@nifrajs/cli 3.2.0 → 3.5.0

package/docs/llms-full.txt

@@ -21,12 +21,20 @@ _Extracted from the docs at nifra.dev/docs._
 
 ## Nifra - Getting started
 
-> Get started with Nifra: install, server, typed client, loaders, deploy.
+> Get started with Nifra: typed backend, agentic UI, bounded agent runs, full-stack SSR, and portable deployment.
 
-Nifra is a contract-first TypeScript framework. Start with just a typed backend - like Hono or
-Elysia - and the client infers its types with zero codegen. Add a frontend only when you need
-one: the same route model then drives SSR across React, Solid, Vue, Preact, and Svelte, on
-Bun, Node, Deno, and the edge.
+Nifra is a contract-first TypeScript framework for applications with agents in the loop. Start
+with just a typed backend - like Hono or Elysia - and the client infers its types with zero
+codegen. Add a full-stack UI, a bounded agent runtime, or page-local WebMCP when you need one:
+the same contracts drive all of them across Bun, Node, Deno, and the edge.
+
+### One app, two agent loops
+
+A coding agent can inspect the live project, change it, run real requests, and prove the result.
+A user-facing agent can discover explicit page tools, stream progress into the UI, predict a
+state change, and reconcile it with the server. Both use the same typed capabilities and
+verification boundary. Start with the [agent layer](/docs/agents) or the
+[WebMCP & predictive UI guide](/docs/webmcp) when you are ready to add them.
 
 ### Install
 
@@ -97,7 +105,7 @@ See the [benchmarks](/benchmarks) for how it performs.
 
 ## Nifra vs. other frameworks - the honest comparison
 
-> How Nifra compares to the full-stack frameworks (Next.js, Nuxt, SvelteKit, Remix, TanStack Start) - and, as a standalone backend, to Hono and Elysia. Five UI frameworks, five runtimes, end-to-end types, and an AI-agent toolchain no competitor ships.
+> How Nifra compares to the full-stack frameworks (Next.js, Nuxt, SvelteKit, Remix, TanStack Start) - and, as a standalone backend, to Hono and Elysia. Five UI frameworks, five runtimes, end-to-end types, and an agentic application layer built around typed capabilities.
 
 Honest comparison. Nifra is a **full-stack framework first** - five UI libraries and five runtimes
 from one core, with loaders, actions, streaming, and a typed data layer - and a
@@ -192,13 +200,13 @@ to full-stack later without a rewrite.
 regex), but a router is **~1% of a real request** - the time goes to middleware, validation,
 context, and serialization. In the current matrix (median of 5 full runs) Nifra
 **tops the framework field on Bun** - level with Elysia on `GET /users/:id` at
-101% of the raw-runtime ceiling, 105% of Elysia on the validated `POST` - and
+108% of the raw-runtime ceiling, 106% of Elysia on the validated `POST` - and
 **leads every framework on Deno** on both workloads. On **Node** it
-**leads the framework field too** - ahead of Fastify by ~12% on the validated
-`POST` (96% of the raw-Node ceiling) and level-to-ahead on GET, with Elysia, Hono,
+**leads the framework field too** - ahead of Fastify by ~8% on the validated
+`POST` (92% of the raw-Node ceiling) and ahead on GET, with Elysia, Hono,
 and Express behind. In the realistic shape (security headers + CORS +
 bearer auth + cookies + validated query/body + a ~2.4 KB JSON response, measured with
-`oha`) Nifra runs at **103% of Elysia on GET and 108% on POST**. Treat benchmark
+`oha`) Nifra runs at **101% of Elysia on GET and 97% on POST**. Treat benchmark
 rows as same-run evidence, not a permanent law of nature.
 
 -
@@ -220,8 +228,8 @@ emitting a real 3.1 doc with field-level request/response schemas (+ Scalar UI).
 
 ### The AI-agent toolchain - Nifra-only
 
-No competitor - full-stack or backend - ships this. Every Nifra app is built to be edited by AI agents
-accurately:
+Nifra covers both sides of the agent loop: agents that edit your codebase and agents that are
+part of the product. Every surface is anchored to the same typed capability boundary:
 
 -
 `nifra mcp` - an MCP server exposing `nifra_context` (the project's typed
@@ -244,6 +252,18 @@ _document_ and Semgrep pattern-matches source text; neither sees the real route
 This is what makes agent-written routes safe to merge - an agent (or a human) cannot ship an
 unauthenticated write past it.
 
+-
+`@nifrajs/webmcp` - explicit page-local tools using the browser WebMCP standard,
+deterministic predictive UI, bounded receipts, and versioned reconciliation.
+`@nifrajs/ag-ui` streams the same run into a product UI, while
+`@nifrajs/agent-app` provides negotiated browser views, approvals, handoffs, and
+Run Studio projections.
+
+-
+`@nifrajs/agent` - bounded typed agent turns with budgets, approvals, cancellation,
+resumable evidence, shared state, and provider-neutral model ports.
+`@nifrajs/a2a` exposes the same runner to other agents without rewriting the core.
+
 ### Where Nifra fits
 
 Reach for Nifra when you want:
@@ -958,15 +978,48 @@ function Row({ id }: { id: string }) {
 const anyPending = useFetchers().some((f) => f.snapshot().pending)
 ```
 
-## Nifra - Rendering: SSG & ISR
+## Nifra - Rendering: SSR, streaming, SSG & ISR
 
-> Prerender static routes, enumerate dynamic ones, and cache rendered pages with stale-while-revalidate - on every runtime including the edge.
+> Render critical HTML first, stream deferred data progressively, prerender static routes, and cache rendered pages with stale-while-revalidate - on every runtime including the edge.
 
 Nifra renders on one framework-agnostic seam, so the same app can be server-rendered per
-request (the default), **prerendered** to static files at build (SSG), or cached and served
+request (the default), streamed progressively, **prerendered** to static files at build (SSG), or cached and served
 **stale-while-revalidate** (ISR) - and every strategy works on Bun, Node, Deno, **and**
 the edge.
 
+### Progressive rendering with `defer()`
+
+Keep critical loader data in the first HTML shell and mark slower, non-critical values with
+`defer()`. Nifra flushes the document shell and the adapter's rendered stream first,
+then sends each deferred resolution through `<Await>` without a second data
+fetch. The same protocol works for actions and soft navigations, including NDJSON on the client
+side.
+
+```ts
+import { defer } from "@nifrajs/web"
+
+export async function loader({ api }: LoaderArgs<typeof app>) {
+  return {
+    product: (await api.products.get()).data, // critical: rendered in the first shell
+    reviews: defer(api.reviews.get()),        // non-critical: streamed when ready
+  }
+}
+
+export default function Product(props: { data: LoaderData<typeof loader> }) {
+  return (
+    <>
+      <ProductSummary product={props.data.product} />
+      <Await resolve={props.data.reviews} fallback={<p>Loading reviews…</p>}>
+        {(reviews) => <Reviews items={reviews} />}
+      </Await>
+    </>
+  )
+}
+```
+
+This is request-time progressive SSR/partial rendering. It is distinct from build-time SSG:
+the shell is not a precomputed PPR artifact, and deferred values remain request-scoped.
+
 ### SSG - prerender at build
 
 Opt a static route into prerendering with `export const prerender = true`. Its
@@ -4240,11 +4293,13 @@ the command printed by the build.
 
 ## Nifra - Coding agents
 
-> Nifra's agent layer: live MCP tools for coding agents, bounded typed turns, resumable evidence, a coding-agent host, browser views, A2A and AG-UI bridges, and token-only telemetry.
+> Nifra's agent layer: live MCP tools, bounded repairable turns, native approvals, resumable evidence, content-free browser views, capability registry, decision inbox, Run Studio, A2A, and AG-UI.
 
 Nifra ships an MCP server. It is not a documentation lookup bolted onto a framework: an agent
 can read the project, learn the real API, run actual requests against the backend it just
-edited, and finish with a report of what the change proved.
+edited, and finish with a report of what the change proved. The same typed capabilities can
+power the agent inside your product through [WebMCP and predictive UI](/docs/webmcp)
+or stream into a product surface through AG-UI.
 
 ### One MCP, two ways to connect
 
@@ -4324,6 +4379,8 @@ nifra_check             # typecheck + lints, each with a structured fix
 nifra_fix               # applies the mechanical ones
 nifra_run    {request}  # a real request through the backend: status, headers, parsed body
 nifra_render {path}     # SSR a page route, returns the HTML
+nifra_inspect {port}    # recent dev-server request traces: status, duration, ISR hit/miss
+nifra_explain {error}   # turn a failure into a structured diagnostic and fix
 nifra_test              # bun test, bounded structured results
 
 # 4. What does it now prove?
@@ -4465,8 +4522,28 @@ bunx nifra-agent --backend pi --message "run the checks and explain failures"
 ```
 
 The public host keeps live queues and captured evidence bounded, filters verification process
-environments, and treats extensions as an explicit opt-in. The local process adapter and
-extension worker are crash-containment helpers, not hostile-code sandboxes.
+environments, and treats extensions as an explicit opt-in. Post-turn `check`,
+`assure`, or `test` gates emit `verification.completed` and
+`repair.required`; when enabled, the host sends a bounded repair prompt and reruns
+the gate until it passes or the attempt cap is reached. The local process adapter and extension
+worker are crash-containment helpers, not hostile-code sandboxes.
+
+```ts
+# Post-turn gates are opt-in. A failed gate becomes bounded repair work.
+bunx nifra-agent --backend pi --message "implement the change" \
+  --verify-after-turn check,assure --max-repair-attempts 2
+
+# Set --max-repair-attempts 0 for observe-only verification.
+```
+
+### Native approval protocol
+
+`@nifrajs/coding-agent` can pause a native tool call at the decision boundary and
+emit `approval.required` with an opaque approval id, action, capability, and bounded
+coordinates. Resolve it through the host or RPC with `approval.resolve`; the backend
+emits `approval.resolved` and only then executes the tool. Denial, cancellation,
+timeout, and closed sessions all fail closed, and `approvalTimeoutMs` bounds how long
+a pending decision can remain open.
 
