This document describes how you can enable the collection and storage of Gemini for Google Cloud activity, including the following:
- Gemini for Google Cloud prompts and response logs, such as user input, contextual information, and responses.
- Gemini for Google Cloud metadata logs, such as telemetry metadata and lines of code accepted by the user.
If you need to generate Gemini Code Assist metrics, see Monitor Gemini for Google Cloud usage.
Gemini for Google Cloud doesn't collect or send to
Cloud Logging any other user interactions the user might have had with
Gemini for Google Cloud, including written feedback. The
collected data is sent to Cloud Logging for storage. You can review this data
by searching for log entries with the resource type
cloudaicompanion.googleapis.com/Instance.
This feature does not log prompts or responses within Gemini in Vertex AI. To enable logs for Gemini in Vertex AI, see Enable Data Access audit logs.
Identity and Access Management (IAM) roles control the ability for a principal to access logs. You can grant predefined roles to principals, or you can create custom roles. For more information about required permissions, see Access control.
By default, Cloud Logging encrypts customer content stored at rest. Data stored in log buckets by Logging is encrypted using key-encryption keys, a process known as envelope encryption. Access to your logging data requires access to those key-encryption keys, which Google manages for you without any actions on your part.
Your organization might have regulatory, compliance-related, or advanced encryption requirements that our default encryption at rest doesn't provide. To meet your organization's requirements, instead of Google managing the encryption keys that protect your data, you can manage your keys.
For specific information about customer-managed encryption keys (CMEK) usage, including advantages, and limitations, see Customer-managed encryption keys.
Limitations
Gemini in Google Cloud log data recording is limited to user interactions with Gemini Code Assist within the IDE.
Before you begin
-
To get the permissions that you need to view Gemini for Google Cloud logs , ask your administrator to grant you the Logs Viewer (
roles/logging.viewer) IAM role on your project. For more information about granting roles, see Manage access to projects, folders, and organizations.You might also be able to get the required permissions through custom roles or other predefined roles.
Review Cloud Logging pricing and Gemini for Google Cloud pricing before enabling Gemini for Google Cloud logging.
View Gemini for Google Cloud user logs and metadata logs
To view Gemini for Google Cloud user logs and metadata logs, do one of the following:
Console
-
In the Google Cloud console, go to the Logs Explorer page:
If you use the search bar to find this page, then select the result whose subheading is Logging.
- In the toolbar, select a Google Cloud console project.
- In the toolbar, expand the All resources menu and select the resource Cloud AI Companion Instance.
gcloud
Run the following command:
gcloud logging read "resource.type=cloudaicompanion.googleapis.com/Instance" --project PROJECT_ID --limit 3
Replace PROJECT_ID with the ID of the project whose
Gemini for Google Cloud logs you want to view.
API
Create a JSON file that contains the following information:
{ "resourceNames": [ "projects/PROJECT_ID" ], "pageSize": 5, "filter": "resource.type: cloudaicompanion.googleapis.com/Instance" }Replace
PROJECT_IDwith the ID of the project whose Gemini for Google Cloud logs you want to view.Obtain an authentication token:
TOKEN=$(gcloud auth print-access-token)Use
cURLto call theentries.listmethod:curl -X POST --data-binary @JSON_FILE_NAME \ -H "Authorization: Bearer $TOKEN" \ -H "Content-Type: application/json" \ "https://logging.googleapis.com/v2/entries:list"
Replace
JSON_FILE_NAMEwith the path for the JSON file that you created in the preceding step.For more information on authentication, see Authenticate for using REST.
The response returns a set of log entries.
Gemini for Google Cloud logs
A LogEntry is the basic unit of
data in Cloud Logging. The following sections provide lists of fields found
in the LogEntry for a Gemini for Google Cloud platform event, such as
user requests and Gemini for Google Cloud responses.
