Expand chat-first workbench and shared workspace capabilities

.agents/plugins/agent-native-turn-into-app/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-native-turn-into-app",
-  "version": "1.0.0+codex.5430c9cab656",
+  "version": "1.0.0+codex.c50dbd31a986",
   "description": "Turn visible project context, a proven thread, skill, or workflow into a runnable Agent-Native app. On Claude or ChatGPT Web, it hands a bounded source brief to Builder through Dispatch; local code agents can build and verify in a workspace.",
   "author": { "name": "Agent-Native", "url": "https://agent-native.com" },
   "homepage": "https://dispatch.agent-native.com",

.agents/plugins/agent-native-turn-into-app/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "agent-native-turn-into-app",
-  "version": "1.0.0+codex.5430c9cab656",
+  "version": "1.0.0+codex.c50dbd31a986",
   "description": "Turn visible project context, a proven thread, skill, or workflow into a runnable Agent-Native app. On Claude or ChatGPT Web, it hands a bounded source brief to Builder through Dispatch; local code agents can build and verify in a workspace.",
   "author": { "name": "Agent-Native", "url": "https://agent-native.com" },
   "homepage": "https://dispatch.agent-native.com",

.agents/plugins/agent-native-turn-into-app/skills/turn-into-app/SKILL.md

@@ -3,8 +3,9 @@ name: turn-into-app
 description: >-
   Turn visible project context, a proven thread, skill, or workflow into a
   runnable Agent-Native app with simple buttons, visible agent steps, preview,
-  and deployment handoff. Use when a user invokes `/turn-into-app` or asks to
-  make a workflow into an app, including from Claude or ChatGPT on the web.
+  and deployment handoff. Use when a user invokes `/turn-into-app`,
+  `/make-into-app`, or asks to make a workflow into an app, including from
+  Claude or ChatGPT on the web.
 user-invocable: true
 scope: both
 metadata:
@@ -38,6 +39,15 @@ The build location depends on the host. Treat this as a hard routing rule:
   workspace, follow the local implementation steps below. The local agent may
   scaffold, edit, run, and verify the app there.
 
+Once the source brief is sufficient to identify a repeatable workflow, the
+handoff is non-interactive. Do not ask the user for visual, product, copy,
+layout, template, integration, or implementation choices that can be resolved
+from the source. Select the source's recommended option; otherwise choose the
+most direct conventional default and record the assumption for later review.
+Only stop for a genuine hard blocker such as missing authorization, a
+destructive external action, an ambiguous target workspace, or no identifiable
+workflow at all.
+
 ## Default behavior
 
 For a local code-agent runtime this is an end-to-end build skill, not a request
@@ -104,14 +114,16 @@ before creating the app. Read the host-provided context in this order:
 Record the brief with these headings before handoff: source and provenance,
 project goal, configuration and constraints, knowledge sources, repeatable
 workflow, inputs and outputs, judgment and review points, representative runs,
-integrations and permissions, and unknowns. This is the compact contract for
+integrations and permissions, and unknowns and assumptions. This is the compact contract for
 the app. It keeps the new app useful without pretending that hidden Project
 history was imported. See [the fresh Project reference](references/fresh-project.md)
 for the host setup and brief template.
 
-If the visible Project context has no concrete repeatable job, ask for one
-focused clarification or a representative artifact. Do not fall back to a
-generic “what app do you want to make?” builder.
+If the visible Project context has no concrete repeatable job and no primary
+goal can be inferred, ask for one focused clarification or a representative
+artifact. Otherwise use the project's primary goal and source conventions; do
+not ask a questionnaire and do not fall back to a generic “what app do you
+want to make?” builder.
 
 ## Source selection guard
 

.agents/plugins/agent-native-turn-into-app/skills/turn-into-app/references/fresh-project.md

@@ -36,7 +36,7 @@ Inputs and outputs:
 Judgment and review points:
 Representative runs: none, or 1-3 selected examples
 Integrations and permissions:
-Unknowns and follow-up:
+Unknowns and assumptions:
 ```
 
 Keep source references bounded. Prefer a file name, URL, resource ID, or short
@@ -69,6 +69,13 @@ do not fall back to a local sandbox build. Claude Code and Codex Code are the
 local-agent exception and may follow the implementation steps in the main
 skill.
 
+The brief is an implementation authorization, not a questionnaire. After a
+repeatable workflow is identifiable, choose any source-recommended option
+automatically. For unresolved non-blocking choices, use the most direct
+conventional default, record it under assumptions, and continue. Ask only when
+there is no identifiable workflow, no authorized target workspace, or a
+destructive/credential boundary genuinely prevents the handoff.
+
 In a new Project chat, say:
 
 ```text

.agents/skills/adding-a-feature/SKILL.md

@@ -81,6 +81,13 @@ or other file-like payloads, design the upload path in the same change:
 provider upload first, then URL/id/blob handle in SQL. Do not add base64/binary
 columns or stuff files into `application_state`.
 
