doesitsupport

← all clients

GitHub Copilot CLI

Category: cli · Last checked: 2026-07-04 · Tested version: 1.0.68

Capability support

FeatureStatusNotes
Image renderingunsupported2026-07-04T14:54:21.844ZTool was called and the model echoed the probe's call-id back to the user — but a terminal/code-exec surface can't render images or iframes. Default unsupported.
Animated GIFunsupported2026-07-04T14:54:29.545ZTool was called and the model echoed the probe's call-id back to the user — but a terminal/code-exec surface can't render images or iframes. Default unsupported.
SVGunsupported2026-07-04T14:54:37.127ZTool was called and the model echoed the probe's call-id back to the user — but a terminal/code-exec surface can't render images or iframes. Default unsupported.
HEICunsupported2026-07-04T14:54:44.933ZTool was called and the model echoed the probe's call-id back to the user — but a terminal/code-exec surface can't render images or iframes. Default unsupported.
MCP Apps HTML widgetunsupported2026-07-04T14:54:53.091ZTool was called and the model echoed the probe's call-id back to the user — but a terminal/code-exec surface can't render images or iframes. Default unsupported.
ChatGPT Apps SDK componentunsupported2026-07-04T14:55:01.645ZTool was called and the model echoed the probe's call-id back to the user — but a terminal/code-exec surface can't render images or iframes. Default unsupported.
Markdown: basicsupported2026-07-04T14:55:09.311ZMarkdown content was returned and the model echoed it (including the call-id) back to the user.
Markdown: tablespartial2026-07-04T14:55:17.814ZTool was called and the model echoed the probe's call-id — but behavioral can't tell whether the client actually rendered the markdown variant (table/code/math/diagram/image/task/URL) vs. surfaced the source. Prefer vision-tier for a definitive answer.
Markdown: code blockspartial2026-07-04T14:55:25.482ZTool was called and the model echoed the probe's call-id — but behavioral can't tell whether the client actually rendered the markdown variant (table/code/math/diagram/image/task/URL) vs. surfaced the source. Prefer vision-tier for a definitive answer.
Markdown: imagespartial2026-07-04T14:55:33.558ZTool was called and the model echoed the probe's call-id — but behavioral can't tell whether the client actually rendered the markdown variant (table/code/math/diagram/image/task/URL) vs. surfaced the source. Prefer vision-tier for a definitive answer.
Markdown: task listspartial2026-07-04T14:55:41.425ZTool was called and the model echoed the probe's call-id — but behavioral can't tell whether the client actually rendered the markdown variant (table/code/math/diagram/image/task/URL) vs. surfaced the source. Prefer vision-tier for a definitive answer.
URL autolinkingpartial2026-07-04T14:55:49.130ZTool was called and the model echoed the probe's call-id — but behavioral can't tell whether the client actually rendered the markdown variant (table/code/math/diagram/image/task/URL) vs. surfaced the source. Prefer vision-tier for a definitive answer.
MCP resourcessupported2026-07-04T15:43:26.550ZThe model's reply quoted the render token that exists only in the resource content block's body — the client surfaced the resource.
MCP prompt templatesunknown2026-07-04T14:56:05.309ZMCP protocol feature; behavioral classifier can't determine rendering — defer to vision or manual review.
MCP elicitationunsupported2026-07-04T15:42:55.046ZClient did not declare the elicitation capability during MCP initialize.
MCP samplingunsupported2026-07-04T15:43:05.285ZClient did not declare the sampling capability during MCP initialize.
MCP structured contentsupported2026-07-04T15:43:15.838ZThe model's reply referenced fields that exist only in the structuredContent payload — the client fed structured content to the model.