eve 0.57.0 → 0.58.1

package/docs/guides/frontend/nextjs.mdx

@@ -3,13 +3,29 @@ title: "Next.js"
 description: "Run an eve agent and a Next.js app as one project with withEve."
 ---
 
-`eve/next` ships a Next.js frontend and an eve agent as a single project. Wrap your config with `withEve()` to run both from one dev server and one Vercel deploy. [`useEveAgent`](./overview) finds the mounted routes on its own, so there's no CORS to configure and no URL env vars to keep in sync.
+`eve/next` connects a Next.js app to one or more eve agents. Wrap your Next.js config with `withEve(nextConfig)` to run the app and agents with one development command and deploy them as one Vercel project. Browser requests use same-origin routes; the agent runtimes remain separate services.
+
+Use this integration when Next.js owns the application's development and deployment lifecycle. If the frontend is a peer of an agent workspace, compose the services with [`eve/vercel`](../deployment/vercel#compose-agents-with-other-vercel-services) on Vercel or your [self-hosted process manager and proxy](../deployment/self-hosting#run-workspace-members). A peer frontend can use `eve/react` without `eve/next`. See [Project Structure](/docs/concepts/project-structure#configure-a-web-deployment) for the choice.
 
 ## Prerequisites
 
 - The `eve` package installed in your project (`npm install eve@latest`).
-- An existing eve agent directory. If you don't have one, start from [Getting started](../../getting-started).
-- A Next.js app to mount the agent in.
+- An existing eve agent directory. If you don't have one, start from [Getting Started](../../getting-started).
+- A Next.js app, or a single-agent project where you want to generate one below.
+
+## Add the generated Web Chat app
+
+For a single-agent project, install the generated Next.js Web Chat app:
+
+```bash
+eve add channel/web
+```
+
+The installer adds a Next.js application and wraps `next.config.ts` with `withEve()`. The generated chat calls the unnamed agent through same-origin `/eve/v1/*` routes.
+
+Before accepting production browser traffic, replace the generated placeholder authorization policy. See [Authenticate browser requests](./overview#authenticate-browser-requests).
+
+The Web Chat installer does not support eve agent workspaces. If you want Next.js to host the integration, create a root Next.js application and follow the steps below; `withEve(nextConfig)` discovers workspace members but does not generate a chat UI. To keep the frontend as a peer application instead, follow the [workspace layout guidance](/docs/concepts/project-structure#configure-a-web-deployment).
 
 ## Wrap the Next.js config
 
@@ -22,7 +38,7 @@ const nextConfig: NextConfig = {};
 export default withEve(nextConfig);
 ```
 
-By default `withEve()` looks for an `agent/` folder inside your Next.js project root. When the project root is an eve workspace with `agents/<name>/` members, it discovers every member and mounts each at `/eve/agents/<name>/eve/v1/*` instead.
+By default `withEve(nextConfig)` looks for an `agent/` folder inside your Next.js project root and mounts its API at `/eve/v1/*`. When the project root is an eve workspace with `agents/<name>/` members, it discovers every member and mounts each at `/eve/<name>/v1/*` instead. You do not need an explicit `agents` map for this layout.
 
 If one agent lives somewhere else, point at it with `eveRoot`:
 
@@ -32,14 +48,16 @@ export default withEve(nextConfig, {
 });
 ```
 
+## Mount agents outside a workspace
+
 To mount agents that are not members of the project-level `agents/` workspace, use `agents`. String values are agent roots; object values can override the build command or private production service prefix for that agent:
 
 ```ts
 export default withEve(nextConfig, {
   agents: {
-    support: "./agents/support",
+    support: "./apps/support-agent",
     billing: {
-      root: "./agents/billing",
+      root: "./apps/billing-agent",
       buildCommand: "pnpm build:billing-agent",
       servicePrefix: "/_eve_internal/billing",
     },
@@ -47,7 +65,7 @@ export default withEve(nextConfig, {
 });
 ```
 
