Skip to content

guanyang/open-agent-hub / skills/claude-api

claude-api

Unverified

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

FileKindSize
LICENSE.txtmarkdown11.1 KB
SKILL.mdskill md102.7 KB
csharp/claude-api.mdmarkdown15.3 KB
csharp/claude-api/README.mdmarkdown18.5 KB
csharp/claude-api/batches.mdmarkdown413 B
csharp/claude-api/files-api.mdmarkdown900 B
csharp/claude-api/streaming.mdmarkdown787 B
csharp/claude-api/tool-use.mdmarkdown7.4 KB
curl/examples.mdmarkdown9.5 KB
curl/managed-agents.mdmarkdown10.5 KB
go/claude-api.mdmarkdown14.4 KB
go/claude-api/README.mdmarkdown8.3 KB
go/claude-api/files-api.mdmarkdown936 B
go/claude-api/streaming.mdmarkdown1.0 KB
go/claude-api/tool-use.mdmarkdown9.8 KB
go/managed-agents/README.mdmarkdown21.9 KB
java/claude-api.mdmarkdown15.5 KB
java/claude-api/README.mdmarkdown11.7 KB
java/claude-api/files-api.mdmarkdown1.2 KB
java/claude-api/streaming.mdmarkdown655 B
java/claude-api/tool-use.mdmarkdown10.9 KB
java/managed-agents/README.mdmarkdown20.0 KB
php/claude-api.mdmarkdown11.5 KB
php/claude-api/README.mdmarkdown6.4 KB
php/claude-api/batches.mdmarkdown447 B
php/claude-api/files-api.mdmarkdown476 B
php/claude-api/streaming.mdmarkdown682 B
php/claude-api/tool-use.mdmarkdown9.5 KB
php/managed-agents/README.mdmarkdown16.2 KB
python/agent-sdk/README.mdmarkdown12.4 KB
python/agent-sdk/patterns.mdmarkdown9.0 KB
python/claude-api/README.mdmarkdown20.1 KB
python/claude-api/batches.mdmarkdown5.6 KB
python/claude-api/files-api.mdmarkdown4.4 KB
python/claude-api/sdk-upgrade.mdmarkdown28.1 KB
python/claude-api/streaming.mdmarkdown11.7 KB
python/claude-api/tool-use.mdmarkdown20.9 KB
python/managed-agents/README.mdmarkdown14.5 KB
ruby/claude-api.mdmarkdown3.4 KB
ruby/claude-api/README.mdmarkdown4.7 KB
ruby/claude-api/streaming.mdmarkdown235 B
ruby/claude-api/tool-use.mdmarkdown2.6 KB
ruby/managed-agents/README.mdmarkdown11.9 KB
shared/admin-api.mdmarkdown11.3 KB
shared/agent-design.mdmarkdown8.5 KB
shared/anthropic-cli.mdmarkdown23.4 KB
shared/claude-platform-on-aws.mdmarkdown4.3 KB
shared/cost-optimization.mdmarkdown57.1 KB
shared/error-codes.mdmarkdown20.3 KB
shared/evals/build-eval.mdmarkdown53.5 KB
shared/evals/cost-hillclimb.mdmarkdown31.0 KB
shared/evals/eval-audit.mdmarkdown27.2 KB
shared/evals/eval-hillclimb.mdmarkdown67.5 KB
shared/evals/report/SCHEMA.mdmarkdown15.7 KB
shared/evals/report/build-report-lite.mjsscript26.7 KB
shared/evals/report/runner-scaffold.mjsscript32.4 KB
shared/live-sources.mdmarkdown17.3 KB
shared/managed-agents-api-reference.mdmarkdown34.5 KB
shared/managed-agents-client-patterns.mdmarkdown11.8 KB
shared/managed-agents-core.mdmarkdown32.7 KB
shared/managed-agents-environments.mdmarkdown13.9 KB
shared/managed-agents-events.mdmarkdown25.4 KB
shared/managed-agents-memory.mdmarkdown11.1 KB
shared/managed-agents-multiagent.mdmarkdown65.1 KB
shared/managed-agents-onboarding-from-quickstart.mdmarkdown19.3 KB
shared/managed-agents-onboarding-from-url.mdmarkdown31.9 KB
shared/managed-agents-onboarding.mdmarkdown16.4 KB
shared/managed-agents-outcomes.mdmarkdown8.8 KB
shared/managed-agents-overview.mdmarkdown14.2 KB
shared/managed-agents-quickstarts/bug-hunter.mdmarkdown7.9 KB
shared/managed-agents-quickstarts/contract-tracker.mdmarkdown1.8 KB
shared/managed-agents-quickstarts/data-analyst.mdmarkdown1.5 KB
shared/managed-agents-quickstarts/deep-researcher.mdmarkdown2.4 KB
shared/managed-agents-quickstarts/explainer-video-maker.mdmarkdown4.8 KB
shared/managed-agents-quickstarts/field-monitor.mdmarkdown2.1 KB
shared/managed-agents-quickstarts/incident-commander.mdmarkdown1.7 KB
shared/managed-agents-quickstarts/performance-tuner.mdmarkdown11.1 KB
shared/managed-agents-quickstarts/sprint-retro-facilitator.mdmarkdown2.0 KB
shared/managed-agents-quickstarts/structured-extractor.mdmarkdown1.5 KB
shared/managed-agents-quickstarts/support-agent.mdmarkdown1.4 KB
shared/managed-agents-quickstarts/support-to-eng-escalator.mdmarkdown1.8 KB
shared/managed-agents-quickstarts/watchlist-scanner.mdmarkdown5.5 KB
shared/managed-agents-scheduled-deployments.mdmarkdown9.3 KB
shared/managed-agents-self-hosted-sandboxes.mdmarkdown27.3 KB
shared/managed-agents-tools.mdmarkdown37.0 KB
shared/managed-agents-webhooks.mdmarkdown11.1 KB
shared/model-migration.mdmarkdown338.1 KB
shared/models.mdmarkdown17.1 KB
shared/platform-availability.mdmarkdown7.2 KB
shared/preserved-thinking-migration.mdmarkdown62.5 KB
shared/preserved-thinking-migration/causes.mdmarkdown38.8 KB
shared/preserved-thinking-migration/drop_block_probe.pyscript65.0 KB
shared/preserved-thinking-migration/prefix_diff.pyscript91.8 KB
shared/prompt-audit.mdmarkdown48.2 KB
shared/prompt-caching.mdmarkdown32.3 KB
shared/token-counting.mdmarkdown1.6 KB
shared/tool-use-concepts.mdmarkdown43.3 KB
typescript/agent-sdk/README.mdmarkdown10.6 KB
typescript/agent-sdk/patterns.mdmarkdown4.6 KB
typescript/claude-api/README.mdmarkdown15.5 KB
typescript/claude-api/batches.mdmarkdown2.5 KB
typescript/claude-api/files-api.mdmarkdown2.3 KB
typescript/claude-api/streaming.mdmarkdown9.3 KB
typescript/claude-api/tool-use.mdmarkdown23.7 KB
typescript/managed-agents/README.mdmarkdown13.7 KB

