Events changedapi/beta/sessions/events
Nearest release: v2.1.247, published under 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+45added
Lines−3removed
From line
66
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits26to this page, all time
The whole hunk
from line 66, old and new numbered
/
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 66
6666
6767 - `string`
6868
69 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
69 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
7070
7171 - `"message-batches-2024-09-24"`
7272
from line 136
136136
137137 - `"mid-conversation-tool-changes-2026-07-01"`
138138
139 - `"compact-2026-01-12"`
140
141 - `"computer-use-2025-11-24"`
142
143 - `"mcp-tunnels-2026-06-22"`
144
145 - `"structured-outputs-2025-11-13"`
146
147 - `"task-budgets-2026-03-13"`
148
149 - `"thinking-display-updates-2026-08-18"`
150
151 - `"ce-user-management-2026-07-13"`
152
139153### Returns
140154
141155- `data: optional array of BetaManagedAgentsSessionEvent`
from line 2341
23272341
23282342 - `string`
23292343
2330 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
2344 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
23312345
23322346 - `"message-batches-2024-09-24"`
23332347
from line 2411
23972411
23982412 - `"mid-conversation-tool-changes-2026-07-01"`
23992413
2414 - `"compact-2026-01-12"`
2415
2416 - `"computer-use-2025-11-24"`
2417
2418 - `"mcp-tunnels-2026-06-22"`
2419
2420 - `"structured-outputs-2025-11-13"`
2421
2422 - `"task-budgets-2026-03-13"`
2423
2424 - `"thinking-display-updates-2026-08-18"`
2425
2426 - `"ce-user-management-2026-07-13"`
2427
24002428### Body parameters
24012429
24022430- `events: array of BetaManagedAgentsEventParams`
from line 3306
32783306
32793307 - `string`
32803308
3281 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
3309 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
32823310
32833311 - `"message-batches-2024-09-24"`
32843312
from line 3376
33483376
33493377 - `"mid-conversation-tool-changes-2026-07-01"`
33503378
3379 - `"compact-2026-01-12"`
3380
3381 - `"computer-use-2025-11-24"`
3382
3383 - `"mcp-tunnels-2026-06-22"`
3384
3385 - `"structured-outputs-2025-11-13"`
3386
3387 - `"task-budgets-2026-03-13"`
3388
3389 - `"thinking-display-updates-2026-08-18"`
3390
3391 - `"ce-user-management-2026-07-13"`
3392
33513393### Returns
33523394
33533395- `BetaManagedAgentsStreamSessionEvents = BetaManagedAgentsUserMessageEvent or BetaManagedAgentsUserInterruptEvent or BetaManagedAgentsUserToolConfirmationEvent or 34 more`
from line 9333
92919333
92929334 - `result: string`
92939335
9294 Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the session goes idle, but no further evaluation runs. 'failed': grader determined the rubric does not apply to the deliverables. 'interrupted': user sent an interrupt while evaluation was in progress.
9295
9296 - `type: "span.outcome_evaluation_end"`
9297
9298 - `usage: BetaManagedAgentsSpanModelUsage`
9299
9300 Token usage for a single model request.
9301
9302 - `cache_creation_input_tokens: number`
9303
9304 Tokens used to create prompt cache in this request.
9305
9306 format: int32
9307
9308 - `cache_read_input_tokens: number`
9309
9310 Tokens read from prompt cache in this request.
9311
9312 format: int32
9313
9314 - `input_tokens: number`
9315
9316 Input tokens consumed by this request.
9317
9318 format: int32
9319
9320 - `output_tokens: number`
9321
9322 Output tokens generated by this request.
9323
9324 form
9336 Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the s
No line in this hunk matches that.