eve 0.63.0 → 0.64.1

package/docs/README.md

@@ -12,32 +12,28 @@ Important naming note:
 
 ## Find the page for your task
 
-| To do this                                               | Read this                                                                                                                    |
-| -------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
-| Organize agents, subagents, and browser application code | [Project Structure](./concepts/project-structure.mdx)                                                                        |
-| Create a project and run your first agent                | [Getting Started](./getting-started.mdx)                                                                                     |
-| Look up agent files and discovery rules                  | [Agent Files](./reference/agent-files.md)                                                                                    |
-| Set the model, reasoning, or other agent-wide config     | [Agents](./agent-config.md)                                                                                                  |
-| Choose an agent model automatically for each request     | [Automatic Model Selection](./guides/evaluate.md)                                                                            |
-| Change what the agent does and how it behaves            | [Instructions](./instructions.mdx)                                                                                           |
-| Give the agent a typed capability it can call            | [Tools](./tools/overview.mdx)                                                                                                |
-| Require approval, or ask the user something mid-turn     | [Human in the Loop](./tools/human-in-the-loop.md)                                                                            |
-| Call an external HTTP API or MCP server                  | [Connections](./connections/overview.mdx)                                                                                    |
-| Add a messaging surface (Slack, Discord, iMessage, …)    | [Channels](./channels/overview.mdx)                                                                                          |
-| Expose your own HTTP route as a conversation surface     | [Custom Channels](./channels/custom.mdx)                                                                                     |
-| Package a procedure the agent loads only when it applies | [Skills](./skills.mdx)                                                                                                       |
-| Carry state across turns, or shape what the model sees   | [State](./concepts/state.md), [Context Control](./concepts/context-control.md)                                               |
-| Run commands or untrusted code in isolation              | [Sandboxes](./sandbox.mdx)                                                                                                   |
-| Delegate work to a specialist child agent                | [Subagents](./subagents/index.mdx)                                                                                           |
-| Run work on a recurring schedule                         | [Schedules](./schedules.mdx)                                                                                                 |
-| Install an existing integration instead of writing one   | [Add Integrations](./install-integrations.mdx)                                                                               |
-| Link a Vercel project and deploy to production           | [Deploy to Vercel](./guides/deployment/vercel.mdx)                                                                           |
-| Self-host, or compare hosting strategies                 | [Deployment](./guides/deployment/overview.md)                                                                                |
-| Authorize routes, sessions, and per-user access          | [Authentication](./guides/auth-and-route-protection.md)                                                                      |
-| Add a browser application                                | [Next.js](./guides/frontend/nextjs.mdx), [Nuxt](./guides/frontend/nuxt.mdx), or [SvelteKit](./guides/frontend/sveltekit.mdx) |
-| Build a custom web UI, or stream a session to a client   | [Client SDK](./guides/client/overview.mdx), [Frontend](./guides/frontend/overview.mdx)                                       |
-| Test the agent's behavior                                | [Evals](./evals/overview.mdx)                                                                                                |
-| Look up a CLI command or an exported type                | [CLI](./reference/cli.md), [TypeScript API](./reference/typescript-api.md)                                                   |
+| To do this                                               | Read this                                                                              |
+| -------------------------------------------------------- | -------------------------------------------------------------------------------------- |
+| Create a project, or understand the file layout          | [Getting Started](./getting-started.mdx)                                               |
+| Set the model, reasoning, or other agent-wide config     | [Agents](./agent-config.md)                                                            |
+| Change what the agent does and how it behaves            | [Instructions](./instructions.mdx)                                                     |
+| Give the agent a typed capability it can call            | [Tools](./tools/overview.mdx)                                                          |
+| Require approval, or ask the user something mid-turn     | [Human in the Loop](./tools/human-in-the-loop.md)                                      |
+| Call an external HTTP API or MCP server                  | [Connections](./connections/overview.mdx)                                              |
+| Add a messaging surface (Slack, Discord, iMessage, …)    | [Channels](./channels/overview.mdx)                                                    |
+| Expose your own HTTP route as a conversation surface     | [Custom Channels](./channels/custom.mdx)                                               |
+| Package a procedure the agent loads only when it applies | [Skills](./skills.mdx)                                                                 |
+| Carry state across turns, or shape what the model sees   | [State](./concepts/state.md), [Context Control](./concepts/context-control.md)         |
+| Run commands or untrusted code in isolation              | [Sandboxes](./sandbox/index.mdx)                                                       |
+| Delegate work to a specialist child agent                | [Subagents](./subagents/index.mdx)                                                     |
+| Run work on a recurring schedule                         | [Schedules](./schedules.mdx)                                                           |
+| Install an existing integration instead of writing one   | [Add Integrations](./install-integrations.mdx)                                         |
+| Link a Vercel project and deploy to production           | [Deploy to Vercel](./guides/deployment/vercel.mdx)                                     |
+| Self-host, or compare hosting strategies                 | [Deployment](./guides/deployment/overview.md)                                          |
+| Authorize routes, sessions, and per-user access          | [Authentication](./guides/auth-and-route-protection.md)                                |
+| Build a web UI, or stream a session to a client          | [Client SDK](./guides/client/overview.mdx), [Frontend](./guides/frontend/overview.mdx) |
+| Test the agent's behavior                                | [Evals](./evals/overview.mdx)                                                          |
+| Look up a CLI command or an exported type                | [CLI](./reference/cli.md), [TypeScript API](./reference/typescript-api.md)             |
 