-Named agents mount under `/eve/agents/<name>/eve/v1/*`. Call the matching agent from React with `agent`:
+Named agents mount under `/eve/<name>/v1/*`. Call the matching agent from React with `agent`:
 
 ```tsx
 const support = useEveAgent({ agent: "support" });
@@ -56,19 +74,19 @@ const billing = useEveAgent({ agent: "billing" });
 
 Use either `eveRoot` or `agents`, not both. `eveRoot` remains the shorthand for a single unnamed agent mounted at `/eve/v1/*`.
 
-Generated agent services build with `EVE_PUBLIC_ROUTE_PREFIX` set to the agent's public mount (for example `/eve/agents/support`) so framework-minted callback URLs — OAuth connection callbacks and remote-subagent session callbacks — resolve to the public per-agent path. If you configure eve services manually in `vercel.json` instead, export that variable in each named agent's build command.
+Generated agent services build with `EVE_PUBLIC_ROUTE_PREFIX` set to the agent's public mount (for example `/eve/support`) so framework-minted callback URLs — OAuth connection callbacks and remote-subagent session callbacks — resolve to the public per-agent path. If you configure eve services manually in `vercel.json` instead, export that variable in each named agent's build command.
 
 ### `withEve` options
 
 All fields are optional.
 
-| Option               | Type                  | Default                  | Purpose                                                                                                                                                                                                                                                     |
-| -------------------- | --------------------- | ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `eveRoot`            | `string`              | Next.js app root         | Path to one unnamed eve app root, relative to `process.cwd()` unless absolute. Do not combine with `agents`.                                                                                                                                                |
-| `agents`             | `Record<string, ...>` | inferred for a workspace | Named eve agents to mount under `/eve/agents/<name>/eve/v1/*`. `withEve()` discovers project-level `agents/<name>/` members when neither `agents` nor `eveRoot` is set; otherwise each value is a root string or `{ root, buildCommand?, servicePrefix? }`. |
-| `eveBuildCommand`    | `string`              | generated                | Build command for generated eve Vercel services. In multi-agent mode this is the default for agents without their own `buildCommand`.                                                                                                                       |
-| `servicePrefix`      | `string`              | `"/_eve_internal/eve"`   | Private route namespace for legacy manual Vercel service configs and non-Vercel production proxying. Named agents derive unique defaults from this prefix.                                                                                                  |
-| `devServerTimeoutMs` | `number`              | `180000`                 | Maximum time to wait for each eve development server to become available.                                                                                                                                                                                   |
+| Option               | Type                  | Default                  | Purpose                                                                                                                                                                                                                                          |
+| -------------------- | --------------------- | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `eveRoot`            | `string`              | Next.js app root         | Path to one unnamed eve app root, relative to `process.cwd()` unless absolute. Do not combine with `agents`.                                                                                                                                     |
+| `agents`             | `Record<string, ...>` | inferred for a workspace | Named eve agents to mount under `/eve/<name>/v1/*`. `withEve()` discovers project-level `agents/<name>/` members when neither `agents` nor `eveRoot` is set; otherwise each value is a root string or `{ root, buildCommand?, servicePrefix? }`. |
+| `eveBuildCommand`    | `string`              | generated                | Build command for generated eve Vercel services. In multi-agent mode this is the default for agents without their own `buildCommand`.                                                                                                            |
+| `servicePrefix`      | `string`              | `"/_eve_internal/eve"`   | Private route namespace for legacy manual Vercel service configs and non-Vercel production proxying. Named agents derive unique defaults from this prefix.                                                                                       |
+| `devServerTimeoutMs` | `number`              | `180000`                 | Maximum time to wait for each eve development server to become available.                                                                                                                                                                        |
 
 For slow cold starts, increase the development timeout:
 
@@ -80,7 +98,24 @@ export default withEve(nextConfig, {
 
 ## Call the hook
 
-With `withEve()` in `next.config.ts`, the eve routes are same-origin, so client code can call [`useEveAgent`](./overview) without naming a host. Cookie-based auth (Auth.js or any session cookie) needs no extra wiring, since the browser already sends those cookies on every eve request. For non-cookie schemes, attach the credentials yourself:
+For a single unnamed agent, call [`useEveAgent`](./overview) without `agent` or `host`. For named agents, whether discovered from a workspace or configured explicitly, pass the name:
+
+```tsx
+"use client";
+
+import { useEveAgent } from "eve/react";
+
+export function SupportStatus() {
+  const support = useEveAgent({ agent: "support" });
+  return <p>{support.status}</p>;
+}
+```
+
+See [Basic chat](./overview#basic-chat-react) for rendering messages and sending turns.
+
+Bind each chat route to its agent, and include the agent identity in durable-session URLs so the UI does not restore a session through the wrong agent route. Remount the chat component when switching agents: the hook reads `agent` when it creates its store.
+
+Requests are same-origin, so the browser sends application cookies to the agent. Each agent must verify those credentials through its own channel authentication policy. For non-cookie schemes, attach the credentials yourself:
 
