@agent-native/core 0.152.1 → 0.153.1

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

@@ -1,364 +0,0 @@
----
-name: integration-webhooks
-description: >-
-  Cross-platform pattern for handling messaging integration webhooks (Slack,
-  Telegram, WhatsApp, email, etc.) on serverless hosts. Use when adding a new
-  integration adapter, debugging dropped messages, or wiring long-running agent
-  work into a webhook handler.
-scope: dev
-metadata:
-  internal: true
----
-
-# Integration Webhooks
-
-## Rule
-
-Integration webhooks (Slack, Telegram, WhatsApp, email, Google Docs, etc.) must
-**enqueue work to SQL and return 200 immediately**, then process the work in a
-**separate fresh function execution** kicked off by a self-fired HTTP POST. SQL
-is always the source of truth. Long-lived hosts use an in-process retry loop as
-a best-effort safety net; serverless deployments must use an external durable
-sweep when recovery cannot depend on a process staying alive.
-
-Do not run agent loops inside the webhook handler itself. Do not rely on
-fire-and-forget `Promise`s after `return`ing from a serverless handler — they get
-killed when the function freezes.
-
-## Why
-
-Messaging platforms expect a 200 response within a tight window — Slack will
-retry after 3 seconds, and a retried event triggers duplicate agent runs. At the
-same time, an agent loop replying to the message can take 30–60+ seconds because
-it may make multiple LLM calls and tool calls.
-
-Past attempts that don't work cross-host:
-
-- **Fire-and-forget `Promise.then(...)` after returning** — Lambda/Vercel/CF
-  freeze the execution context the moment the response goes out. The promise
-  is silently killed, the user gets no reply, and there's no error in the
-  logs.
-- **A platform background function as the queue** — host-specific execution is
-  useful as a delivery mechanism, but it cannot replace the SQL row or atomic
-  claim shared by every host.
-- **Cloudflare `event.waitUntil()`** — CF Workers only, not portable.
-- **Vercel Fluid / `after()`** — Vercel-only, gated behind specific runtimes.
-- **A long-lived in-process queue** — fine on a single Node box, but on
-  serverless every cold start gets a fresh queue and any pending work is
-  lost.
-
-The only universal answer: **persist the work, then trigger a brand new
-function execution to do it.** SQL is the queue, a self-webhook is the trigger,
-and a recurring job is the safety net.
-
-## The Flow
-
-```
-┌──────────┐    1. POST /integrations/:platform/webhook
-│ Platform │────────────────────────────────────────────►┌──────────────────┐
-└──────────┘                                             │ Webhook handler  │
-                                                         │ (function exec 1)│
-                                                         └──────────────────┘
-                                                                  │
-                            2. INSERT INTO integration_pending_tasks
-                                 (status='pending', payload=...)
-                                                                  │
-                            3. dispatch POST /integrations/process-task
-                                 — portable self-fire by default
-                                 — acknowledged background handoff when enabled
-                                                                  │
-                            4. return 200 to platform ◄───────────┘
-
-                                                         ┌──────────────────┐
-                          5. POST arrives at processor   │ Processor        │
-                             (separate fresh function)   │ (function exec 2)│
-                                                         └──────────────────┘
-                                                                  │
-                            6. claimPendingTask(id) → status='processing'
-                            7. runAgentLoop(...) — full timeout budget here
-                            8. adapter.sendResponse(...) back to platform
-                            9. markTaskCompleted(id)
-
-
-                          ┌──────────────────────────────────────────────┐
-                          │  Recovery sweep (every 60s) — safety net    │
-                          │  Re-fires processor for tasks stuck in       │
-                          │  'pending' or 'processing' beyond timeout.   │
-                          │  Caps retries at 3 then marks 'failed'.      │
-                          └──────────────────────────────────────────────┘
-```
-
-The webhook handler does as little as possible. The fresh function execution
-that handles `_process-task` gets its own full timeout budget for the agent
-loop.