+If the feature adds a server-side dependency carrying a native binary or heavy
+runtime — headless browser, ffmpeg, image/video processing, ML runtime — read
+the `performance` skill §9 before adding it. A deployed app has one `/*` page
+function that every visitor's cache miss wakes, and it ships whatever the server
+bundle depends on. Run that work from a background function or a job so the page
+function never carries the weight.
+
 **If the action produces or lists a navigable resource**, add a `link` builder that returns `{ url: buildDeepLink({ app, view, params }), label }`. External coding agents and MCP hosts (Claude / ChatGPT / Claude Code / Cowork / Codex, over MCP/A2A) then surface an "Open in … →" deep link that drops the user back into the running UI focused on the record — for free. If a compatible MCP host should render an inline review/edit surface, also add `mcpApp` with `embedApp()` so the action embeds the real React app route instead of a one-off HTML UI. The `link` builder and `mcpApp` metadata must be pure and synchronous (no I/O). Any external-agent read/ingest action must be `http: { method: "GET" }` + `readOnly: true` + `publicAgent: { expose: true, readOnly: true, requiresAuth: true }`. See the `external-agents` skill.
 
 ### 3. Skills / Instructions
@@ -195,4 +202,6 @@ TL;DR: declare the vocabulary once with `defineAppRoles({ appId, roles, defaultR
 - **create-skill** — How to create skills for new patterns (area 3 in detail)
 - **storing-data** — Where to store the feature's data
 - **real-time-sync** — How the UI stays in sync when the agent writes data
+- **performance** — Query/load cost, and (§9) cold-start artifact size when a
+  feature adds a server-side dependency
 - **internationalization** — How to update localized UI copy and catalogs

.agents/skills/chat-first-workbench/SKILL.md

@@ -0,0 +1,54 @@
+---
+name: chat-first-workbench
+description: >-
+  Implement or extend the opt-in Codex/T3-like chat-first shell. Use when
+  changing chat rails, contextual app panes, app opening, or local/mobile shell
+  preferences across Electron, Dispatch, or mobile.
+scope: dev
+---
+
+# Chat-first workbench
+
+## Contract
+
+The chat remains the primary surface. Workspace apps are a bounded discovery
+rail, not a second navigation system. An app pane is opened from an explicit
+app selection or a completed open_app action and carries only an app id plus a
+validated app-relative path or view.
+
+## Client behavior
+
+- The preference is opt-in and local to the client. Keep the existing app-first
+  shell unchanged when it is disabled.
+- Electron uses the shared Code Agents rail and AppWebview.
+- Dispatch uses list-workspace-apps and create_embed_session; never iframe a
+  raw workspace URL. Resolve an absolute open_app URL against the registered
+  app first, then pass the resulting app-relative path.
+- Mobile uses the existing app registry and secure AppWebView routes instead of
+  accepting arbitrary URLs or adding a second navigator.
+- Show no nested app sidebar or browser chrome in a contextual pane.
+- The app shelf is capped at six visible entries. Pinning and drag-reordering
+  are device-local presentation preferences; the agent-visible target remains
+  the registered app id and route.
+
+## Agent and state boundaries
+
+- Keep app discovery, embed-session minting, and thread operations on the
+  existing action surfaces.
+- Emit the shared chat-first open-app event only for the completed first-party
+  `open_app` action with a real app, path, or view. A missing or unreadable
+  result is not success, and namespaced third-party tools cannot steer the
+  pane.
+- Both web and desktop resolve the event through the same core origin/base-path
+  allow-list. An unresolved target produces a visible notice and no pane.
+- If the agent needs to know which app is visible, expose a compact
+  application-state selection instead of scraping the iframe DOM.
+- Cloud handoff is a future execution-residence seam. Do not claim that a local
+  run has moved to a worker until a durable worker snapshot and readback exist.
+
+## Verification
+
+Test the disabled path and the enabled path separately. For the enabled path,
+verify rail ordering, chat history, app selection, embed-session errors, pane
+close, and completed open_app behavior in a running client. Treat configuration
+alone as insufficient proof.