 ```tsx
 const agent = useEveAgent({
@@ -90,7 +125,7 @@ const agent = useEveAgent({
 });
 ```
 
-The browser still needs a production authentication policy. See [Authenticate browser requests](./overview#authenticate-browser-requests) for the default fail-closed behavior and channel configuration.
+Configure authorization for every exposed agent before accepting production browser traffic. See [Authenticate browser requests](./overview#authenticate-browser-requests) for the default fail-closed behavior and channel configuration.
 
 ## Use the generated Web Chat routes
 
@@ -129,15 +164,21 @@ See [Resumable sessions](./overview#resumable-sessions) for persistence and repl
 - **Local production build.** `next build && next start` serves the eve runtime from its built `.output/server/index.mjs` on a stable local port (`4274`) and proxies the eve routes to it. Run `eve build` first so that output exists. In an `agents/` workspace, build every member from its `agents/<name>/` directory before starting Next.js. Change the port with `EVE_NEXT_PRODUCTION_PORT`:
 
   ```bash
-  EVE_NEXT_PRODUCTION_PORT=5000 npm run build && npm start
+  export EVE_NEXT_PRODUCTION_PORT=5000
+  npm run build && npm start
   ```
 
-- **Non-Vercel hosts.** When the eve service lives on a separate origin, tell Next.js where to find it with `EVE_NEXT_PRODUCTION_ORIGIN`:
+- **Non-Vercel hosts.** `withEve()` provides both agent process startup and Next.js proxy rewrites; self-hosters using this path do not need to recreate the browser-facing routing. The Vercel service output is a separate integration, not a self-hosting requirement. By default, `next start` runs each built eve service on its derived loopback port. If your host supervises eve services itself, run each service separately and set `EVE_NEXT_PRODUCTION_ORIGIN` to the origin that serves its private route prefix:
 
   ```bash
-  EVE_NEXT_PRODUCTION_ORIGIN=https://agent.example.com npm run build
+  export EVE_NEXT_PRODUCTION_ORIGIN=https://agent.example.com
+  npm run build && npm start
   ```
 
+  This setting disables automatic production agent startup. The destination includes `servicePrefix`: for named agents, the default is `/_eve_internal/eve/<name>/eve/v1/*`. Configure that routing on the destination host, and use the same origin setting when building and starting Next.js.
+
+  If the public routing layer mounts an agent below a path, set `EVE_PUBLIC_ROUTE_PREFIX` in that agent's build and runtime environments so callback URLs use the public path. Process restarts, persistent workflow storage, sandbox configuration, and workflow callback routing remain hosting responsibilities; see [Self-host eve](../deployment/self-hosting).
+
 ## What to read next
 
 - [Frontend overview](./overview): the `useEveAgent` API

package/docs/guides/frontend/overview.mdx

@@ -3,16 +3,16 @@ title: "Overview"
 description: "Put an eve agent behind a browser chat UI with useEveAgent."
 ---
 
-The frontend helpers put a browser chat or agent UI on top of an eve agent. `useEveAgent()` opens a durable session, sends turns, streams the reply back, and turns the raw event stream into render-ready state. React is the reference implementation; [Vue](./use-eve-agent-vue) and [Svelte](./use-eve-agent-svelte) ship the same surface.
+Use this guide when you already have a browser application and need to connect it to an eve agent. `useEveAgent()` opens a durable session, sends turns, streams the reply back, and turns the raw event stream into render-ready state. React is the reference implementation; [Vue](./use-eve-agent-vue) and [Svelte](./use-eve-agent-svelte) ship the same surface.
 
 ## The integration model
 
 A browser UI is a client of the agent's HTTP routes (the [eve channel](../../channels/overview)). Two layers wire it up:
 
-- **The framework integration** mounts the eve routes on your app's origin, so the browser never crosses a CORS boundary or reads an env var to find the agent. Pick yours: [Next.js](./nextjs) (`withEve`), [Nuxt](./nuxt) (the `eve/nuxt` module), or [SvelteKit](./sveltekit) (the `eveSvelteKit` Vite plugin). On any other stack the hook talks to same-origin `/eve/v1/*` routes directly, or you pass an explicit `host`.
+- **Routing** makes the agent reachable from the browser. A framework integration can mount eve on your app's origin: [Next.js](./nextjs) (`withEve`), [Nuxt](./nuxt) (the `eve/nuxt` module), or [SvelteKit](./sveltekit) (the `eveSvelteKit` Vite plugin). If the frontend and agents are peer services, use your deployment platform or reverse proxy instead. The hook works with either setup; pass `host` for a different origin or a named path mount.
 - **The hook** (`useEveAgent`) holds the session state, streaming, errors, and composer status. It defaults to same-origin eve routes such as `/eve/v1/session`.
 
-The per-framework pages below walk through the wiring step by step: [Next.js](./nextjs), [Nuxt](./nuxt), and [SvelteKit](./sveltekit).
+The framework pages walk through the wiring step by step: [Next.js](./nextjs), [Nuxt](./nuxt), and [SvelteKit](./sveltekit). See [Project Structure](../../concepts/project-structure#configure-a-web-deployment) to choose between a framework integration and peer services.
 
 For scripts, server-to-server calls, evals, tests, or custom clients that do not need framework UI state, use the [Client SDK](../client/overview) directly.
 

package/docs/guides/instrumentation/otel.mdx

@@ -40,6 +40,8 @@ export default otel({
 The OpenTelemetry `tracePolicy` is a capture ceiling shared by every OTel
 destination. A destination cannot restore content excluded by this policy. It
 does not affect lifecycle-event providers created with `defineInstrumentation()`.
+See [Audience](../channels/overview#audience) for how channels classify the
+conversation passed to this policy.
 
 ## Add an OpenTelemetry destination
 
@@ -72,8 +74,11 @@ invoke_agent <agent>
 ```
 
