Skip to main content 首页 创作者 jeremylongshore tons-of-skills-marketplace langfuse-migration-deep-dive
langfuse-migration-deep-dive Execute complex Langfuse migrations including data migration and platform changes.
Use when migrating from other observability platforms, moving between Langfuse instances,
or performing major infrastructure migrations.
Trigger with phrases like "langfuse migration", "migrate to langfuse",
"langfuse data migration", "langfuse platform migration", "switch to langfuse".
跳到安装 Skills Marketplace 发现并探索由社区构建的 Agent Skills
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill langfuse-migration-deep-dive命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
下载 Zip 下载中... 同仓库更多 Skills langchain-deploy-integration Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", or "langchain docker".
langchain-langgraph-agents Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", or "agent loop cost".
langchain-langgraph-human-in-loop Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before /
interrupt_after and Command(resume=...) — JSON-serializable state, clean
resume semantics, and UI wiring for approval decisions. Use when adding an
approval gate before an expensive tool call, wiring a Slack/web UI for agent
approvals, or debugging a graph that crashes on interrupt.
Trigger with "langgraph human in loop", "langgraph interrupt_before",
"langgraph approval flow", "Command resume", "langgraph HITL".
jeremylongshore
jeremylongshore/tons-of-skills-marketplace
打开 GitHub 仓库 name langfuse-migration-deep-dive description Execute complex Langfuse migrations including data migration and platform changes.
Use when migrating from other observability platforms, moving between Langfuse instances,
or performing major infrastructure migrations.
Trigger with phrases like "langfuse migration", "migrate to langfuse",
"langfuse data migration", "langfuse platform migration", "switch to langfuse".
allowed-tools Read, Write, Edit, Bash(npm:*) version 1.12.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> tags ["saas","langfuse","observability","migration"] compatibility Designed for Claude Code
Langfuse Migration Deep Dive
Current State
!npm list langfuse @langfuse/client 2>/dev/null | head -5 || echo 'No langfuse packages'
Overview
Comprehensive guide for complex migrations: cloud-to-self-hosted, LangSmith-to-Langfuse, cross-instance data migration, and zero-downtime dual-write patterns.
Prerequisites
Understanding of source and target Langfuse instances
API keys for both source and target
Git branch for migration work
Rollback plan documented
Migration Scenarios
Scenario Complexity Downtime Data Loss Risk Cloud to Cloud (different project) Low None None Cloud to Self-hosted Medium Minutes Low Self-hosted to Cloud Medium Minutes Low LangSmith to Langfuse High Hours Medium SDK v3 to v4+ (no data migration) Low None None
Instructions
Step 1: Export Data from Source Instance
import { LangfuseClient } from "@langfuse/client" ;
import { writeFileSync, mkdirSync } from "fs" ;
const source = new LangfuseClient ({
publicKey : process.env .SOURCE_LANGFUSE_PUBLIC_KEY ,
secretKey : process.env .SOURCE_LANGFUSE_SECRET_KEY ,
baseUrl : process.env .SOURCE_LANGFUSE_BASE_URL ,
});
async function exportAll
outputDir : string
mkdirSync
recursive
true
let
1
let
allTraces
any
let
true
console
log
"Exporting traces..."
while
const
await
api
traces
list
limit
100
push
data
data
length
100
await
new
Promise
(r ) =>
setTimeout
200
writeFileSync
`${outputDir} /traces.json`
JSON
stringify
null
2
console
log
` Exported ${allTraces.length} traces`
1
let
allScores
any
true
console
log
"Exporting scores..."
while
const
await
api
scores
list
limit
100
push
data
data
length
100
await
new
Promise
(r ) =>
setTimeout
200
writeFileSync
`${outputDir} /scores.json`
JSON
stringify
null
2
console
log
` Exported ${allScores.length} scores`
console
log
"Exporting prompts..."
const
await
api
prompts
list
limit
100
writeFileSync
`${outputDir} /prompts.json`
JSON
stringify
data
null
2
console
log
` Exported ${prompts.data.length} prompts`
console
log
"Exporting datasets..."