.agents/skills/turn-into-app/SKILL.md

@@ -3,8 +3,9 @@ name: turn-into-app
 description: >-
   Turn visible project context, a proven thread, skill, or workflow into a
   runnable Agent-Native app with simple buttons, visible agent steps, preview,
-  and deployment handoff. Use when a user invokes `/turn-into-app` or asks to
-  make a workflow into an app, including from Claude or ChatGPT on the web.
+  and deployment handoff. Use when a user invokes `/turn-into-app`,
+  `/make-into-app`, or asks to make a workflow into an app, including from
+  Claude or ChatGPT on the web.
 user-invocable: true
 scope: both
 metadata:
@@ -38,6 +39,15 @@ The build location depends on the host. Treat this as a hard routing rule:
   workspace, follow the local implementation steps below. The local agent may
   scaffold, edit, run, and verify the app there.
 
+Once the source brief is sufficient to identify a repeatable workflow, the
+handoff is non-interactive. Do not ask the user for visual, product, copy,
+layout, template, integration, or implementation choices that can be resolved
+from the source. Select the source's recommended option; otherwise choose the
+most direct conventional default and record the assumption for later review.
+Only stop for a genuine hard blocker such as missing authorization, a
+destructive external action, an ambiguous target workspace, or no identifiable
+workflow at all.
+
 ## Default behavior
 
 For a local code-agent runtime this is an end-to-end build skill, not a request
@@ -104,14 +114,16 @@ before creating the app. Read the host-provided context in this order:
 Record the brief with these headings before handoff: source and provenance,
 project goal, configuration and constraints, knowledge sources, repeatable
 workflow, inputs and outputs, judgment and review points, representative runs,
-integrations and permissions, and unknowns. This is the compact contract for
+integrations and permissions, and unknowns and assumptions. This is the compact contract for
 the app. It keeps the new app useful without pretending that hidden Project
 history was imported. See [the fresh Project reference](references/fresh-project.md)
 for the host setup and brief template.
 
-If the visible Project context has no concrete repeatable job, ask for one
-focused clarification or a representative artifact. Do not fall back to a
-generic “what app do you want to make?” builder.
+If the visible Project context has no concrete repeatable job and no primary
+goal can be inferred, ask for one focused clarification or a representative
+artifact. Otherwise use the project's primary goal and source conventions; do
+not ask a questionnaire and do not fall back to a generic “what app do you
+want to make?” builder.
 
 ## Source selection guard
 

.agents/skills/turn-into-app/references/fresh-project.md

@@ -36,7 +36,7 @@ Inputs and outputs:
 Judgment and review points:
 Representative runs: none, or 1-3 selected examples
 Integrations and permissions:
-Unknowns and follow-up:
+Unknowns and assumptions:
 ```
 
 Keep source references bounded. Prefer a file name, URL, resource ID, or short
@@ -69,6 +69,13 @@ do not fall back to a local sandbox build. Claude Code and Codex Code are the
 local-agent exception and may follow the implementation steps in the main
 skill.
 
+The brief is an implementation authorization, not a questionnaire. After a
+repeatable workflow is identifiable, choose any source-recommended option
+automatically. For unresolved non-blocking choices, use the most direct
+conventional default, record it under assumptions, and continue. Ask only when
+there is no identifiable workflow, no authorized target workspace, or a
+destructive/credential boundary genuinely prevents the handoff.
+
 In a new Project chat, say:
 
