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

List Agent Versions changed

api/beta/agents/versions/list

Nearest release: v2.1.268, published under an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+368added
Lines−313removed
From line 1 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits9to this page, all time

The whole hunk

from line 1, old and new numbered
/
lines
from line 1
1---
2title: List Agent Versions
3url: https://platform.claude.com/docs/en/api/beta/agents/versions/list
4---
5 
16# List Agent Versions
27 
38**GET** `/v1/agents/{agent_id}/versions`
from line 33
2833 
2934 - `string`
3035 
31 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
36 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
3237 
3338 - `"message-batches-2024-09-24"`
3439 
from line 81
7681 
7782 - `"user-profiles-2026-08-18"`
7883 
84 - `"user-profiles-2026-09-04"`
85 
7986 - `"advisor-tool-2026-03-01"`
8087 
8188 - `"managed-agents-2026-04-01"`
from line 125
118125 
119126 - `"mid-conversation-system-clear-at-2026-08-21"`
120127 
128- `"anthropic-workspace-id": optional string`
129 
121130## Returns
122131 
123132- `data: array of BetaManagedAgentsAgent`
from line 133
124133 
125134 Agent versions.
126135 
136 - `type: "agent"`
137 
127138 - `id: string`
128139 
129140 - `archived_at: string or null`
from line 153
142153 
143154 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
144155 
145 - `name: string`
146 
147156 - `type: "url"`
148157 
158 - `name: string`
159 
149160 - `url: string`
150161 
151162 - `metadata: map[string]`
from line 285
274285 
275286 Resolved coordinator topology with a concrete agent roster.
276287 
288 - `type: "coordinator"`
289 
277290 - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor`
278291 
279292 Agents the coordinator may spawn as session threads, each resolved to a specific version.
from line 295
282295 
283296 A resolved agent reference with a concrete version.
284297 
285 - `id: string`
286 
287298 - `type: "agent"`
288299 
300 - `id: string`
301 
289302 - `version: number`
290303 
291304 format: int32
from line 307
294307 
295308 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
296309 
310 - `type: "advisor"`
311 
297312 - `model: string`
298313 
299314 The advisor model id.
300315 
301 - `type: "advisor"`
302 
303 - `type: "coordinator"`
304 
305316 - `name: string`
306317 
307318 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`
from line 321
310321 
311322 A resolved Anthropic-managed skill.
312323 
313 - `skill_id: string`
314 
315324 - `type: "anthropic"`
316325 
326 - `skill_id: string`
327 
317328 - `version: string`
318329 
319330 - `BetaManagedAgentsCustomSkill object`
from line 331
320331 
321332 A resolved user-created custom skill.
322333 
323 - `skill_id: string`
324 
325334 - `type: "custom"`
326335 
336 - `skill_id: string`
337 
327338 - `version: string`
328339 
329340 - `system: string or null`
from line 343
332343 
333344 - `BetaManagedAgentsAgentToolset20260401 object`
334345 
346 - `type: "agent_toolset_20260401"`
347 
335348 - `configs: array of BetaManagedAgentsAgentToolConfig`
336349 
337350 - `BetaManagedAgentsBashToolConfig object`
from line 351
338351 
339352 Configuration for the bash tool.
340353 
354 - `type: "bash"`
355 
341356 - `enabled: boolean`
342357 
343358 - `name: "bash"`
344359 
345 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
360 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
346361 
347362 Permission policy for tool execution.
348363 
from line 373
358373 
359374 - `type: "always_ask"`
360375 
361 - `type: "bash"`
376 - `BetaManagedAgentsAutoPolicy object`
362377 
378 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.
379 
380 - `type: "auto"`
381 
363382 - `BetaManagedAgentsEditToolConfig object`
364383 
365384 Configuration for the edit tool.
366385 
386 - `type: "edit"`
387 
367388 - `enabled: boolean`
368389 
369390 - `name: "edit"`
370391 
371 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
392 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
372393 
373394 Permission policy for tool execution.
374395 
from line 401
380401 
381402 Tool calls require user confirmation before execution.
382403 
383 - `type: "edit"`
404 - `BetaManagedAgentsAutoPolicy object`
384405 
406 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.
407 
385408 - `BetaManagedAgentsReadToolConfig object`
386409 
387410 Configuration for the read tool.
388411 
412 - `type: "read"`
413 
389414 - `enabled: boolean`
390415 
391416 - `name: "read"`
392417 
393 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
418 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
394419 
395420 Permission policy for tool execution.
396421 
from line 427
402427 
403428 Tool calls require user confirmation before execution.
404429 
405 - `type: "read"`
430 - `BetaManagedAgentsAutoPolicy object`
406431 
432 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.
433 
407434 - `BetaManagedAgentsWriteToolConfig object`
408435 
409436 Configuration for the write tool.
410437 
438 - `type: "write"`
439 
411440 - `enabled: boolean`
412441 
413442 - `name: "write"`
414443 
415 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
