One read of Claude Developer Platformapi-20260821T200735Z
123 pages moved out of 584 read.
Pages moved
123
significant first
Pages read
584
in this capture
Captured
20:07 UTC
Corpus hash
10824cc06631
index-hash
What this read moved
101-123 of 123, page 5 of 5This capture is too large to show at once. Changes 101-123 of 123 are below, significant first; the rest are on the following screens.
build-with-claude/fast-mode Changed · +1 / -1 lines
from line 22
2222* Claude Opus 4.8 (claude-opus-4-8)
2323
2424<Note>
25 Fast mode for Claude Opus 5 and Claude Opus 4.8 is available as a research preview on the Claude API, including [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), only. It is not available on Amazon Bedrock, Google Cloud, or Microsoft Foundry.
25 Fast mode for Claude Opus 5 and Claude Opus 4.8 is available as a research preview on the Claude API, including [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), only. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud, or Microsoft Foundry.
2626</Note>
2727
2828<Note>
build-with-claude/handling-stop-reasons Changed · +1 / -2 lines
from line 897
897897
898898 <CodeGroup exclude="shell:cURL">
899899 ```bash CLI
900 RESPONSE=$(ant messages create --max-tokens 1024 \
901 --format jsonl < request.yaml)
900 RESPONSE=$(ant messages create --max-tokens 1024 --format jsonl < request.yaml)
902901
903902 # Check if the response was truncated mid tool use
904903 STOP_REASON=$(jq -r '.stop_reason' <<<"$RESPONSE")
build-with-claude/mid-conversation-system-messages Changed · +2 / -2 lines
from line 12
1212
1313Mid-conversation system messages close that gap. You append a `{"role": "system"}` message at the point in the conversation where the new instruction becomes relevant, instead of editing the top-level `system` field. The cached prefix stays the same, so the next request still reads it from cache, and the new instruction is still applied as a system instruction rather than as ordinary user text.
1414
15This page covers two features: mid-conversation system messages, which are generally available, and [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes), a beta introduced with Claude Opus 5 that applies the same approach to the `tools` array.
15This page covers two features: mid-conversation system messages, and [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes), a beta introduced with Claude Opus 5 that applies the same approach to the `tools` array.
1616
1717<Note>
1818 Mid-conversation system messages are available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai).
1919
20 This feature is available on Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 4.8, Claude Opus 5, and Claude Sonnet 5. No beta header is required for mid-conversation system messages.
20 This feature is available on Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 4.8, and Claude Opus 5. No beta header is required for mid-conversation system messages. This feature is not available on Claude Sonnet 5; use the top-level `system` field instead.
2121
2222 Mid-conversation tool changes are in beta and require the `mid-conversation-tool-changes-2026-07-01` beta header. They are available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.8, and Claude Opus 5, on the Claude API, Amazon Bedrock, and Google Cloud. They are not available on Claude Sonnet 5.
2323</Note>
build-with-claude/prompt-caching Changed · +1 / -1 lines
from line 659
659659| **Non-tool results passed to extended thinking requests** | ✓ | ✓ | Model-specific | On Opus 4.5+ and Sonnet 4.6+, thinking blocks are preserved by default, so the cache remains valid (✓). On earlier Opus/Sonnet models and all Haiku models, all previously-cached thinking blocks are stripped from context, and any messages that follow those thinking blocks are removed from the cache (✘). For more details, see [Caching with thinking blocks](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#caching-with-thinking-blocks). |
660660
661661<Note>
662 On Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 4.8, Claude Opus 5, and Claude Sonnet 5, you can add a new system instruction partway through a conversation without invalidating the system or message caches. Append a `{"role": "system"}` message to `messages` instead of editing the top-level `system` field, so the cached prefix stays unchanged. See [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages).
662 On Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 4.8, and Claude Opus 5, you can add a new system instruction partway through a conversation without invalidating the system or message caches. Append a `{"role": "system"}` message to `messages` instead of editing the top-level `system` field, so the cached prefix stays unchanged. This feature is not available on Claude Sonnet 5; use the top-level `system` field instead. See [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages).
