Pydantic AI OpenTelemetry instrumentation: retry prompt content is not redacted when `include_content=False`
pydantic-ai · pydantic-ai-slim
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| pydantic-ai PyPI |
|
|
| pydantic-ai-slim PyPI |
|
pydantic-ai · pydantic-ai-slim
| Product | Affected | Fixed in |
|---|---|---|
| pydantic-ai PyPI |
|
|
| pydantic-ai-slim PyPI |
|
|
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.3.4 until 1.107.4 and 2.27.1, OpenTelemetry instrumentation configured with InstrumentationSettings(include_content=False) can export retry prompts outside tool calls in gen_ai.input.messages and pydantic_ai.all_messages. Agents using NativeOutput, PromptedOutput, or output validators on text output can therefore disclose validation feedback, including invalid model values quoted by that feedback, to readers of the telemetry backend. Tool-call retries and deployments that do not use include_content=False are not affected by this specific path. This issue is fixed in versions 1.107.4 and 2.27.1.
From the CVE record · GitHub_M
When OpenTelemetry instrumentation uses InstrumentationSettings(include_content=False), retry prompts outside tool calls can be exported in telemetry. Agents using NativeOutput, PromptedOutput, or output validators on text output can disclose validation feedback, including quoted invalid model values, to readers of the telemetry backend.
Check deployments using PyPI pydantic-ai or pydantic-ai-slim versions >=0.3.4 and <1.107.4, or >=2.0.0b1 and <2.27.1.