List Session Threads changedapi/beta/sessions/threads/list
Nearest release: v2.1.283, published 3 hours 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+14added
Lines−14removed
From line
151
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits11to this page, all time
The whole hunk
from line 151, old and new numbered
/
from line 151
151151
152152 - `agent: BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`
153153
154 The resolved agent a `session_thread` runs.
154 Resolved agent definition for this thread. Snapshot of the agent at thread creation time.
155155
156156 - `BetaManagedAgentsSessionThreadAgent object`
157157
from line 181
181181
182182 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
183183
184 - `string`
185
184186 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
185187
186188 The model that will power your agent.
from line 249
247249
248250 High-performance model for agents and coding
249251
250 - `string`
251
252252 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
253253
254 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
254 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.
255255
256256 - `BetaManagedAgentsEffortLow object`
257257
from line 289
289289
290290 - `speed: optional "standard" or "fast"`
291291
292 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.
292 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.
293293
294294 - `"standard"`
295295
from line 693
693693
694694 - `archived_at: string or null`
695695
696 A timestamp in RFC 3339 format
696 When the thread was archived. Null if not archived.
697697
698698 format: date-time
699699
700700 - `created_at: string`
701701
702 A timestamp in RFC 3339 format
702 When the thread was created.
703703
704704 format: date-time
705705
from line 713
713713
714714 - `stats: BetaManagedAgentsSessionThreadStats or null`
715715
716 Timing statistics for a session thread.
716 Timing statistics for this thread. Null until the thread's first status transition.
717717
718718 - `active_seconds: optional number`
719719
from line 735
735735
736736 - `status: BetaManagedAgentsSessionThreadStatus`
737737
738 SessionThreadStatus enum
738 Current execution status of the thread.
739739
740740 - `"running"`
741741
from line 747
747747
748748 - `updated_at: string`
749749
750 A timestamp in RFC 3339 format
750 When the thread was last updated.
751751
752752 format: date-time
753753
754754 - `usage: BetaManagedAgentsSessionThreadUsage or null`
755755
756 Cumulative token usage for a session thread across all turns.
756 Cumulative token usage for this thread. Null until the thread's first idle transition.
757757
758758 - `active_seconds: optional number`
759759
from line 763
763763
764764 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
765765
766 Prompt-cache creation token usage broken down by cache lifetime.
766 Tokens used to create prompt cache entries, broken down by cache TTL.
767767
768768 - `ephemeral_1h_input_tokens: optional number`
769769
from line 791
791791
792792 - `list_cost: optional BetaMonetaryAmount or null`
793793
794 A monetary amount in a specific currency.
794 Cumulative list cost of this thread across all turns, priced at public list rates. Absent until cost tracking is available for the thread. Each figure is rounded to the nearest cent independently and the session's aggregate `usage.list_cost` additionally includes session runtime, so per-thread costs do not sum exactly to the session figure; the session figure is authoritative and is what a budget is enforced against.
795795
796796 - `amount: string`
797797
from line 809
809809
810810 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
811811
812 Cumulative count of server-executed tool invocations, broken down by tool.
812 Cumulative server-executed tool usage across all turns of this thread. Absent until server-tool tracking is available for the thread.
813813
814814 - `web_fetch_requests: optional number`
815815
No line in this hunk matches that.