Tuning Stele
Stele works well out of the box, and most people never touch a setting. But when you want to steer it, here are the dials and what each one changes. They all live in the project's settings in the dashboard.
Auto-RAG, the retrieval layer
Auto-RAG is what decides which prior knowledge gets injected before your agent answers. The defaults are tuned to stay out of the way; the settings let you change how much it pulls and from where. One setting, every surface: what you tune here governs your coding agent, the assistant in the app, and the graph search alike.
- Preview before you commit. Type a prompt and see exactly what Auto-RAG would inject for it, side by side: the default behavior next to your customized one , so you're tuning against real output.
- Tune the two stages. Retrieval runs in stages: a full-text and semantic search that finds the starting nodes, then a walk out across the graph. You can adjust how aggressively each stage contributes, and reset to the defaults in one click.
- Pause it. When you want a clean slate for a few turns, say a tangent unrelated to the project's history, you can pause injection without changing any settings.
The fastest way to tune is to paste a prompt you actually use into the preview and adjust until the injected set looks right. The numbers mean less than what they surface for the prompts you care about.
When retrieval gets slow
Auto-RAG runs before your agent sees your prompt, so it holds the prompt open while it works. To stop a slow network from turning that into a long wait, it works to a time budget. If the budget runs out mid-walk, it injects the nodes that matched your prompt directly and skips the ones it would have reached by walking out along their edges. You still get context, just less of it.
That trade-off is easy to miss, because a degraded run looks exactly like a healthy one from the outside, because the agent still answers. So run stele doctor. It reports how long injection has actually been taking, and tells you when it has been quietly cutting itself short:
A hook that always succeeds and always takes nine seconds is still broken, so slowness is reported as a problem in its own right, alongside outright errors. If you need a tighter or looser ceiling than the default, set STELE_AUTORAG_BUDGET_MS in the environment your agent runs in.
Lowering the budget below what retrieval actually needs doesn't make it faster. It makes every prompt pay the new ceiling and return less context. Check stele doctor before and after, and watch whether the semantic-recall warning appears.
Deduplication
As a record grows, the same fact sometimes gets written twice in slightly different words. The dedupe view scans for near-duplicate clusters and lets you resolve each: pick the one to keep, and the others merge into it, their links rewired onto the survivor and a pointer left behind, so nothing that referenced the old node breaks. It's a review surface, not an automatic shredder: you approve every merge.
Topics
Topics are the lightweight tags that cut across components. Over a project's life their vocabulary drifts: perf and performance end up as two tags for one idea. The topics settings list every topic with its count and let you rename one or merge several into a single canonical tag, so the cross-cutting view stays clean.
Notifications
Control which emails Stele sends you. The non-essential categories, a weekly digest and product news, are yours to switch off; account and security messages stay on, because they're about access to your own data. The same page keeps a history of every email we've sent you, as a plain audit log you can scroll back through.