@agent-native/core 0.92.12 → 0.94.0

package/docs/content/workspace.mdx

@@ -5,7 +5,11 @@ description: "Claude-Code-level customization per user — skills, memory, instr
 
 # Workspace
 
-> **Which workspace doc?** This page covers the **customization layer** — what a workspace _is_. For the deployment shape (one monorepo, many apps) see [Multi-App Workspaces](/docs/multi-app-workspace); for governance (who reviews, approves, and owns what) see [Workspace Governance](/docs/workspace-management).
+<Callout tone="info">
+
+**Which workspace doc?** This page covers the **customization layer** — what a workspace _is_. For the deployment shape (one monorepo, many apps) see [Multi-App Workspaces](/docs/multi-app-workspace); for governance (who reviews, approves, and owns what) see [Workspace Governance](/docs/workspace-management).
+
+</Callout>
 
 Every agent-native app ships with a **workspace**: the customization layer that makes the agent yours. It contains team instructions (`AGENTS.md`), shared learnings (`LEARNINGS.md`), personal structured memory (`memory/MEMORY.md`), skills the agent pulls in on demand, custom sub-agents, scheduled jobs, and connected MCP servers — everything you'd expect from a Claude Code / Codex setup.
 
@@ -82,7 +86,7 @@ The twist: **it's SQL rows, not filesystem files.** Each user gets their own wor
 | Per-project `CLAUDE.md` / skills | Per-app `AGENTS.md` + workspace memory resources   |
 | MCP config in a JSON file        | MCP config in JSON _or_ the settings UI, per scope |
 
-Same capabilities. Different economics. See [Templates](/docs/cloneable-saas) for why this matters for SaaS.
+Same capabilities. Different economics. See [Apps](/docs/cloneable-saas) for why this matters for SaaS.
 
 ## Overview {#overview}
 
@@ -219,11 +223,9 @@ workspace context/brand.md
 -> personal context/brand.md
 ```
 
-Keep `context/` files short and factual — a few bullets the agent can skim:
-
-```text
-<!-- context/brand.md -->
+For example:
 
+```text filename="context/brand.md"
 # Brand
 
 - Voice: direct, warm, concrete
@@ -386,15 +388,9 @@ There are two agent types in Workspace:
 
 Use custom agents for delegation within one app. Use connected agents when you need to call another app over A2A.
 
-## @ Tagging {#at-tagging}
-
-Type `@` in the chat input to reference workspace items. A dropdown appears at the cursor showing matching agents and files. Use arrow keys to navigate and Enter to select. The selected item appears as an inline chip in the input.
-
-When you send a message, **files/resources** are passed as references the agent can read, **custom agents** run locally with their profile instructions, and **connected agents** are called over A2A.
+## @ Tagging and / Slash Commands {#at-tagging}
 
-## / Slash Commands {#slash-commands}
-
-Type `/` at the start of a line to invoke a skill. A dropdown shows available skills with their names and descriptions; selecting one adds an inline chip and includes its content as context when the message is sent. If no skills are configured, the dropdown links to these docs.
+Type `@` in the chat input to reference an agent, file, or resource, or `/` to invoke a skill — both open a dropdown at the cursor and add an inline chip when you select an item. See [Agent Mentions](/docs/agent-mentions) for the full mechanics (routing, `MentionProvider`, sub-agent selection) and [Skills Guide](/docs/skills-guide) for how skills are authored and discovered.
 
 ## Code vs App Mode {#dev-vs-prod}
 
@@ -414,10 +410,6 @@ Workspace Connections let apps share the same provider account (Slack, GitHub, H
 
 See [Workspace Connections](/docs/workspace-connections) for the quickstart, connection/grant/credentialRef API, and concrete Slack, HubSpot, and GitHub examples.
 
----
-
-# Reference
-
 ## Resource API {#resource-api}
 
 Resources can be managed from server code, actions, or the REST API.
@@ -461,3 +453,12 @@ pnpm action resource-write --path "notes/meeting.md" --content "# Meeting Notes.
 # Delete a resource
 pnpm action resource-delete --path "notes/old.md"
 ```
+
+## What's next {#whats-next}
+
+- [**Skills Guide**](/docs/skills-guide) — author and scope the skill files referenced from `skills/`
+- [**Agent Mentions**](/docs/agent-mentions) — `@`-mention and `/`-command mechanics in full
+- [**Recurring Jobs**](/docs/recurring-jobs) — schedule the prompts created from Scheduled Tasks
+- [**Workspace Governance**](/docs/workspace-management) — who reviews, approves, and owns workspace changes
+- [**Multi-App Workspaces**](/docs/multi-app-workspace) — the deployment shape one workspace spans
+- [**Workspace Connections**](/docs/workspace-connections) — share provider credentials across apps