 ## Legal and safeguards
 
@@ -58,25 +54,24 @@ Unless you configure stricter controls, eve agents may operate with permissive s
 For a full picture rather than a single task, read in this order:
 
 1. [Getting Started](./getting-started.mdx)
-2. [Project Structure](./concepts/project-structure.mdx)
-3. [Tutorial](./tutorial/first-agent.mdx)
-4. [Agents](./agent-config.md)
-5. [TypeScript API Reference](./reference/typescript-api.md)
-6. [Context Control](./concepts/context-control.md)
-7. [Skills](./skills.mdx)
-8. [Tools](./tools/overview.mdx)
-9. [Connections](./connections/overview.mdx)
-10. [Sandboxes](./sandbox.mdx)
-11. [Channels](./channels/overview.mdx)
-12. [Session Context](./guides/session-context.md)
-13. [Sessions and Streaming](./concepts/sessions-runs-and-streaming.md)
-14. [Client SDK](./guides/client/overview.mdx)
-15. [Subagents](./subagents/index.mdx)
-16. [Schedules](./schedules.mdx)
-17. [Evals](./evals/overview.mdx)
-18. [Authentication](./guides/auth-and-route-protection.md)
-19. [Deployment](./guides/deployment/overview.md)
-20. [CLI](./reference/cli.md)
+2. [Tutorial](./tutorial/first-agent.mdx)
+3. [Agents](./agent-config.md)
+4. [TypeScript API Reference](./reference/typescript-api.md)
+5. [Context Control](./concepts/context-control.md)
+6. [Skills](./skills.mdx)
+7. [Tools](./tools/overview.mdx)
+8. [Connections](./connections/overview.mdx)
+9. [Sandboxes](./sandbox/index.mdx)
+10. [Channels](./channels/overview.mdx)
+11. [Session Context](./guides/session-context.md)
+12. [Sessions and Streaming](./concepts/sessions-runs-and-streaming.md)
+13. [Client SDK](./guides/client/overview.mdx)
+14. [Subagents](./subagents/index.mdx)
+15. [Schedules](./schedules.mdx)
+16. [Evals](./evals/overview.mdx)
+17. [Authentication](./guides/auth-and-route-protection.md)
+18. [Deployment](./guides/deployment/overview.md)
+19. [CLI](./reference/cli.md)
 
 ## The public mental model
 

package/docs/agent-config.md

@@ -1,5 +1,5 @@
 ---
-title: "Agents"
+title: "Agent Configuration"
 description: "Configure an eve agent's model, reasoning effort, compaction, limits, and runtime behavior in agent.ts."
 ---
 
@@ -21,7 +21,7 @@ For a static AI Gateway model ID, you can make the same source change from the
 project root with `eve set --model anthropic/claude-opus-4.8` or from the local
 dev TUI with `/model anthropic/claude-opus-4.8`.
 
-The root `agent.ts` can be omitted when no runtime config is needed. eve then selects its default `agent.ts` source at the same slot, configured with `openai/gpt-5.6-luna-fast`; authoring the file replaces that source.
+The root `agent.ts` can be omitted when no runtime config is needed. eve then selects its default `agent.ts` source at the same slot, configured with `spacexai/grok-4.7`; authoring the file replaces that source.
 When `agent.ts` is present, `model` is required.
 
 A config that selects a static Gateway model is compile-only. A config that contains a dynamic model or a direct-provider `LanguageModel` remains a runtime entry because eve must resolve that authored value while the agent runs. See [Authored module lifecycle](./reference/typescript-api#authored-module-lifecycle).

package/docs/channels/eve.mdx

@@ -34,7 +34,7 @@ The default eve channel inspects the agent, creates sessions, accepts callbacks
 
 The session routes use only durable session IDs. Create a session explicitly, then put its returned ID in every follow-up, control, and stream path.
 