 ### Expose the same agent to other clients
 
@@ -4509,11 +4586,15 @@ auth and authorization middleware, and scope every injected port to the request
 ### Browser views and the Workbench
 
 `@nifrajs/agent-app` is a backend-free browser SDK for negotiated commands, ordered
-and resumable event streams, approvals, handoffs, and Run Studio projections. Its public views
-contain structure - statuses, counters, coordinates, and error codes - rather than prompts,
-tool payloads, model output, or filesystem paths. The optional Workbench uses that same surface:
-run `bun run --filter '@nifrajs/workbench' dev -- --cwd /path/to/project` for the
-local browser client.
+and resumable event streams, approvals, handoffs, and Run Studio projections. It negotiates
+optional features including `approvals`, `checkpoint`,
+`fork`, `handoff`, `inbox`, `reload`,
+`resume`, and `workflows`, so a browser can degrade deliberately when a
+host does not offer one. Its public views contain structure - statuses, counters, coordinates,
+and error codes - rather than prompts, tool payloads, model output, or filesystem paths. The
+optional Workbench uses that same surface: run
+`bun run --filter '@nifrajs/workbench' dev -- --cwd /path/to/project` for the local
+browser client.
 
 ```ts
 import { AgentAppClient, HttpAgentTransport } from "@nifrajs/agent-app"
@@ -4532,14 +4613,30 @@ for await (const view of client.send("summarize the diff")) {
 }
 ```
 
+### Capability registry, decision inbox, and Run Studio
+
+The Workbench's `registry.list` view shows content-free identity cards for admitted
+capabilities: kind, name, version, schema digest, required capability tokens, and approval,
+retry, idempotency, and isolation classes. It never renders a prompt, input schema, tool
+payload, model output, or filesystem path.
+
+The `inbox` feature lists pending approval and handoff boundaries by exact structural
+coordinate - run, node, capability, child vector, request id, and expiry. Every approve, deny,
+assign, resolve, or cancel command carries that coordinate, so stale, mismatched, or expired
+decisions are refused by the host. `run.studio` projects the same bounded evidence
+into a run graph, retry/recovery timeline, eval comparison, and deterministic fault-injection
+view. These are presentation-safe views: content stays in the host.
+
 ### Evidence, streaming, and telemetry
 
 `@nifrajs/agent` runs bounded typed turns with tool contracts, budgets, approvals,
 resumable token-only evidence, model deltas, and a transient shared-state channel. Add an
 `evidenceLog` to the HTTP seams for SSE replay after a dropped connection; replay
-resumes evidence and never re-executes the turn. `@nifrajs/agent-telemetry` converts
-the same constrained evidence into fail-open OpenTelemetry run and step spans. Providers,
-credentials, durable storage, retention, and tenant policy remain application-owned ports.
+resumes evidence and never re-executes the turn. The additive run-lifecycle contract supplies
+content-free snapshots, ordered evidence refs, feature negotiation, handoff state, and cursor
+resume. `@nifrajs/agent-telemetry` converts the same constrained evidence into
+fail-open OpenTelemetry run and step spans. Providers, credentials, durable storage, retention,
+and tenant policy remain application-owned ports.
 
 ### Projects without a web config
 
@@ -4916,6 +5013,34 @@ export const app = createWebApp({
 This is the _global imports_ tier: one bundled stylesheet linked on every page (the
 common case - a global stylesheet or Tailwind output).
 
+#### Prefetch-safe aggregate CSS
+
+Vite's default CSS splitting can attach a new stylesheet when a prefetched lazy route module
+evaluates. If those selectors affect content already on the page, each attachment can trigger
+style recalculation and layout work. For an app whose stylesheet is already bounded (for
+example, one using atomic StyleX plus a small legacy CSS-Modules layer), opt into one aggregate
+CSS asset and deferred activation in the CLI config. The aggregate file is still content-hashed;
+only its activation is deferred until the browser has fetched it.
+
+```ts
+// nifra.config.ts - opt into Vite's single-file CSS path for apps that prefetch many lazy routes.
+export const cssCodeSplit = false
+export const cssLoading = "deferred"
+
+// cssCodeSplit: false emits one content-hashed stylesheet, so lazy module prefetch cannot attach a
+// new stylesheet for every route. cssLoading: "deferred" fetches that file with media="print"; the
+// generated client promotes it to media="all" after load/error/timeout and before hydration.
+// `nifra build` selects Vite automatically for this Vite-only output policy. The default stays
+// backward-compatible: split CSS + blocking links.
+// `cssLoading: "deferred"` must be paired with `cssCodeSplit: false` on Vite.
+```
+
+This is opt-in and Vite-specific. Nifra rejects `cssLoading: "deferred"` with split
+Vite CSS because that combination would leave the prefetch insertion problem in place. A failed
+or slow stylesheet request is bounded: the client promotes the link and hydrates rather than
+leaving the loader visible forever. Non-hydrated pages keep ordinary blocking links for
+JavaScript-off and terminal-page styling.
+
 #### Scoped styles - CSS Modules & SFC <style>
 
 For component-local styles you have two collision-free options, both bundled into that same
@@ -7962,21 +8087,41 @@ isolated fixtures and a test database. Never point a contract laboratory at prod
 
 ## Nifra - Types-first architecture
 
-> One schema is the single source of truth: it drives runtime validation, inferred TypeScript types, the no-codegen typed client, an OpenAPI document, and the MCP contract your agents read.
+> Nifra infers route types from path literals and handlers automatically, with optional Standard Schemas for validation, explicit contracts, OpenAPI, and agent-readable APIs.
 
-In Nifra a single schema is the **source of truth**. The same definition drives runtime
-validation, inferred TypeScript types, the no-codegen typed client, an OpenAPI document, and
-the contract your coding agents read - so the five never drift apart.
+Nifra starts with automatic inference. A route's path literal, handler context, and return
+value produce its TypeScript surface; add a Standard Schema when you need runtime validation,
+coercion, or an explicit request/response contract. The same server type then drives the
+no-codegen client and the agent-readable API surface.
 
-### One schema
+### Inline inference first
 
-Define request inputs and the response shape once with `t`. Nothing here is
-framework-specific; it's a plain object you attach to a route.
+The chainable builder is fully type-inferred. Path parameters are parsed from the route
+pattern, handler context is typed automatically, and plain return values become the success
+response seen by the client. This is the quick-start style, similar to Elysia's inline route
+inference.
+
+```ts
+import { server } from "@nifrajs/core/server"
+
+export const app = server()
+  .get("/users/:id", (c) => ({ id: c.params.id, name: "Ada" }))
+  // c.params.id is inferred from the path; the return type becomes the client response.
+  .post("/users", () => ({ created: true }))
+
+// No schema, annotation, or codegen is required for the route types.
+```
+
+### Schemas at the trust boundary
+
+Attach a Standard Schema when inputs must be validated before the handler runs, or when you
+want an explicit response contract. Path params are already inferred from `:id`;
+the `params` schema below adds runtime constraints/coercion as well.
 
 ```ts
 import { t } from "@nifrajs/schema"
 
-// One contract, defined once. Everything below is derived from it.
+// Add a schema when the boundary needs runtime validation or a declared contract.
 export const GetUser = {
   params: t.object({ id: t.string() }),
   response: t.object({
@@ -8006,9 +8151,10 @@ export const app = server().get("/users/:id", GetUser, (c) => {
 
 ### Inferred types
 
-The same schema types the handler: `c.params.id` is `string`, and the
-return value is checked against `response`. Change the schema and the handler
-stops compiling until it matches - types and validation can't disagree.
+Without a schema, `c.params.id` is still `string` and the handler return
+is captured automatically. With a schema, its output types the handler and its declared
+`response` constrains what the handler may return. Change either the route or the
+contract and the typed client follows at compile time.
 
 ### The typed client
 
@@ -8030,6 +8176,16 @@ if (res.ok) {
 }
 ```
 
+### Contract-first when the surface must be separate
+
+Inline inference is the default. If the API needs to be shared, versioned, or implemented by
+more than one service, declare it with `defineContract` and connect handlers with
+`implement`. That keeps the contract type available without importing a server
+implementation into the client.
+
+See [Framework contract](/docs/contract) for the decoupled form and its scaling
+guidance.
+
 ### OpenAPI
 
 The `openapi()` middleware builds an OpenAPI 3.1 document from your registered
@@ -8175,6 +8331,98 @@ The `nifra_levels` MCP tool returns the same
 `{ achieved, levels[] }` report. An agent can read what its change proved, and a
 level that regressed comes back with the reason it broke.
 
+## Nifra - WebMCP & predictive UI
+
+> Expose explicit page-local WebMCP tools from typed Nifra capabilities while keeping remote MCP, authorization, receipts, and predictive UI reconciliation on one contract.
+
+WebMCP is the right page-local transport for an agent to discover and call tools in the
+currently open site. Nifra adopts that standard directly and adds a complementary contract for
+the semantics WebMCP does not define: typed capabilities, deterministic prediction, versioned
+reconciliation, bounded receipts, and host-independent conformance tests.
+
+### One capability, one trust boundary
+
+Define an explicit capability once. Its input and output schemas are the same Nifra core
+schemas used by every other adapter, and the handler still runs behind capability, approval,
+idempotency, budget, cancellation, and output checks.
+
+```ts
+// doc-check: skip - addItemOnServer is supplied by the application.
+import { t } from "@nifrajs/schema"
+import { defineAgentCapability } from "@nifrajs/webmcp"
+
+export const addToCart = defineAgentCapability({
+  name: "cart.add",
+  description: "Add a product to the current cart.",
+  input: t.object({ sku: t.string(), quantity: t.number() }),
+  output: t.object({ cartVersion: t.string() }),
+  annotations: { readOnlyHint: false, destructiveHint: false },
+  writes: ["cart"],
+  execute: (input) => addItemOnServer(input),
+})
+```
+
+### Adopt WebMCP without a fork
+
+Register only the tools your page intentionally offers. Nifra feature-detects
+`document.modelContext.registerTool`, isolates host registration failures, and
+makes unsupported browsers a no-op. Registration is discovery, not authorization: the server
+must enforce authorization again for writes.
+
+```ts
+// doc-check: skip - addToCart is declared in the preceding section.
+import { registerWebMcpTools } from "@nifrajs/webmcp"
+
+// Explicit allowlist. On ordinary browsers this resolves to a safe unsupported report.
+const registration = await registerWebMcpTools([addToCart])
+console.log(registration.supported, registration.registered, registration.failed)
+// The host receives the standard document.modelContext.registerTool({
+//   name, description, inputSchema, annotations, execute
+// }) shape.
+```
+
+### Keep remote MCP as the durable surface
+
+WebMCP needs an open page and is local to that page. Remote MCP remains the right surface for
+background work, integrations, and MCP Apps. Project the same `capability.tool` into
+the existing MCP adapter; do not maintain a second schema or handler.
+
+```ts
+// doc-check: skip - addToCart is declared in the preceding section.
+import { toMcpTool } from "@nifrajs/mcp/tool-contract"
+
+// Same core schemas, authorization, approval, idempotency, and evidence - different transport.
+const remoteTool = toMcpTool(addToCart.tool, {
+  capabilities: [addToCart.tool.capability],
+})
+```
+
+### Predict, then reconcile
+
+Predictive UI is application-owned deterministic state, not an LLM guess. A predictor returns a
+bounded `add`/`replace`/`remove` patch tied to an authoritative
+version. The store applies it atomically, and a successful server response either replaces the
+authoritative state or rolls the overlay back on failure, expiry, or conflict.
+
+```ts
+// doc-check: skip - addToCart is declared in the preceding section.
+import { createPredictionStore, executePredicted } from "@nifrajs/webmcp"
+
+const store = createPredictionStore({ state: { items: [] }, version: "cart-1" })
+const result = await executePredicted(addToCart, { sku: "sku-1", quantity: 1 }, store)
+// committed | rolled-back | conflicted | expired | stale | invalid | executed
+console.log(result.outcome, result.snapshot)
+// predict is a pure RFC 6902 subset patch; reconcile accepts the authoritative server version.
+```
+
+### What belongs in the complementary contract
+
+Keep the browser standard small: discovery and execution. Keep Nifra’s public seam provider
+neutral: scope, bounded state paths, reconciliation policy, receipts, and deterministic
+conformance. Keep durable idempotency, tenancy, credentials, retention, pricing, and operated
+policy injected behind the same core contract. This makes the surface useful with any WebMCP
+host while preserving Nifra’s server-side trust boundary.
+
 ---
 
 # Package reference (READMEs)
@@ -8415,6 +8663,24 @@ const result = await runAgent(definition, { value: input }, ports, {
 The public in-memory adapters are for local development and tests. Durable state, provider
 credentials, and operated policy remain adapter concerns.
 
