Get task-scoped brand context
brand_contextSelect a task-scoped brand context for writing in brand voice. Returns governed rules relevant to the specific task type and audience.
Instructions
Select a task-scoped brand context from the compiled runtime. THE tool to call first when the user says 'write this in our voice', 'write this LinkedIn post in our brand voice', 'make an on-brand social graphic', or 'build a landing page' — it returns only the governed rules relevant to that task instead of the full runtime. Deterministic: task_type maps to sections via a fixed table, audience matches governed personas exactly or reports no-match — no inference. Returns data.context (the selected brand slices), matched_selectors (what was chosen and why), and no_governed_match. NOT for reading the entire runtime (use brand_runtime) or checking finished content (use brand_check).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| budget | No | 'standard' returns the selected sections in full. 'compact' returns identity colors/typography plus hard rules only (anti-patterns + never_say) — for tight sub-agent contexts. | standard |
| channel | No | Optional channel label (e.g. 'LinkedIn'). Recorded in matched_selectors for the agent; does not alter governed rules. | |
| audience | No | Optional audience label (e.g. 'security leaders'). Matched against governed persona names by normalized substring — an explicit no-match is returned rather than guessing. | |
| task_type | Yes | What is being created. Deterministically selects runtime sections: visual tasks (code-ui, image-graphic) get identity+visual; copy tasks (blog-article, email, video-script) get voice+strategy; mixed tasks get both. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | ||
| context | No | ||
| approval | No | ||
| _metadata | Yes | ||
| matched_selectors | No | ||
| no_governed_match | No |