-`GET /eve/v1/health` is public and returns `{ ok: true, status: "ready", workflowId: string }`. `GET /eve/v1/info` uses the channel's auth policy and returns agent-info version 4. The TypeScript client validates both successful payloads: malformed health JSON throws `HealthResponseError`, malformed inspection JSON throws `AgentInfoResponseError`, and a non-success response from either route throws `ClientError`.
+`GET /eve/v1/health` is public and returns `{ ok: true, status: "ready", workflowId: string }`. `GET /eve/v1/info` uses the channel's auth policy and returns agent-info version 6. The TypeScript client validates both successful payloads: malformed health JSON throws `HealthResponseError`, malformed inspection JSON throws `AgentInfoResponseError`, and a non-success response from either route throws `ClientError`.
 
 ### Start and continue a session
 

package/docs/channels/overview.mdx

@@ -76,6 +76,54 @@ When eve doesn't ship a channel for your surface, build one with `defineChannel`
 
 A cross-channel `send(...)` supplies input to the agent and invokes the model on the destination channel. eve does not currently provide a direct cross-channel provider-message queue. To post without starting a turn, use the provider API. See [Durable cross-channel notifications](../patterns/durable-cross-channel-notifications) when delivery also needs application-managed retries and deduplication.
 
+## Background task results
+
+Pass `taskDeliveryPolicy` to `send(...)` to choose how the session reports background results:
+
+- `"auto"` (default for new channel sessions): ready results can invoke the parent while other tasks continue. The parent reports results that are useful independently and stays silent when a useful answer needs unfinished work.
+- `"cohort"`: wait for overlapping tasks to settle, then deliver their terminal outcomes together.
+
+```ts title="agent/channels/reports.ts"
+import { defineChannel, POST } from "eve/channels";
+import { localDev, routeAuth } from "eve/channels/auth";
+
+export default defineChannel({
+  routes: [
+    POST("/reports", async (request, { from }) => {
+      const auth = await routeAuth(request, localDev());
+      if (auth instanceof Response) return auth;
+      const session = await from("daily-report").send("Prepare the daily reports.", {
+        auth,
+        taskDeliveryPolicy: "cohort",
+      });
+      return Response.json({ sessionId: session.id });
+    }),
+  ],
+});
+```
+
+The option is available on channel-local `from(...).send(...)`, cross-channel
+`to(...).send(...)`, fixed-session `send(...)`, Chat SDK `bridge.send(...)`, and client
+sends. An explicit value
+updates the session's policy, including pending background tasks; later sends that
+omit it preserve that policy. A cross-channel send carries its setting through the
+receiver's `from(...).send(...)` unless that call supplies an explicit value.
+
+[Schedules](../schedules#background-task-results) default new sessions to `"cohort"`.
+A schedule handler can pass `taskDeliveryPolicy: "auto"` to `send(...)` to override
+that default. Child sessions use their own policy.
+
+With `"auto"`, a model call may finish without a user-visible message. Results
+already queued from the same cohort may share a turn. Each reporting turn receives
+the whole cohort, including pending tasks and available outputs, so previously
+withheld results remain available for a later combined report.
+
+Input requests and explicit task messages remain eligible for delivery under
+either policy. Failure and cancellation update task state immediately; their
+automatic reports follow the selected policy. User messages follow `turnPolicy`.
+See [Completion batching](../subagents#completion-batching) for cohort membership
+and result ordering.
+
 ## Relationship to the Chat SDK
 
 eve uses the [Chat SDK's card-builder components](https://chat-sdk.dev/docs/api/cards) (Cards, Buttons, Actions, etc.) for composing rich Slack messages. When you build a card with the [Slack channel](./slack), the underlying primitives come from the Chat SDK and get converted to Slack Block Kit at post time.