+For transient prompt assembly, `@nifrajs/agent/context` provides a deterministic, token-budgeted
+selection seam:
+
+```ts
+import { assembleContext } from "@nifrajs/agent/context"
+
+const context = assembleContext(
+  [
+    { id: "system", kind: "instruction", content: "You are concise.", required: true },
+    { id: "memory", kind: "memory", content: "The user prefers short answers.", priority: 10 },
+  ],
+  { budget: { maxTokens: 2_000, reserveTokens: 256 } },
+)
+```
+
+The assembler owns selection, ordering, and accounting only. Persistence, embeddings, retrieval
+indexes, provider tokenizers, redaction, and product policy stay in caller-owned adapters.
+
 Gateway and deployment contracts are deliberately provider-neutral. Retry, fallback, budget,
 deadline, workspace, and hostile-code isolation claims are admitted only from a host-approved
 capability report. The local and replay reference profiles are not hostile-code sandboxes, and no
@@ -8563,6 +8829,55 @@ belong in these public contracts.
 For AI agents, see [`LLM.md`](./LLM.md) and the full corpus
 [`../../llms-full.txt`](../../llms-full.txt).
 
+## @nifrajs/agent-review
+
+`@nifrajs/agent-review` is a small, provider-neutral contract for bounded review results. It is a
+leaf package: it does not run checks, read a repository, invoke fixes, provide a CLI, or persist
+review data.
+
+```ts
+import { composeReviewReport, parseReviewReport } from "@nifrajs/agent-review"
+
+const report = await composeReviewReport({
+  strict: false,
+  scope: {
+    kind: "project",
+    state: "valid",
+    changedPaths: [],
+    pathDigest: "a".repeat(64),
+    outOfScopeCount: 0,
+  },
+  checks: [],
+  findings: [],
+})
+
+const verified = await parseReviewReport(JSON.stringify(report))
+```
+
+The parser accepts a JSON string or an unknown value and fails closed. It rejects unknown keys and
+content-bearing keys such as `message`, `prompt`, `output`, `payload`, `body`, and `secret` at any
+depth. Findings carry only stable codes, structural categories, safe locations, and opaque
+evidence references; they do not carry diagnostic messages, source text, requests, responses, or
+model content.
+
+Reports are limited to 256 KiB, depth 8, 32 keys per object, 1,024 array items, 512-byte paths,
+256-byte Git references, and bounded identifiers. Paths are project-relative POSIX paths. Parsed
+reports are deeply frozen. Report status, blocking count, and success are derived and verified;
+callers cannot make an invalid report pass by changing those fields.
+
+Canonical report digests use lowercase Web Crypto SHA-256. Check duration is display-only and is
+excluded from the digest, so equivalent structure has the same identity across runtimes and timing.
+The package uses no runtime dependencies, filesystem access, environment reads, provider SDKs, or
+Nifra package imports. It relies on `globalThis.crypto.subtle` and `TextEncoder`, which are available
+in Bun, modern Node, Deno, Workers, and browsers.
+
+The composer accepts only the typed structural inputs already produced by a trusted collector. It
+sorts and copies them, derives the outcome, signs the canonical report, and runs the same parser
+boundary before returning it. Repository collectors, CLI/MCP projections, SARIF, and safe fix
+recipes belong in higher-level packages.
+
+For coding agents, see [`LLM.md`](./LLM.md). The full machine-readable corpus is [`../../llms-full.txt`](../../llms-full.txt).
+
 ## @nifrajs/agent-telemetry
 
 Child-span telemetry for AI tool calls made through Nifra tool and MCP endpoints.
@@ -10095,6 +10410,10 @@ Mount `mcp.fetch` at `POST /mcp`. The package also exposes the JSON-RPC protocol
 layers directly, plus `defineMcpWidget` and the React adapter for tool results that render UI in MCP
 hosts.
 
+MCP servers are same-origin for browser clients by default. Set an exact `allowedOrigins` list for
+known cross-origin clients, or set `allowAnyOrigin: true` only for a deliberately public,
+secret-free server. Authentication is still the host application's responsibility.
+
 Clients that include `text/event-stream` in `Accept` receive progress notifications as they happen,
 followed by the final JSON-RPC response in the same stream. An SSE `GET /mcp` opens a cancellable
 server-message connection; a plain `GET /mcp` remains a health page.
@@ -11309,6 +11628,133 @@ one cheap read instead of the whole corpus. For the wider framework: the repo's
 [`llms-full.txt`](../../llms-full.txt) is the full machine-readable corpus. Run `nifra check` as the
 done-gate, or `nifra mcp` to give the agent live project tools.
 
+## @nifrajs/webmcp
+
+Typed WebMCP site tools plus a deterministic predictive-UI contract for Nifra applications.
+
+WebMCP is the browser-local surface: compatible hosts discover tools from the page through
+`document.modelContext.registerTool`. This package does not replace WebMCP or MCP. It makes one Nifra
+core tool contract usable from a page-local agent while adding prediction, reconciliation, receipts, and
+host-independent conformance tests.
+
+```sh
+bun add @nifrajs/webmcp
+```
+
+```ts
+import { t } from "@nifrajs/schema"
+import {
+  defineAgentCapability,
+  registerWebMcpTools,
+} from "@nifrajs/webmcp"
+
+const addItem = defineAgentCapability({
+  name: "cart.add",
+  description: "Add a product to the current cart.",
+  input: t.object({ sku: t.string(), quantity: t.number() }),
+  output: t.object({ cartVersion: t.string() }),
+  annotations: { readOnlyHint: false, destructiveHint: false, idempotentHint: true },
+  writes: ["cart"],
+  execute: async (input) => addItemOnTheServer(input),
+})
+
+// Safe no-op on browsers/hosts without WebMCP.
+const registration = await registerWebMcpTools([addItem])
+```
+
+The returned WebMCP `execute` function runs Nifra's existing input validation, capability, approval,
+idempotency, budget, cancellation, output validation, and evidence path. By default it returns a bounded
+receipt envelope so an agent can verify whether the operation committed. The normal human UI remains the
+source of page rendering and works when WebMCP is absent.
+
+Receipt output is retained only while its JSON encoding stays within the bounded `maxReceiptBytes`
+limit (16 KiB by default, 64 KiB maximum); oversized or non-JSON output is represented by
+`outputTruncated: true`. Use `resultMode: "output"` only when the embedding host provides its own
+response-size and serialization boundary.
+
+## Predictive UI
+
+Predictions are application-owned and deterministic. They are not LLM guesses. Pair `predict` with
+`reconcile`; prediction patches use an atomic, defensive subset of RFC 6902 (`add`, `replace`, `remove`):
+
+```ts
+const addItem = defineAgentCapability({
+  // ...typed core tool options...
+  predict: ({ input, snapshot, version }) => ({
+    baseVersion: version,
+    patch: [
+      { op: "add", path: "/items/-", value: { sku: input.sku, quantity: input.quantity } },
+    ],
+  }),
+  reconcile: ({ previous, output }) => ({
+    state: { items: previous.state.items },
+    version: output.cartVersion,
+  }),
+})
+```
+
+Use `createPredictionStore` and `executePredicted` for the full lifecycle:
+
+```ts
+const store = createPredictionStore({
+  state: { items: [] },
+  version: "cart-1",
+})
+
+const result = await executePredicted(addItem, input, store)
+// committed | rolled-back | conflicted | expired | stale | invalid | executed
+console.log(result.outcome, result.snapshot)
+```
+
+The store is atomic, defensive, expiry-aware, version-aware, and rejects prototype-grafting paths.
+Successful server state replaces the authoritative base; failed calls roll the overlay back; stale
+commits become conflicts.
+
+## Remote MCP and MCP Apps
+
+The capability contains the canonical `capability.tool`. Project it into the existing MCP adapter without
+creating a second contract:
+
+```ts
+import { toMcpTool } from "@nifrajs/mcp/tool-contract"
+
+const remoteTool = toMcpTool(addItem.tool, {
+  capabilities: [addItem.tool.capability],
+})
+```
+
+Use `@nifrajs/mcp`'s existing `defineMcpTool`, `structuredContent`, `ui://` widgets, and render intents
+when the result should render as an MCP App. WebMCP is page-local; remote MCP remains available without an
+open page.
+
+## Security
+
+- Register an explicit allowlist; never expose every route, DOM event, or `fetch` call.
+- WebMCP registration is not authorization. Enforce authorization again at the server boundary.
+- Keep inputs narrow and annotations honest. A safety hint is not a permission.
+- Predictions are pure local transforms and cannot grant capability or bypass core policy.
+- Receipts contain status, bounded evidence, and error codes—not credentials, request bodies, secrets, or
+  stack traces.
+- Normal browsers and non-WebMCP hosts receive a safe unsupported report.
+
+## AI conformance
+
+`runAgentSurfaceConformance` accepts an injectable host and optional deterministic calls, so CI can verify
+the surface without ChatGPT or a live model:
+
+```ts
+const result = await runAgentSurfaceConformance([addItem], {
+  target: fakeWebMcpHost,
+  cases: [{ capability: addItem, input: { sku: "sku-1", quantity: 1 } }],
+})
+```
+
+For the complete contract, see [`LLM.md`](./LLM.md), the repository [`AGENTS.md`](../../AGENTS.md), and
+the root machine-readable [`llms-full.txt`](../../llms-full.txt) corpus.
+
+See [`examples/webmcp`](../../examples/webmcp) for a complete capability projected to both WebMCP and
+the existing remote MCP adapter.
+
 ## @nifrajs/workers
 
 Cloudflare Workers helpers for nifra - a Durable Object hub for cross-connection WebSocket broadcast.
@@ -11431,16 +11877,20 @@ done-gate, or `nifra mcp` to give the agent live project tools.
 
