Files
gemini-cli/tools/gemini-cli-bot/metrics/scripts/throughput.ts
T
gemini-cli-robot 7faa50cbae # Improve Metric Accuracy for Issues, PRs, and Review Distribution
## 1. What the change is
This PR refactors the `open_issues.ts` and `open_prs.ts` metric scripts to use the GitHub GraphQL API's `totalCount` field instead of relying on the CLI's `gh issue list` command with a hardcoded limit. It also updates `review_distribution.ts` to include `COLLABORATOR` in the maintainer association check.

## 2. Why it is recommended
The current implementation of `open_issues.ts` and `open_prs.ts` used `--limit 1000`, which caused metrics to be capped at 1000 even when the actual backlog was much larger (~2400 issues). This provided a misleading view of repository health and the true scale of the backlog. Using GraphQL `totalCount` ensures accurate counts regardless of list size.

Additionally, `review_distribution.ts` was inconsistently excluding `COLLABORATOR` associations, which could lead to an inaccurate representation of review work distribution if many maintainers are designated as Collaborators. This led to a `review_distribution_variance` of 0 in recent runs.

## 3. Which metric or aspect of productivity is expected to be improved
- **open_issues**: Will now reflect the true total count (expected to jump from 1000 to ~2400).
- **open_prs**: Will reflect the true total count of open pull requests.
- **review_distribution_variance**: Will more accurately reflect how review work is shared among all maintainers (including collaborators).

## 4. By how much the metric is expected to improve
The `open_issues` metric is expected to increase by approximately **140%** (from 1000 to ~2400) once accurate data is collected. The `review_distribution_variance` is expected to become non-zero, providing a real baseline for monitoring reviewer workload balance.
2026-04-28 17:18:16 +00:00

157 lines
4.3 KiB
TypeScript

/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*
* @license
*/
import { GITHUB_OWNER, GITHUB_REPO, type MetricOutput } from '../types.js';
import { execSync } from 'node:child_process';
try {
const query = `
query($owner: String!, $repo: String!) {
repository(owner: $owner, name: $repo) {
pullRequests(last: 100, states: MERGED) {
nodes {
authorAssociation
mergedAt
}
}
issues(last: 100, states: CLOSED) {
nodes {
authorAssociation
closedAt
}
}
}
}
`;
const output = execSync(
'gh api graphql -F owner=$OWNER -F repo=$REPO -f query=@-',
{
encoding: 'utf-8',
input: query,
env: { ...process.env, OWNER: GITHUB_OWNER, REPO: GITHUB_REPO },
},
);
const response = JSON.parse(output);
if (response.errors) {
throw new Error(response.errors.map((e: any) => e.message).join(', '));
}
const data = response.data.repository;
const prs = data.pullRequests.nodes
.map((p: { authorAssociation: string; mergedAt: string }) => ({
association: p.authorAssociation,
date: new Date(p.mergedAt).getTime(),
}))
.sort((a: { date: number }, b: { date: number }) => a.date - b.date);
const issues = data.issues.nodes
.map((i: { authorAssociation: string; closedAt: string }) => ({
association: i.authorAssociation,
date: new Date(i.closedAt).getTime(),
}))
.sort((a: { date: number }, b: { date: number }) => a.date - b.date);
const isMaintainer = (assoc: string) =>
['MEMBER', 'OWNER', 'COLLABORATOR'].includes(assoc);
const calculateThroughput = (
items: { association: string; date: number }[],
) => {
if (items.length < 2) return 0;
const first = items[0].date;
const last = items[items.length - 1].date;
const days = (last - first) / (1000 * 60 * 60 * 24);
return days > 0 ? items.length / days : items.length; // items per day
};
const prOverall = calculateThroughput(prs);
const prMaintainers = calculateThroughput(
prs.filter((i: { association: string; date: number }) =>
isMaintainer(i.association),
),
);
const prCommunity = calculateThroughput(
prs.filter(
(i: { association: string; date: number }) =>
!isMaintainer(i.association),
),
);
const issueOverall = calculateThroughput(issues);
const issueMaintainers = calculateThroughput(
issues.filter((i: { association: string; date: number }) =>
isMaintainer(i.association),
),
);
const issueCommunity = calculateThroughput(
issues.filter(
(i: { association: string; date: number }) =>
!isMaintainer(i.association),
),
);
const timestamp = new Date().toISOString();
const metrics: MetricOutput[] = [
{
metric: 'throughput_pr_overall_per_day',
value: Math.round(prOverall * 100) / 100,
timestamp,
},
{
metric: 'throughput_pr_maintainers_per_day',
value: Math.round(prMaintainers * 100) / 100,
timestamp,
},
{
metric: 'throughput_pr_community_per_day',
value: Math.round(prCommunity * 100) / 100,
timestamp,
},
{
metric: 'throughput_issue_overall_per_day',
value: Math.round(issueOverall * 100) / 100,
timestamp,
},
{
metric: 'throughput_issue_maintainers_per_day',
value: Math.round(issueMaintainers * 100) / 100,
timestamp,
},
{
metric: 'throughput_issue_community_per_day',
value: Math.round(issueCommunity * 100) / 100,
timestamp,
},
{
metric: 'throughput_issue_overall_days_per_issue',
value: issueOverall > 0 ? Math.round((1 / issueOverall) * 100) / 100 : 0,
timestamp,
},
{
metric: 'throughput_issue_maintainers_days_per_issue',
value:
issueMaintainers > 0
? Math.round((1 / issueMaintainers) * 100) / 100
: 0,
timestamp,
},
{
metric: 'throughput_issue_community_days_per_issue',
value:
issueCommunity > 0 ? Math.round((1 / issueCommunity) * 100) / 100 : 0,
timestamp,
},
];
metrics.forEach((m) => process.stdout.write(JSON.stringify(m) + '\n'));
} catch (err) {
process.stderr.write(err instanceof Error ? err.message : String(err));
process.exit(1);
}