vault backup: 2026-04-17 13:06:56
This commit is contained in:
Vadym Samoilenko
parent
ca246dc5a7
commit
bd1f19619b
6 changed files with 137 additions and 2 deletions
|
|
@ -242,3 +242,9 @@ tags: [daily]
|
|||
- 13:04 (<1min) | `memory-compiler`
|
||||
- **Asked:** Asked for WezTerm plugins article to be compiled into the knowledge base wiki structure.
|
||||
- **Done:** Created structured wiki article on WezTerm plugin installation, updates, removal, and local development workflows.
|
||||
- 13:06 (<1min) | `memory-compiler`
|
||||
- **Asked:** Compile a raw wiki article about Claude Code channels into the knowledge base structure.
|
||||
- **Done:** Created `wiki/claude-code/channels.md` with channel features, platforms, security model, and enterprise controls; updated both index files.
|
||||
- 13:06 (<1min) | `memory-compiler`
|
||||
- **Asked:** Compile a new raw article into the knowledge base as a structured wiki article.
|
||||
- **Done:** Created quickstart.md article documenting query() entry point, message streams, permissions, and customization with 6 wikilinks.
|
||||
|
|
|
|||
|
|
@ -30,9 +30,9 @@ This 3-hop pattern works for hundreds of articles without vector search.
|
|||
| [[wiki/web-agency/_index\|web-agency/]] | AI-assisted website building & selling: Claude Code, Nanobanana 2, Kling, LaunchPath MCP | 1 |
|
||||
| [[wiki/dotfiles/_index\|dotfiles/]] | Linux terminal ricing: Kitty, Fish, WezTerm CLI, modern Rust CLI tools, LazyVim, unified themes, Tabby | 18 |
|
||||
|
||||
| [[wiki/agent-sdk/_index\|agent-sdk/]] | Claude Agent SDK (formerly Claude Code SDK) — build autonomous AI agents in Python and TypeScript | 17 |
|
||||
| [[wiki/agent-sdk/_index\|agent-sdk/]] | Claude Agent SDK (formerly Claude Code SDK) — build autonomous AI agents in Python and TypeScript | 18 |
|
||||
| [[wiki/llm-models/_index\|llm-models/]] | OpenAI model catalog — GPT-5.x, o-series reasoning, audio/realtime, embeddings, moderation | 1 |
|
||||
| [[wiki/claude-code/_index\|claude-code/]] | Claude Code product docs — install, capabilities, surfaces, MCP, hooks, scheduling, multi-agent, plugins, skills, error recovery | 8 |
|
||||
| [[wiki/claude-code/_index\|claude-code/]] | Claude Code product docs — install, capabilities, surfaces, MCP, hooks, scheduling, multi-agent, plugins, skills, channels, error recovery | 9 |
|
||||
|
||||
<!-- New topic folders added here automatically as they are created -->
|
||||
<!-- Format: | [[wiki/topic/_index\|topic/]] | One-line description | N articles | -->
|
||||
|
|
|
|||
|
|
@ -31,3 +31,4 @@ Build production AI agents using the same tools, agent loop, and context managem
|
|||
| [[wiki/agent-sdk/migration-guide\|migration-guide]] | Migrate from claude-code-sdk to claude-agent-sdk: package rename, import updates, v0.1.0 breaking changes (system prompt, settingSources) | raw/Migrate to Claude Agent SDK.md | 2026-04-17 |
|
||||
| [[wiki/agent-sdk/modifying-system-prompts\|modifying-system-prompts]] | Four methods to customize system prompts: CLAUDE.md, output styles, append preset, custom string; prompt caching with excludeDynamicSections | raw/Modifying system prompts.md, raw/Modifying system prompts 1.md | 2026-04-17 |
|
||||
| [[wiki/agent-sdk/observability-opentelemetry\|observability-opentelemetry]] | Export traces, metrics, log events via OTEL to any OTLP backend; span names, sensitive data controls, flush config | raw/Observability with OpenTelemetry.md | 2026-04-17 |
|
||||
| [[wiki/agent-sdk/quickstart\|quickstart]] | Minimal working agent: query(), allowed_tools, permission modes, message stream types, troubleshooting | raw/Quickstart.md | 2026-04-17 |
|
||||
|
|
|
|||
128
wiki/agent-sdk/quickstart.md
Normal file
128
wiki/agent-sdk/quickstart.md
Normal file
|
|
@ -0,0 +1,128 @@
|
|||
---
|
||||
title: "Agent SDK Quickstart"
|
||||
aliases: [agent-sdk-quickstart, sdk-quickstart, getting-started-agent-sdk]
|
||||
tags: [agent-sdk, quickstart, python, typescript, anthropic, claude]
|
||||
sources: [raw/Quickstart.md]
|
||||
created: 2026-04-17
|
||||
updated: 2026-04-17
|
||||
---
|
||||
|
||||
# Agent SDK Quickstart
|
||||
|
||||
Build an AI agent that autonomously reads, analyzes, and fixes code — no manual intervention.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- **Python 3.10+** or **Node.js 18+**
|
||||
- Anthropic account with `ANTHROPIC_API_KEY` set
|
||||
|
||||
## Minimal Agent (Python)
|
||||
|
||||
```python
|
||||
import asyncio
|
||||
from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, ResultMessage
|
||||
|
||||
async def main():
