Preserve CSS easing values in Motion previews

.agents/skills/actions/SKILL.md

@@ -22,6 +22,8 @@ Before creating any custom route for app data, check `actions/` and the action t
 
 An action may call a provider API, validate data, and persist records without being an AI feature — keep it deterministic, focused, and independently useful to the agent. Don't put LLM calls or a second model runtime in app actions.
 
+The sanctioned model-backed exception is `@agent-native/core/decisions` for capability-aware classification and scoring, and it returns a result without performing or authorizing the selected action.
+
 When a workflow is research, analysis, generation, recommendation, or synthesis — or spans several provider calls and writes — route it to the AgentSidebar via `sendToAgentChat({ openSidebar: true })` and let the agent orchestrate focused actions instead of hiding an AI-shaped workflow behind one opaque `generate-*`/`create-*` action just because its implementation happens to be deterministic.
 
 ## How to Create an Action
@@ -105,7 +107,7 @@ for interrupted-run recovery.
 
 An action that hands control back to the user (question form, intake dialog) sets `endsTurn: true`; that hides it from MCP/WebMCP/A2A unless `mcpTool: true` is explicit — `references/action-fields.md`. For external-agent integrations, use the external-agents documentation slug listed by `agent-native-docs`.
 
-Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
+Every new action declares `outputSchema`: it types the action's return and is enforced strictly by default (`guard:action-output-schema`). Declare its failure codes with `defineActionErrors` and fail through them. Reach for `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
 ### Write receipts
 
@@ -176,7 +178,7 @@ Everything else — CRUD, settings, search, list/detail reads, auth state, anyth
 - **Do** render `actionErrorMessage(error) ?? yourCopy` in UI, never bare `error.message`. The message keeps an `Action <name> failed:` prefix that belongs in a console, so a toast built from it reads "Action update-brand-kit failed: That name is taken." The helper returns only what the action wrote, and `undefined` when nothing did (network drop, proxy HTML page), which is why the fallback is not optional.
 - **Do** pass a real `errorCode` when the agent should branch on the failure rather than re-read it. Codes other than the default `action_failed` are appended to the tool result as `(errorCode: not_found)`, on both the in-app agent and MCP. `details` follow as an `Error details: {...}` JSON line, and as `structuredContent.error` over MCP, capped at 2,000 characters, so keep them to what the agent acts on next: ids, limits, field names. The status never reaches either.
 - **Don't** re-export actions as REST — `/_agent-native/actions/:name` is already the REST surface; duplicating it under `/api/*` hides the operation from agents.
-- **Don't** reach for provider integrations, `outputSchema`, `authorize`, `needsApproval`, or `_agentImages` without checking `references/` first — each has sharp edges covered there, not here.
+- **Don't** reach for provider integrations, `authorize`, `needsApproval`, or `_agentImages` without checking `references/` first — each has sharp edges covered there, not here.
 