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-native/core",
-  "version": "0.92.12",
+  "version": "0.94.0",
   "description": "Framework for agent-native application development — where AI agents and UI share SQL state, actions, and context",
   "homepage": "https://github.com/BuilderIO/agent-native#readme",
   "bugs": {
@@ -46,6 +46,8 @@
     "./server/agent-discovery": "./dist/server/agent-discovery.js",
     "./server/request-context": "./dist/server/request-context.js",
     "./server/design-token-utils": "./dist/server/design-token-utils.js",
+    "./integrations": "./dist/integrations/index.js",
+    "./automation": "./dist/automation/index.js",
     "./brand-kit": "./dist/brand-kit/index.js",
     "./brand-kit/fig": "./dist/brand-kit/fig/index.js",
     "./data-widgets": "./dist/data-widgets/index.js",
@@ -280,6 +282,7 @@
     "ajv": "^8.20.0",
     "better-auth": "1.6.16",
     "better-sqlite3": "^12.8.0",
+    "botframework-connector": "^4.23.3",
     "clsx": "^2.1.1",
     "cron-parser": "^5.5.0",
     "diff-match-patch": "^1.0.5",
@@ -312,6 +315,7 @@
     "tiptap-markdown": "^0.9.0",
     "turndown": "7.2.4",
     "tw-animate-css": "1.4.0",
+    "tweetnacl": "^1.0.3",
     "y-protocols": "^1.0.7",
     "yjs": "^13.6.31",
     "zod": "^4.3.6",

package/src/templates/default/.agents/skills/capture-learnings/SKILL.md

@@ -11,11 +11,14 @@ metadata:
 
 # Capture Learnings
 
-This is background knowledge, not a slash command. **Your memory index is loaded at the start of every conversation.** Use `save-memory` proactively when you learn something worth remembering.
+This is background knowledge, not a slash command. **Organization learnings and your personal memory index are loaded at the start of every conversation, including Slack/integration turns.** Capture durable context proactively when you learn something worth remembering.
 
 ## How to Read & Write Memories
 
-Memories are stored as **resources** in the SQL database (personal scope), not as files on disk.
+Memories are stored as **resources** in the SQL database, not as files on disk.
+
+- **Team/organization knowledge:** shared `LEARNINGS.md`. Read it first, merge the new fact, then write the full updated file with the `resources` tool using `scope: "shared"`. Shared scope resolves to the active organization; it must never leak to another organization in the same deployment.
+- **Personal knowledge:** `memory/MEMORY.md` plus `memory/<name>.md`, written with `save-memory`.
 
 - **Save a memory:** `save-memory --name <name> --type <type> --description "..." --content "..."`
 - **Read a memory:** `resource-read --path memory/<name>.md`
@@ -33,6 +36,14 @@ Memories are stored as **resources** in the SQL database (personal scope), not a
 
 ## When to Capture
 
+### Team and organization knowledge (`LEARNINGS.md`, shared scope)
+- Canonical destinations and workflows (for example, which Content database receives a type of Slack request)
+- Required intake fields, ownership, prioritization conventions, metric definitions, and approved terminology
+- Durable external references that the whole team needs, including the canonical page/database URL
+- Corrections or decisions that should affect every organization member's future Slack and app conversations
+
+Store the fact and a concise provenance link when available. Do not paste full private conversations, customer data, credentials, or secrets into learnings. Put stable always-on policy in shared `AGENTS.md`; put learned facts and evolving conventions in shared `LEARNINGS.md`.
+
 ### User Preferences & Memory (`user`)
 - **Tone and style** — "I prefer casual tone", "don't use emojis", "keep replies short"
 - **Personal context** — contacts, relationships, habits ("my wife's email is...", "I'm in PST timezone")
@@ -58,19 +69,21 @@ Memories are stored as **resources** in the SQL database (personal scope), not a
 - Things obvious from reading the code
 - Standard language/framework behavior
 - Temporary debugging notes
-- Anything already in AGENTS.md or skills
+- Anything already in AGENTS.md, shared LEARNINGS.md, or skills
 - Ephemeral task details (use tasks/plans instead)
 
