cloud-trace-and-logging

Cloud Trace & Prompt-Response Logging (Scaffolded Projects)

> **Assumes `/google-agents-cli-scaffold` scaffolding.** Observability infrastructure is provisioned by Terraform in scaffolded projects.

> **Feature gaps in ADK Go.** Traces and logs are exported over OTLP to `telemetry.googleapis.com`. > Three things below are **ADK Python only**: the BigQuery Agent Analytics plugin (`--bq-analytics`), > the GCS completion upload (`OTEL_INSTRUMENTATION_GENAI_COMPLETION_HOOK`) that backs prompt-response > logging, and `ADK_CAPTURE_MESSAGE_CONTENT_IN_SPANS`. > > `OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT` exists in both but means different things: > ADK Python takes the semconv enum, ADK Go treats it as a boolean — `"1"` or `"true"` capture > content, and every other value (including `NO_CONTENT`) elides it.

Cloud Trace

Always-on distributed tracing, exporting spans/logs to Cloud Trace and Cloud Logging. The exporters are wired at app startup (**ADK Python:** `get_fast_api_app(otel_to_cloud=True)`; **ADK Go:** `setupObservability()` in `observability.go`, which exports traces and logs over OTLP to `telemetry.googleapis.com` regardless of the launcher's `-otel_to_cloud` flag; other templates call their own setup, e.g. `app/app_utils/telemetry.py`). For **Agent Runtime in Gemini platform** it's gated on `GOOGLE_CLOUD_AGENT_ENGINE_ENABLE_TELEMETRY` (set by deploy), and traces also appear on the Agent Runtime page in the Google Cloud console. Content env vars are declared statically (Terraform `service.tf` for deployed, `.env` for local). Tracks requests through LLM calls and tool executions with latency analysis and error visibility.

View traces: **Cloud Console → Trace → Trace explorer**

No configuration required. Works in local dev (`agents-cli playground`) and all deployed environments.

Prompt-Response Logging Infrastructure

All provisioned automatically by `deployment/terraform/single-project/telemetry.tf` (and the `cicd/` variant):

• **Log sinks** — Route GenAI inference logs directly to BigQuery (partitioned tables)
• **BigQuery dataset** — Telemetry dataset with external tables over GCS data and pre-created log export table
• **Pre-created log export table** — Cloud Logging BQ export schema (labels flattened: dots become underscores). Cloud Logging names the sink table after the log id, so it varies by deployment target: `gen_ai_client_inference_operation_details` (Cloud Run / GKE) or `aiplatform_googleapis_com_reasoning_engine_stdout` (Agent Runtime, where GenAI logs arrive via stdout)
• **GCS logs bucket** — Stores completions as NDJSON
• **BigQuery connection** — Service account for GCS access from BigQuery
• **Completions view** — Joins BQ log export data with GCS-stored prompt/response data

Check `deployment/terraform/single-project/telemetry.tf` for exact configuration. IAM bindings grant log sink service accounts `roles/bigquery.dataEditor` on the telemetry dataset.

**Collecting user feedback?** The same infrastructure supports a feedback mechanism (endpoint + structured logging → log sink → BigQuery). See `references/feedback-mechanism.md`.

Environment Variables

Set automatically by Terraform on the deployed service. The `OTEL_INSTRUMENTATION_GENAI_*` content-capture and upload variables (capture modes, `OTEL_SEMCONV_STABILITY_OPT_IN`, completion hook / upload) are documented in [`opentelemetry-util-genai`](https://github.com/open-telemetry/opentelemetry-python-genai/tree/main/util/opentelemetry-util-genai) and the [OpenTelemetry GenAI semantic conventions](https://opentelemetry.io/docs/specs/semconv/gen-ai/).

Common (Python & Go)

| Variable | Purpose | Notes | |----------|---------|--------| | `OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT` | Controls content capture for the traces/events tier only | Python accepts `NO_CONTENT`/`EVENT_ONLY`/`SPAN_ONLY`/`SPAN_AND_EVENT`; Go accepts `true`/`false` |

Python only

| Variable | Purpose | |----------|---------| | `LOGS_BUCKET_NAME` | GCS bucket for completions and logs. Required to enable prompt-response logging | | `ADK_CAPTURE_MESSAGE_CONTENT_IN_SPANS` | **ADK only.** Keeps message content out of trace spans; Terraform sets `false` (ADK defaults to `true`) | | `BQ_ANALYTICS_DATASET_ID` | BigQuery dataset for telemetry (ADK BigQuery Agent Analytics plugin; only when scaffolded with `--bq-analytics`) | | `BQ_ANALYTICS_CONNECTION_ID` | BigQuery connection for GCS access (only when scaffolded with `--bq-analytics`) | | `BQ_ANALYTICS_GCS_BUCKET` | GCS bucket for BigQuery Analytics multimodal offloading (only when scaffolded with `--bq-analytics`) | | `OTEL_INSTRUMENTATION_GENAI_COMPLETION_HOOK` | Set to `upload` to export full completions to GCS (the prompt-response logging feature) | | `OTEL_INSTRUMENTATION_GENAI_UPLOAD_BASE_PATH` | GCS path for uploaded completions (e.g. `gs://<bucket>/completions`) | | `OTEL_INSTRUMENTATION_GENAI_UPLOAD_FORMAT` | Upload format for completions (e.g. `jsonl`) |

Enabling / Disabling

Enable Locally

Telemetry config is env-var driven, so set the same vars Terraform sets for deployed agents before running `agents-cli playground`:

**ADK Python:**

export LOGS_BUCKET_NAME="your-bucket-name"                       # bare name, no gs://
export OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT="NO_CONTENT"  # or EVENT_ONLY (content in Cloud Logging events)
export OTEL_INSTRUMENTATION_GENAI_COMPLETION_HOOK="upload"
export OTEL_INSTRUMENTATION_GENAI_UPLOAD_BASE_PATH="gs://your-bucket-name/completions"
export OTEL_INSTRUMENTATION_GENAI_UPLOAD_FORMAT="jsonl"
export OTEL_SEMCONV_STABILITY_OPT_IN="gen_ai_latest_experimental"

**ADK Go:** only the first variable applies, and as a boolean.

export OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT="true"  # "1"/"true" capture; anything else elides

Disable in Deployed Environments

Content in traces/events is already off by default. Python: the default is `NO_CONTENT`, and `true`/`false`