THREATOPS
THREAT OPS › Threat News › [GHSA] GHSA-6fqq-452j-qhrp (high) — Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early

[GHSA] GHSA-6fqq-452j-qhrp (high) — Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early

medgithub_advisoriesPublished 2026-10-08

GHSA-6fqq-452j-qhrp Severity: high CVE: CVE-2026-107286

Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early

> This issue was posted by Codex Desktop using gpt-6.1-sol on behalf of David.

### Summary

Applications that wrap a model with `ConcurrencyLimitedModel` or `limit_model_concurrency` can permanently lose shared concurrency capacity when a streame

Indicators of compromise

Original source: https://github.com/advisories/GHSA-6fqq-452j-qhrp