openclaw/docs/providers/meta.md at codex/qa417-cli-selected-context-owner

mirror of https://github.com/openclaw/openclaw.git synced 2026-08-02 09:41:37 +00:00

Files

Vincent Koc c892a712e6 feat(plugins): externalize Cohere and Meta providers (#116662 )

* feat(plugins): externalize Cohere and Meta providers

* docs(changelog): note provider externalization

* chore: keep changelog release-owned

2026-07-31 12:53:01 +08:00

4.0 KiB

Raw Permalink Blame History

summary, title, read_when

summary

title

read_when

Meta setup (auth + muse-spark-1.1 model selection)

Property	Value
Provider id	`meta`
Plugin	`@openclaw/meta-provider`
Auth env var	`MODEL_API_KEY`
Onboarding flag	`--auth-choice meta-api-key`
Direct CLI flag	`--meta-api-key <key>`
API	Responses API (`openai-responses`)
Base URL	`https://api.meta.ai/v1`
Default model	`meta/muse-spark-1.1`
Default reasoning	`high` (`reasoning.effort`)

Getting started

```bash openclaw plugins install @openclaw/meta-provider openclaw gateway restart ```

openclaw onboard --auth-choice meta-api-key

openclaw onboard --non-interactive --accept-risk \
  --auth-choice meta-api-key \
  --meta-api-key "$MODEL_API_KEY"

export MODEL_API_KEY=<key>

</CodeGroup>

```bash openclaw models list --provider meta ```

Lists the static `muse-spark-1.1` catalog entry. If `MODEL_API_KEY` is unresolved,
`openclaw models status --json` reports the missing credential under
`auth.unusableProfiles`.

Non-interactive setup

openclaw onboard --non-interactive --accept-risk \
  --mode local \
  --auth-choice meta-api-key \
  --meta-api-key "$MODEL_API_KEY"

Built-in catalog

Model ref	Name	Input	Reasoning	Context window	Max output	Input / cached input / output per 1M tokens
`meta/muse-spark-1.1`	Muse Spark 1.1	text, image	yes	1,048,576	131,072	$1.25 / $0.15 / $4.25

Capabilities:

Text and image input
Tool calling and streaming
Reasoning effort: minimal, low, medium, high, xhigh (default: high)
Stateless encrypted reasoning replay (store: false, include: ["reasoning.encrypted_content"])

`muse-spark-1.1` does not accept `reasoning.effort: "none"`. OpenClaw maps `--thinking off` to `minimal` for this provider.

Manual config

{
  env: { MODEL_API_KEY: "<key>" },
  agents: {
    defaults: {
      model: { primary: "meta/muse-spark-1.1" },
      models: {
        "meta/muse-spark-1.1": { alias: "Muse Spark 1.1" },
      },
    },
  },
}

If the Gateway runs as a daemon (launchd, systemd, Docker), make sure `MODEL_API_KEY` is available to that process — for example in `~/.openclaw/.env` or through `env.shellEnv`. A key exported only in an interactive shell will not help a managed service unless the env is imported separately.

Smoke test

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

Live tests use muse-spark-1.1 against POST /v1/responses.

Choosing providers, model refs, and failover behavior. Reasoning effort levels for muse-spark-1.1. Agent defaults and model configuration.

4.0 KiB Raw Permalink Blame History