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 capture · api

One read of Claude Developer Platformapi-20260925T153714Z

310 pages moved out of 637 read.

Pages moved 310 significant first
Pages read 637 in this capture
Captured 15:37 UTC
Corpus hash 850f99a0d461 corpus-hash

What this read moved

51-75 of 310, page 3 of 13

This capture is too large to show at once. Changes 51-75 of 310 are below, significant first; the rest are on the following screens.

api/beta/models Changed · +28 / -36 lines

from line 29
2929 
3030 Defaults to `20`. Ranges from `1` to `1000`.
3131 
32 default: 20, maximum: 1000, minimum: 1
32 default: 20, minimum: 1, maximum: 1000
3333 
3434### Headers
3535 
from line 165
165165 
166166 - `capabilities: BetaModelCapabilities or null`
167167 
168 Model capability information.
168 Object mapping capability names to their support details. Keys are always present for all known capabilities.
169169 
170170 - `batch: BetaCapabilitySupport`
171171 
from line 185
185185 
186186 - `compaction: BetaCompactionCapability or null`
187187 
188 Compaction capability details: whether the model accepts the top-level
189 `compaction` request parameter, with one entry per supported
190 `compaction.type` value.
188 Server-side compaction support (the top-level `compaction` parameter) and the accepted `compaction.type` values.
191189 
192190 - `summarize: BetaCapabilitySupport`
193191 
from line 201
203201 
204202 - `clear_thinking_20251015: BetaCapabilitySupport or null`
205203 
206 Indicates whether a capability is supported.
204 Whether the clear_thinking_20251015 strategy is supported.
207205 
208206 - `clear_tool_uses_20250919: BetaCapabilitySupport or null`
209207 
210 Indicates whether a capability is supported.
208 Whether the clear_tool_uses_20250919 strategy is supported.
211209 
212210 - `compact_20260112: BetaCapabilitySupport or null`
213211 
214 Indicates whether a capability is supported.
212 Whether the compact_20260112 strategy is supported.
215213 
216214 - `supported: boolean`
217215 
from line 241
243241 
244242 - `xhigh: BetaCapabilitySupport or null`
245243 
246 Indicates whether a capability is supported.
244 Whether the model supports xhigh effort level.
247245 
248246 - `image_input: BetaCapabilitySupport`
249247 
from line 551
553551 
554552 - `capabilities: BetaModelCapabilities or null`
555553 
556 Model capability information.
554 Object mapping capability names to their support details. Keys are always present for all known capabilities.
557555 
558556 - `batch: BetaCapabilitySupport`
559557 
from line 571
573571 
574572 - `compaction: BetaCompactionCapability or null`
575573 
576 Compaction capability details: whether the model accepts the top-level
577 `compaction` request parameter, with one entry per supported
578 `compaction.type` value.
574 Server-side compaction support (the top-level `compaction` parameter) and the accepted `compaction.type` values.
579575 
580576 - `summarize: BetaCapabilitySupport`
581577 
from line 587
591587 
592588 - `clear_thinking_20251015: BetaCapabilitySupport or null`
593589 
594 Indicates whether a capability is supported.
590 Whether the clear_thinking_20251015 strategy is supported.
595591 
596592 - `clear_tool_uses_20250919: BetaCapabilitySupport or null`
597593 
598 Indicates whether a capability is supported.
594 Whether the clear_tool_uses_20250919 strategy is supported.
599595 
600596 - `compact_20260112: BetaCapabilitySupport or null`
601597 
602 Indicates whether a capability is supported.
598 Whether the compact_20260112 strategy is supported.
603599 
604600 - `supported: boolean`
605601 
from line 627
631627 
632628 - `xhigh: BetaCapabilitySupport or null`
633629 
634 Indicates whether a capability is supported.
630 Whether the model supports xhigh effort level.
635631 
636632 - `image_input: BetaCapabilitySupport`
637633 
from line 810
814810 
815811 - `clear_thinking_20251015: BetaCapabilitySupport or null`
816812 
817 Indicates whether a capability is supported.
813 Whether the clear_thinking_20251015 strategy is supported.
818814 
819815 - `supported: boolean`
820816 
from line 818
822818 
823819 - `clear_tool_uses_20250919: BetaCapabilitySupport or null`
824820 
825 Indicates whether a capability is supported.
821 Whether the clear_tool_uses_20250919 strategy is supported.
826822 
827823 - `compact_20260112: BetaCapabilitySupport or null`
828824 
829 Indicates whether a capability is supported.
825 Whether the compact_20260112 strategy is supported.
830826 
831827 - `supported: boolean`
832828 
from line 860
864860 
865861 - `xhigh: BetaCapabilitySupport or null`
866862 
867 Indicates whether a capability is supported.
863 Whether the model supports xhigh effort level.
868864 
869865### Beta Model Capabilities
870866 
from line 886
890886 
891887 - `compaction: BetaCompactionCapability or null`
892888 
893 Compaction capability details: whether the model accepts the top-level
894 `compaction` request parameter, with one entry per supported
895 `compaction.type` value.
889 Server-side compaction support (the top-level `compaction` parameter) and the accepted `compaction.type` values.
896890 
897891 - `summarize: BetaCapabilitySupport`
898892 
from line 902
908902 
909903 - `clear_thinking_20251015: BetaCapabilitySupport or null`
910904 
911 Indicates whether a capability is supported.
905 Whether the clear_thinking_20251015 strategy is supported.
912906 
913907 - `clear_tool_uses_20250919: BetaCapabilitySupport or null`
914908 
915 Indicates whether a capability is supported.
909 Whether the clear_tool_uses_20250919 strategy is supported.
916910 
917911 - `compact_20260112: BetaCapabilitySupport or null`
918912 
919 Indicates whether a capability is supported.
913 Whether the compact_20260112 strategy is supported.
920914 
921915 - `supported: boolean`
922916 
from line 942
948942 
949943 - `xhigh: BetaCapabilitySupport or null`
950944 
951 Indicates whether a capability is supported.
945 Whether the model supports xhigh effort level.
952946 
953947 - `image_input: BetaCapabilitySupport`
954948 
from line 998
1004998 
1005999 - `capabilities: BetaModelCapabilities or null`
10061000 
1007 Model capability information.
1001 Object mapping capability names to their support details. Keys are always present for all known capabilities.
10081002 
10091003 - `batch: BetaCapabilitySupport`
10101004 
from line 1018
10241018 
10251019 - `compaction: BetaCompactionCapability or null`
10261020 
1027 Compaction capability details: whether the model accepts the top-level
1028 `compaction` request parameter, with one entry per supported
1029 `compaction.type` value.
1021 Server-side compaction support (the top-level `compaction` parameter) and the accepted `compaction.type` values.
10301022 
10311023 - `summarize: BetaCapabilitySupport`
10321024 
from line 1034
10421034 
10431035 - `clear_thinking_20251015: BetaCapabilitySupport or null`
10441036 
1045 Indicates whether a capability is supported.
1037 Whether the clear_thinking_20251015 strategy is supported.
10461038 
10471039 - `clear_tool_uses_20250919: BetaCapabilitySupport or null`
10481040 
1049 Indicates whether a capability is supported.
1041 Whether the clear_tool_uses_20250919 strategy is supported.
10501042 
10511043 - `compact_20260112: BetaCapabilitySupport or null`
10521044 
1053 Indicates whether a capability is supported.
1045 Whether the compact_20260112 strategy is supported.
10541046 
10551047 - `supported: boolean`
10561048 
from line 1074
10821074 
10831075 - `xhigh: BetaCapabilitySupport or null`
10841076 
1085 Indicates whether a capability is supported.
1077 Whether the model supports xhigh effort level.
10861078 
10871079 - `image_input: BetaCapabilitySupport`
10881080 

api/beta/models/list Changed · +7 / -9 lines

from line 27
2727 
2828 Defaults to `20`. Ranges from `1` to `1000`.
2929 
30 default: 20, maximum: 1000, minimum: 1
30 default: 20, minimum: 1, maximum: 1000
3131 
3232## Headers
3333 
from line 163
163163 
164164 - `capabilities: BetaModelCapabilities or null`
165165 
166 Model capability information.
166 Object mapping capability names to their support details. Keys are always present for all known capabilities.
167167 
168168 - `batch: BetaCapabilitySupport`
169169 
from line 183
183183 
184184 - `compaction: BetaCompactionCapability or null`
185185 
186 Compaction capability details: whether the model accepts the top-level
187 `compaction` request parameter, with one entry per supported
188 `compaction.type` value.
186 Server-side compaction support (the top-level `compaction` parameter) and the accepted `compaction.type` values.
189187 
190188 - `summarize: BetaCapabilitySupport`
191189 
from line 199
201199 
202200 - `clear_thinking_20251015: BetaCapabilitySupport or null`
203201 
204 Indicates whether a capability is supported.
202 Whether the clear_thinking_20251015 strategy is supported.
205203 
206204 - `clear_tool_uses_20250919: BetaCapabilitySupport or null`
207205 
208 Indicates whether a capability is supported.
206 Whether the clear_tool_uses_20250919 strategy is supported.
209207 
210208 - `compact_20260112: BetaCapabilitySupport or null`
211209 
212 Indicates whether a capability is supported.
210 Whether the compact_20260112 strategy is supported.
213211 
214212 - `supported: boolean`
215213 
from line 239
241239 
242240 - `xhigh: BetaCapabilitySupport or null`
243241 
244 Indicates whether a capability is supported.
242 Whether the model supports xhigh effort level.
245243 
246244 - `image_input: BetaCapabilitySupport`
247245 

api/beta/models/retrieve Changed · +6 / -8 lines

from line 151
151151 
152152 - `capabilities: BetaModelCapabilities or null`
153153 
154 Model capability information.
154 Object mapping capability names to their support details. Keys are always present for all known capabilities.
155155 
156156 - `batch: BetaCapabilitySupport`
157157 
from line 171
171171 
172172 - `compaction: BetaCompactionCapability or null`
173173 
174 Compaction capability details: whether the model accepts the top-level
175 `compaction` request parameter, with one entry per supported
176 `compaction.type` value.
174 Server-side compaction support (the top-level `compaction` parameter) and the accepted `compaction.type` values.
177175 
178176 - `summarize: BetaCapabilitySupport`
179177 
from line 187
189187 
190188 - `clear_thinking_20251015: BetaCapabilitySupport or null`
191189 
192 Indicates whether a capability is supported.
190 Whether the clear_thinking_20251015 strategy is supported.
193191 
194192 - `clear_tool_uses_20250919: BetaCapabilitySupport or null`
195193 
196 Indicates whether a capability is supported.
194 Whether the clear_tool_uses_20250919 strategy is supported.
197195 
198196 - `compact_20260112: BetaCapabilitySupport or null`
199197 
200 Indicates whether a capability is supported.
198 Whether the compact_20260112 strategy is supported.
201199 
202200 - `supported: boolean`
203201 
from line 227
229227 
230228 - `xhigh: BetaCapabilitySupport or null`
231229 
232 Indicates whether a capability is supported.
230 Whether the model supports xhigh effort level.
233231 
234232 - `image_input: BetaCapabilitySupport`
235233 

