Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · api

Sessions changed

api/beta/sessions

Nearest release: v2.1.258, published an hour 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+253added
Lines−67removed
From line 14 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits12to this page, all time

The whole hunk

from line 14, old and new numbered
/
lines

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 14
1414 
1515 - `string`
1616 
17 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
17 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
1818 
1919 - `"message-batches-2024-09-24"`
2020 
from line 98
9898 
9999 - `"ce-user-management-2026-07-13"`
100100 
101 - `"mid-conversation-output-config-2026-07-01"`
102 
103 - `"thinking-binding-controls-2026-08-01"`
104 
105 - `"mid-conversation-system-clear-at-2026-08-21"`
106 
101107### Body parameters
102108 
103109- `agent: string or BetaManagedAgentsAgentParams or BetaManagedAgentsAgentWithOverridesParams`
from line 164
158164 
159165 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
160166 
161 - `BetaManagedAgentsModel = "claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more or string`
167 - `BetaManagedAgentsModel = "claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more or string`
162168 
163169 The model that will power your agent.
164170 
165171 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
166172 
167 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
173 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
168174 
169175 The model that will power your agent.
170176 
171177 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
172178 
179 - `"claude-fable-5-1"`
180 
181 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
182 
173183 - `"claude-sonnet-5"`
174184 
175185 High-performance model for coding and agents
from line 1108
10981108 
10991109 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
11001110 
1101 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
1111 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
11021112 
11031113 The model that will power your agent.
11041114 
11051115 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
11061116 
1117 - `"claude-fable-5-1"`
1118 
1119 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
1120 
11071121 - `"claude-sonnet-5"`
11081122 
11091123 High-performance model for coding and agents
from line 1666
16521666 
16531667 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`
16541668 
1655 Per-outcome evaluation state. One entry per define_outcome event sent to the session.
1669 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.
16561670 
16571671 - `completed_at: string or null`
16581672 
from line 1680
16661680 
16671681 - `explanation: string or null`
16681682 
1669 Grader's verdict text from the most recent evaluation. For satisfied, explains why criteria are met; for needs_revision (intermediate), what's missing; for failed, why unrecoverable.
1683 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.
16701684 
16711685 - `iteration: number`
16721686 
from line 1808
17941808 
17951809 - `active_seconds: optional number`
17961810 
1797 Cumulative time in seconds the session spent in running status. Excludes idle time.
1811 Cumulative time in seconds the session spent in `running` status. Excludes idle time.
17981812 
17991813 format: double
18001814 
from line 2135
21212135 
21222136- `agent_version: optional number`
21232137 
2124 Filter by agent version. Only applies when agent_id is also set.
2138 Filter by agent version. Only applies when `agent_id` is also set.
21252139 
21262140 format: int32
21272141 
from line 2179
21652179 
21662180- `memory_store_id: optional string`
21672181 
2168 Filter sessions whose resources contain a memory_store with this memory store ID.
2182 Filter sessions whose resources contain a `memory_store` with this memory store ID.
21692183 
21702184- `order: optional "asc" or "desc"`
21712185 
2172 Sort direction for results, ordered by created_at. Defaults to desc (newest first).
2186 Sort direction for results, ordered by `created_at`. Defaults to `desc` (newest first).
21732187 
21742188 - `"asc"`
21752189 
from line 2213
21992213 
22002214 - `string`
22012215 
2202 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
2216 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
22032217 
22042218 - `"message-batches-2024-09-24"`
22052219 
from line 2297
22832297 
22842298 - `"ce-user-management-2026-07-13"`
22852299 
2300 - `"mid-conversation-output-config-2026-07-01"`
2301 
2302 - `"thinking-binding-controls-2026-08-01"`
2303 
2304 - `"mid-conversation-system-clear-at-2026-08-21"`
2305 
22862306### Returns
22872307 
22882308- `data: optional array of BetaManagedAgentsSession`
from line 2337
23172337 
23182338 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
23192339 
2320 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
2340 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
23212341 
23222342 The model that will power your agent.
23232343 
23242344 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
23252345 
2346 - `"claude-fable-5-1"`
2347 
2348 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
2349 
23262350 - `"claude-sonnet-5"`
23272351 
23282352 High-performance model for coding and agents
from line 2895
28712895 
28722896 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`
28732897 
2874 Per-outcome evaluation state. One entry per define_outcome event sent to the session.
2898 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.