444 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
416445 
417446 Permission policy for tool execution.
418447 
from line 453
424453 
425454 Tool calls require user confirmation before execution.
426455 
427 - `type: "write"`
456 - `BetaManagedAgentsAutoPolicy object`
428457 
458 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.
459 
429460 - `BetaManagedAgentsGlobToolConfig object`
430461 
431462 Configuration for the glob tool.
432463 
464 - `type: "glob"`
465 
433466 - `enabled: boolean`
434467 
435468 - `name: "glob"`
436469 
437 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
470 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
438471 
439472 Permission policy for tool execution.
440473 
from line 479
446479 
447480 Tool calls require user confirmation before execution.
448481 
449 - `type: "glob"`
482 - `BetaManagedAgentsAutoPolicy object`
450483 
484 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.
485 
451486 - `BetaManagedAgentsGrepToolConfig object`
452487 
453488 Configuration for the grep tool.
454489 
490 - `type: "grep"`
491 
455492 - `enabled: boolean`
456493 
457494 - `name: "grep"`
458495 
459 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
496 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
460497 
461498 Permission policy for tool execution.
462499 
from line 505
468505 
469506 Tool calls require user confirmation before execution.
470507 
471 - `type: "grep"`
508 - `BetaManagedAgentsAutoPolicy object`
472509 
510 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.
511 
473512 - `BetaManagedAgentsWebFetchToolConfig object`
474513 
475514 Configuration for the web_fetch tool.
476515 
516 - `type: "web_fetch"`
517 
477518 - `enabled: boolean`
478519 
479520 - `name: "web_fetch"`
480521 
481 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
522 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
482523 
483524 Permission policy for tool execution.
484525 
from line 531
490531 
491532 Tool calls require user confirmation before execution.
492533 
493 - `type: "web_fetch"`
534 - `BetaManagedAgentsAutoPolicy object`
494535 
536 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.
537 
495538 - `allowed_domains: optional array of string`
496539 
497540 - `blocked_domains: optional array of string`
from line 547
504547 
505548 Configuration for the web_search tool.
506549 
550 - `type: "web_search"`
551 
507552 - `enabled: boolean`
508553 
509554 - `name: "web_search"`
510555 
511 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
556 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
512557 
513558 Permission policy for tool execution.
514559 
from line 565
520565 
521566 Tool calls require user confirmation before execution.
522567 
523 - `type: "web_search"`
568 - `BetaManagedAgentsAutoPolicy object`
524569 
570 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.
571 
525572 - `allowed_domains: optional array of string`
526573 
527574 - `blocked_domains: optional array of string`
from line 609
562609 
563610 - `enabled: boolean`
564611 
565 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
612 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
566613 
567614 Permission policy for tool execution.
568615 
from line 621
574621 
575622 Tool calls require user confirmation before execution.
576623 
577 - `type: "agent_toolset_20260401"`
624 - `BetaManagedAgentsAutoPolicy object`
578625 
626 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.
627 
579628 - `BetaManagedAgentsMCPToolset object`
580629 
630 - `type: "mcp_toolset"`
631 
581632 - `configs: array of BetaManagedAgentsMCPToolConfig`
582633 
583634 - `enabled: boolean`
from line 635
584635 
585636 - `name: string`
586637 
587 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
638 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
588639 
589640 Permission policy for tool execution.
590641 
from line 647
596647 
597648 Tool calls require user confirmation before execution.
598649 
650 - `BetaManagedAgentsAutoPolicy object`
651 
652 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.
653 
599654 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`
600655 
601656 Resolved default configuration for all tools from an MCP server.
from line 657
602657 
603658 - `enabled: boolean`
604659 
605 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
660 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
606661 
607662 Permission policy for tool execution.
608663 
from line 669
614669 
615670 Tool calls require user confirmation before execution.
616671 
617 - `mcp_server_name: string`
672 - `BetaManagedAgentsAutoPolicy object`
618673 
619 - `type: "mcp_toolset"`
674 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.
620675 
676 - `mcp_server_name: string`
677 
621678 - `BetaManagedAgentsCustomTool object`
622679 
623680 A custom tool as returned in API responses.
624681 
682 - `type: "custom"`
683 
625684 - `description: string`
626685 
627686 - `input_schema: BetaManagedAgentsCustomToolInputSchema`
from line 694
635694 - `required: optional array of string or null`
636695 
637696 - `name: string`
638 
639 - `type: "custom"`
640 
641 - `type: "agent"`
642697 
643698 - `updated_at: string`
644699