 ## Key Rules
 
-1. **Save proactively — don't ask permission.** When you learn something, save it immediately.
-2. **One memory per topic** — e.g. `coding-style`, `project-alpha`, not one giant dump
-3. **Read before updating** — if a memory exists, read it first and merge, don't overwrite
-4. **Keep descriptions concise** — the index is loaded every conversation
-5. **Memories are SQL-backed** — safe for personal info, persist across sessions, not in git
+1. **Save proactively — don't ask permission.** When you learn something durable, save it immediately at the correct scope.
+2. **Choose scope by audience.** Organization workflow or reference → shared `LEARNINGS.md`; one person's preference/context → personal memory.
+3. **One memory per topic** — e.g. `coding-style`, `project-alpha`, not one giant dump
+4. **Read before updating** — if a memory exists, read it first and merge, don't overwrite
+5. **Keep descriptions concise** — the index is loaded every conversation
+6. **Memories are SQL-backed** — they persist across sessions and are not in git; still minimize sensitive content
 
 ## Graduation
 
 When a memory is referenced repeatedly, it may belong in AGENTS.md or a skill:
-- Saving a memory is lightweight (auto-apply, personal scope)
+- Saving a personal memory is lightweight (auto-apply, personal scope)
+- Shared LEARNINGS.md is the lightweight organization knowledge layer
 - Updating AGENTS.md or a skill is heavier (affects all users/agents)

package/src/templates/default/AGENTS.md

@@ -76,9 +76,13 @@ only the hosted URL/reference in SQL.
 1. **`AGENTS.md`** -- inherited workspace defaults, app/team instructions, and user-specific context.
 2. **`LEARNINGS.md`** -- user preferences, corrections, and patterns. Read personal and shared scopes.
 
-**Update `LEARNINGS.md` when you learn something important.** Built-in app
-chat agents use the `resources` tool with the `action` argument. External CLI
-agents can use the equivalent `pnpm action resource-*` commands.
+**Update the shared `LEARNINGS.md` when you learn something important for the
+team.** Canonical destinations, request fields, metric definitions, routing
+conventions, and corrections learned in Slack belong there with concise source
+links. Shared scope resolves to the active organization. Personal preferences
+and user-specific context go through `save-memory` into `memory/MEMORY.md`.
+Built-in app chat agents use the `resources` tool with the `action` argument.
+External CLI agents can use the equivalent `pnpm action resource-*` commands.
 
 | Built-in agent tool call                                                | CLI equivalent                                                                         | Purpose                 |
 | ----------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | ----------------------- |

package/src/templates/workspace-core/.agents/skills/authentication/SKILL.md

@@ -19,7 +19,7 @@ Auth is powered by **Better Auth** with account-first design. Every new user cre
 
 | Mode                      | Behavior                                                                                                                                 |
 | ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
-| **Development (default)** | Real Better Auth — same flow as production. There is **no auth bypass**. On first run the framework auto-creates a throwaway dev account and signs you in (credentials printed once to the console; disable with `AGENT_NATIVE_DISABLE_AUTO_DEV_ACCOUNT=1`), so you are not stuck at a login wall. `getSession()` returns the signed-in user or `null` — it never falls back to a sentinel identity. |
+| **Development (default)** | Real Better Auth — same flow as production. There is **no auth bypass**. On first run the framework auto-creates a throwaway dev account and signs you in without printing its credentials (disable with `AGENT_NATIVE_DISABLE_AUTO_DEV_ACCOUNT=1`), so you are not stuck at a login wall. `getSession()` returns the signed-in user or `null` — it never falls back to a sentinel identity. |
 | **Production (default)**  | Better Auth with email/password + social providers (Google, GitHub). Organizations built in.                                             |
 | **`AUTH_MODE=local`**     | **Not** a browser auth bypass, and never returns `local@localhost`. It only affects CLI/agent identity: it lets `pnpm action` / the local agent loop auto-bind to the single real signed-in dev user from the `sessions` table (see `scripts/dev-session.ts`). Browser login is unchanged. |
 | **`AUTH_SKIP_EMAIL_VERIFICATION=1`** | QA/preview escape hatch for real email/password accounts. Signup skips email verification and does not send the signup verification email. Local dev/test skips verification by default; set `AUTH_SKIP_EMAIL_VERIFICATION=0` only when testing verification itself. Use `+qa` emails for test accounts. |

