Monitoring changedmonitoring-usage
Nearest release: v2.1.310, published 5 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 24 Oct 2026 03:04 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 24 Oct 2026 03:07 UTC.
Upstream edited
Recorded here
Lines+16added
Lines−3removed
From line
601
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits68to this page, all time
The whole hunk
from line 601, old and new numbered
/
from line 601
601601
602602* `prompt.id`: UUID correlating a user prompt with all subsequent events until the next prompt. See [Event correlation attributes](#event-correlation-attributes).
603603* `workspace.host_paths`: host workspace directories selected in the desktop app, as a string array
604* `workflow.run_id`: run identifier, prefixed `wf_`, on the API and tool events emitted by agents that belong to a [Workflow](https://code.claude.com/docs/en/workflows.md) tool run. Filtering events by one `workflow.run_id` reconstructs that run's API requests and tool results. The identifier covers the agents the workflow script spawns and any agents those spawn in turn, such as skill invocations. It matches the run identifier reported in the Workflow tool result. Absent on all other events.
604* `workflow.run_id`: run identifier, prefixed `wf_`, on the API and tool events emitted by agents that belong to a [Workflow](https://code.claude.com/docs/en/workflows.md) tool run. Filtering events by one `workflow.run_id` reconstructs that run's API requests and tool results. The identifier covers the agents the workflow script spawns and any agents those spawn in turn, such as skill invocations. It matches the run identifier reported in the Workflow tool result.
605605* `workflow.name`: name of the workflow, its script's `meta.name`, emitted alongside `workflow.run_id`. Built-in workflow names appear verbatim when the run executes the unmodified built-in script. User-authored names, including edited copies of built-in scripts, are replaced with `custom` unless `OTEL_LOG_TOOL_DETAILS=1` is set.
606* `agent_id`: identifier of the [subagent](https://code.claude.com/docs/en/sub-agents.md) that raised the event, such as `a3f2c1b4d5e6f7a80`. Events that carry it include a subagent's API and tool events, its [`assistant_response`](#assistant-response-event) events, and [`subagent_completed`](#subagent-completed-event) for the finished subagent. Absent on main-session and [in-process teammate](https://code.claude.com/docs/en/agent-teams.md#choose-a-display-mode) events. The subagent's [span `agent_id`](#span-attributes) is the same value, or adds a label after the leading `a` as in `acompact-3f2c1b4d5e6f7a80`. Requires Claude Code v2.1.310 or later
607* `parent_agent_id`: the `agent_id` of the agent that spawned or last resumed the subagent that raised the event. Absent when that agent is the main session. Requires Claude Code v2.1.310 or later
606608
607609#### Repository attributes
608610
from line 753
751753| `prompt.id` | UUID v4 identifier linking all events produced while processing a single user prompt |
752754| `event.sequence` | 0-based counter for ordering events, counted per Claude Code process rather than per session |
753755| `message.uuid` | UUID of the message as persisted in the session transcript, the `~/.claude/projects/*/*.jsonl` files. Present on `assistant_response`, on `api_response_body`, and on `user_prompt` except for command dispatches, which can produce zero or many messages. On `assistant_response` and `api_response_body`, this is the response's final transcript entry, which the next turn's `parentUuid` chains from. Requires Claude Code v2.1.274 or later on `api_response_body` |
754| `request_id` | Server-assigned ID of the API request, read from the `request-id` response header, such as `req_011...`. On a response with no `request-id` header, as on [Amazon Bedrock](https://code.claude.com/docs/en/amazon-bedrock.md), the value comes from the `x-amzn-requestid` header instead. Present on `api_request`, `api_error`, `api_refusal`, `assistant_response`, and `api_response_body` when the response carries either header. Matches the same attribute on the `llm_request` trace span. The `x-amzn-requestid` source requires Claude Code v2.1.282 or later |
756| `request_id` | Server-assigned ID of the API request, read from the `request-id` response header, such as `req_011...`. On a response with no `request-id` header, as on [Amazon Bedrock](https://code.claude.com/docs/en/amazon-bedrock.md), the value comes from the `x-amzn-requestid` header instead. Present on `api_request`, `api_error`, `api_refusal`, `assistant_response`, `api_response_body`, [`tool_result`](#tool-result-event), and [`tool_decision`](#tool-decision-event) when the response carries either header. Matches the same attribute on the `llm_request` trace span. The `x-amzn-requestid` source requires Claude Code v2.1.282 or later |
755757| `client_request_id` | Client-generated UUID sent as the `x-client-request-id` request header. Present on `api_request` and `api_error` on first-party API connections; absent on third-party provider backends and when the request was retried through the non-streaming fallback. Pairs a request with its response and remains available for failures such as timeouts that never produced a server `request_id`. Matches the same attribute on the `llm_request` trace span |
756758
757759To trace all activity triggered by a single prompt, filter your events by a specific `prompt.id` value. This returns the user\_prompt event, any api\_request events, and any tool\_result events that occurred while processing that prompt.