-
-## Key Files
-
-| File                                                                    | Purpose                                                                |
-| ----------------------------------------------------------------------- | ---------------------------------------------------------------------- |
-| `packages/core/src/integrations/plugin.ts`                              | Mounts `/_agent-native/integrations/*` routes                          |
-| `packages/core/src/integrations/webhook-handler.ts`                     | Verifies signature, parses, enqueues task, fires processor             |
-| `packages/core/src/integrations/pending-tasks-store.ts`                 | SQL queue: `insertPendingTask`, `claimPendingTask`, `markTaskCompleted`, `markTaskFailed` |
-| `packages/core/src/integrations/pending-tasks-retry-job.ts`             | Recurring retry sweep (`startPendingTasksRetryJob`, `retryStuckPendingTasks`) |
-| `packages/core/src/integrations/integration-durable-dispatch.ts`        | Default-off acknowledged dispatch, scoped rollout, and outcome recording |
-| `packages/core/src/integrations/types.ts`                               | `PlatformAdapter`, `IncomingMessage`, `OutgoingMessage`                |
-| `packages/core/src/integrations/adapters/{slack,telegram,whatsapp,email,google-docs}.ts` | One adapter per platform                                               |
-
-## Routes
-
-All under `/_agent-native/integrations/`:
-
-| Method | Path                       | Purpose                                                       |
-| ------ | -------------------------- | ------------------------------------------------------------- |
-| POST   | `/:platform/webhook`       | Platform pings this. Verifies, enqueues, returns 200 quickly. |
-| POST   | `/process-task`            | Processor target. Claims a task and runs the agent loop.      |
-| POST   | `/retry-stuck-tasks`       | Signed, bounded recovery sweep for durable schedulers.        |
-| GET    | `/status`                  | All integrations status (settings UI).                        |
-| GET    | `/:platform/status`        | One platform's status.                                        |
-| POST   | `/:platform/enable`        | Enable an integration.                                        |
-| POST   | `/:platform/disable`       | Disable an integration.                                       |
-| POST   | `/:platform/setup`         | Platform-specific setup (e.g. Telegram webhook registration). |
-
-## SQL Schema
-
-The pending-task queue lives in `integration_pending_tasks`:
-
-```sql
-CREATE TABLE IF NOT EXISTS integration_pending_tasks (
-  id                 TEXT    PRIMARY KEY,
-  platform           TEXT    NOT NULL,
-  external_thread_id TEXT    NOT NULL,
-  payload            TEXT    NOT NULL,   -- JSON-serialized IncomingMessage
-  owner_email        TEXT    NOT NULL,
-  org_id             TEXT,
-  status             TEXT    NOT NULL,   -- pending | processing | completed | failed
-  attempts           INTEGER NOT NULL DEFAULT 0,
-  dispatch_attempts  INTEGER NOT NULL DEFAULT 0,
-  last_dispatch_at   INTEGER,
-  last_dispatch_outcome TEXT,
-  dispatch_scope     TEXT,             -- persisted channel scope for recovery
-  error_message      TEXT,
-  created_at         INTEGER NOT NULL,
-  updated_at         INTEGER NOT NULL,
-  completed_at       INTEGER
-);
-CREATE INDEX IF NOT EXISTS idx_pending_tasks_status_created
-  ON integration_pending_tasks(status, created_at);
-CREATE INDEX IF NOT EXISTS idx_pending_tasks_dispatch_scope
-  ON integration_pending_tasks(platform, dispatch_scope);
-```
-
-The store layer creates this lazily on first use via `ensureTable()` and uses
-`intType()` from `db/client.ts` so it works on both SQLite and Postgres.
-
-`claimPendingTask` is the critical concurrency primitive: it atomically flips
-`pending` → `processing` and increments `attempts`, returning `null` if another
-worker beat us to it. Both the initial dispatch and every recovery sweep
-funnel through the same processor endpoint, and `claimPendingTask` is what
-prevents the same task from being processed twice.