package/docs/channels/slack.mdx

@@ -135,7 +135,7 @@ Check the delivery path in order so you can identify where a Slack event stops:
 | Mentions work but DMs or thread replies do not                        | Check the Slack app's Event Subscriptions and OAuth scopes. DMs require `message.im` and `im:history`; channel replies require the matching message event and history scope.           | Add the missing events or scopes, then reinstall the Slack app if Slack requires it.                                                                                 |
 | A long response cannot be uploaded as a snippet                       | Check whether the installed Slack app has the `files:write` bot scope.                                                                                                                 | Add `files:write`, then reinstall the Slack app so the new scope takes effect.                                                                                       |
 | A preview request receives an authentication page or protection error | Check whether the branch domain is exempt or the direct Slack request URL includes `x-vercel-protection-bypass`. Slack cannot complete an interactive Vercel Authentication challenge. | Add a Deployment Protection Exception for the branch domain, or add the automation bypass query parameter to a Slack app that uses environment-variable credentials. |
-| The webhook reaches the deployment but the agent does not reply       | Open the project's Vercel runtime logs, then inspect the session in **Agent Runs** when your team has access.                                                                          | Use the first missing or failed stage to narrow the issue to channel dispatch, the agent run, or outbound Slack delivery.                                            |
+| The webhook reaches the deployment but the agent does not reply       | Open the project's Vercel runtime logs and locate the request for the inbound Slack event.                                                                                             | Use the first missing or failed stage to narrow the issue to channel dispatch, model or tool execution, or outbound Slack delivery.                                  |
 
 ## Audience
 

package/docs/concepts/execution-model-and-durability.mdx

@@ -56,7 +56,7 @@ that has not reached its next turn dispatch has not migrated yet.
 Transparent rollback to the former execution model is unsupported. Retire and
 restart affected sessions before rolling back.
 
-Nitro hosts the HTTP routes and workflow entrypoints. It does not supply the workflow state store or the sandbox runtime. Those are separate adapters: Workflow uses the active world implementation, and Sandbox uses the backend from `agent/sandbox` or `defaultBackend()`.
+Nitro hosts the HTTP routes and workflow entrypoints. It does not supply the workflow state store or the sandbox runtime. Those are separate adapters: Workflow uses the active world implementation, and Sandbox uses the backend from `agent/sandbox` or the default sandbox environment.
 
 For advanced self-hosted deployments, the root `agent.ts` can select the installed Workflow world package to use with `experimental.workflow.world`:
 

package/docs/concepts/sessions-runs-and-streaming.md

@@ -214,7 +214,7 @@ With one question-only batch, an exact option match or permitted freeform respon
 
 A structured response matches any currently pending request by ID, not only the newest batch. It becomes stale only after that request was answered, cleared, or cancelled. eve delivers a stale response to the model as a new user message, and the model decides whether the old selection still matters. A stale approval never authorizes the earlier tool call; the model must request the action and approval again if they are still needed.
 
-One delivery can answer requests from several batches. eve resumes approval-bearing batches in durable order and carries later answers forward until each batch can resume.
+One delivery can answer requests from several batches. eve resumes approval-bearing batches in durable order and carries later answers forward until each batch can resume. If you answer only some approvals in a batch, eve saves those responses until the remaining approvals are answered. Meanwhile, unrelated messages can run tools and receive a completed reply. The saved partial responses neither block that reply nor trigger another model call after it.
 
 Multiple steering messages retain their durable arrival order and may be folded into one input at the next boundary. A message accepted after turn settlement starts the next turn. See [message delivery and steering](./execution-model-and-durability#message-delivery-and-steering).
 
@@ -301,7 +301,7 @@ Start with the [Client SDK](../guides/client/overview) guide. It covers basic us
 
 ## Inspect the agent over HTTP
 
-`GET /eve/v1/info` returns agent-info version 4, a JSON inspection snapshot of the effective compiled agent. It reports the selected config; active tools, instructions, memory slots, skills, channels, schedules, sandbox, connections, hooks, and instrumentation with explicit source ownership; dynamic resolvers separately from their session-specific output; local and remote agents in separate collections; prepared built-in effects; and shadowed or disabled source diagnostics. Memory tool wrappers include their selected memory-source dependency. Channel routes appear in the same effective order used by the HTTP host. Static instructions remain an ordered array whose entries expose `content` and `role`.
+`GET /eve/v1/info` returns agent-info version 6, a JSON inspection snapshot of the effective compiled agent. It reports the selected config; active tools, instructions, memory slots, skills, channels, schedules, sandbox, connections, hooks, and instrumentation with explicit source ownership; dynamic resolvers separately from their session-specific output; local and remote agents in separate collections; prepared built-in effects; and shadowed or disabled source diagnostics. Memory tool wrappers include their selected memory-source dependency. Channel routes appear in the same effective order used by the HTTP host. Static instructions remain an ordered array whose entries expose `content` and `role`. Sandbox inspection exposes the opaque `revisionHash` that identifies its compiler-discovered environment inputs.
 
 The info route belongs to the selected `channels/eve.ts` source and uses its resolved auth policy. Without an authored replacement, eve selects the default channel source with Vercel OIDC, local development access, and the production placeholder. Replacing or disabling that source replaces or removes the info route too; no native fallback serves it.
 
