ai-core/adapter-configuration

A guide to selecting and configuring provider adapters for an AI application, including OpenAI, Anthropic, Gemini, Ollama, and other text-model providers. It also covers model options, reasoning settings, runtime switching, and custom adapters.

In plain words
What is it for?
Use it to create chat streams, configure API keys and endpoints, set sampling or output limits, switch providers at runtime, and extend the adapter system for custom models.
Why use it?
It helps connect an application to the intended provider and model while keeping provider-specific settings in the right place and checking current model information.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tanstack/ai/adapter-configuration
Any agent
npx skills add TanStack/ai --skill adapter-configuration
Clone the repo
git clone --depth 1 https://github.com/TanStack/ai

Made for: Claude Code, Codex.

Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,351 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00227 $0.05351
Opus 5 $0.00113 $0.02676
Sonnet 5 $0.00045 $0.01070
Haiku 4.5 $0.00023 $0.00535

Measured yesterday against content hash e068f8dcedd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-core/adapter-configuration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/ai/skills/ai-core/adapter-configuration/SKILL.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adapter Configuration

Dependency: This skill builds on ai-core. Read it first for critical rules.

Before implementing: Ask the user which provider and model they want. Then fetch the latest available models from the provider's source code (check the adapter's model metadata file, e.g. packages/ai-openai/src/model-meta.ts) or from the provider's API/docs to recommend the most current model. The model lists in this skill and its reference files may be outdated. Always verify against the source before recommending a specific model.

Setup

Create an adapter and use it with chat():

import { chat, toServerSentEventsResponse } from '@tanstack/ai'
import { openaiText } from '@tanstack/ai-openai'

const stream = chat({
  adapter: openaiText('gpt-5.2'),
  messages,
  modelOptions: {
    temperature: 0.7,
    max_output_tokens: 1000,
  },
})

return toServerSentEventsResponse(stream)

The adapter factory function takes the model name as a string literal and an optional config object (API key, base URL, etc.). The model name is passed into the factory, not into chat().

Sampling options (temperature, token limits, top_p/topP, etc.) live inside modelOptions using each provider's native key — they are not top-level options on chat(). See the per-provider table in Configuring Sampling below.

Core Patterns

1. Adapter Selection

Each provider has a dedicated package with tree-shakeable adapter factories. The text adapter is the primary one for chat/completions:

Provider Package Factory Env Var
OpenAI @tanstack/ai-openai openaiText OPENAI_API_KEY
Anthropic @tanstack/ai-anthropic anthropicText ANTHROPIC_API_KEY
Gemini @tanstack/ai-gemini geminiText GOOGLE_API_KEY or GEMINI_API_KEY
Grok (xAI) @tanstack/ai-grok grokText XAI_API_KEY
Groq @tanstack/ai-groq groqText GROQ_API_KEY
OpenRouter @tanstack/ai-openrouter openRouterText OPENROUTER_API_KEY
Ollama @tanstack/ai-ollama ollamaText OLLAMA_HOST (default: http://localhost:11434)
Bedrock @tanstack/ai-bedrock bedrockText BEDROCK_API_KEY or AWS_BEARER_TOKEN_BEDROCK
BytePlus @tanstack/ai-byteplus byteplusText ARK_API_KEY (falls back to BYTEPLUS_API_KEY)
OpenAI-compatible @tanstack/ai-openai/compatible openaiCompatible / openaiCompatibleText provider-specific (passed via apiKey)

Read the full file on GitHub · 482 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 482 lines · 227 tokens per session scan A e068f8dcedd9

Subscribe to this mod's changes

ai-core/adapter-configuration is a skill published in the GitHub repository TanStack/ai (3,045 stars, last pushed 2d ago), licensed MIT. It adds 227 tokens to every session and 5,351 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.