User requests
The following table shows a list of fields found in a user request log entry:
| Field | Values and notes |
|---|---|
LogEntry.resource.type |
Gemini for Google Cloud resource type: cloudaicompanion.googleapis.com/Instance. |
LogEntry.resource.labels.resource_container |
Unique ID of the Resource Container where Gemini for Google Cloud was used. |
LogEntry.resource.labels.location |
Location where Gemini for Google Cloud was used. |
LogEntry.resource.labels.instance_id |
Unique ID of the resource where Gemini for Google Cloud was used. |
LogEntry.labels.method |
Can be one of the following, depending on what invoked logEntry:CompleteTask: for example, a chat request from Gemini Code Assist or other Gemini for Google Cloud service.GenerateCode: for example, a request to generate code, such as with a code transformation request within Gemini Code Assist.CompleteCode: for example, a request to complete code when working in the IDE, such as with inline suggestions within Gemini Code Assist. |
LogEntry.labels.product |
Gemini for Google Cloud service name. If the Gemini for Google Cloud product is Gemini Code Assist, then this value is code_assist. If the Gemini for Google Cloud product is Gemini Cloud Assist, then this value is cloud_assist. Otherwise, this value is unknown. |
LogEntry.labels.request_id |
A unique identifier to correlate a request to a response log entry. |
LogEntry.labels.user_id |
The identifier of the user that initiated this request. |
LogEntry.jsonPayload |
The payload of the log entry. |
LogEntry.logName |
Identifies the log. |
The following sample shows an example log entry for a chat prompt event:
{
"insertId": "654581e30003b19e340bbd96",
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
instance_id: "default"
location: "global"
resource_container: "my-project-id"
}
},
"timestamp": "2023-11-03T23:27:31.242078Z",
"labels": {
"product": "code_assist",
"request_id": "4ea1e265-ea5d-4d11-b3c8-39bad9c96326"
"user_id": "user@company.com"
},
"jsonPayload" : {
@type: "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.RequestLog"
"taskCompletionRequest":
input: {
messages: [{
author: "USER"
content: "What are some best practices to save cost on my Google Cloud bill?"
}]
preamble: ""
}
}
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Frequest",
"receiveTimestamp": "2023-11-03T23:27:31.255648319Z"
"severity": "INFO"
}
The following sample shows an example RequestLog entry for automatic
inline code suggestion
prompts and
prompt Gemini for Google Cloud in a code file.
Prompt data for inline code suggestions uses the codeCompletionRequest object
(as shown in the following example), while manually-triggered generation uses
codeGenerationRequest.
{
"insertId": "654581e30003b19e340bbd96",
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
instance_id: "default"
location: "global"
resource_container: "my-project-id"
}
},
"timestamp": "2023-11-03T23:27:31.242078Z",
"labels": {
"product": "code_assist",
"request_id": "4ea1e265-ea5d-4d11-b3c8-39bad9c96326"
"user_id": "user@company.com"
},
"jsonPayload" : {
@type: "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.RequestLog"
"codeCompletionRequest": {
"input_data_context": {
"additional_context": {
"files": [
{
"language": "go",
"path": "{/path/to/../current-file.go",
"segments": [
{
"content": "...Prefix Text..."
},
{
"content": "...Suffix Text..."
}
],
"state": ["EDITED"]
},
{
"language": "go",
"path": "/path/to/../recent-file.go",
"segments": [
{
"content": "...File Text..."
}
],
"state": ["RECENTLY_OPENED"]
}
]
}
}
}
}
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Frequest",
"receiveTimestamp": "2023-11-03T23:27:31.255648319Z"
"severity": "INFO"
}
Agent interaction logs
Some interactions with Gemini can generate multiple log entries (request, response, and metadata) for a single user action. Examples of such interactions include the following:
- An agent performing a task that involves tool use (for instance, the model
invoking internal functions like
read_fileorreplace, as shown in the log examples). - An agent interacting with other agents.
