiltered 0.7.3 server there
+Discover `canvas` tools with `tool_search`; for the full unfiltered 0.8.2 server there
 are 24 tools. If still absent, inspect the server status, command/PATH and target instead
 of reinstalling blindly. See [Amp MCP documentation](https://ampcode.com/docs/customize/mcp).
 

package/skills/pmx-canvas-testing/SKILL.md

@@ -68,10 +68,11 @@ and check `$?`, then read the file.
 
 - In the product source checkout, Bun tests live under `tests/unit/`.
 - In the product source checkout, Playwright browser smoke lives under `tests/e2e/`.
-- Playwright runs two projects: `desktop` (1440×900, the whole suite) and `pane-600` (600×900,
-  `tests/e2e/reference-pane.pw.ts` only). `pane-600` is the release reference surface: every node
-  type must paint there. A new node type fails its coverage test until it gets a reference case.
-  Run it alone with `bash scripts/run-playwright.sh --project=pane-600`.
+- Playwright runs `desktop` (1440×900, the whole suite except the reference cases) and three
+  reference projects for `tests/e2e/reference-pane.pw.ts`: `narrow-600`, `middle-1024` and
+  `wide-1920`. The workbench lives anywhere from a narrow side pane to a full window, so every
+  node type must paint at all three. A new node type fails its coverage test until it gets a
+  reference case. Run one width alone with `bash scripts/run-playwright.sh --project=narrow-600`.
 - Product CI runs those checkout suites: Bun coverage plus the browser smoke flow.
 - An isolated installed consumer instead tests the package's public transports and host behavior;
   it does not run or depend on the product checkout's source suites.

package/src/cli/commands/copilot.ts

@@ -20,6 +20,11 @@ cmd(
     const sourcePaths = [
       fileURLToPath(new URL('../../../.github/extensions/pmx-canvas/extension.mjs', import.meta.url)),
       fileURLToPath(new URL('../../../.github/extensions/pmx-canvas/steering-delivery.mjs', import.meta.url)),
+      fileURLToPath(new URL('../../../.github/extensions/pmx-canvas/runtime.mjs', import.meta.url)),
+      fileURLToPath(new URL('../../../.github/extensions/pmx-canvas/runtime.json', import.meta.url)),
+      fileURLToPath(new URL('../../../.github/extensions/pmx-canvas/start-mcp.mjs', import.meta.url)),
+      fileURLToPath(new URL('../../../.github/extensions/pmx-canvas/tools.json', import.meta.url)),
+      fileURLToPath(new URL('../../../.github/extensions/pmx-canvas/THIRD_PARTY_LICENSES.txt', import.meta.url)),
     ];
     const missingSource = sourcePaths.find((sourcePath) => !existsSync(sourcePath));
     if (missingSource) {

package/src/cli/commands/nodes.ts

@@ -796,11 +796,12 @@ cmd(
     const id = positional[0];
     if (!id) die('Missing node ID', 'pmx-canvas node get <node-id>');
 
+    const requestedFields = collectRequestedFields(args, flags);
     const result = (await invokeOperation('node.get', {
       id,
       board: typeof flags.board === 'string' ? flags.board : undefined,
+      contextDelivery: !flags.summary && !flags.compact && requestedFields.length === 0,
     })) as Record<string, unknown>;
-    const requestedFields = collectRequestedFields(args, flags);
     if (requestedFields.length > 0) {
       const picked = Object.fromEntries(requestedFields.map((field) => [field, resolveNodeFieldValue(result, field)]));
       const missing = requestedFields.filter((field) => picked[field] === undefined);
@@ -893,7 +894,7 @@ cmd(
       frameHeight !== undefined ||
       arrangeLocked !== undefined
     ) {
-      const existing = (await invokeOperation('node.get', { id })) as {
+      const existing = (await invokeOperation('node.get', { id, contextDelivery: false })) as {
         position: { x: number; y: number };
         size: { width: number; height: number };
         data: Record<string, unknown>;

package/src/cli/commands/view.ts

@@ -179,7 +179,7 @@ cmd(
   [
     'pmx-canvas serve',
     'pmx-canvas serve --port=8080 --no-open',
-    'pmx-canvas serve --demo --theme=light',
+    'pmx-canvas serve --demo --theme=daylight',
     'pmx-canvas --no-open --webview-automation',
   ],
   async (_args) => {

package/src/cli/index.ts

@@ -149,9 +149,10 @@ function commandAfterGlobalTargetFlags(argv: string[]): string {
   return '';
 }
 