const
await
api
datasets
list
limit
100
const
for
const
of
data
const
await
api
datasetItems
list
datasetName
name
limit
1000
push
items
data
await
new
Promise
(r ) =>
setTimeout
200
writeFileSync
`${outputDir} /datasets.json`
JSON
stringify
null
2
console
log
` Exported ${fullDatasets.length} datasets`
exportAll
"./migration-export"
Step 2: Import Data to Target Instance
import { LangfuseClient } from "@langfuse/client" ;
import { readFileSync } from "fs" ;
const target = new LangfuseClient ({
publicKey : process.env .TARGET_LANGFUSE_PUBLIC_KEY ,
secretKey : process.env .TARGET_LANGFUSE_SECRET_KEY ,
baseUrl : process.env .TARGET_LANGFUSE_BASE_URL ,
});
async function importAll (inputDir : string console .log ("Importing prompts..." );
const prompts = JSON .parse (readFileSync (`${inputDir} /prompts.json` , "utf-8" ));
for (const prompt of prompts) {
await target.api .prompts .create ({
name : prompt.name ,
prompt : prompt.prompt ,
type : prompt.type ,
config : prompt.config ,
labels : prompt.labels ,
});
console .log (` Imported prompt: ${prompt.name} ` );
await new Promise ((r ) => setTimeout (r, 100 ));
}
console .log ("Importing datasets..." );
const datasets = JSON .parse (readFileSync (`${inputDir} /datasets.json` , "utf-8" ));
for (const ds of datasets) {
await target.api .datasets .create ({
name : ds.name ,
description : ds.description ,
metadata : { ...ds.metadata , migratedFrom : "source-instance" },
});
for (const item of ds.items || []) {
await target.api .datasetItems .create ({
datasetName : ds.name ,
input : item.input ,
expectedOutput : item.expectedOutput ,
metadata : item.metadata ,
});
await new Promise ((r ) => setTimeout (r, 50 ));
}
console .log (` Imported dataset: ${ds.name} (${ds.items?.length || 0 } items)` );
}
console .log ("Import complete." );
console .log ("Note: Traces and scores are historical -- they reference old trace IDs." );
console .log ("New traces will be created by your application pointing to the target." );
}
importAll ("./migration-export" );
Step 3: Dual-Write for Zero-Downtime Migration Write traces to both instances during transition:
import { LangfuseSpanProcessor } from "@langfuse/otel" ;
import { NodeSDK } from "@opentelemetry/sdk-node" ;
const sourceProcessor = new LangfuseSpanProcessor ({
publicKey : process.env .SOURCE_LANGFUSE_PUBLIC_KEY ,
secretKey : process.env .SOURCE_LANGFUSE_SECRET_KEY ,
baseUrl : process.env .SOURCE_LANGFUSE_BASE_URL ,
});
const targetProcessor = new LangfuseSpanProcessor ({
publicKey : process.env .TARGET_LANGFUSE_PUBLIC_KEY ,
secretKey : process.env .TARGET_LANGFUSE_SECRET_KEY ,
baseUrl : process.env .TARGET_LANGFUSE_BASE_URL ,
});
const sdk = new NodeSDK ({
spanProcessors : [sourceProcessor, targetProcessor],
});
sdk.start ();
Step 4: Validate Migration
import { LangfuseClient } from "@langfuse/client" ;
const source = new LangfuseClient ({
publicKey : process.env .SOURCE_LANGFUSE_PUBLIC_KEY ,
secretKey : process.env .SOURCE_LANGFUSE_SECRET_KEY ,
baseUrl : process.env .SOURCE_LANGFUSE_BASE_URL ,
});
const target = new LangfuseClient ({
publicKey : process.env .TARGET_LANGFUSE_PUBLIC_KEY ,
secretKey : process.env .TARGET_LANGFUSE_SECRET_KEY ,
baseUrl : process.env .TARGET_LANGFUSE_BASE_URL ,
});
async function validate (const sourcePrompts = await source.api .prompts .list ({ limit : 100 });
const targetPrompts = await target.api .prompts .list ({ limit : 100 });
console .log (`Prompts: source=${sourcePrompts.data.length} , target=${targetPrompts.data.length} ` );
const sourceDatasets = await source.api .datasets .list ({ limit : 100 });
const targetDatasets = await target.api .datasets .list ({ limit : 100 });
console .log (`Datasets: source=${sourceDatasets.data.length} , target=${targetDatasets.data.length} ` );
const since = new Date (Date .now () - 3600000 ).toISOString ();
const sourceTraces = await source.api .traces .list ({ fromTimestamp : since, limit : 100 });
const targetTraces = await target.api .traces .list ({ fromTimestamp : since, limit : 100 });
console .log (`Recent traces (1h): source=${sourceTraces.data.length} , target=${targetTraces.data.length} ` );
const variance = Math .abs (sourceTraces.data .length - targetTraces.data .length ) / Math .max (sourceTraces.data .length , 1 );
console .log (`Trace variance: ${(variance * 100 ).toFixed(1 )} % (target: <5%)` );
}
validate ();
Step 5: Cutover and Cleanup
const sdk = new NodeSDK ({
spanProcessors : [targetProcessor],
});
Rollback Plan set -euo pipefail
export LANGFUSE_PUBLIC_KEY="pk-lf-source-..."
export LANGFUSE_SECRET_KEY="sk-lf-source-..."
export LANGFUSE_BASE_URL="https://source.langfuse.com"
Error Handling Issue Cause Solution Export timeout Too much data Paginate with smaller page sizes Import duplicates Re-running import Use idempotent creates with unique names Dual-write divergence One instance failing Monitor both, alert on variance > 5% Missing prompts Not exported Export prompts before datasets
Resources 