anthropics / anthropics/claude-agent-sdk-python

[FEATURE] Prompt Caching Support in Claude Agent SDK

Open
#626 4 comments 17 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
8.1k
Forks
1.3k
Avg merge
2d 31m
Merged PRs (30d)
1

Description

# [Feature Request] Support Bedrock Prompt Caching in Claude Agent SDK

## Description
I am currently using the **Claude Agent SDK** with **Amazon Bedrock** as the model provider. I am unable to enable **Prompt Caching** via the SDK because the current `ClaudeAgentOptions` (and the underlying Bedrock provider) do not support the injection of cache control metadata into the message payload.

To leverage Bedrock's prompt caching, the payload must allow for `cache_control` or `cachePoint` blocks within the messages or system prompts.

## Proposed Change
Update the `ClaudeAgentOptions` and the Bedrock model provider logic to support the following structures in the request payload:

**For Ephemeral Caching:**
```json
"cache_control": {
"type": "ephemeral"
}
```
**For Cache Points:**
```json
"cachePoint": {
"type": "default"
}
```
---

## 1. Documentation Links
* **Main Guide**: [Amazon Bedrock Prompt Caching User Guide](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html)
* **API Reference**: [Amazon Bedrock Runtime - InvokeModel](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html)
* **Model Specifics**: [Anthropic Claude Models on Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html)

---

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating ClaudeAgentOptions and the underlying Bedrock provider logic, then compare their request-building path with the linked Bedrock prompt-caching documentation. Done means the SDK can pass cache_control and cachePoint blocks in message or system-prompt payloads for ephemeral caching and cache points, with coverage in the relevant existing tests if available.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws, python
Domain
api, backend, cloud
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.