Follow Discord
Sweep 09 Oct 2026 · 17:27Z Build v2.1.296 517 read Stable v2.1.287 Latest v2.1.296 Next v2.1.296 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

List Sessions changedapi/beta/sessions/list

Nearest release: v2.1.296, published 4 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+571added
Lines−437removed
From line 295 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits18to this page, all time

The whole hunk

from line 295, old and new numbered
/
lines

The two sides of this change are more than 400 edits apart, too far apart to line up, so this is the differ's own diff of it and the words inside a line are not marked.

from line 295
295295 
296296 - `"claude-haiku-4-5"`
297297 
298 Fastest model with near-frontier intelligence
299 
300298 - `"claude-haiku-4-5-20251001"`
301299 
302 Fastest model with near-frontier intelligence
303 
304300 - `"claude-opus-4-5"`
305301 
306302 Powerful intelligence for long-running agents and coding
from line 365
369365 
370366 - `"fast"`
371367 
372 - `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
368 - `multiagent: BetaManagedAgentsSessionMultiagent or null`
373369 
374370 Resolved multiagent orchestration configuration. Null when the agent is single-threaded.
375371 
376 - `type: "coordinator"`
377 
378 - `agents: array of BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`
379 
380 Full `agent` definitions the coordinator may spawn as session threads.
381 
382 - `BetaManagedAgentsSessionThreadAgent object`
383 
384 Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`.
385 
386 - `type: "agent"`
387 
388 - `id: string`
389 
390 - `description: string or null`
391 
392 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
393 
394 - `type: "url"`
372 - `BetaManagedAgentsSessionMultiagentCoordinator object`
373 
374 Resolved coordinator topology with full agent definitions for each roster member.
375 
376 - `type: "coordinator"`
377 
378 - `agents: array of BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`
379 
380 Full `agent` definitions the coordinator may spawn as session threads.
381 
382 - `BetaManagedAgentsSessionThreadAgent object`
383 
384 Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`.