api/beta/organization Changed · +52 / -76 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 125
125125 
126126 Defaults to `20`. Ranges from `1` to `1000`.
127127 
128 default: 20, maximum: 1000, minimum: 1
128 default: 20, minimum: 1, maximum: 1000
129129 
130130- `status: optional "active" or "archived" or "expired" or "inactive"`
131131 
from line 510
510510 
511511 Name of the API key.
512512 
513 maxLength: 500, minLength: 1
513 minLength: 1, maxLength: 500
514514 
515515- `status: optional "active" or "archived" or "inactive" or null`
516516 
from line 751
751751 
752752 Human-friendly display name.
753753 
754 maxLength: 255, minLength: 1
754 minLength: 1, maxLength: 255
755755 
756756- `geo: optional "us"`
757757 
from line 911
911911 
912912 Number of results per page.
913913 
914 default: 20, maximum: 100, minimum: 1
914 default: 20, minimum: 1, maximum: 100
915915 
916916- `page: optional string`
917917 
from line 1222
12221222 
12231223 Human-friendly display name.
12241224 
1225 maxLength: 255, minLength: 1
1225 minLength: 1, maxLength: 255
12261226 
12271227- `geo: optional "us" or null`
12281228 
from line 1654
16541654 
16551655 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
16561656 
1657 maxLength: 255, minLength: 1
1657 minLength: 1, maxLength: 255
16581658 
16591659- `check_jti: optional boolean or null`
16601660 
from line 1714
17141714 
17151715 Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Defaults to 3600 (1h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected.
17161716 
1717 maximum: 176400, exclusiveMinimum: 0
1717 minimum: 1, maximum: 176400
17181718 
17191719#### Returns
17201720 
from line 1827
18271827 
18281828 - `poll_status: BetaFederationIssuerPollStatus or null`
18291829 
1830 Status of automatic JWKS polling for a federation issuer.
1830 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
18311831 
1832 Anthropic periodically fetches the issuer's signing keys in the
1833 background. These fields summarize the most recent fetches so the
1834 health of the JWKS endpoint can be monitored.
1835 
18361832 - `consecutive_failures: number`
18371833 
18381834 Consecutive fetch failures since the last success.
from line 1920
19241920 
19251921 Number of results per page.
19261922 
1927 default: 20, maximum: 100, minimum: 1
1923 default: 20, minimum: 1, maximum: 100
19281924 
19291925- `page: optional string`
19301926 
from line 2138
21422138 
21432139 - `poll_status: BetaFederationIssuerPollStatus or null`
21442140 
2145 Status of automatic JWKS polling for a federation issuer.
2141 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
21462142 
2147 Anthropic periodically fetches the issuer's signing keys in the
2148 background. These fields summarize the most recent fetches so the
2149 health of the JWKS endpoint can be monitored.
2150 
21512143 - `consecutive_failures: number`
21522144 
21532145 Consecutive fetch failures since the last success.
from line 2444
24522444 
24532445 - `poll_status: BetaFederationIssuerPollStatus or null`
24542446 
2455 Status of automatic JWKS polling for a federation issuer.
2447 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
24562448 
2457 Anthropic periodically fetches the issuer's signing keys in the
2458 background. These fields summarize the most recent fetches so the
2459 health of the JWKS endpoint can be monitored.
2460 
24612449 - `consecutive_failures: number`
24622450 
24632451 Consecutive fetch failures since the last success.
from line 2707
27192707 
27202708 Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected.
27212709 
2722 maximum: 176400, exclusiveMinimum: 0
2710 minimum: 1, maximum: 176400
27232711 
27242712- `name: optional string or null`
27252713 
27262714 Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
27272715 
2728 maxLength: 255, minLength: 1
2716 minLength: 1, maxLength: 255
27292717 
27302718#### Returns
27312719 
from line 2826
28382826 
28392827 - `poll_status: BetaFederationIssuerPollStatus or null`
28402828 
2841 Status of automatic JWKS polling for a federation issuer.
2829 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
28422830 
2843 Anthropic periodically fetches the issuer's signing keys in the
2844 background. These fields summarize the most recent fetches so the
2845 health of the JWKS endpoint can be monitored.
2846 
28472831 - `consecutive_failures: number`
28482832 
28492833 Consecutive fetch failures since the last success.
from line 3130
31463130 
31473131 - `poll_status: BetaFederationIssuerPollStatus or null`
31483132 
3149 Status of automatic JWKS polling for a federation issuer.
3133 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
31503134 
3151 Anthropic periodically fetches the issuer's signing keys in the
3152 background. These fields summarize the most recent fetches so the
3153 health of the JWKS endpoint can be monitored.
3154 
31553135 - `consecutive_failures: number`
31563136 
31573137 Consecutive fetch failures since the last success.
from line 3363
33833363 
33843364 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
33853365 
3386 maxLength: 255, minLength: 1
3366 minLength: 1, maxLength: 255
33873367 
33883368- `oauth_scope: string`
33893369 
from line 3403
34233403 
34243404 Lifetime in seconds for access tokens minted via this rule (60-86400). Defaults to 3600 (1h). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds.
34253405 
3426 maximum: 86400, minimum: 60
3406 minimum: 60, maximum: 86400
34273407 
34283408- `workspace_id: optional string or null`
34293409 
from line 3630
36503630 
36513631 Number of results per page.
36523632 
3653 default: 20, maximum: 100, minimum: 1
3633 default: 20, minimum: 1, maximum: 100
36543634 
36553635- `page: optional string`
36563636 
from line 4380
44004380 
44014381- `match: optional BetaFederationRuleMatch or null`
44024382 
4403 Does the incoming JWT qualify?
4383 Replaces the entire match object. All populated matcher fields must pass.
44044384 
4405 All populated fields must pass; omitted fields are skipped. At least one
4406 of `subject_prefix` (other than a wildcard-only value like `*`), `claims`,
4407 or `condition` is required; `audience` alone is not sufficient.
4408 
44094385 - `audience: optional string or null`
44104386 
44114387 Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default.
from line 4408
44324408 
44334409 Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
44344410 
4435 maxLength: 255, minLength: 1
4411 minLength: 1, maxLength: 255
44364412 
44374413- `oauth_scope: optional string or null`
44384414 
from line 4418
44424418 
44434419- `target: optional BetaServiceAccountTarget or null`
44444420 
4445 Bind to a fixed service account by ID.
4421 Replaces the entire target object. Currently always a `service_account` target.
44464422 
44474423 - `type: "service_account"`
44484424 
from line 4434
44584434 
44594435 Replaces the lifetime in seconds for access tokens minted via this rule (60-86400). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds.
44604436 
4461 maximum: 86400, minimum: 60
4437 minimum: 60, maximum: 86400
44624438 
44634439- `workspace_id: optional string or null`
44644440 
from line 5155
51795155 
51805156 Number of results per page.
51815157 
5182 default: 20, maximum: 100, minimum: 1
5158 default: 20, minimum: 1, maximum: 100
51835159 
51845160- `page: optional string`
51855161 
from line 5664
56885664 
56895665 Defaults to `20`. Ranges from `1` to `1000`.
56905666 
5691 default: 20, maximum: 1000, minimum: 1
5667 default: 20, minimum: 1, maximum: 1000
56925668 
56935669- `roles: optional array of string`
56945670 
from line 6091
61156091 
61166092 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
61176093 
6118 maxLength: 255, minLength: 1
6094 minLength: 1, maxLength: 255
61196095 
61206096- `description: optional string or null`
61216097 
from line 6224
62486224 
62496225 Number of results per page.
62506226 
6251 default: 20, maximum: 100, minimum: 1
6227 default: 20, minimum: 1, maximum: 100
62526228 
62536229- `page: optional string`
62546230 
from line 7330
73547330 
73557331 Number of results per page.
73567332 
7357 default: 20, maximum: 100, minimum: 1
7333 default: 20, minimum: 1, maximum: 100
73587334 
73597335- `page: optional string`
73607336 
from line 7705
77297705 
77307706 Defaults to `20`. Ranges from `1` to `1000`.
77317707 
7732 default: 20, maximum: 1000, minimum: 1
7708 default: 20, minimum: 1, maximum: 1000
77337709 
77347710- `roles: optional array of string`
77357711 
from line 8071
80958071 
80968072 Defaults to `20`. Ranges from `1` to `1000`.
80978073 
8098 default: 20, maximum: 1000, minimum: 1
8074 default: 20, minimum: 1, maximum: 1000
80998075 
81008076#### Returns
81018077 
from line 8338
83628338 
83638339 Name of the Workspace.
83648340 
8365 maxLength: 40, minLength: 1
8341 minLength: 1, maxLength: 40
83668342 
83678343- `data_residency: optional BetaDataResidencyCreateConfig or null`
83688344 
from line 8730
87548730 
87558731 Name of the Workspace.
87568732 
8757 maxLength: 40, minLength: 1
8733 minLength: 1, maxLength: 40
87588734 
87598735- `tags: optional map[string] or null`
87608736 
from line 9066
90909066 
90919067 When omitted, every remaining entry is returned in a single page and `next_page` is `null`.
90929068 
9093 maximum: 1000, minimum: 1
9069 minimum: 1, maximum: 1000
90949070 
90959071- `page: optional string`
90969072 
from line 9306
93309306 
93319307 Defaults to `20`. Ranges from `1` to `1000`.
93329308 
9333 default: 20, maximum: 1000, minimum: 1
9309 default: 20, minimum: 1, maximum: 1000
93349310 
93359311#### Returns
93369312 
from line 9708
97329708 
97339709 Number of results per page.
97349710 
9735 default: 20, maximum: 100, minimum: 1
9711 default: 20, minimum: 1, maximum: 100
97369712 
97379713- `page: optional string`
97389714 
from line 10506
1053010506Remove a service account from a workspace.
1053110507 
1053210508Removal is idempotent (returns 200 even if the membership was already
10533removed). A DELETE against the
10509removed). A DELETE against the im

api/beta/organization/analytics Changed · +4 / -4 lines

from line 930
930930 
931931 Number of rows per page (1-1000, default 20). One row per actor unless `group_by[]` or `bucket_width` splits an actor across rows; `cost_type`/`token_type` fan-out rows (cost endpoint only) are the exception — they do not count toward this limit, so `data` can exceed it.
932932 
933 default: 20, maximum: 1000, minimum: 1
933 default: 20, minimum: 1, maximum: 1000
934934 
935935- `models: optional array of string`
936936 
from line 1712
17121712 
17131713 Number of rows per page (1-1000, default 20). One row per actor unless `group_by[]` or `bucket_width` splits an actor across rows; `cost_type`/`token_type` fan-out rows (cost endpoint only) are the exception — they do not count toward this limit, so `data` can exceed it.
17141714 
1715 default: 20, maximum: 1000, minimum: 1
1715 default: 20, minimum: 1, maximum: 1000
17161716 
17171717- `models: optional array of string`
17181718 
from line 2377
23772377 
23782378 - `user: optional BetaAnalyticsUser or null`
23792379 
2380 A user in the organization, identified by tagged id and email address.
2380 The user this row describes. Null on rows aggregated across users.
23812381 
23822382 - `type: "user"`
23832383 
from line 3130
31303130 
31313131 - `created_by: optional BetaAnalyticsUser or null`
31323132 
3133 A user in the organization, identified by tagged id and email address.
3133 User who created the project. Null if the project was deleted before attribution was recorded, or if the creator's account no longer exists.
31343134 
31353135 - `type: "user"`
31363136 

api/beta/organization/external_keys Changed · +3 / -3 lines

from line 71
7171 
7272 Human-friendly display name.
7373 
74 maxLength: 255, minLength: 1
74 minLength: 1, maxLength: 255
7575 
7676- `geo: optional "us"`
7777 
from line 231
231231 
232232 Number of results per page.
233233 
234 default: 20, maximum: 100, minimum: 1
234 default: 20, minimum: 1, maximum: 100
235235 
236236- `page: optional string`
237237 
from line 542
542542 
543543 Human-friendly display name.
544544 
545 maxLength: 255, minLength: 1
545 minLength: 1, maxLength: 255
546546 
547547- `geo: optional "us" or null`
548548 

api/beta/organization/federation Changed · +18 / -42 lines

from line 143
143143 
144144 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
145145 
146 maxLength: 255, minLength: 1
146 minLength: 1, maxLength: 255
147147 
148148- `check_jti: optional boolean or null`
149149 
from line 203
203203 
204204 Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Defaults to 3600 (1h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected.
205205 
206 maximum: 176400, exclusiveMinimum: 0
206 minimum: 1, maximum: 176400
207207 
208208#### Returns
209209 
from line 316
316316 
317317 - `poll_status: BetaFederationIssuerPollStatus or null`
318318 
319 Status of automatic JWKS polling for a federation issuer.
319 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
320320 
321 Anthropic periodically fetches the issuer's signing keys in the
322 background. These fields summarize the most recent fetches so the
323 health of the JWKS endpoint can be monitored.
324 
325321 - `consecutive_failures: number`
326322 
327323 Consecutive fetch failures since the last success.
from line 409
413409 
414410 Number of results per page.
415411 
416 default: 20, maximum: 100, minimum: 1
412 default: 20, minimum: 1, maximum: 100
417413 
418414- `page: optional string`
419415 
from line 627
631627 
632628 - `poll_status: BetaFederationIssuerPollStatus or null`
633629 
634 Status of automatic JWKS polling for a federation issuer.
630 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
635631 
636 Anthropic periodically fetches the issuer's signing keys in the
637 background. These fields summarize the most recent fetches so the
638 health of the JWKS endpoint can be monitored.
639 
640632 - `consecutive_failures: number`
641633 
642634 Consecutive fetch failures since the last success.
from line 933
941933 
942934 - `poll_status: BetaFederationIssuerPollStatus or null`
943935 
944 Status of automatic JWKS polling for a federation issuer.
936 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
945937 
946 Anthropic periodically fetches the issuer's signing keys in the
947 background. These fields summarize the most recent fetches so the
948 health of the JWKS endpoint can be monitored.
949 
950938 - `consecutive_failures: number`
951939 
952940 Consecutive fetch failures since the last success.
from line 1196
12081196 
12091197 Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected.
12101198 
1211 maximum: 176400, exclusiveMinimum: 0
1199 minimum: 1, maximum: 176400
12121200 
12131201- `name: optional string or null`
12141202 
12151203 Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
12161204 
1217 maxLength: 255, minLength: 1
1205 minLength: 1, maxLength: 255
12181206 
12191207#### Returns
12201208 
from line 1315
13271315 
13281316 - `poll_status: BetaFederationIssuerPollStatus or null`
13291317 
1330 Status of automatic JWKS polling for a federation issuer.
1318 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
13311319 
1332 Anthropic periodically fetches the issuer's signing keys in the
1333 background. These fields summarize the most recent fetches so the
1334 health of the JWKS endpoint can be monitored.
1335 
13361320 - `consecutive_failures: number`
13371321 
13381322 Consecutive fetch failures since the last success.
from line 1619
16351619 
16361620 - `poll_status: BetaFederationIssuerPollStatus or null`
16371621 
1638 Status of automatic JWKS polling for a federation issuer.
1622 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
16391623 
1640 Anthropic periodically fetches the issuer's signing keys in the
1641 background. These fields summarize the most recent fetches so the
1642 health of the JWKS endpoint can be monitored.
1643 
16441624 - `consecutive_failures: number`
16451625 
16461626 Consecutive fetch failures since the last success.
from line 1852
18721852 
18731853 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
18741854 
1875 maxLength: 255, minLength: 1
1855 minLength: 1, maxLength: 255
18761856 
18771857- `oauth_scope: string`
18781858 
from line 1892
19121892 
19131893 Lifetime in seconds for access tokens minted via this rule (60-86400). Defaults to 3600 (1h). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds.
19141894 
1915 maximum: 86400, minimum: 60
1895 minimum: 60, maximum: 86400
19161896 
19171897- `workspace_id: optional string or null`
19181898 
from line 2119
21392119 
21402120 Number of results per page.
21412121 
2142 default: 20, maximum: 100, minimum: 1
2122 default: 20, minimum: 1, maximum: 100
21432123 
21442124- `page: optional string`
21452125 
from line 2869
28892869 
28902870- `match: optional BetaFederationRuleMatch or null`
28912871 
2892 Does the incoming JWT qualify?
2872 Replaces the entire match object. All populated matcher fields must pass.
28932873 
2894 All populated fields must pass; omitted fields are skipped. At least one
2895 of `subject_prefix` (other than a wildcard-only value like `*`), `claims`,
2896 or `condition` is required; `audience` alone is not sufficient.
2897 
28982874 - `audience: optional string or null`
28992875 
29002876 Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default.
from line 2897
29212897 
29222898 Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
29232899 
2924 maxLength: 255, minLength: 1
2900 minLength: 1, maxLength: 255
29252901 
29262902- `oauth_scope: optional string or null`
29272903 
from line 2907
29312907 
29322908- `target: optional BetaServiceAccountTarget or null`
29332909 
2934 Bind to a fixed service account by ID.
2910 Replaces the entire target object. Currently always a `service_account` target.
29352911 
29362912 - `type: "service_account"`
29372913 
from line 2923
29472923 
29482924 Replaces the lifetime in seconds for access tokens minted via this rule (60-86400). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds.
29492925 
2950 maximum: 86400, minimum: 60
2926 minimum: 60, maximum: 86400
29512927 
29522928- `workspace_id: optional string or null`
29532929 
from line 3644
36683644 
36693645 Number of results per page.
36703646 
3671 default: 20, maximum: 100, minimum: 1
3647 default: 20, minimum: 1, maximum: 100
36723648 
36733649- `page: optional string`
36743650 

