OpenClaw

langfuse-continuous-optimizer

Continuous LangFuse-driven optimization loop for OpenClaw/OpenRouter model routing and prompt usage controls with persistent local memory. Use when Codex needs to ingest LangFuse observations and evaluator scores, generate task-level routing policy JSON, and run scheduled safe promotion cycles that tune cost-quality-latency tradeoffs automatically.

ekalb810 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install ekalb81/langfuse-continuous-optimizer

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Langfuse Continuous Optimizer

Overview

Run an automated observe -> evaluate -> adapt loop backed by LangFuse data.

This skill is independent and self-contained: it includes both policy builder and continuous optimizer scripts.

Quick Start

# Single optimization cycle (LangFuse API -> staged policy -> promoted live policy if gate passes)
python scripts/langfuse_openclaw_optimizer.py run-once \
  --langfuse-host https://us.cloud.langfuse.com \
  --window-hours 24 \
  --out-dir ~/.openclaw/optimizer \
  --live-policy-path ~/.openclaw/llm_routing_policy.json \
  --promote-live-policy \
  --write-memory \
  --save-config

# Continuous daemon
python scripts/langfuse_openclaw_optimizer.py daemon \
  --interval-min 30 \
  --save-config

# Toggle settings later (persisted)
python scripts/langfuse_openclaw_optimizer.py configure --disable-promote-live-policy --show
python scripts/langfuse_openclaw_optimizer.py configure --promote-live-policy --write-memory --show

Credentials:

LANGFUSE_PUBLIC_KEY
LANGFUSE_SECRET_KEY

Workflow

Pull LangFuse observations and scores from the configured time window.
Normalize telemetry and build staged routing policy artifacts.
Compare staged policy against current live policy with switch guardrails.
Promote only when gain and quality constraints are met and promotion is explicitly enabled.
Persist cycle memory to reduce policy churn and enable rollback reasoning.

Safety

Network egress: calls LangFuse Public API.
Local writes: writes raw snapshots, staged artifacts, and optional memory state under --out-dir.
Live policy overwrite is opt-in via --promote-live-policy.
Without --promote-live-policy, cycles are non-destructive (stage/evaluate only).
Save persisted defaults with --save-config; edit/toggle with configure.

Runtime Integration

Use the generated live policy in OpenClaw/LLM runtime via:

--llm-routing-policy-file ~/.openclaw/llm_routing_policy.json
--...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/ekalb81/langfuse-continuous-optimizer
Version: —
Commit: 153fe5f0de3ea0d22013092aba07ded3f0db24be
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Langfuse Continuous Optimizer

## Overview

Run an automated observe -> evaluate -> adapt loop backed by LangFuse data.

This skill is independent and self-contained: it includes both policy builder and continuous optimizer scripts.

## Quick Start

```bash
# Single optimization cycle (LangFuse API -> staged policy -> promoted live policy if gate passes)
python scripts/langfuse_openclaw_optimizer.py run-once \
--langfuse-host https://us.cloud.langfuse.com \
--window-hours 24 \
--out-dir ~/.openclaw/optimizer \
--live-policy-path ~/.openclaw/llm_routing_policy.json \
--promote-live-policy \
--write-memory \
--save-config

# Continuous daemon
python scripts/langfuse_openclaw_optimizer.py daemon \
--interval-min 30 \
--save-config

# Toggle settings later (persisted)
python scripts/langfuse_openclaw_optimizer.py configure --disable-promote-live-policy --show
python scripts/langfuse_openclaw_optimizer.py configure --promote-live-policy --write-memory --show
```

Credentials:

- `LANGFUSE_PUBLIC_KEY`
- `LANGFUSE_SECRET_KEY`

## Workflow

1. Pull LangFuse observations and scores from the configured time window.
2. Normalize telemetry and build staged routing policy artifacts.
3. Compare staged policy against current live policy with switch guardrails.
4. Promote only when gain and quality constraints are met and promotion is explicitly enabled.
5. Persist cycle memory to reduce policy churn and enable rollback reasoning.

## Safety

- Network egress: calls LangFuse Public API.
- Local writes: writes raw snapshots, staged artifacts, and optional memory state under `--out-dir`.
- Live policy overwrite is opt-in via `--promote-live-policy`.
- Without `--promote-live-policy`, cycles are non-destructive (stage/evaluate only).
- Save persisted defaults with `--save-config`; edit/toggle with `configure`.

## Runtime Integration

Use the generated live policy in OpenClaw/LLM runtime via:

```bash
--llm-routing-policy-file ~/.openclaw/llm_routing_policy.json
--...

搜索