package/src/templates/workspace-core/.agents/skills/capture-learnings/SKILL.md

@@ -11,11 +11,14 @@ metadata:
 
 # Capture Learnings
 
-This is background knowledge, not a slash command. **Your memory index is loaded at the start of every conversation.** Use `save-memory` proactively when you learn something worth remembering.
+This is background knowledge, not a slash command. **Organization learnings and your personal memory index are loaded at the start of every conversation, including Slack/integration turns.** Capture durable context proactively when you learn something worth remembering.
 
 ## How to Read & Write Memories
 
-Memories are stored as **resources** in the SQL database (personal scope), not as files on disk.
+Memories are stored as **resources** in the SQL database, not as files on disk.
+
+- **Team/organization knowledge:** shared `LEARNINGS.md`. Read it first, merge the new fact, then write the full updated file with the `resources` tool using `scope: "shared"`. Shared scope resolves to the active organization; it must never leak to another organization in the same deployment.
+- **Personal knowledge:** `memory/MEMORY.md` plus `memory/<name>.md`, written with `save-memory`.
 
 - **Save a memory:** `save-memory --name <name> --type <type> --description "..." --content "..."`
 - **Read a memory:** `resource-read --path memory/<name>.md`
@@ -33,6 +36,14 @@ Memories are stored as **resources** in the SQL database (personal scope), not a
 
 ## When to Capture
 
+### Team and organization knowledge (`LEARNINGS.md`, shared scope)
+- Canonical destinations and workflows (for example, which Content database receives a type of Slack request)
+- Required intake fields, ownership, prioritization conventions, metric definitions, and approved terminology
+- Durable external references that the whole team needs, including the canonical page/database URL
+- Corrections or decisions that should affect every organization member's future Slack and app conversations
+
+Store the fact and a concise provenance link when available. Do not paste full private conversations, customer data, credentials, or secrets into learnings. Put stable always-on policy in shared `AGENTS.md`; put learned facts and evolving conventions in shared `LEARNINGS.md`.
+
 ### User Preferences & Memory (`user`)
 - **Tone and style** — "I prefer casual tone", "don't use emojis", "keep replies short"
 - **Personal context** — contacts, relationships, habits ("my wife's email is...", "I'm in PST timezone")
@@ -58,19 +69,21 @@ Memories are stored as **resources** in the SQL database (personal scope), not a
 - Things obvious from reading the code
 - Standard language/framework behavior
 - Temporary debugging notes
-- Anything already in AGENTS.md or skills
+- Anything already in AGENTS.md, shared LEARNINGS.md, or skills
 - Ephemeral task details (use tasks/plans instead)
 
 ## Key Rules
 
-1. **Save proactively — don't ask permission.** When you learn something, save it immediately.
-2. **One memory per topic** — e.g. `coding-style`, `project-alpha`, not one giant dump
-3. **Read before updating** — if a memory exists, read it first and merge, don't overwrite
-4. **Keep descriptions concise** — the index is loaded every conversation
-5. **Memories are SQL-backed** — safe for personal info, persist across sessions, not in git
+1. **Save proactively — don't ask permission.** When you learn something durable, save it immediately at the correct scope.
+2. **Choose scope by audience.** Organization workflow or reference → shared `LEARNINGS.md`; one person's preference/context → personal memory.
+3. **One memory per topic** — e.g. `coding-style`, `project-alpha`, not one giant dump
+4. **Read before updating** — if a memory exists, read it first and merge, don't overwrite
+5. **Keep descriptions concise** — the index is loaded every conversation
+6. **Memories are SQL-backed** — they persist across sessions and are not in git; still minimize sensitive content
 