|
||||
async for message in query(
|
||||
prompt="Review utils.py for bugs that would cause crashes. Fix any issues you find.",
|
||||
options=ClaudeAgentOptions(
|
||||
allowed_tools=["Read", "Edit", "Glob"],
|
||||
permission_mode="acceptEdits",
|
||||
),
|
||||
):
|
||||
if isinstance(message, AssistantMessage):
|
||||
for block in message.content:
|
||||
if hasattr(block, "text"):
|
||||
print(block.text)
|
||||
elif hasattr(block, "name"):
|
||||
print(f"Tool: {block.name}")
|
||||
elif isinstance(message, ResultMessage):
|
||||
print(f"Done: {message.subtype}")
|
||||
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
## Three Core Parts
|
||||
|
||||
| Part | What it does |
|
||||
|------|-------------|
|
||||
| `query()` | Main entry point — creates the agentic loop, returns an async iterator |
|
||||
| `prompt` | Natural language task — Claude decides which tools to call |
|
||||
| `options` | Config: `allowed_tools`, `permission_mode`, `system_prompt`, `mcpServers` |
|
||||
|
||||
## Tools Reference
|
||||
|
||||
| Tools | Agent capability |
|
||||
|-------|----------------|
|
||||
| `Read`, `Glob`, `Grep` | Read-only analysis |
|
||||
| `Read`, `Edit`, `Glob` | Analyze and modify code |
|
||||
| `Read`, `Edit`, `Bash`, `Glob`, `Grep` | Full automation |
|
||||
| + `WebSearch` | Add web search capability |
|
||||
|
||||
## Permission Modes
|
||||
|
||||
| Mode | Behavior | Use case |
|
||||
|------|----------|----------|
|
||||
| `acceptEdits` | Auto-approves file edits + common FS commands | Trusted dev workflows |
|
||||
| `dontAsk` | Denies anything not in `allowedTools` | Locked-down headless agents |
|
||||
| `auto` *(TS only)* | Model classifier approves/denies each tool call | Autonomous with guardrails |
|
||||
| `bypassPermissions` | No prompts at all | Sandboxed CI |
|
||||
| `default` | Requires `canUseTool` callback | Custom approval flows |
|
||||
|
||||
## Customization Examples
|
||||
|
||||
**Custom system prompt:**
|
||||
```python
|
||||
options = ClaudeAgentOptions(
|
||||
allowed_tools=["Read", "Edit", "Glob"],
|
||||
permission_mode="acceptEdits",
|
||||
system_prompt="You are a senior Python developer. Always follow PEP 8.",
|
||||
)
|
||||
```
|
||||
|
||||
**Add Bash for full automation:**
|
||||
```python
|
||||
options = ClaudeAgentOptions(
|
||||
allowed_tools=["Read", "Edit", "Glob", "Bash"],
|
||||
permission_mode="acceptEdits",
|
||||
)
|
||||
# Prompt: "Write unit tests for utils.py, run them, and fix any failures"
|
||||
```
|
||||
|
||||
## Message Stream Types
|
||||
|
||||
The `async for` loop yields four message types:
|
||||
1. **AssistantMessage** — Claude's reasoning text + tool calls
|
||||
2. **Tool result** — output from each tool execution
|
||||
3. **ResultMessage** — final outcome (`subtype` = success/error/etc.)
|
||||
4. System/internal state (filter out for clean output)
|
||||
|
||||
See [[wiki/agent-sdk/agent-loop|agent-loop]] for the full message lifecycle.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
| Error | Fix |
|
||||
|-------|-----|
|
||||
| `API key not found` | Set `ANTHROPIC_API_KEY` env var |
|
||||
| `thinking.type.enabled not supported` | Upgrade to Agent SDK v0.2.111+ (Opus 4.7 changed to `thinking.type.adaptive`) |
|
||||
|
||||
## Key Takeaways
|
||||
|
||||
- `query()` is the single entry point — it drives the full agentic loop with `async for`
|
||||
- `allowed_tools` pre-approves tools; `permission_mode="acceptEdits"` removes interactive prompts
|
||||
- The loop ends when Claude finishes the task or hits an error — SDK handles orchestration
|
||||
- Streaming (async for) is for real-time output; collect all messages for background/CI jobs
|
||||
- `system_prompt` and `mcpServers` in `ClaudeAgentOptions` are the main extension points
|
||||
|
||||
## Next Steps
|
||||
|
||||
- [[wiki/agent-sdk/configure-permissions|configure-permissions]] — full permission modes + allow/deny rules
|
||||
- [[wiki/agent-sdk/sdk-hooks|sdk-hooks]] — intercept tool calls with PreToolUse/PostToolUse
|
||||
- [[wiki/agent-sdk/mcp-integration|mcp-integration]] — connect to databases, browsers, external APIs
|
||||
- [[wiki/agent-sdk/hosting-production|hosting-production]] — deploy to Docker, cloud, CI/CD
|
||||
- [[wiki/agent-sdk/user-input-approvals|user-input-approvals]] — `canUseTool` callback for custom approval flows
|
||||
- [[wiki/agent-sdk/agent-loop|agent-loop]] — understand message lifecycle and context management
|
||||
|
||||
---
|
||||
|
||||
*Source: raw/Quickstart.md*
|
||||
Loading…
Add table
Reference in a new issue