385 
386 - `type: "agent"`
387 
388 - `id: string`
389 
390 - `description: string or null`
391 
392 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
393 
394 - `type: "url"`
395 
396 - `name: string`
397 
398 - `url: string`
399 
400 - `model: BetaManagedAgentsModelConfig`
401 
402 Model identifier and configuration.
395403 
396404 - `name: string`
397405 
398 - `url: string`
399 
400 - `model: BetaManagedAgentsModelConfig`
401 
402 Model identifier and configuration.
403 
404 - `name: string`
405 
406 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`
407 
408 - `BetaManagedAgentsAnthropicSkill object`
409 
410 A resolved Anthropic-managed skill.
411 
412 - `type: "anthropic"`
413 
414 - `skill_id: string`
415 
416 - `version: string`
417 
418 - `BetaManagedAgentsCustomSkill object`
419 
420 A resolved user-created custom skill.
421 
422 - `type: "custom"`
423 
424 - `skill_id: string`
425 
426 - `version: string`
427 
428 - `system: string or null`
429 
430 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`
431 
432 - `BetaManagedAgentsAgentToolset20260401 object`
433 
434 - `type: "agent_toolset_20260401"`
435 
436 - `configs: array of BetaManagedAgentsAgentToolConfig`
437 
438 - `BetaManagedAgentsBashToolConfig object`
439 
440 Configuration for the bash tool.
441 
442 - `type: "bash"`
406 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`
407 
408 - `BetaManagedAgentsAnthropicSkill object`
409 
410 A resolved Anthropic-managed skill.
411 
412 - `type: "anthropic"`
413 
414 - `skill_id: string`
415 
416 - `version: string`
417 
418 - `BetaManagedAgentsCustomSkill object`
419 
420 A resolved user-created custom skill.
421 
422 - `type: "custom"`
423 
424 - `skill_id: string`
425 
426 - `version: string`
427 
428 - `system: string or null`
429 
430 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`
431 
432 - `BetaManagedAgentsAgentToolset20260401 object`
433 
434 - `type: "agent_toolset_20260401"`
435 
436 - `configs: array of BetaManagedAgentsAgentToolConfig`
437 
438 - `BetaManagedAgentsBashToolConfig object`
439 
440 Configuration for the bash tool.
441 
442 - `type: "bash"`
443 
444 - `enabled: boolean`
445 
446 - `name: "bash"`
447 
448 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
449 
450 Permission policy for tool execution.
451 
452 - `BetaManagedAgentsAlwaysAllowPolicy object`
453 
454 Tool calls are automatically approved without user confirmation.
455 
456 - `type: "always_allow"`
457 
458 - `BetaManagedAgentsAlwaysAskPolicy object`
459 
460 Tool calls require user confirmation before execution.
461 
462 - `type: "always_ask"`
463 
464 - `BetaManagedAgentsAutoPolicy object`
465 
466 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.
467 
468 - `type: "auto"`
469 
470 - `BetaManagedAgentsEditToolConfig object`
471 
472 Configuration for the edit tool.
473 
474 - `type: "edit"`
475 
476 - `enabled: boolean`
477 
478 - `name: "edit"`
479 
480 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
481 
482 Permission policy for tool execution.
483 
484 - `BetaManagedAgentsAlwaysAllowPolicy object`
485 
486 Tool calls are automatically approved without user confirmation.
487 
488 - `BetaManagedAgentsAlwaysAskPolicy object`
489 
490 Tool calls require user confirmation before execution.
491 
492 - `BetaManagedAgentsAutoPolicy object`
493 
494 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.
495 
496 - `BetaManagedAgentsReadToolConfig object`
497 
498 Configuration for the read tool.
499 
500 - `type: "read"`
501 
502 - `enabled: boolean`
503 
504 - `name: "read"`
505 
506 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
507 
508 Permission policy for tool execution.
509 
510 - `BetaManagedAgentsAlwaysAllowPolicy object`
511 
512 Tool calls are automatically approved without user confirmation.
513 
514 - `BetaManagedAgentsAlwaysAskPolicy object`
515 
516 Tool calls require user confirmation before execution.
517 
518 - `BetaManagedAgentsAutoPolicy object`
519 
520 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.
521 
522 - `BetaManagedAgentsWriteToolConfig object`
523 
524 Configuration for the write tool.
525 
526 - `type: "write"`
527 
528 - `enabled: boolean`
529 
530 - `name: "write"`
531 
532 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
533 
534 Permission policy for tool execution.
535 
536 - `BetaManagedAgentsAlwaysAllowPolicy object`
537 
538 Tool calls are automatically approved without user confirmation.
539 
540 - `BetaManagedAgentsAlwaysAskPolicy object`
541 
542 Tool calls require user confirmation before execution.
543 
544 - `BetaManagedAgentsAutoPolicy object`
545 
546 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.
547 
548 - `BetaManagedAgentsGlobToolConfig object`
549 
550 Configuration for the glob tool.
551 
552 - `type: "glob"`
553 
554 - `enabled: boolean`
555 
556 - `name: "glob"`
557 
558 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
559 
560 Permission policy for tool execution.
561 
562 - `BetaManagedAgentsAlwaysAllowPolicy object`
563 
564 Tool calls are automatically approved without user confirmation.
565 
566 - `BetaManagedAgentsAlwaysAskPolicy object`
567 
568 Tool calls require user confirmation before execution.
569 
570 - `BetaManagedAgentsAutoPolicy object`
571 
572 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.
573 
574 - `BetaManagedAgentsGrepToolConfig object`
575 
576 Configuration for the grep tool.
577 
578 - `type: "grep"`
579 
580 - `enabled: boolean`
581 
582 - `name: "grep"`
583 
584 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
585 
586 Permission policy for tool execution.
587 
588 - `BetaManagedAgentsAlwaysAllowPolicy object`
589 
590 Tool calls are automatically approved without user confirmation.
591 
592 - `BetaManagedAgentsAlwaysAskPolicy object`
593 
594 Tool calls require user confirmation before execution.
595 
596 - `BetaManagedAgentsAutoPolicy object`
597 
598 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.