api/beta/organization/federation/issuers Changed · +11 / -35 lines

from line 141
141141 
142142 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
143143 
144 maxLength: 255, minLength: 1
144 minLength: 1, maxLength: 255
145145 
146146- `check_jti: optional boolean or null`
147147 
from line 201
201201 
202202 Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Defaults to 3600 (1h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected.
203203 
204 maximum: 176400, exclusiveMinimum: 0
204 minimum: 1, maximum: 176400
205205 
206206### Returns
207207 
from line 314
314314 
315315 - `poll_status: BetaFederationIssuerPollStatus or null`
316316 
317 Status of automatic JWKS polling for a federation issuer.
317 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
318318 
319 Anthropic periodically fetches the issuer's signing keys in the
320 background. These fields summarize the most recent fetches so the
321 health of the JWKS endpoint can be monitored.
322 
323319 - `consecutive_failures: number`
324320 
325321 Consecutive fetch failures since the last success.
from line 407
411407 
412408 Number of results per page.
413409 
414 default: 20, maximum: 100, minimum: 1
410 default: 20, minimum: 1, maximum: 100
415411 
416412- `page: optional string`
417413 
from line 625
629625 
630626 - `poll_status: BetaFederationIssuerPollStatus or null`
631627 
632 Status of automatic JWKS polling for a federation issuer.
628 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
633629 
634 Anthropic periodically fetches the issuer's signing keys in the
635 background. These fields summarize the most recent fetches so the
636 health of the JWKS endpoint can be monitored.
637 
638630 - `consecutive_failures: number`
639631 
640632 Consecutive fetch failures since the last success.
from line 931
939931 
940932 - `poll_status: BetaFederationIssuerPollStatus or null`
941933 
942 Status of automatic JWKS polling for a federation issuer.
934 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
943935 
944 Anthropic periodically fetches the issuer's signing keys in the
945 background. These fields summarize the most recent fetches so the
946 health of the JWKS endpoint can be monitored.
947 
948936 - `consecutive_failures: number`
949937 
950938 Consecutive fetch failures since the last success.
from line 1194
12061194 
12071195 Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected.
12081196 
1209 maximum: 176400, exclusiveMinimum: 0
1197 minimum: 1, maximum: 176400
12101198 
12111199- `name: optional string or null`
12121200 
12131201 Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
12141202 
1215 maxLength: 255, minLength: 1
1203 minLength: 1, maxLength: 255
12161204 
12171205### Returns
12181206 
from line 1313
13251313 
13261314 - `poll_status: BetaFederationIssuerPollStatus or null`
13271315 
1328 Status of automatic JWKS polling for a federation issuer.
1316 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
13291317 
1330 Anthropic periodically fetches the issuer's signing keys in the
1331 background. These fields summarize the most recent fetches so the
1332 health of the JWKS endpoint can be monitored.
1333 
13341318 - `consecutive_failures: number`
13351319 
13361320 Consecutive fetch failures since the last success.
from line 1617
16331617 
16341618 - `poll_status: BetaFederationIssuerPollStatus or null`
16351619 
1636 Status of automatic JWKS polling for a federation issuer.
1620 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
16371621 
1638 Anthropic periodically fetches the issuer's signing keys in the
1639 background. These fields summarize the most recent fetches so the
1640 health of the JWKS endpoint can be monitored.
1641 
16421622 - `consecutive_failures: number`
16431623 
16441624 Consecutive fetch failures since the last success.
from line 1797
18171797 
18181798 - `poll_status: BetaFederationIssuerPollStatus or null`
18191799 
1820 Status of automatic JWKS polling for a federation issuer.
1821 
1822 Anthropic periodically fetches the issuer's signing keys in the
1823 background. These fields summarize the most recent fetches so the
1824 health of the JWKS endpoint can be monitored.
1800 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
18251801 
18261802 - `consecutive_failures: number`
18271803 

api/beta/organization/federation/issuers/archive Changed · +1 / -5 lines

from line 239
239239 
240240 - `poll_status: BetaFederationIssuerPollStatus or null`
241241 
242 Status of automatic JWKS polling for a federation issuer.
243 
244 Anthropic periodically fetches the issuer's signing keys in the
245 background. These fields summarize the most recent fetches so the
246 health of the JWKS endpoint can be monitored.
242 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
247243 
248244 - `consecutive_failures: number`
249245 

api/beta/organization/federation/issuers/create Changed · +3 / -7 lines

from line 139
139139 
140140 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
141141 
142 maxLength: 255, minLength: 1
142 minLength: 1, maxLength: 255
143143 
144144- `check_jti: optional boolean or null`
145145 
from line 199
199199 
200200 Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Defaults to 3600 (1h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected.
201201 
202 maximum: 176400, exclusiveMinimum: 0
202 minimum: 1, maximum: 176400
203203 
204204## Returns
205205 
from line 312
312312 
313313 - `poll_status: BetaFederationIssuerPollStatus or null`
314314 
315 Status of automatic JWKS polling for a federation issuer.
316 
317 Anthropic periodically fetches the issuer's signing keys in the
318 background. These fields summarize the most recent fetches so the
319 health of the JWKS endpoint can be monitored.
315 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
320316 
321317 - `consecutive_failures: number`
322318 

api/beta/organization/federation/issuers/list Changed · +2 / -6 lines

from line 25
2525 
2626 Number of results per page.
2727 
28 default: 20, maximum: 100, minimum: 1
28 default: 20, minimum: 1, maximum: 100
2929 
3030- `page: optional string`
3131 
from line 243
243243 
244244 - `poll_status: BetaFederationIssuerPollStatus or null`
245245 
246 Status of automatic JWKS polling for a federation issuer.
247 
248 Anthropic periodically fetches the issuer's signing keys in the
249 background. These fields summarize the most recent fetches so the
250 health of the JWKS endpoint can be monitored.
246 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
251247 
252248 - `consecutive_failures: number`
253249 

api/beta/organization/federation/issuers/retrieve Changed · +1 / -5 lines

from line 234
234234 
235235 - `poll_status: BetaFederationIssuerPollStatus or null`
236236 
237 Status of automatic JWKS polling for a federation issuer.
238 
239 Anthropic periodically fetches the issuer's signing keys in the
240 background. These fields summarize the most recent fetches so the
241 health of the JWKS endpoint can be monitored.
237 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
242238 
243239 - `consecutive_failures: number`
244240 

api/beta/organization/federation/issuers/update Changed · +3 / -7 lines

from line 200
200200 
201201 Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected.
202202 
203 maximum: 176400, exclusiveMinimum: 0
203 minimum: 1, maximum: 176400
204204 
205205- `name: optional string or null`
206206 
207207 Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
208208 
209 maxLength: 255, minLength: 1
209 minLength: 1, maxLength: 255
210210 
211211## Returns
212212 
from line 319
319319 
320320 - `poll_status: BetaFederationIssuerPollStatus or null`
321321 
322 Status of automatic JWKS polling for a federation issuer.
323 
324 Anthropic periodically fetches the issuer's signing keys in the
325 background. These fields summarize the most recent fetches so the
326 health of the JWKS endpoint can be monitored.
322 Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet.
327323 
328324 - `consecutive_failures: number`
329325 

api/beta/organization/federation/rules Changed · +8 / -12 lines

from line 169
169169 
170170 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
171171 
172 maxLength: 255, minLength: 1
172 minLength: 1, maxLength: 255
173173 
174174- `oauth_scope: string`
175175 
from line 209
209209 
210210 Lifetime in seconds for access tokens minted via this rule (60-86400). Defaults to 3600 (1h). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds.
211211 
212 maximum: 86400, minimum: 60
212 minimum: 60, maximum: 86400
213213 
214214- `workspace_id: optional string or null`
215215 
from line 436
436436 
437437 Number of results per page.
438438 
439 default: 20, maximum: 100, minimum: 1
439 default: 20, minimum: 1, maximum: 100
440440 
441441- `page: optional string`
442442 
from line 1186
11861186 
11871187- `match: optional BetaFederationRuleMatch or null`
11881188 
1189 Does the incoming JWT qualify?
1189 Replaces the entire match object. All populated matcher fields must pass.
11901190 
1191 All populated fields must pass; omitted fields are skipped. At least one
1192 of `subject_prefix` (other than a wildcard-only value like `*`), `claims`,
1193 or `condition` is required; `audience` alone is not sufficient.
1194 
11951191 - `audience: optional string or null`
11961192 
11971193 Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default.
from line 1214
12181214 
12191215 Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
12201216 
1221 maxLength: 255, minLength: 1
1217 minLength: 1, maxLength: 255
12221218 
12231219- `oauth_scope: optional string or null`
12241220 
from line 1224
12281224 
12291225- `target: optional BetaServiceAccountTarget or null`
12301226 
1231 Bind to a fixed service account by ID.
1227 Replaces the entire target object. Currently always a `service_account` target.
12321228 
12331229 - `type: "service_account"`
12341230 
from line 1240
12441240 
12451241 Replaces the lifetime in seconds for access tokens minted via this rule (60-86400). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds.
12461242 
1247 maximum: 86400, minimum: 60
1243 minimum: 60, maximum: 86400
12481244 
12491245- `workspace_id: optional string or null`
12501246 
from line 2174
21782174 
21792175 Number of results per page.
21802176 
2181 default: 20, maximum: 100, minimum: 1
2177 default: 20, minimum: 1, maximum: 100
21822178 
21832179- `page: optional string`
21842180 

api/beta/organization/federation/rules/update Changed · +4 / -8 lines

from line 157
157157 
158158- `match: optional BetaFederationRuleMatch or null`
159159 
160 Does the incoming JWT qualify?
160 Replaces the entire match object. All populated matcher fields must pass.
161161 
162 All populated fields must pass; omitted fields are skipped. At least one
163 of `subject_prefix` (other than a wildcard-only value like `*`), `claims`,
164 or `condition` is required; `audience` alone is not sufficient.
165 
166162 - `audience: optional string or null`
167163 
168164 Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default.
from line 185
189185 
190186 Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
191187 
192 maxLength: 255, minLength: 1
188 minLength: 1, maxLength: 255
193189 
194190- `oauth_scope: optional string or null`
195191 
from line 195
199195 
200196- `target: optional BetaServiceAccountTarget or null`
201197 
202 Bind to a fixed service account by ID.
198 Replaces the entire target object. Currently always a `service_account` target.
203199 
204200 - `type: "service_account"`
205201 
from line 211
215211 
216212 Replaces the lifetime in seconds for access tokens minted via this rule (60-86400). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds.
217213 
218 maximum: 86400, minimum: 60
214 minimum: 60, maximum: 86400
219215 
220216- `workspace_id: optional string or null`
221217 

api/beta/organization/rbac_groups Changed · +4 / -4 lines

from line 21
2121 
2222 Defaults to `20`. Ranges from `1` to `1000`.
2323 
24 default: 20, maximum: 1000, minimum: 1
24 default: 20, minimum: 1, maximum: 1000
2525 
2626- `page: optional string`
2727 
from line 223
223223 
224224 Name of the RBAC Group. Not uniqueness-enforced.
225225 
226 maxLength: 255, minLength: 1
226 minLength: 1, maxLength: 255
227227 
228228### Returns
229229 
from line 326
326326 
327327 Name of the RBAC Group. Not uniqueness-enforced.
328328 
329 maxLength: 255, minLength: 1
329 minLength: 1, maxLength: 255
330330 
331331### Returns
332332 
from line 549
549549 
550550 Defaults to `20`. Ranges from `1` to `1000`.
551551 
552 default: 20, maximum: 1000, minimum: 1
552 default: 20, minimum: 1, maximum: 1000
553553 
554554- `page: optional string`
555555 

api/beta/organization/service_accounts Changed · +3 / -3 lines

from line 133
133133 
134134 Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409.
135135 
136 maxLength: 255, minLength: 1
136 minLength: 1, maxLength: 255
137137 
138138- `description: optional string or null`
139139 
from line 266
266266 
267267 Number of results per page.
268268 
269 default: 20, maximum: 100, minimum: 1
269 default: 20, minimum: 1, maximum: 100
270270 
271271- `page: optional string`
272272 
from line 1475
14751475 
14761476 Number of results per page.
14771477 
1478 default: 20, maximum: 100, minimum: 1
1478 default: 20, minimum: 1, maximum: 100
14791479 
14801480- `page: optional string`
14811481 

api/beta/organization/workspaces Changed · +6 / -6 lines

from line 33
3333 
3434 Defaults to `20`. Ranges from `1` to `1000`.
3535 
36 default: 20, maximum: 1000, minimum: 1
36 default: 20, minimum: 1, maximum: 1000
3737 
3838### Returns
3939 
from line 300
300300 
301301 Name of the Workspace.
302302 
303 maxLength: 40, minLength: 1
303 minLength: 1, maxLength: 40
304304 
305305- `data_residency: optional BetaDataResidencyCreateConfig or null`
306306 
from line 692
692692 
693693 Name of the Workspace.
694694 
695 maxLength: 40, minLength: 1
695 minLength: 1, maxLength: 40
696696 
697697- `tags: optional map[string] or null`
698698 
from line 1274
12741274 
12751275 When omitted, every remaining entry is returned in a single page and `next_page` is `null`.
12761276 
1277 maximum: 1000, minimum: 1
1277 minimum: 1, maximum: 1000
12781278 
12791279- `page: optional string`
12801280 
from line 1514
15141514 
15151515 Defaults to `20`. Ranges from `1` to `1000`.
15161516 
1517 default: 20, maximum: 1000, minimum: 1
1517 default: 20, minimum: 1, maximum: 1000
15181518 
15191519#### Returns
15201520 
from line 1916
19161916 
19171917 Number of results per page.
19181918 
1919 default: 20, maximum: 100, minimum: 1
1919 default: 20, minimum: 1, maximum: 100
19201920 
19211921- `page: optional string`
19221922 

