Skip to main content

Context Management

Strongly agents handle arbitrarily long conversations without exceeding the model's context limit. You pick the strategy at build time and adjust later in Agent Settings → Context Policy.

Three policies, plus two knobs. That's the whole set.

Pick a policy

Window

Keep the most recent turns; drop older turns once the budget is hit.

  • Cost: lowest.
  • Recall: lowest. The agent won't remember turns it dropped.
  • Pick this for: short conversational agents, support triage, one-shot Q&A.

Summarise

Keep a rolling summary of older turns plus the most recent turns verbatim.

  • Cost: medium — one summarisation pass when the budget tightens.
  • Recall: good. Decisions made earlier survive into the summary.
  • Pick this for: personal assistants, long threads, anything where earlier context matters later. This is Iris's default.

Hierarchical

Three tiers — recent turns verbatim, older turns summarised, oldest turns reduced to titles.

  • Cost: highest.
  • Recall: best.
  • Pick this for: research assistants and multi-day operational threads.

The two knobs

KnobWhat it doesSensible default
Token budgetHard cap on the conversation history sent to the model on each turn.70 % of your model's context window
Keep recentThe minimum number of recent turns retained verbatim, regardless of policy.12–20

The wizard auto-fills the token budget based on the primary model you picked. You can override.

When edits take effect

Context-policy changes need an agent redeploy. The Settings page surfaces the Apply changes button when a redeploy is needed.

See also