599 
600 - `BetaManagedAgentsWebFetchToolConfig object`
601 
602 Configuration for the web_fetch tool.
603 
604 - `type: "web_fetch"`
605 
606 - `enabled: boolean`
607 
608 - `name: "web_fetch"`
609 
610 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
611 
612 Permission policy for tool execution.
613 
614 - `BetaManagedAgentsAlwaysAllowPolicy object`
615 
616 Tool calls are automatically approved without user confirmation.
617 
618 - `BetaManagedAgentsAlwaysAskPolicy object`
619 
620 Tool calls require user confirmation before execution.
621 
622 - `BetaManagedAgentsAutoPolicy object`
623 
624 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.
625 
626 - `url_sources: BetaManagedAgentsWebFetchURLSources or null`
627 
628 Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source.
629 
630 - `client_tool_results: BetaManagedAgentsWebFetchURLSourceToolFilter or null`
631 
632 Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results.
633 
634 - `BetaManagedAgentsWebFetchURLSourceAll object`
635 
636 Every URL from this source may be fetched. This is the default.
637 
638 - `type: "all"`
639 
640 - `BetaManagedAgentsWebFetchURLSourceNone object`
641 
642 This source contributes no URLs that may be fetched.
643 
644 - `type: "none"`
645 
646 - `BetaManagedAgentsWebFetchURLSourceOnly object`
647 
648 Only the named tools' results contribute URLs that may be fetched.
649 
650 - `type: "only"`
651 
652 - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference`
653 
654 The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results.
655 
656 - `type: "tool_reference"`
657 
658 Must be "tool_reference".
659 
660 - `name: string`
661 
662 Name of the tool. Compared exactly, so upper and lower case letters are different.
663 
664 minLength: 1, maxLength: 128
665 
666 - `BetaManagedAgentsWebFetchURLSourceExcept object`
667 
668 Every tool's results contribute URLs that may be fetched, except the named tools' results.
669 
670 - `type: "except"`
671 
672 - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference`
673 
674 The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results.
675 
676 - `type: "tool_reference"`
677 
678 Must be "tool_reference".
679 
680 - `name: string`
681 
682 Name of the tool. Compared exactly, so upper and lower case letters are different.
683 
684 minLength: 1, maxLength: 128
685 
686 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceToolFilter or null`
687 
688 Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both.
689 
690 - `user_input: BetaManagedAgentsWebFetchURLSourceUserInput or null`
691 
692 Whether URLs in the text of user messages may be fetched. Null when not set, which allows them.
693 
694 - `BetaManagedAgentsWebFetchURLSourceAll object`
695 
696 Every URL from this source may be fetched. This is the default.
697 
698 - `BetaManagedAgentsWebFetchURLSourceNone object`
699 
700 This source contributes no URLs that may be fetched.
701 
702 - `allowed_domains: optional array of string`
703 
704 - `blocked_domains: optional array of string`
705 
706 - `max_content_tokens: optional number or null`
707 
708 format: int32
709 
710 - `BetaManagedAgentsWebSearchToolConfig object`
711 
712 Configuration for the web_search tool.
713 
714 - `type: "web_search"`
715 
716 - `enabled: boolean`
717 
718 - `name: "web_search"`
719 
720 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
721 
722 Permission policy for tool execution.
723 
724 - `BetaManagedAgentsAlwaysAllowPolicy object`
725 
726 Tool calls are automatically approved without user confirmation.
727 
728 - `BetaManagedAgentsAlwaysAskPolicy object`
729 
730 Tool calls require user confirmation before execution.
731 
732 - `BetaManagedAgentsAutoPolicy object`
733 
734 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.