 ## @nifrajs/agent
 
-`AgentApprovalPort`, `AgentApprovalResult`, `AgentDefinition`, `AgentDeltaSink`, `AgentDeployment`, `AgentDeploymentAdapter`, `AgentDeploymentPlan`, `AgentModelDelta`, `AgentModelPort`, `AgentModelRequest`, `AgentModelResponse`, `AgentPendingContinuation`, `AgentPendingKind`, `AgentPorts`, `AgentRunResult`, `AgentSharedState`, `AgentStatePatchOp`, `AgentStateStore`, `AgentStatus`, `AgentStepEvidence`, `AgentTelemetryPort`, `AgentToolContract`, `AgentToolDescriptor`, `AgentToolResult`, `AgentTranscript`, `AgentTurnBaseResult`, `AgentTurnError`, `AgentTurnInput`, `AgentTurnResult`, `AgentTurnState`, `ApprovalClass`, `assertDeploymentAuthorityMonotonic`, `CAPABILITY_DESCRIPTOR_VERSION`, `CapabilityDescriptor`, `CapabilityKind`, `combineAgentDeltaSinks`, `combineAgentTelemetry`, `composeDescriptor`, `composeRegistrySnapshot`, `createAgentSharedState`, `createAgentState`, `createDeploymentAuthority`, `createLocalProcessAdapter`, `createStructuredOutputParser`, `DeploymentActivationOptions`, `DeploymentAuthority`, `DeploymentCancellation`, `DeploymentCancelRequest`, `DeploymentCancelResult`, `DeploymentCapabilities`, `DeploymentCapabilityReport`, `DeploymentDisposeRequest`, `DeploymentDisposeResult`, `DeploymentError`, `DeploymentErrorCode`, `DeploymentEvidence`, `DeploymentFilesystem`, `DeploymentInspection`, `DeploymentInspectRequest`, `DeploymentNetwork`, `DeploymentPrepareRequest`, `DeploymentPrepareResult`, `DeploymentProcess`, `DeploymentRuntime`, `DeploymentSecrets`, `DeploymentStartRequest`, `DeploymentStartResult`, `DeploymentState`, `descriptorFromTool`, `DescriptorInput`, `ExecutionPolicy`, `ExecutionPolicyAdapter`, `FakeModelGateway`, `FakeModelGatewayOptions`, `HostileCodeIsolation`, `IdempotencyClass`, `isModelGatewayErrorCode`, `IsolationClass`, `LOCAL_PROCESS_LIMITATION`, `LocalProcessAdapter`, `LocalProcessAdapterOptions`, `LocalProcessPolicyError`, `LocalProcessRequest`, `LocalProcessResult`, `MemoryAgentStateStore`, `MODEL_GATEWAY_ERROR_CODES`, `ModelGateway`, `ModelGatewayAttemptRequest`, `ModelGatewayBudget`, `ModelGatewayEnvelope`, `ModelGatewayError`, `ModelGatewayErrorCode`, `ModelGatewayEvidence`, `ModelGatewayExecutionResult`, `ModelGatewayFailure`, `ModelGatewayFailureError`, `ModelGatewayRawResult`, `ModelGatewayRequest`, `ModelGatewayResult`, `ModelGatewaySuccess`, `ModelGatewayTerminalFailure`, `ModelGatewayUsage`, `ModelRoute`, `ModelRoutePolicy`, `ModelRouteRef`, `parseCapabilityDescriptor`, `parseDeploymentCapabilityReport`, `parseDeploymentPlan`, `parseModelGatewayError`, `parseModelGatewayResult`, `REGISTRY_SNAPSHOT_VERSION`, `RegistryError`, `RegistryErrorCode`, `RegistrySnapshot`, `replayAgent`, `ReplayModelGateway`, `ReplayModelGatewayOptions`, `resumeAgent`, `RetryClass`, `runAgent`, `RunAgentOptions`, `runModelGateway`, `structuredOutputParser`, `StructuredOutputParser`, `ToolDescriptorOptions`, `turn`
+`AgentApprovalPort`, `AgentApprovalResult`, `AgentDefinition`, `AgentDeltaSink`, `AgentDeployment`, `AgentDeploymentAdapter`, `AgentDeploymentPlan`, `AgentModelDelta`, `AgentModelPort`, `AgentModelRequest`, `AgentModelResponse`, `AgentPendingContinuation`, `AgentPendingKind`, `AgentPorts`, `AgentRunResult`, `AgentSharedState`, `AgentStatePatchOp`, `AgentStateStore`, `AgentStatus`, `AgentStepEvidence`, `AgentTelemetryPort`, `AgentToolContract`, `AgentToolDescriptor`, `AgentToolResult`, `AgentTranscript`, `AgentTurnBaseResult`, `AgentTurnError`, `AgentTurnInput`, `AgentTurnResult`, `AgentTurnState`, `ApprovalClass`, `approximateContextTokens`, `assembleContext`, `assertDeploymentAuthorityMonotonic`, `CAPABILITY_DESCRIPTOR_VERSION`, `CapabilityDescriptor`, `CapabilityKind`, `collectContext`, `combineAgentDeltaSinks`, `combineAgentTelemetry`, `composeDescriptor`, `composeRegistrySnapshot`, `ContextAssembly`, `ContextAssemblyOptions`, `ContextBudget`, `ContextBudgetError`, `ContextItem`, `ContextSource`, `ContextTokenCounter`, `createAgentSharedState`, `createAgentState`, `createDeploymentAuthority`, `createLocalProcessAdapter`, `createStructuredOutputParser`, `DeploymentActivationOptions`, `DeploymentAuthority`, `DeploymentCancellation`, `DeploymentCancelRequest`, `DeploymentCancelResult`, `DeploymentCapabilities`, `DeploymentCapabilityReport`, `DeploymentDisposeRequest`, `DeploymentDisposeResult`, `DeploymentError`, `DeploymentErrorCode`, `DeploymentEvidence`, `DeploymentFilesystem`, `DeploymentInspection`, `DeploymentInspectRequest`, `DeploymentNetwork`, `DeploymentPrepareRequest`, `DeploymentPrepareResult`, `DeploymentProcess`, `DeploymentRuntime`, `DeploymentSecrets`, `DeploymentStartRequest`, `DeploymentStartResult`, `DeploymentState`, `descriptorFromTool`, `DescriptorInput`, `ExecutionPolicy`, `ExecutionPolicyAdapter`, `FakeModelGateway`, `FakeModelGatewayOptions`, `HostileCodeIsolation`, `IdempotencyClass`, `isModelGatewayErrorCode`, `IsolationClass`, `LOCAL_PROCESS_LIMITATION`, `LocalProcessAdapter`, `LocalProcessAdapterOptions`, `LocalProcessPolicyError`, `LocalProcessRequest`, `LocalProcessResult`, `MemoryAgentStateStore`, `MODEL_GATEWAY_ERROR_CODES`, `ModelGateway`, `ModelGatewayAttemptRequest`, `ModelGatewayBudget`, `ModelGatewayEnvelope`, `ModelGatewayError`, `ModelGatewayErrorCode`, `ModelGatewayEvidence`, `ModelGatewayExecutionResult`, `ModelGatewayFailure`, `ModelGatewayFailureError`, `ModelGatewayRawResult`, `ModelGatewayRequest`, `ModelGatewayResult`, `ModelGatewaySuccess`, `ModelGatewayTerminalFailure`, `ModelGatewayUsage`, `ModelRoute`, `ModelRoutePolicy`, `ModelRouteRef`, `parseCapabilityDescriptor`, `parseDeploymentCapabilityReport`, `parseDeploymentPlan`, `parseModelGatewayError`, `parseModelGatewayResult`, `REGISTRY_SNAPSHOT_VERSION`, `RegistryError`, `RegistryErrorCode`, `RegistrySnapshot`, `replayAgent`, `ReplayModelGateway`, `ReplayModelGatewayOptions`, `resumeAgent`, `RetryClass`, `runAgent`, `RunAgentOptions`, `runModelGateway`, `structuredOutputParser`, `StructuredOutputParser`, `ToolDescriptorOptions`, `turn`
 
 ## @nifrajs/agent-app
 
-`AGENT_APP_FEATURES`, `AgentAppClient`, `AgentAppClientOptions`, `AgentAppError`, `AgentEventView`, `AgentTransport`, `AgentTransportError`, `AgentTransportRequest`, `ApprovalRequiredView`, `ApprovalResolvedView`, `AssistantChunkView`, `AuthProvider`, `boundaryCommands`, `BoundaryDecisionResult`, `boundaryIsStale`, `BoundaryItemView`, `BoundaryStateView`, `CommandOutcome`, `CreateSessionInput`, `EvalComparisonView`, `EvidenceTimelineView`, `ExtensionReloadedView`, `FaultInjectionView`, `HandoffView`, `HttpAgentTransport`, `HttpAgentTransportOptions`, `MemoryCompactedView`, `OrderedEventBuffer`, `parseEventStream`, `PendingApprovalView`, `RegistryCapabilityView`, `RepairRequiredView`, `ReplayEntryView`, `ReplayResult`, `ResolveHandoffInput`, `ResumeInput`, `RunStudioNodeState`, `RunStudioNodeView`, `RunStudioView`, `RunView`, `SessionFailedView`, `SessionLifecycleView`, `SessionStoppedView`, `SessionView`, `toEvalComparisonView`, `toEventView`, `toEvidenceTimelineView`, `toFaultInjectionViews`, `toHandoffView`, `ToolCompletedView`, `ToolDeltaView`, `ToolStartedView`, `toRegistryCapabilityView`, `toRunStudioView`, `toRunView`, `toSessionView`, `TurnStartedView`, `VerificationCompletedView`, `virtualizeEvidenceRows`
+`AGENT_APP_FEATURES`, `AgentAppClient`, `AgentAppClientOptions`, `AgentAppError`, `AgentEventView`, `AgentTransport`, `AgentTransportError`, `AgentTransportRequest`, `ApprovalRequiredView`, `ApprovalResolvedView`, `AssistantChunkView`, `AuthProvider`, `boundaryCommands`, `BoundaryDecisionResult`, `boundaryIsStale`, `BoundaryItemView`, `BoundaryStateView`, `CommandOutcome`, `CreateSessionInput`, `EvalComparisonView`, `EvidenceTimelineView`, `ExtensionReloadedView`, `FaultInjectionView`, `HandoffView`, `HttpAgentTransport`, `HttpAgentTransportOptions`, `MemoryCompactedView`, `OrderedEventBuffer`, `parseEventStream`, `PendingApprovalView`, `RegistryCapabilityView`, `RepairRequiredView`, `ReplayEntryView`, `ReplayResult`, `ResolveHandoffInput`, `ResumeInput`, `ReviewView`, `ReviewViewCheck`, `ReviewViewEvidence`, `ReviewViewFinding`, `ReviewViewStatus`, `RunStudioNodeState`, `RunStudioNodeView`, `RunStudioView`, `RunView`, `SessionFailedView`, `SessionLifecycleView`, `SessionStoppedView`, `SessionView`, `toEvalComparisonView`, `toEventView`, `toEvidenceTimelineView`, `toFaultInjectionViews`, `toHandoffView`, `ToolCompletedView`, `ToolDeltaView`, `ToolStartedView`, `toRegistryCapabilityView`, `toReviewView`, `toRunStudioView`, `toRunView`, `toSessionView`, `TurnStartedView`, `VerificationCompletedView`, `virtualizeEvidenceRows`
 