python/claude-api/streaming.md

View on GitHub
# Streaming - Python

## Quick Start

```python
with client.messages.stream(
    model="claude-opus-5-5",
    max_tokens=64000,
    messages=[{"role": "user", "content": "Write a story"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)
```

### Async

```python
async with async_client.messages.stream(
    model="claude-opus-5-5",
    max_tokens=64000,
    messages=[{"role": "user", "content": "Write a story"}]
) as stream:
    async for text in stream.text_stream:
        print(text, end="", flush=True)
```

### Low-level: `stream=True`

`messages.stream()` (above) is the recommended helper - it accumulates state and exposes `text_stream` / `get_final_message()`. If you only need the raw event iterator and want lower memory use, pass `stream=True` to `messages.create()` instead:

```python
for event in client.messages.create(
    model="claude-opus-5-5",
    max_tokens=64000,
    messages=[{"role": "user", "content": "Write a story"}],
    stream=True,
):
    print(event.type)
```

No final-message accumulation is done for you in this form.

---

## Handling Different Content Types

Claude may return text, thinking blocks, or tool use. Handle each appropriately:

> **Fable 5 / Claude Opus 5.5 / Claude Opus 5 / Opus 4.8 / Opus 4.7 / Opus 4.6:** Use `thinking: {type: "adaptive"}`. On Claude Opus 5.5 and Claude Opus 5 adaptive is also what you get by omitting `thinking` entirely (Claude Opus 5.5 accepts no other setting - `disabled` and `budget_tokens` both 400). On older models, use `thinking: {type: "enabled", budget_tokens: N}` instead.

```python
with client.messages.stream(
    model="claude-opus-5-5",
    max_tokens=64000,
    thinking={"type": "adaptive", "display": "summarized"},  # display opt-in: default is omitted (empty thinking text) on Fable 5/5.1, Mythos 5/5.1, Claude Opus 5.5, Claude Opus 5, Opus 4.8/4.7, Claude Sonnet 5.5, and Claude Sonnet 5
    messages=[{"role": "user", "content": "Analyze this problem"}]
) as stream:
    for event in stream:
        if event.type == "content_block_start":
            if event.content_block.type == "thinking":
                print("\n[Thinking...]")
            elif event.content_block.type == "text":
                print("\n[Response:]")

        elif event.type == "content_block_delta":
            if event.delta.type == "thinking_delta":
                print(event.delta.thinking, end="", flush=True)
            elif event.delta.type == "text_delta":
                print(event.delta.text, end="", flush=True)
```

---

## Streaming with Tool Use

The Python tool runner supports streaming: pass `stream=True` to `client.beta.messages.tool_runner(...)` and each iteration yields a stream you consume event-by-event, with `get_final_message()` for the accumulated message per turn (see `shared/tool-use-concepts.md` -> Tool Runner vs Manual Loop). Declare tool-runner tools with `@beta_tool(eager_input_streaming=True)` so their inputs stream as they are generated (default rule: `shared/tool-use-concepts.md` -> Eager input streaming). The runner never calls your function on unparseable input; the `ValueError` surfaces while you iterate the per-turn stream, so wrap the `for ... in runner` loop and, on failure, restart a new runner from a history you mirror while iterating, in this order for each yielded stream: take `message = stream.get_final_message()`, append it (the assistant turn), then check its `stop_reason` - on `max_tokens` with a `tool_use` present or on `refusal`, stop right there and never call `generate_tool_call_response()` for that turn (it executes the tools) - and only for a turn that continues append `runner.generate_tool_call_response()` (the matching `tool_result` user turn), exactly as `tool-use.md` does to resume `pause_turn`. The Python runner exposes no `params` read, a consumed runner cannot be iterated again, and a history missing the tool-result half of a continued turn is rejected by the API. `pause_turn` you resume yourself; a truncated text answer is simply the final message.

