The whole hunk
from line 79, old and new numbered
/
lines
from line 79
7979
8080 Message identifier, prefixed `clsm_`. Stable for as long as the message's turn is retained: identifiers of retained turns do not change as older turns age out of the organization's retention period. The `retention_elapsed` placeholder's identifier is distinct from every retained turn's and changes only when further turns age out.
8181
82 - `content: array of object or object or object`
82 - `content: array of Text or ToolUse or ToolResult`
8383
8484 Content blocks within the message, discriminated on `type` (`text` / `tool_use` / `tool_result`: the same discriminator values as the claude.ai chat-messages endpoint; the tool variants omit `integration_name` and `mcp_server_url`, and `text` carries `truncated`). Extended-thinking content is never included. The request's `system` field is never included; a presence-only marker message is emitted when it was set. The request's `tools[]` definitions are never included as transcript messages. Project-level instructions (such as CLAUDE.md files) appear in the message stream as a user-role context block and are included. Empty when `provenance.type` is `content_unavailable`.
8585
from line 175
175175
176176 The model that served this assistant turn, as reported in the `model` field of the underlying Messages API response. Null on user messages and on any assistant message whose `provenance` is set: client-asserted history and synthetic markers were not produced by a model during this session, and for unavailable content the serving model is not known.
177177
178 - `provenance: object or object or object or null`
178 - `provenance: ContentUnavailable or ClientAsserted or SyntheticMarker or null`
179179
180180 Where this turn's content came from, discriminated on `type`. Null (the common case) means verified content: on an assistant message, content Claude produced during this session; on a user message, content the user sent. `content_unavailable`: the turn's content cannot be returned and `content` is empty; `reason` says why. `client_asserted`: assistant content the client supplied as conversation history; `content` shows what the model received but its authorship is not verified; never on user-role messages. `synthetic_marker`: a transcript marker the endpoint generated rather than content either party sent during the session. Both `client_asserted` and `synthetic_marker` can result from normal request or client processing, not only client modification. Callers should tolerate unrecognized `type` values.
181181