 ## @nifrajs/agent-protocol
 
 `AGENT_PROTOCOL_VERSION`, `AgentApprovalRequiredEvent`, `AgentApprovalResolvedEvent`, `AgentAssistantDeltaEvent`, `AgentAssistantMessageEvent`, `AgentBackend`, `AgentBackendInfo`, `agentError`, `AgentError`, `AgentEvent`, `AgentEventPayload`, `AgentEventSink`, `AgentEventStream`, `AgentEventType`, `AgentExtensionReloadedEvent`, `AgentMemoryCompactedEvent`, `AgentRepairRequiredEvent`, `AgentRepairTask`, `AgentSessionCheckpoint`, `AgentSessionCompletedEvent`, `AgentSessionEventBase`, `AgentSessionFailedEvent`, `AgentSessionSnapshot`, `AgentSessionStartedEvent`, `AgentSessionStatus`, `AgentSessionStoppedEvent`, `AgentSessionUpdatedEvent`, `AgentToolCompletedEvent`, `AgentToolDeltaEvent`, `AgentToolStartedEvent`, `AgentTurnStartedEvent`, `AgentVerificationCompletedEvent`, `createAgentEventStream`, `CreateSessionInput`, `ForkSessionInput`, `ForkSessionResult`, `isAgentEvent`, `ReloadResult`, `SendMessageInput`
 
+## @nifrajs/agent-review
+
+`canonicalizeReviewReport`, `composeReviewReport`, `digestReviewReport`, `parseReviewReport`, `REVIEW_MAX_ARRAY_ITEMS`, `REVIEW_MAX_BYTES`, `REVIEW_MAX_CODE_BYTES`, `REVIEW_MAX_DEPTH`, `REVIEW_MAX_ID_BYTES`, `REVIEW_MAX_OBJECT_KEYS`, `REVIEW_MAX_PATH_BYTES`, `REVIEW_MAX_REF_BYTES`, `ReviewParserError`
+
 ## @nifrajs/agent-telemetry
 
 `AgentRunEvidence`, `AgentRunOutcome`, `AgentRunTrace`, `agentTelemetry`, `AgentTelemetryOptions`, `consoleAgentExporter`, `orchestrationTelemetry`, `OrchestrationTelemetry`, `OrchestrationTelemetryEvent`, `OrchestrationTelemetryKind`, `OrchestrationTelemetryOptions`, `traceAgentRun`, `TraceAgentRunOptions`
@@ -11467,7 +11917,7 @@ done-gate, or `nifra mcp` to give the agent live project tools.
 
 ## @nifrajs/coding-agent
 
-`AGENT_CAPABILITY_MANIFEST_VERSION`, `AGENT_PRESETS`, `AgentCapability`, `AgentCapabilityManifest`, `AgentPlan`, `AgentPreset`, `AgentPresetName`, `ApprovalDecision`, `ApprovalManager`, `ApprovalManagerOptions`, `ApprovalMatchRejection`, `ApprovalMatchResult`, `ApprovalRequest`, `approvalRequestFromEvent`, `approvalResolvedEvent`, `BoundedSubagentRunner`, `BoundedText`, `CapabilityDescriptor`, `CiDeploymentAdapter`, `CodingAgentExtension`, `CodingAgentHost`, `CodingAgentHostOptions`, `CodingAgentRpcServer`, `CodingAgentRpcServerHandle`, `CodingAgentRpcServerOptions`, `CompactionReport`, `ContextRecord`, `ContextWindow`, `ContextWindowOptions`, `createCapabilityManifest`, `createCiDeploymentAdapter`, `createLocalProcessDeploymentAdapter`, `createNativeGatewayModelPort`, `createNifraTools`, `createPresetSpec`, `createReplayDeploymentAdapter`, `createVerificationRepairTask`, `deniedCapabilities`, `DEPLOYMENT_REFERENCE_PROFILES`, `discoverExtensions`, `ExtensionCommand`, `ExtensionContext`, `extensionDescriptor`, `ExtensionDescriptorOptions`, `extensionDescriptors`, `ExtensionDescriptorSource`, `ExtensionEventHandler`, `ExtensionHost`, `ExtensionHostOptions`, `ExtensionProvider`, `ExtensionReloadResult`, `ExtensionSubagent`, `ExtensionTool`, `FileSessionStore`, `FileSessionStoreOptions`, `getAgentPreset`, `HandoffCoordinator`, `HandoffCoordinatorOptions`, `HandoffDecision`, `HandoffError`, `HandoffRejection`, `HandoffView`, `HealingEvent`, `HealingOptions`, `HealingResult`, `IsolatedExtensionSnapshot`, `IsolatedExtensionTool`, `IsolatedExtensionWorker`, `IsolatedExtensionWorkerOptions`, `LocalProcessDeploymentAdapter`, `migrateLegacySession`, `MigrateLegacySessionOptions`, `NativeApprovalPort`, `NativeGatewayModelPortOptions`, `NativeMessage`, `NativeModelChunk`, `NativeModelPort`, `NativeModelRequest`, `NativeModelResponse`, `NativeTool`, `NIFRA_AGENT_INSTRUCTIONS`, `NifraAgentTool`, `NifraBackend`, `NifraBackendOptions`, `NifraContextOptions`, `NifraContextResult`, `OpenHandoffInput`, `parseCapabilityManifest`, `parseSessionEvidenceRecord`, `PiBackend`, `PiBackendOptions`, `PlanEvent`, `PlanPhase`, `PlanResult`, `PlanRunner`, `PlanRunnerOptions`, `ProjectDiffOptions`, `ProjectDiffResult`, `readBoundedText`, `readProjectDiff`, `readReplayEvents`, `RepairProposal`, `ReplayBackend`, `ReplayBackendOptions`, `ReplayDeploymentAdapter`, `runNifraContext`, `runNifraVerification`, `SelfHealingController`, `SESSION_EVIDENCE_VERSION`, `SessionEvidenceRecord`, `SessionLogEntry`, `SessionMigrationError`, `SessionMigrationReport`, `SessionStore`, `stableSessionEventCode`, `SubagentExecutor`, `SubagentResult`, `SubagentRunnerOptions`, `SubagentSpec`, `UiExtensionHost`, `UiExtensionHostOptions`, `UiExtensionManifest`, `UiExtensionSlot`, `UiReloadResult`, `UiStatusWidget`, `UiThemeDescriptor`, `validateExtensionModule`, `VerificationOptions`, `VerificationRepairTask`, `VerificationResult`, `WorkflowContext`, `WorkflowEvent`, `WorkflowResult`, `WorkflowRunner`, `WorkflowRunnerOptions`, `WorkflowStep`
+`AGENT_CAPABILITY_MANIFEST_VERSION`, `AGENT_PRESETS`, `AgentCapability`, `AgentCapabilityManifest`, `AgentPlan`, `AgentPreset`, `AgentPresetName`, `ApprovalDecision`, `ApprovalManager`, `ApprovalManagerOptions`, `ApprovalMatchRejection`, `ApprovalMatchResult`, `ApprovalRequest`, `approvalRequestFromEvent`, `approvalResolvedEvent`, `BoundedSubagentRunner`, `BoundedText`, `CapabilityDescriptor`, `CiDeploymentAdapter`, `CodingAgentExtension`, `CodingAgentHost`, `CodingAgentHostOptions`, `CodingAgentRpcServer`, `CodingAgentRpcServerHandle`, `CodingAgentRpcServerOptions`, `CompactionReport`, `ContextRecord`, `ContextWindow`, `ContextWindowOptions`, `createCapabilityManifest`, `createCiDeploymentAdapter`, `createLocalProcessDeploymentAdapter`, `createNativeGatewayModelPort`, `createNifraTools`, `createPresetSpec`, `createReplayDeploymentAdapter`, `createVerificationRepairTask`, `deniedCapabilities`, `DEPLOYMENT_REFERENCE_PROFILES`, `discoverExtensions`, `ExtensionCommand`, `ExtensionContext`, `extensionDescriptor`, `ExtensionDescriptorOptions`, `extensionDescriptors`, `ExtensionDescriptorSource`, `ExtensionEventHandler`, `ExtensionHost`, `ExtensionHostOptions`, `ExtensionProvider`, `ExtensionReloadResult`, `ExtensionSubagent`, `ExtensionTool`, `FileSessionStore`, `FileSessionStoreOptions`, `getAgentPreset`, `HandoffCoordinator`, `HandoffCoordinatorOptions`, `HandoffDecision`, `HandoffError`, `HandoffRejection`, `HandoffView`, `HealingEvent`, `HealingOptions`, `HealingResult`, `IsolatedExtensionSnapshot`, `IsolatedExtensionTool`, `IsolatedExtensionWorker`, `IsolatedExtensionWorkerOptions`, `isSafeReviewDiff`, `LocalProcessDeploymentAdapter`, `migrateLegacySession`, `MigrateLegacySessionOptions`, `NativeApprovalPort`, `NativeGatewayModelPortOptions`, `NativeMessage`, `NativeModelChunk`, `NativeModelPort`, `NativeModelRequest`, `NativeModelResponse`, `NativeTool`, `NIFRA_AGENT_INSTRUCTIONS`, `NifraAgentTool`, `NifraBackend`, `NifraBackendOptions`, `NifraContextOptions`, `NifraContextResult`, `OpenHandoffInput`, `parseCapabilityManifest`, `parseSessionEvidenceRecord`, `PiBackend`, `PiBackendOptions`, `PlanEvent`, `PlanPhase`, `PlanResult`, `PlanRunner`, `PlanRunnerOptions`, `ProjectDiffOptions`, `ProjectDiffResult`, `readBoundedText`, `readProjectDiff`, `readReplayEvents`, `RepairProposal`, `ReplayBackend`, `ReplayBackendOptions`, `ReplayDeploymentAdapter`, `ReviewExecutionErrorCode`, `ReviewExecutionResult`, `ReviewOptions`, `runNifraContext`, `runNifraReview`, `runNifraVerification`, `SelfHealingController`, `SESSION_EVIDENCE_VERSION`, `SessionEvidenceRecord`, `SessionLogEntry`, `SessionMigrationError`, `SessionMigrationReport`, `SessionStore`, `stableSessionEventCode`, `SubagentExecutor`, `SubagentResult`, `SubagentRunnerOptions`, `SubagentSpec`, `UiExtensionHost`, `UiExtensionHostOptions`, `UiExtensionManifest`, `UiExtensionSlot`, `UiReloadResult`, `UiStatusWidget`, `UiThemeDescriptor`, `validateExtensionModule`, `VerificationOptions`, `VerificationRepairTask`, `VerificationResult`, `WorkflowContext`, `WorkflowEvent`, `WorkflowResult`, `WorkflowRunner`, `WorkflowRunnerOptions`, `WorkflowStep`
 
