vrr/openclaw
2
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-08-22 07:15:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 17
openclaw/extensions/meta
History
Exact
Peter Steinberger 430c293ee0
refactor: remove duplicate provider and runtime code (#115529) 
* refactor: remove duplicated runtime and provider code

* refactor: exclude unrelated browser test cleanup

* refactor: preserve canonical subagent cleanup ordering
2026-07-29 00:04:52 -04:00
..
api.ts refactor(providers): shared manifest row builder and fleet default-model adoption (#113879) 2026-07-25 15:00:02 -07:00
index.test.ts refactor(providers): shared manifest row builder and fleet default-model adoption (#113879) 2026-07-25 15:00:02 -07:00
index.ts refactor(providers): derive simple providers from manifests (#114331) 2026-07-27 01:29:53 -04:00
meta.live.test.ts refactor: reduce plugin SDK test import overhead (#109333) 2026-07-16 13:55:23 -07:00
models.ts refactor(providers): shared manifest row builder and fleet default-model adoption (#113879) 2026-07-25 15:00:02 -07:00
onboard.ts refactor: remove duplicate provider and runtime code (#115529) 2026-07-29 00:04:52 -04:00
openclaw.plugin.json refactor(providers): shared manifest row builder and fleet default-model adoption (#113879) 2026-07-25 15:00:02 -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.