api/beta/sessions Changed · +10002 / -10010 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 183
183183 
184184 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
185185 
186 - `BetaManagedAgentsModel = "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more or string`
186 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
187187 
188188 The model that will power your agent.
189189 
190190 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
191191 
192 - `string`
193 
192194 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
193195 
194196 The model that will power your agent.
from line 257
255257 
256258 High-performance model for agents and coding
257259 
258 - `string`
259 
260260 - `BetaManagedAgentsModelConfigParams object`
261261 
262262 An object that defines additional configuration control over model use
from line 331
331331 
332332 - `speed: optional "standard" or "fast" or null`
333333 
334 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.
334 Inference speed mode. Defaults to `standard`.
335335 
336336 - `"standard"`
337337 
from line 413
413413 
414414 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
415415 
416 Permission policy for tool execution.
416 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
417417 
418418 - `BetaManagedAgentsAlwaysAllowPolicy object`
419419 
from line 449
449449 
450450 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
451451 
452 Permission policy for tool execution.
452 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
453453 
454454 - `BetaManagedAgentsAlwaysAllowPolicy object`
455455 
from line 479
479479 
480480 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
481481 
482 Permission policy for tool execution.
482 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
483483 
484484 - `BetaManagedAgentsAlwaysAllowPolicy object`
485485 
from line 509
509509 
510510 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
511511 
512 Permission policy for tool execution.
512 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
513513 
514514 - `BetaManagedAgentsAlwaysAllowPolicy object`
515515 
from line 539
539539 
540540 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
541541 
542 Permission policy for tool execution.
542 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
543543 
544544 - `BetaManagedAgentsAlwaysAllowPolicy object`
545545 
from line 569
569569 
570570 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
571571 
572 Permission policy for tool execution.
572 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
573573 
574574 - `BetaManagedAgentsAlwaysAllowPolicy object`
575575 
from line 613
613613 
614614 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
615615 
616 Permission policy for tool execution.
616 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
617617 
618618 - `BetaManagedAgentsAlwaysAllowPolicy object`
619619 
from line 651
651651 
652652 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
653653 
654 Permission policy for tool execution.
654 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
655655 
656656 - `BetaManagedAgentsAlwaysAllowPolicy object`
657657 
from line 697
697697 
698698 - `default_config: optional BetaManagedAgentsAgentToolsetDefaultConfigParams or null`
699699 
700 Default configuration for all tools in a toolset.
700 Default configuration applied to all tools in this set.
701701 
702702 - `enabled: optional boolean or null`
703703 
from line 705
705705 
706706 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
707707 
708 Permission policy for tool execution.
708 Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation.
709709 
710710 - `BetaManagedAgentsAlwaysAllowPolicy object`
711711 
from line 747
747747 
748748 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
749749 
750 Permission policy for tool execution.
750 Permission policy for this tool. Overrides the `default_config` setting.
751751 
752752 - `BetaManagedAgentsAlwaysAllowPolicy object`
753753 
from line 763
763763 
764764 - `default_config: optional BetaManagedAgentsMCPToolsetDefaultConfigParams or null`
765765 
766 Default configuration for all tools from an MCP server.
766 Default configuration for all tools from this server.
767767 
768768 - `enabled: optional boolean or null`
769769 
from line 771
771771 
772772 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
773773 
774 Permission policy for tool execution.
774 Default permission policy for tools from this server.
775775 
776776 - `BetaManagedAgentsAlwaysAllowPolicy object`
777777 
from line 799
799799 
800800 - `input_schema: BetaManagedAgentsCustomToolInputSchema`
801801 
802 JSON Schema for custom tool input parameters.
802 JSON Schema defining the expected input parameters for the tool.
803803 
804804 - `type: "object"`
805805 
from line 827
827827 
828828- `budget: optional BetaManagedAgentsBudgetLimit`
829829 
830 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
830 Enforced spend ceiling for the session. Omit to create an uncapped session. Every model the session can run — the agent's model and each callable agent's model — must have a public list price, or the request is rejected with reason `model_not_budgetable`.
831831 
832832 - `type: "limit"`
833833 
834834 - `max_list_cost: BetaMonetaryAmount`
835835 
836 A monetary amount in a specific currency.
836 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
837837 
838838 - `amount: string`
839839 
from line 877
877877 
878878 - `source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource`
879879 
880 Union type for image source variants.
880 The source of the image data.
881881 
882882 - `BetaManagedAgentsBase64ImageSource object`
883883 
from line 929
929929 
930930 - `source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource`
931931 
932 Union type for document source variants.
932 The source of the document data.
933933 
934934 - `BetaManagedAgentsBase64DocumentSource object`
935935 
from line 1015
10151015 
10161016 - `rubric: BetaManagedAgentsFileRubricParams or BetaManagedAgentsTextRubricParams`
10171017 
1018 Rubric for grading the quality of an outcome.
1018 How to grade the outcome. Text or file reference.
10191019 
10201020 - `BetaManagedAgentsFileRubricParams object`
10211021 
from line 1131
11311131 
11321132 - `access: optional "read_write" or "read_only" or null`
11331133 
1134 Access mode for an attached memory store.
1134 Access mode for the mounted store. Defaults to read_write. read_only mounts the store as a read-only filesystem.
11351135 
11361136 - `"read_write"`
11371137 
from line 1191
11911191 
11921192 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
11931193 
1194 - `string`
1195 
11941196 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
11951197 
11961198 The model that will power your agent.
from line 1259
12571259 
12581260 High-performance model for agents and coding
12591261 
1260 - `string`
1261 
12621262 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
12631263 
1264 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
1264 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
12651265 
12661266 - `BetaManagedAgentsEffortLow object`
12671267 
from line 1299
12991299 
13001300 - `speed: optional "standard" or "fast"`
13011301 
1302 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.
1302 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
13031303 
13041304 - `"standard"`
13051305 
from line 1307
13071307 
13081308 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
13091309 
1310 Resolved coordinator topology with full agent definitions for each roster member.
1310 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
13111311 
13121312 - `type: "coordinator"`
13131313 
from line 1763
17631763 
17641764 - `archived_at: string or null`
17651765 
1766 A timestamp in RFC 3339 format
1766 When the session was archived. Null if not archived.
17671767 
17681768 format: date-time
17691769 
17701770 - `budget: BetaManagedAgentsBudgetLimit or null`
17711771 
1772 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
1772 The session's enforced spend ceiling, or null when no budget is set.
17731773 
17741774 - `type: "limit"`
17751775 
17761776 - `max_list_cost: BetaMonetaryAmount`
17771777 
1778 A monetary amount in a specific currency.
1778 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
17791779 
17801780 - `amount: string`
17811781 
from line 1803
18031803 
18041804 - `completed_at: string or null`
18051805 
1806 A timestamp in RFC 3339 format
1806 When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`.
18071807 
18081808 format: date-time
18091809 
from line 1909
19091909 
19101910 - `access: optional "read_write" or "read_only" or null`
19111911 
1912 Access mode for an attached memory store.
1912 Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem.
19131913 
19141914 - `"read_write"`
19151915 
from line 1935
19351935 
19361936 - `stats: BetaManagedAgentsSessionStats`
19371937 
1938 Timing statistics for a session.
1938 Timing statistics for the session.
19391939 
19401940 - `active_seconds: optional number`
19411941 
from line 1979
19791979 
19801980 - `usage: BetaManagedAgentsSessionUsage`
19811981 
1982 Cumulative token usage for a session across all turns.
1982 Cumulative token usage for the session.
19831983 
19841984 - `active_seconds: optional number`
19851985 
from line 1989
19891989 
19901990 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
19911991 
1992 Prompt-cache creation token usage broken down by cache lifetime.
1992 Tokens used to create prompt cache entries, broken down by cache TTL.
19931993 
19941994 - `ephemeral_1h_input_tokens: optional number`
19951995 
from line 2017
20172017 
20182018 - `list_cost: optional BetaMonetaryAmount or null`
20192019 
2020 A monetary amount in a specific currency.
2020 Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session.
20212021 
20222022 - `output_tokens: optional number`
20232023 
from line 2027
20272027 
20282028 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
20292029 
2030 Cumulative count of server-executed tool invocations, broken down by tool.
2030 Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session.
20312031 
20322032 - `web_fetch_requests: optional number`
20332033 
from line 2500
25002500 
25012501 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
25022502 
2503 - `string`
2504 
25032505 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
25042506 
25052507 The model that will power your agent.
from line 2568
25662568 
25672569 High-performance model for agents and coding
25682570 
2569 - `string`
2570 
25712571 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
25722572 
2573 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
2573 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
25742574 
25752575 - `BetaManagedAgentsEffortLow object`
25762576 
from line 2608
26082608 
26092609 - `speed: optional "standard" or "fast"`
26102610 
2611 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.
2611 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
26122612 
26132613 - `"standard"`
26142614 
from line 2616
26162616 
26172617 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
26182618 
2619 Resolved coordinator topology with full agent definitions for each roster member.
2619 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
26202620 
26212621 - `type: "coordinator"`
26222622 
from line 3072
30723072 
30733073 - `archived_at: string or null`
30743074 
3075 A timestamp in RFC 3339 format
3075 When the session was archived. Null if not archived.
30763076 
30773077 format: date-time
30783078 
30793079 - `budget: BetaManagedAgentsBudgetLimit or null`
30803080 
3081 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
3081 The session's enforced spend ceiling, or null when no budget is set.
30823082 
30833083 - `type: "limit"`
30843084 
30853085 - `max_list_cost: BetaMonetaryAmount`
30863086 
3087 A monetary amount in a specific currency.
3087 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
30883088 
30893089 - `amount: string`
30903090 
from line 3112
31123112 
31133113 - `completed_at: string or null`
31143114 
3115 A timestamp in RFC 3339 format
3115 When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`.
31163116 
31173117 format: date-time
31183118 
from line 3218
32183218 
32193219 - `access: optional "read_write" or "read_only" or null`
32203220 
3221 Access mode for an attached memory store.
3221 Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem.
32223222 
32233223 - `"read_write"`
32243224 
from line 3244
32443244 
32453245 - `stats: BetaManagedAgentsSessionStats`
32463246 
3247 Timing statistics for a session.
3247 Timing statistics for the session.
32483248 
32493249 - `active_seconds: optional number`
32503250 
from line 3288
32883288 
32893289 - `usage: BetaManagedAgentsSessionUsage`
32903290 
3291 Cumulative token usage for a session across all turns.
3291 Cumulative token usage for the session.
32923292 
32933293 - `active_seconds: optional number`
32943294 
from line 3298
32983298 
32993299 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
33003300 
3301 Prompt-cache creation token usage broken down by cache lifetime.
3301 Tokens used to create prompt cache entries, broken down by cache TTL.
33023302 
33033303 - `ephemeral_1h_input_tokens: optional number`
33043304 
from line 3326
33263326 
33273327 - `list_cost: optional BetaMonetaryAmount or null`
33283328 
3329 A monetary amount in a specific currency.
3329 Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session.
33303330 
33313331 - `output_tokens: optional number`
33323332 
from line 3336
33363336 
33373337 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
33383338 
3339 Cumulative count of server-executed tool invocations, broken down by tool.
3339 Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session.
33403340 
33413341 - `web_fetch_requests: optional number`
33423342 
from line 3735
37353735 
37363736 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
37373737 
3738 - `string`
3739 
37383740 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
37393741 
37403742 The model that will power your agent.
from line 3803
38013803 
38023804 High-performance model for agents and coding
38033805 
3804 - `string`
3805 
38063806 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
38073807 
3808 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
3808 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
38093809 
38103810 - `BetaManagedAgentsEffortLow object`
38113811 
from line 3843
38433843 
38443844 - `speed: optional "standard" or "fast"`
38453845 
3846 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.
3846 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
38473847 
38483848 - `"standard"`
38493849 
from line 3851
38513851 
38523852 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
38533853 
3854 Resolved coordinator topology with full agent definitions for each roster member.
3854 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
38553855 
38563856 - `type: "coordinator"`
38573857 
from line 4307
43074307 
43084308 - `archived_at: string or null`
43094309 
4310 A timestamp in RFC 3339 format
4310 When the session was archived. Null if not archived.
43114311 
43124312 format: date-time
43134313 
43144314 - `budget: BetaManagedAgentsBudgetLimit or null`
43154315 
4316 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
4316 The session's enforced spend ceiling, or null when no budget is set.
43174317 
43184318 - `type: "limit"`
43194319 
43204320 - `max_list_cost: BetaMonetaryAmount`
43214321 
4322 A monetary amount in a specific currency.
4322 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
43234323 
43244324 - `amount: string`
43254325 
from line 4347
43474347 
43484348 - `completed_at: string or null`
43494349 
4350 A timestamp in RFC 3339 format
4350 When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`.
43514351 
43524352 format: date-time
43534353 
from line 4453
44534453 
44544454 - `access: optional "read_write" or "read_only" or null`
44554455 
4456 Access mode for an attached memory store.
4456 Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem.
44574457 
44584458 - `"read_write"`
44594459 
from line 4479
44794479 
44804480 - `stats: BetaManagedAgentsSessionStats`
44814481 
4482 Timing statistics for a session.
4482 Timing statistics for the session.
44834483 
44844484 - `active_seconds: optional number`
44854485 
from line 4523
45234523 
45244524 - `usage: BetaManagedAgentsSessionUsage`
45254525 
4526 Cumulative token usage for a session across all turns.
4526 Cumulative token usage for the session.
45274527 
45284528 - `active_seconds: optional number`
45294529 
from line 4533
45334533 
45344534 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
45354535 
4536 Prompt-cache creation token usage broken down by cache lifetime.
4536 Tokens used to create prompt cache entries, broken down by cache TTL.
45374537 
45384538 - `ephemeral_1h_input_tokens: optional number`
45394539 
from line 4561
45614561 
45624562 - `list_cost: optional BetaMonetaryAmount or null`
45634563 
4564 A monetary amount in a specific currency.
4564 Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session.
45654565 
45664566 - `output_tokens: optional number`
45674567 
from line 4571
45714571 
45724572 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
45734573 
4574 Cumulative count of server-executed tool invocations, broken down by tool.
4574 Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session.
45754575 
45764576 - `web_fetch_requests: optional number`
45774577 
from line 4922
49224922 
49234923- `agent: optional BetaManagedAgentsSessionAgentUpdate`
49244924 
4925 Mid-session agent configuration update. Only `tools` and `mcp_servers` are updatable. Full replacement: the provided array becomes the new value. To preserve existing entries, GET the session, modify the array, and POST it back.
4925 Agent configuration update. Only `tools` and `mcp_servers` are updatable mid-session. Only valid for sessions created from an agent or deployment reference. The session must not be running.
49264926 
49274927 - `mcp_servers: optional array of BetaManagedAgentsURLMCPServerParams`
49284928 
from line 4972
49724972 
49734973 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
49744974 
4975 Permission policy for tool execution.
4975 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
49764976 
49774977 - `BetaManagedAgentsAlwaysAllowPolicy object`
49784978 
from line 5008
50085008 
50095009 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
50105010 
5011 Permission policy for tool execution.
5011 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
50125012 
50135013 - `BetaManagedAgentsAlwaysAllowPolicy object`
50145014 
from line 5038
50385038 
50395039 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
50405040 
5041 Permission policy for tool execution.
5041 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
50425042 
50435043 - `BetaManagedAgentsAlwaysAllowPolicy object`
50445044 
from line 5068
50685068 
50695069 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
50705070 
5071 Permission policy for tool execution.
5071 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
50725072 
50735073 - `BetaManagedAgentsAlwaysAllowPolicy object`
50745074 
from line 5098
50985098 
50995099 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
51005100 
5101 Permission policy for tool execution.
5101 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
51025102 
51035103 - `BetaManagedAgentsAlwaysAllowPolicy object`
51045104 
from line 5128
51285128 
51295129 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
51305130 
5131 Permission policy for tool execution.
5131 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
51325132 
51335133 - `BetaManagedAgentsAlwaysAllowPolicy object`
51345134 
from line 5172
51725172 
51735173 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
51745174 
5175 Permission policy for tool execution.
5175 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
51765176 
51775177 - `BetaManagedAgentsAlwaysAllowPolicy object`
51785178 
from line 5210
52105210 
52115211 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
52125212 
5213 Permission policy for tool execution.
5213 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
52145214 
52155215 - `BetaManagedAgentsAlwaysAllowPolicy object`
52165216 
from line 5256
52565256 
52575257 - `default_config: optional BetaManagedAgentsAgentToolsetDefaultConfigParams or null`
52585258 
5259 Default configuration for all tools in a toolset.
5259 Default configuration applied to all tools in this set.
52605260 
52615261 - `enabled: optional boolean or null`
52625262 
from line 5264
52645264 
52655265 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
52665266 
5267 Permission policy for tool execution.
5267 Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation.
52685268 
52695269 - `BetaManagedAgentsAlwaysAllowPolicy object`
52705270 
from line 5306
53065306 
53075307 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
53085308 
5309 Permission policy for tool execution.
5309 Permission policy for this tool. Overrides the `default_config` setting.
53105310 
53115311 - `BetaManagedAgentsAlwaysAllowPolicy object`
53125312 
from line 5322
53225322 
53235323 - `default_config: optional BetaManagedAgentsMCPToolsetDefaultConfigParams or null`
53245324 
5325 Default configuration for all tools from an MCP server.
5325 Default configuration for all tools from this server.
53265326 
53275327 - `enabled: optional boolean or null`
53285328 
from line 5330
53305330 
53315331 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
53325332 
5333 Permission policy for tool execution.
5333 Default permission policy for tools from this server.
53345334 
53355335 - `BetaManagedAgentsAlwaysAllowPolicy object`
53365336 
from line 5358
53585358 
53595359 - `input_schema: BetaManagedAgentsCustomToolInputSchema`
53605360 
5361 JSON Schema for custom tool input parameters.
5361 JSON Schema defining the expected input parameters for the tool.
53625362 
53635363 - `type: "object"`
53645364 
from line 5374
53745374 
53755375- `budget: optional BetaManagedAgentsBudgetLimit or null`
53765376 
5377 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
5377 Enforced spend ceiling for the session. Set an object to replace the budget of a session that was created with one, or `null` to remove it; omit to preserve. A budget cannot be added to a session created without one (rejected with reason `budget_create_only`), and a removed budget cannot be re-added. Allowed in any non-terminated status. Lowering `max_list_cost` to at or below the session's consumed list cost is rejected with reason `budget_not_raised`, and every model the session can run must have a public list price or the request is rejected with reason `model_not_budgetable`.
53785378 
53795379 - `type: "limit"`
53805380 
53815381 - `max_list_cost: BetaMonetaryAmount`
53825382 
5383 A monetary amount in a specific currency.
5383 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
53845384 
53855385 - `amount: string`
53865386 
from line 5442
54425442 
54435443 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
54445444 
5445 - `string`
5446 
54455447 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
54465448 
54475449 The model that will power your agent.
from line 5510
55085510 
55095511 High-performance model for agents and coding
55105512 
5511 - `string`
5512 
55135513 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
55145514 
5515 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
5515 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
55165516 
55175517 - `BetaManagedAgentsEffortLow object`
55185518 
from line 5550
55505550 
55515551 - `speed: optional "standard" or "fast"`
55525552 
5553 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.
5553 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
55545554 
55555555 - `"standard"`
55565556 
from line 5558
55585558 
55595559 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
55605560 
5561 Resolved coordinator topology with full agent definitions for each roster member.
5561 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
55625562 
55635563 - `type: "coordinator"`
55645564 
from line 6014
60146014 
60156015 - `archived_at: string or null`
60166016 
6017 A timestamp in RFC 3339 format
6017 When the session was archived. Null if not archived.
60186018 
60196019 format: date-time
60206020 
60216021 - `budget: BetaManagedAgentsBudgetLimit or null`
60226022 
6023 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
6023 The session's enforced spend ceiling, or null when no budget is set.
60246024 
60256025 - `type: "limit"`
60266026 
60276027 - `max_list_cost: BetaMonetaryAmount`
60286028 
6029 A monetary amount in a specific currency.
6029 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
60306030 
60316031 - `amount: string`
60326032 
from line 6054
60546054 
60556055 - `completed_at: string or null`
60566056 
6057 A timestamp in RFC 3339 format
6057 When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`.
60586058 
60596059 format: date-time
60606060 
from line 6160
61606160 
61616161 - `access: optional "read_write" or "read_only" or null`
61626162 
6163 Access mode for an attached memory store.
6163 Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem.
61646164 
61656165 - `"read_write"`
61666166 
from line 6186
61866186 
61876187 - `stats: BetaManagedAgentsSessionStats`
61886188 
6189 Timing statistics for a session.
6189 Timing statistics for the session.
61906190 
61916191 - `active_seconds: optional number`
61926192 
from line 6230
62306230 
62316231 - `usage: BetaManagedAgentsSessionUsage`
62326232 
6233 Cumulative token usage for a session across all turns.
6233 Cumulative token usage for the session.
62346234 
62356235 - `active_seconds: optional number`
62366236 
from line 6240
62406240 
62416241 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
62426242 
6243 Prompt-cache creation token usage broken down by cache lifetime.
6243 Tokens used to create prompt cache entries, broken down by cache TTL.
62446244 
62456245 - `ephemeral_1h_input_tokens: optional number`
62466246 
from line 6268
62686268 
62696269 - `list_cost: optional BetaMonetaryAmount or null`
62706270 
6271 A monetary amount in a specific currency.
6271 Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session.
62726272 
62736273 - `output_tokens: optional number`
62746274 
from line 6278
62786278 
62796279 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
62806280 
6281 Cumulative count of server-executed tool invocations, broken down by tool.
6281 Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session.
62826282 
62836283 - `web_fetch_requests: optional number`
62846284 
from line 6818
68186818 
68196819 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
68206820 
6821 - `string`
6822 
68216823 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
68226824 
68236825 The model that will power your agent.
from line 6886
68846886 
68856887 High-performance model for agents and coding
68866888 
6887 - `string`
6888 
68896889 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
68906890 
6891 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
6891 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
68926892 
68936893 - `BetaManagedAgentsEffortLow object`
68946894 
from line 6926
69266926 
69276927 - `speed: optional "standard" or "fast"`
69286928 
6929 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.
6929 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
69306930 
69316931 - `"standard"`
69326932 
from line 6934
69346934 
69356935 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
69366936 
6937 Resolved coordinator topology with full agent definitions for each roster member.
6937 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
69386938 
69396939 - `type: "coordinator"`
69406940 
from line 7390
73907390 
73917391 - `archived_at: string or null`
73927392 
7393 A timestamp in RFC 3339 format
7393 When the session was archived. Null if not archived.
73947394 
73957395 format: date-time
73967396 
73977397 - `budget: BetaManagedAgentsBudgetLimit or null`
73987398 
7399 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
7399 The session's enforced spend ceiling, or null when no budget is set.
74007400 
74017401 - `type: "limit"`
74027402 
74037403 - `max_list_cost: BetaMonetaryAmount`
74047404 
7405 A monetary amount in a specific currency.
7405 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
74067406 
74077407 - `amount: string`
74087408 
from line 7430
74307430 
74317431 - `completed_at: string or null`
74327432 
7433 A timestamp in RFC 3339 format
7433 When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`.
74347434 
74357435 format: date-time
74367436 
from line 7536
75367536 
75377537 - `access: optional "read_write" or "read_only" or null`
75387538 
7539 Access mode for an attached memory store.
7539 Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem.
75407540 
75417541 - `"read_write"`
75427542 
from line 7562
75627562 
75637563 - `stats: BetaManagedAgentsSessionStats`
75647564 
7565 Timing statistics for a session.
7565 Timing statistics for the session.
75667566 
75677567 - `active_seconds: optional number`
75687568 
from line 7606
76067606 
76077607 - `usage: BetaManagedAgentsSessionUsage`
76087608 
7609 Cumulative token usage for a session across all turns.
7609 Cumulative token usage for the session.
76107610 
76117611 - `active_seconds: optional number`
76127612 
from line 7616
76167616 
76177617 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
76187618 
7619 Prompt-cache creation token usage broken down by cache lifetime.
7619 Tokens used to create prompt cache entries, broken down by cache TTL.
76207620 
76217621 - `ephemeral_1h_input_tokens: optional number`
76227622 
from line 7644
76447644 
76457645 - `list_cost: optional BetaMonetaryAmount or null`
76467646 
7647 A monetary amount in a specific currency.
7647 Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session.
76487648 
76497649 - `output_tokens: optional number`
76507650 
from line 7654
76547654 
76557655 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
76567656 
7657 Cumulative count of server-executed tool invocations, broken down by tool.
7657 Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session.
76587658 
76597659 - `web_fetch_requests: optional number`
76607660 
from line 7972
79727972 
79737973 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
79747974 
7975 - `BetaManagedAgentsModel = "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more or string`
7975 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
79767976 
79777977 The model that will power your agent.
79787978 
79797979 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
79807980 
7981 - `string`
7982 
79817983 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
79827984 
79837985 The model that will power your agent.
from line 8046
80448046 
80458047 High-performance model for agents and coding
80468048 
8047 - `string`
8048 
80498049 - `BetaManagedAgentsModelConfigParams object`
80508050 
80518051 An object that defines additional configuration control over model use
from line 8120
81208120 
81218121 - `speed: optional "standard" or "fast" or null`
81228122 
8123 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.
8123 Inference speed mode. Defaults to `standard`.
81248124 
81258125 - `"standard"`
81268126 
from line 8202
82028202 
82038203 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
82048204 
8205 Permission policy for tool execution.
8205 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
82068206 
82078207 - `BetaManagedAgentsAlwaysAllowPolicy object`
82088208 
from line 8238
82388238 
82398239 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
82408240 
8241 Permission policy for tool execution.
8241 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
82428242 
82438243 - `BetaManagedAgentsAlwaysAllowPolicy object`
82448244 
from line 8268
82688268 
82698269 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
82708270 
8271 Permission policy for tool execution.
8271 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
82728272 
82738273 - `BetaManagedAgentsAlwaysAllowPolicy object`
82748274 
from line 8298
82988298 
82998299 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
83008300 
8301 Permission policy for tool execution.
8301 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
83028302 
83038303 - `BetaManagedAgentsAlwaysAllowPolicy object`
83048304 
from line 8328
83288328 
83298329 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
83308330 
8331 Permission policy for tool execution.
8331 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
83328332 
83338333 - `BetaManagedAgentsAlwaysAllowPolicy object`
83348334 
from line 8358
83588358 
83598359 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
83608360 
8361 Permission policy for tool execution.
8362 
8363 - `BetaManagedAgentsAlwaysAllowPolicy object`
8364 
8365 Tool calls are automatically approved without user confirmation.
8366 
8367 - `BetaManagedAgentsAlwaysAskPolicy object`
8368 
8369 Tool calls require user confirmation before execution.
8370 
8371 - `BetaManagedAgentsAutoPolicy object`
8372 
8373 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
8374 
8375 - `BetaManagedAgentsWebFetchToolConfigParams object`
8376 
8377 Configuration override for the web_fetch tool.
8378 
8379 - `type: optional "web_fetch"`
8380 
8381 - `name: "web_fetch"`
8382 
8383 Must be "web_fetch".
8384 
8385 - `allowed_domains: optional array of string`
8386 
8387 Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
8388 
8389 - `blocked_domains: optional array of string`
8390 
8391 Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains.
8392 
8393 - `enabled: optional boolean or null`
8394 
8395 Whether this tool is enabled and available to Claude. Overrides the default_config setting.
8396 
8397 - `max_content_tokens: optional number or null`
8398 
8399 Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs.
8400 
8401 format: int32
8402 
8403 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
8404 
8405 Permission policy for tool execution.
8406 
8407 - `BetaManagedAgentsAlwaysAllowPolicy object`
8408 
8409 Tool calls are automatically approved without user confirmation.
8410 
8411 - `BetaManagedAgentsAlwaysAskPolicy object`
8412 
8413 Tool calls require user confirmation before execution.
8414 
8415 - `BetaManagedAgentsAutoPolicy object`
8416 
8417 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
8418 
8419 - `BetaManagedAgentsWebSearchToolConfigParams object`
8420 
8421 Configuration override for the web_search tool.
8422 
8423 - `type: optional "web_search"`
8424 
8425 - `name: "web_search"`
8426 
8427 Must be "web_search".
8428 
8429 - `allowed_domains: optional array of string`
8430 
8431 Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
8432 
8433 - `blocked_domains: optional array of string`
8434 
8435 Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains.
8436 
8437 - `enabled: optional boolean or null`
8438 
8439 Whether this tool is enabled and available to Claude. Overrides the default_config setting.
8440 
8441 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
8442 
8443 Permission policy for tool execution.
8444 
8445 - `BetaManagedAgentsAlwaysAllowPolicy object`
8446 
8447 Tool calls are automatically approved without user confirmation.
8448 
8449 - `BetaManagedAgentsAlwaysAskPolicy object`
8450 
8451 Tool calls require user confirmation before execution.
8452 
8453 - `BetaManagedAgentsAutoPolicy object`
8454 
8455
8361 Permission p