 ## @nifrajs/content
 
@@ -11475,7 +11925,7 @@ done-gate, or `nifra mcp` to give the agent live project tools.
 
 ## @nifrajs/core
 
-`AdmissionController`, `AdmissionDecision`, `AnyServer`, `commonSecretPatterns`, `Context`, `ContextPlugin`, `cookieNamePrefix`, `CookieOptions`, `CookieSecret`, `defineContextPlugin`, `defineIdentityPlugin`, `definePlugin`, `DefinePluginResult`, `defineRouterPlugin`, `DurableObjectNamespaceLike`, `ExecutionContext`, `FetchApp`, `FRAMEWORK_NAME`, `FrameworkError`, `FrameworkName`, `Handler`, `IdentityPlugin`, `InferInput`, `InferOutput`, `isSameOriginPath`, `isSameOriginRequest`, `jsonLogger`, `LambdaEvent`, `LambdaHandler`, `LambdaResponse`, `LambdaV1Event`, `LambdaV2Event`, `LogFields`, `Logger`, `McpPromptDescriptor`, `McpResourceDescriptor`, `Method`, `METHODS`, `Middleware`, `NetlifyEvent`, `NetlifyHandler`, `NifraFeatureVersion`, `NifraPlugin`, `NifraWebSocket`, `NodeRequestContext`, `NodeRequestHook`, `NodeResponseContext`, `NodeResponseHook`, `NodeServeOutcome`, `OnRequestResult`, `Params`, `parseCookies`, `pathnameOf`, `PlainRender`, `Platform`, `PlatformResponse`, `PluginTypeCollapsed`, `Prettify`, `PromptArgument`, `PromptMessage`, `redactLogFields`, `RedactOptions`, `Registry`, `ResponseBodyHook`, `ResponseBodyReplacement`, `ResponseControls`, `ResponseFinalization`, `ResponseHeadersHook`, `ResponseHeadersView`, `ResponseMapFor`, `ResponseResult`, `RouteConfigError`, `RouteConfigErrorCode`, `RouteDescriptor`, `RouteInfo`, `RouteInfoFor`, `Router`, `RouterMatch`, `RouteSchema`, `RunningServer`, `ScheduledController`, `ScheduledHandler`, `serializeCookie`, `server`, `Server`, `ServerOptions`, `signValue`, `silentLogger`, `SSEContext`, `SSEInit`, `SSEMessage`, `SSEStream`, `StandardIssue`, `StandardResult`, `StandardSchemaV1`, `StandardTypes`, `StandardWebSocket`, `status`, `StatusResponse`, `toFetchHandler`, `toLambdaHandler`, `toNetlifyHandler`, `ToolAnnotations`, `toVercelHandler`, `TypedSSEStream`, `unsignValue`, `UrlParts`, `urlPartsOf`, `ValidationOutcome`, `VercelHandler`, `Version`, `VERSION`, `WebSocketContext`, `WebSocketData`, `WebSocketHandler`, `WebSocketUpgradeOutcome`
+`AdmissionController`, `AdmissionDecision`, `AnyServer`, `commonSecretPatterns`, `Context`, `ContextPlugin`, `cookieNamePrefix`, `CookieOptions`, `CookieSecret`, `defineContextPlugin`, `defineIdentityPlugin`, `definePlugin`, `DefinePluginResult`, `defineRouterPlugin`, `DurableObjectNamespaceLike`, `ExecutionContext`, `FetchApp`, `FRAMEWORK_NAME`, `FrameworkError`, `FrameworkName`, `Handler`, `hasDuplicateCookie`, `IdentityPlugin`, `InferInput`, `InferOutput`, `isSameOriginPath`, `isSameOriginRequest`, `jsonLogger`, `LambdaEvent`, `LambdaHandler`, `LambdaResponse`, `LambdaV1Event`, `LambdaV2Event`, `LogFields`, `Logger`, `McpPromptDescriptor`, `McpResourceDescriptor`, `Method`, `METHODS`, `Middleware`, `NetlifyEvent`, `NetlifyHandler`, `NifraFeatureVersion`, `NifraPlugin`, `NifraWebSocket`, `NodeRequestContext`, `NodeRequestHook`, `NodeResponseContext`, `NodeResponseHook`, `NodeServeOutcome`, `OnRequestResult`, `Params`, `parseCookies`, `pathnameOf`, `PlainRender`, `Platform`, `PlatformResponse`, `PluginTypeCollapsed`, `Prettify`, `PromptArgument`, `PromptMessage`, `redactLogFields`, `RedactOptions`, `Registry`, `ResponseBodyHook`, `ResponseBodyReplacement`, `ResponseControls`, `ResponseFinalization`, `ResponseHeadersHook`, `ResponseHeadersView`, `ResponseMapFor`, `ResponseResult`, `RouteConfigError`, `RouteConfigErrorCode`, `RouteDescriptor`, `RouteInfo`, `RouteInfoFor`, `Router`, `RouterMatch`, `RouteSchema`, `RunningServer`, `ScheduledController`, `ScheduledHandler`, `serializeCookie`, `server`, `Server`, `ServerOptions`, `signValue`, `silentLogger`, `SSEContext`, `SSEInit`, `SSEMessage`, `SSEStream`, `StandardIssue`, `StandardResult`, `StandardSchemaV1`, `StandardTypes`, `StandardWebSocket`, `status`, `StatusResponse`, `toFetchHandler`, `toLambdaHandler`, `toNetlifyHandler`, `ToolAnnotations`, `toVercelHandler`, `TypedSSEStream`, `unsignValue`, `UrlParts`, `urlPartsOf`, `ValidationOutcome`, `VercelHandler`, `Version`, `VERSION`, `WebSocketContext`, `WebSocketData`, `WebSocketHandler`, `WebSocketUpgradeOutcome`
 
 ## @nifrajs/cron
 
@@ -11523,7 +11973,7 @@ done-gate, or `nifra mcp` to give the agent live project tools.
 
 ## @nifrajs/jobs
 
-`Backoff`, `CapabilityBeacon`, `createQueue`, `EnqueueOptions`, `exponentialBackoff`, `ExponentialOptions`, `fixedBackoff`, `JobContext`, `JobCounts`, `JobDefinition`, `JobError`, `JobHandle`, `JobHandler`, `JobStore`, `JobValidationError`, `MemoryJobStore`, `noBackoff`, `Queue`, `QueueOptions`, `RetryPolicy`, `StandardResult`, `StandardSchemaV1`, `StoredJob`, `Worker`, `WorkerOptions`
+`Backoff`, `CapabilityBeacon`, `createQueue`, `DeadLetterRecord`, `DeadLetterView`, `EnqueueOptions`, `exponentialBackoff`, `ExponentialOptions`, `fixedBackoff`, `JobContext`, `JobCounts`, `JobDefinition`, `JobError`, `JobHandle`, `JobHandler`, `JobStore`, `JobValidationError`, `MemoryJobStore`, `noBackoff`, `Queue`, `QueueHealth`, `QueueOptions`, `RetryPolicy`, `StandardResult`, `StandardSchemaV1`, `StoredJob`, `toDeadLetterView`, `toQueueHealth`, `Worker`, `WorkerOptions`
 
 ## @nifrajs/mcp
 
@@ -11567,7 +12017,7 @@ done-gate, or `nifra mcp` to give the agent live project tools.
 
 ## @nifrajs/schema
 
-`decodeCursor`, `encodeCursor`, `fromTypeBox`, `NifraSchema`, `OpenAPIDocument`, `OpenAPIInfo`, `Page`, `paginate`, `registerFormat`, `t`, `toOpenAPI`
+`decodeCursor`, `diffOpenApiInventory`, `encodeCursor`, `fromTypeBox`, `ImportedApiInventory`, `ImportedRoute`, `ImportedRouteQuery`, `importOpenAPI`, `ImportOpenAPIOptions`, `NifraSchema`, `OpenAPIDocument`, `OpenAPIImportError`, `OpenAPIInfo`, `OpenApiInventoryDrift`, `Page`, `paginate`, `registerFormat`, `t`, `toOpenAPI`, `toOpenAPIFromEvidence`
 
 ## @nifrajs/storage
 
@@ -11575,7 +12025,7 @@ done-gate, or `nifra mcp` to give the agent live project tools.
 
