The whole hunk
from line 16, old and new numbered
/
lines
from line 16
1616
1717 - `string`
1818
19 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
19 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
2020
2121 - `"message-batches-2024-09-24"`
2222
from line 100
100100
101101 - `"ce-user-management-2026-07-13"`
102102
103 - `"mid-conversation-output-config-2026-07-01"`
104
105 - `"thinking-binding-controls-2026-08-01"`
106
107 - `"mid-conversation-system-clear-at-2026-08-21"`
108
103109## Body parameters
104110
105111- `agent: optional BetaManagedAgentsSessionAgentUpdate`
from line 580
574580
575581 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
576582
577 - `"claude-sonnet-5" or "claude-fable-5" or "claude-opus-5" or 10 more`
583 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
578584
579585 The model that will power your agent.
580586
581587 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
582588
589 - `"claude-fable-5-1"`
590
591 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
592
583593 - `"claude-sonnet-5"`
584594
585595 High-performance model for coding and agents
from line 1138
11281138
11291139 - `outcome_evaluations: array of BetaManagedAgentsOutcomeEvaluationResource`
11301140
1131 Per-outcome evaluation state. One entry per define_outcome event sent to the session.
1141 Per-outcome evaluation state. One entry per `define_outcome` event sent to the session.
11321142
11331143 - `completed_at: string or null`
11341144
from line 1152
11421152
11431153 - `explanation: string or null`
11441154
1145 Grader's verdict text from the most recent evaluation. For satisfied, explains why criteria are met; for needs_revision (intermediate), what's missing; for failed, why unrecoverable.
1155 Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable.
11461156
11471157 - `iteration: number`
11481158
from line 1280
12701280
12711281 - `active_seconds: optional number`
12721282
1273 Cumulative time in seconds the session spent in running status. Excludes idle time.
1283 Cumulative time in seconds the session spent in `running` status. Excludes idle time.
12741284
12751285 format: double
12761286