Problem
The replay proxy's GET /models response advertises vision support but does not declare capabilities.limits.vision.max_prompt_images. Saved image conversations can require two image-bearing messages: an attached blob and a subsequent image-view result.
When a runtime applies a one-image fallback for the omitted capability, these histories no longer match the strict replay snapshots. The proxy reports a missing cached response rather than completing the attachment or model-vision scenario.
Affected scenarios include both SessionConfigE2ETests.Should_Accept_Blob_Attachments and SessionE2ETests.Should_Accept_Blob_Attachments, plus SessionConfigE2ETests.Vision_Disabled_Then_Enabled_Via_SetModel.
Expected behavior
The fake catalog should explicitly support the image capacity required by its recorded conversations. Keep the original attachment and vision assertions, saved histories, and strict replay matching intact.
An explicit two-image capacity resolves these scenarios. A harness-only fix and HTTP endpoint regression coverage are prepared; no product change or retry is needed.
Generated by Copilot
Problem
The replay proxy's
GET /modelsresponse advertises vision support but does not declarecapabilities.limits.vision.max_prompt_images. Saved image conversations can require two image-bearing messages: an attached blob and a subsequent image-view result.When a runtime applies a one-image fallback for the omitted capability, these histories no longer match the strict replay snapshots. The proxy reports a missing cached response rather than completing the attachment or model-vision scenario.
Affected scenarios include both
SessionConfigE2ETests.Should_Accept_Blob_AttachmentsandSessionE2ETests.Should_Accept_Blob_Attachments, plusSessionConfigE2ETests.Vision_Disabled_Then_Enabled_Via_SetModel.Expected behavior
The fake catalog should explicitly support the image capacity required by its recorded conversations. Keep the original attachment and vision assertions, saved histories, and strict replay matching intact.
An explicit two-image capacity resolves these scenarios. A harness-only fix and HTTP endpoint regression coverage are prepared; no product change or retry is needed.
Generated by Copilot