@@ -309,7 +309,7 @@ The info route belongs to the selected `channels/eve.ts` source and uses its res
 curl http://127.0.0.1:2000/eve/v1/info
 ```
 
-With the default auth chain (`[vercelOidc(), localDev(), placeholderAuth()]`), a Vercel OIDC bearer takes precedence, an `eve dev` or `vercel dev` server authenticates local requests, and everything else is rejected. A deployed Vercel target requires a valid OIDC bearer, with a same-project bypass for in-deployment callers. See [auth & route protection](../guides/auth-and-route-protection).
+With the default auth chain (`[vercelOidc(), localDev(), placeholderAuth()]`), a Vercel OIDC bearer takes precedence, `localDev()` accepts requests to an `eve dev` or `vercel dev` server, and everything else is rejected. A deployed Vercel target requires a valid OIDC bearer, with a same-project bypass for in-deployment callers. See [auth & route protection](../guides/auth-and-route-protection).
 
 ## Dispatch order
 

package/docs/dynamic-configuration/meta.json

@@ -0,0 +1,5 @@
+{
+  "title": "Dynamic Capabilities",
+  "defaultOpen": false,
+  "pages": ["../guides/dynamic-capabilities", "../guides/evaluate"]
+}

package/docs/evals/overview.mdx

@@ -58,6 +58,49 @@ export default defineEvalConfig({
 
 Everything is optional. `judge` sets the default model for [LLM-as-judge](./judge) assertions (`t.judge(...)`); omit it to use the default evaluator, `typesafe-ai/jev`. Deterministic evals make no judge requests. `reporters`, `maxConcurrency`, and `timeoutMs` round out the defaults. Config `reporters` observe every eval in the run, so set one `Braintrust()` here instead of adding it to each eval. CLI flags (`--max-concurrency`, `--timeout`) and per-eval values take precedence over the config defaults.
 
+### Run setup and teardown
+
+Use `setup` to start shared resources or run migrations before eve starts the local agent server. Return shared context directly from `setup`, then release resources in `teardown`:
+
+```ts title="evals/evals.config.ts"
+import { defineEvalConfig } from "eve/evals";
+import { startTestDatabase } from "./database.js";
+
+export default defineEvalConfig({
+  async setup() {
+    const database = await startTestDatabase();
+    return { database };
+  },
+  async teardown(context) {
+    await context?.database.close();
+  },
+});
+```
+
+`context` is inferred from the setup return value. To use that type in an eval file, pass the config's type to `defineEval`:
+
+```ts title="evals/database.eval.ts"
+import { defineEval } from "eve/evals";
+import { equals } from "eve/evals/expect";
+import type config from "./evals.config.js";
+
+export default defineEval<typeof config>({
+  async test(t) {
+    const result = await t.context.database.query("SELECT 1 AS value");
+    await t.require(result.rows[0]?.value, equals(1));
+  },
+});
+```
+
+Setup, eval bodies, and teardown share the same context object in the runner process. Class instances and functions keep their identity; context is neither serialized nor sent to the agent server. Concurrent evals share these resources, so isolate any database records they modify.
+
+`setup` can also return nothing.
+
+- Setup runs once per `eve eval` invocation, after discovery and config loading, before target startup.
+- Teardown runs after the local server and its sandbox handles shut down, including after setup, startup, or eval failures. Cleanup failures fail the command.
+
+`teardown` receives `undefined` when setup returns no context or throws before returning. In that case, setup must clean up resources that only it can access. Teardown can also be used without setup. The per-eval `timeoutMs` does not apply to setup or teardown.
+
 ## Deterministic fixture models
 
 Use `mockModel` when an eval fixture needs to exercise eve's runtime without calling a model provider. A static fixture can be one line:

package/docs/getting-started.mdx

@@ -50,7 +50,7 @@ npx eve@latest init my-agent --model openai/gpt-5.6-terra --reasoning high
 
 ## Run the agent
 
-The terminal UI opens after interactive initialization. To return later, enter the project and run:
+The [terminal UI](/docs/guides/dev-tui) opens after interactive initialization. To return later, enter the project and run:
 
 ```bash
 cd my-agent

package/docs/guides/client/overview.mdx

@@ -34,7 +34,7 @@ The client requires the successful response to match `{ ok: true, status: "ready
 
