generate_architecture_insight
Produce architectural trade-offs, risks, patterns, and recommendations by analyzing project code activity. Apply filters to refine analysis and address specific questions.
Instructions
Generate an architecture insight: trade-offs, risks, patterns and recommendations inferred from the project's code activity (requires a connected code source – github, gitlab, bitbucket or azure_devops). This is the deepest and most expensive insight (it runs extended reasoning). Use for technical review of architectural direction. Runs synchronously and returns Markdown. Consumes credits, charged once on success. Call list_filter_options before using filters.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| filters | No | Per-source advanced filters, AND-combined across dimensions. Keys MUST be source ids (an unknown source id is rejected with 400). The dimension VALUES are matched leniently – call list_filter_options first to get the real selectable values for the project rather than guessing. | |
| sources | No | Restrict to these source ids. Unknown ids are rejected with 400. | |
| max_events | No | Cap on events processed (1-1000, default 250). | |
| project_id | Yes | Project id from list_projects to generate the insight for. | |
| lookback_days | No | Days of history to review (1-365, default 14). | |
| focus_question | No | A specific architectural question or component to investigate (e.g. "is the billing layer coupled to providers?"). |