feat: chat uploads, vision turn isolation, and MindSpace agent improvements

Add chat file/image upload UX, attachment proxying, vision thumbnails, and per-turn image scoping so agents only use the current upload. Extend MindSpace asset context, billing token state, OA/scenario verify scripts, and related runtime config.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
john
2026-07-11 00:23:01 +08:00
parent e3063ea806
commit 32fb2cdeaf
51 changed files with 4588 additions and 186 deletions
+10
View File
@@ -19,6 +19,7 @@ import {
snapshotPublicHtml,
verifyPageAccess,
verifySurveyDelivery,
verifyChildrenHobbyDietSurvey,
waitForAssistantGrowth,
waitForRunTerminal,
extractAssistantTexts,
@@ -200,6 +201,15 @@ async function runScenario(scenario, port) {
});
}
if (step.expect?.surveyDietUpdate) {
await verifyChildrenHobbyDietSurvey({
publishKey,
baseUrl,
reporter,
testInsert: step.expect.testInsert !== false,
});
}
const forbidReply = step.expect?.forbidReplyPatterns ?? [];
for (const pattern of forbidReply) {
if (pattern && reply.combined.includes(pattern)) {