api/beta/sessions/archive Changed · +250 / -250 lines

from line 163
163163 
164164 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
165165 
166 - `string`
167 
166168 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
167169 
168170 The model that will power your agent.
from line 231
229231 
230232 High-performance model for agents and coding
231233 
232 - `string`
233 
234234 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
235235 
236 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
236 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
237237 
238238 - `BetaManagedAgentsEffortLow object`
239239 
from line 271
271271 
272272 - `speed: optional "standard" or "fast"`
273273 
274 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.
274 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
275275 
276276 - `"standard"`
277277 
from line 279
279279 
280280 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
281281 
282 Resolved coordinator topology with full agent definitions for each roster member.
282 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
283283 
284284 - `type: "coordinator"`
285285 
from line 735
735735 
736736 - `archived_at: string or null`
737737 
738 A timestamp in RFC 3339 format
738 When the session was archived. Null if not archived.
739739 
740740 format: date-time
741741 
742742 - `budget: BetaManagedAgentsBudgetLimit or null`
743743 
744 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
744 The session's enforced spend ceiling, or null when no budget is set.
745745 
746746 - `type: "limit"`
747747 
748748 - `max_list_cost: BetaMonetaryAmount`
749749 
750 A monetary amount in a specific currency.
750 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
751751 
752752 - `amount: string`
753753 
from line 775
775775 
776776 - `completed_at: string or null`
777777 
778 A timestamp in RFC 3339 format
778 When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`.
779779 
780780 format: date-time
781781 
from line 881
881881 
882882 - `access: optional "read_write" or "read_only" or null`
883883 
884 Access mode for an attached memory store.
884 Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem.
885885 
886886 - `"read_write"`
887887 
from line 907
907907 
908908 - `stats: BetaManagedAgentsSessionStats`
909909 
910 Timing statistics for a session.
910 Timing statistics for the session.
911911 
912912 - `active_seconds: optional number`
913913 
from line 951
951951 
952952 - `usage: BetaManagedAgentsSessionUsage`
953953 
954 Cumulative token usage for a session across all turns.
954 Cumulative token usage for the session.
955955 
956956 - `active_seconds: optional number`
957957 
from line 961
961961 
962962 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
963963 
964 Prompt-cache creation token usage broken down by cache lifetime.
964 Tokens used to create prompt cache entries, broken down by cache TTL.
965965 
966966 - `ephemeral_1h_input_tokens: optional number`
967967 
from line 989
989989 
990990 - `list_cost: optional BetaMonetaryAmount or null`
991991 
992 A monetary amount in a specific currency.
992 Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session.
993993 
994994 - `output_tokens: optional number`
995995 
from line 999
999999 
10001000 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
10011001 
1002 Cumulative count of server-executed tool invocations, broken down by tool.
1002 Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session.
10031003 
10041004 - `web_fetch_requests: optional number`
10051005 

