Merge branch 'main' into docs-style-improvements-ls

Author: katmayb

packages.yml

@@ -140,6 +140,7 @@ def load_subagents(config_path: Path) -> list:
 def create_content_writer():
     """Create a content writer agent configured by filesystem files."""
     return create_deep_agent(
+        model="openai:gpt-5.4",
         memory=["./AGENTS.md"],
         skills=["./skills/"],
         tools=[generate_cover, generate_social_image],

src/code-samples/deepagents/content-builder.py

@@ -11,6 +11,16 @@ rss: true
 
 [Agent Server](/langsmith/agent-server) is an API platform for creating and managing agent-based applications. It provides built-in persistence, a task queue, and supports deploying, configuring, and running assistants (agentic workflows) at scale. This changelog documents all notable updates, features, and fixes to Agent Server releases.
 
+<Update label="2026-04-10" tags={["agent-server"]}>
+## v0.7.100
+
+- Implemented background deletion of checkpoints to improve thread deletion and pruning performance, reducing I/O pressure and enhancing efficiency.
+- Bumped `@hono/node-server` from 1.19.12 to 1.19.13 to fix a security issue with the Serve Static Middleware.
+- Updated hono from version 4.12.9 to 4.12.12, including critical security patches for middleware and utilities.
+- Upgraded the hono library to version 4.12.12, addressing several security vulnerabilities.
+- Implemented strict version locking for build dependencies to ensure consistency across builds.
+</Update>
+
 <Update label="2026-04-09" tags={["agent-server"]}>
 ## v0.7.99
 

