Follow Discord
Sweep 28 Sep 2026 · 18:16Z Build v2.1.284 505 read Stable v2.1.277 Latest v2.1.284 Next v2.1.284 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

Sessions changedapi/beta/sessions

Nearest release: v2.1.284, published 8 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+8,125added
Lines−7,985removed
From line 183 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits15to this page, all time

The whole hunk

from line 183, old and new numbered
/
lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 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 = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
186 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
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`
192 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
193193 
194 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
195 
196194 The model that will power your agent.
197195 
198196 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
199197 
198 - `"claude-sonnet-5-5"`
199 
200 Efficient model for coding and agents
201 
200202 - `"claude-opus-5-5"`
201203 
202204 Powerful intelligence for coding, knowledge work, and long-running agents
from line 209
207209 
208210 - `"claude-sonnet-5"`
209211 
210 High-performance model for coding and agents
212 Efficient model for coding and agents
211213 
212214 - `"claude-fable-5"`
213215 
from line 259
257259 
258260 High-performance model for agents and coding
259261 
262 - `string`
263 
260264 - `BetaManagedAgentsModelConfigParams object`
261265 
262266 An object that defines additional configuration control over model use
from line 1195
11911195 
11921196 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
11931197 
1194 - `string`
1198 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
11951199 
1196 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
1197 
11981200 The model that will power your agent.
11991201 
12001202 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
12011203 
1204 - `"claude-sonnet-5-5"`
1205 
1206 Efficient model for coding and agents
1207 
12021208 - `"claude-opus-5-5"`
12031209 
12041210 Powerful intelligence for coding, knowledge work, and long-running agents
from line 1215
12091215 
12101216 - `"claude-sonnet-5"`
12111217 
1212 High-performance model for coding and agents
1218 Efficient model for coding and agents
12131219 
12141220 - `"claude-fable-5"`
12151221 
from line 1265
12591265 
12601266 High-performance model for agents and coding
12611267 
1268 - `string`
1269 
12621270 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
12631271 
12641272 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.
from line 2508
25002508 
25012509 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
25022510 
2503 - `string`
2511 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
25042512 
2505 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
2506 
25072513 The model that will power your agent.
25082514 
25092515 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
25102516 
2517 - `"claude-sonnet-5-5"`
2518 
2519 Efficient model for coding and agents
2520 
25112521 - `"claude-opus-5-5"`
25122522 
25132523 Powerful intelligence for coding, knowledge work, and long-running agents
from line 2528
25182528 
25192529 - `"claude-sonnet-5"`
25202530 
2521 High-performance model for coding and agents
2531 Efficient model for coding and agents
25222532 
25232533 - `"claude-fable-5"`
25242534 
from line 2578
25682578 
25692579 High-performance model for agents and coding
25702580 
2581 - `string`
2582 
25712583 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
25722584 
25732585 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.
from line 3747
37353747 
37363748 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
37373749 
3738 - `string`
3750 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
37393751 
3740 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
3741 
37423752 The model that will power your agent.
37433753 
37443754 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
37453755 
3756 - `"claude-sonnet-5-5"`
3757 
3758 Efficient model for coding and agents
3759 
37463760 - `"claude-opus-5-5"`
37473761 
37483762 Powerful intelligence for coding, knowledge work, and long-running agents
from line 3767
37533767 
37543768 - `"claude-sonnet-5"`
37553769 
3756 High-performance model for coding and agents
3770 Efficient model for coding and agents
37573771 
37583772 - `"claude-fable-5"`
37593773 
from line 3817
38033817 
38043818 High-performance model for agents and coding
38053819 
3820 - `string`
3821 
38063822 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
38073823 
38083824 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.
from line 5458
54425458 
54435459 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
54445460 
5445 - `string`
5461 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
54465462 
5447 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
5448 
54495463 The model that will power your agent.
54505464 
54515465 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
54525466 
5467 - `"claude-sonnet-5-5"`
5468 
5469 Efficient model for coding and agents
5470 
54535471 - `"claude-opus-5-5"`
54545472 
54555473 Powerful intelligence for coding, knowledge work, and long-running agents
from line 5478
54605478 
54615479 - `"claude-sonnet-5"`
54625480 
5463 High-performance model for coding and agents
5481 Efficient model for coding and agents
54645482 
54655483 - `"claude-fable-5"`
54665484 
from line 5528
55105528 
55115529 High-performance model for agents and coding
55125530 
5531 - `string`
5532 
55135533 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
55145534 
55155535 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.
from line 6838
68186838 
68196839 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
68206840 
6821 - `string`
6841 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
68226842 
6823 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
6824 
68256843 The model that will power your agent.
68266844 
68276845 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
68286846 
6847 - `"claude-sonnet-5-5"`
6848 
6849 Efficient model for coding and agents
6850 
68296851 - `"claude-opus-5-5"`
68306852 
68316853 Powerful intelligence for coding, knowledge work, and long-running agents
from line 6858
68366858 
68376859 - `"claude-sonnet-5"`
68386860 
6839 High-performance model for coding and agents
6861 Efficient model for coding and agents
68406862 
68416863 - `"claude-fable-5"`
68426864 
from line 6908
68866908 
68876909 High-performance model for agents and coding
68886910 
6911 - `string`
6912 
68896913 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
68906914 
68916915 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.
from line 7996
79727996 
79737997 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
79747998 
7975 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
7999 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
79768000 
79778001 The model that will power your agent.
79788002 
79798003 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
79808004 
7981 - `string`
8005 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
79828006 
7983 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
7984 
79858007 The model that will power your agent.
79868008 
79878009 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
79888010 
8011 - `"claude-sonnet-5-5"`
8012 
8013 Efficient model for coding and agents
8014 
79898015 - `"claude-opus-5-5"`
79908016 
79918017 Powerful intelligence for coding, knowledge work, and long-running agents
from line 8022
79968022 
79978023 - `"claude-sonnet-5"`
79988024 
7999 High-performance model for coding and agents
8025 Efficient model for coding and agents
80008026 
80018027 - `"claude-fable-5"`
80028028 
from line 8072
80468072 
80478073 High-performance model for agents and coding
80488074 
8075 - `string`
8076 
80498077 - `BetaManagedAgentsModelConfigParams object`
80508078 
80518079 An object that defines additional configuration control over model use
from line 8368
83408368 
83418369 - `BetaManagedAgentsAutoPolicy object`
83428370 
8343 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.
8344 
8345 - `BetaManagedAgentsGrepToolConfigParams object`
8346 
8347 Configuration override for the grep tool.
8348 
8349 - `type: optional "grep"`
8350 
8351 - `name: "grep"`
8352 
8353 Must be "grep".
8354 
8355 - `enabled: optional boolean or null`
8356 
8357 Whether this tool is enabled and available to Claude. Overrides the default_config setting.
8358 
8359 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
8360 
8361 Permission p
8371 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 j
Feedback