Adovo

Applied AI

An agent memory limit can cut a reasoning response in half

Test how OpenAI Agents SDK session limits trim reasoning and message items before long-lived agents reach production.

November 18, 2026

A session that stays small can still fail on its next turn. In an open Agents SDK issue, a reporter found that SessionSettings(limit=N) could retain a message while dropping its paired reasoning item, leading to an API 400 in the reported SDK version. The session guide describes the limit as an item count. That distinction matters when one logical response spans multiple items.

Reproduce the boundary, not just a short chat

Use the exact SDK and model planned for deployment. Create enough turns to cross the session limit, including tool calls and responses with reasoning items. Then inspect the items sent on the next request. A five-turn demo can miss a defect that appears only when the oldest item is trimmed.

Preserve complete response units

Treat an assistant response and its required companion items as a unit when deciding what history to keep. If your implementation cannot guarantee that, use a higher limit or a summarization boundary that emits a valid new turn. Test both after a tool call and after an interrupted run. Do not assume that increasing the number alone permanently solves growth.

Make the failure visible

Record the configured limit, SDK version, item types, and failing request identifier in an internal trace, without storing sensitive message content unnecessarily. An API 400 after many successful turns should lead to a session-integrity check before a model outage diagnosis.

Adovo’s view

Memory budgets are protocol decisions. A smaller history is useful only when the remaining conversation is still structurally valid.

Continue exploring

Applied AI

LangGraphAgent Reliability

A cancelled LangGraph dev run may still finish its work

Test late cancellation in LangGraph's in-memory dev runtime and bound side effects inside long-running nodes.

Read more

Applied AI

LangGraphAgent Reliability

A LangGraph Postgres checkpoint read can scan old blob versions

Investigate checkpoint read latency that grows with a thread’s history in the JavaScript Postgres saver.

Read more

Applied AI

LangGraphAgent Reliability

A LangGraph SQLite filter can select the wrong large integer

Protect agent memory lookups that filter integer IDs above 2^53 in LangGraph SQLite store.

Read more
Explore applied AI services →