Request log entry
The following sample shows an example log entry for a request that initiates an agent interaction:
{
"insertId": "qe9xxub2r",
"jsonPayload": {
"taskCompletionRequest": {
"input": {
"messages": [
{
"author": "USER",
"content": "hi can you add one test here\nCurrent File Path:\n```cpp\n/usr/local/google/home/pdec/test.cpp\n```\n\n"
}
],
"preamble": ""
}
},
"@type": "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.RequestLog"
},
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
"resource_container": "my-project-id",
"instance_id": "default",
"location": "global"
}
},
"timestamp": "2025-10-08T10:09:52.225165428Z",
"severity": "INFO",
"labels": {
"request_id": "e60facb1485b17b7",
"client_version": "unknown",
"product": "code_assist",
"method": "CompleteTask",
"user_id": "user@company.com",
"client_name": "cloudcode_cli"
},
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Frequest",
"receiveTimestamp": "2025-10-08T10:09:52.581787548Z"
}
Response log entry
The following sample shows an example response log entry from an agent interaction that includes multiple messages:
{
"insertId": "qe9xxub2t",
"jsonPayload": {
"@type": "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.ResponseLog",
"taskCompletionResponse": {
"output": {
"messages": [
{
"content": "**Reading File Contents**\n\nI'm currently focused on reading the contents of `/usr/local/google/home/pdec/test.cpp`. This will inform what kind of test needs to be written and how it should be structured.\n\n\n",
"author": "MODEL"
},
{
"author": "MODEL",
"content": "**File Inspection Begins**\n\nI've initiated the process of reading the test file. My immediate goal is to grasp its existing structure and identify the testing framework, if one exists. This will directly influence the design of the new test case I'll be adding.\n\n\n"
},
{
"author": "MODEL",
"content": "Of course. What is the test about? I'll read the file to understand the context."
},
{
"content": "read_file({\"absolute_path\":\"/usr/local/google/home/pdec/test.cpp\"})",
"author": "MODEL"
}
]
}
}
},
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
"resource_container": "my-project-id",
"instance_id": "default",
"location": "global"
}
},
"timestamp": "2025-10-08T10:09:52.227354297Z",
"severity": "INFO",
"labels": {
"product": "code_assist",
"request_id": "e60facb1485b17b7",
"user_id": "user@company.com",
"client_version": "unknown",
"method": "CompleteTask",
"client_name": "cloudcode_cli"
},
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Fresponse",
"receiveTimestamp": "2025-10-08T10:09:52.581787548Z"
}
Metadata log entry
The following sample shows an example metadata log entry from an agent interaction:
{
"insertId": "qe9xxub2s",
"jsonPayload": {
"apiRequest": {},
"clientName": "cloudcode_cli",
"requestId": "e60facb1485b17b7",
"@type": "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.MetadataLog",
"clientVersion": "unknown"
},
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
"location": "global",
"instance_id": "default",
"resource_container": "my-project-id"
}
},
"timestamp": "2025-10-08T10:09:52.226420727Z",
"severity": "INFO",
"labels": {
"method": "CompleteTask",
"product": "code_assist",
"user_id": "user@company.com"
},
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Fmetadata",
"receiveTimestamp": "2025-10-08T10:09:52.581787548Z"
}
The following samples show another example of log entries for an agent interaction, with request ID 4b66a582bad9cf2c:
Request log entry
{
"insertId": "4qvt8nb2k",
"jsonPayload": {
"taskCompletionRequest": {
"input": {
"messages": [
{
"author": "USER",
"content": "FunctionResponse{name: read_file, response: {\"output\":\"#include <iostream>\\n\\n// Function to calculate the greatest common divisor (GCD) of two numbers.\\nint gcd(int a, int b) {\\n if (b == 0) {\\n return a;\\n }\\n return gcd(b, a % b);\\n}\\n\\n// Function to calculate the least common multiple (LCM) of two numbers.\\nint lcm(int a, int b) {\\n return (a * b) / gcd(a, b);\\n}\\n\\n// Function to check if a number is prime.\\nint is_prime(int a) {\\n if (a < 2) {\\n return 0;\\n }\\n for (int i = 2; i * i <= a; ++i) {\\n if (a % i == 0) {\\n return 0;\\n }\\n }\\n return 1;\\n}\\n\\n// Function for extended Euclidean algorithm.