Skip to main content

OpenTelemetry real-time events

Kiro can send each LLM request and each tool call to your OpenTelemetry Protocol (OTLP) collector as an event. Each event is one OTLP log record. LLM request events usually arrive within seconds. Tool call events take longer, because the Kiro client reports each call to Kiro first.

EventOne record for eachMeasured by
kiro.chat.messageLLM request that the Kiro service completesThe Kiro service
kiro.tool.callTool call that finishedThe Kiro client

To set up the export, prepare credentials, and then turn on real-time events. To learn how the events relate to each other, see Understanding real-time events.

How Kiro sends events

  • Protocol. OTLP logs over HTTP/protobuf, compressed with gzip. gRPC is not supported for events.
  • Delivery. Best effort. Kiro retries an event that can't be delivered for up to about 10 minutes, and then drops it. Kiro doesn't send dropped events again. Rarely, an event arrives twice. See Remove duplicates.
  • Content. Events carry IDs, counts, and timings. kiro.chat.message also carries the user's email address. Events don't carry prompts, responses, code, or file content.
  • Record time. The time when the event happened: when the request completed, or when the tool call finished. The observed time is when Kiro sent the event. For an LLM request, that is usually a few seconds after the record time. For a tool call, the gap is larger, and can be up to 45 minutes when the client reports the call late. See kiro.tool.call.
  • Availability. Kiro profiles in US East (N. Virginia) and Europe (Frankfurt).

Common fields

Every record has instrumentation scope kiro.enterprise.events, severity INFO, and the body kiro.enterprise.event. All data is in the attributes. Each record has an eventName, and the attribute kiro.event.name with the same value. Some platforms, such as Dynatrace, don't show eventName, so filter on kiro.event.name. Kiro leaves out attributes that have no value.

These resource attributes appear once for each delivery:

Resource attributeValue
service.namekiro-enterprise
kiro.profile.arnarn:aws:codewhisperer:<region>:<account-id>:profile/<profile-id>
kiro.profile.idThe Kiro profile ID
kiro.account.idThe AWS account that holds the Kiro profile

kiro.chat.message

One record for each LLM request. One user prompt can produce several requests, for example when the agent calls tools.

AttributeTypePresenceDescription
kiro.message.idstringAlwaysThe request ID. Unique for each request. Use it to remove duplicates
kiro.user.idstringAlwaysThe user's IAM Identity Center user ID. If the profile signs in through an external identity provider, the user ID from that provider
kiro.user.emailstringWhen Kiro finds itThe user's email address. With an external identity provider that has no email address for the user, the user name
kiro.client.typestringAlwaysKIRO_IDE, KIRO_CLI, KIRO_WEB, KIRO_CREW, or PLUGIN. Other values can appear as Kiro adds clients
kiro.client.versionstringWhen setThe client version from the request's user agent, such as 3.1.0. Not sent when the client sent no version. An updated client reports its new version after it restarts
kiro.model.namestringAlwaysThe model, such as auto. Requests on internal models are not sent
kiro.conversation.idstringWhen setThe conversation of the request. A chat from an earlier Kiro CLI engine gets an ID of the form cli_<uuid>_<8 characters> when you open it on the current engine. It gets a new ID each time you open it. Treat each such ID as its own conversation
kiro.root_conversation_idstringWhen setThe top-level conversation of the session. A top-level request has its own kiro.conversation.id. A sub-agent request has its parent session's ID. Not sent by Kiro CLI on the V2 agent engine
kiro.agent_modestringWhen setThe agent mode of the session. Same values as kiro.tool.agent_mode. A sub-agent request has the mode of its parent session
kiro.credits.useddoubleWhen setCredits that the request used
kiro.credits.overagedoubleWhen setOverage credits that the request used
kiro.tool_call_countintegerWhen setNumber of tools that the model asked for
kiro.tool_callsstringWhen the model asked for a toolA JSON object of tool names and counts, such as {"fs_write":1,"read_file":3}. Up to 32 tools, keeping the most called. A call to an MCP tool is listed as tool_call
kiro.request.subagentbooleanWhen settrue for a request that Kiro starts, such as a sub-agent, a summary, or a session title
kiro.answer.cut_offbooleanWhen setWhether the answer stopped at the model's output limit
kiro.response.duration_msintegerWhen setTime in milliseconds from the request to the complete answer
kiro.subscription.tierstringWhen setPRO, PRO_PLUS, PRO_MAX, POWER, or POOLING
kiro.usage.limitintegerWhen setThe user's credit limit. 999999 for a shared-pool user with no individual limit
kiro.overage.enabledbooleanWhen setWhether overage is enabled for the user
kiro.overage.capdoubleWhen setThe user's overage cap

kiro.tool.call

One record for each tool call that finished. A request in which the model asks for no tool has no kiro.tool.call record.

The record time is when the tool call finished. If the client reports the call more than 45 minutes late, the record time is when Kiro received it.