 Each turn starts a new trace. The first subagent trace links to its caller with
-`eve.link.type=agent.dispatch`. Use `gen_ai.conversation.id` to find the traces
-for one conversation in your destination's span-search surface.
+`eve.link.type=agent.dispatch`; the link is not an authorization grant. For a
+remote agent, `trustedForwarders` lets the receiver accept the sender's session
+lineage and trace-content policy. See [Remote agents](../guides/remote-agents#preserving-trace-content).
+Use `gen_ai.conversation.id` to find the traces for one conversation in your
+destination's span-search surface.
 
 ## Manage built-in destinations
 

package/docs/guides/instrumentation/providers.mdx

@@ -109,9 +109,8 @@ requests for user input, provider metadata, and error details. Omitted content
 fields are unavailable to the handler.
 
 The channel assigns the audience once when it creates the session. It controls
-content capture, not access. Configure it in the [default eve HTTP
-channel](../channels/eve#audience) or a [custom
-channel](../channels/custom#conversation-audience).
+content capture, not access. See [Audience](../channels/overview#audience) for
+how the channel derives `public`, `private`, and `unknown`.
 
 ## Redact fields in a custom provider
 

package/docs/guides/remote-agents.md

@@ -137,7 +137,7 @@ This makes caller authority turn-scoped even when the remote child session is pe
 
 Identity forwarding does not make a persistent session private to one caller. Conversation history, tool outputs, and other child-session state still persist. If those values must not be visible across users, give each user a distinct child session or enforce that ownership at the application boundary.
 
