Disclosure summary
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 2.10.0 until 2.53.0, streamed requests made through ConcurrencyLimitedModel or limit_model_concurrency can retain shared concurrency slots because anyio.CapacityLimiter associates an acquired slot with the borrowing task while streaming cleanup can run in a different task. Early stream termination, cancellation, consumer exceptions, or complete stream_text() consumption with debounce_by=0.1 can therefore leave capacity occupied, eventually preventing later requests that share the long-lived limiter from proceeding and causing a denial of service. Agent-level max_concurrency and non-streaming model requests are not affected. This issue is fixed in version 2.53.0.
Source-reported weakness categories
CWE-772
Source-specific records & product guidance
Sources retain their own attribution and scoring. Follow the original record to confirm affected versions, fixed releases, and configuration conditions.
NIST National Vulnerability Database · NVD-CVE-2026-107286
Open original source · Updated Oct 08, 2026
Only CPE matches marked vulnerable=true are indexed. AND/OR platform conditions must be checked in the original NVD record.
GitHub Reviewed Security Advisories · GHSA-6fqq-452j-qhrp
Open original source · Updated Oct 08, 2026
Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early
Source severity: HIGH / 0
| Ecosystem | Package | Affected range | First patched |
|---|---|---|---|
| pip | pydantic-ai | >= 2.10.0, < 2.53.0 | 2.53.0 |
| pip | pydantic-ai-slim | >= 2.10.0, < 2.53.0 | 2.53.0 |
Original records & references
PUBLISHED 2026-10-08T11:17:40-04:00
MODIFIED 2026-10-08T16:35:31-04:00
INGESTED 2026-10-10T20:55:03-04:00