28752899 
28762900 - `completed_at: string or null`
28772901 
from line 2909
28852909 
28862910 - `explanation: string or null`
28872911 
2888 Grader's verdict text from the most recent evaluation. For satisfied, explains why criteria are met; for needs_revision (intermediate), what's missing; for failed, why unrecoverable.
2912 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.
28892913 
28902914 - `iteration: number`
28912915 
from line 3037
30133037 
30143038 - `active_seconds: optional number`
30153039 
3016 Cumulative time in seconds the session spent in running status. Excludes idle time.
3040 Cumulative time in seconds the session spent in `running` status. Excludes idle time.
30173041 
30183042 format: double
30193043 
from line 3376
33523376 
33533377 - `string`
33543378 
3355 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
3379 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
33563380 
33573381 - `"message-batches-2024-09-24"`
33583382 
from line 3460
34363460 
34373461 - `"ce-user-management-2026-07-13"`
34383462 
3463 - `"mid-conversation-output-config-2026-07-01"`
3464 
3465 - `"thinking-binding-controls-2026-08-01"`
3466 
3467 - `"mid-conversation-system-clear-at-2026-08-21"`
3468 
34393469### Returns
34403470 
34413471- `BetaManagedAgentsSession object`
from line 3500
34703500 
34713501 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
34723502 
3473 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
3503 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
34743504 
34753505 The model that will power your agent.
34763506 
34773507 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
34783508 
3509 - `"claude-fable-5-1"`
3510 
3511 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
3512 
34793513 - `"claude-sonnet-5"`
34803514 
34813515 High-performance model for coding and agents
from line 4058
40244058 
40254059 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`
40264060 
4027 Per-outcome evaluation state. One entry per define_outcome event sent to the session.
4061 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.
40284062 
40294063 - `completed_at: string or null`
40304064 
from line 4072
40384072 
40394073 - `explanation: string or null`
40404074 
4041 Grader's verdict text from the most recent evaluation. For satisfied, explains why criteria are met; for needs_revision (intermediate), what's missing; for failed, why unrecoverable.
4075 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.
40424076 
40434077 - `iteration: number`
40444078 
from line 4200
41664200 
41674201 - `active_seconds: optional number`
41684202 
4169 Cumulative time in seconds the session spent in running status. Excludes idle time.
4203 Cumulative time in seconds the session spent in `running` status. Excludes idle time.
41704204 
41714205 format: double
41724206 
from line 4525
44914525 
44924526 - `string`
44934527 
4494 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
4528 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
44954529 
44964530 - `"message-batches-2024-09-24"`
44974531 
from line 4609
45754609 
45764610 - `"ce-user-management-2026-07-13"`
45774611 
4612 - `"mid-conversation-output-config-2026-07-01"`
4613 
4614 - `"thinking-binding-controls-2026-08-01"`
4615 
4616 - `"mid-conversation-system-clear-at-2026-08-21"`
4617 
45784618### Body parameters
45794619 
45804620- `agent: optional BetaManagedAgentsSessionAgentUpdate`
from line 5089
50495089 
50505090 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
50515091 
5052 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
5092 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
50535093 
50545094 The model that will power your agent.
50555095 
50565096 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
50575097 
5098 - `"claude-fable-5-1"`
5099 
5100 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
5101 
50585102 - `"claude-sonnet-5"`
50595103 
50605104 High-performance model for coding and agents
from line 5647
56035647 
56045648 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`
56055649 
5606 Per-outcome evaluation state. One entry per define_outcome event sent to the session.
5650 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.