 ## @nifrajs/testing
 
-`AdapterCertificationError`, `AdapterCertificationProfile`, `AdapterCertificationReport`, `AdversarialContractError`, `AdversarialContractOptions`, `AdversarialContractReport`, `AdversarialContractResult`, `AgentEvalCase`, `AgentEvalComponentEvidence`, `AgentEvalCompositionOptions`, `AgentEvalCompositionReport`, `AgentEvalRegressionError`, `AgentEvalReport`, `AgentEvalSuite`, `AgentEvalSuiteSpec`, `AgentFailureMatrixCase`, `AgentFailureMatrixError`, `AgentFailureMatrixKind`, `AgentFailureMatrixReport`, `AppLike`, `assertAdapterCertification`, `assertAdversarialContract`, `assertAgentEval`, `assertAgentEvalBaseline`, `assertAgentFailureMatrix`, `assertIncidentReplays`, `assertTrajectoryInvariants`, `BaselineComparison`, `BaselineOptions`, `cacheStoreCertificationProfile`, `CapturedRequest`, `CapturedRequestInput`, `captureIncident`, `CaptureIncidentOptions`, `CaseComparison`, `CaseResult`, `CertifiableCacheEntry`, `CertifiableCacheStore`, `CertifiableDeploymentAdapter`, `CertifiableDescriptorAdapter`, `CertifiableDomainEvent`, `CertifiableEventDeliveryAdapter`, `CertifiableEventRecord`, `CertifiableJobStore`, `CertifiableModelGateway`, `CertifiableRuntimeAdapter`, `CertifiableRuntimeServer`, `CertifiableStorageAdapter`, `CertificationCapabilityEvidence`, `CertificationCheck`, `CertificationCheckEvidence`, `certifyAdapter`, `checkTrajectoryInvariants`, `compareAgentEvalBaseline`, `ComparisonCode`, `ContractCaseContext`, `ContractCaseKind`, `ContractCoverageGap`, `ContractCoverageGapCode`, `ContractLabHandler`, `ContractLabRuntimeAdapter`, `ContractLabServer`, `ContractLabWitness`, `contractLabWitnesses`, `ContractReplay`, `ContractRuntime`, `ContractTarget`, `ContractTestApp`, `ContractWitness`, `cookieJar`, `CookieJar`, `createFailureLab`, `createReferenceContractLabHandler`, `createTrajectoryTranscript`, `CreateTrajectoryTranscriptOptions`, `defineAgentEvalSuite`, `defineCertificationProfile`, `defineFaultProfile`, `deploymentAdapterCertificationProfile`, `deploymentCertificationProfile`, `EffectLedger`, `eventDeliveryCertificationProfile`, `FailureDirective`, `FailureEvidence`, `FailureInjectedError`, `FailureKind`, `FailureLab`, `FailureLabOptions`, `FailureReplay`, `FailureScenario`, `FailureScenarioReport`, `FaultProfile`, `FaultProfileFault`, `FaultProfileFaultKind`, `FaultProfileReport`, `FaultProfileScenario`, `FaultProfileScenarioReport`, `gatewayCertificationProfile`, `generateRegressionTest`, `GenerateRegressionTestOptions`, `httpToolAdapter`, `IdempotencyDivergence`, `IdempotencyProof`, `IncidentCapsule`, `IncidentReplayError`, `IncidentReplayResult`, `inProcessToolAdapter`, `jobStoreCertificationProfile`, `mcpToolAdapter`, `modelGatewayCertificationProfile`, `parseRubricVerdict`, `proveIdempotency`, `recordTrajectory`, `redactForEmission`, `referenceFaultProfile`, `registryCertificationProfile`, `replayIncident`, `ReplayIncidentOptions`, `replayTrajectory`, `ReplayTrajectoryOptions`, `RubricShape`, `RubricSpec`, `RubricVerdict`, `runAdversarialContract`, `runAgentEvalComposition`, `runAgentFailureMatrix`, `runContractLab`, `runContractLabOverHttp`, `runContractLabThroughAdapter`, `runFailureScenario`, `runFaultProfile`, `RunFaultProfileOptions`, `runtimeAdapterCertificationProfile`, `runTrajectory`, `ScoreTolerance`, `shapeOf`, `storageAdapterCertificationProfile`, `testSession`, `TestSession`, `TestSessionOptions`, `testToolAdapter`, `TrajectoryInvariantId`, `TrajectoryInvariantOptions`, `TrajectoryInvariantResult`, `trajectoryRegressionId`, `TrajectoryReplayResult`, `TrajectoryRun`, `TrajectoryTranscript`, `verifyAdapterCertification`
+`AdapterCertificationError`, `AdapterCertificationProfile`, `AdapterCertificationReport`, `AdversarialContractError`, `AdversarialContractOptions`, `AdversarialContractReport`, `AdversarialContractResult`, `AgentEvalCase`, `AgentEvalComponentEvidence`, `AgentEvalCompositionOptions`, `AgentEvalCompositionReport`, `AgentEvalRegressionError`, `AgentEvalReport`, `AgentEvalSuite`, `AgentEvalSuiteSpec`, `AgentFailureMatrixCase`, `AgentFailureMatrixError`, `AgentFailureMatrixKind`, `AgentFailureMatrixReport`, `AppLike`, `assertAdapterCertification`, `assertAdversarialContract`, `assertAgentEval`, `assertAgentEvalBaseline`, `assertAgentFailureMatrix`, `assertIncidentReplays`, `assertPredictionLab`, `assertTrajectoryInvariants`, `BaselineComparison`, `BaselineOptions`, `cacheStoreCertificationProfile`, `CapturedRequest`, `CapturedRequestInput`, `captureIncident`, `CaptureIncidentOptions`, `CaseComparison`, `CaseResult`, `CertifiableCacheEntry`, `CertifiableCacheStore`, `CertifiableDeploymentAdapter`, `CertifiableDescriptorAdapter`, `CertifiableDomainEvent`, `CertifiableEventDeliveryAdapter`, `CertifiableEventRecord`, `CertifiableJobStore`, `CertifiableModelGateway`, `CertifiableRuntimeAdapter`, `CertifiableRuntimeServer`, `CertifiableStorageAdapter`, `CertificationCapabilityEvidence`, `CertificationCheck`, `CertificationCheckEvidence`, `CertificationTarget`, `certifyAdapter`, `checkTrajectoryInvariants`, `compareAgentEvalBaseline`, `ComparisonCode`, `ContractCaseContext`, `ContractCaseKind`, `ContractCoverageGap`, `ContractCoverageGapCode`, `ContractLabHandler`, `ContractLabRuntimeAdapter`, `ContractLabServer`, `ContractLabWitness`, `contractLabWitnesses`, `ContractReplay`, `ContractRuntime`, `ContractTarget`, `ContractTestApp`, `ContractWitness`, `cookieJar`, `CookieJar`, `createFailureLab`, `createReferenceContractLabHandler`, `createTrajectoryTranscript`, `CreateTrajectoryTranscriptOptions`, `defineAgentEvalSuite`, `defineCertificationProfile`, `defineFaultProfile`, `deploymentAdapterCertificationProfile`, `deploymentCertificationProfile`, `EffectLedger`, `eventDeliveryCertificationProfile`, `FailureDirective`, `FailureEvidence`, `FailureInjectedError`, `FailureKind`, `FailureLab`, `FailureLabOptions`, `FailureReplay`, `FailureScenario`, `FailureScenarioReport`, `FaultProfile`, `FaultProfileFault`, `FaultProfileFaultKind`, `FaultProfileReport`, `FaultProfileScenario`, `FaultProfileScenarioReport`, `gatewayCertificationProfile`, `generateRegressionTest`, `GenerateRegressionTestOptions`, `httpToolAdapter`, `IdempotencyDivergence`, `IdempotencyProof`, `IncidentCapsule`, `IncidentReplayError`, `IncidentReplayResult`, `inProcessToolAdapter`, `jobStoreCertificationProfile`, `mcpToolAdapter`, `modelGatewayCertificationProfile`, `parseRubricVerdict`, `PREDICTION_LAB_SEED`, `predictionLabCaseIds`, `PredictionLabContext`, `PredictionLabOptions`, `PredictionLabReplay`, `PredictionLabReport`, `PredictionLabResult`, `PredictionLabTarget`, `proveIdempotency`, `recordTrajectory`, `redactForEmission`, `referenceFaultProfile`, `registryCertificationProfile`, `replayIncident`, `ReplayIncidentOptions`, `replayTrajectory`, `ReplayTrajectoryOptions`, `RubricShape`, `RubricSpec`, `RubricVerdict`, `runAdversarialContract`, `runAgentEvalComposition`, `runAgentFailureMatrix`, `runContractLab`, `runContractLabOverHttp`, `runContractLabThroughAdapter`, `runFailureScenario`, `runFaultProfile`, `RunFaultProfileOptions`, `runPredictionLab`, `runtimeAdapterCertificationProfile`, `runTrajectory`, `ScoreTolerance`, `shapeOf`, `storageAdapterCertificationProfile`, `testSession`, `TestSession`, `TestSessionOptions`, `testToolAdapter`, `toPredictionLabContext`, `TrajectoryInvariantId`, `TrajectoryInvariantOptions`, `TrajectoryInvariantResult`, `trajectoryRegressionId`, `TrajectoryReplayResult`, `TrajectoryRun`, `TrajectoryTranscript`, `verifyAdapterCertification`
 
 ## @nifrajs/ts-plugin
 
@@ -11587,7 +12037,7 @@ done-gate, or `nifra mcp` to give the agent live project tools.
 
