docs: revert SystemPromptConfig docs [langchain-ai/deepagents#4969]

pipeline/preprocessors/link_map.py

@@ -35,7 +35,6 @@ class LinkMap(TypedDict):
             # Deep Agents
             "create_deep_agent": "deepagents/graph/create_deep_agent",
             "DeepAgentState": "deepagents/graph/DeepAgentState",
-            "SystemPromptConfig": "deepagents/graph/SystemPromptConfig",
             "SubAgent": "deepagents/middleware/subagents/SubAgent",
             "CompiledSubAgent": "deepagents/middleware/subagents/CompiledSubAgent",
             "SubAgentMiddleware": "deepagents/middleware/subagents/SubAgentMiddleware",

src/oss/deepagents/customization.mdx

@@ -177,7 +177,7 @@ For detailed configuration options including stdio servers, OAuth authentication
 
 ## System prompt
 
-Deep Agents ship with a built-in base system prompt that teaches the agent how to use the harness scaffolding (planning, filesystem tools, subagents). Pass `system_prompt=` to prepend your own instructions before that base prompt:
+Pass `system_prompt=` to give the agent your own instructions:
 
 :::python
 <CustomizationSystemPromptPy />
@@ -188,37 +188,9 @@ Deep Agents ship with a built-in base system prompt that teaches the agent how t
 :::
 
 <Note>
-Besides a string, the main agent also accepts a @[`SystemMessage`] with structured [content blocks](/oss/langchain/messages#standard-content-blocks); Deep Agents preserve those blocks and append the built-in base prompt ([subagent](/oss/deepagents/subagents) dictionary specs remain strings).
+Besides a string, the main agent also accepts a @[`SystemMessage`] with structured [content blocks](/oss/langchain/messages#standard-content-blocks); Deep Agents preserve those blocks ([subagent](/oss/deepagents/subagents) dictionary specs remain strings).
 </Note>
 
-When middleware adds special tools, like the filesystem tools, it appends its own guidance to the system prompt at runtime.
-
-:::python
-<Note>
-`SystemPromptConfig` requires `deepagents>=0.7.0a6`.
-</Note>
-
-For full control over prompt assembly, pass a @[`SystemPromptConfig`] dict with `prefix`, `base`, and `suffix` keys:
-
-- **`prefix`**: text placed before the base prompt (same as passing a bare string).
-- **`base`**: replaces the built-in base prompt. Omit the key to keep the built-in base, or set it to `None` to drop the base entirely.
-- **`suffix`**: text placed after the base prompt.
-
-Parts are assembled in order: `prefix` -> `base` -> `suffix` -> any model-specific [profile](/oss/deepagents/profiles) suffix. Each part accepts a `str` or a `SystemMessage` (to preserve `cache_control` markers for Anthropic prompt caching).
-
-```python
-# Overwrite the default base prompt:
-create_deep_agent(..., system_prompt={"base": "..."})
-
-# No system prompt except from middleware:
-create_deep_agent(..., system_prompt={"base": None})
-
-# Sandwich the default base prompt:
-create_deep_agent(..., system_prompt={"prefix": "...", "suffix": "..."})
-```
-
-For model-specific system prompt customization, such as replacing the base prompt or appending a suffix for a particular provider, use a [harness profile](/oss/deepagents/profiles#harness-profiles).
-:::
 
 <AccordionGroup>
     <Accordion title="Subagent prompts">

src/snippets/create-deep-agent-config-options-js.mdx

@@ -15,7 +15,7 @@ const agent = createDeepAgent({
   store?: BaseStore,
   streamTransformers?: TStreamTransformers,
   subagents?: TSubagents,
-  systemPrompt?: string | SystemMessage<MessageStructure<MessageToolSet>> | SystemPromptConfig,
+  systemPrompt?: string | SystemMessage<MessageStructure<MessageToolSet>>,
   tools?: TTools | StructuredTool<ToolInputSchemaBase, any, any, any, unknown>[]
 });
 ```