api/beta/sessions/create Changed · +1738 / -1738 lines

from line 181
181181 
182182 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
183183 
184 - `BetaManagedAgentsModel = "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more or string`
184 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
185185 
186186 The model that will power your agent.
187187 
188188 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
189189 
190 - `string`
191 
190192 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
191193 
192194 The model that will power your agent.
from line 255
253255 
254256 High-performance model for agents and coding
255257 
256 - `string`
257 
258258 - `BetaManagedAgentsModelConfigParams object`
259259 
260260 An object that defines additional configuration control over model use
from line 329
329329 
330330 - `speed: optional "standard" or "fast" or null`
331331 
332 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.
332 Inference speed mode. Defaults to `standard`.
333333 
334334 - `"standard"`
335335 
from line 411
411411 
412412 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
413413 
414 Permission policy for tool execution.
414 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
415415 
416416 - `BetaManagedAgentsAlwaysAllowPolicy object`
417417 
from line 447
447447 
448448 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
449449 
450 Permission policy for tool execution.
450 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
451451 
452452 - `BetaManagedAgentsAlwaysAllowPolicy object`
453453 
from line 477
477477 
478478 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
479479 
480 Permission policy for tool execution.
480 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
481481 
482482 - `BetaManagedAgentsAlwaysAllowPolicy object`
483483 
from line 507
507507 
508508 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
509509 
510 Permission policy for tool execution.
510 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
511511 
512512 - `BetaManagedAgentsAlwaysAllowPolicy object`
513513 
from line 537
537537 
538538 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
539539 
540 Permission policy for tool execution.
540 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
541541 
542542 - `BetaManagedAgentsAlwaysAllowPolicy object`
543543 
from line 567
567567 
568568 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
569569 
570 Permission policy for tool execution.
570 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
571571 
572572 - `BetaManagedAgentsAlwaysAllowPolicy object`
573573 
from line 611
611611 
612612 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
613613 
614 Permission policy for tool execution.
614 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
615615 
616616 - `BetaManagedAgentsAlwaysAllowPolicy object`
617617 
from line 649
649649 
650650 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
651651 
652 Permission policy for tool execution.
652 Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
653653 
654654 - `BetaManagedAgentsAlwaysAllowPolicy object`
655655 
from line 695
695695 
696696 - `default_config: optional BetaManagedAgentsAgentToolsetDefaultConfigParams or null`
697697 
698 Default configuration for all tools in a toolset.
698 Default configuration applied to all tools in this set.
699699 
700700 - `enabled: optional boolean or null`
701701 
from line 703
703703 
704704 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
705705 
706 Permission policy for tool execution.
706 Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation.
707707 
708708 - `BetaManagedAgentsAlwaysAllowPolicy object`
709709 
from line 745
745745 
746746 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
747747 
748 Permission policy for tool execution.
748 Permission policy for this tool. Overrides the `default_config` setting.
749749 
750750 - `BetaManagedAgentsAlwaysAllowPolicy object`
751751 
from line 761
761761 
762762 - `default_config: optional BetaManagedAgentsMCPToolsetDefaultConfigParams or null`
763763 
764 Default configuration for all tools from an MCP server.
764 Default configuration for all tools from this server.
765765 
766766 - `enabled: optional boolean or null`
767767 
from line 769
769769 
770770 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
771771 
772 Permission policy for tool execution.
772 Default permission policy for tools from this server.
773773 
774774 - `BetaManagedAgentsAlwaysAllowPolicy object`
775775 
from line 797
797797 
798798 - `input_schema: BetaManagedAgentsCustomToolInputSchema`
799799 
800 JSON Schema for custom tool input parameters.
800 JSON Schema defining the expected input parameters for the tool.
801801 
802802 - `type: "object"`
803803 
from line 825
825825 
826826- `budget: optional BetaManagedAgentsBudgetLimit`
827827 
828 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
828 Enforced spend ceiling for the session. Omit to create an uncapped session. Every model the session can run — the agent's model and each callable agent's model — must have a public list price, or the request is rejected with reason `model_not_budgetable`.
829829 
830830 - `type: "limit"`
831831 
832832 - `max_list_cost: BetaMonetaryAmount`
833833 
834 A monetary amount in a specific currency.
834 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
835835 
836836 - `amount: string`
837837 
from line 875
875875 
876876 - `source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource`
877877 
878 Union type for image source variants.
878 The source of the image data.
879879 
880880 - `BetaManagedAgentsBase64ImageSource object`
881881 
from line 927
927927 
928928 - `source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource`
929929 
930 Union type for document source variants.
930 The source of the document data.
931931 
932932 - `BetaManagedAgentsBase64DocumentSource object`
933933 
from line 1013
10131013 
10141014 - `rubric: BetaManagedAgentsFileRubricParams or BetaManagedAgentsTextRubricParams`
10151015 
1016 Rubric for grading the quality of an outcome.
1016 How to grade the outcome. Text or file reference.
10171017 
10181018 - `BetaManagedAgentsFileRubricParams object`
10191019 
from line 1129
11291129 
11301130 - `access: optional "read_write" or "read_only" or null`
11311131 
1132 Access mode for an attached memory store.
1132 Access mode for the mounted store. Defaults to read_write. read_only mounts the store as a read-only filesystem.
11331133 
11341134 - `"read_write"`
11351135 
from line 1189
11891189 
11901190 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
11911191 
1192 - `string`
1193 
11921194 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
11931195 
11941196 The model that will power your agent.
from line 1257
12551257 
12561258 High-performance model for agents and coding
12571259 
1258 - `string`
1259 
12601260 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
12611261 
1262 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
1262 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
12631263 
12641264 - `BetaManagedAgentsEffortLow object`
12651265 
from line 1297
12971297 
12981298 - `speed: optional "standard" or "fast"`
12991299 
1300 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.
1300 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
13011301 
13021302 - `"standard"`
13031303 
from line 1305
13051305 
13061306 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
13071307 
1308 Resolved coordinator topology with full agent definitions for each roster member.
1308 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
13091309 
13101310 - `type: "coordinator"`
13111311 
from line 1761
17611761 
17621762 - `archived_at: string or null`
17631763 
1764 A timestamp in RFC 3339 format
1764 When the session was archived. Null if not archived.
17651765 
17661766 format: date-time
17671767 
17681768 - `budget: BetaManagedAgentsBudgetLimit or null`
17691769 
1770 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
1770 The session's enforced spend ceiling, or null when no budget is set.
17711771 
17721772 - `type: "limit"`
17731773 
17741774 - `max_list_cost: BetaMonetaryAmount`
17751775 
1776 A monetary amount in a specific currency.
1776 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
17771777 
17781778 - `amount: string`
17791779 
from line 1801
18011801 
18021802 - `completed_at: string or null`
18031803 
1804 A timestamp in RFC 3339 format
1804 When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`.
18051805 
18061806 format: date-time
18071807 
from line 1907
19071907 
19081908 - `access: optional "read_write" or "read_only" or null`
19091909 
1910 Access mode for an attached memory store.
1910 Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem.
19111911 
19121912 - `"read_write"`
19131913 
from line 1933
19331933 
19341934 - `stats: BetaManagedAgentsSessionStats`
19351935 
1936 Timing statistics for a session.
1936 Timing statistics for the session.
19371937 
19381938 - `active_seconds: optional number`
19391939 
from line 1977
19771977 
19781978 - `usage: BetaManagedAgentsSessionUsage`
19791979 
1980 Cumulative token usage for a session across all turns.
1980 Cumulative token usage for the session.
19811981 
19821982 - `active_seconds: optional number`
19831983 
from line 1987
19871987 
19881988 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
19891989 
1990 Prompt-cache creation token usage broken down by cache lifetime.
1990 Tokens used to create prompt cache entries, broken down by cache TTL.
19911991 
19921992 - `ephemeral_1h_input_tokens: optional number`
19931993 
from line 2015
20152015 
20162016 - `list_cost: optional BetaMonetaryAmount or null`
20172017 
2018 A monetary amount in a specific currency.
2018 Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session.
20192019 
20202020 - `output_tokens: optional number`
20212021 
from line 2025
20252025 
20262026 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
20272027 
2028 Cumulative count of server-executed tool invocations, broken down by tool.
2028 Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session.
20292029 
20302030 - `web_fetch_requests: optional number`
20312031 

api/beta/sessions/events Changed · +4384 / -4388 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.

Nothing in the body moved in this read. What changed is above.

