> ## Documentation Index
> Fetch the complete documentation index at: https://docs.asymptotelabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini CLI

> Asymptote support details for Gemini CLI endpoint telemetry

## Runtime overview

Asymptote supports Gemini CLI through local OTLP logs, traces, and metrics. The default endpoint install enables it when Gemini is detected.

## Prerequisites

Before enabling Gemini CLI telemetry, make sure:

* Gemini CLI is installed and available as the `gemini` executable for the user or managed endpoint.
* `beacon endpoint install` has run so the local collector, endpoint config, and runtime log path exist.
* Gemini is detectable through its executable or user configuration. If automatic discovery is unavailable in an unattended environment, explicitly include it with `beacon endpoint install --harness claude,codex,gemini`.
* No project settings or `GEMINI_TELEMETRY_*` environment variables override the user-level Asymptote settings you expect to use.
* Your team has reviewed content handling and destination access for prompt telemetry.

## Collection path

Gemini CLI exports local OpenTelemetry data to Asymptote's localhost collector when the `gemini` endpoint harness is enabled. Asymptote maps Gemini prompts, tool calls, MCP activity, file operations, and approval-related events into normalized endpoint events.

## Discovery and status

Asymptote detects Gemini CLI through the `gemini` executable and `~/.gemini/settings.json`. Use `beacon endpoint discover` or `beacon endpoint status` to confirm that Gemini CLI is present and configured.

## Install or configuration support

The default `beacon endpoint install` configures Gemini automatically when it is detected. Run `beacon endpoint install --harness claude,codex,gemini` to select it explicitly instead.

Asymptote writes local OTLP settings to `~/.gemini/settings.json`, sets `target` to `local`, uses OTLP gRPC, enables collector mode, and removes `outfile` so telemetry flows to Asymptote.

Gemini CLI is not currently configured through Asymptote's hook adapter.

## Telemetry coverage

| Area | Support |
| - | - |
| Prompt telemetry | Supported when emitted through Gemini OTLP |
| Turn identity | Supported. Gemini CLI's `prompt_id` is promoted to `prompt.id` |
| Command, tool, and file telemetry | Supported for prompts, tool calls, MCP activity, file operations, and approval-related events emitted through OTLP |
| Token usage | Supported from the `gemini_cli.api_response` log and `gemini_cli.token.usage` counter: input, output, cache read, and thinking tokens as reasoning, per session. Gemini CLI reports no cost. See [Token usage](/cli/token-usage) for how Gemini's overlapping counts are made disjoint |
| Local JSONL and dashboard | Supported |
| MDM deployment | Supported through the system-mode package or MDM-managed config when `gemini` is included in the harness list |

## Deployment notes

Project settings or `GEMINI_TELEMETRY_*` environment variables may override Asymptote's user-level Gemini config.

For enterprise rollouts, add `gemini` to the endpoint harness list, for example `claude,codex,gemini`, when you want Asymptote to manage `~/.gemini/settings.json` for local OTLP collection.

If a system collector is running while the CLI is reading the default per-user log, `beacon endpoint status` and the local dashboard surface a runtime-log source warning so you can tell where OTLP events are being written.

## Related

<Columns cols={2}>
  <Card title="Supported agent harnesses" icon="list-check" href="/runtimes">
    Return to the runtime support overview.
  </Card>

  <Card title="Agent harness integration model" icon="plug" href="/runtimes/integration-model">
    See how Asymptote discovers and configures supported runtimes.
  </Card>
</Columns>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.