735 
736 - `allowed_domains: optional array of string`
737 
738 - `blocked_domains: optional array of string`
739 
740 - `user_location: optional BetaManagedAgentsUserLocation or null`
741 
742 Approximate user location for search result localization.
743 
744 - `type: "approximate"`
745 
746 Location precision. Only "approximate" is supported.
747 
748 - `city: optional string or null`
749 
750 City name.
751 
752 minLength: 1, maxLength: 255
753 
754 - `country: optional string or null`
755 
756 Two-letter ISO 3166-1 country code, uppercase.
757 
758 - `region: optional string or null`
759 
760 Region or state name.
761 
762 minLength: 1, maxLength: 255
763 
764 - `timezone: optional string or null`
765 
766 IANA timezone identifier, e.g. "America/Los_Angeles".
767 
768 minLength: 1, maxLength: 255
769 
770 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig`
771 
772 Resolved default configuration for agent tools.
443773 
444774 - `enabled: boolean`
445775 
446 - `name: "bash"`
447 
448776 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
449777 
450778 Permission policy for tool execution.
from line 781
453781 
454782 Tool calls are automatically approved without user confirmation.
455783 
456 - `type: "always_allow"`
457 
458784 - `BetaManagedAgentsAlwaysAskPolicy object`
459785 
460786 Tool calls require user confirmation before execution.
461787 
462 - `type: "always_ask"`
463 
464788 - `BetaManagedAgentsAutoPolicy object`
465789 
466790 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.
467791 
468 - `type: "auto"`
469 
470 - `BetaManagedAgentsEditToolConfig object`
471 
472 Configuration for the edit tool.
473 
474 - `type: "edit"`
792 - `BetaManagedAgentsMCPToolset object`
793 
794 - `type: "mcp_toolset"`
795 
796 - `configs: array of BetaManagedAgentsMCPToolConfig`
475797 
476798 - `enabled: boolean`
477799 
478 - `name: "edit"`
800 - `name: string`
479801 
480802 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
481803 
from line 815
493815 
494816 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.
495817 
496 - `BetaManagedAgentsReadToolConfig object`
497 
498 Configuration for the read tool.
499 
500 - `type: "read"`
818 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`
819 
820 Resolved default configuration for all tools from an MCP server.
501821 
502822 - `enabled: boolean`
503823 
504 - `name: "read"`
505 
506824 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
507825 
508826 Permission policy for tool execution.
from line 837
519837 
520838 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.
521839 
522 - `BetaManagedAgentsWriteToolConfig object`
523 
524 Configuration for the write tool.
525 
526 - `type: "write"`
527 
528 - `enabled: boolean`
529 
530 - `name: "write"`
531 
532 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
533 
534 Permission policy for tool execution.
535 
536 - `BetaManagedAgentsAlwaysAllowPolicy object`
537 
538 Tool calls are automatically approved without user confirmation.
539 
540 - `BetaManagedAgentsAlwaysAskPolicy object`
541 
542 Tool calls require user confirmation before execution.
543 
544 - `BetaManagedAgentsAutoPolicy object`
545 
546 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.
547 
548 - `BetaManagedAgentsGlobToolConfig object`
549 
550 Configuration for the glob tool.
551 
552 - `type: "glob"`
553 
554 - `enabled: boolean`
555 
556 - `name: "glob"`
557 
558 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
559 
560 Permission policy for tool execution.
561 
562 - `BetaManagedAgentsAlwaysAllowPolicy object`
563 
564 Tool calls are automatically approved without user confirmation.
565 
566 - `BetaManagedAgentsAlwaysAskPolicy object`
567 
568 Tool calls require user confirmation before execution.
569 
570 - `BetaManagedAgentsAutoPolicy object`
571 
572 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.
