mirror of https://github.com/openclaw/openclaw.git synced 2026-07-24 15:16:05 +00:00

History

Vincent Koc 046bf2468d refactor(meta): remove unused stream helper export (#105443 )		2026-07-12 16:09:01 +02:00
..
api.ts
index.test.ts	fix(providers): align Meta Model API contract (#103680 )	2026-07-10 05:24:14 -07:00
index.ts
meta.live.test.ts	fix(providers): align Meta Model API contract (#103680 )	2026-07-10 05:24:14 -07:00
models.ts	feat(tooling): enforce noUncheckedIndexedAccess in the extensions lane (NUIA phase 4) (#105132 )	2026-07-12 09:17:31 +01:00
npm-shrinkwrap.json	chore(release): set version to 2026.7.2	2026-07-11 04:00:49 +01:00
onboard.ts	chore(tooling): enforce formatting and refresh TypeScript checks (#104239 )	2026-07-11 01:09:51 -07:00
openclaw.plugin.json	fix(providers): align Meta Model API contract (#103680 )	2026-07-10 05:24:14 -07:00
package.json	chore(release): set version to 2026.7.2	2026-07-11 04:00:49 +01:00
provider-catalog.ts
README.md	fix(providers): align Meta Model API contract (#103680 )	2026-07-10 05:24:14 -07:00
stream.ts	refactor(meta): remove unused stream helper export (#105443 )	2026-07-12 16:09:01 +02:00
thinking.ts	chore(tooling): enforce formatting and refresh TypeScript checks (#104239 )	2026-07-11 01:09:51 -07:00
tsconfig.json

README.md

Meta provider

Bundled OpenClaw provider plugin for the Meta API — an OpenAI-compatible Responses API endpoint (POST /v1/responses).

Base URL: https://api.meta.ai/v1
Auth: Authorization: Bearer $MODEL_API_KEY
Model: muse-spark-1.1 (reasoning model)
- Context window: 1,048,576 tokens (input + output share the budget)
- Maximum output: 131,072 tokens
- Reasoning effort: minimal | low | medium | high | xhigh (default: high)
- Vision: image input in user messages
- Tool calling + streaming
- Stateless encrypted reasoning replay (store: false)

Usage

Set the API key and select the model:

export MODEL_API_KEY=<key>

// ~/.openclaw/openclaw.json
{
  agents: {
    defaults: {
      model: { primary: "meta/muse-spark-1.1" },
    },
  },
}

Or run onboarding and choose Meta.

Thinking / reasoning

--thinking <level> and /think <level> map to Responses API reasoning.effort. Default thinking level is high. off maps to minimal because Muse Spark does not accept none.

Docs

See docs/providers/meta.md for setup, onboarding, and smoke tests.

Live test

export MODEL_API_KEY=<key>
pnpm test:live -- extensions/meta/meta.live.test.ts

Live tests call muse-spark-1.1 on /v1/responses.