-function runMcpServerProcess(): Promise<void> {
+function runMcpServerProcess(app = false): Promise<void> {
   return new Promise((resolvePromise, rejectPromise) => {
-    const child = spawn(process.execPath, ['run', mcpServerEntry], {
+    const entry = app ? resolve(cliDir, '..', 'mcp', 'app-server.ts') : mcpServerEntry;
+    const child = spawn(process.execPath, ['run', entry], {
       stdio: 'inherit',
       env: process.env,
     });
@@ -222,6 +223,9 @@ if (firstArg === 'serve') {
 const routedCommand = commandAfterGlobalTargetFlags(args);
 if (AGENT_COMMANDS.has(routedCommand) && routedCommand !== 'serve') {
   await runAgentCli(args);
+} else if (args.includes('--mcp-app')) {
+  // Private MCP Apps profile: focused tools and a self-contained UI resource.
+  await runMcpServerProcess(true);
 } else if (args.includes('--mcp')) {
   // MCP server mode: stdio transport, auto-starts canvas on first tool call
   await runMcpServerProcess();
@@ -274,7 +278,7 @@ Server options:
   --log-file=PATH  Daemon log file (default: ./.pmx-canvas/daemon-${port}.log)
   --pid-file=PATH  Optional daemon PID file (default: ./.pmx-canvas/daemon-${port}.pid)
   --wait-ms=MS   Health-check wait budget for daemon mode (default: 10000)
-  --theme=THEME  Theme: dark (default), light, high-contrast, midnight, sepia, arctic, ember, forest, volt
+  --theme=THEME  Theme: harbor (default), daylight, high-contrast, midnight, sepia, arctic, ember, forest, volt
   --webview-automation        Start a headless Bun.WebView automation session for /workbench
   --webview-backend=BACKEND   Bun.WebView backend: chrome or webkit
   --webview-width=PX          Automation WebView width (default: 1280)
@@ -283,6 +287,7 @@ Server options:
   --webview-chrome-argv=CSV   Extra Chrome args for Bun.WebView, comma-separated
   --webview-data-dir=PATH     Persist automation browser storage in PATH
   --mcp          Run as MCP server (stdio transport)
+  --mcp-app      Run the private MCP App profile (stdio; shared active board)
   --help, -h     Show this help
 
 Agent CLI (works against running server):
@@ -311,7 +316,8 @@ Agent CLI (works against running server):
   diagram add                         Add an Excalidraw diagram node
   html primitive add|schema           Add or inspect HTML communication primitives
   pin <ids...> | --list | --clear     Manage context pins
-  board list|create|rename|category   Manage boards (the human opens them in the workbench)
+  board list|create|open|rename|category
+                                      Manage boards and open the target before writing
   backup [status|schedule]            Back up every board, now or on a schedule
   restore <backup-file>               Replace every board with a backup
   export [--board id] [--out file]    Export a board as one HTML file anyone can open

package/src/client/App.tsx

@@ -54,6 +54,7 @@ import {
 import { connectSSE } from './state/sse-bridge';
 import { intents } from './state/intent-store';
 import { sessionActive } from './state/presence-store';
+import { isHostedWorkbench } from './state/workbench-transport';
 import {
   createGroupFromClient,
   removeEdgeFromClient,
@@ -376,7 +377,11 @@ export function App() {
             intents.value.size === 0 && <EmptyState onOpenPalette={() => setPaletteOpen(true)} />
           )}
           {selectedNodeIds.value.size > 0 && <SelectionBar />}
-          {sessionIsActive ? <CommandBar /> : contextPinnedNodeIds.value.size > 0 && <ContextPinBar />}
+          {sessionIsActive && !isHostedWorkbench() ? (
+            <CommandBar />
+          ) : (
+            contextPinnedNodeIds.value.size > 0 && <ContextPinBar />
+          )}
           <SessionReceipt onOpenSnapshots={() => setSnapshotOpen(true)} />
           <TextPrompt />
           <ExportDialog />

package/src/client/canvas/AgentPresenceLayer.tsx

@@ -1,7 +1,7 @@
 import { useRef } from 'preact/hooks';
-import { agentIdentityHue, agentPhaseLabel, type AgentPresence } from '../../shared/agent-presence.js';
+import { agentPhaseLabel, type AgentPresence } from '../../shared/agent-presence.js';
 import { nodes, viewport } from '../state/canvas-store';
-import { agentPresences, presenceWorldPosition } from '../state/presence-store';
+import { agentPresences, presenceWorldPosition, writerColor } from '../state/presence-store';
 
 /**
  * Agent presence layer (rail-chrome-v2 phase 3): one cursor + phase chip per
@@ -49,7 +49,7 @@ export function AgentPresenceLayer() {
           data-session-id={presence.sessionId}
           style={{
             transform: `translate(${position.x}px, ${position.y}px)`,
-            '--identity-color': `hsl(${agentIdentityHue(presence.sessionId)} 65% 62%)`,
+            '--identity-color': writerColor(presence.sessionId),
           }}
         >
           <div class="agent-cursor-inner" style={{ transform: `scale(${counterScale})` }}>

package/src/client/canvas/AnnotationLayer.tsx

@@ -23,7 +23,7 @@ export function AnnotationLayer({ annotations }: { annotations: CanvasAnnotation
               y={point.y}
               fill={color}
               font-size={annotation.width}
-              font-family="var(--font)"
+              font-family="var(--font-ui)"
               font-weight="700"
               opacity="0.95"
             >