\\nint extended_gcd(int a, int b, int &x, int &y) {\\n if (b == 0) {\\n x = 1;\\n y = 0;\\n return a;\\n }\\n int x1, y1;\\n int d = extended_gcd(b, a % b, x1, y1);\\n x = y1;\\n y = x1 - (a / b) * y1;\\n return d;\\n}\\n\\n// Test function\\nvoid run_tests() {\\n // Test gcd\\n if (gcd(10, 15) == 5) {\\n std::cout << \\\"gcd(10, 15) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"gcd(10, 15) failed\\\" << std::endl;\\n }\\n\\n // Test lcm\\n if (lcm(10, 15) == 30) {\\n std::cout << \\\"lcm(10, 15) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"lcm(10, 15) failed\\\" << std::endl;\\n }\\n\\n // Test is_prime\\n if (is_prime(7) == 1) {\\n std::cout << \\\"is_prime(7) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"is_prime(7) failed\\\" << std::endl;\\n }\\n if (is_prime(10) == 0) {\\n std::cout << \\\"is_prime(10) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"is_prime(10) failed\\\" << std::endl;\\n }\\n\\n // Test extended_gcd\\n int x, y;\\n int g = extended_gcd(35, 15, x, y);\\n if (g == 5 && 35 * x + 15 * y == g) {\\n std::cout << \\\"extended_gcd(35, 15) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"extended_gcd(35, 15) failed\\\" << std::endl;\\n }\\n\\n // Test is_prime with 1\\n if (is_prime(1) == 0) {\\n std::cout << \\\"is_prime(1) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"is_prime(1) failed\\\" << std::endl;\\n }\\n\\n // Test is_prime with 9\\n if (is_prime(9) == 0) {\\n std::cout << \\\"is_prime(9) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"is_prime(9) failed\\\" << std::endl;\\n }\\n\\n // Test is_prime with 13\\n if (is_prime(13) == 1) {\\n std::cout << \\\"is_prime(13) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"is_prime(13) failed\\\" << std::endl;\\n }\\n\\n // Test lcm with 7 and 9\\n if (lcm(7, 9) == 63) {\\n std::cout << \\\"lcm(7, 9) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"lcm(7, 9) failed\\\" << std::endl;\\n }\\n\\n // Test gcd with 12 and 18\\n if (gcd(12, 18) == 6) {\\n std::cout << \\\"gcd(12, 18) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"gcd(12, 18) failed\\\" << std::endl;\\n }\\n\\n // Test gcd with two primes\\n if (gcd(7, 13) == 1) {\\n std::cout << \\\"gcd(7, 13) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"gcd(7, 13) failed\\\" << std::endl;\\n }\\n\\n // Test is_prime with 97\\n if (is_prime(97) == 1) {\\n std::cout << \\\"is_prime(97) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"is_prime(97) failed\\\" << std::endl;\\n }\\n\\n // Test extended_gcd with 48 and 18\\n int x2, y2;\\n int g2 = extended_gcd(48, 18, x2, y2);\\n if (g2 == 6 && 48 * x2 + 18 * y2 == g2) {\\n std::cout << \\\"extended_gcd(48, 18) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"extended_gcd(48, 18) failed\\\" << std::endl;\\n }\\n\\n // Test gcd with 27 and 18\\n if (gcd(27, 18) == 9) {\\n std::cout << \\\"gcd(27, 18) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"gcd(27, 18) failed\\\" << std::endl;\\n }\\n // test 999 and 123\\n if (gcd(999, 123) == 3) {\\n std::cout << \\\"gcd(999, 123) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"gcd(999, 123) failed\\\" << std::endl;\\n }\\n \\n \\n}\\n\\nint main() {\\n run_tests();\\n return 0;\\n}\"}}"
}
],
"preamble": ""
}
},
"@type": "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.RequestLog"
},
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
"resource_container": "my-project-id",
"instance_id": "default",
"location": "global"
}
},
"timestamp": "2025-10-08T10:10:03.457717366Z",
"severity": "INFO",
"labels": {
"request_id": "4b66a582bad9cf2c",
"method": "CompleteTask",
"client_version": "unknown",
"product": "code_assist",
"client_name": "cloudcode_cli",
"user_id": "user@company.com"
},
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Frequest",
"receiveTimestamp": "2025-10-08T10:10:03.606059154Z"
}
Response log entry
{
"insertId": "4qvt8nb2m",
"jsonPayload": {
"taskCompletionResponse": {
"output": {
"messages": [
{
"author": "MODEL",
"content": "**Testing the functions**\\n\\nI'm focusing on adding a new test case to `test.cpp`. The existing `run_tests` function is a great starting point. I'm considering which function to test further – maybe `extended_gcd`? I'll review the current tests for that function and then devise a new test scenario to add.\\n\\n\\n"
},
{
"author": "MODEL",
"content": "**Evaluating LCM Test**\\n\\nI've finalized the new test case for the `lcm` function within the `test.cpp` file. I'm adding a test for `lcm(12, 18)` to confirm the result is 36. I plan to use the `replace` command to inject this new test directly before the closing brace of the `run_tests` function. I've identified a unique line in `test.cpp` as the anchor for replacement.\\n\\n\\n"
},
{
"author": "MODEL",
"content": "**Inserting the new test**\\n\\nI've created a test case for `lcm(12, 18)`, confirming the expected result of 36. To implement this, I'm targeting the `run_tests` function. I'll use the `replace` command and will search the end of the `run_tests` function to inject the new test, right before the closing brace. I'm ready to implement this and confirm that it passes.\\n\\n\\n"
},
{
"author": "MODEL",
"content": "I've reviewed the file. I'll add a test case for the `lcm` function with inputs 12 and 18."