api/beta/sessions/events/list Changed · +72 / -72 lines

from line 211
211211 
212212 - `source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource`
213213 
214 Union type for image source variants.
214 The source of the image data.
215215 
216216 - `BetaManagedAgentsBase64ImageSource object`
217217 
from line 263
263263 
264264 - `source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource`
265265 
266 Union type for document source variants.
266 The source of the document data.
267267 
268268 - `BetaManagedAgentsBase64DocumentSource object`
269269 
from line 339
339339 
340340 - `processed_at: optional string or null`
341341 
342 A timestamp in RFC 3339 format
342 Timestamp when the agent finished processing this message.
343343 
344344 format: date-time
345345 
from line 355
355355 
356356 - `processed_at: optional string or null`
357357 
358 A timestamp in RFC 3339 format
358 Timestamp when the interrupt was processed.
359359 
360360 format: date-time
361361 
from line 375
375375 
376376 - `result: "allow" or "deny"`
377377 
378 UserToolConfirmationResult enum
378 The confirmation result: 'allow' or 'deny'.
379379 
380380 - `"allow"`
381381 
from line 393
393393 
394394 - `processed_at: optional string or null`
395395 
396 A timestamp in RFC 3339 format
396 Timestamp when the confirmation was processed.
397397 
398398 format: date-time
399399 
from line 439
439439 
440440 - `citations: BetaManagedAgentsSearchResultCitations`
441441 
442 Citation settings for a search result.
442 Citation settings for this search result.
443443 
444444 - `enabled: boolean`
445445 
from line 475
475475 
476476 - `processed_at: optional string or null`
477477 
478 A timestamp in RFC 3339 format
478 Timestamp when this result was processed.
479479 
480480 format: date-time
481481 
from line 503
503503 
504504 - `processed_at: string`
505505 
506 A timestamp in RFC 3339 format
506 Timestamp when this tool use was processed.
507507 
508508 format: date-time
509509 
from line 535
535535 
536536 - `processed_at: string`
537537 
538 A timestamp in RFC 3339 format
538 Timestamp when this response was generated.
539539 
540540 format: date-time
541541 
from line 551
551551 
552552 - `processed_at: string`
553553 
554 A timestamp in RFC 3339 format
554 Timestamp when this thinking was produced.
555555 
556556 format: date-time
557557 
from line 579
579579 
580580 - `processed_at: string`
581581 
582 A timestamp in RFC 3339 format
582 Timestamp when this event was processed.
583583 
584584 format: date-time
585585 
586586 - `evaluated_permission: optional BetaManagedAgentsAgentEvaluatedPermission`
587587 
588 AgentEvaluatedPermission enum
588 The evaluated permission policy for this tool invocation.
589589 
590590 - `"allow"`
591591 
from line 595
595595 
596596 - `evaluation: optional BetaManagedAgentsAgentToolEvaluation`
597597 
598 Names the resolved permission_policy that produced evaluated_permission, and under auto carries the judgement. Open union: clients must tolerate unknown variants.
598 Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask).
599599 
600600 - `BetaManagedAgentsAgentToolEvaluationAlwaysAllow object`
601601 
from line 617
617617 
618618 - `evaluated_permission: BetaManagedAgentsAgentAutoEvaluatedPermission`
619619 
620 The server's per-invocation judgement under the auto permission policy. Its type always equals the event's top-level evaluated_permission. Open union: clients must tolerate unknown variants.
620 The server's judgement for this invocation.
621621 
622622 - `BetaManagedAgentsAgentAutoEvaluatedPermissionAllow object`
623623 
from line 669
669669 
670670 - `processed_at: string`
671671 
672 A timestamp in RFC 3339 format
672 Timestamp when this event was processed.
673673 
674674 format: date-time
675675 
from line 717
717717 
718718 - `processed_at: string`
719719 
720 A timestamp in RFC 3339 format
720 Timestamp when this event was processed.
721721 
722722 format: date-time
723723 
724724 - `evaluated_permission: optional BetaManagedAgentsAgentEvaluatedPermission`
725725 
726 AgentEvaluatedPermission enum
726 The evaluated permission policy for this tool invocation.
727727 
728728 - `evaluation: optional BetaManagedAgentsAgentToolEvaluation`
729729 
730 Names the resolved permission_policy that produced evaluated_permission, and under auto carries the judgement. Open union: clients must tolerate unknown variants.
730 Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask).
731731 
732732 - `session_thread_id: optional string or null`
733733 
from line 745
745745 
746746 - `processed_at: string`
747747 
748 A timestamp in RFC 3339 format
748 Timestamp when this event was processed.
749749 
750750 format: date-time
751751 
from line 813
813813 
814814 - `processed_at: string`
815815 
816 A timestamp in RFC 3339 format
816 Timestamp when the message was received.
817817 
818818 format: date-time
819819 
from line 853
853853 
854854 - `processed_at: string`
855855 
856 A timestamp in RFC 3339 format
856 Timestamp when the message was sent.
857857 
858858 format: date-time
859859 
from line 877
877877 
878878 - `processed_at: string`
879879 
880 A timestamp in RFC 3339 format
880 Timestamp when compaction was processed.
881881 
882882 format: date-time
883883 
from line 905
905905 
906906 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
907907 
908 What the client should do next in response to this error.
908 What the client should do next.
909909 
910910 - `BetaManagedAgentsRetryStatusRetrying object`
911911 
from line 937
937937 
938938 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
939939 
940 What the client should do next in response to this error.
940 What the client should do next.
941941 
942942 - `BetaManagedAgentsRetryStatusRetrying object`
943943 
from line 963
963963 
964964 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
965965 
966 What the client should do next in response to this error.
966 What the client should do next.
967967 
968968 - `BetaManagedAgentsRetryStatusRetrying object`
969969 
from line 989
989989 
990990 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
991991 
992 What the client should do next in response to this error.
992 What the client should do next.
993993 
994994 - `BetaManagedAgentsRetryStatusRetrying object`
995995 
from line 1019
10191019 
10201020 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
10211021 
1022 What the client should do next in response to this error.
1022 What the client should do next.
10231023 
10241024 - `BetaManagedAgentsRetryStatusRetrying object`
10251025 
from line 1049
10491049 
10501050 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
10511051 
1052 What the client should do next in response to this error.
1052 What the client should do next.
10531053 
10541054 - `BetaManagedAgentsRetryStatusRetrying object`
10551055 
from line 1075
10751075 
10761076 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
10771077 
1078 What the client should do next in response to this error.
1078 What the client should do next.
10791079 
10801080 - `BetaManagedAgentsRetryStatusRetrying object`
10811081 
from line 1105
11051105 
11061106 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
11071107 
1108 What the client should do next in response to this error.
1108 What the client should do next.
11091109 
11101110 - `BetaManagedAgentsRetryStatusRetrying object`
11111111 
from line 1125
11251125 
11261126 - `processed_at: string`
11271127 
1128 A timestamp in RFC 3339 format
1128 Timestamp when the error occurred.
11291129 
11301130 format: date-time
11311131 
from line 1141
11411141 
11421142 - `processed_at: string`
11431143 
1144 A timestamp in RFC 3339 format
1144 Timestamp of status change.
11451145 
11461146 format: date-time
11471147 
from line 1157
11571157 
11581158 - `processed_at: string`
11591159 
1160 A timestamp in RFC 3339 format
1160 Timestamp of status change.
11611161 
11621162 format: date-time
11631163 
from line 1173
11731173 
11741174 - `processed_at: string`
11751175 
1176 A timestamp in RFC 3339 format
1176 Timestamp of status change.
11771177 
11781178 format: date-time
11791179 
from line 1219
12191219 
12201220 - `processed_at: string`
12211221 
1222 A timestamp in RFC 3339 format
1222 Timestamp of status change.
12231223 
12241224 format: date-time
12251225 
from line 1239
12391239 
12401240 - `processed_at: string`
12411241 
1242 A timestamp in RFC 3339 format
1242 Timestamp when the thread was created.
12431243 
12441244 format: date-time
12451245 
from line 1269
12691269 
12701270 - `processed_at: string`
12711271 
1272 A timestamp in RFC 3339 format
1272 Timestamp when outcome evaluation started.
12731273 
12741274 format: date-time
12751275 
from line 1303
13031303 
13041304 - `processed_at: string`
13051305 
1306 A timestamp in RFC 3339 format
1306 Timestamp when outcome evaluation ended.
13071307 
13081308 format: date-time
13091309 
from line 1313
13131313 
13141314 - `usage: BetaManagedAgentsSpanModelUsage`
13151315 
1316 Token usage for a single model request.
1316 Aggregate token usage for this evaluation cycle. Sums across all grader model requests within the cycle.
13171317 
13181318 - `cache_creation_input_tokens: number`
13191319 
from line 1341
13411341 
13421342 - `speed: optional "standard" or "fast" or null`
13431343 
1344 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.
1344 Inference speed tier this request actually ran at. Mirrors `usage.speed` on /v1/messages. Only present when the fast-mode beta is active.
13451345 
13461346 - `"standard"`
13471347 
from line 1359
13591359 
13601360 - `processed_at: string`
13611361 
1362 A timestamp in RFC 3339 format
1362 Timestamp when the model request started.
13631363 
13641364 format: date-time
13651365 
from line 1383
13831383 
13841384 - `model_usage: BetaManagedAgentsSpanModelUsage`
13851385 
1386 Token usage for a single model request.
1386 Token usage for this model request.
13871387 
13881388 - `processed_at: string`
13891389 
1390 A timestamp in RFC 3339 format
1390 Timestamp when the model request completed.
13911391 
13921392 format: date-time
13931393 
from line 1413
14131413 
14141414 - `processed_at: string`
14151415 
1416 A timestamp in RFC 3339 format
1416 Timestamp when this heartbeat was emitted.
14171417 
14181418 format: date-time
14191419 
from line 1443
14431443 
14441444 - `processed_at: string`
14451445 
1446 A timestamp in RFC 3339 format
1446 Timestamp when the outcome was accepted.
14471447 
14481448 format: date-time
14491449 
14501450 - `rubric: BetaManagedAgentsFileRubric or BetaManagedAgentsTextRubric`
14511451 
1452 Rubric for grading the quality of an outcome.
1452 How to grade the outcome. File rubrics are currently resolved to their text content; clients should handle both variants.
14531453 
14541454 - `BetaManagedAgentsFileRubric object`
14551455 
from line 1483
14831483 
14841484 - `processed_at: string`
14851485 
1486 A timestamp in RFC 3339 format
1486 Timestamp when the session was deleted.
14871487 
14881488 format: date-time
14891489 
from line 1503
15031503 
15041504 - `processed_at: string`
15051505 
1506 A timestamp in RFC 3339 format
1506 Timestamp of the status transition.
15071507 
15081508 format: date-time
15091509 
from line 1527
15271527 
15281528 - `processed_at: string`
15291529 
1530 A timestamp in RFC 3339 format
1530 Timestamp of the status transition.
15311531 
15321532 format: date-time
15331533 
from line 1569
15691569 
15701570 - `processed_at: string`
15711571 
1572 A timestamp in RFC 3339 format
1572 Timestamp of the status transition.
15731573 
15741574 format: date-time
15751575 
from line 1617
16171617 
16181618 - `processed_at: optional string or null`
16191619 
1620 A timestamp in RFC 3339 format
1620 Timestamp when this result was processed.
16211621 
16221622 format: date-time
16231623 
from line 1641
16411641 
16421642 - `processed_at: string`
16431643 
1644 A timestamp in RFC 3339 format
1644 Timestamp of the status transition.
16451645 
16461646 format: date-time
16471647 
from line 1661
16611661 
16621662 - `processed_at: string`
16631663 
1664 A timestamp in RFC 3339 format
1664 Timestamp when the update was applied.
16651665 
16661666 format: date-time
16671667 
16681668 - `agent: optional BetaManagedAgentsSessionAgent or null`
16691669 
1670 Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time.
1670 The session's effective agent configuration after the update. Present only when the update changed `agent` (tools or mcp_servers); when present it is the full materialised snapshot, not a diff.
16711671 
16721672 - `type: "agent"`
16731673 
from line 1693
16931693 
16941694 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
16951695 
1696 - `string`
1697 
16961698 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
16971699 
16981700 The model that will power your agent.
from line 1761
17591761 
17601762 High-performance model for agents and coding
17611763 
1762 - `string`
1763 
17641764 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
17651765 
1766 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
1766 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
17671767 
17681768 - `BetaManagedAgentsEffortLow object`
17691769 
from line 1801
18011801 
18021802 - `speed: optional "standard" or "fast"`
18031803 
1804 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.
1804 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
18051805 
18061806 - `"standard"`
18071807 
from line 1809
18091809 
18101810 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
18111811 
1812 Resolved coordinator topology with full agent definitions for each roster member.
1812 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
18131813 
18141814 - `type: "coordinator"`
18151815 
from line 2265
22652265 
22662266 - `budget: optional BetaManagedAgentsBudgetLimit or null`
22672267 
2268 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
2268 The session's budget after the update: the new budget when set or replaced, or null when the update removed it. Present only when the update changed the budget.
22692269 
22702270 - `type: "limit"`
22712271 
22722272 - `max_list_cost: BetaMonetaryAmount`
22732273 
2274 A monetary amount in a specific currency.
2274 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
22752275 
22762276 - `amount: string`
22772277 
from line 2313
23132313 
23142314 - `processed_at: optional string or null`
23152315 
2316 A timestamp in RFC 3339 format
2316 Timestamp when this system message was processed.
23172317 
23182318 format: date-time
23192319 
from line 2329
23292329 
23302330 - `processed_at: string`
23312331 
2332 A timestamp in RFC 3339 format
2332 Timestamp when the snapshot was taken.
23332333 
23342334 format: date-time
23352335 
23362336 - `usage: BetaManagedAgentsSessionUsageSnapshot`
23372337 
2338 Point-in-time snapshot of a session's cumulative usage.
2338 The session's cumulative usage at the snapshot time.
23392339 
23402340 - `active_seconds: optional number`
23412341 
from line 2345
23452345 
23462346 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
23472347 
2348 Prompt-cache creation token usage broken down by cache lifetime.
2348 Tokens used to create prompt cache entries, broken down by cache TTL.
23492349 
23502350 - `ephemeral_1h_input_tokens: optional number`
23512351 
from line 2373
23732373 
23742374 - `list_cost: optional BetaMonetaryAmount`
23752375 
2376 A monetary amount in a specific currency.
2376 Cumulative list cost of the session across all turns, priced at public list rates.
23772377 
23782378 - `output_tokens: optional number`
23792379 
from line 2383
23832383 
23842384 - `server_tool_use: optional BetaManagedAgentsServerToolUsage`
23852385 
2386 Cumulative count of server-executed tool invocations, broken down by tool.
2386 Cumulative server-executed tool usage across all turns.
23872387 
23882388 - `web_fetch_requests: optional number`
23892389 
from line 2399
23992399 
24002400 - `budget: optional BetaManagedAgentsBudgetLimit or null`
24012401 
2402 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
2402 The session's configured budget at the snapshot time, or null when the session has no budget.
24032403 
24042404- `next_page: optional string or null`
24052405 

api/beta/sessions/events/send Changed · +17 / -17 lines

from line 161
161161 
162162 - `source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource`
163163 
164 Union type for image source variants.
164 The source of the image data.
165165 
166166 - `BetaManagedAgentsBase64ImageSource object`
167167 
from line 213
213213 
214214 - `source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource`
215215 
216 Union type for document source variants.
216 The source of the document data.
217217 
218218 - `BetaManagedAgentsBase64DocumentSource object`
219219 
from line 305
305305 
306306 - `result: "allow" or "deny"`
307307 
308 UserToolConfirmationResult enum
308 The confirmation result: 'allow' or 'deny'.
309309 
310310 - `"allow"`
311311 
from line 359
359359 
360360 - `citations: BetaManagedAgentsSearchResultCitations`
361361 
362 Citation settings for a search result.
362 Citation settings for this search result.
363363 
364364 - `enabled: boolean`
365365 
from line 405
405405 
406406 - `rubric: BetaManagedAgentsFileRubricParams or BetaManagedAgentsTextRubricParams`
407407 
408 Rubric for grading the quality of an outcome.
408 How to grade the outcome. Text or file reference.
409409 
410410 - `BetaManagedAgentsFileRubricParams object`
411411 
from line 533
533533 
534534 - `source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource`
535535 
536 Union type for image source variants.
536 The source of the image data.
537537 
538538 - `BetaManagedAgentsBase64ImageSource object`
539539 
from line 585
585585 
586586 - `source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource`
587587 
588 Union type for document source variants.
588 The source of the document data.
589589 
590590 - `BetaManagedAgentsBase64DocumentSource object`
591591 
from line 661
661661 
662662 - `processed_at: optional string or null`
663663 
664 A timestamp in RFC 3339 format
664 Timestamp when the agent finished processing this message.
665665 
666666 format: date-time
667667 
from line 677
677677 
678678 - `processed_at: optional string or null`
679679 
680 A timestamp in RFC 3339 format
680 Timestamp when the interrupt was processed.
681681 
682682 format: date-time
683683 
from line 697
697697 
698698 - `result: "allow" or "deny"`
699699 
700 UserToolConfirmationResult enum
700 The confirmation result: 'allow' or 'deny'.
701701 
702702 - `"allow"`
703703 
from line 715
715715 
716716 - `processed_at: optional string or null`
717717 
718 A timestamp in RFC 3339 format
718 Timestamp when the confirmation was processed.
719719 
720720 format: date-time
721721 
from line 761
761761 
762762 - `citations: BetaManagedAgentsSearchResultCitations`
763763 
764 Citation settings for a search result.
764 Citation settings for this search result.
765765 
766766 - `enabled: boolean`
767767 
from line 797
797797 
798798 - `processed_at: optional string or null`
799799 
800 A timestamp in RFC 3339 format
800 Timestamp when this result was processed.
801801 
802802 format: date-time
803803 
from line 831
831831 
832832 - `processed_at: string`
833833 
834 A timestamp in RFC 3339 format
834 Timestamp when the outcome was accepted.
835835 
836836 format: date-time
837837 
838838 - `rubric: BetaManagedAgentsFileRubric or BetaManagedAgentsTextRubric`
839839 
840 Rubric for grading the quality of an outcome.
840 How to grade the outcome. File rubrics are currently resolved to their text content; clients should handle both variants.
841841 
842842 - `BetaManagedAgentsFileRubric object`
843843 
from line 899
899899 
900900 - `processed_at: optional string or null`
901901 
902 A timestamp in RFC 3339 format
902 Timestamp when this result was processed.
903903 
904904 format: date-time
905905 
from line 931
931931 
932932 - `processed_at: optional string or null`
933933 
934 A timestamp in RFC 3339 format
934 Timestamp when this system message was processed.
935935 
936936 format: date-time
937937 

