lightflow-llm-generate

# LightFlow LLM Generate Use `lightflow.llm_generate` for deterministic offline mock text generation. Provider-backed RIG workflows can still declare `lightflow.llm_generate` without the builtin mock engine. ## Workflow - Workflow id: `lightflow.llm_generate` - Runtime ownership: this workflow crate owns its public `execute()` entry and exposes it through the `lightflow-llm-generate-runner` package binary. - Host engine: `package.command.v1`; discovery, help, and plan do not execute package source. - Input values are validated against their declared JSON types without string coercion. - Runtime: `lightflow.llm.generate`, engine `builtin.llm.mock.v1`. - Input `prompt`: required prompt text. - Input `model`: optional mock model name. - Outputs `text` and `response`. ## Usage ```bash lfw run lightflow.llm_generate -i prompt='hello' -i model=mock ``` ## API Usage Start `lfw serve`, then call the workflow through the shared HTTP run contract. Adjust `inputs` to match the workflow contract above. ```bash curl -sS -X POST http://127.0.0.1:5174/workflows/lightflow.llm_generate/run \ -H 'content-type: application/json' \ -d '{"inputs":{}}' ```