from line 818
816818* `event.sequence`: per-process counter for ordering events, described under [Event correlation attributes](#event-correlation-attributes)
817819* `tool_name`: Name of the tool
818820* `tool_use_id`: Unique identifier for this tool invocation. Matches the `tool_use_id` passed to hooks, allowing correlation between OTel events and hook-captured data.
821* `request_id`: the [`request_id`](#event-correlation-attributes) of the API response that contained this tool call, so you can join the call to that response's API events. Absent when that response had no request ID, or when no API response contained the call. Requires Claude Code v2.1.310 or later
819822* `success`: `"true"` or `"false"`
820823* `duration_ms`: Execution time in milliseconds
821824* `error_type`: Error category string when the tool failed, such as `"Error:ENOENT"` or `"ShellError"`
from line 971
968971* `event.sequence`: per-process counter for ordering events, described under [Event correlation attributes](#event-correlation-attributes)
969972* `tool_name`: Name of the tool (for example, "Read", "Edit", "Write", "NotebookEdit")
970973* `tool_use_id`: Unique identifier for this tool invocation. Matches the `tool_use_id` passed to hooks, allowing correlation between OTel events and hook-captured data.
974* `request_id`: the [`request_id`](#event-correlation-attributes) of the API response that contained this tool call, so you can join the call to that response's API events. Absent when that response had no request ID, or when no API response contained the call. Requires Claude Code v2.1.310 or later
971975* `decision`: Either `"accept"` or `"reject"`
972976* `tool_source`: Always present. The tool's provenance, as a closed set of CLI-authored values:
973977 * `"builtin"`: the CLI's own tools
from line 1024
10201024 * For Skill tool: includes `skill_name`
10211025 * For Agent tool or legacy Task tool: includes `subagent_type`
10221026
1023If you lower the OpenTelemetry SDK's `OTEL_LOGRECORD_ATTRIBUTE_COUNT_LIMIT` below the number of attributes on a `tool_decision` event, the SDK drops the attributes that Claude Code set last. The SDK drops `permission_mode` first, `classifier_category` second, and `classifier_verdict` third, and drops the event's other attributes only after those three. This ordering requires Claude Code v2.1.302 or later.
1027If you lower the OpenTelemetry SDK's `OTEL_LOGRECORD_ATTRIBUTE_COUNT_LIMIT` below the number of attributes on a `tool_decision` event, the SDK drops the attributes that Claude Code set last. The SDK drops these before any other attribute, in this order, skipping any the event doesn't carry:
1028
10291. `parent_agent_id`
10302. `agent_id`
10313. `request_id`
10324. `permission_mode`
10335. `classifier_category`
10346. `classifier_verdict`
1035
1036`permission_mode`, `classifier_category`, and `classifier_verdict` drop in this order on Claude Code v2.1.302 or later. `parent_agent_id`, `agent_id`, and `request_id` require v2.1.310 or later.
10241037
10251038#### Safety event
10261039
No line in this hunk matches that.