Follow Discord
Sweep 25 Sep 2026 · 19:33Z Build v2.1.283 504 read Stable v2.1.274 Latest v2.1.283 Next v2.1.283 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

Create a Message changedapi/messages/create

Nearest release: v2.1.282, published an hour before 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+78added
Lines−0removed
From line 1,197 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits13to this page, all time

The whole hunk

from line 1197, old and new numbered
/
lines
from line 1197
11971197 
11981198 - `string`
11991199 
1200- `diagnostics: optional DiagnosticsParam or null`
1201 
1202 Request-level diagnostics. Currently carries the previous response
1203 id for prompt-cache divergence reporting.
1204 
1205 - `previous_message_id: optional string or null`
1206 
1207 The `id` (`msg_...`) from this client's previous /v1/messages response. The server compares that request's prompt fingerprint against this one and returns `diagnostics.cache_miss_reason` when the prompt-cache prefix could not be reused. Pass `null` on the first turn to opt in without a prior message to compare.
1208 
1209 maxLength: 256
1210 
12001211- `inference_geo: optional string or null`
12011212 
12021213 Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used.
from line 3873
38623873 
38633874 - `file_id: string`
38643875 
3876 - `diagnostics: Diagnostics or null`
3877 
3878 Request-level diagnostics: why the prompt cache could not fully reuse
3879 the prefix of the request named by `diagnostics.previous_message_id`.
3880 
3881 - `cache_miss_reason: CacheMissReason or null`
3882 
3883 Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed.
3884 
3885 - `CacheMissModelChanged object`
3886 
3887 - `type: "model_changed"`
3888 
3889 default: model_changed
3890 
3891 - `cache_missed_input_tokens: number`
3892 
3893 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
3894 
3895 - `CacheMissSystemChanged object`
3896 
3897 - `type: "system_changed"`
3898 
3899 default: system_changed
3900 
3901 - `cache_missed_input_tokens: number`
3902 
3903 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
3904 
3905 - `CacheMissToolsChanged object`
3906 
3907 - `type: "tools_changed"`
3908 
3909 default: tools_changed
3910 
3911 - `cache_missed_input_tokens: number`
3912 
3913 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
3914 
3915 - `CacheMissMessagesChanged object`
3916 
3917 - `type: "messages_changed"`
3918 
3919 default: messages_changed
3920 
3921 - `cache_missed_input_tokens: number`
3922 
3923 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
3924 
3925 - `CacheMissPreviousMessageNotFound object`
3926 
3927 - `type: "previous_message_not_found"`
3928 
3929 default: previous_message_not_found
3930 
3931 - `CacheMissUnavailable object`
3932 
3933 - `type: "unavailable"`
3934 
3935 default: unavailable
3936 
38653937 - `model: Model`
38663938 
38673939 The model that will complete your prompt.
from line 4478
44064478 "type": "text"
44074479 }
44084480 ],
4481 "diagnostics": {
4482 "cache_miss_reason": {
4483 "cache_missed_input_tokens": 0,
4484 "type": "model_changed"
4485 }
4486 },
44094487 "model": "claude-opus-5",
44104488 "role": "assistant",
44114489 "stop_details": {
Feedback