-
-### Netlify durable recovery
-
-The portable self-dispatch remains the default. To emit and use Netlify's
-acknowledged background worker plus a one-minute scheduled recovery function,
-set `AGENT_INTEGRATION_DURABLE_DISPATCH=true` at build and runtime. A production
-rollout can be narrowed with the comma-separated
-`AGENT_INTEGRATION_DURABLE_DISPATCH_SCOPES` allowlist. Supported values are
-`<platform>:*`, `<platform>:<external-thread-id>`, and, for adapters that expose
-one, `<platform>:<channel-id>` (for example `slack:C123`).
-Channel-scoped handoffs persist that scope separately from the provider thread
-identity so a later bounded recovery sweep applies the same allowlist decision.
-
-Workspace deploys emit this pair only for the Dispatch control-plane app, which
-owns workspace messaging integrations. Standalone templates emit their own
-pair when the same flag is enabled.
-
-The background handoff waits only for Netlify's enqueue acknowledgement, not
-for the agent loop. A failed or non-2xx acknowledgement falls back to the
-portable processor. The scheduled function calls the HMAC-authenticated,
-bounded `/retry-stuck-tasks` route; its atomic compare-and-set update prevents
-overlapping sweeps from dispatching the same stale row twice.
-Rows acknowledged by the 15-minute background worker use a 16-minute stale
-cutoff, while portable synchronous dispatches retain the shorter serverless
-cutoff. Apply that lease predicate before `LIMIT` so healthy long runs cannot
-hide recoverable work. The background processor writes its lease marker in the
-same atomic update that claims the row; best-effort dispatch telemetry is not
-trusted for replay safety.
-
-## Adding a New Platform Adapter
-
-1. **Implement `PlatformAdapter`** in `packages/core/src/integrations/adapters/<platform>.ts`:
-
-   ```ts
-   export function myPlatformAdapter(): PlatformAdapter {
-     return {
-       platform: "myplatform",
-       label: "MyPlatform",
-       getRequiredEnvKeys: () => [
-         { name: "MYPLATFORM_TOKEN", label: "MyPlatform Bot Token", scope: "global" },
-         { name: "MYPLATFORM_SIGNING_SECRET", label: "MyPlatform Signing Secret", scope: "global" },
-       ],
-       async handleVerification(event) {
-         // Platform-specific challenge response, if any
-         return { handled: false };
-       },
-       async verifyWebhook(event) {
-         // Verify HMAC/signature with a server-side secret and constant-time comparison.
-         // Never leave this as a permissive stub in production.
-         return verifyMyPlatformSignature(event);
-       },
-       async parseIncomingMessage(event) {
-         // Map raw payload → IncomingMessage, or null to ignore
-         return null;
-       },
-       async sendResponse(message, context) {
-         // POST back to the platform's API
-       },
-       formatAgentResponse(text) {
-         return { text, platformContext: {} };
-       },
-       async getStatus(baseUrl) {
-         return { platform: "myplatform", label: "MyPlatform", enabled: false, configured: false };
-       },
-     };
-   }
-   ```
-
-2. **Register it** in `getDefaultAdapters()` inside `plugin.ts`. The webhook,
-   queue, processor, and retry job are shared infrastructure — you do not
-   write any of that per-adapter.
-
-3. **Declare required env keys** so the secrets/onboarding UI surfaces them.
-   See `secrets` and `onboarding` skills.
-
-4. **Update the platform's webhook URL** to point at
-   `${baseUrl}/_agent-native/integrations/<platform>/webhook`. For platforms
-   with a registration API (Telegram), implement `POST /:platform/setup`.
-
-Never hardcode bot tokens, signing secrets, verification tokens, webhook URLs,
-channel/customer identifiers, or copied platform payloads with real private data
-inside the adapter, tests, docs, prompts, or fixtures. `getRequiredEnvKeys()`
-declares credential names only. Values come from deployment configuration,
-registered secrets, OAuth, or scoped credential stores, and tests should use
-obvious fake placeholders.
-
-The adapter is **only** responsible for:
-
-- platform-specific verification (signatures, challenges)
-- payload → `IncomingMessage` mapping
-- agent text → platform format
-- delivering the response back to the platform
-
-It does **not** know about the queue, the processor, retries, or the agent
-loop. Those are handled by the shared webhook handler.
