ai.report

Write a report about a bundle of results -- Markdown with charts and named statistics -- for viz.report_html to render. Numbers in the text are computed by the renderer, never written by the model.

Kind: standard
Network: yes
Secrets: llm (optional) -- see Secrets

Inputs🔗

Name	Type	Required	Default	Description
`bundle`	directory	yes		A base.bundle output: the tables, figures and results to report on.
`description`	string	yes		What the artifact should do, in plain language.
`model`	string	yes		Model identifier, exactly as the provider names it (e.g. claude-opus-5-5).
`provider`	string	no	`anthropic`	Who serves the model. The key is the block's `llm` secret. One of `anthropic`, `openai`, `openai_compatible`.
`base_url`	string	no	blank	Endpoint for an OpenAI-compatible server (vLLM, Ollama, Azure, a gateway). Leave blank for the provider's own API.
`share`	string	no	`schema`	How much of the data the model may see. Column names are always sent; summary statistics reveal values; samples send rows. Everything sent is recorded in the provenance output. One of `schema`, `summary`, `samples`.
`max_turns`	number	no	`24`	Model calls before the block gives up.
`max_tokens`	number	no	`400000`	Input plus output tokens across all calls, billed to your key.
`nonce`	string	no	blank	Change to generate afresh with nothing else changed; the block ignores its value.

Outputs🔗

Name	Type	Description
`report`	directory	report.md, specs/ and stats.json.
`provenance`	json	Every tool result sent to the model, the model and endpoint used, and token usage.

Example🔗

- id: "@report"
  name: ai.report
  inputs: [{block: "@bundle", output: bundle, as: bundle}]
  args:
    description: 'A short report on the plots: count, mean biomass, and the map.'
    provider: anthropic
    model: claude-opus-5-5
  secrets:
    llm: my-anthropic-key