-Forwarding is explicit on both sides. The receiver names which forwarders it trusts with `eveChannel({ trustedForwarders })` (see [Auth & route protection](./auth-and-route-protection#accepting-forwarded-identity-from-another-deployment)); a receiver that refuses the forwarder — or has no `trustedForwarders` at all — rejects with a 403 and the dispatch fails.
+Forwarding identity is explicit on both sides. The receiver names which deployments it trusts with `eveChannel({ trustedForwarders })` (see [Auth & route protection](./auth-and-route-protection#accepting-forwarded-identity-from-another-deployment)); refusing the forwarder rejects a forwarded principal with a 403. The same trust decision covers parent session lineage and, with principal forwarding, trace-content constraints.
 
 ## Trace propagation
 
@@ -147,6 +147,10 @@ traces for one conversation. Trace context is observability metadata, not an
 authorization grant. See [OpenTelemetry](../observability/otel#trace-topology)
 for the trace topology.
 
+eve carries parent session lineage separately. The receiver accepts it only
+when `trustedForwarders` approves the authenticated caller; otherwise, trace
+correlation continues without it.
+
 ## Preserving trace content
 
 With `forwardPrincipal: true`, a sampled remote dispatch forwards its original

package/docs/install-integrations.mdx

@@ -19,7 +19,7 @@ eve add memory/file
 
 If an item is not found, `eve add` searches the available catalogs and prints close matches without installing anything.
 
-Web Chat installs a project-level Next.js application and cannot currently be added to a top-level `agents/` workspace. For that topology, create a root Next.js application and wrap its config with [`withEve()`](./guides/frontend/nextjs); eve discovers the workspace agents automatically. eve rejects `eve add channel/web` before writing files when the selected agent belongs to such a workspace.
+Web Chat installs a project-level Next.js application. It cannot be added to an eve agent workspace; eve rejects the installation before writing files. See [Project Structure](./concepts/project-structure) for browser-app placement and [Next.js](./guides/frontend/nextjs) for manual integration.
 
 If you do not know an item name yet, run `eve add` without an argument. Its help output shows how to search the registry with `eve registry search <query>`.
 

package/docs/meta.json

@@ -21,6 +21,7 @@
     "---Integrate---",
     "install-integrations",
     "extensions",
+    "guides/evaluate",
     "guides/remote-agents",
     "protocols",
     "guides/frontend",