-
-### Slack non-message events
-
-Slack's Events API also sends events that are not agent messages, such as
-`link_shared` for app unfurls. Do not map those into `IncomingMessage` unless
-they should actually run the agent. Handle them as short, provider-specific
-webhook work: verify the Slack signature, return `200 OK` quickly, and call the
-provider API needed for the event (`chat.unfurl` for link previews). If a single
-Slack app must handle both agent chat and app unfurls, put a dispatcher in front
-of the one Slack Events Request URL and route message events to the integration
-webhook flow while routing `link_shared` to the app-specific unfurl handler.
-
-## Long-Running Agent Work
-
-The processor endpoint runs in a fresh function execution with its own full
-timeout (typically 30–60s on Netlify/Vercel, longer on background-friendly
-hosts). That budget is dedicated entirely to the agent loop — there is no
-platform-side timer racing it.
-
-If a single agent run might exceed the function timeout (large multi-step
-plans, deep delegation chains), the agent should:
-
-1. Send an interim acknowledgement back to the platform so the user knows the
-   request landed (`adapter.sendResponse({ text: "Working on it..." })`).
-2. Persist intermediate state in chat-thread data, application state, or a
-   recurring job so the next invocation can pick up where this one left off.
-
-The retry job will only re-fire tasks stuck in `processing` for over 5 minutes,
-so a normal long-running reply is safe.
-
-## Cross-Platform Considerations
-
-- **Portable correctness, optional host acceleration.** Every host uses SQL,
-  HMAC-authenticated processor routes, and atomic claims. A host-specific
-  background function or scheduler may provide a more reliable wake-up, but
-  disabling it must preserve the portable path.
-- **No assumed runtime.** The processor endpoint is a normal H3 handler under
-  `/_agent-native/`. It runs wherever the rest of the framework runs.
-- **No persistent in-memory state.** The dedup map in the webhook handler is
-  best-effort only; the SQL queue is the source of truth. Any cold start
-  loses the dedup map but the queue stays consistent.
-- **Postgres + SQLite both supported.** `claimPendingTask` uses `RETURNING` on
-  Postgres and a re-read on SQLite. No platform-specific SQL.
-- **Self-webhook URL resolution.** The processor URL is built from
-  `WEBHOOK_BASE_URL`, `APP_URL`, or `URL` env vars (with `localhost:3000` as
-  the dev fallback). Templates that change their public URL must keep one of
-  these set.
-
-## Why Fire-and-Forget on Serverless Is Unreliable
-
-The portable webhook path gives the outbound processor request a short head
-start but does not wait for the response body, so that initial dispatch is
-**not** guaranteed to complete before the function freezes. On a long-lived
-host, the in-process retry loop is a best-effort safety net. On Netlify with
-durable dispatch enabled, the initial handoff is acknowledged and the external
-scheduled function supplies the recovery wake-up for cases where:
-
-- The serverless platform froze the handler before the outbound `fetch`
-  flushed its bytes.
-- The processor function 502'd or cold-started slow enough to time out.
-- The processor itself was killed mid-agent-loop (function timeout, container
-  shutdown, deploy mid-run).
-
-Tasks stuck in `pending` for >90s or `processing` for >5min get re-fired up to
-3 times. After 3 attempts they're marked `failed` permanently so we stop
-spamming the processor.
-
-**Never assume the initial dispatch succeeded.** Rely on the SQL queue, atomic
-claim, and a recovery mechanism whose lifetime is independent of the original
-request. An in-process timer alone is not that mechanism on serverless.
-
-## Debugging Checklist
-
-1. **Platform sent the webhook?** Check the platform's delivery logs (Slack
-   admin, Telegram `getWebhookInfo`).
-2. **Webhook handler returned 200?** If not, the platform retries — look for
-   duplicate task rows. Signature failures return 401.
-3. **Task in the queue?** `SELECT * FROM integration_pending_tasks WHERE
-   external_thread_id = '...' ORDER BY created_at DESC LIMIT 5`.
-4. **Status?** `pending` means the processor never picked it up — check that
-   `_process-task` is reachable from the box itself (the self-fetch must work
-   over the public URL). `processing` for over 5 minutes means the processor
-   died mid-run — a live recovery sweep will pick it up.