 ## Graduation
 
 When a memory is referenced repeatedly, it may belong in AGENTS.md or a skill:
-- Saving a memory is lightweight (auto-apply, personal scope)
+- Saving a personal memory is lightweight (auto-apply, personal scope)
+- Shared LEARNINGS.md is the lightweight organization knowledge layer
 - Updating AGENTS.md or a skill is heavier (affects all users/agents)

package/src/templates/workspace-core/.agents/skills/extension-points/SKILL.md

@@ -195,9 +195,12 @@ the `slot-installs` query and the host re-renders without the iframe.
 - **Not a slot manifest.** Slot targets live in the `tool_slots` table
   (Drizzle export `extensionSlots`), not in the extension's HTML content.
   The agent can re-target an extension without rewriting it.
-- **Not for arbitrary code modification.** If a user wants to change how
-  the app itself behaves (not add a sandboxed widget), use the
-  `self-modifying-code` skill instead.
+- **Not for arbitrary code modification.** If the exact request needs UI inside
+  a native component or at a location with no slot, do not stop at "slots
+  cannot do that" or silently move it elsewhere. Treat it as full app
+  customization: use `connect-builder` for the Builder.io Cloud Agent/local
+  editing handoff in hosted chat, or follow `self-modifying-code` in a local
+  code-editing surface.
 
 ## Cross-references
 

package/src/templates/workspace-core/.agents/skills/extensions/SKILL.md

@@ -51,6 +51,31 @@ and Alpine.js runtime.
 - Action files in `actions/`
 - Routes
 
+## When the Request Needs Code Instead
+
+Route by the user's exact outcome, not by whether they called it an
+"extension." Extensions render only on their own page or inside an existing
+named `ExtensionSlot`; they cannot inject UI into arbitrary native components,
+replace built-in views, or appear at a location where the host app has no slot.
+
+If the requested placement or behavior requires changing native components,
+host layout/styles/routes/business logic, or adding a new slot:
+
+1. Briefly explain the extension boundary.
+2. Do **not** stop at "an extension cannot do that," and do not silently move the
+   UI to a less useful slot.
+3. Continue through the normal source-code customization flow:
+   - In hosted/app-rendered chat, call `connect-builder`. When its
+     `builderEnabled` result is true, offer the Builder.io Cloud Agent handoff;
+     when false, say the change can be made with local code editing, Agent
+     Native Desktop, or Builder.io cloud editing.
+   - In a local development or outer code-editing surface, follow the
+     `self-modifying-code` skill and edit the app source directly.
+
+Full source-code customization is a core Agent Native capability. Extensions
+are the fast, sandboxed, no-deploy layer—not the limit of what the app can
+become.
+
 **When a user asks to "make an extension", "create an extension", or "build
 a ... extension" (or the older phrasings "make a tool" / "create a tool"):**
 

package/src/templates/workspace-core/.agents/skills/integration-webhooks/SKILL.md

@@ -298,6 +298,21 @@ queue + retry job for at-least-once delivery.
 6. **Reply not delivered?** The processor likely succeeded but
    `adapter.sendResponse` failed — check the adapter's outbound logs.
 
+## Automation connectors
+
+Workflow systems such as n8n and Zapier are not messaging channels. Do not add
+them as `PlatformAdapter`s or route them through `provider-api`.
+
+For n8n-style workflow invocation and callbacks, use
+`@agent-native/core/automation` with static workflow IDs and allow-listed
+origins. Agents provide structured input, never a target URL or credential.
+Callbacks must verify a configured secret/signature, claim a durable event ID,
+enqueue work through the established queue, and acknowledge quickly.
+
+Zapier is blueprint-only unless the app implements Zapier's explicit REST Hook
+subscribe/unsubscribe contract or configures a separate Zapier MCP connection.
+Do not imply a generic Zapier workflow-execution API exists.
+
 ## Related Skills
 
 - `server-plugins` — How `/_agent-native/` routes get mounted

package/src/templates/workspace-core/.agents/skills/voice-transcription/SKILL.md

@@ -13,17 +13,21 @@ metadata:
 
 # Voice Transcription
 
-Click-to-toggle microphone inside the sidebar composer turns speech into
-text. Users configure live transcription separately from AI cleanup in
-Settings → Voice Transcription. The feature is available in every template
-that renders `TiptapComposer`.
+The microphone inside the sidebar composer offers two distinct paths:
+editable dictation and an opt-in realtime speech-to-speech agent session.
+Users configure dictation separately from AI cleanup in Settings → Voice
+Transcription. Both paths are available in every template that renders the
+shared agent sidebar.
 