 ## Troubleshooting
 

.agents/skills/actions/references/action-fields.md

@@ -73,17 +73,34 @@ export default defineAction({
   description: "Summarize a thread.",
   schema: z.object({ threadId: z.string() }),
   outputSchema: z.object({ summary: z.string(), messageCount: z.number() }),
-  outputErrorStrategy: "warn", // default; "strict" | "fallback"
-  // outputFallback: { summary: "", messageCount: 0 }, // used only by "fallback"
   run: async ({ threadId }) => {
     /* ... */
   },
 });
 ```
 
-- `"warn"` (default) — `console.warn` the issues and return the **original** result unchanged. Non-breaking, with one exception: a connection request or stop signal thrown while the result is checked (from a transform or refinement) still ends the call as that signal, with a framework message in place of its own.
-- `"strict"` — throw `ActionOutputContractError` (`errorCode: "output_contract_violation"`) so a buggy action surfaces loudly.
-- `"fallback"` — return `outputFallback` in place of the invalid result.
+Every new action declares `outputSchema` (`guard:action-output-schema` fails a new `defineAction` without one). The action's return type is inferred from it, and `run` must return what the schema accepts, so a drifting result is a compile error.
+
+- `"strict"` (default) — throw `ActionOutputContractError` (`errorCode: "output_contract_violation"`) so a buggy action surfaces loudly.
+- `"warn"` — `console.warn` the issues and return the **original** result unchanged. Only for an existing schema you are still fixing. A connection request or stop signal thrown while the result is checked (from a transform or refinement) still ends the call as that signal, with a framework message in place of its own.
+- `"fallback"` — deprecated, and the guard rejects new uses: it returns `outputFallback`, a value callers cannot tell from a real result.
+
+Declare the codes an action fails with as a closed set, and fail through it so a misspelled code does not compile:
+
+```ts
+const errors = defineActionErrors("thread_not_found", "thread_locked");
+export default defineAction({
+  /* schema, outputSchema, */
+  errors, // published as `errorCodes` on the definition
+  run: async ({ threadId }) => {
+    if (!thread)
+      errors.noWrite("Thread not found.", "thread_not_found", {
+        statusCode: 404,
+      });
+    /* ... */
+  },
+});
+```
 
 On success the validated value is returned, so coercion/defaults on `outputSchema` apply. Omit `outputSchema` and behavior is byte-for-byte unchanged (no wrapping).
 

.agents/skills/decisions/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: decisions
+description: >-
+  How to use `@agent-native/core/decisions` for capability-aware classification
+  and scoring. Use when implementing or reviewing decision evaluation, provider
+  ordering, per-provider thresholds, or decision-result caches.
+scope: dev
+metadata:
+  internal: true
+---
+
+# Decisions
+
+## Rule
+
+Use `decide()` to classify or score supplied inputs. It returns a result and
+never performs, authorizes, or replaces the action selected from that result.
+
+## How
+
+Pass an explicit `ownerEmail`, an `input` string or array of parts, and named
+`questions` to `decide()` from `@agent-native/core/decisions`:
+
+```ts
+import { decide } from "@agent-native/core/decisions";
+
+const result = await decide({
+  ownerEmail: "owner@example.com",
+  input: [{ type: "text", text: "Please cancel Friday's lunch reservation." }],
+  questions: [
+    {
+      type: "predicate",
+      name: "isCancellationRequest",
+      instructions: "Does the message ask to cancel a reservation?",
+    },
+  ],
+});
+```
+
+`input` can be a plain string or contain text, structured JSON, or an image URL.
+Questions are named and use one of these shapes:
+
+| Type | Fields | Use |
+| --- | --- | --- |
+| `predicate` | `name`, `instructions` | Evaluate one stated predicate |
+| `choice` | `name`, `instructions`, `choices: { value: string, description: string }[]` | Choose among the supplied string values |
+| `score` | `name`, `instructions`, `levels: { label: string, description: string }[]` | Score against 2–10 ordered levels |
+
+Provider and model capabilities can differ. Treat question support as
+capability-aware. Only claim a provider/model supports a question type after
+that combination has been verified. An `ok` result includes `provider`, `model`, and `answers` keyed by question name;
+`cached` and `usage` are optional. A `not_configured` result includes the
+`missing_credentials` reason and configured provider list. A `failed` result has
+a typed reason and may include `provider` and `questionNames`. Handle these
+statuses as distinct outcomes; never turn a failure into an answer.
+
+## Provider routing and caches
+
+Provider order is configurable per workspace. New customer workspaces try
+Builder Jev first, then a personal Jev key, then OpenAI. Within Jev, the
+Builder gateway is tried before falling back to a direct key. If no provider
+is configured, `decide()` returns `not_configured`.
+
+`getDecisionsStatus()` reports credential readiness separately from provider
+capabilities. The Builder Jev proxy is verified for `predicate` and `choice`.
+Jev `score` remains unverified and disabled by its capability flag, so
+`decide()` skips Jev for score questions and continues to the next configured
+provider. A Jev-only score request returns `failed` with
+`unverified_capability`. The OpenAI Decisions API supports scores with 2–10
+ordered levels; its request and response mapping is covered by documented
+fixtures.
+
+Key any per-provider threshold or cache by both provider and model. `cacheKey`
+enables caching only when supplied. Cache identity includes the owner,
+organization, provider, model, cache key, input, and questions. The in-memory
+cache has a 60-second TTL and a 256-entry cap.
+
+## Related skills
+
+- **actions** — keep action behavior focused and deterministic.

.changeset/core-decisions.md

@@ -0,0 +1,5 @@
+---
+"@agent-native/core": minor
+---
+
+Add a typed Decisions API with route-aware capability reporting, verified Jev and OpenAI score support, bounded inputs, provider-order validation, credential-aware cancellation and timeout handling, and validated evaluation metrics with target-recall threshold selection.

.changeset/fresh-handoff-heartbeat.md

@@ -0,0 +1,5 @@
+---
+"@agent-native/core": patch
+---
+
