scout_report
Generate the final markdown report with findings, page quality scores, role matrix, and an explicit gap ledger; gates by level so extensive reports refuse while untested gaps remain.
Instructions
Generate the final markdown report — findings, page quality scores (worst first), role capability matrix, oracle rollup, and the GAP LEDGER (an explicit list of what was NOT tested). Writes the full document to .scenescout/report.md and returns a bounded SUMMARY (full reports exceed client token limits). Gates by level: 'minimal' needs all routes visited + ≥1 design audit; 'medium' additionally needs several routes audited; 'extensive' REFUSES while the gap ledger is non-empty — that refusal is the completeness guarantee: an extensive report only generates when nothing known is left untested. force=true overrides (only when the user capped the budget).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | Generate even though gates are unmet (only when the user capped the budget) | |
| level | No | Which completion contract to enforce — match the level the run was asked for | medium |
| report | No | Which parts the report carries. 'both' (default): the Summary first — what was checked, when, for how long and how carefully, what was found, the problems as a table with their impact (blocks users, annoying, cosmetic), then each problem folded with its numbered steps, what was expected and what happened — then the Evidence (each problem's picture and the frames recorded before it, only when there is one), then the technical details, folded. 'qa': the Summary and the Evidence alone, for a tester or anyone not technical. 'dev': the technical report alone, unfolded. report.html adds the steps every session took, folded, whichever is chosen. It applies to the files this call writes; the live view always shows both. | both |
| history | No | How much of the history to print. 'index' lists findings from earlier runs, and resolved ones, as a row each: id, severity, age, title. 'full' prints every one in full as before — on one project that was 1.75 MB against 113 KB, nearly half of it findings already fixed. Use 'full' when handing the document to someone who has no access to the memory. | index |
| session | No | Target this session directly instead of the active one — pass it explicitly when dispatching to MULTIPLE sessions in one turn (e.g. two scout_click calls with different `session`), which then run CONCURRENTLY rather than queueing. Omit for single-session sequential use. |