package/docs/reference/agent-files.md

@@ -0,0 +1,104 @@
+---
+title: "Agent Files"
+description: "Look up agent directory slots, path-derived names, subagent files, and filesystem discovery rules."
+---
+
+eve builds an agent from files under its agent directory. Each supported path determines how eve loads the file. For recommended project layouts and when to split agents, read [Project Structure](/docs/concepts/project-structure).
+
+## Agent directory layout
+
+In a single-agent project, the agent directory is `agent/`. In an eve agent workspace, each member has an `agents/<name>/agent/` directory. A minimal root agent needs an instructions source; `agent.ts` is optional when the default configuration is sufficient.
+
+```text
+agent/
+├── agent.ts
+├── instructions.md
+├── instrumentation.ts
+├── channels/
+├── connections/
+├── extensions/
+├── hooks/
+├── skills/
+├── lib/
+├── memory/
+├── sandbox/
+├── tools/
+├── schedules/
+└── subagents/
+```
+
+Add only the files you need. Framework defaults use the same slots, so a file at the same path replaces the default when eve compiles the agent. Evals live beside `agent/`, not inside it.
+
+## Naming from paths
+
+eve derives capability names from file paths:
+
+| Path                                  | Resolves to           |
+| ------------------------------------- | --------------------- |
+| `agent/tools/get_weather.ts`          | tool `get_weather`    |
+| `agent/connections/linear.ts`         | connection `linear`   |
+| `agent/skills/summarize.md`           | skill `summarize`     |
+| `agent/subagents/researcher/agent.ts` | subagent `researcher` |
+
+A standalone root agent uses its package name (without an npm scope), or its app directory name when no name is set. An eve workspace member uses its directory name under `agents/`. A local subagent uses its directory name under `subagents/`.
+
+## Agent files and directories
+
+Paths below are relative to the agent directory. Root agents can use every path; subagents can use paths marked **Yes**.
+
+| Path                                                    | Purpose                                   | Available to subagents | Notes                                                                                                                                   |
+| ------------------------------------------------------- | ----------------------------------------- | ---------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
+| `agent.ts`                                              | Runtime config                            | Yes                    | Model, model options, compaction, build, and experimental settings. See [Agents](/docs/agent-config).                                   |
+| `instructions.md` / `instructions.ts` / `instructions/` | Base system prompt                        | Yes                    | A flat file or directory of `.md` and `.ts` files. Required on the root, optional on subagents. See [Instructions](/docs/instructions). |
+| `instrumentation.ts`                                    | Telemetry config                          | No                     | Auto-discovered and run before agent code. See [Instrumentation](/docs/observability/instrumentation).                                  |
+| `channels/`                                             | HTTP and messaging entry points           | No                     | See [Channels](/docs/channels/overview).                                                                                                |
+| `connections/`                                          | External MCP and OpenAPI services         | Yes                    | Static files define path-named connections; dynamic sources can resolve caller-specific connections.                                    |
+| `extensions/`                                           | Mounted reusable capabilities             | Yes                    | File or directory mounts. See [Extensions](/docs/extensions).                                                                           |
+| `hooks/`                                                | Lifecycle and stream-event subscribers    | Yes                    | Module-backed only; recursive directories are supported.                                                                                |
+| `skills/`                                               | On-demand procedures and capability packs | Yes                    | Flat Markdown, module-backed skills, or packaged skills.                                                                                |
+| `lib/`                                                  | Shared authored helper code               | Yes                    | Import-only; not copied into the sandbox.                                                                                               |
+| `memory.ts` or `memory/<name>.ts`                       | Cross-session memory                      | Yes                    | Provider-backed slots. See [Memory](/docs/memory).                                                                                      |
+| `sandbox.ts` or `sandbox/sandbox.ts`                    | The agent's sandbox                       | Yes                    | The framework default applies when neither is authored.                                                                                 |
+| `sandbox/workspace/**`                                  | Files seeded into the sandbox             | Yes                    | Mirrored into `/workspace/` when a session starts.                                                                                      |
+| `tools/`                                                | Typed executable integrations             | Yes                    | Module-backed only.                                                                                                                     |
+| `schedules/`                                            | Recurring jobs                            | No                     | `defineSchedule` modules or Markdown prompts with `cron` frontmatter; recursive nesting is supported.                                   |
+| `subagents/`                                            | Specialist child agents                   | Yes                    | Local directories or remote-agent definitions; nested subagents are supported.                                                          |
+
+## Files available in the sandbox
+
+Agent source files are not automatically available to shell commands. Put files to copy into the sandbox's `/workspace/` under `agent/sandbox/workspace/`. Skill runtime files are seeded separately under `$HOME/.agents/skills/`, with `/workspace/skills/` as a fallback. See [Sandboxes](/docs/sandbox) and [Skills](/docs/skills).
+
+## Local subagents
+
+A local declared subagent lives at `agent/subagents/<name>/`:
+
+```text
+agent/subagents/researcher/
+├── agent.ts                # required; must include description
+├── instructions.md         # optional
+├── tools/
+└── subagents/
+```
+
+It uses the same `defineAgent` helper as the root and supports the slots marked **Yes** above. Channels, schedules, and instrumentation are root-only. A declared subagent does not inherit its parent's authored slots; see [Subagents](/docs/subagents#the-isolation-boundary) for defaults and isolation behavior.
+
+## Flat layout
+
+eve also supports agent files directly in the app root, without an `agent/` directory:
+
+```text
+my-agent/
+├── package.json
+├── agent.ts
+├── instructions.md
+├── tools/
+└── skills/
+```
+
+Workspace members can also use flat agent files directly under `agents/<name>/`. Prefer the nested layouts in [Project Structure](/docs/concepts/project-structure) to keep application files separate from agent definitions.
+
+## Debug file discovery
+
+Run `eve info` from the agent's app directory, or `eve info --agent <name>` from an eve workspace root. It lists the discovered files and diagnostics. eve also writes inspectable artifacts under `.eve/`; see the [CLI reference](/docs/reference/cli#eve-info).
+
+Workspace discovery includes only direct `agents/<name>/` children with agent files and no `package.json` of their own. A root `agent/` directory takes precedence over `agents/` and makes the project single-agent. See [Add a second root agent](/docs/concepts/project-structure#add-a-second-root-agent) to convert that layout.

