extensions/llm-task/README.md
Adds an optional agent tool llm-task for running JSON-only LLM tasks
(drafting, summarizing, classifying) with optional JSON Schema validation.
Designed to be called from workflow engines (for example, Lobster via
openclaw.invoke --each) without adding new OpenClaw code per workflow.
{
"plugins": {
"entries": {
"llm-task": { "enabled": true }
}
}
}
optional: true):{
"agents": {
"list": [
{
"id": "main",
"tools": { "allow": ["llm-task"] }
}
]
}
}
{
"plugins": {
"entries": {
"llm-task": {
"enabled": true,
"config": {
"defaultProvider": "openai-codex",
"defaultModel": "gpt-5.2",
"defaultAuthProfileId": "main",
"allowedModels": ["openai-codex/gpt-5.2"],
"maxTokens": 800,
"timeoutMs": 30000
}
}
}
}
}
allowedModels is an allowlist of provider/model strings. If set, any request
outside the list is rejected.
prompt (string, required)input (any, optional)schema (object, optional JSON Schema)provider (string, optional)model (string, optional)thinking (string, optional)authProfileId (string, optional)temperature (number, optional)maxTokens (number, optional)timeoutMs (number, optional)Returns details.json containing the parsed JSON (and validates against
schema when provided).
This extension depends on OpenClaw internal modules (the embedded agent runner).
It is intended to ship as a bundled OpenClaw extension (like lobster) and
be enabled via plugins.entries + tool allowlists.
It is not currently designed to be copied into
~/.openclaw/extensions as a standalone plugin directory.