+Keep claimed background chat runs alive during setup and abort timed-out setup.

.changeset/strict-action-contracts.md

@@ -0,0 +1,5 @@
+---
+"@agent-native/core": minor
+---
+
+Make action results a typed, enforced contract. An action that declares `outputSchema` now defaults to `outputErrorStrategy: "strict"`: a result that does not match fails with `ActionOutputContractError` (`errorCode: "output_contract_violation"`) instead of logging a warning and returning the unchecked value. Pass `outputErrorStrategy: "warn"` to keep the old behavior while you fix a schema. `defineAction` now infers the action's return type from `outputSchema`, and its `run` must return a value the schema accepts, so a drifting result is a compile error. `outputErrorStrategy: "fallback"` and `outputFallback` are deprecated, because a fallback hides a broken result behind a plausible one. New `defineActionErrors(...codes)` declares an action's closed set of error codes; its `fail` and `noWrite` accept only those codes, and passing it to `defineAction` as `errors` publishes them as `errorCodes` on the definition. The CLI sources are now type-checked under `strict`, which fixes `agent-native agents list --app` and `--capabilities` throwing a `ReferenceError`. The shared `tsconfig.base.json` and the scaffolded workspace base now turn on `noUncheckedIndexedAccess`, `exactOptionalPropertyTypes`, `noImplicitOverride`, and `noFallthroughCasesInSwitch`. An app that extends `@agent-native/core/tsconfig.base.json` gets them on upgrade; set any of them to `false` in the app's own `tsconfig.json` to keep compiling while you fix the errors they report.

.changeset/strict-compiler-flags-packages.md

@@ -0,0 +1,13 @@
+---
+"@agent-native/agentkit": patch
+"@agent-native/creative-context": patch
+"@agent-native/dispatch": patch
+"@agent-native/otel": patch
+"@agent-native/pinpoint": patch
+"@agent-native/recap-cli": patch
+"@agent-native/scheduling": patch
+"@agent-native/skills": patch
+"@agent-native/toolkit": patch
+---
+
+Compile with `noImplicitOverride` and `noFallthroughCasesInSwitch`, and, where the code already passes them, `noUncheckedIndexedAccess` and `exactOptionalPropertyTypes`. Optional fields that legitimately hold `undefined` are now typed `T | undefined`. No runtime behavior changes.

.github/workflows/ci.yml

@@ -2029,6 +2029,9 @@ jobs:
       - name: Test legacy MCP hint baseline guard
         run: pnpm test:no-new-legacy-mcp-hints
 
+      - name: Test strictness ratchet guards
+        run: pnpm test:strictness-guards
+
       - name: Test Neon transfer alert and offline backtest
         run: pnpm test:neon-transfer-alert
 

AGENTS.md

@@ -15,6 +15,7 @@ this file records only invariants.
 A few entry points:
 
 - `adding-a-feature` — four-area feature checklist.
+- `decisions` — when using capability-aware classification and scoring.
 - `content-product-development` — Content's product contract and shared changes.
 - `writing-agent-instructions` — before editing instructions, skills, or tool/action descriptions.
 - `verifying-changes` — exercise the broken path before calling a fix done.
@@ -137,12 +138,15 @@ exist, and both are narrow on purpose.
 Code, and a human equally). `pnpm guards --list` prints the current set;
 `no-silent-coercion`, `no-raw-colors`, `no-boot-data-work`,
 `no-heavy-dashboard-list-reads`, `no-unbounded-table-reads`,
-`no-bare-error-in-actions`, `external-result-contract`, and
-`no-source-reading-tests` check only lines this branch added, so the
+`no-bare-error-in-actions`, `external-result-contract`,
+`no-source-reading-tests`, `action-output-schema`, `strict-lint`, and
+`compiler-strictness` check only lines this branch added, so the
 pre-existing backlog stays a separate cleanup. Each guard has a documented
 opt-out pragma, and every opt-out is a decision a reviewer should see.
-`no-new-legacy-mcp-hints` has none: the MCP `destructiveHint` baseline only
-shrinks.
+`no-new-legacy-mcp-hints`, `no-new-escape-hatches`, and `compiler-strictness`
+have none: the MCP `destructiveHint` baseline, each file's count of `any`,
+`!`, and suppression comments, and the list of tsconfig strictness opt-outs
+only shrink.
 
 A guard reports three outcomes, not two: exit 0 passed, exit 1 failed, exit 2
 could not run. A diff-scoped guard that cannot resolve a base ref exits 2 via

community-templates/account-expert/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/account-expert/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {

community-templates/account-tiering/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/account-tiering/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {

community-templates/call-follow-up-drafter/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/call-follow-up-drafter/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {

community-templates/churn-early-warning/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/churn-early-warning/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {

community-templates/demo-clip-library/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/demo-clip-library/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {

community-templates/linkedin-icp-prospect-tracker/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/linkedin-icp-prospect-tracker/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {

community-templates/linkedin-signal-watch/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/linkedin-signal-watch/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {

community-templates/outbound-in-your-voice/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/outbound-in-your-voice/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {

community-templates/win-loss-memo/app/components/ui/toolkit-provider.tsx

@@ -8,7 +8,7 @@ import { Button } from "@/components/ui/button";
 import { designSystem } from "@/design-system";
 
 const components: ToolkitComponents = {
-  Button: Button as ToolkitComponents["Button"],
+  Button: Button as NonNullable<ToolkitComponents["Button"]>,
 };
 
 export function AppToolkitProvider({ children }: { children: ReactNode }) {

community-templates/win-loss-memo/tsconfig.json

@@ -1,6 +1,8 @@
 {
   "extends": "@agent-native/core/tsconfig.base.json",
   "compilerOptions": {
+    "noUncheckedIndexedAccess": false,
+    "exactOptionalPropertyTypes": false,
     "ignoreDeprecations": "6.0",
     "rootDirs": [".", "./.react-router/types"],
     "paths": {