The model reads a PNG/JPEG/WebP/GIF file, the bytes commit through the durable attachment lifecycle, and the tool result carries the real ImageBlock so the image enters context from the next request onward. FileSystem gains a bounded readBytes primitive (local + E2B providers); registration is conditional on the attachment store, and a strict execution gate refuses routes that do not declare image input, so a text route's durable history stays free of image blocks. llm-replay models may declare inputModalities, letting keyless ACP snapshots pin both the sha256-referenced success and the verbatim refusal. Supersedes the withdrawn route-scoped design of PR #598; the decision record is .agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md.
15 lines
253 B
JSON
15 lines
253 B
JSON
{
|
|
"steps": [
|
|
{
|
|
"op": "initialize"
|
|
},
|
|
{
|
|
"op": "newSession"
|
|
},
|
|
{
|
|
"op": "prompt",
|
|
"text": "Use read_image to look at red.png in the current directory, then reply with exactly the single word DONE."
|
|
}
|
|
]
|
|
}
|