 ## UX rules
 
 - **Always show the mic alongside the send button.** Cursor replaces send
   with mic when the composer is empty; their users complain. We keep both
   visible — Lovable does the same.
-- **Click-to-toggle, not push-to-talk.** More forgiving in a sidebar, avoids
+- **Ask before switching modes.** The mic opens a shadcn popover offering
+  **Start voice mode** and **Keep dictating**; never silently replace the
+  established dictation behavior.
+- **Dictation is click-to-toggle, not push-to-talk.** More forgiving in a sidebar, avoids
   host-app hotkey clashes. Keyboard shortcut is `Cmd/Ctrl+Shift+M` and
   `Escape` cancels mid-recording.
 - **Transcript lands in the composer, editable, never auto-sent.** Insert at
@@ -34,6 +38,31 @@ that renders `TiptapComposer`.
   Never use a sparkle or robot icon.
 - **Errors via inline alert or toast, never `window.alert`.**
 
+## Realtime speech mode
+
+Realtime speech mode is a full-duplex OpenAI Realtime WebRTC session, separate
+from the dictation providers below. It requires the authenticated user's
+`OPENAI_API_KEY`, uses the server-owned `gpt-realtime-2.1` session
+configuration, and keeps the key out of browser code.
+
+- Starting voice mode collapses the chat into a persistent bottom-end speech
+  orb. Clicking the orb shows or hides chat without ending the session; ending
+  the session is a separate, explicit control.
+- Semantic VAD keeps listening, starts responses automatically, and supports
+  barge-in while the agent is speaking.
+- Function calls must cross the authenticated realtime tool bridge and enter
+  `executeAgentToolCall`. Never call `ActionEntry.run` directly: that bypasses
+  schema validation, approvals, audit/journal behavior, timeouts, redaction,
+  and mutation refreshes.
+- Preserve the active browser-tab id in request context so `set-url`,
+  `set-search-params`, `view-screen`, and tab-scoped application state affect
+  the app the user is actually speaking to.
+- Do not persist audio. Store only compact lifecycle and latest-transcript
+  context at `application_state["realtime-voice-session"]`; delete it when the
+  session ends.
+- Missing-key failures should open Settings focused on the user-scoped
+  `OPENAI_API_KEY` field. Never send, log, or echo the key to the browser.
+
 ## Source And Cleanup
 
 Settings must keep these as separate choices:
@@ -80,11 +109,14 @@ Default behavior:
 | --------------------------------------------------------------------- | --------------------------------------------------- |
 | `packages/core/src/client/composer/useVoiceDictation.ts`              | Provider-routing hook (MediaRecorder / Web Speech)  |
 | `packages/core/src/client/composer/VoiceButton.tsx`                   | Mic button + live amplitude + cancel overlay        |
+| `packages/core/src/client/composer/RealtimeVoiceMode.tsx`            | Opt-in popover + persistent speech orb              |
+| `packages/core/src/client/composer/useRealtimeVoiceMode.tsx`         | WebRTC lifecycle, provider events, and tool bridge  |
 | `packages/core/src/client/composer/TiptapComposer.tsx`                | Wires the hook, insertion, and keyboard shortcut    |
 | `packages/core/src/client/settings/VoiceTranscriptionSection.tsx`     | Live source + cleanup controls in sidebar settings  |
 | `packages/core/src/client/transcription/BuilderTranscriptionCta.tsx`  | CTA shown when Builder account isn't connected      |
 | `packages/core/src/client/transcription/use-live-transcription.ts`    | Web Speech live-transcription hook for recordings   |
 | `packages/core/src/server/transcribe-voice.ts`                        | Route handler (routes to Builder/Gemini/Groq/Whisper) |
+| `packages/core/src/server/realtime-voice.ts`                          | Authenticated OpenAI SDP and action-tool routes     |
 | `packages/core/src/transcription/builder-transcription.ts`            | Builder proxy transcription client                  |
 | `packages/core/src/voice/`                                            | Shared voice context pack, prompt, and replacement helpers |
 | `packages/core/src/secrets/register-framework-secrets.ts`             | Framework-level provider key registration           |
@@ -139,4 +171,6 @@ Templates can:
 - Don't call transcription providers from the client — go through `/_agent-native/transcribe-voice` so the user's secret stays server-side.
 - Don't remove the cancel affordance — mic permission abuse paranoia is real.
 - Don't auto-submit the transcript — users always edit before sending.
+- Don't route realtime tool calls around the central guarded agent executor.
+- Don't persist realtime audio or put provider keys in SDP/session payloads.
 - Don't copy Cursor's "hide send when empty" pattern — it confuses users.