Use the manual-loop pattern below only when you're not using the tool runner and need per-token streaming with tools. Set `eager_input_streaming: True` on each user-defined tool. With eager streaming the server no longer validates the input: the Python SDK's tolerant parser returns a partial object for a truncated input (check `stop_reason == "max_tokens"`) and can return a silently truncated one for malformed JSON (validate the parsed input before running the tool); only JSON it cannot parse at all raises `ValueError` **from the stream iterator**, so that guard wraps the stream, not the final-message read. Schema validation is not path validation: the model-supplied `path` is untrusted output, so confine it to a project root before writing (`shared/tool-use-concepts.md` -> the text-editor security note):

```python
import json
from pathlib import Path

ROOT = Path.cwd().resolve()

tools = [
    {
        "name": "write_file",
        "description": "Write text to a file at the given path",
        "eager_input_streaming": True,  # stream large inputs as generated
        "input_schema": {
            "type": "object",
            "properties": {
                "path": {"type": "string"},
                "contents": {"type": "string"},
            },
            "required": ["path", "contents"],
        },
    }
]

messages = [{"role": "user", "content": task}]
json_retries = 0

while True:
    try:
        with client.messages.stream(
            model="claude-opus-5-5",
            max_tokens=64000,
            tools=tools,
            messages=messages,
        ) as stream:
            for event in stream:
                if event.type == "text":
                    print(event.text, end="", flush=True)
                elif event.type == "input_json":
                    # Tool input fragment - arrives immediately with eager streaming
                    print(event.partial_json, end="", flush=True)
            response = stream.get_final_message()
        json_retries = 0  # the cap is on consecutive failures of one turn
    except ValueError:
        # JSON the SDK could not parse at all. It raised before the tool_use
        # block completed, so there is no tool_use_id to answer; re-issue the
        # turn (bounded). API errors are not ValueError and propagate.
        json_retries += 1
        if json_retries > 2:
            raise
        continue

    # Server-side tool hit its iteration limit: append the turn and re-send
    if response.stop_reason == "pause_turn":
        messages.append({"role": "assistant", "content": response.content})
        continue

    tool_uses = [b for b in response.content if b.type == "tool_use"]
    if response.stop_reason == "refusal" or not tool_uses:
        # end_turn, a text-only answer, or a refusal (which can cut a
        # tool_use off mid-input): nothing to run
        break
    if response.stop_reason == "max_tokens":
        # A truncated tool input parses as a valid partial object; don't run it.
        raise RuntimeError("tool input truncated; retry with a higher max_tokens")

    # The SDK's tolerant parser can return a silently truncated or mistyped
    # input (for example at an unescaped inner quote), so validate first.
    tool_results = []
    for block in tool_uses:
        args = block.input
        if not (isinstance(args, dict) and isinstance(args.get("path"), str)
                and isinstance(args.get("contents"), str)):
            tool_results.append({"type": "tool_result", "tool_use_id": block.id, "is_error": True,
                                 "content": json.dumps({"INVALID_JSON": json.dumps(args)})})
            continue
        # `path` is untrusted model output: resolve it and reject anything that
        # escapes the project root (`..`, absolute paths, symlinks) before the
        # write - schema validation alone does not check this.
        target = (ROOT / args["path"]).resolve()
        if not target.is_relative_to(ROOT):
            tool_results.append({"type": "tool_result", "tool_use_id": block.id, "is_error": True,
                                 "content": "path escapes the project root"})
            continue
        tool_results.append({"type": "tool_result", "tool_use_id": block.id,
                             "content": run_tool(block.name, {**args, "path": str(target)})})
    messages.append({"role": "assistant", "content": response.content})
    messages.append({"role": "user", "content": tool_results})
```