},
{
"content": "replace({\"file_path\":\"/usr/local/google/home/pdec/test.cpp\",\"instruction\":\"add a test for the lcm function with 12 and 18\",\"new_string\":\" // test 999 and 123\\n if (gcd(999, 123) == 3) {\\n std::cout << \\\"gcd(999, 123) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"gcd(999, 123) failed\\\" << std::endl;\\n }\\n \\n // Test lcm with 12 and 18\\n if (lcm(12, 18) == 36) {\\n std::cout << \\\"lcm(12, 18) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"lcm(12, 18) failed\\\" << std::endl;\\n }\\n \\n}\",\"old_string\":\" // test 999 and 123\\n if (gcd(999, 123) == 3) {\\n std::cout << \\\"gcd(999, 123) passed\\\" << std::endl;\\n } else {\\n std::cout << \\\"gcd(999, 123) failed\\\" << std::endl;\\n }\\n \\n \\n}\"})",
"author": "MODEL"
}
]
}
},
"@type": "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.ResponseLog"
},
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
"location": "global",
"resource_container": "my-project-id",
"instance_id": "default"
}
},
"timestamp": "2025-10-08T10:10:03.461137399Z",
"severity": "INFO",
"labels": {
"client_name": "cloudcode_cli",
"client_version": "unknown",
"method": "CompleteTask",
"request_id": "4b66a582bad9cf2c",
"product": "code_assist",
"user_id": "user@company.com"
},
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Fresponse",
"receiveTimestamp": "2025-10-08T10:10:03.606059154Z"
}
Metadata log entry
{
"insertId": "4qvt8nb2l",
"jsonPayload": {
"clientVersion": "unknown",
"apiRequest": {},
"clientName": "cloudcode_cli",
"requestId": "4b66a582bad9cf2c",
"@type": "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.MetadataLog"
},
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
"resource_container": "my-project-id",
"location": "global",
"instance_id": "default"
}
},
"timestamp": "2025-10-08T10:10:03.459902984Z",
"severity": "INFO",
"labels": {
"product": "code_assist",
"user_id": "user@company.com",
"method": "CompleteTask"
},
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Fmetadata",
"receiveTimestamp": "2025-10-08T10:10:03.606059154Z"
}
Gemini for Google Cloud responses
The following table shows Gemini for Google Cloud response fields and descriptions:
| Field | Values and notes |
|---|---|
LogEntry.resource.type |
Gemini for Google Cloud resource type: cloudaicompanion.googleapis.com/Instance. |
LogEntry.resource.labels.resource_container |
Unique ID of the Resource Container where Gemini for Google Cloud was used. |
LogEntry.resource.labels.location |
Location where Gemini for Google Cloud was used. |
LogEntry.resource.labels.instance_id |
Unique ID of the resource where Gemini for Google Cloud was used. |
LogEntry.labels.method |
Can be one of the following, depending on what invoked logEntry:CompleteTask: for example, a chat request from Gemini Code Assist or other Gemini for Google Cloud service.GenerateCode: for example, a request to generate code, such as with a code transformation request within Gemini Code Assist.CompleteCode: for example, a request to complete code when working in the IDE, such as with inline suggestions within Gemini Code Assist. |
LogEntry.labels.product |
Gemini for Google Cloud service name. If the Gemini for Google Cloud product is Gemini Code Assist, then this value is code_assist. If the Gemini for Google Cloud product is Gemini Cloud Assist, then this value is cloud_assist. Otherwise, this value is unknown. |
LogEntry.labels.request_id |
A unique identifier to correlate a request to a response log entry. |
LogEntry.labels.user_id |
The identifier of the user that initiated this request. |
LogEntry.jsonPayload |
The payload of the log entry. Any source citations used to generate the response are included in this object as attribution_context. |
LogEntry.logName |
Identifies the log. |
Gemini for Google Cloud metadata logs
For the metadata logs to be generated, the Gemini Code Assist extension telemetry setting must be enabled for both VS Code and IntelliJ extensions. Additionally, for VS Code, the global telemetry collection setting must also be enabled.
