Skip to main content

Documentation Index

Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt

Use this file to discover all available pages before exploring further.

Trace Kiro CLI agent turns, tool calls, and credit usage in Arize AX for full observability.
Kiro is AWS’s agentic IDE and CLI for spec-driven development. The Arize Coding Harness Tracing registers hooks on a Kiro agent and exports OpenInference spans to Arize AX or Phoenix. Each agent turn is captured as an LLM span with tool calls, model info, credit cost, and turn duration.

​
Launch Arize AX

To get started, sign up for a free Arize AX account and get your Space ID and API Key:
  1. Log in at app.arize.com
  2. Click Settings and copy the Space ID
  3. Open the API Keys tab and create or copy an API key

​
Install

​
Curl installer

macOS / Linux: 
curl -sSL https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.sh | bash -s -- kiro
Windows (PowerShell): 
iwr -useb https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.bat -OutFile $env:TEMP\install.bat
& $env:TEMP\install.bat kiro

​
Local clone

git clone https://github.com/Arize-ai/coding-harness-tracing.git
cd coding-harness-tracing
./install.sh kiro          # macOS / Linux
install.bat kiro           # Windows
The installer prompts you through:
  1. Agent name — the Kiro agent to install hooks into (default: arize-traced)
  2. Set as default — whether to run kiro-cli agent set-default <name> so the agent is used by default
  3. Backend — Phoenix or Arize AX, plus endpoint and credentials
  4. Project name — project name in your backend (default: kiro)
  5. User ID — optional user identifier added to all spans
  6. Logging — whether to include prompt text, tool content, and tool details in spans
Once installed, run Kiro as usual. If you set the traced agent as the default during install: 
kiro-cli chat
Otherwise, point Kiro at the traced agent explicitly: 
kiro-cli chat --agent arize-traced

​
Configuration

Credentials live under harnesses.kiro in ~/.arize/harness/config.yaml (written by the installer). Environment variables override values in config.yaml and can be set in your shell profile so they apply to every Kiro session.

​
Phoenix (self-hosted)

export PHOENIX_ENDPOINT="http://localhost:6006"
export ARIZE_PROJECT_NAME="kiro"
export ARIZE_TRACE_ENABLED="true"

​
Arize AX (cloud)

export ARIZE_API_KEY="<your-api-key>"
export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_PROJECT_NAME="kiro"
export ARIZE_TRACE_ENABLED="true"

​
Redaction controls

Each ARIZE_LOG_* flag accepts "true" or "false" and defaults to "true". Set to "false" to opt out per category: 
export ARIZE_LOG_PROMPTS="false"
export ARIZE_LOG_TOOL_DETAILS="false"
export ARIZE_LOG_TOOL_CONTENT="false"
FlagRedacts
ARIZE_LOG_PROMPTSUser prompt and assistant response text
ARIZE_LOG_TOOL_DETAILSTool names and arguments
ARIZE_LOG_TOOL_CONTENTTool call output content
The same flags can be set in config.yaml under harnesses.kiro.logging as log_prompts, log_tool_details, and log_tool_content — env vars take precedence.

​
Observe

Once tracing is enabled, Kiro activity is streamed to Arize AX. You’ll see:
  • Turn traces — each agent turn (user prompt to assistant response) as a parent LLM span
  • Tool call spans — one per pre/post tool event pair, parented to the LLM turn
  • Session grouping — all turns from the same Kiro session grouped by session.id
  • Credit cost — Kiro meters in credits rather than tokens; cost is captured as kiro.cost.credits
  • Model and duration — llm.model_name, kiro.turn_duration_ms, and kiro.context_usage_percentage from the session sidecar

​
Hooks Captured

HookSpan KindDescription
agentSpawnCHAINAgent spawned, trace/tool counters reset
userPromptSubmitCHAINUser prompt captured, session lazy-initialized
preToolUseTOOLTool invocation started, records tool name and input
postToolUseTOOLTool invocation completed, records output and duration
stopLLMModel response completed with input/output values

​
Span attributes

LLM spans are enriched from the session sidecar at ~/.kiro/sessions/cli/<session_id>.json with model name, cost in credits, metering usage, and turn duration. Enrichment is fail-soft — if the sidecar is unavailable, the span is emitted with basic attributes only.
AttributeDescription
session.idKiro session UUID
llm.model_nameModel ID from the session sidecar
kiro.cost.creditsCost in credits from metering data
kiro.metering_usageFull metering usage JSON
kiro.turn_duration_msTurn duration in milliseconds
kiro.agent_nameName of the Kiro agent
kiro.context_usage_percentageContext window usage percentage

​
Known limitations

  • Token counts are 0. Kiro CLI does not report prompt or completion token counts in current versions and meters in credits instead. Token count attributes are omitted when 0; see kiro.cost.credits.
  • FIFO tool matching. Kiro does not expose a tool-call ID, so pre/post tool events are matched using a FIFO stack. This assumes serial tool execution within a session.
  • Per-workspace agents not supported. Only global agents under ~/.kiro/agents/ are instrumented.

​
Reference

For the full list of environment variables, default file paths, and troubleshooting steps, see the Kiro tracing README.

​
Uninstall

curl -sSL https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.sh | bash -s -- uninstall kiro
Uninstall removes hook entries from every Kiro agent file. If the arize-traced agent was created by the installer, that agent file is deleted; pre-existing agents are preserved.

​
Resources

Arize Coding Harness Tracing

OpenInference

Kiro Documentation