573 
574 - `BetaManagedAgentsGrepToolConfig object`
575 
576 Configuration for the grep tool.
577 
578 - `type: "grep"`
579 
580 - `enabled: boolean`
581 
582 - `name: "grep"`
583 
584 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
585 
586 Permission policy for tool execution.
587 
588 - `BetaManagedAgentsAlwaysAllowPolicy object`
589 
590 Tool calls are automatically approved without user confirmation.
591 
592 - `BetaManagedAgentsAlwaysAskPolicy object`
593 
594 Tool calls require user confirmation before execution.
595 
596 - `BetaManagedAgentsAutoPolicy object`
597 
598 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.
599 
600 - `BetaManagedAgentsWebFetchToolConfig object`
601 
602 Configuration for the web_fetch tool.
603 
604 - `type: "web_fetch"`
605 
606 - `enabled: boolean`
607 
608 - `name: "web_fetch"`
609 
610 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
611 
612 Permission policy for tool execution.
613 
614 - `BetaManagedAgentsAlwaysAllowPolicy object`
615 
616 Tool calls are automatically approved without user confirmation.
617 
618 - `BetaManagedAgentsAlwaysAskPolicy object`
619 
620 Tool calls require user confirmation before execution.
621 
622 - `BetaManagedAgentsAutoPolicy object`
623 
624 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.
625 
626 - `url_sources: BetaManagedAgentsWebFetchURLSources or null`
627 
628 Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source.
629 
630 - `client_tool_results: BetaManagedAgentsWebFetchURLSourceToolFilter or null`
631 
632 Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results.
633 
634 - `BetaManagedAgentsWebFetchURLSourceAll object`
635 
636 Every URL from this source may be fetched. This is the default.
637 
638 - `type: "all"`
639 
640 - `BetaManagedAgentsWebFetchURLSourceNone object`
641 
642 This source contributes no URLs that may be fetched.
643 
644 - `type: "none"`
645 
646 - `BetaManagedAgentsWebFetchURLSourceOnly object`
647 
648 Only the named tools' results contribute URLs that may be fetched.
649 
650 - `type: "only"`
651 
652 - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference`
653 
654 The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results.
655 
656 - `type: "tool_reference"`
657 
658 Must be "tool_reference".
659 
660 - `name: string`
661 
662 Name of the tool. Compared exactly, so upper and lower case letters are different.
663 
664 minLength: 1, maxLength: 128
665 
666 - `BetaManagedAgentsWebFetchURLSourceExcept object`
667 
668 Every tool's results contribute URLs that may be fetched, except the named tools' results.
669 
670 - `type: "except"`
671 
672 - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference`
673 
674 The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results.
675 
676 - `type: "tool_reference"`
677 
678 Must be "tool_reference".
679 
680 - `name: string`
681 
682 Name of the tool. Compared exactly, so upper and lower case letters are different.
683 
684 minLength: 1, maxLength: 128
685 
686 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceToolFilter or null`
687 
688 Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both.
689 
690 - `user_input: BetaManagedAgentsWebFetchURLSourceUserInput or null`
691 
692 Whether URLs in the text of user messages may be fetched. Null when not set, which allows them.
693 
694 - `BetaManagedAgentsWebFetchURLSourceAll object`
695 
696 Every URL from this source may be fetched. This is the default.
697 
698 - `BetaManagedAgentsWebFetchURLSourceNone object`
699 
700 This source contributes no URLs that may be fetched.
701 
702 - `allowed_domains: optional array of string`
703 
704 - `blocked_domains: optional array of string`
705 
706 - `max_content_tokens: optional number or null`
707 
708 format: int32
709 
710 - `BetaManagedAgentsWebSearchToolConfig object`
711 
712 Configuration for the web_search tool.
713 
714 - `type: "web_search"`
715 
716 - `enabled: boolean`
717 
718 - `name: "web_search"`
719 
720 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
721 
722 Permission policy for tool execution.
723 
724 - `BetaManagedAgentsAlwaysAllowPolicy object`
725 
726 Tool calls are automatically approved without user confirmation.
727 
728 - `BetaManagedAgentsAlwaysAskPolicy object`
729 
730 Tool calls require user confirmation before execution.
731 
732 - `BetaManagedAgentsAutoPolicy object`
733 
734 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.
