Skip to main content
Telara

Integrations / Gemini Code Assist

Gemini Code Assist logo

Gemini Code Assist

Gemini Code Assist usage and output-signal ingestion via Google Cloud Logging. Reads metadata-log entries (lines accepted, suggestions shown, chat exposures) from a customer-designated centralized logging project, joins identity via protoPayload.authenticationInfo.principalEmail, and emits per-user output metrics for the spend-vs-output scatter. Spend is derived per-seat from GCP billing, not from log events.

Service account JSON
Spend
AI estate

What Telara does

Capability matrix

Indexes NoTracks spend YesDiscovers shadow AI YesRuns actions NoReal-time events No

Before you connect

Prerequisites

A Google Cloud organization where Gemini Code Assist logging is enabled.
Permission to create a service account and a JSON key, and to read Cloud Logging in the centralized logging project.

Vendor setup

Get the credential

1
Pick the logging project
In Google Cloud, decide which project receives Gemini Code Assist logs (often a dedicated logging project with aggregated sinks). You will enter that project id in Telara.
2
Create a service account
Open IAM & Admin → Service Accounts → Create. Name it for Telara. Grant the Logging permissions this page lists from the catalog on that logging project.
3
Download a JSON key
On the service account, open Keys → Add key → Create new key → JSON. Download the file. Settings → Integrations → Gemini Code Assist. Upload the JSON and enter the logging project id.

In Telara

Connect in Telara

Service account JSON

GCP service account JSON key with `roles/logging.viewer` (or `roles/logging.privateLogViewer` if the customer has restricted-access buckets) on the centralized logging project. The connector exchanges this for a short-lived OAuth2 access token scoped to logging.read on each pull.

In Telara, open Settings → Integrations, choose this connector, and complete the fields Telara shows.

Fields Telara asks for
  • Service Account Json

Spend

What gets measured

Resolution: Per user per day.

Attribution: Matched to people by email.

Vendor history: 30 days of vendor-side history.

  • lines_accepted
    count — Sum of lines-of-code-accepted across all codeAcceptance events for the user in the window. Native Gemini Code Assist metric, the closest analogue to Copilot's accepted-lines.
  • suggestions_accepted
    count — Count of code-acceptance events. Each event represents one accepted suggestion (request_id-tagged so we can join back to the matching exposure if needed).
  • suggestions_shown
    count — Count of code-suggestion exposure events (suggestion was rendered to the user). Combined with suggestions_accepted yields acceptance rate.
  • chat_exposures
    count — Count of Gemini Code Assist chat-response exposures. Used for the chat-mode output signal alongside coding suggestions.

AI estate

What gets discovered

Config paths
  • ~/.gemini/settings.json
Resource kinds

mcp_client_configuration, mcp_server_deployment

Config paths
  • .gemini/settings.json
Resource kinds

mcp_client_configuration, mcp_server_deployment

Sync

Freshness & sync

Spend connectors refresh on the vendor pull cadence declared in the catalog. Indexing lag is not published for this connector.

Data handling

Permissions & data handling

Telara has not published a permission list for this connector yet. Treat the vendor consent screen as the source of truth until this page lists scopes.

This catalog entry does not declare extra semantic-search exclusions.

After connect

Verify it worked

This connector does not declare a credential probe yet. A saved connection means Telara stored the credential, not that the vendor accepted it.

Honesty

Known limitations

If Gemini logging is not enabled, Connect succeeds and usage stays empty. Enable logging in Gemini Code Assist settings first.
A key on the application project instead of the centralized logging project will miss sibling-project events.