 ## Inspect an agent
 
-Use `info()` to inspect an agent. The client requires the complete agent-info version 4 response before returning it:
+Use `info()` to inspect an agent. The client requires the complete agent-info version 6 response before returning it:
 
 ```ts
 const info = await client.info();

package/docs/guides/deployment/overview.md

@@ -3,7 +3,7 @@ title: "Overview"
 description: "Choose a deployment strategy and prepare an eve agent for production."
 ---
 
-Deploy eve to Vercel or run it as a Node service on your own infrastructure. Your deployment strategy determines the build output, workflow storage, sandbox backend, and routing. The agent’s filesystem-based configuration remains portable across these strategies.
+Deploy eve to Vercel or run it as a Node service on your own infrastructure. Your deployment strategy determines the build output, workflow storage, sandbox provider, and routing. The agent’s filesystem-based configuration remains portable across these strategies.
 
 ## Choose a deployment strategy
 

package/docs/guides/deployment/self-hosting.md

@@ -1,6 +1,6 @@
 ---
 title: "Self-Host eve"
-description: "Run an eve agent as a Node service with your own workflow storage, sandbox backend, and routing."
+description: "Run an eve agent as a Node service with your own workflow storage, sandbox provider, and routing."
 ---
 
 Self-host eve when you operate a Node service, container platform, or reverse proxy. You run eve’s Nitro server and choose the infrastructure that stores workflows and executes sandbox sessions.
@@ -46,11 +46,11 @@ The package must export a default factory or `createWorld()` function. Read cred
 
 See [Workflow Worlds](https://workflow-sdk.dev/worlds) for the underlying Workflow software development kit (SDK) abstraction.
 
-## Select a sandbox backend
+## Select a sandbox provider
 
-`defaultBackend()` selects a local sandbox backend in availability order. You can instead select Docker, microsandbox, or a custom `SandboxBackend` adapter for your container, virtual machine, or isolation service.
+The default sandbox environment selects Docker, microsandbox, or just-bash according to local availability. You can select one explicitly or implement a custom provider with `defineSandboxProvider()` for your container, virtual machine, or isolation service.
 
-Don’t select `vercel()` unless the self-hosted process should create hosted Vercel sandboxes. See [Sandbox](../../sandbox) for backend configuration and selection order.
+Don’t select `VercelSandbox.environment()` unless the self-hosted process should create hosted Vercel sandboxes. See [Sandbox](../../sandbox) for provider configuration and selection order.
 
 ## Configure proxy routes
 
@@ -125,4 +125,4 @@ Use these guides to secure and observe the deployed agent:
 
 - [Authentication](../auth-and-route-protection): configure the host’s route policy
 - [Instrumentation](../../observability/instrumentation): export traces and diagnose runtime failures
-- [Sandbox](../../sandbox): select and secure a sandbox backend
+- [Sandbox](../../sandbox): select and secure a sandbox provider

package/docs/guides/deployment/vercel.mdx

@@ -27,26 +27,24 @@ A string model ID routes requests through the [Vercel AI Gateway](https://vercel
 
 Add credentials for direct model providers, tools, and connections to the Vercel project environment. Add any signing keys or passwords required by your [route authentication policy](../auth-and-route-protection). Replace `placeholderAuth()` before a browser sends a production request.
 
-## Select the sandbox backend
+## Select the sandbox environment
 
-Leave the sandbox `backend` unset to use `defaultBackend()`. On Vercel, it selects Vercel Sandbox. You can also select the backend explicitly:
+The default environment selects Vercel Sandbox on Vercel. To select it explicitly:
 
 ```typescript
 import { defineSandbox } from "eve/sandbox";
-import { vercel } from "eve/sandbox/vercel";
+import { VercelSandbox } from "eve/sandbox/vercel";
 
