Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

LLM nodes

nodes:
  llm_fix_lint:
    kind: llm
    model: auto
    prompt_file: .definitively/prompts/fix-lint.md
    timeout_ms: 3600000
    command:
      - cursor-agent
      - agent
      - --force
      - --workspace
      - "."
      - --print
      - --output-format
      - stream-json
      - --
    outcome:
      success:
        - jq: '.status == "ok"'
        - signal: fix_complete
      failure:
        - timeout: true
        - signal: refused

Fields

FieldRequiredDescription
kindyesMust be llm
prompt_fileyesPath to markdown prompt (relative to workspace root)
commandyesargv prefix for the LLM runner; prompt appended after --
modelnoModel hint passed to runner
timeout_msnoSession timeout
outcomeyesOften uses jq on stream JSON and signal predicates

Prompt files

Store prompts under .definitively/prompts/. Reference them by path in prompt_file.

The dev quality loop uses one prompt per fix step (fix-lint.md, fix-test.md, etc.).

Try it: Copy prompts/example.md from templates and wire a minimal LLM node (use stub runner in dev if no agent installed).