663663</Note>
664664
665665### Tracking cache performance
build-with-claude/refusals-and-fallback Changed · +4 / -0 lines
from line 218
218218
219219Set the `fallbacks` parameter to the string `"default"` and send the `server-side-fallback-2026-07-01` beta header. The API then applies the requested model's server-defined default routing, which selects a recommended fallback model based on the refusal category the classifier reports, so refused requests are served without you maintaining a model list as recommendations change.
220220
221Default routing never draws the up-front [oversized-image rejection](https://platform.claude.com/docs/en/build-with-claude/vision-coordinates#oversized-image-error) for models you did not choose: a routed model that would resize an image marked `"oversized_image": "error"` is dropped from the routing instead, so a marked image is never served resized.
222
221223<CodeGroup>
222224 ```bash cURL
223225 curl --fail-with-body -sS https://api.anthropic.com/v1/messages \
from line 486
484486### Naming your own fallback models
485487
486488Instead of default routing, you can set `fallbacks` to a list of up to three models. When the requested model declines, the API runs the next model in the chain on the same request. Use this form when you want to control exactly which models serve refused requests, such as pinning a model your application has qualified.
489
490Named fallback models count toward the [oversized-image check](https://platform.claude.com/docs/en/build-with-claude/vision-coordinates#oversized-image-error): a request whose image block sets `"oversized_image": "error"` is checked up front against the requested model and every named fallback, is rejected if any of them would resize that image, and the rejection's reported rescale target fits them all.
487491
488492<CodeGroup>
489493 ```bash cURL
build-with-claude/structured-outputs Changed · +1 / -1 lines
from line 19
1919You can use these features independently or together in the same request.
2020
2121<Tip>
22 **Migrating from beta?** The `output_format` parameter has moved to `output_config.format`, and beta headers are no longer required. The old beta header (`structured-outputs-2025-11-13`) and `output_format` parameter will continue working for a transition period. See the following code examples for the updated API shape.
22 **Migrating from beta?** The `output_format` parameter has moved to `output_config.format`, and beta headers are no longer required. The API continues to accept the old beta header (`structured-outputs-2025-11-13`) and the `output_format` request field for a transition period, but the Python SDK (v1.0 and later) does not accept `output_format={...}` on `client.beta.messages.create()` or `count_tokens()` and raises a `TypeError`; use `output_config` instead. See the following code examples for the updated API shape.
2323</Tip>
2424
2525## Why use structured outputs
build-with-claude/working-with-messages Changed · +2 / -2 lines
from line 592
592592
593593 ```python Python
594594 import base64
595 import httpx
595 import httpx2
596596
597597 # Option 1: Base64-encoded image
598598 image_url = "https://platform.claude.com/docs/images/vision-example.jpg"
599599 image_media_type = "image/jpeg"
600 image_data = base64.standard_b64encode(httpx.get(image_url).content).decode("utf-8")
600 image_data = base64.standard_b64encode(httpx2.get(image_url).content).decode("utf-8")
601601
602602 message = anthropic.Anthropic().messages.create(
603603 model="claude-opus-5",
cli-sdks-libraries/cli/scripting Changed · +1 / -2 lines
from line 148
148148`--transform id --raw-output` on a list endpoint emits one bare ID per line, so standard tools such as `head` and `xargs` apply directly. Capture the first result, then pass it to a follow-up command:
149149
150150```bash
151FIRST_AGENT=$(ant beta:agents list \
152 --transform id --raw-output | head -1)
151FIRST_AGENT=$(ant beta:agents list --transform id --raw-output | head -1)
153152
154153ant beta:agents:versions list \
155154 --agent-id "$FIRST_AGENT" \
cli-sdks-libraries/libraries/apple-foundation-models Changed · +1 / -1 lines
from line 9
99Requests go directly from your app to the Claude API; Apple is not in the request path and does not see prompts or responses. Usage is billed to your Anthropic account at [standard API pricing](https://platform.claude.com/docs/en/about-claude/pricing), so your organization needs an available credit balance or an active billing method. Your app decides when to use Claude and when to use Apple's on-device model: pass whichever model you want to each session.