-export default defineSandbox({
-  backend: vercel(),
-});
+export const environment = VercelSandbox.environment();
+export default defineSandbox(() => environment.open());
 ```
 
-See [Sandbox](../../sandbox) for resource limits, network policy, and lifecycle hooks.
+See [Sandbox](../../sandbox) for preparation, resource limits, network policy, and lifecycle.
 
 <Callout type="info" title="Sandbox prewarming">
-  During a Vercel build, eve automatically creates or reuses a sandbox template when your sandbox
-  has `bootstrap()` or seed files. The build needs permission to create Vercel Sandbox templates,
-  and a prewarm failure stops the deployment. See the [sandbox lifecycle](../../sandbox#lifecycle)
-  for template and session setup.
+  During a Vercel build, eve creates or reuses a snapshot-backed template when an environment uses
+  `VercelSandbox.environment({prepare})` or has seed files. A prewarm failure stops the deployment.
+  See the [sandbox lifecycle](../../sandbox#lifecycle).
 </Callout>
 
 ## Deploy the agent
@@ -137,7 +135,7 @@ Vercel uses the generated output to configure these services:
 - **Web runtime**: serves health, session, stream, channel, callback, and schedule routes
 - **Vercel Workflow**: persists and resumes durable runs, with optimistic replay preconditions enabled so stale event-log snapshots reload before they can commit
 - **Vercel Cron**: invokes authored schedules
-- **Vercel Sandbox**: runs sandbox sessions selected by `defaultBackend()`
+- **Vercel Sandbox**: runs sandbox sessions selected by the default sandbox environment
 
 ## Verify the deployment
 
@@ -157,12 +155,6 @@ eve dev https://your_agent.vercel.app/eve/support
 
 Set `VERCEL_AUTOMATION_BYPASS_SECRET` locally before connecting if the deployment uses Deployment Protection.
 
-## Inspect agent runs
-
-Vercel detects eve and can add an **Agent Runs** tab under the project’s **Observability** view. Use it to browse sessions and inspect each conversation trace.
-
-The Agent Runs tab requires enablement for your Vercel team. Contact your Vercel representative if the tab doesn’t appear. For third-party tracing backends, configure [OpenTelemetry instrumentation](../../observability/instrumentation).
-
 ## Continue configuring production
 
 Use these guides to secure and observe the deployed agent:

package/docs/guides/dev-tui.md

@@ -71,7 +71,7 @@ Changes apply together after the final choice, then the picker returns to chat.
 
 A successful login or model change takes effect on the next prompt.
 
-OpenAI, ChatGPT, and Gateway connections default to `gpt-5.6-luna-fast`; Anthropic defaults to `claude-sonnet-5`. An explicitly authored compatible model stays selected. If a new default is unavailable, eve offers the connection's available models. Dynamic or custom model expressions must be edited in `agent.ts`.
+Gateway connections default to `spacexai/grok-4.7`; OpenAI and ChatGPT default to `gpt-5.6-luna-fast`; Anthropic defaults to `claude-sonnet-5`. An explicitly authored compatible model stays selected. If a new default is unavailable, eve offers the connection's available models. Dynamic or custom model expressions must be edited in `agent.ts`.
 
 ## Add an integration
 

package/docs/guides/hooks.md

@@ -86,6 +86,10 @@ handle can also automatically resume on later I/O. A hook failure, including a
 failed stop, follows the normal
 [hook failure behavior](#what-happens-when-a-hook-throws).
 
+For `subagent.called` and `subagent.completed`, `ctx.session.id` identifies the
+parent session. Typed handlers and `*` handlers receive this context even when
+the subagent event arrives between parent turns.
+
 ### Narrowing tool results
 
 `toolResultFrom` narrows an `action.result` event to a specific authored tool or MCP connection and returns typed output. Import it from `eve/tools`:

package/docs/guides/instrumentation/instrumentation.mdx

@@ -159,6 +159,6 @@ not depend on execution order. Use `flush` to drain buffered records and
 ## What to read next
 
 - [Migrate instrumentation](/docs/observability/instrumentation-migration): replace `agent/instrumentation.ts`.
-- [OpenTelemetry](/docs/observability/otel): configure OTel destinations and managed exports.
+- [OpenTelemetry](/docs/observability/otel): configure OTel destinations and third-party exports.
 - [Local development](../guides/dev-tui): inspect local traces in the TUI
 - [Hooks](../guides/hooks): react to runtime events outside the instrumentation lifecycle

package/docs/guides/instrumentation/migration.md

@@ -89,9 +89,4 @@ see
 Run `eve build`. A remaining `agent/instrumentation.ts` fails the build with a
 message directing you to the instrumentation directory.
 
-Before verifying a Vercel deployment, configure trace sampling. A deployed eve
-project needs at least one sampling rule with a rate above 0%; we recommend
-setting the rate to 100%. See
-[Enable tracing on Vercel](/docs/observability/otel#enable-tracing-on-vercel).
-
-Then run the agent and verify each destination independently.
+Run the agent and verify each destination independently.

package/docs/guides/instrumentation/otel.mdx

@@ -1,13 +1,11 @@
 ---
 title: "OpenTelemetry"
-description: "Configure OpenTelemetry destinations, content capture, and managed exports."
+description: "Configure OpenTelemetry destinations, content capture, and third-party exports."
 url: "/observability/otel"
 ---
 
-eve configures its built-in OpenTelemetry destinations automatically.
-`eve dev` records local traces, and preview and production deployments export
-to Vercel Agent Runs by default. You do not need `otel()` or
-`otelIntegration()` to use these defaults.
+`eve dev` records local traces automatically. You do not need `otel()` or
+`localTraces()` to use this default.
 
 ## Configure OpenTelemetry
 
@@ -118,11 +116,7 @@ lineage and trace-content policy. See [Remote agents](../guides/remote-agents#pr
 Use `gen_ai.conversation.id` to find the traces for one conversation in your
 destination's span-search surface.
 
-## Manage built-in destinations
-
-Instrumentation has two environment-specific defaults.
-
-### Local traces
+## Local traces
 
 `eve dev` records local traces by default. Omitting
 `agent/instrumentation/local.ts` preserves that default. Export
@@ -134,42 +128,16 @@ import { disableInstrumentation } from "eve/instrumentation";
 export default disableInstrumentation();
 ```
 