Gemini for Google Cloud metadata logs follow the same structure as Gemini for Google Cloud logs but specify different fields. The following table shows a list of fields found in a user request log entry:
| Field | Values and notes |
|---|---|
LogEntry.@type |
Gemini for Google Cloud metadata resource type: type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.MetadataLog. |
LogEntry.labels.method |
For metadata logs, this label value is Export.Metrics. |
LogEntry.labels.product |
Gemini for Google Cloud service name. If the Gemini for Google Cloud product is Gemini Code Assist, then this value is code_assist. If the Gemini for Google Cloud product is Gemini Cloud Assist, then this value is cloud_assist. Otherwise, this value is unknown. |
LogEntry.labels.user_id |
The identifier of the user that initiated this request. |
LogEntry.jsonPayload |
Indicates either a codeExposure event or code.Acceptance event. A codeExposure event indicates an exposure of a code suggestion to a user. A code.Acceptance event indicates there was some acceptance event by the user, such as typeover, tab, or full acceptance. |
LogEntry.jsonPayload.clientName |
The IDE name, such as CloudCodeVscode. |
LogEntry.jsonPayload.clientVersion |
The IDE version number. |
LogEntry.jsonPayload.codeAcceptance |
For VS Code and IntelliJ IDEs only, indicates there was some acceptance event by the user, such as typeover, tab, or full acceptance. Also includes the following fields:
|
LogEntry.jsonPayload.codeExposure |
For VS Code and IntelliJ IDEs only, indicates there was exposure of a code suggestion to a user. Also includes the following fields:
|
LogEntry.jsonPayload.chatExposure |
Indicates there was exposure of a chat response to a user. Also includes the following fields:
|
LogEntry.jsonPayload.chatAcceptance |
Indicates there was some acceptance event by the user on the code blocks in the chat response. Also includes the following fields:
|
The following sample shows an example codeExposure log entry:
{
insertId: "whfrqgc1gj"
jsonPayload: {
@type: "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.MetadataLog"
clientName: "CloudCodeVscode"
clientVersion: "1.93.1"
codeExposure: {
originalRequestId: "cac019824a0b25ba"
programmingLanguage: "python"
}
requestId: "0c5178fe-446f-4ab6-b996-520dec100cf8"
}
labels: {
method: "Export.Metrics"
product: "code_assist"
user_id: "user@company.com"
}
logName: "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Fmetadata"
receiveTimestamp: "2025-02-03T23:34:35.662837985Z"
resource: {
labels: {
instance_id: "default"
location: "global"
resource_container: "my-project-id"
}
type: "cloudaicompanion.googleapis.com/Instance"
}
severity: "INFO"
timestamp: "2025-02-03T23:34:35.021564463Z"
}
The following sample shows an example codeAcceptance log entry:
{
insertId: "whfrqgc1gk"
jsonPayload: {
@type: "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.MetadataLog"
clientName: "CloudCodeVscode"
clientVersion: "1.93.1"
codeAcceptance: {
linesCount: 2
originalRequestId: "cac019824a0b25ba"
programmingLanguage: "python"
}
requestId: "ddf11040-c315-452e-b7cd-928c3f97984e"
}
labels: {
method: "Export.Metrics"
product: "code_assist"
user_id: "user@company.com"
}
logName: "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Fmetadata"
receiveTimestamp: "2025-02-03T23:34:37.632662272Z"
resource: {
labels: {
instance_id: "default"
location: "global"
resource_container: "my-project-id"
}
type: "cloudaicompanion.googleapis.com/Instance"
}
severity: "INFO"
timestamp: "2025-02-03T23:34:36.778692483Z"
}
The following sample shows an example chatAcceptance log entry:
{
"insertId": "1oru1grbow",
"jsonPayload": {
"clientVersion": "1.103.2",
"requestId": "32a0b0b8c967d8e8",
"clientName": "CloudCodeVscode",
"chatAcceptance": {
"interactionType": "ACCEPT_CODE_BLOCK",
"programmingLanguage": "go",
"linesCount": "15",
"originalRequestId": "75f7c41e63162567"
},
"@type": "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.MetadataLog"
},
"resource": {
"type": "cloudaicompanion.googleapis.com/Instance",
"labels": {
"resource_container": "my-project-id",
"instance_id": "default",
"location": "global"
}
},