1010
1111<Note>
12 **Beta.** This package targets the Foundation Models server-side language model API introduced in the OS 27 betas. APIs might change before general availability.
12 **Beta.** This package targets the Foundation Models server-side language model API introduced in the OS 27 betas. APIs might change during the beta.
1313</Note>
1414
1515<Info>
home Changed · +2 / -2 lines
from line 37
3737 API reference
3838 </HomeCardLink>
3939
40 <HomeCardLink icon="code-brackets" href="https://platform.claude.com/docs/en/api/client-sdks">
40 <HomeCardLink icon="code-brackets" href="https://platform.claude.com/docs/en/cli-sdks-libraries/overview">
4141 Client SDKs
4242 </HomeCardLink>
4343 </HomePlatformCard>
from line 90
9090 Choose a model
9191 </HomeJourneyLink>
9292
93 <HomeJourneyLink icon="code-brackets" href="https://platform.claude.com/docs/en/api/client-sdks">
93 <HomeJourneyLink icon="code-brackets" href="https://platform.claude.com/docs/en/cli-sdks-libraries/overview">
9494 Install an SDK
9595 </HomeJourneyLink>
9696
manage-claude/analytics-api Changed · +1 / -1 lines
from line 81
8181
8282Claude Enterprise Analytics API data is available for dates on or after January 1, 2026.
8383
84**Engagement and adoption endpoints** (user activity, summaries, projects, skills, connectors) return a per-day snapshot for the date you specify. Data for a given day is aggregated at 10UTC the following day and is typically available with a 1-day lag. Exact freshness varies by query, so rather than assuming a fixed lag, check the error response: requesting a date that is not yet available returns a 400 error naming the most recent available day. If data is not available well past the typical lag, it usually indicates a data pipeline failure on Anthropic's side; contact support if the gap persists.
84**Engagement and adoption endpoints** (user activity, summaries, projects, skills, connectors) return a per-day snapshot for the date you specify. Data for a given day is aggregated at 10:00 UTC the following day and is typically available with a 1-day lag. Exact freshness varies by query, so rather than assuming a fixed lag, check the error response: requesting a date that is not yet available returns a 400 error naming the most recent available day. If data is not available well past the typical lag, it usually indicates a data pipeline failure on Anthropic's side; contact support if the gap persists.
8585
8686**Cost and usage endpoints** follow a different freshness model. Data is typically available within four hours of the underlying usage but may take up to 24 hours. Values for a given date can be revised for up to 30 days as late events arrive and reconciliation runs. For invoicing-grade totals, query dates at least 30 days in the past.
8787
manage-claude/cmek Changed · +1 / -1 lines
from line 108
108108* Claude Code Desktop, Claude Code on the web, and Claude in Slack. Anthropic recommends disabling any of these that are not appropriate for your use case in the admin console.
109109* Beta and research preview features may not be covered by CMEK and can break in CMEK organizations, for example, Claude Security and Claude Design.
110110* On-demand data export under **Settings** > **Privacy**.
111* [Personal preferences - Instructions for Claude section](https://claude.ai/new#settings/general). These are set at the account level and shared across all of a user's organizations.
111* [Personal preferences - Instructions for Claude section](https://claude.ai/new#settings/general) and Cowork Global instructions. These are set at the account level and shared across all of a user's organizations.
112112
113113On both products, account data for users in your organization (such as names, email addresses, and profile pictures) is not encrypted under your key.
114114
manage-claude/compliance-faq Changed · +1 / -1 lines
from line 130
130130
131131<AccordionGroup>
132132 <Accordion title="How do I correlate Compliance API records with my SIEM?">
133 Join `Activity` records to your SIEM on `actor.user_id`, `actor.email_address`, `actor.ip_address`, and `created_at`. See [Design your compliance integration](https://platform.claude.com/docs/en/manage-claude/compliance-integration-patterns#correlate-with-your-siem) for the join-key table and consumption patterns.