package/src/templates/workspace-core/AGENTS.md

@@ -71,8 +71,9 @@ agent should know.
 
 ## Adding Apps
 
-When a user asks from Dispatch chat or by tagging `@agent-native` in Slack to
-create, build, make, scaffold, or generate an "agent", classify the ask first.
+When a user asks from Dispatch chat or through `@agent-native` in Slack or
+Telegram to create, build, make, scaffold, or generate an "agent", classify
+the ask first.
 Simple Dispatch-native behavior such as a reminder, digest, monitor, routing
 rule, saved instruction, or recurring workflow can stay in Dispatch as a
 recurring job/resource/destination. Robust unique products or teammates that

package/corpus/core/docs/content/locales/ar-SA/migration-workbench.mdx

@@ -1,76 +0,0 @@
----
-title: "الترحيل إلى Agent-Native (/الترحيل)"
-description: "الترحيل هو هدف مضمن/ترحيل في مساحة عمل Agent-Native Code - وليس تطبيقًا منفصلاً. راجع رمز Agent-Native UI للحصول على الدليل الكامل."
----
-
-# الترحيل إلى Agent-Native (/الترحيل)
-
-الترحيل **ليس منتجًا أو قالبًا منفصلاً** — فهو مضمن
-هدف `/migrate` داخل مساحة عمل [Agent-Native Code](/docs/code-agents-ui).
-يتم تشغيله كجلسة تعليمات برمجية عادية يمكنك استئنافها والإرفاق بها وفحصها وإيقافها.
-
-<Diagram id="doc-block-4n71h8" title={"/migrate عبارة عن جلسة تعليمات برمجية، وليست تطبيقًا منفصلاً"} summary={"يتم إدخال المسار، URL، أو الوصف؛ يشترك التشغيل في نفس المخزن والنص وعناصر التحكم مثل أي جلسة تعليمات برمجية أخرى، ويمكن أن يصدر ملفًا محمولاً."}>
-
-```html
-<div class="diagram-migrate">
-  <div class="diagram-col">
-    <div class="diagram-pill">./local-app</div>
-    <div class="diagram-pill">https://example.com</div>
-    <div class="diagram-pill">--describe \"...\"</div>
-  </div>
-  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
-  <div class="diagram-panel center" data-rough>
-    <span class="diagram-pill accent">/migrate goal</span
-    ><small class="diagram-muted"
-      >نفس المخزن · النص · عناصر تشغيل التنفيذ</small
-    >
-  </div>
-  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
-  <div class="diagram-col">
-    <div class="diagram-box" data-rough>تطبيق مرحل</div>
-    <div class="diagram-pill ok">--emit dossier</div>
-  </div>
-</div>
-```
-
-```css
-.diagram-migrate {
-  display: flex;
-  align-items: center;
-  gap: 12px;
-  flex-wrap: wrap;
-}
-.diagram-migrate .diagram-col {
-  display: flex;
-  flex-direction: column;
-  gap: 8px;
-}
-.diagram-migrate .diagram-arrow {
-  font-size: 22px;
-  line-height: 1;
-}
-.diagram-migrate .center {
-  display: flex;
-  flex-direction: column;
-  align-items: center;
-  gap: 4px;
-}
-```
-
-</Diagram>
-
-```bash
-npx @agent-native/core@latest code /migrate ./my-next-app --out ../migrated-app
-npx @agent-native/core@latest code /migrate https://example.com --describe "marketing site plus dashboard"
-npx @agent-native/core@latest migrate ./my-next-app --out ../migrated-app   # shortcut into the same goal
-```
-
-الدليل الكامل — أشكال الإدخال (المسار / URL / الوصف)، ملفات `--emit`،
-وضع التخطيط مقابل الوضع التلقائي، وعناصر التحكم في التشغيل، وبيانات الاعتماد، والروابط العميقة لسطح المكتب، و
-صادرات الحزمة `@agent-native/migrate` — موجودة في
-[Agent-Native Code UI → Migrating to Agent-Native](/docs/code-agents-ui#migrate).
-
-> [!NOTE]
-> تمت إزالة تطبيق تفاصيل `migration` القديم المخفي. استخدم الكود
-> ، أو علامة التبويب Desktop Code، أو الملف المنبعث كالملف المدعوم
-> الأسطح.