---

## Getting the Final Message

```python
with client.messages.stream(
    model="claude-opus-5-5",
    max_tokens=64000,
    messages=[{"role": "user", "content": "Hello"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

    # Get full message after streaming
    final_message = stream.get_final_message()
    print(f"\n\nTokens used: {final_message.usage.output_tokens}")
```

---

## Streaming with Progress Updates

```python
def stream_with_progress(client, **kwargs):
    """Stream a response with progress updates."""
    total_tokens = 0
    content_parts = []

    with client.messages.stream(**kwargs) as stream:
        for event in stream:
            if event.type == "content_block_delta":
                if event.delta.type == "text_delta":
                    text = event.delta.text
                    content_parts.append(text)
                    print(text, end="", flush=True)

            elif event.type == "message_delta":
                if event.usage and event.usage.output_tokens is not None:
                    total_tokens = event.usage.output_tokens

        final_message = stream.get_final_message()

    print(f"\n\n[Tokens used: {total_tokens}]")
    return "".join(content_parts)
```

---

## Error Handling in Streams

```python
try:
    with client.messages.stream(
        model="claude-opus-5-5",
        max_tokens=64000,
        messages=[{"role": "user", "content": "Write a story"}]
    ) as stream:
        for text in stream.text_stream:
            print(text, end="", flush=True)
except anthropic.APIConnectionError:
    print("\nConnection lost. Please retry.")
except anthropic.RateLimitError:
    print("\nRate limited. Please wait and retry.")
except anthropic.APIStatusError as e:
    print(f"\nAPI error: {e.status_code}")
```

---

## Stream Event Types

| Event Type            | Description                 | When it fires                     |
| --------------------- | --------------------------- | --------------------------------- |
| `message_start`       | Contains message metadata   | Once at the beginning             |
| `content_block_start` | New content block beginning | When a text/tool_use block starts |
| `content_block_delta` | Incremental content update  | For each token/chunk              |
| `content_block_stop`  | Content block complete      | When a block finishes             |
| `message_delta`       | Message-level updates       | Contains `stop_reason`, usage     |
| `message_stop`        | Message complete            | Once at the end                   |

## Best Practices

1. **Always flush output** - Use `flush=True` to show tokens immediately
2. **Handle partial responses** - If the stream is interrupted, you may have incomplete content
3. **Track token usage** - The `message_delta` event contains usage information
4. **Use timeouts** - Set appropriate timeouts for your application
5. **Default to streaming** - Use `.get_final_message()` to get the complete response even when streaming, giving you timeout protection without needing to handle individual events
6. **Large `max_tokens` without streaming raises `ValueError`** - The SDK refuses non-streaming requests it estimates will exceed ~10 minutes (idle connections drop). Pass `stream=True` / use `messages.stream()`, or explicitly override `timeout`, to suppress the guard.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall