跳到正文
cccskills
免费在 GitHub 公开

anth-upgrade-migration

Upgrade the Anthropic Python or TypeScript SDK and adapt applications to API changes such as moving from Text Completions to Messages. Review breaking changes, update request shapes and streaming code, run compatibility checks, and keep a rollback path for the release.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Upgrade Anthropic SDK versions and migrate between Claude API versions. Use when upgrading the Python/TypeScript SDK, migrating from Text Completions to Messages API, or adopting new API features like tool use or batches. Trigger with phrases like "upgrade anthropic sdk", "anthropic migration", "update claude sdk", "migrate to messages api".

实测评分 未实测

查看安装方法

适用场景

  • Upgrade the Anthropic Python SDK
  • Update a TypeScript project to a newer SDK
  • Move from Text Completions to Messages API
  • Check streaming and tool-use compatibility

包含的文件(1)

  • SKILL.md6.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Anthropic Upgrade & Migration

Overview

Guide for upgrading the Anthropic SDK and migrating between API versions. The SDK follows semver — major versions may have breaking changes.

Check Current Versions

# Python
pip show anthropic | grep Version
# Version: 0.40.0

# TypeScript
npm list @anthropic-ai/sdk
# @anthropic-ai/sdk@0.35.0

# Check latest available
pip index versions anthropic 2>/dev/null | head -1
npm view @anthropic-ai/sdk version

Upgrade Path

Step 1: Create Upgrade Branch

git checkout -b upgrade/anthropic-sdk

Step 2: Upgrade SDK

# Python
pip install --upgrade anthropic
pip show anthropic | grep Version

# TypeScript
npm install @anthropic-ai/sdk@latest

Step 3: Review Breaking Changes

Key breaking changes by version:

Python SDK 0.20+ (anthropic-version: 2023-06-01)

# OLD: Text Completions API (deprecated)
response = client.completions.create(
    model="claude-2",
    prompt="\n\nHuman: Hello\n\nAssistant:",
    max_tokens_to_sample=256
)

# NEW: Messages API
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=256,
    messages=[{"role": "user", "content": "Hello"}]
)

Python SDK 0.30+ (streaming changes)

# OLD: Manual SSE parsing
response = client.messages.create(..., stream=True)
for line in response.iter_lines():
    ...

# NEW: High-level streaming
with client.messages.stream(...) as stream:
    for text in stream.text_stream:
        print(text)

TypeScript SDK 0.20+ (import path change)

// OLD
import Anthropic from 'anthropic';

// NEW
import Anthropic from '@anthropic-ai/sdk';

Step 4: Update API Version Header

# The SDK sends anthropic-version header automatically
# To pin a specific version:
client = anthropic.Anthropic(
    default_headers={"anthropic-version": "2023-06-01"}
)

# For beta features:
client = anthropic.Anthropic(
    default_headers={"anthropic-beta": "token-counting-2024-11-01"}
)

Step 5: Run Tests and Verify

# Run your test suite
python -m pytest tests/ -v
npm test

# Verify a live call
python3 -c "
import anthropic
c = anthropic.Anthropic()
m = c.messages.create(model='claude-haiku-4-20250514', max_tokens=8, messages=[{'role':'user','content':'hi'}])
print(f'OK: {m.model} {m.usage}')
"

Migration: Text Completions to Messages

Text CompletionsMessages API
client.completions.create()client.messages.create()
prompt (string)messages (array)
max_tokens_to_samplemax_tokens
model: "claude-2"model: "claude-sonnet-4-20250514"
\n\nHuman:...\n\nAssistant:[{role: "user"}, {role: "assistant"}]
response.completionresponse.content[0].text

Rollback

# Python — pin to previous version
pip install anthropic==0.39.0

# TypeScript — pin to previous version
npm install @anthropic-ai/sdk@0.34.0

# Git rollback
git checkout main -- package.json package-lock.json
npm install

Prerequisites

  • Record the current SDK version, lockfile digest, API version header, model identifiers, supported runtime versions, and a tested rollback revision.
  • Obtain release notes from the official SDK/API sources and an approved sandbox workspace with synthetic prompts; production credentials must not be used for migration tests.
  • Define compatibility, latency, cost, and response-shape acceptance thresholds and identify the owner who approves promotion.