133 Join `Activity` records to your SIEM on `actor.user_id`, `actor.email_address`, `actor.ip_address`, `actor.user_agent`, and `created_at`. See [Design your compliance integration](https://platform.claude.com/docs/en/manage-claude/compliance-integration-patterns#correlate-with-your-siem) for the join-key table and consumption patterns.
134134 </Accordion>
135135
136136 <Accordion title="Can one customer have multiple organizations under one parent?">
manage-claude/inference-hooks-endpoint Changed · +1 / -1 lines
from line 5
55---
66
77<Note>
8 Inference hooks are in beta and available to Claude Enterprise organizations. Field names, request shapes, and headers may change before general availability.
8 Inference hooks are in beta and available to Claude Enterprise organizations. Field names, request shapes, and headers may change during the beta.
99</Note>
1010
1111An Inference hooks integration is an AI security server: an HTTPS service that Anthropic calls. For each governed request, your server receives a signed `POST` carrying the conversation transcript and responds with an allow or deny verdict. This page documents the protocol for building that server: the request and verdict schemas, signature verification, and the operational contract.
manage-claude/spend-limits-api Changed · +1 / -1 lines
from line 55
5555
5656### Period
5757
58`period` is the recurring window over which the spend limit is enforced and spend resets. A spend limit is identified by its `(scope, period)` pair. Currently `monthly` is the only supported period; monthly spend resets at 00UTC on the first of each calendar month. Treat `period` as an open set.
58`period` is the recurring window over which the spend limit is enforced and spend resets. A spend limit is identified by its `(scope, period)` pair. Currently `monthly` is the only supported period; monthly spend resets at 00:00 UTC on the first of each calendar month. Treat `period` as an open set.
5959
6060### Amounts and currency
6161
manage-claude/user-management Changed · +2 / -2 lines
from line 7
77This page covers managing the people in your **Claude Enterprise** (claude.ai) organization programmatically, using the [Admin API](https://platform.claude.com/docs/en/api/admin): list members and look them up by email address, change a member's role, remove members, send and withdraw invites, manage your enterprise's groups and their membership, and read your organization's custom roles. For Claude Console (Claude Platform) organizations, see the [Admin API guide for Claude Console](https://platform.claude.com/docs/en/manage-claude/admin-api).
88
99<Note>
10 **The endpoints on this page are generally available for Claude Enterprise organizations.** The [beta header](https://platform.claude.com/docs/en/api/beta-headers) `anthropic-beta: ce-user-management-2026-07-13` is no longer required on group and custom-role requests; requests that still send it are accepted and behave identically.
10 Group and custom-role requests don't require the `anthropic-beta: ce-user-management-2026-07-13` [beta header](https://platform.claude.com/docs/en/api/beta-headers). Requests that still send it are accepted and behave identically.
1111</Note>
1212
1313## Which endpoints can your organization use?
from line 458
458458
459459`GET /v1/organizations/rbac_roles/{role_id}/permissions` returns the role's permissions. Each permission pairs a `resource` (what it applies to: the organization's product features, a connector tool, a connector OAuth scope, one connector, or every connector) with an `action` (what it grants on that resource). Rows for features not enabled for your organization are omitted, so a page might contain fewer than `limit` rows while `has_more` is `true`. Requires the `read:members` scope.
460460
461Two `action` values need special care: an `organization` permission whose action is `capability_access_all` (every product feature) or `capability_access_all_ga` (every generally available product feature) is a blanket grant (one that covers neither model access nor the `permission_`-prefixed admin-panel permissions) and is listed as that single row rather than expanded. When you tally what a role grants, treat a blanket row as covering everything its variant describes, not just the features named in other rows.
461Two `action` values need special care: an `organization` permission whose action is `capability_access_all` (every product feature) or `capability_access_all_ga` (every stable product feature, that is, every feature not labeled beta or research preview) is a blanket grant (one that covers neither model access nor the `permission_`-prefixed admin-panel permissions) and is listed as that single row rather than expanded. When you tally what a role grants, treat a blanket row as covering everything its variant describes, not just the features named in other rows.
