# Practical ways to use the Claude Agent SDK 📡 Master streaming input mode for image uploads, interrupts, and persistent context. Streaming vs Single-Message Input covers the streaming mode for persistent conversations and single-message mode for stateless environments. 📌 Title: Streaming Input 🔗 URL: 🧩 Overview Streaming input mode (recommended) supports image uploads, message queues, interrupts, and context persistence for rich interactive experiences. Single-message input is ideal for stateless environments like AWS Lambda for one-shot responses. 🛠 How to use it Streaming mode is the default. Single-message mode is explicitly selected for stateless environments like Lambda. 🏗 Practical usage - In a chat UI, upload an architecture diagram after "Analyze this codebase" for visual code review. - Inject external events (CI results, Slack notifications) via message queues to dynamically extend context. - Use single-message mode for serverless functions that run "Explain the auth flow" as a one-shot task. 💡 Use cases 🖼 Code review with image attachments 📨 Dynamic injection of external events ⚡ One-shot task execution in serverless environments ⚠️ Watch out Single-message mode doesn't support image attachments, interrupts, or multi-turn conversations. Use streaming mode when rich interaction is needed. #ClaudeAgentSDK# #AI#

# Practical ways to use the Claude Agent SDK 💬 Continue, resume, and fork agent conversations to tackle complex tasks across multiple turns. Session Management uses `continue`, `resume`, and `fork` to maintain context across multi-turn conversations. 📌 Title: Working with Sessions 🔗 URL: 🧩 Overview Sessions preserve conversation context. Python uses `ClaudeSDKClient` (auto session ID management), TypeScript uses `continue: true`. `resume` restarts interrupted sessions, and `fork_session` branches history to explore alternatives. 🛠 How to use it ```python options = ClaudeAgentOptions(resume=session_id) # Resume options = ClaudeAgentOptions(fork_session=True) # Fork ``` 🏗 Practical usage - Build multi-turn conversations: "Analyze the auth module" → "Refactor it to use JWT" with full context preserved. - Resume sessions that ended with `error_max_turns` using `resume` with higher limits. - Use `fork_session=True` to explore an OAuth2 approach without destroying the original JWT approach. Two independent histories are maintained. - Build session picker UIs with `list_sessions` / `get_session_messages` / `rename_session`. 💡 Use cases 🔄 Resuming sessions after hitting limits 🌿 Parallel exploration of alternative approaches via fork 🗂 Building session management UIs ⚠️ Watch out Sessions are saved at `~/.claude/projects//.jsonl`. Cross-host resume requires matching `cwd`. Sub-agent transcripts persist independently from the main conversation. #ClaudeAgentSDK# #AI#