mistral-upgrade-migration
Analyze, plan, and execute Mistral AI SDK upgrades with breaking change detection. Use when upgrading Mistral SDK versions, detecting deprecations, or migrating to new API versions. Trigger with phrases like "upgrade mistral", "mistral breaking changes", "update mistral SDK", "analyze mistral version".
What this skill does
# Mistral AI Upgrade & Migration
## Current State
!`npm list @mistralai/mistralai 2>/dev/null || echo 'not installed'`
!`pip show mistralai 2>/dev/null | grep -E "^(Name|Version)" || echo 'not installed'`
## Overview
Guide for upgrading the Mistral AI SDK between major versions. The TypeScript SDK (`@mistralai/mistralai`) moved from CommonJS to ESM-only in v1.x, with significant API surface changes. This skill covers version detection, breaking change migration, automated code transforms, and rollback.
## Prerequisites
- Current Mistral AI SDK installed
- Git for version control
- Test suite available
## Instructions
### Step 1: Check Versions
```bash
set -euo pipefail
# Current version
npm list @mistralai/mistralai 2>/dev/null
# Latest available
npm view @mistralai/mistralai version
# All versions
npm view @mistralai/mistralai versions --json | jq '.[-5:]'
# Python
pip show mistralai 2>/dev/null | grep Version
```
### Step 2: Known Breaking Changes (v0.x to v1.x)
| Change | v0.x (old) | v1.x (current) |
|--------|-----------|----------------|
| Module format | CommonJS + ESM | **ESM only** |
| Import | `import MistralClient from '...'` | `import { Mistral } from '...'` |
| Constructor | `new MistralClient(apiKey)` | `new Mistral({ apiKey })` |
| Chat method | `client.chat(params)` | `client.chat.complete(params)` |
| Streaming | `client.chatStream(params)` | `client.chat.stream(params)` |
| Stream events | `for await (const chunk of stream)` | `for await (const event of stream)` access `.data` |
| Embeddings | `client.embeddings(params)` | `client.embeddings.create(params)` |
| Response types | Longer names | Shorter type names |
| Enum values | String constants | Forward-compatible unions |
### Step 3: Automated Migration Script
```typescript
// scripts/migrate-mistral-v1.ts
import { readFileSync, writeFileSync } from 'fs';
import { glob } from 'glob';
const TRANSFORMS = [
// Import statement
{
find: /import\s+MistralClient\s+from\s+['"]@mistralai\/mistralai['"]/g,
replace: "import { Mistral } from '@mistralai/mistralai'",
},
// Constructor
{
find: /new\s+MistralClient\((\w+)\)/g,
replace: 'new Mistral({ apiKey: $1 })',
},
// Chat method (careful: only top-level .chat(), not .chat.complete())
{
find: /\.chat\((?!\.)/g,
replace: '.chat.complete(',
},
// Streaming
{
find: /\.chatStream\(/g,
replace: '.chat.stream(',
},
// Embeddings
{
find: /\.embeddings\((?!\.)/g,
replace: '.embeddings.create(',
},
];
async function migrate() {
const files = await glob('src/**/*.{ts,js}');
let totalChanges = 0;
for (const file of files) {
let content = readFileSync(file, 'utf-8');
let changes = 0;
for (const { find, replace } of TRANSFORMS) {
const newContent = content.replace(find, replace);
if (newContent !== content) {
changes++;
content = newContent;
}
}
if (changes > 0) {
writeFileSync(file, content);
console.log(`Migrated: ${file} (${changes} changes)`);
totalChanges += changes;
}
}
console.log(`\nTotal: ${totalChanges} changes across ${files.length} files`);
}
migrate();
```
### Step 4: Upgrade Procedure
```bash
set -euo pipefail
# Create branch
git checkout -b upgrade/mistral-sdk-v1
# Backup lock file
cp package-lock.json package-lock.json.bak
# Upgrade
npm install @mistralai/mistralai@latest
# Ensure package.json has "type": "module"
node -e "const p=require('./package.json'); if(p.type!=='module') console.warn('WARNING: Add \"type\": \"module\" to package.json for ESM')"
# Run migration script
npx tsx scripts/migrate-mistral-v1.ts
# Verify
npm run typecheck
npm test
```
### Step 5: Model Name Updates
Model names change over time. Update hardcoded references:
```typescript
// Model alias mapping — update when models deprecate
const MODEL_ALIASES: Record<string, string> = {
// Deprecated → Current
'mistral-tiny': 'mistral-small-latest',
'mistral-medium': 'mistral-small-latest', // Deprecated Q1 2025
'open-mistral-7b': 'mistral-small-latest',
'open-mixtral-8x7b': 'mistral-small-latest',
// Current (no change needed)
'mistral-small-latest': 'mistral-small-latest',
'mistral-large-latest': 'mistral-large-latest',
'codestral-latest': 'codestral-latest',
'mistral-embed': 'mistral-embed',
};
function resolveModel(model: string): string {
const resolved = MODEL_ALIASES[model];
if (resolved && resolved !== model) {
console.warn(`Model "${model}" is deprecated, using "${resolved}"`);
}
return resolved ?? model;
}
```
### Step 6: Validation Tests
```typescript
import { describe, it, expect } from 'vitest';
import { Mistral } from '@mistralai/mistralai';
describe('SDK Upgrade Validation', () => {
it('should import Mistral correctly', () => {
expect(Mistral).toBeDefined();
expect(typeof Mistral).toBe('function');
});
it('should construct client', () => {
const client = new Mistral({ apiKey: 'test-key' });
expect(client.chat).toBeDefined();
expect(client.chat.complete).toBeDefined();
expect(client.chat.stream).toBeDefined();
expect(client.embeddings).toBeDefined();
expect(client.embeddings.create).toBeDefined();
expect(client.models).toBeDefined();
expect(client.models.list).toBeDefined();
});
});
```
### Step 7: Rollback
```bash
set -euo pipefail
# Quick rollback
npm install @mistralai/[email protected] --save-exact
git checkout -- src/ # Restore pre-migration code
npm test
# Or just revert the branch
git checkout main
git branch -D upgrade/mistral-sdk-v1
```
## Error Handling
| Error After Upgrade | Cause | Solution |
|---------------------|-------|----------|
| `ERR_REQUIRE_ESM` | Missing "type": "module" | Add to package.json |
| `Mistral is not a constructor` | Old import style | Use `import { Mistral }` |
| `.chat is not a function` | Old method call | Use `.chat.complete()` |
| Type errors | Interface changes | Update types to match v1.x |
| Test failures | Response shape changed | Update assertions and mocks |
## Resources
- [TypeScript SDK Releases](https://github.com/mistralai/client-ts/releases)
- [Python SDK Releases](https://github.com/mistralai/client-python/releases)
- [Changelog](https://docs.mistral.ai/getting-started/changelog/)
- [Models Deprecation](https://docs.mistral.ai/getting-started/models/)
## Output
- Updated SDK to latest version
- Automated code migration applied
- Model name references updated
- Test suite passing after upgrade
- Rollback procedure documented
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.