docs: add version added flags to deep agents documentation

src/oss/deepagents/acp.mdx

@@ -2,6 +2,7 @@
 title: Agent Client Protocol (ACP)
 description: Expose Deep Agents over the Agent Client Protocol (ACP) to integrate with code editors and IDEs.
 ---
+
 [Agent Client Protocol (ACP)](https://agentclientprotocol.com/get-started/introduction) standardizes communication between coding agents and code editors or IDEs.
 With the ACP protocol, you can make use of your custom deep agents with any ACP-compatible client, allowing your code editor to provide project context and receive rich updates.
 

src/oss/deepagents/backends.mdx

@@ -719,6 +719,10 @@ class PolicyWrapper implements BackendProtocolV2 {
 :::js
 ## Multimodal and binary files
 
+<Note>
+Multi-modal file support (PDFs, audio, video) requires `deepagents>=1.9.0`.
+</Note>
+
 V2 backends support binary files natively. When `read()` encounters a binary file (determined by MIME type from the file extension), it returns a `ReadResult` with `Uint8Array` content and the corresponding `mimeType`. Text files return `string` content.
 
 ### Supported MIME types
@@ -774,7 +778,12 @@ Backends may encounter either format when reading from state or store. The frame
 ## Migrate from backend factories
 
 <Warning>
-The backend factory pattern is **deprecated**. Pass pre-constructed backend instances directly instead of factory functions.
+:::python
+The backend factory pattern is **deprecated** as of `deepagents` 0.5.0. Pass pre-constructed backend instances directly instead of factory functions.
+:::
+:::js
+The backend factory pattern is **deprecated** as of `deepagents` 1.9.0. Pass pre-constructed backend instances directly instead of factory functions.
+:::
 </Warning>
 
 Previously, backends like `StateBackend` and `StoreBackend` required a factory function that received a runtime object, because they needed runtime context (state, store) to operate. Backends now resolve this context internally via LangGraph's `get_config()`, `get_store()`, and `get_runtime()` helpers, so you can pass instances directly.

src/oss/deepagents/context-engineering.mdx

@@ -330,6 +330,12 @@ Content offloading happens when tool call inputs or results exceed a token thres
 
 ### Summarization
 
+:::js
+<Note>
+The current summarization behavior (in-model summarization via `wrapModelCall`, accurate token counting, and automatic `ContextOverflowError` fallback) requires `deepagents>=1.6.0`.
+</Note>
+:::
+
 When the context size crosses the model's context window limit (for example 85% of `max_input_tokens`), and there is no more context eligible for offloading, the deep agent summarizes the message history.
 
 This process has two components:
@@ -390,6 +396,12 @@ for await (const [namespace, chunk] of await agent.stream(
 
 ##### Summarization Tool
 
+:::js
+<Note>
+The summarization tool middleware requires `deepagents>=1.6.0`.
+</Note>
+:::
+
 Deep Agents includes an optional [tool](/oss/langchain/tools) for summarization, enabling agents to trigger summarization at opportune times—such as between tasks—instead of at fixed token intervals.
 
 You can enable this tool by appending it to the middleware list:

src/oss/deepagents/sandboxes.mdx

@@ -71,6 +71,10 @@ For provider-specific setup, authentication, and lifecycle details, see [sandbox
 :::
 
 :::js
+<Note>
+Skills require `deepagents>=1.7.0`.
+</Note>
+
 <div className="grid grid-cols-1 md:grid-cols-2 gap-3">
     <a href="/oss/integrations/providers/modal" className="flex items-center justify-center gap-1.5 p-2 rounded-lg border border-gray-200 dark:border-gray-700 hover:border-gray-300 dark:hover:border-gray-600 no-underline">
         <img className="block dark:hidden w-5 h-5" src="/images/providers/light/modal.svg" alt="" />

src/oss/deepagents/skills.mdx

@@ -8,6 +8,12 @@ import SkillsUsageTabsJs from '/snippets/skills-usage-tabs-js.mdx';
 
 Skills are reusable agent capabilities that provide specialized workflows and domain knowledge.
 
+:::js
+<Note>
+Skills require `deepagents>=1.7.0`.
+</Note>
+:::
+
 You can use [Agent Skills](https://agentskills.io/) to provide your deep agent with new capabilities and expertise. For ready-to-use skills that improve your agent's performance on LangChain ecosystem tasks, see the [LangChain Skills](https://github.com/langchain-ai/langchain-skills) repository.
 
 Deep agent skills follow the [Agent Skills specification](https://agentskills.io/specification).

src/oss/deepagents/subagents.mdx

@@ -265,6 +265,10 @@ result = await agent.ainvoke(
 :::
 
 :::js
+<Note>
+Structured output for subagents requires `deepagents` version 1.8.4 or newer.
+</Note>
+
 Pass `responseFormat` on the subagent config. When the subagent finishes, its structured response is JSON-serialized and returned as the `ToolMessage` content to the parent agent. The schema accepts anything supported by `createAgent`: Zod schemas, JSON schema objects, `toolStrategy(...)`, or `providerStrategy(...)`.
 
 ```typescript