Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.308 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 22 Oct 2026
One change · api

Messages changedapi/compliance/apps/chats/messages

Nearest release: v2.1.309, published 2 hours after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+22added
Lines−6removed
From line 163 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits14to this page, all time

The whole hunk

from line 163, old and new numbered
/
lines
from line 163
163163 
164164 default: text
165165 
166 - `added_as_context: boolean`
167 
168 True when this text block was added to a human message as context for the assistant: the user did not type it in the message box. The wording of the app's own notes for the assistant is not exported: such a block has an empty `text`. Other added text is exported and can include content that the user or their app chose. False does not mean that the user typed the text. Always false on the last text block of a message, on assistant messages, and on messages sent before 2026-10-09, whose notes are exported in full.
169 
170 default: false
171 
166172 - `text: string`
167173 
168174 Text content from human or assistant
from line 175
169175 
170176 - `thinking_redacted: boolean`
171177 
172 True when content enclosed in the assistant's internal-reasoning tags (or the tag markup itself) was removed from `text` during export. Removal never occurs with this field false. Always false on human messages, whose text is exported verbatim.
178 True when content enclosed in the assistant's internal-reasoning tags (or the tag markup itself) was removed from `text` during export. Removal never occurs with this field false. Always false on human messages.
173179 
174180 default: false
175181 
from line 438
432438 "type": "text",
433439 "text": "Can you help me draft requirements for our new dashboard feature?",
434440 "truncated": false,
435 "thinking_redacted": false
441 "thinking_redacted": false,
442 "added_as_context": false
436443 }
437444 ],
438445 "files": [
from line 462
455462 "type": "text",
456463 "text": "I'd be happy to help you draft requirements for your dashboard feature...",
457464 "truncated": false,
458 "thinking_redacted": false
465 "thinking_redacted": false,
466 "added_as_context": false
459467 }
460468 ],
461469 "artifacts": [
from line 484
476484 "type": "text",
477485 "text": "Are there any open support tickets about the dashboard?",
478486 "truncated": false,
479 "thinking_redacted": false
487 "thinking_redacted": false,
488 "added_as_context": false
480489 }
481490 ]
482491 },
from line 522
513522 "type": "text",
514523 "text": "There are two open tickets: one about slow loading and one about a missing export button.",
515524 "truncated": false,
516 "thinking_redacted": false
525 "thinking_redacted": false,
526 "added_as_context": false
517527 }
518528 ]
519529 }
from line 581
571581 
572582 default: text
573583 
584 - `added_as_context: boolean`
585 
586 True when this text block was added to a human message as context for the assistant: the user did not type it in the message box. The wording of the app's own notes for the assistant is not exported: such a block has an empty `text`. Other added text is exported and can include content that the user or their app chose. False does not mean that the user typed the text. Always false on the last text block of a message, on assistant messages, and on messages sent before 2026-10-09, whose notes are exported in full.
587 
588 default: false
589 
574590 - `text: string`
575591 
576592 Text content from human or assistant
from line 593
577593 
578594 - `thinking_redacted: boolean`
579595 
580 True when content enclosed in the assistant's internal-reasoning tags (or the tag markup itself) was removed from `text` during export. Removal never occurs with this field false. Always false on human messages, whose text is exported verbatim.
596 True when content enclosed in the assistant's internal-reasoning tags (or the tag markup itself) was removed from `text` during export. Removal never occurs with this field false. Always false on human messages.
581597 
582598 default: false
583599 
Feedback