56075651 
56085652 - `completed_at: string or null`
56095653 
from line 5661
56175661 
56185662 - `explanation: string or null`
56195663 
5620 Grader's verdict text from the most recent evaluation. For satisfied, explains why criteria are met; for needs_revision (intermediate), what's missing; for failed, why unrecoverable.
5664 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.
56215665 
56225666 - `iteration: number`
56235667 
from line 5789
57455789 
57465790 - `active_seconds: optional number`
57475791 
5748 Cumulative time in seconds the session spent in running status. Excludes idle time.
5792 Cumulative time in seconds the session spent in `running` status. Excludes idle time.
57495793 
57505794 format: double
57515795 
from line 6118
60746118 
60756119 - `string`
60766120 
6077 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
6121 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
60786122 
60796123 - `"message-batches-2024-09-24"`
60806124 
from line 6202
61586202 
61596203 - `"ce-user-management-2026-07-13"`
61606204 
6205 - `"mid-conversation-output-config-2026-07-01"`
6206 
6207 - `"thinking-binding-controls-2026-08-01"`
6208 
6209 - `"mid-conversation-system-clear-at-2026-08-21"`
6210 
61616211### Returns
61626212 
61636213- `BetaManagedAgentsDeletedSession object`
from line 6255
62056255 
62066256 - `string`
62076257 
6208 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
6258 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
62096259 
62106260 - `"message-batches-2024-09-24"`
62116261 
from line 6339
62896339 
62906340 - `"ce-user-management-2026-07-13"`
62916341 
6342 - `"mid-conversation-output-config-2026-07-01"`
6343 
6344 - `"thinking-binding-controls-2026-08-01"`
6345 
6346 - `"mid-conversation-system-clear-at-2026-08-21"`
6347 
62926348### Returns
62936349 
62946350- `BetaManagedAgentsSession object`
from line 6379
63236379 
63246380 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
63256381 
6326 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
6382 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
63276383 
63286384 The model that will power your agent.
63296385 
63306386 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
63316387 
6388 - `"claude-fable-5-1"`
6389 
6390 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
6391 
63326392 - `"claude-sonnet-5"`
63336393 
63346394 High-performance model for coding and agents
from line 6937
68776937 
68786938 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`
68796939 
6880 Per-outcome evaluation state. One entry per define_outcome event sent to the session.
6940 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.
68816941 
68826942 - `completed_at: string or null`
68836943 
from line 6951
68916951 
68926952 - `explanation: string or null`
68936953 
6894 Grader's verdict text from the most recent evaluation. For satisfied, explains why criteria are met; for needs_revision (intermediate), what's missing; for failed, why unrecoverable.
6954 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.
68956955 
68966956 - `iteration: number`
68976957 
from line 7079
70197079 
70207080 - `active_seconds: optional number`
70217081 
7022 Cumulative time in seconds the session spent in running status. Excludes idle time.
7082 Cumulative time in seconds the session spent in `running` status. Excludes idle time.
70237083 
70247084 format: double
70257085 
from line 7479
74197479 
74207480 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
74217481 
7422 - `BetaManagedAgentsModel = "claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more or string`
7482 - `BetaManagedAgentsModel = "claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more or string`
74237483 
74247484 The model that will power your agent.
74257485 
74267486 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
74277487 
7428 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
7488 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
74297489 
74307490 The model that will power your agent.
74317491 
74327492 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
74337493 
7494 - `"claude-fable-5-1"`
7495 
7496 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
7497 
74347498 - `"claude-sonnet-5"`
74357499 
74367500 High-performance model for coding and agents
from line 8425
83618425 
83628426- `BetaManagedAgentsOutcomeEvaluationResource object`
83638427 
8364 Evaluation state for a single outcome defined via a define_outcome event.
8428 Evaluation state for a single outcome defined via a `define_outcome` event.
83658429 
83668430 - `completed_at: string or null`
83678431 
from line 8439
83758439 
83768440 - `explanation: string or null`
83778441 
8378 Grader's verdict text from the most recent evaluation. For satisfied, explains why criteria are met; for needs_revision (intermediate), what's missing; for failed, why unrecoverable.