package/corpus/core/docs/content/locales/de-DE/migration-workbench.mdx

@@ -1,76 +0,0 @@
----
-title: "Migration nach Agent-Native (/migrate)"
-description: "Migration ist ein integriertes /migrate-Ziel im Agent-Native-Code-Arbeitsbereich – keine separate App. Die vollständige Anleitung finden Sie unter Agent-Native-Code UI."
----
-
-# Migration nach Agent-Native (/migrate)
-
-Migration ist **kein separates Produkt oder eine separate Vorlage** – sie ist integriert
-`/migrate`-Ziel im [Agent-Native Code](/docs/code-agents-ui)-Arbeitsbereich.
-Es wird als normale Code-Sitzung ausgeführt, die Sie fortsetzen, anhängen, überprüfen und beenden können.
-
-<Diagram id="doc-block-g1pprw" title="/migrate ist eine Code-Sitzung, keine separate App" summary={"Ein Pfad, URL oder eine Beschreibung wird eingegeben; Die Ausführung nutzt den gleichen Speicher, das gleiche Transkript und die gleichen Steuerelemente wie jede andere Code-Sitzung und kann ein tragbares Dossier ausgeben."}>
-
-```html
-<div class="diagram-migrate">
-  <div class="diagram-col">
-    <div class="diagram-pill">./local-app</div>
-    <div class="diagram-pill">https://example.com</div>
-    <div class="diagram-pill">--describe \"...\"</div>
-  </div>
-  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
-  <div class="diagram-panel center" data-rough>
-    <span class="diagram-pill accent">/migrate goal</span
-    ><small class="diagram-muted"
-      >gleicher Store · Transkript · Laufsteuerung</small
-    >
-  </div>
-  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
-  <div class="diagram-col">
-    <div class="diagram-box" data-rough>Migrierte App</div>
-    <div class="diagram-pill ok">--emit dossier</div>
-  </div>
-</div>
-```
-
-```css
-.diagram-migrate {
-  display: flex;
-  align-items: center;
-  gap: 12px;
-  flex-wrap: wrap;
-}
-.diagram-migrate .diagram-col {
-  display: flex;
-  flex-direction: column;
-  gap: 8px;
-}
-.diagram-migrate .diagram-arrow {
-  font-size: 22px;
-  line-height: 1;
-}
-.diagram-migrate .center {
-  display: flex;
-  flex-direction: column;
-  align-items: center;
-  gap: 4px;
-}
-```
-
-</Diagram>
-
-```bash
-npx @agent-native/core@latest code /migrate ./my-next-app --out ../migrated-app
-npx @agent-native/core@latest code /migrate https://example.com --describe "marketing site plus dashboard"
-npx @agent-native/core@latest migrate ./my-next-app --out ../migrated-app   # shortcut into the same goal
-```
-
-Der vollständige Leitfaden – Eingabeformen (Pfad / URL / Beschreibung), `--emit`-Dossiers,
-Plan vs. Auto-Modus, Ausführungskontrollen, Anmeldeinformationen, Desktop-Deep-Links und
-`@agent-native/migrate`-Paketexporte – lebt in
-[Agent-Native Code UI → Migrating to Agent-Native](/docs/code-agents-ui#migrate).
-
-> [!NOTE]
-> Die alte versteckte `migration`-Detail-App wurde entfernt. Verwenden Sie den Code
-> -Arbeitsbereich, die Registerkarte „Desktop-Code“ oder ein ausgegebenes Dossier als unterstützt
-> Oberflächen.