api/beta/sessions/events/stream Changed · +73 / -75 lines

from line 175
175175 
176176 - `source: BetaManagedAgentsBase64ImageSource or BetaManagedAgentsURLImageSource or BetaManagedAgentsFileImageSource`
177177 
178 Union type for image source variants.
178 The source of the image data.
179179 
180180 - `BetaManagedAgentsBase64ImageSource object`
181181 
from line 227
227227 
228228 - `source: BetaManagedAgentsBase64DocumentSource or BetaManagedAgentsPlainTextDocumentSource or BetaManagedAgentsURLDocumentSource or BetaManagedAgentsFileDocumentSource`
229229 
230 Union type for document source variants.
230 The source of the document data.
231231 
232232 - `BetaManagedAgentsBase64DocumentSource object`
233233 
from line 303
303303 
304304 - `processed_at: optional string or null`
305305 
306 A timestamp in RFC 3339 format
306 Timestamp when the agent finished processing this message.
307307 
308308 format: date-time
309309 
from line 319
319319 
320320 - `processed_at: optional string or null`
321321 
322 A timestamp in RFC 3339 format
322 Timestamp when the interrupt was processed.
323323 
324324 format: date-time
325325 
from line 339
339339 
340340 - `result: "allow" or "deny"`
341341 
342 UserToolConfirmationResult enum
342 The confirmation result: 'allow' or 'deny'.
343343 
344344 - `"allow"`
345345 
from line 357
357357 
358358 - `processed_at: optional string or null`
359359 
360 A timestamp in RFC 3339 format
360 Timestamp when the confirmation was processed.
361361 
362362 format: date-time
363363 
from line 403
403403 
404404 - `citations: BetaManagedAgentsSearchResultCitations`
405405 
406 Citation settings for a search result.
406 Citation settings for this search result.
407407 
408408 - `enabled: boolean`
409409 
from line 439
439439 
440440 - `processed_at: optional string or null`
441441 
442 A timestamp in RFC 3339 format
442 Timestamp when this result was processed.
443443 
444444 format: date-time
445445 
from line 467
467467 
468468 - `processed_at: string`
469469 
470 A timestamp in RFC 3339 format
470 Timestamp when this tool use was processed.
471471 
472472 format: date-time
473473 
from line 499
499499 
500500 - `processed_at: string`
501501 
502 A timestamp in RFC 3339 format
502 Timestamp when this response was generated.
503503 
504504 format: date-time
505505 
from line 515
515515 
516516 - `processed_at: string`
517517 
518 A timestamp in RFC 3339 format
518 Timestamp when this thinking was produced.
519519 
520520 format: date-time
521521 
from line 543
543543 
544544 - `processed_at: string`
545545 
546 A timestamp in RFC 3339 format
546 Timestamp when this event was processed.
547547 
548548 format: date-time
549549 
550550 - `evaluated_permission: optional BetaManagedAgentsAgentEvaluatedPermission`
551551 
552 AgentEvaluatedPermission enum
552 The evaluated permission policy for this tool invocation.
553553 
554554 - `"allow"`
555555 
from line 559
559559 
560560 - `evaluation: optional BetaManagedAgentsAgentToolEvaluation`
561561 
562 Names the resolved permission_policy that produced evaluated_permission, and under auto carries the judgement. Open union: clients must tolerate unknown variants.
562 Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask).
563563 
564564 - `BetaManagedAgentsAgentToolEvaluationAlwaysAllow object`
565565 
from line 581
581581 
582582 - `evaluated_permission: BetaManagedAgentsAgentAutoEvaluatedPermission`
583583 
584 The server's per-invocation judgement under the auto permission policy. Its type always equals the event's top-level evaluated_permission. Open union: clients must tolerate unknown variants.
584 The server's judgement for this invocation.
585585 
586586 - `BetaManagedAgentsAgentAutoEvaluatedPermissionAllow object`
587587 
from line 633
633633 
634634 - `processed_at: string`
635635 
636 A timestamp in RFC 3339 format
636 Timestamp when this event was processed.
637637 
638638 format: date-time
639639 
from line 681
681681 
682682 - `processed_at: string`
683683 
684 A timestamp in RFC 3339 format
684 Timestamp when this event was processed.
685685 
686686 format: date-time
687687 
688688 - `evaluated_permission: optional BetaManagedAgentsAgentEvaluatedPermission`
689689 
690 AgentEvaluatedPermission enum
690 The evaluated permission policy for this tool invocation.
691691 
692692 - `evaluation: optional BetaManagedAgentsAgentToolEvaluation`
693693 
694 Names the resolved permission_policy that produced evaluated_permission, and under auto carries the judgement. Open union: clients must tolerate unknown variants.
694 Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask).
695695 
696696 - `session_thread_id: optional string or null`
697697 
from line 709
709709 
710710 - `processed_at: string`
711711 
712 A timestamp in RFC 3339 format
712 Timestamp when this event was processed.
713713 
714714 format: date-time
715715 
from line 777
777777 
778778 - `processed_at: string`
779779 
780 A timestamp in RFC 3339 format
780 Timestamp when the message was received.
781781 
782782 format: date-time
783783 
from line 817
817817 
818818 - `processed_at: string`
819819 
820 A timestamp in RFC 3339 format
820 Timestamp when the message was sent.
821821 
822822 format: date-time
823823 
from line 841
841841 
842842 - `processed_at: string`
843843 
844 A timestamp in RFC 3339 format
844 Timestamp when compaction was processed.
845845 
846846 format: date-time
847847 
from line 869
869869 
870870 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
871871 
872 What the client should do next in response to this error.
872 What the client should do next.
873873 
874874 - `BetaManagedAgentsRetryStatusRetrying object`
875875 
from line 901
901901 
902902 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
903903 
904 What the client should do next in response to this error.
904 What the client should do next.
905905 
906906 - `BetaManagedAgentsRetryStatusRetrying object`
907907 
from line 927
927927 
928928 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
929929 
930 What the client should do next in response to this error.
930 What the client should do next.
931931 
932932 - `BetaManagedAgentsRetryStatusRetrying object`
933933 
from line 953
953953 
954954 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
955955 
956 What the client should do next in response to this error.
956 What the client should do next.
957957 
958958 - `BetaManagedAgentsRetryStatusRetrying object`
959959 
from line 983
983983 
984984 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
985985 
986 What the client should do next in response to this error.
986 What the client should do next.
987987 
988988 - `BetaManagedAgentsRetryStatusRetrying object`
989989 
from line 1013
10131013 
10141014 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
10151015 
1016 What the client should do next in response to this error.
1016 What the client should do next.
10171017 
10181018 - `BetaManagedAgentsRetryStatusRetrying object`
10191019 
from line 1039
10391039 
10401040 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
10411041 
1042 What the client should do next in response to this error.
1042 What the client should do next.
10431043 
10441044 - `BetaManagedAgentsRetryStatusRetrying object`
10451045 
from line 1069
10691069 
10701070 - `retry_status: BetaManagedAgentsRetryStatusRetrying or BetaManagedAgentsRetryStatusExhausted or BetaManagedAgentsRetryStatusTerminal`
10711071 
1072 What the client should do next in response to this error.
1072 What the client should do next.
10731073 
10741074 - `BetaManagedAgentsRetryStatusRetrying object`
10751075 
from line 1089
10891089 
10901090 - `processed_at: string`
10911091 
1092 A timestamp in RFC 3339 format
1092 Timestamp when the error occurred.
10931093 
10941094 format: date-time
10951095 
from line 1105
11051105 
11061106 - `processed_at: string`
11071107 
1108 A timestamp in RFC 3339 format
1108 Timestamp of status change.
11091109 
11101110 format: date-time
11111111 
from line 1121
11211121 
11221122 - `processed_at: string`
11231123 
1124 A timestamp in RFC 3339 format
1124 Timestamp of status change.
11251125 
11261126 format: date-time
11271127 
from line 1137
11371137 
11381138 - `processed_at: string`
11391139 
1140 A timestamp in RFC 3339 format
1140 Timestamp of status change.
11411141 
11421142 format: date-time
11431143 
from line 1183
11831183 
11841184 - `processed_at: string`
11851185 
1186 A timestamp in RFC 3339 format
1186 Timestamp of status change.
11871187 
11881188 format: date-time
11891189 
from line 1203
12031203 
12041204 - `processed_at: string`
12051205 
1206 A timestamp in RFC 3339 format
1206 Timestamp when the thread was created.
12071207 
12081208 format: date-time
12091209 
from line 1233
12331233 
12341234 - `processed_at: string`
12351235 
1236 A timestamp in RFC 3339 format
1236 Timestamp when outcome evaluation started.
12371237 
12381238 format: date-time
12391239 
from line 1267
12671267 
12681268 - `processed_at: string`
12691269 
1270 A timestamp in RFC 3339 format
1270 Timestamp when outcome evaluation ended.
12711271 
12721272 format: date-time
12731273 
from line 1277
12771277 
12781278 - `usage: BetaManagedAgentsSpanModelUsage`
12791279 
1280 Token usage for a single model request.
1280 Aggregate token usage for this evaluation cycle. Sums across all grader model requests within the cycle.
12811281 
12821282 - `cache_creation_input_tokens: number`
12831283 
from line 1305
13051305 
13061306 - `speed: optional "standard" or "fast" or null`
13071307 
1308 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.
1308 Inference speed tier this request actually ran at. Mirrors `usage.speed` on /v1/messages. Only present when the fast-mode beta is active.
13091309 
13101310 - `"standard"`
13111311 
from line 1323
13231323 
13241324 - `processed_at: string`
13251325 
1326 A timestamp in RFC 3339 format
1326 Timestamp when the model request started.
13271327 
13281328 format: date-time
13291329 
from line 1347
13471347 
13481348 - `model_usage: BetaManagedAgentsSpanModelUsage`
13491349 
1350 Token usage for a single model request.
1350 Token usage for this model request.
13511351 
13521352 - `processed_at: string`
13531353 
1354 A timestamp in RFC 3339 format
1354 Timestamp when the model request completed.
13551355 
13561356 format: date-time
13571357 
from line 1377
13771377 
13781378 - `processed_at: string`
13791379 
1380 A timestamp in RFC 3339 format
1380 Timestamp when this heartbeat was emitted.
13811381 
13821382 format: date-time
13831383 
from line 1407
14071407 
14081408 - `processed_at: string`
14091409 
1410 A timestamp in RFC 3339 format
1410 Timestamp when the outcome was accepted.
14111411 
14121412 format: date-time
14131413 
14141414 - `rubric: BetaManagedAgentsFileRubric or BetaManagedAgentsTextRubric`
14151415 
1416 Rubric for grading the quality of an outcome.
1416 How to grade the outcome. File rubrics are currently resolved to their text content; clients should handle both variants.
14171417 
14181418 - `BetaManagedAgentsFileRubric object`
14191419 
from line 1447
14471447 
14481448 - `processed_at: string`
14491449 
1450 A timestamp in RFC 3339 format
1450 Timestamp when the session was deleted.
14511451 
14521452 format: date-time
14531453 
from line 1467
14671467 
14681468 - `processed_at: string`
14691469 
1470 A timestamp in RFC 3339 format
1470 Timestamp of the status transition.
14711471 
14721472 format: date-time
14731473 
from line 1491
14911491 
14921492 - `processed_at: string`
14931493 
1494 A timestamp in RFC 3339 format
1494 Timestamp of the status transition.
14951495 
14961496 format: date-time
14971497 
from line 1533
15331533 
15341534 - `processed_at: string`
15351535 
1536 A timestamp in RFC 3339 format
1536 Timestamp of the status transition.
15371537 
15381538 format: date-time
15391539 
from line 1581
15811581 
15821582 - `processed_at: optional string or null`
15831583 
1584 A timestamp in RFC 3339 format
1584 Timestamp when this result was processed.
15851585 
15861586 format: date-time
15871587 
from line 1605
16051605 
16061606 - `processed_at: string`
16071607 
1608 A timestamp in RFC 3339 format
1608 Timestamp of the status transition.
16091609 
16101610 format: date-time
16111611 
from line 1625
16251625 
16261626 - `processed_at: string`
16271627 
1628 A timestamp in RFC 3339 format
1628 Timestamp when the update was applied.
16291629 
16301630 format: date-time
16311631 
16321632 - `agent: optional BetaManagedAgentsSessionAgent or null`
16331633 
1634 Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time.
1634 The session's effective agent configuration after the update. Present only when the update changed `agent` (tools or mcp_servers); when present it is the full materialised snapshot, not a diff.
16351635 
16361636 - `type: "agent"`
16371637 
from line 1657
16571657 
16581658 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
16591659 
1660 - `string`
1661 
16601662 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
16611663 
16621664 The model that will power your agent.
from line 1725
17231725 
17241726 High-performance model for agents and coding
17251727 
1726 - `string`
1727 
17281728 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
17291729 
1730 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
1730 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
17311731 
17321732 - `BetaManagedAgentsEffortLow object`
17331733 
from line 1765
17651765 
17661766 - `speed: optional "standard" or "fast"`
17671767 
1768 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.
1768 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
17691769 
17701770 - `"standard"`
17711771 
from line 1773
17731773 
17741774 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
17751775 
1776 Resolved coordinator topology with full agent definitions for each roster member.
1776 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
17771777 
17781778 - `type: "coordinator"`
17791779 
from line 2229
22292229 
22302230 - `budget: optional BetaManagedAgentsBudgetLimit or null`
22312231 
2232 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
2232 The session's budget after the update: the new budget when set or replaced, or null when the update removed it. Present only when the update changed the budget.
22332233 
22342234 - `type: "limit"`
22352235 
22362236 - `max_list_cost: BetaMonetaryAmount`
22372237 
2238 A monetary amount in a specific currency.
2238 Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge.
22392239 
22402240 - `amount: string`
22412241 
from line 2293
22932293 
22942294 - `content: BetaManagedAgentsTextBlock`
22952295 
2296 Regular text content.
2296 A partial element of the content array at index, typed like the element itself — the same shape the buffered agent.message carries in content.
22972297 
22982298 - `index: optional number`
22992299 
23002300 Which entry in the previewed event's content array this fragment lands in. Insert content as that entry when the index is new; append to the existing entry otherwise.
23012301 
2302 format: uint32
2303 
23042302 - `event_id: string`
23052303 
23062304 The id of the event being previewed. Matches event.id on the corresponding event_start and the buffered event that reconciles the preview.
from line 2327
23292327 
23302328 - `processed_at: optional string or null`
23312329 
2332 A timestamp in RFC 3339 format
2330 Timestamp when this system message was processed.
23332331 
23342332 format: date-time
23352333 
from line 2343
23452343 
23462344 - `processed_at: string`
23472345 
2348 A timestamp in RFC 3339 format
2346 Timestamp when the snapshot was taken.
23492347 
23502348 format: date-time
23512349 
23522350 - `usage: BetaManagedAgentsSessionUsageSnapshot`
23532351 
2354 Point-in-time snapshot of a session's cumulative usage.
2352 The session's cumulative usage at the snapshot time.
23552353 
23562354 - `active_seconds: optional number`
23572355 
from line 2359
23612359 
23622360 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
23632361 
2364 Prompt-cache creation token usage broken down by cache lifetime.
2362 Tokens used to create prompt cache entries, broken down by cache TTL.
23652363 
23662364 - `ephemeral_1h_input_tokens: optional number`
23672365 
from line 2387
23892387 
23902388 - `list_cost: optional BetaMonetaryAmount`
23912389 
2392 A monetary amount in a specific currency.
2390 Cumulative list cost of the session across all turns, priced at public list rates.
23932391 
23942392 - `output_tokens: optional number`
23952393 
from line 2397
23992397 
24002398 - `server_tool_use: optional BetaManagedAgentsServerToolUsage`
24012399 
2402 Cumulative count of server-executed tool invocations, broken down by tool.
2400 Cumulative server-executed tool usage across all turns.
24032401 
24042402 - `web_fetch_requests: optional number`
24052403 
from line 2413
24152413 
24162414 - `budget: optional BetaManagedAgentsBudgetLimit or null`
24172415 
2418 A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`.
2416 The session's configured budget at the snapshot time, or null when the session has no budget.
24192417 
24202418## Example
24212419 
Feedback