Follow Discord
Sweep 08 Oct 2026 · 18:53Z Build v2.1.295 516 read Stable v2.1.286 Latest v2.1.295 Next v2.1.295 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 6 Oct 2026
One change · claude-code

Monitoring changedmonitoring-usage

Nearest release: v2.1.291, published 2 hours after 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 6 Oct 2026 01:08 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 6 Oct 2026 01:37 UTC.

Upstream edited
Recorded here
Lines+5added
Lines−5removed
From line 114 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits46to this page, all time

The whole hunk

from line 114, old and new numbered
/
lines
from line 114
114114| `OTEL_METRIC_EXPORT_INTERVAL` | Export interval in milliseconds (default: 60000) | `5000`, `60000` |
115115| `OTEL_LOGS_EXPORT_INTERVAL` | Logs export interval in milliseconds (default: 5000) | `1000`, `10000` |
116116| `OTEL_LOG_USER_PROMPTS` | Enable logging of user prompt content (default: disabled) | `1` to enable |
117| `OTEL_LOG_ASSISTANT_RESPONSES` | Enable logging of assistant response text on `assistant_response` events (default: disabled). When unset, falls back to the value of `OTEL_LOG_USER_PROMPTS`. Requires Claude Code v2.1.193 or later | `1` to enable, `0` to keep redacted |
117| `OTEL_LOG_ASSISTANT_RESPONSES` | Enable logging of assistant response text on `assistant_response` events (default: disabled). When unset, falls back to the value of `OTEL_LOG_USER_PROMPTS` | `1` to enable, `0` to keep redacted |
118118| `OTEL_LOG_TOOL_DETAILS` | Enable logging of tool parameters and input arguments in tool events and trace span attributes: Bash commands, MCP server and tool names, skill names, user-authored workflow names, and tool input. Also enables custom, plugin, and MCP command names on `user_prompt` events, and real agent, skill, plugin, and MCP server and tool names on the [cost and token counters](#cost-counter) (default: disabled). For Claude Desktop's built-in servers, in sessions Claude Desktop owns, `mcp_server_name`/`mcp_tool_name` emit on `tool_decision`/`tool_result` even with the flag off. The exception requires Claude Code v2.1.214 or later | `1` to enable |
119119| `OTEL_LOG_TOOL_CONTENT` | Enable logging of tool content in the [`tool.output` span event](#tool-output-span-event) (default: disabled). Span attributes carry tool content under [their own gates](#new-context-gates). Requires [tracing](#traces-beta). Content is truncated at the content limit (60 KB by default) | `1` to enable |
120120| `OTEL_LOG_MANAGED_SETTINGS` | Add the redacted managed settings, and a SHA-256 digest of the settings before redaction, to [managed settings resolved](#managed-settings-resolved-event) events (default: disabled). A value in project or local settings doesn't turn it on. Requires Claude Code v2.1.274 or later | `1` to enable |
from line 745
745745 
746746#### Assistant response event
747747 
748Logged after each API request that returns text content from the model. Only the response's text blocks are included; thinking blocks and tool-use blocks are excluded. Requires Claude Code v2.1.193 or later.
748Logged after each API request that returns text content from the model. Only the response's text blocks are included; thinking blocks and tool-use blocks are excluded.
749749 
750750**Event Name**: `claude_code.assistant_response`
751751 
from line 1057
10571057* `plugin_id_hash`: deterministic hash of the plugin name and marketplace, sent only to your configured exporter. Lets you count the distinct third-party plugins loaded across your fleet without recording their names. For [plugins synced from claude.ai](/docs/en/plugins/loading#synced-plugins), Claude Code hashes the plugin name with the marketplace name that claude.ai reports for the plugin, or with `synced` otherwise. Before v2.1.246, Claude Code didn't use the marketplace name claude.ai reports in the hash
10581058* `has_hooks`: whether the plugin contributes hooks
10591059* `has_mcp`: whether the plugin contributes MCP servers
1060* `host_owned_mcp`: `true` when the SDK host manages this plugin's MCP connections and Claude Code skipped reading the plugin's MCP server configuration, `false` otherwise. Requires Claude Code v2.1.172 or later
1060* `host_owned_mcp`: `true` when the SDK host manages this plugin's MCP connections and Claude Code skipped reading the plugin's MCP server configuration, `false` otherwise
10611061* `skill_path_count`: number of skill directories the plugin declares
10621062* `command_path_count`: number of command directories the plugin declares
10631063* `agent_path_count`: number of agent directories the plugin declares
from line 1220
12201220* `pre_tokens`: Approximate token count before compaction
12211221* `post_tokens`: Approximate token count after compaction
12221222* `error`: Error message when compaction failed
1223* `precompute_reuse`: Only set when `trigger` is `"manual"`. Auto-compaction can prepare a summary in the background before the context window fills, and this attribute records whether `/compact` reused that prepared summary. `"hit"` means it was reused; `"miss_custom_instructions"`, `"miss_hook"`, and `"miss_not_ready"` give the reason a fresh summary was computed instead. Requires Claude Code v2.1.153 or later
1223* `precompute_reuse`: Only set when `trigger` is `"manual"`. Auto-compaction can prepare a summary in the background before the context window fills, and this attribute records whether `/compact` reused that prepared summary. `"hit"` means it was reused; `"miss_custom_instructions"`, `"miss_hook"`, and `"miss_not_ready"` give the reason a fresh summary was computed instead
12241224 
12251225#### Subagent completed event
12261226 
from line 1386
13861386* Unusual token consumption
13871387* High session volume from specific users
13881388 
1389All metrics can be segmented by the [standard attributes](#standard-attributes). The `model` attribute is available on `claude_code.token.usage`, `claude_code.cost.usage`, and from v2.1.172, `claude_code.lines_of_code.count`.
1389All metrics can be segmented by the [standard attributes](#standard-attributes). The `model` attribute is available on `claude_code.token.usage`, `claude_code.cost.usage`, and `claude_code.lines_of_code.count`.
13901390 
13911391Per-model breakdowns of commits can only be approximated by joining against the token or cost metrics on `session.id`, since one session can span multiple models. Filter the token or cost side to rows where `query_source` is `"main"` so auxiliary and subagent requests don't attribute the session's commits to a model that didn't make them.
13921392 
Feedback