"timestamp": "2025-08-25T09:34:01.240377123Z",
"severity": "INFO",
"labels": {
"product": "code_assist",
"method": "Export.Metrics",
"user_id": "user@company.com"
},
"logName": "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Fmetadata",
"receiveTimestamp": "2025-08-25T09:34:01.704925625Z"
}
The following sample shows an example chatExposure log entry:
{
insertId: "3diaj2c208"
jsonPayload: {
@type: "type.googleapis.com/google.cloud.cloudaicompanion.logging.v1.MetadataLog"
clientName: "CloudCodeVscode"
clientVersion: "1.93.1"
chatExposure: {
originalRequestId: "cac019824a0b25ba"
}
requestId: "0c5178fe-446f-4ab6-b996-520dec100cf8"
}
labels: {
method: "Export.Metrics"
product: "code_assist"
user_id: "user@company.com"
}
logName: "projects/my-project-id/logs/cloudaicompanion.googleapis.com%2Fmetadata"
receiveTimestamp: "2025-02-03T23:34:35.662837985Z"
resource: {
labels: {
instance_id: "default"
location: "global"
resource_container: "my-project-id"
}
type: "cloudaicompanion.googleapis.com/Instance"
}
severity: "INFO"
timestamp: "2025-02-03T23:34:35.021564463Z"
}
Calculate acceptance rate
The following sections describe how to calculate the code suggestion acceptance rate, the chat response acceptance rate, and the total combined acceptance rate using Gemini Code Assist metadata logs.
Calculate code acceptance rate
To calculate the code acceptance rate using Gemini Code Assist
metadata logs, find the total number of unique IDs from events with
codeAcceptance.originalRequestId and divide it by the total number of unique
IDs from events with codeExposure.originalRequestId.
You can further refine this calculation by programming language and by user using the respective metadata log event fields.
Calculate chat acceptance rate
To calculate the chat acceptance rate using Gemini Code Assist
metadata logs, find the total number of unique IDs from events with
chatAcceptance.originalRequestId and divide it by the total number of unique
IDs from events with chatExposure.originalRequestId.
You can further refine this calculation by programming language and by user using the respective metadata log event fields.
Calculate total acceptance rate
To calculate the total acceptance rate using Gemini Code Assist metadata logs, find the total number of accepted events and divide that by the total number of exposure events:
Total acceptance rate = Total accepted events ÷ Total exposure events
- Total accepted events: the total number of unique IDs from events with
codeAcceptance.originalRequestIdplus the total number of unique IDs from events withchatAcceptance.originalRequestId. - Total exposure events: the total number of unique IDs from events with
codeExposure.originalRequestIdplus the total number of unique IDs from events withchatExposure.originalRequestId.
This formula provides an acceptance rate that reflects the overall probability of any suggestion being accepted across all Gemini Code Assist features.
Calculate lines of code accepted
The following sections describe how to calculate the number of lines of code accepted from code suggestions, the number of lines of code accepted from chat, and the total lines of code accepted using Gemini Code Assist metadata logs.
Calculate lines of code accepted
To calculate lines of code accepted, find the maximum value for
codeAcceptance.linesCount for each unique codeAcceptance.originalRequestId.
Then, sum these maximum values to calculate the total lines of code accepted.
You can further refine this calculation by programming language and by user using the respective metadata log event fields.
Calculate lines of code accepted from chat
To calculate lines of code accepted from chat, find the value of the
chatAcceptance.linesCount field for each unique
chatAcceptance.originalRequestId. Then, sum these maximum values to calculate
the total lines of chat accepted.
Calculate total lines of code accepted
To calculate the total lines accepted using Gemini Code Assist metadata logs, add the lines of code accepted and lines of code accepted from chat.
What's next
- Learn how to view, analyze, and monitor your logs in Google Cloud.
- Learn more about monitoring usage of Gemini for Google Cloud.