src/code-samples/package-lock.json

@@ -487,6 +487,60 @@ async def main():
             token = await svc.get_token()
 ```
 
+## Trace sandbox activity
+
+Pass LangSmith tracing environment variables through the `env` parameter on `run()` to send traces from code running inside a sandbox. Call `flush()` before the process exits to ensure all traces are delivered.
+
+<CodeGroup>
+
+```python Python
+from langsmith.sandbox import SandboxClient
+
+client = SandboxClient()
+
+tracing_env = {
+    "LANGSMITH_API_KEY": "lsv2_pt_...",
+    "LANGSMITH_ENDPOINT": "https://api.smith.langchain.com",
+    "LANGSMITH_TRACING": "true",
+    "LANGSMITH_PROJECT": "my-sandbox-traces",
+}
+
+with client.sandbox(template_name="my-template") as sandbox:
+    sandbox.run("pip install langsmith", timeout=120, env=tracing_env)
+    result = sandbox.run("python3 my_agent.py", env=tracing_env)
+    print(result.stdout)
+```
+
+```ts TypeScript
+import { SandboxClient } from "langsmith/experimental/sandbox";
+
+const client = new SandboxClient();
+
+const tracingEnv = {
+  LANGSMITH_API_KEY: "lsv2_pt_...",
+  LANGSMITH_ENDPOINT: "https://api.smith.langchain.com",
+  LANGSMITH_TRACING: "true",
+  LANGSMITH_PROJECT: "my-sandbox-traces",
+};
+
+const sandbox = await client.createSandbox("my-template");
+try {
+  await sandbox.run("pip install langsmith", { timeout: 120, env: tracingEnv });
+  const result = await sandbox.run("python3 my_agent.py", { env: tracingEnv });
+  console.log(result.stdout);
+} finally {
+  await sandbox.delete();
+}
+```
+
+</CodeGroup>
+
+Inside the sandbox, any LangSmith-instrumented code (`@traceable`, LangChain, LangGraph) automatically picks up the tracing configuration from the injected environment variables.
+
+<Warning>
+Always call `flush()` before the sandbox process exits — `langsmith.Client().flush()` in Python or `await new Client().flush()` in TypeScript. Without it, traces may be lost because the container is destroyed when the command finishes.
+</Warning>
+
 ## Error handling
 
 Both SDKs provide typed exceptions for specific error handling:

src/langsmith/agent-server-changelog.mdx

@@ -103,6 +103,7 @@ def yearly_balance_schedule(
 
 
 agent = create_deep_agent(
+    model="openai:gpt-5.4",
     tools=[compute_compound_interest, yearly_balance_schedule],
     system_prompt=(
         "You are a careful assistant. "
@@ -238,6 +239,7 @@ def yearly_balance_schedule(
 
 
 agent = create_deep_agent(
+    model="openai:gpt-5.4",
     tools=[compute_compound_interest, yearly_balance_schedule],
     system_prompt=(
         "You are a careful assistant. "

src/langsmith/sandbox-sdk.mdx

@@ -59,6 +59,7 @@ from deepagents_acp.server import AgentServerACP
 
 async def main() -> None:
     agent = create_deep_agent(
+        model="openai:gpt-5.4",
         # You can customize your Deep Agent here: set a custom prompt,
         # add your own tools, attach middleware, or compose subagents.
         system_prompt="You are a helpful coding assistant",

src/langsmith/trace-deep-agents.mdx

@@ -27,6 +27,7 @@ This page explains how to:
 - [choose a backend](#specify-a-backend),
 - [route different paths to different backends](#route-to-different-backends),
 - [implement your own virtual filesystem](#use-a-virtual-filesystem) (e.g., S3 or Postgres),
+- [set permissions](#permissions) on filesystem access,
 :::js
 - [add policy hooks](#add-policy-hooks),
 [work with binary and multimodal files](#multimodal-and-binary-files),
@@ -42,11 +43,11 @@ Here are a few prebuilt filesystem backends that you can quickly use with your d
 
 | Built-in backend | Description |
 |---|---|
-| [Default](#statebackend-ephemeral) | `agent = create_deep_agent()` <br></br> Ephemeral in state. The default filesystem backend for an agent is stored in `langgraph` state. Note that this filesystem only persists _for a single thread_. |
-| [Local filesystem persistence](#filesystembackend-local-disk) | `agent = create_deep_agent(backend=FilesystemBackend(root_dir="/Users/nh/Desktop/"))` <br></br>This gives the deep agent access to your local machine's filesystem. You can specify the root directory that the agent has access to. Note that any provided `root_dir` must be an absolute path. |
-| [Durable store (LangGraph store)](#storebackend-langgraph-store) | `agent = create_deep_agent(backend=StoreBackend())` <br></br>This gives the agent access to long-term storage that is _persisted across threads_. This is great for storing longer term memories or instructions that are applicable to the agent over multiple executions. |
-| [Sandbox](/oss/deepagents/sandboxes) | `agent = create_deep_agent(backend=sandbox)` <br></br>Execute code in isolated environments. Sandboxes provide filesystem tools plus the `execute` tool for running shell commands. Choose from Modal, Daytona, Deno, or local VFS. |
-| [Local shell](#localshellbackend-local-shell) | `agent = create_deep_agent(backend=LocalShellBackend(root_dir=".", env={"PATH": "/usr/bin:/bin"}))` <br></br>Filesystem and shell execution directly on the host. No isolation—use only in controlled development environments. See [security considerations](#localshellbackend-local-shell) below. |
+| [Default](#statebackend-ephemeral) | `agent = create_deep_agent(model="openai:gpt-5.4")` <br></br> Ephemeral in state. The default filesystem backend for an agent is stored in `langgraph` state. Note that this filesystem only persists _for a single thread_. |