-### Vercel Agent Runs
-
-Preview and production deployments export to Vercel Agent Runs by default.
-Omitting `agent/instrumentation/agent-runs.ts` preserves that default. Export
-`agentRuns(...)` from that file to reconfigure it, or export
-`disableInstrumentation()` to disable it.
-
-## Enable tracing on Vercel
-
-A deployed eve project needs at least one
-[sampling rule with a rate above 0%](https://vercel.com/docs/tracing/always-on-tracing#enable-always-on-tracing)
-before Vercel collects traces. We recommend setting the rate to **100%** for
-eve projects so every matching request is traced.
-
-Select your team and project, then open
-[**Settings → Tracing**](https://vercel.com/d?to=%2F%5Bteam%5D%2F%5Bproject%5D%2Fsettings%2Ftracing&title=Go+to+Tracing+settings):
-
-1. Select **Add Sampling Rule**.
-2. Choose **All Environments**, **Production**, or **Preview**.
-3. Set **Rate** to `100%`.
-4. Select **Save**.
-
-Tracing starts as soon as you save the rule. You can also manage sampling
-rules with [`vercel traces config`](https://vercel.com/docs/cli/traces#manage-trace-sampling-rules).
-The CLI accepts rates from 1 to 100%; add a 0% rule from the dashboard.
-
 ## Filter a destination
 
-`otelIntegration()`, `localTraces()`, and `agentRuns()` accept one
+`otelIntegration()` and `localTraces()` accept one
 `exportPolicy` object or an array applied in order. Each policy filters spans
 and attributes before that destination's processors receive them:
 
-```ts title="agent/instrumentation/agent-runs.ts"
-import { agentRuns } from "eve/instrumentation/otel";
+```ts title="agent/instrumentation/local.ts"
+import { localTraces } from "eve/instrumentation/otel";
 
-export default agentRuns({
+export default localTraces({
   exportPolicy: {
     span: ({ name }) => ({ emit: name !== "internal.cache.refresh" }),
     attribute: ({ key }) => (key === "customer.id" ? { emit: false } : { emit: true }),
@@ -188,17 +156,17 @@ A throwing `span` callback drops the span from this destination. Return
 `{ replace: true, value }` from `attribute` to retain, remove, or change
 one attribute.
 
-### Further narrow a built-in destination
+### Redact content from local traces
 
-Return a redaction decision to further narrow what a built-in destination
+Return a redaction decision to further narrow what the local trace destination
 receives after the process-wide `otel({ tracePolicy })` has admitted a trace.
-For example, keep the spans in Agent Runs while redacting their inputs and
-outputs unless the session is public:
+For example, keep spans in the local trace viewer while redacting their inputs
+and outputs unless the session is public:
 
-```ts title="agent/instrumentation/agent-runs.ts"
-import { agentRuns } from "eve/instrumentation/otel";
+```ts title="agent/instrumentation/local.ts"
+import { localTraces } from "eve/instrumentation/otel";
 
-export default agentRuns({
+export default localTraces({
   exportPolicy: {
     span: ({ audience }) =>
       audience === "public" ? { emit: true } : { redact: true, inputs: true, outputs: true },

package/docs/memory/meta.json

@@ -1,5 +1,5 @@
 {
   "title": "Memory",
   "defaultOpen": false,
-  "pages": ["overview", "file", "custom-provider"]
+  "pages": ["overview", "file", "../patterns/multi-tenant-memory", "custom-provider"]
 }

package/docs/memory/overview.mdx

@@ -28,6 +28,10 @@ caller using the built-in file provider. Swap `provider` for
 [Supermemory](#supermemory), [Upstash AgentKit](#upstash-agentkit), or your own
 implementation and the rest of the definition stays the same.
 
+For an application with multiple tenants, follow the
+[Multi-tenant memory](/docs/patterns/multi-tenant-memory) guide to scope memory
+by authenticated tenant and caller.
+
 ## How a memory slot works
 
 A memory slot is the unit eve manages. Each slot binds one provider to an