AttributeTypePresenceDescription
kiro.tool.use.idstringAlwaysUnique for each tool call. Use it to remove duplicates
kiro.message.idstringAlwaysThe request that asked for the tool. All tool calls of one request share it
kiro.user.idstringAlwaysSame value as on kiro.chat.message
kiro.conversation.idstringWhen setSame value as on kiro.chat.message
kiro.client.typestringAlwaysKIRO_IDE, KIRO_CLI, KIRO_WEB, or UNKNOWN
kiro.tool.namestringWhen setThe tool, such as read_file or invoke_sub_agent. An MCP tool is mcp_<server>_<tool>, with each - in the server name written as _, such as mcp_my_mcp_server_find_city. Kiro web search is remote_web_search. A skill load is disclose_context
kiro.tool.kindstringAlwaysBUILTIN, MCP, SKILL, or UNKNOWN
kiro.tool.outcomestringWhen setCOMPLETED, ERROR, FAULT, ABORT, or UNKNOWN. A call that the user denies or cancels is ABORT. FAILURE appears only when the client sends it
kiro.tool.duration_msintegerWhen setHow long the call took, in milliseconds
kiro.tool.agent_modestringWhen setVIBE, SPEC, QUICK_SPEC, BUG_FIX, PLAN, AUTONOMOUS, CUSTOM, or UNKNOWN. The client shows VIBE as Default
kiro.error.typestringWhen the call didn't completeThe type of error
kiro.mcp.serverstringMCP callsThe configured MCP server name. remote is Kiro web search, not a server that you configured
kiro.skill.namestringSkill loadsThe name in the skill's SKILL.md file
kiro.sourcestringAlwaysCLIENT. The client measures every tool call

Client versions

The Kiro client reports tool calls, so some attributes need a supported client version. kiro.chat.message events arrive from every client version.

For Kiro IDE, update to the latest release.

For Kiro CLI, the table lists the minimum version that Kiro supports for each kind of data. Some earlier versions send part of it, but Kiro doesn't support them for this data. Kiro CLI sends tool call data only on the V3 agent engine.

DataKiro CLI
kiro.tool.call events3.0.0 or later
kiro.tool.call events when Collect metrics per user is off3.1.0 or later
kiro.tool.agent_mode3.0.0 or later
kiro.agent_mode and kiro.skill.name3.1.0 or later
Web search as remote_web_search3.1.0 or later
MCP tool names in kiro.tool.name, such as mcp_my_mcp_server_find_city3.2.1 or later

After an update, quit every open IDE window and kiro-cli process, and start them again. An old process keeps sending data with its old version.

Confirm the export

Kiro doesn't notify you when delivery succeeds or fails. Check your collector after users are active.

CheckExpected
RecordsOne for each LLM request, and one for each finished tool call
Resource attributeservice.name = kiro-enterprise
AttributesAt least kiro.event.name, kiro.user.id, and kiro.message.id, plus kiro.tool.use.id on tool calls
PlatformWhere to check
HoneycombThe kiro-enterprise dataset. Query COUNT grouped by eventName
Grafana CloudExplore, your Loki data source, {service_name="kiro-enterprise"}
DynatraceThe Logs app, filtered on service.name = kiro-enterprise
DatadogLog Explorer, filtered on service:kiro-enterprise
Amazon CloudWatch LogsLogs Insights on your log group: filter eventName = "kiro.chat.message" | stats count(*) by attributes.kiro.model.name

Platforms store attribute names in different ways:

  • Grafana Cloud replaces periods with underscores, so kiro.model.name becomes kiro_model_name. Don't add | json to a query. The body is plain text.
  • CloudWatch Logs nests attributes. Use attributes.kiro.model.name and resource.attributes.service.name.
  • Dynatrace doesn't show eventName. Filter on kiro.event.name.

Remove duplicates

A retry can deliver an event twice. Remove duplicates on these keys:

  • kiro.message.id for kiro.chat.message
  • kiro.tool.use.id for kiro.tool.call. Don't use kiro.message.id, because tool calls share it.

Kiro doesn't guarantee the order of events. Sort by record time, not by arrival.

Delivery behavior

  • Temporary failures are retried. An HTTP 5xx, 408, 425, or 429, a timeout, or a connection error is retried for up to about 10 minutes. Then the events are dropped.
  • Configuration errors are not retried. Kiro drops the events at once for any other 4xx, such as 400, 401, 403, or 404. It also drops them for a secret that Kiro can't read, or a malformed header.
  • A failing profile pauses. After 5 configuration failures with no successful delivery in between, Kiro stops sending for the profile for about 5 minutes, and drops its events. Then Kiro tries again.
  • Private connectivity has no fallback. Until the private connection is ready, deliveries fail and are retried as temporary failures.
  • Daily metrics don't change. Dropped events don't affect the daily CSV report or OpenTelemetry metrics.

Turn events into metrics

  • Honeycomb. Query the events, for example SUM(kiro.credits.used) grouped by kiro.model.name. Save the query to a board, or add a trigger.
  • Grafana Cloud. Use LogQL metric queries, for example sum by (kiro_model_name) (count_over_time({service_name="kiro-enterprise"} [5m])). Use a recording rule to keep the result as a metric.
  • Amazon CloudWatch Logs. Use Logs Insights. For metric filters, add a log transformer that copies each field you need into a flat field, because metric filters can't read names with periods. Don't use kiro.user.id as a metric dimension. Each value is a billed metric, and CloudWatch turns off a metric filter at 1,000 distinct values.

Costs

  • AWS Secrets Manager and AWS KMS. Kiro reads your events secret, and decrypts it with your key, for each delivery. A delivery carries up to 5 seconds of a profile's LLM request events or of its tool call events, never both. A busy profile usually causes two reads every 5 seconds, one for each event type. A large batch can cause more. Your account pays for these requests.
  • Your platform. Your observability platform charges for log ingestion and storage.
Page updated: November 16, 2026