AGENTS.md@web/src/features/ai-gatewayA

AGENTS.md@web/src/features/ai-gateway from langfuse/langfuse is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add langfuse/langfuse/web/src/features/ai-gateway/AGENTS.md@git:20261118.fe6aa6b

Pins git:20261118.fe6aa6b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
langfuse/langfuse
Path
web/src/features/ai-gateway/AGENTS.md
Versions recorded
4
Latest version
git:20261118.fe6aa6b, committed Nov 18, 2026
First version recorded
Sep 10, 2026
Size
791 bytes
Repository stars
37,634
License
a license file GitHub does not identify

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

## AI Gateway

### Implementation

- performance of the `/resolve` API path is critical - ideally stays under 10ms
- no tautological frontend component tests that check stuff like height / width
- never read or write the gateway's spend Redis keyspace (`gateway-spend:*`); it belongs to the Rust gateway. Spend shown in the control plane comes from ClickHouse.

### Testing

- When changing the core flow or model provider-specifics: ensure that the end-to-end test suite remains valid: one suite per provider in `web/src/__e2e__/ai-gateway/`, all run by the single `test-ai-gateway-e2e` CI job. Each suite adds the provider connection, starts the built binary, lists models, and checks that completions are ingested with model, usage and cost. Shared setup lives in `gatewayE2eHarness.ts`.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add langfuse/langfuse/web/src/features/ai-gateway/AGENTS.md@sha256:67cb75ab8df30506

The line at the top of this page pins the label git:20261118.fe6aa6b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_prpktancp7ptgk3w.svg)](https://markdownregistry.com/a/art_prpktancp7ptgk3w)

0 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in langfuse/langfuse/web/src/features/ai-gateway/AGENTS.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of AGENTS.md from somewhere else? Ask it: where did my AGENTS.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 4 versions of this file, between Sep 10, 2026 and Nov 18, 2026, about one every 23 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261118.fe6aa6b latest2026-11-18 fe6aa6b 791 BA view · diff
git:20261113.6c700f12026-11-13 6c700f1 625 BA view · diff
git:20261015.d3f61322026-10-15 d3f6132 477 BA view · diff
git:20260910.8ee053b2026-09-10 8ee053b 366 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (791 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

langfuse/langfuse · 37,634 stars · license a license file GitHub does not identify · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_prpktancp7ptgk3w
GET https://markdownregistry.com/api/v1/resolve?ref=langfuse/langfuse/web/src/features/ai-gateway/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/67cb75ab8df305063c52686ed8ebbd5db0b4fb775574dd520ba3ac31ead0bbcc

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from langfuse/langfuse

AGENTS.md@.agents AGENTS.md file
langfuse/langfuse · .agents/AGENTS.md
git:20261105.a869249 · audit A · 37,634 stars
add-model-price SKILL.md skill
langfuse/langfuse · .agents/skills/add-model-price/SKILL.md · Use when editing worker/src/constants/default-model-prices.json, packages/shared/src/server/llm/types.ts, pricing…
git:20261006.39cb678 · audit A · 37,634 stars
add-to-dependabot-csv SKILL.md skill
langfuse/langfuse · .agents/skills/add-to-dependabot-csv/SKILL.md · Append GitHub Dependabot or Snyk/code-scanning alerts to an existing vulnerability CSV after verifying their API…
git:20261002.3b02ae4 · audit A · 37,634 stars
agent-setup-maintenance SKILL.md skill
langfuse/langfuse · .agents/skills/agent-setup-maintenance/SKILL.md · Shared workflow for editing Langfuse's repo-owned agent setup under `.agents/`. Use when changing AGENTS files, shared…
git:20260921.1357013 · audit A · 37,634 stars
analyze-cloud-costs SKILL.md skill
langfuse/langfuse · .agents/skills/analyze-cloud-costs/SKILL.md · Analyze Langfuse Cloud infrastructure cost structure using Metabase cost marts. Use when asked about cloud spend, AWS…
git:20260511.5e5ed8a · audit A · 37,634 stars
backend-dev-guidelines SKILL.md skill
langfuse/langfuse · .agents/skills/backend-dev-guidelines/SKILL.md · Build or review Langfuse backend code. Use for tRPC routers, public REST APIs, BullMQ processors, services, middleware…
git:20261105.4fa3d2e · audit B · 37,634 stars
changelog-writing SKILL.md skill
langfuse/langfuse · .agents/skills/changelog-writing/SKILL.md · Shared workflow for writing Langfuse changelog entries after a feature is complete. Use when a branch is ready for…
git:20260811.7617df6 · audit A · 37,634 stars
clickhouse-best-practices SKILL.md skill
langfuse/langfuse · .agents/skills/clickhouse-best-practices/SKILL.md · MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before…
v0.3.0 · audit A · 37,634 stars
code-review SKILL.md skill
langfuse/langfuse · .agents/skills/code-review/SKILL.md · Review Langfuse code changes for correctness, regressions, and best practices.
git:20261004.c37160d · audit A · 37,634 stars
create-repo-agent SKILL.md skill
langfuse/langfuse · .agents/skills/create-repo-agent/SKILL.md · Design, implement, review, or harden Langfuse repo-owned autonomous agents. Use for LLM-powered GitHub Actions…
git:20260729.6d2988f · audit A · 37,634 stars
cursor-agents-workflow SKILL.md skill
langfuse/langfuse · .agents/skills/cursor-agents-workflow/SKILL.md · Human handoff, Linear branch names, reviewable (non-draft) PRs, the `cursor` GitHub label, Claude, Greptile, and Codex…
git:20261105.a869249 · audit A · 37,634 stars
datadog-query-recipes SKILL.md skill
langfuse/langfuse · .agents/skills/datadog-query-recipes/SKILL.md · Research Langfuse production telemetry with reusable Datadog queries. Use for tenant or project activity, API usage…
git:20261119.d535d56 · audit A · 37,634 stars

Every file in langfuse/langfuse

Browse by kind, by grade A, or by owner.