-5. **Failed?** Check `error_message` and `attempts`. After 3 attempts the row
-   is parked at `failed` and won't be retried.
-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
-- `recurring-jobs` — Pattern the retry job follows
-- `actions` — When to use an action vs a webhook
-- `secrets` — Registering platform tokens
-- `onboarding` — Surfacing setup steps for each platform
-- `delegate-to-agent` — How the processor invokes the agent loop

package/dist/templates/workspace-core/.agents/skills/internationalization/SKILL.md

@@ -1,82 +0,0 @@
----
-name: internationalization
-description: >-
-  How to add or edit localized UI copy in agent-native apps. Use when adding,
-  removing, or changing user-visible interface text, prompts, toasts, labels,
-  empty states, or date/number/list formatting.
-scope: dev
-metadata:
-  internal: true
----
-
-# Internationalization
-
-## Rule
-
-Visible framework/template UI copy belongs in the app's i18n catalog, not
-inline in components. When you add or edit UI text, update the English source
-catalog first, update existing locale catalogs, and run the i18n guard.
-
-## Catalogs
-
-Templates use `app/i18n/`:
-
-- `en-US.ts` is the canonical source tree and fallback.
-- Other locale files keep the same non-plural keys and the same placeholders.
-- `index.ts` exports an `AgentNativeI18nCatalog` with English bundled and
-  non-English catalogs loaded by dynamic import.
-
-Use BCP-47 filenames from the supported set: `en-US`, `zh-CN`, `es-ES`,
-`fr-FR`, `de-DE`, `ja-JP`, `ko-KR`, `pt-BR`, `hi-IN`, `ar-SA`.
-
-If an app only ships translations for a subset of that set, set
-`supportedLocales` on the `AgentNativeI18nCatalog` to that subset. Without it,
-`<LanguagePicker />` lists every framework-supported locale regardless of
-whether `loadMessages` can actually resolve it.
-
-## UI Pattern
-
-- Wrap apps with `AppProviders i18n={{ catalog: i18nCatalog }}`.
-- Read strings with `useT()` and keep keys stable.
-- Sidebar apps should expose a `/settings` route in the app sidebar. Put
-  `<LanguagePicker />` in that settings page, usually in a Language or General
-  section, and keep the header language icon only as a quick-access shortcut.
-- Settings pages should include an "Agent settings" row/card that calls
-  `openAgentSettings()` from `@agent-native/core/client` to open the right
-  agent sidebar's Settings tab. Localize the title, description, and button.
-- Use `useFormatters()` for dates, numbers, relative time, and lists instead
-  of embedding formatted values in translation strings.
-- Do not translate stable identifiers: action names, route names, enum values,
-  app-state keys, database values, protocol fields, env var names, or provider
-  names.
-
-## Plurals And Placeholders
-
-Plural strings use i18next/CLDR suffixes. Do not force every locale to copy
-English plural categories:
-
-- English uses `_one` and `_other`.
-- Chinese and Japanese usually use `_other`.
-- Arabic uses `_zero`, `_one`, `_two`, `_few`, `_many`, and `_other`.
-
-Keep interpolation placeholders identical across locales, such as
-`{{count}}`, `{{name}}`, or ICU-style `{count}` arguments.
-
-## RTL
-
-New UI should be RTL-safe. Prefer logical CSS utilities/properties such as
-`ms-*`, `me-*`, `ps-*`, `pe-*`, `start-*`, `end-*`, `text-start`, and
-`text-end` when direction matters. Avoid hardcoded left/right positioning for
-new localized UI unless it is genuinely physical.
-
-## Verification
-
-Run:
-
-```bash
-pnpm guard:i18n-catalogs
-```
-
-For broader changes, also run the affected template tests and `pnpm typecheck`.
-Machine translation is only a starting point; high-visibility strings need
-human review.

package/dist/templates/workspace-core/.agents/skills/mvp-followup/SKILL.md

@@ -1,52 +0,0 @@
----
-name: mvp-followup
-description: >-
-  Use when asking what to do next after a feature pass while avoiding bloat and
-  checking for unfinished MVP work.