package/docs/reference/cli.md

@@ -399,10 +399,10 @@ Lists the user-authored channels in the current project.
 4. `eve build` before shipping.
 5. `eve start` to smoke-test the built output locally.
 
-Related: [Project layout](../getting-started#project-layout) · [Instrumentation](../observability/instrumentation).
+Related: [Agent Files](/docs/reference/agent-files) · [Instrumentation](../observability/instrumentation).
 
 ## What to read next
 
-- [Project layout](../getting-started#project-layout): what `eve info` discovers
+- [Agent Files](/docs/reference/agent-files): what `eve info` discovers
 - [Instrumentation](../observability/instrumentation): tracing and the error catalog
 - [Deployment](../guides/deployment/overview): `eve build` and `eve start` in production

package/docs/reference/meta.json

@@ -1 +1 @@
-{ "title": "Reference", "pages": ["typescript-api", "cli", "telemetry"] }
+{ "title": "Reference", "pages": ["agent-files", "typescript-api", "cli", "telemetry"] }

package/docs/reference/typescript-api.md

@@ -137,6 +137,7 @@ import template from "../../prompts/template.txt?raw";
 | `eve/local-dev`                                                             | `getLocalDevCapability`, `LocalDevCapability`                                                           |
 | `eve/models/openai`                                                         | `openai`, `chatgpt`, deprecated `experimental_chatgpt`                                                  |
 | `eve/models/anthropic`                                                      | `anthropic`                                                                                             |
+| [`eve/experimental/evaluate`](../guides/evaluate)                           | Experimental `autoModel`                                                                                |
 | `eve/evals`                                                                 | `defineEval`, `defineEvalConfig`, `mockModel`, eval types                                               |
 | `eve/evals/expect`                                                          | `includes`, `equals`, `matches`, `similarity`                                                           |
 | `eve/evals/reporters`                                                       | `Braintrust`, `JUnit`, `EvalReporter`                                                                   |
@@ -223,4 +224,4 @@ Troubleshooting:
 
 - [`agent.ts`](../agent-config): the agent config these helpers configure
 - [Tools](../tools): `defineTool`, the most-used helper
-- [Project layout](../getting-started#project-layout): where each define\* lives on disk
+- [Agent Files](/docs/reference/agent-files): where each define\* lives on disk

package/docs/schedules.mdx

@@ -107,7 +107,7 @@ The route is dev-only. Production builds never mount it, and it needs no auth si
 
 ## On Vercel
 
-Hosted Vercel builds turn every `defineSchedule(...)` into a Vercel Cron Job, with each `cron` written as an entry in `.vercel/output/config.json`. This also applies when [`withEve`](./guides/frontend/nextjs) embeds one or more agents in a Next.js deployment: Vercel assembles each generated eve service's schedules into the project Build Output config while preserving existing project cron entries. Named agents use their public `/eve/agents/<name>` route prefix automatically.
+Hosted Vercel builds turn every `defineSchedule(...)` into a Vercel Cron Job, with each `cron` written as an entry in `.vercel/output/config.json`. This also applies when [`withEve`](./guides/frontend/nextjs) embeds one or more agents in a Next.js deployment: Vercel assembles each generated eve service's schedules into the project Build Output config while preserving existing project cron entries. Named agents use their public `/eve/<name>` route prefix automatically.
 