462462
463463For complete parameter details and response schemas, see [List role permissions](https://platform.claude.com/docs/en/api/admin/rbac_roles/permissions/list) in the API reference.
464464
manage-claude/wif-providers/okta Changed · +2 / -2 lines
from line 112
112112
113113 ```python Python
114114 import os
115 import httpx
115 import httpx2
116116 import anthropic
117117 from anthropic import WorkloadIdentityCredentials
118118
119119
120120 def fetch_okta_token() -> str:
121 response = httpx.post(
121 response = httpx2.post(
122122 f"{os.environ['OKTA_ISSUER']}/v1/token",
123123 data={
124124 "grant_type": "client_credentials",
managed-agents/events-and-streaming Changed · +2 / -2 lines
from line 17
1717* **User events** and **system events** are what you send to the agent: `user.*` events start a session and steer it as it progresses; `system.message` appends system-level context that applies to the accompanying turn and all subsequent turns.
1818* **Session events**, **span events**, and **agent events** are sent to you for observability into your session state and agent progress. Stream connections that opt in also receive [event deltas](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#event-deltas).
1919
20Session, span, agent, user, and system event type strings follow a `{domain}.{action}` naming convention. The stream-only delta preview events (`event_start`, `event_delta`) are the exception. See [Event types](https://platform.claude.com/docs/en/managed-agents/reference#event-types) in the reference for the full catalog.
20Session, span, agent, user, and system event type strings follow a `{domain}.{action}` naming convention. The stream-only delta preview events (`event_start`, `event_delta`) are the exception. See [Event types](https://platform.claude.com/docs/en/managed-agents/reference#event-types) in the reference for the full catalog. [Webhook event types](https://platform.claude.com/docs/en/managed-agents/webhooks#supported-event-types) are separate, and some of their names differ from the stream's (for example, `session.status_idled` rather than `session.status_idle`).
2121
2222Every persisted event includes a `processed_at` timestamp set when the event finishes processing. On events you send, `processed_at` is null while the event is still queued behind earlier events. The exceptions are `user.define_outcome`, `user.custom_tool_result`, and `user.tool_result`, which are processed on receipt and echoed back with `processed_at` already populated.
2323
from line 362
362362 ```
363363 </CodeGroup>
364364
365 The agent acknowledges the interruption and switches to the new task. The interrupted turn ends with a `session.status_idle` event whose `stop_reason` is `end_turn`, the same value as a turn that finishes on its own; there is no stop reason specific to interruption.
365 The call returns as soon as the events are queued, and the interrupt's `processed_at` stays null until the agent applies it. A model response in progress stops immediately. The interrupt can take longer to apply while tool calls are running, and the session stays `running` until it does. The `user.interrupt` event then appears on the stream, and the interrupted turn ends with a `session.status_idle` event. Its `stop_reason` is `end_turn`, the same value as a turn that finishes on its own; there is no stop reason specific to interruption. The agent starts its next turn with the `user.message` you sent after the interrupt.
366366 </Tab>
367367
368368 <Tab title="Streaming events">
managed-agents/reference Changed · +1 / -1 lines
from line 12
1212
1313## Event types
1414
15Persisted event type strings follow a `{domain}.{action}` naming convention; the stream-only event deltas (see the Event deltas tab) are the exception. See [Session event stream](https://platform.claude.com/docs/en/managed-agents/events-and-streaming) for sending, streaming, and listing events.
15Persisted event type strings follow a `{domain}.{action}` naming convention; the stream-only event deltas (see the Event deltas tab) are the exception. See [Session event stream](https://platform.claude.com/docs/en/managed-agents/events-and-streaming) for sending, streaming, and listing events. Webhook event types are listed separately in [Subscribe to webhooks](https://platform.claude.com/docs/en/managed-agents/webhooks#supported-event-types), and some of their names differ from the stream's (for example, `session.status_idled` rather than `session.status_idle`).
1616
1717<Tabs>
1818 <Tab title="User events">
managed-agents/scheduled-deployments Changed · +1 / -1 lines
from line 252
252252
253253* **Expression:** Standard POSIX cron (`minute hour day-of-month month day-of-week`). You can generate and validate these cron expressions in the [Claude Console](https://platform.claude.com/workspaces/default/deployments).