Instructions

  1. Create a migration branch and lock the current dependency graph. Compare the target SDK and API behavior against official release notes; do not infer compatibility from a package version alone.
  2. Update the SDK and request shapes in a sandbox, preserving explicit model IDs, max_tokens, authentication through the secret manager, and least-privileged workspace access.
  3. Run unit, contract, streaming, tool-use, error, and token-count tests using synthetic fixtures. Compare redacted response-shape and usage receipts with the baseline; never log prompt or response content.
  4. Canary the pinned artifact on an isolated workspace with zero customer traffic. Promote only after owner approval and threshold checks; monitor errors, latency, rate limits, and spend during the rollout.
  5. If any gate fails, stop promotion, restore the prior lockfile/revision, revoke temporary credentials, and preserve the redacted migration receipt.

Output

Produce a migration receipt containing source and target SDK versions, API-version header, lockfile/artifact digests, test and canary results, model IDs, workspace/environment, approval, rollout state, rollback reference, and retention deadline. Exclude API keys, prompt/response text, customer identifiers, and raw exception payloads.

Error Handling

FailureResponse
Dependency or API contract test failsPin the prior version, isolate the failing fixture, and do not promote.
Authentication or permission failureStop the canary, verify the secret-manager reference and workspace scope, and never print the key.
429/5xx, timeout, or latency regressionRespect SDK retry guidance, apply a bounded circuit breaker, and roll back when the canary threshold is exceeded.
Response-shape or tool-use driftQuarantine the result, update the adapter only after an approved contract decision, and rerun the full suite.

Examples

For a synthetic migration fixture, pin anthropic from 0.39.0 to the reviewed target, run 100 sandbox Messages API calls with customer=fixture-017, assert response-shape parity and customer_content_logged=0, then promote to a 1% internal canary. A failed threshold yields promotion=halted; rollback=prior-lockfile.

Resources

Next Steps

For CI integration during upgrades, see anth-ci-integration.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Add a synthetic-data CI gate for customer-owned Abridge integration code. Test consent handling, note-review handoffs, redaction, and rollback behavior with mocked vendor boundaries, without connecting CI to a live Abridge or EHR tenant.

中文简介正在准备中。当前显示英语简介。

  • Adding regression checks to an Abridge integration repository
  • Testing consent and note-release handling
  • Checking logs for sensitive data exposure
jeremylongshore/tons-of-skills-marketplace28672026年10月23日 更新

Triage Abridge recording, note review, Epic handoff, and access problems using observed symptoms and approved guidance. Identify the affected workflow stage, organize a minimal timeline, and prepare a redacted escalation record for the responsible team.

中文简介正在准备中。当前显示英语简介。

  • Separate recording problems from upload failures
  • Investigate note creation delays and editor issues
  • Identify the responsible team for Epic handoff failures
jeremylongshore/tons-of-skills-marketplace28672026年10月23日 更新

Map and review an Abridge clinical documentation workflow from consent and recording through draft review, evidence checks, edits, and final disposition. Keep clinician approval explicit, identify failure exits, and separate verified facts from tenant-specific details and pending approvals.

中文简介正在准备中。当前显示英语简介。

  • Map a clinical note workflow for a care setting
  • Check where consent and patient identity are verified
  • Review draft notes against linked evidence before sign-off
jeremylongshore/tons-of-skills-marketplace28672026年10月23日 更新

Audit how clinician-reviewed Abridge note sections map into Epic templates and downstream workflows. Use approved test records to document destinations, exceptions, evidence, rollback steps, and a go or no-go decision for a specific environment.

中文简介正在准备中。当前显示英语简介。

  • Checking Abridge note section mappings to Epic templates
  • Auditing a department’s approved documentation handoff
  • Preparing test evidence and a go or no-go decision
jeremylongshore/tons-of-skills-marketplace28672026年10月23日 更新

Review Abridge adoption and workflow value using local usage records, clinician feedback, and verified contract costs. Build an evidence based decision table covering adoption, quality, support burden, and options to expand, hold, or improve the rollout.

中文简介正在准备中。当前显示英语简介。

  • Reviewing adoption after an Abridge rollout
  • Preparing evidence for a renewal decision
  • Comparing workflow outcomes across care settings
jeremylongshore/tons-of-skills-marketplace28672026年10月23日 更新

Prepare a bounded support bundle for an Abridge issue using allowlisted operational details such as versions, coarse timestamps, and correlation references. Exclude recordings, transcripts, patient identifiers, credentials, and unrestricted logs, then document redactions and review details.

中文简介正在准备中。当前显示英语简介。

  • Preparing reviewed evidence for an Abridge support case
  • Documenting redactions and excluded data
  • Collecting approved operational details for an incident
jeremylongshore/tons-of-skills-marketplace28672026年10月23日 更新

查看 jeremylongshore 的全部技能

报告此技能的问题