 When running `vercel build` locally, use Vercel CLI 56.4.0 or later so generated-service cron entries are included in the project output.
 

package/docs/subagents/index.mdx

@@ -79,7 +79,7 @@ export default defineWorkspaceAgent({
 });
 ```
 
-The helper uses the peer's root `defineAgent({ description })` value as the model-visible tool description. Pass `description` to override it for this caller. When `transport` is omitted, eve selects the built-in transport for the runtime environment. Vercel deployments route through the current deployment and authenticate with the caller's Vercel OIDC token. A workspace hosted through `withEve()` in a Next.js app uses its `/eve/agents/<name>` mount; a hostless workspace uses `/<name>`. Outside Vercel, provide an explicit transport with `url` and optional `auth` or `headers`:
+The helper uses the peer's root `defineAgent({ description })` value as the model-visible tool description. Pass `description` to override it for this caller. When `transport` is omitted, eve selects the built-in transport for the Vercel runtime environment. Local `vercel dev` routes workspace calls without deployment credentials; Vercel deployments route calls through the current deployment and authenticate with the caller's Vercel OIDC token. Named peers use their `/eve/<name>` mount. Outside those environments, provide an explicit transport with `url` and optional `auth` or `headers`:
 
 ```ts title="agents/foreman/agent/subagents/research.ts"
 import { defineWorkspaceAgent } from "eve";
@@ -96,7 +96,7 @@ export default defineWorkspaceAgent({
 
 An explicit transport replaces the environment default completely. The receiving peer must still accept the transport's credentials through its channel authentication policy. Set `forwardPrincipal: true` only when the peer trusts the caller to forward user identity, as described in [Remote agents](./guides/remote-agents#forward-the-callers-identity).
 
-Use the peer's directory name under `agents/`. eve requires an exact workspace-member match, so add another declared subagent file for each additional peer. `eve dev` does not provide local workspace routing; configure an explicit transport to target a separately running peer.
+Use the peer's directory name under `agents/`. eve requires an exact workspace-member match, so add another declared subagent file for each additional peer. Run `vercel dev --local` with a root `vercel.ts` composed by `withEve` to start every member and enable the default local workspace transport. `eve dev` starts only the selected agent; use an explicit transport if it must call a separately running peer.
 
 ### Conditional availability
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "eve",
-  "version": "0.57.0",
+  "version": "0.58.1",
   "private": false,
   "description": "Filesystem-first framework for durable backend AI agents that run anywhere.",
   "keywords": [
@@ -437,6 +437,11 @@
       "types": "./dist/src/self-modification/config.d.ts",
       "import": "./dist/src/self-modification/config.js",
       "default": "./dist/src/self-modification/config.js"
+    },
+    "./experimental/evaluate": {
+      "types": "./dist/src/public/experimental/evaluate/index.d.ts",
+      "import": "./dist/src/public/experimental/evaluate/index.js",
+      "default": "./dist/src/public/experimental/evaluate/index.js"
     }
   },
   "publishConfig": {
@@ -449,7 +454,7 @@
   "devDependencies": {
     "@agentclientprotocol/sdk": "1.3.0",
     "@ai-sdk/anthropic": "^4.0.49",
-    "@ai-sdk/code-mode": "^1.0.50",
+    "@ai-sdk/code-mode": "^1.0.62",
     "@ai-sdk/google": "^4.0.64",
     "@ai-sdk/mcp": "^2.0.45",
     "@ai-sdk/openai": "^4.0.60",
@@ -490,7 +495,7 @@
     "@workflow/world": "5.0.0-beta.35",
     "@workflow/world-local": "5.0.0-beta.44",
     "@workflow/world-vercel": "5.0.0-beta.46",
-    "ai": "^7.0.93",
+    "ai": "^7.0.105",
     "autoevals": "0.0.132",
     "chat": "4.34.0",
     "chokidar": "5.0.0",
@@ -524,7 +529,7 @@
   },
   "peerDependencies": {
     "@opentelemetry/api": "^1.0.0",
-    "ai": "^7.0.93",
+    "ai": "^7.0.105",
     "braintrust": "^3.0.0",
     "dd-trace": "^6.13.0",
     "just-bash": "^3.1.0",