735 
736 - `allowed_domains: optional array of string`
737 
738 - `blocked_domains: optional array of string`
739 
740 - `user_location: optional BetaManagedAgentsUserLocation or null`
741 
742 Approximate user location for search result localization.
743 
744 - `type: "approximate"`
745 
746 Location precision. Only "approximate" is supported.
747 
748 - `city: optional string or null`
749 
750 City name.
751 
752 minLength: 1, maxLength: 255
753 
754 - `country: optional string or null`
755 
756 Two-letter ISO 3166-1 country code, uppercase.
757 
758 - `region: optional string or null`
759 
760 Region or state name.
761 
762 minLength: 1, maxLength: 255
763 
764 - `timezone: optional string or null`
765 
766 IANA timezone identifier, e.g. "America/Los_Angeles".
767 
768 minLength: 1, maxLength: 255
769 
770 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig`
771 
772 Resolved default configuration for agent tools.
773 
774 - `enabled: boolean`
775 
776 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
777 
778 Permission policy for tool execution.
779 
780 - `BetaManagedAgentsAlwaysAllowPolicy object`
781 
782 Tool calls are automatically approved without user confirmation.
783 
784 - `BetaManagedAgentsAlwaysAskPolicy object`
785 
786 Tool calls require user confirmation before execution.
787 
788 - `BetaManagedAgentsAutoPolicy object`
789 
790 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.
791 
792 - `BetaManagedAgentsMCPToolset object`
793 
794 - `type: "mcp_toolset"`
795 
796 - `configs: array of BetaManagedAgentsMCPToolConfig`
797 
798 - `enabled: boolean`
840 - `mcp_server_name: string`
841 
842 - `BetaManagedAgentsCustomTool object`
843 
844 A custom tool as returned in API responses.
845 
846 - `type: "custom"`
847 
848 - `description: string`
849 
850 - `input_schema: BetaManagedAgentsCustomToolInputSchema`
851 
852 JSON Schema for custom tool input parameters.
853 
854 - `type: "object"`
855 
856 - `properties: optional map[unknown] or null`
857 
858 - `required: optional array of string or null`
799859 
800860 - `name: string`
801861 
802 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
803 
804 Permission policy for tool execution.
805 
806 - `BetaManagedAgentsAlwaysAllowPolicy object`
807 
808 Tool calls are automatically approved without user confirmation.
809 
810 - `BetaManagedAgentsAlwaysAskPolicy object`
811 
812 Tool calls require user confirmation before execution.
813 
814 - `BetaManagedAgentsAutoPolicy object`
815 
816 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.
817 
818 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`
819 
820 Resolved default configuration for all tools from an MCP server.
821 
822 - `enabled: boolean`
823 
824 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
825 
826 Permission policy for tool execution.
827 
828 - `BetaManagedAgentsAlwaysAllowPolicy object`
829 
830 Tool calls are automatically approved without user confirmation.
831 
832 - `BetaManagedAgentsAlwaysAskPolicy object`
833 
834 Tool calls require user confirmation before execution.
835 
836 - `BetaManagedAgentsAutoPolicy object`
837 
838 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.