 ```text

.agents/skills/workspace-conventions/SKILL.md

@@ -69,6 +69,12 @@ Preview before `--apply`, commit `agent-native.ejections.json`, and never edit
   data, or credential-looking literals in source, docs, prompts, fixtures,
   application state, action responses, or generated app content. Use
   secrets/OAuth/runtime configuration and obvious placeholders in examples.
+- Each app deploys its own `/*` page function, and that function ships whatever
+  the app's server bundle depends on — including a dependency only a background
+  job uses. Before an app takes on a heavy runtime (headless browser, ffmpeg,
+  media processing, ML), read `.agents/skills/performance/SKILL.md` §9 and keep
+  that work in a background function or job. A dependency belonging to one app
+  does not belong in `packages/shared`.
 - Prefer framework defaults until the workspace has a real custom rule,
   component, plugin, action, or skill to share.
 - Keep the Workspace files view for user-authored or user-requested resources.
@@ -91,5 +97,6 @@ Preview before `--apply`, commit `agent-native.ejections.json`, and never edit
 - **agent-native-toolkit** — Inventory of shared workspace and agent UI.
 - **customizing-agent-native** — The configure → compose → eject ladder.
 - **delegate-to-agent** — Routing every AI feature through the agent chat.
+- **performance** — Load cost, and (§9) cold-start artifact size per app.
 - **secrets** — Registering API keys and service credentials.
 - **storing-data** — Where structured data and large payloads belong.

.changeset/agent-plugin-agent-visible.md

@@ -0,0 +1,5 @@
+---
+"@agent-native/core": patch
+---
+
+Keep imported Agent Plugin skills in the agent-visible workspace skills tree, including namespaced plugin skills.

.changeset/autonomous-workspace-app-builds.md

@@ -0,0 +1,5 @@
+---
+"@agent-native/dispatch": patch
+---
+
+Make turn-into-app Builder handoffs autonomous by choosing recommended defaults and recording non-blocking assumptions instead of stopping for questions.

.changeset/chat-first-workbench.md

@@ -0,0 +1,7 @@
+---
+"@agent-native/core": minor
+"@agent-native/dispatch": minor
+"@agent-native/toolkit": patch
+---
+
+Add an opt-in chat-first workbench with contextual app surfaces for desktop, Dispatch, and mobile clients.

.changeset/fence-background-automation-workers.md

@@ -0,0 +1,5 @@
+---
+"@agent-native/core": patch
+---
+
+Prevent duplicate recurring automation dispatch across multiple app deployments and preserve verified Builder credentials for detached background runs.

.changeset/prerender-public-template-pages.md

@@ -0,0 +1,5 @@
+---
+"@agent-native/core": patch
+---
+
+Document prerendering in the scaffolded app's `react-router.config.ts`: a commented, correct example with the three conditions a path must meet (public, build-time constant, never redirecting), left off by default because every route the scaffold ships is signed-in and a prerendered file is served without auth middleware running.

.changeset/repair-structured-document-titles.md

@@ -0,0 +1,5 @@
+---
+"@agent-native/core": patch
+---
+
+Repair structured route metadata before it can appear as a serialized payload in browser tab titles.

.github/workflows/ci.yml

@@ -618,18 +618,22 @@ jobs:
       - name: Build Content template (Cloudflare Pages preset)
         run: NITRO_PRESET=cloudflare_pages pnpm --filter content build
 
-      # Plan covers diagram-heavy SSR and Clips covers public-share SSR. Build
-      # both real Netlify function artifacts so a core runtime dependency cannot
-      # be missing from either deployment's server bundle.
-      - name: Build Plan and Clips templates (netlify preset)
-        run: NITRO_PRESET=netlify pnpm --filter plan --filter clips build
+      # Three templates, one per size class, because building all 17 per PR is
+      # too slow: Plan covers diagram-heavy SSR, Clips covers public-share SSR,
+      # and Assets is the one that legitimately depends on creative-context — so
+      # it is the only build that exercises the browser-runtime size budget.
+      - name: Build Plan, Clips, and Assets templates (netlify preset)
+        run: NITRO_PRESET=netlify pnpm --filter plan --filter clips --filter assets build
 
       - name: Import SSR handler — must not crash at cold-start
         # External timeout is a backstop against a pathological synchronous hang;
         # the script itself races module eval against a 30s window and force-exits.
         # Match the deployed Netlify environment so failed best-effort local
         # SQLite setup cannot call process.exit during this import-only probe.
-        run: NETLIFY=true timeout 120 node scripts/ssr-boot-smoke.mjs plan clips
+        # This lane intentionally probes the three built representatives above.
+        # The smoke script's optional `--report-uncovered` mode is fail-closed;
+        # use it only when the caller intends to gate on full template coverage.
+        run: NETLIFY=true timeout 180 node scripts/ssr-boot-smoke.mjs plan clips assets
 
       # Exercise the two other Node serverless presets as well. These import
       # their generated handlers, so an unresolved bare runtime dependency