254254* **Timezone:** IANA timezone identifier (for example, `"America/Los_Angeles"`).
255* **DST:** Cron schedules use literal wall-clock matching, so `"0 20 * * *"` in `America/New_York` fires at 8PM local time regardless of whether EST or EDT is in effect.
255* **DST:** Cron schedules use literal wall-clock matching, so `"0 20 * * *"` in `America/New_York` fires at 8:00 PM local time regardless of whether EST or EDT is in effect.
256256
257257<Note>
258258 Wall-clock times that do not exist on a spring-forward day (such as 2 AM) are not triggered. Wall-clock times that occur twice on a fall-back day fire twice. Schedule outside the 1–3 AM local window, or use UTC, when missed or duplicate executions are unacceptable.
managed-agents/self-hosted-sandboxes-security Changed · +1 / -1 lines
from line 16
1616* **Tool-execution blast radius.** Tools run inside your sandbox with whatever permissions your process has. Apply least privilege to the process user and mount only the directories your tools require.
1717* **Log retention and session content.** Conversation content and tool outputs pass through your worker and stay in your environment. You are responsible for retaining, redacting, or deleting that data in compliance with your own policies. Anthropic has no visibility into what your worker does with session content once delivered.
1818* **Memory store contents.** [Memory stores](https://platform.claude.com/docs/en/managed-agents/memory) remain hosted by Anthropic, including their version history. When a session attaches one, the worker keeps a working copy under `/mnt/memory/` in your sandbox for the session's duration and syncs changes back. The worker deletes that copy when the session ends, but a worker that exits without running its teardown leaves it behind. Cleaning up leftover copies, the permissions on that path, and isolation between sessions that share a filesystem are your responsibility.
19* **Read-only memory stores.** A store attached with `read_only` access is protected from upload, not from local modification. The worker's `write` and `edit` tools refuse to write under its directory, nothing there syncs back, and the memory store endpoints reject writes to it made with the session's `secret`. Other processes in the sandbox, including commands the agent runs through the `bash` tool, can still change the local copy, and later tool calls in that session read the changed copy until that memory next changes in the store. If the agent must not be able to alter even its local view of such a store, disable the `bash` tool for that agent.
19* **Read-only memory stores.** A store attached with `read_only` access is protected from upload, not from local modification. The worker's `write` and `edit` tools refuse to write under its directory, nothing there syncs back, and the memory store endpoints reject writes to it made with the session's `secret`. Other processes in the sandbox can still change the local copy: commands the agent runs through the `bash` tool, and [custom tools](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes#serve-custom-tools-from-your-sandbox) or MCP servers you serve from the sandbox, which run with the worker's permissions. Later tool calls in that session read the changed copy until that memory next changes in the store. If the agent must not be able to alter even its local view of such a store, disable the `bash` tool for that agent and give it no custom tool that writes to the sandbox's filesystem.
2020
2121## What Anthropic cannot do for you
2222
managed-agents/tools Changed · +1 / -0 lines
from line 648
648648
649649* Each list is capped at 64 domains.
650650* Domains listed for `web_fetch` cannot include a path.
651* Domains must be ASCII: use the `xn--` (Punycode) form for internationalized domain names. The Messages API accepts Unicode entries, though it recommends against them.
651652* `max_uses`, `citations`, and `cache_control` are not available on the toolset.
652653
653654## Custom tools
managed-agents/webhooks Changed · +2 / -0 lines
from line 12
1212
1313<Tabs>
1414 <Tab title="Session events">
15 Some of these events are named differently from the matching events on the session's [event stream](https://platform.claude.com/docs/en/managed-agents/events-and-streaming). For example, the stream's `session.status_idle` and `session.status_running` correspond to the `session.status_idled` and `session.status_run_started` webhook events.
16
1517 | Event | Trigger |
1618 | ---------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1719 | `session.status_run_started` | Agent execution started. This triggers at every session status transition to `running`. |