839 
840 - `mcp_server_name: string`
841 
842 - `BetaManagedAgentsCustomTool object`
843 
844 A custom tool as returned in API responses.
845 
846 - `type: "custom"`
847 
848 - `description: string`
849 
850 - `input_schema: BetaManagedAgentsCustomToolInputSchema`
851 
852 JSON Schema for custom tool input parameters.
853 
854 - `type: "object"`
855 
856 - `properties: optional map[unknown] or null`
857 
858 - `required: optional array of string or null`
862 - `version: number`
863 
864 format: int32
865 
866 - `BetaManagedAgentsAdvisor object`
867 
868 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
869 
870 - `type: "advisor"`
871 
872 - `model: string`
873 
874 The advisor model id.
875 
876 - `BetaManagedAgentsSessionMultiagent20261001 object`
877 
878 Resolved multiagent configuration with three members, as copied to the `session` at creation.
879 
880 - `type: "multiagent_20261001"`
881 
882 - `advisor: BetaManagedAgentsMultiagentAdvisor`
883 
884 Whether the session's primary thread can consult an advisor model.
885 
886 - `BetaManagedAgentsMultiagentAdvisorEnabled object`
887 
888 The session's primary thread can consult `model` mid-turn.
889 
890 - `type: "enabled"`
891 
892 - `model: string`
893 
894 The advisor model id.
895 
896 - `BetaManagedAgentsMultiagentAdvisorDisabled object`
897 
898 The agent has no advisor.
899 
900 - `type: "disabled"`
901 
902 - `subagents: BetaManagedAgentsSessionMultiagentSubagents`
903 
904 Whether the agent can spawn session threads.
905 
906 - `BetaManagedAgentsSessionMultiagentSubagentsEnabled object`
907 
908 The agent can spawn session threads.
909 
910 - `type: "enabled"`
911 
912 - `inline_agents: BetaManagedAgentsMultiagentInlineAgents`
913 
914 Whether the agent can define inline agents, which are not saved, when it spawns session threads.
915 
916 - `BetaManagedAgentsMultiagentInlineAgentsEnabled object`
917 
918 The agent can define inline agents.
919 
920 - `type: "enabled"`
921 
922 - `BetaManagedAgentsMultiagentInlineAgentsDisabled object`
923 
924 The agent cannot define inline agents.
925 
926 - `type: "disabled"`
927 
928 - `predefined_agents: array of BetaManagedAgentsSessionThreadAgent`
929 
930 Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads.
931 
932 - `type: "agent"`
933 
934 - `id: string`
935 
936 - `description: string or null`
937 
938 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
939 
940 - `model: BetaManagedAgentsModelConfig`
941 
942 Model identifier and configuration.
859943 
860944 - `name: string`
861945 
862 - `version: number`
863 
864 format: int32
865 
866 - `BetaManagedAgentsAdvisor object`
867 
868 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
869 
870 - `type: "advisor"`
871 
872 - `model: string`
873 
874 The advisor model id.
946 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`
947 
948 - `system: string or null`
949 
950 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`
951 
952 - `version: number`
953 
954 format: int32
955 
956 - `BetaManagedAgentsMultiagentSubagentsDisabled object`
957 
958 The agent cannot spawn session threads.
959 
960 - `type: "disabled"`
961 
962 - `workflows: BetaManagedAgentsSessionMultiagentWorkflows`
963 
964 Whether the agent can start workflow runs.
965 
966 - `BetaManagedAgentsSessionMultiagentWorkflowsEnabled object`
967 
968 The agent can start workflow runs.
969 
970 - `type: "enabled"`
971 
972 - `inline_agents: BetaManagedAgentsMultiagentInlineAgents`
973 
974 Whether a run's plan can define inline agents, which are not saved.
975 
976 - `predefined_agents: array of BetaManagedAgentsSessionThreadAgent`
977 
978 Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use.
979 
980 - `type: "agent"`
981 
982 - `id: string`
983 
984 - `description: string or null`
985 
986 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
987 
988 - `model: BetaManagedAgentsModelConfig`
989 
990 Model identifier and configuration.
991 
992 - `name: string`
993 
994 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`
995 
996 - `system: string or null`
997 
998 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`
999 
1000 - `version: number`
1001 
1002 format: int32
1003 
1004 - `BetaManagedAgentsMultiagentWorkflowsDisabled object`
1005 
1006 The agent cannot start workflow runs.
1007 
1008 - `type: "disabled"`
8751009 
8761010 - `name: string`
8771011 
8781012 
Feedback