8442 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.
83798443 
83808444 - `iteration: number`
83818445 
from line 8509
84458509 
84468510 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
84478511 
8448 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
8512 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
84498513 
84508514 The model that will power your agent.
84518515 
84528516 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
84538517 
8518 - `"claude-fable-5-1"`
8519 
8520 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
8521 
84548522 - `"claude-sonnet-5"`
84558523 
84568524 High-performance model for coding and agents
from line 9067
89999067 
90009068 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`
90019069 
9002 Per-outcome evaluation state. One entry per define_outcome event sent to the session.
9070 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.
90039071 
90049072 - `completed_at: string or null`
90059073 
from line 9081
90139081 
90149082 - `explanation: string or null`
90159083 
9016 Grader's verdict text from the most recent evaluation. For satisfied, explains why criteria are met; for needs_revision (intermediate), what's missing; for failed, why unrecoverable.
9084 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.
90179085 
90189086 - `iteration: number`
90199087 
from line 9209
91419209 
91429210 - `active_seconds: optional number`
91439211 
9144 Cumulative time in seconds the session spent in running status. Excludes idle time.
9212 Cumulative time in seconds the session spent in `running` status. Excludes idle time.
91459213 
91469214 format: double
91479215 
from line 9341
92739341 
92749342 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
92759343 
9276 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
9344 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
92779345 
92789346 The model that will power your agent.
92799347 
92809348 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
92819349 
9350 - `"claude-fable-5-1"`
9351 
9352 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
9353 
92829354 - `"claude-sonnet-5"`
92839355 
92849356 High-performance model for coding and agents
from line 9395
93239395 
93249396 Powerful intelligence for long-running agents and coding
93259397 
9326 - `"claude-sonnet-4-5"`
9327 
9328 High-performance model for agents and coding
9329 
9330 - `"claude-sonnet-4-5-20250929"`
9331 
9332 High-performance model for agents and coding
9333 
9334 - `string`
9335 
9336 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
9337 
9338 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
9339 
9340 - `BetaManagedAgentsEffortLow object`
9341 
9342 Low effort. Favors latency over reasoning depth.
9343 
9344 - `type: "low"`
9345 
9346 - `BetaManagedAgentsEffortMedium object`
9347 
9348 Medium effort. Balances latency and reasoning depth.
9349 
9350 - `type: "medium"`
9351 
9352 - `BetaManagedAgentsEffortHigh object`
9353 
9354 High effort. Favors reasoning depth.
9355 
9356 - `type: "high"`
9357 
9358 - `BetaManagedAgentsEffortXhigh object`
9359 
9360 Extra-high effort. Not all models accept this level.
9361 
9362 - `type: "xhigh"`
9363 
9364 - `BetaManagedAgentsEffortMax object`
9365 
9366 Maximum effort. Favors reasoning depth over latency.
9367 
9368 - `type: "max"`
9369 
9370 - `inference_geo: optional string`
9371 
9372 Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
9373 
9374 - `speed: optional "standard" or "fast"`
9375 
9376 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time.
9377 
9378 - `"standard"`
9379 
9380 - `"fast"`
9381 
9382 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
9383 
9384 Resolved coordinator topology with full agent definitions for each roster member.
9385 
9386 - `agents: array of BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`
9387 
9388 Full `agent` definitions the coordinator may spawn as session threads.
9389 
9390 - `BetaManagedAgentsSessionThreadAgent object`
9391 
9392 Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`.
9393 
9394 - `id: string`
9395 
9396 - `description: string or null`
9397 
9398 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
9399 
9400 - `name: string`
9401 
9402 - `type: "url"`
9403 
9404 - `url: string`
9405 
9406 - `model: BetaManagedAgentsModelConfig`
9407 
9408 Model identifier and configuration.
9409 
9410 
9398 - `"claude-sonnet-4-5