+| [Local filesystem persistence](#filesystembackend-local-disk) | `agent = create_deep_agent(model="openai:gpt-5.4", backend=FilesystemBackend(root_dir="/Users/nh/Desktop/"))` <br></br>This gives the deep agent access to your local machine's filesystem. You can specify the root directory that the agent has access to. Note that any provided `root_dir` must be an absolute path. |
+| [Durable store (LangGraph store)](#storebackend-langgraph-store) | `agent = create_deep_agent(model="openai:gpt-5.4", backend=StoreBackend())` <br></br>This gives the agent access to long-term storage that is _persisted across threads_. This is great for storing longer term memories or instructions that are applicable to the agent over multiple executions. |
+| [Sandbox](/oss/deepagents/sandboxes) | `agent = create_deep_agent(model="openai:gpt-5.4", backend=sandbox)` <br></br>Execute code in isolated environments. Sandboxes provide filesystem tools plus the `execute` tool for running shell commands. Choose from Modal, Daytona, Deno, or local VFS. |
+| [Local shell](#localshellbackend-local-shell) | `agent = create_deep_agent(model="openai:gpt-5.4", backend=LocalShellBackend(root_dir=".", env={"PATH": "/usr/bin:/bin"}))` <br></br>Filesystem and shell execution directly on the host. No isolation—use only in controlled development environments. See [security considerations](#localshellbackend-local-shell) below. |
 | [Composite](#compositebackend-router) | Ephemeral by default, `/memories/` persisted. The Composite backend is maximally flexible. You can specify different routes in the filesystem to point towards different backends. See Composite routing below for a ready-to-paste example. |
 
 
@@ -342,7 +343,7 @@ Namespace components must contain only alphanumeric characters, hyphens, undersc
 ## Specify a backend
 
 :::python
-- Pass a backend instance to `create_deep_agent(backend=...)`. The filesystem middleware uses it for all tooling.
+- Pass a backend instance to `create_deep_agent(model=..., backend=...)`. The filesystem middleware uses it for all tooling.
 - The backend must implement `BackendProtocol` (for example, `StateBackend()`, `FilesystemBackend(root_dir=".")`, `StoreBackend()`).
 - If omitted, the default is `StateBackend()`.
 :::
@@ -368,6 +369,7 @@ from deepagents import create_deep_agent
 from deepagents.backends import CompositeBackend, StateBackend, FilesystemBackend
 
 agent = create_deep_agent(
+    model="openai:gpt-5.4",
     backend=CompositeBackend(
         default=StateBackend(),
         routes={
@@ -400,7 +402,7 @@ Behavior:
 
 Notes:
 - Longer prefixes win (for example, route `"/memories/projects/"` can override `"/memories/"`).
-- For StoreBackend routing, ensure a store is provided via `create_deep_agent(store=...)` or provisioned by the platform.
+- For StoreBackend routing, ensure a store is provided via `create_deep_agent(model=..., store=...)` or provisioned by the platform.
 
 ## Use a virtual filesystem
 
@@ -544,9 +546,43 @@ Postgres-style outline:
   - `grep` can fetch candidate rows by extension or last modified time, then scan lines (skip rows where `mime_type` is binary) → return `GrepResult`
 :::
 
+## Permissions
+
+Use [permissions](/oss/deepagents/permissions) to declaratively control which files and directories the agent can read or write. Permissions apply to the built-in filesystem tools and are evaluated before the backend is called.
+
+:::python
+```python
+from deepagents import create_deep_agent, FilesystemPermission
+
+agent = create_deep_agent(
+    model="openai:gpt-5.4",
+    backend=CompositeBackend(
+        default=StateBackend(),
+        routes={
+            "/memories/": StoreBackend(
+                namespace=lambda rt: (rt.server_info.user.identity,),
+            ),
+            "/policies/": StoreBackend(
+                namespace=lambda rt: (rt.context.org_id,),
+            ),
+        },
+    ),
+    permissions=[
+        FilesystemPermission(
+            operations=["write"],
+            paths=["/policies/**"],
+            mode="deny",
+        ),
+    ],
+)
+```
+:::
+
+For the full set of options including rule ordering, subagent permissions, and composite backend interactions, see the [permissions guide](/oss/deepagents/permissions).
+
 ## Add policy hooks
 
-Enforce enterprise rules by subclassing or wrapping a backend.
+For custom validation logic beyond path-based allow/deny rules (rate limiting, audit logging, content inspection), enforce enterprise rules by subclassing or wrapping a backend.
 
 Block writes/edits under selected prefixes (subclass):
 
@@ -792,6 +828,7 @@ from deepagents import create_deep_agent
 from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
 
 agent = create_deep_agent(
+    model="openai:gpt-5.4",
     backend=lambda rt: CompositeBackend(
         default=StateBackend(rt),
         routes={"/memories/": StoreBackend(rt, namespace=lambda rt: (rt.server_info.user.identity,))},
@@ -800,6 +837,7 @@ agent = create_deep_agent(
 
 # After
 agent = create_deep_agent(
+    model="openai:gpt-5.4",
     backend=CompositeBackend(
         default=StateBackend(),
         routes={"/memories/": StoreBackend(namespace=lambda rt: (rt.server_info.user.identity,))},