 ## @nifrajs/web
 
-`Action`, `ACTION_GLOBAL`, `assertRenderAdapterConformance`, `assertStaticBoundaryImports`, `Blocker`, `BlockerController`, `BlockerFunction`, `BlockerLocation`, `BlockerState`, `Boundary`, `BOUNDARY_GLOBAL`, `BoundaryDescriptor`, `boundaryDescriptors`, `BoundaryError`, `BoundaryMode`, `boundaryModeKey`, `BoundaryRegistration`, `BoundaryRequestCtx`, `BoundaryState`, `BoundaryStates`, `BoundaryStatus`, `BrowserNavigate`, `buildManifest`, `CachedResponse`, `CacheStore`, `canonical`, `ClientAction`, `ClientActionArgs`, `ClientActionResult`, `ClientLoader`, `ClientLoaderArgs`, `ClientRequestBody`, `ClientRouteHooks`, `ClientRouter`, `ClientRouterOptions`, `createClientRouter`, `createMatcher`, `createMutation`, `createQueryClient`, `createWebApp`, `CreateWebAppOptions`, `DATA_GLOBAL`, `DATA_HEADER`, `DEFAULT_DEV_PORT`, `defer`, `Deferred`, `DehydratedState`, `disableDraft`, `DRAFT_COOKIE`, `DraftCookieControls`, `DynamicBoundary`, `DynamicBoundaryBatch`, `enableDraft`, `EnableDraftOptions`, `enumerateStaticRoutes`, `Fetcher`, `FetcherState`, `FetchRouteData`, `filePathToPattern`, `filePathToPatterns`, `FontDisplay`, `fontFace`, `FontFace`, `fontPreload`, `FontPreloadInput`, `FontSource`, `generateClientEntry`, `GenerateClientEntryOptions`, `generateRouteSearchTypes`, `GenerateRouteSearchTypesOptions`, `generateServerManifest`, `GenerateServerManifestOptions`, `getBrowserNavigate`, `GetStaticPaths`, `gone`, `hashQueryKey`, `IDLE_BLOCKER`, `InertScriptType`, `InfiniteData`, `InfiniteQueryHandle`, `InfiniteQueryOptions`, `InterceptBoundary`, `isDraftEnabled`, `ISR_REVALIDATE_HEADER`, `ISR_REVALIDATE_TAGS_HEADER`, `ISR_STATUS_HEADER`, `ISRApp`, `ISROptions`, `ISRPlatform`, `jsonLd`, `KVCacheStore`, `KVCacheStoreOptions`, `KVNamespaceLike`, `LAYOUT_DATA_GLOBAL`, `LayoutEntry`, `LinkDescriptor`, `Loader`, `LoaderContext`, `Manifest`, `MemoryCacheStore`, `MemoryCacheStoreOptions`, `MemoryStaticBoundaryCache`, `mergeHeads`, `Meta`, `MetaArgs`, `MetaDescriptor`, `MetaInput`, `MountRouterOptions`, `MutationCallbacks`, `MutationHandle`, `MutationState`, `MutationStatus`, `NAV_FROM_HEADER`, `NavigateFunction`, `NavigateOptions`, `NavigateSearchOf`, `NavigateTargetInput`, `notFound`, `openGraph`, `OpenGraphInput`, `PendingBoundary`, `PRE_HYDRATION_GUARD`, `previewEndpoint`, `PreviewEndpointOptions`, `PublicDirCache`, `QueryClient`, `QueryClientOptions`, `QueryHandle`, `QueryOptions`, `QueryState`, `QueryStatus`, `redirect`, `REDIRECT_HEADER`, `RedirectOptions`, `registerBlocker`, `RenderAdapter`, `RenderAdapterConformanceError`, `RenderAdapterConformanceFixture`, `RenderAssemblyCache`, `RenderedPage`, `renderPage`, `RenderPageInput`, `RenderPageOptions`, `renderPageResult`, `RenderProps`, `resolveDynamicBoundaries`, `resolveMeta`, `resolveNavigate`, `resolvePublicPath`, `resolveStaticBoundaries`, `RETAIN_HEADER`, `revalidate`, `REVALIDATE_HEADER`, `revalidateEndpoint`, `RevalidateEndpointOptions`, `RevalidateResult`, `ROOT_ATTRIBUTE`, `ROUTE_GLOBAL`, `RouteEntry`, `RouteMatch`, `RouteModule`, `RoutePattern`, `RouterState`, `RouteSearch`, `ScriptDescriptor`, `searchOf`, `SearchOf`, `searchOfChain`, `serializeData`, `serializeSearch`, `servePublicDir`, `ServePublicDirOptions`, `SERVER_FN_MODULE`, `SERVER_ONLY_MODULE`, `ServerOnly`, `setBlockerController`, `setBrowserNavigate`, `setSsrModuleLoader`, `ssrModuleLoader`, `SsrModuleLoader`, `startDynamicBoundaries`, `StaticBoundary`, `StaticBoundaryCache`, `StaticBoundaryImportEdge`, `StaticBoundaryRoot`, `StaticCtx`, `StaticPath`, `StaticPaths`, `StaticRoutes`, `STATUS_HEADER`, `statusPage`, `StatusPageOptions`, `Submission`, `SubmitOptions`, `unsafeInlineScript`, `UnsafeScriptDescriptor`, `withISR`
+`Action`, `ACTION_GLOBAL`, `assertCssLoadingCompatible`, `assertRenderAdapterConformance`, `assertStaticBoundaryImports`, `Blocker`, `BlockerController`, `BlockerFunction`, `BlockerLocation`, `BlockerState`, `Boundary`, `BOUNDARY_GLOBAL`, `BoundaryDescriptor`, `boundaryDescriptors`, `BoundaryError`, `BoundaryMode`, `boundaryModeKey`, `BoundaryRegistration`, `BoundaryRequestCtx`, `BoundaryState`, `BoundaryStates`, `BoundaryStatus`, `BrowserNavigate`, `buildManifest`, `CachedResponse`, `CacheStore`, `canonical`, `ClientAction`, `ClientActionArgs`, `ClientActionResult`, `ClientLoader`, `ClientLoaderArgs`, `ClientRequestBody`, `ClientRouteHooks`, `ClientRouter`, `ClientRouterOptions`, `createClientRouter`, `createMatcher`, `createMutation`, `createQueryClient`, `createWebApp`, `CreateWebAppOptions`, `CssLoadingMode`, `DATA_GLOBAL`, `DATA_HEADER`, `DEFAULT_CSS_LOADING`, `DEFAULT_DEV_PORT`, `defer`, `Deferred`, `DehydratedState`, `disableDraft`, `DRAFT_COOKIE`, `DraftCookieControls`, `DynamicBoundary`, `DynamicBoundaryBatch`, `enableDraft`, `EnableDraftOptions`, `enumerateStaticRoutes`, `Fetcher`, `FetcherState`, `FetchRouteData`, `filePathToPattern`, `filePathToPatterns`, `FontDisplay`, `fontFace`, `FontFace`, `fontPreload`, `FontPreloadInput`, `FontSource`, `generateClientEntry`, `GenerateClientEntryOptions`, `generateRouteSearchTypes`, `GenerateRouteSearchTypesOptions`, `generateServerManifest`, `GenerateServerManifestOptions`, `getBrowserNavigate`, `GetStaticPaths`, `gone`, `hashQueryKey`, `HtmlSanitizer`, `IDLE_BLOCKER`, `InertScriptType`, `InfiniteData`, `InfiniteQueryHandle`, `InfiniteQueryOptions`, `InterceptBoundary`, `isDraftEnabled`, `ISR_REVALIDATE_HEADER`, `ISR_REVALIDATE_TAGS_HEADER`, `ISR_STATUS_HEADER`, `ISRApp`, `ISROptions`, `ISRPlatform`, `jsonLd`, `KVCacheStore`, `KVCacheStoreOptions`, `KVNamespaceLike`, `LAYOUT_DATA_GLOBAL`, `LayoutEntry`, `LinkDescriptor`, `Loader`, `LoaderContext`, `Manifest`, `MemoryCacheStore`, `MemoryCacheStoreOptions`, `MemoryStaticBoundaryCache`, `mergeHeads`, `Meta`, `MetaArgs`, `MetaDescriptor`, `MetaInput`, `MountRouterOptions`, `MutationCallbacks`, `MutationHandle`, `MutationState`, `MutationStatus`, `NAV_FROM_HEADER`, `NavigateFunction`, `NavigateOptions`, `NavigateSearchOf`, `NavigateTargetInput`, `NonceResolver`, `normalizeCssLoading`, `notFound`, `openGraph`, `OpenGraphInput`, `PendingBoundary`, `PRE_HYDRATION_GUARD`, `previewEndpoint`, `PreviewEndpointOptions`, `PublicDirCache`, `QueryClient`, `QueryClientOptions`, `QueryHandle`, `QueryOptions`, `QueryState`, `QueryStatus`, `redirect`, `REDIRECT_HEADER`, `RedirectOptions`, `registerBlocker`, `RenderAdapter`, `RenderAdapterConformanceError`, `RenderAdapterConformanceFixture`, `RenderAssemblyCache`, `RenderedPage`, `renderPage`, `RenderPageInput`, `RenderPageOptions`, `renderPageResult`, `RenderProps`, `resolveDynamicBoundaries`, `resolveMeta`, `resolveNavigate`, `resolvePublicPath`, `resolveStaticBoundaries`, `RETAIN_HEADER`, `revalidate`, `REVALIDATE_HEADER`, `revalidateEndpoint`, `RevalidateEndpointOptions`, `RevalidateResult`, `ROOT_ATTRIBUTE`, `ROUTE_GLOBAL`, `RouteEntry`, `RouteMatch`, `RouteModule`, `RoutePattern`, `RouterState`, `RouteSearch`, `sanitizedHtml`, `SanitizedHtml`, `sanitizeHtml`, `ScriptDescriptor`, `searchOf`, `SearchOf`, `searchOfChain`, `serializeData`, `serializeSearch`, `servePublicDir`, `ServePublicDirOptions`, `SERVER_FN_MODULE`, `SERVER_ONLY_MODULE`, `ServerOnly`, `setBlockerController`, `setBrowserNavigate`, `setSsrModuleLoader`, `ssrModuleLoader`, `SsrModuleLoader`, `startDynamicBoundaries`, `StaticBoundary`, `StaticBoundaryCache`, `StaticBoundaryImportEdge`, `StaticBoundaryRoot`, `StaticCtx`, `StaticPath`, `StaticPaths`, `StaticRoutes`, `STATUS_HEADER`, `statusPage`, `StatusPageOptions`, `Submission`, `SubmitOptions`, `TrustedHtml`, `trustHtml`, `unsafeInlineScript`, `UnsafeScriptDescriptor`, `withISR`
 
 ## @nifrajs/web-preact
 
@@ -11613,6 +12063,10 @@ done-gate, or `nifra mcp` to give the agent live project tools.
 
 `vueAdapter`
 
+## @nifrajs/webmcp
+
+`AgentCapability`, `AgentCapabilityReference`, `AgentSurfaceAuthoritativeState`, `AgentSurfaceConformanceCase`, `AgentSurfaceConformanceOptions`, `AgentSurfaceConformanceResult`, `AgentSurfaceDescriptor`, `AgentSurfacePrediction`, `AgentSurfacePredictionContext`, `AgentSurfacePredictor`, `AgentSurfaceReconcileContext`, `AgentSurfaceReconciler`, `AgentSurfaceScope`, `AgentSurfaceSnapshot`, `createPredictionStore`, `defineAgentCapability`, `DefineAgentCapabilityOptions`, `executeAgentCapability`, `executePredicted`, `ExecutePredictedOptions`, `PredictedExecutionResult`, `PredictionPatchOperation`, `PredictionStore`, `PredictionStoreEvent`, `PredictionStoreResult`, `PredictionStoreSnapshot`, `ReconciliationMode`, `registerWebMcpTools`, `runAgentSurfaceConformance`, `ToolApproval`, `ToolCallOptions`, `ToolCallResult`, `ToolContract`, `ToolContractOptions`, `ToolError`, `ToolEvidence`, `toWebMcpTool`, `WebMcpExecutionOptions`, `WebMcpModelContext`, `WebMcpReceipt`, `WebMcpRegistrationFailure`, `WebMcpRegistrationReport`, `WebMcpTarget`, `WebMcpToolDefinition`
+
 ## @nifrajs/workers
 
 `createWebSocketHub`, `NifraWebSocketHub`, `WebSocketHubApp`, `WebSocketHubClass`