-scope: dev
-metadata:
-  internal: true
----
-
-# MVP Follow-Up
-
-## Rule
-
-Recommend or execute only closeout work that makes the current MVP more real,
-verified, documented, or shippable. Do not propose new product scope unless
-there is a clear blocker to the MVP working for real users.
-
-## Workflow
-
-1. Identify the current feature or thread outcome.
-2. Check for unfinished work in this order:
-   - failing or skipped verification
-   - unreviewed real-data pilot results
-   - pending review/proposals/approval queues
-   - docs that no longer match behavior
-   - unrelated dirty files that block full prep/ship hygiene
-3. Recommend the smallest next batch that closes those gaps.
-4. Explicitly skip tempting bloat: new integrations, dashboards, settings,
-   abstractions, or extra UI unless they directly unblock real use.
-5. If the user says "do it", run the closeout work in parallel where safe and
-   keep edits minimal.
-
-## Output Shape
-
-Lead with the concrete next step. Keep the list short. Separate:
-
-- **Do now**: validation, real pilot, docs, or bug fixes.
-- **Defer**: useful ideas that should wait for real user feedback.
-- **Blocker**: any specific user/manual action needed.
-
-## Verification Bias
-
-Prefer non-mutating checks when the worktree has unrelated dirty files. Use full
-`pnpm prep` only when it will not rewrite someone else's concurrent work.
-
-## Related Skills
-
-- `qa`
-- `ship`
-- `adding-a-feature`
-- `capture-learnings`

package/dist/templates/workspace-core/.agents/skills/native-navigation/SKILL.md

@@ -1,67 +0,0 @@
----
-name: native-navigation
-description: >-
-  Use when adding or reviewing UI navigation so internal routes preserve
-  normal SPA behavior plus Cmd/Ctrl-click and middle-click new-tab semantics.
-scope: dev
----
-
-# Native Navigation
-
-## Rule
-
-Pure navigation must render a real React Router `<Link>` for same-SPA routes,
-a native `<a href>` for external/public or explicit new-tab destinations, or a
-shadcn `Button asChild` wrapper around one. Do not use a button whose only job
-is to call `navigate()`, `window.open()`, or `window.location`.
-
-## Why
-
-Browser modifier-click, middle-click, keyboard activation, accessibility, and
-normal client-side routing come from real links. Imperative JavaScript
-navigation hides the destination and blocks those browser semantics.
-
-## How
-
-```tsx
-import { Link } from "react-router";
-
-<Link to={`/items/${item.id}`}>...</Link>
-
-<Button asChild>
-  <Link to="/settings">Settings</Link>
-</Button>
-
-<a href={previewUrl} target="_blank" rel="noopener noreferrer">
-  Preview
-</a>
-```
-
-- Use `Link` for same-SPA internal routes.
-- Use `<a>` when the URL is external, crosses an app/public boundary, is an
-  auth or sign-in destination, or intentionally opens in a new tab.
-- Preserve query strings and hashes in `to` or `href`.
-- For cards with nested actions, link only the non-interactive card region or
-  use a transparent Link overlay; never nest links or buttons.
-- If selection mode changes click behavior, prevent default only for an
-  unmodified primary click and preserve modified clicks.
-
-Keep imperative navigation for post-mutation redirects, OAuth and popup flows,
-downloads, media/blob URLs, playback, keyboard shortcuts, and stateful tabs.
-
-## Review
-
-Search for `onClick={() => navigate`, `window.open`, `window.location`,
-`onAuxClick`, and buttons whose only purpose is routing. For each candidate,
-confirm whether it is pure navigation or a stateful workflow before changing
-it.
-
-Verify the rendered DOM exposes an `href`, then test normal click, Cmd/Ctrl-click,
-middle-click, keyboard Enter, and nested controls where applicable. Run oxfmt
-and focused app tests or typechecks for the touched package.
-
-## Related Skills
-
-- `client-side-routing`
-- `frontend-design`
-- `shadcn-ui`