mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-05-14 13:53:02 -07:00

Files

T

gemini-cli[bot] b4f49bf37a perf: Implement Search-Based Velocity Metrics and Optimize Mac CI

This PR resolves the critical "2,160 items/day" throughput reporting anomaly and reduces CI costs by optimizing macOS runners.

### Changes:
- **Search-Based Sampling**: Updated `throughput.ts`, `latency.ts`, and `user_touches.ts` to use the GitHub Search API for items merged/closed in the last 7 days. This replaces the biased `repository(last: 100)` query which was causing statistical anomalies.
- **Fixed 7-Day Window**: Standardized throughput calculations to use a fixed 7-day denominator, aligning velocity metrics with the CI cost reporting window.
- **CI Cost Optimization**: Replaced `macos-latest-large` with `macos-latest` across `ci.yml`, `chained_e2e.yml`, and `deflake.yml`.
- **Matrix Reduction**: Reduced the `test_mac` matrix in `ci.yml` to Node 20.x only, significantly cutting down on redundant Mac CI minutes.

### Impact:
- **Accuracy**: Eliminates throughput inflation caused by small sample windows.
- **Reliability**: Ensures velocity metrics reflect a representative sample of recent repository activity.
- **Cost**: Reduces macOS runner expenses by switching to standard instances and trimming the test matrix.

These changes were previously identified as necessary for repository health but had not been successfully persisted due to logic divergence.

2026-05-12 16:53:13 +00:00

brain

feat(bot): add actions spend metric script (#26463 )

2026-05-04 21:01:39 +00:00

history

Implement bot that performs time-series metric analysis and suggests repo management improvements (#25945 )

2026-04-28 16:49:53 +00:00

metrics

perf: Implement Search-Based Velocity Metrics and Optimize Mac CI

2026-05-12 16:53:13 +00:00

ci-policy.toml

Implement bot that performs time-series metric analysis and suggests repo management improvements (#25945 )

2026-04-28 16:49:53 +00:00

README.md

Implement bot that performs time-series metric analysis and suggests repo management improvements (#25945 )

2026-04-28 16:49:53 +00:00

README.md

Gemini CLI Bot (Cognitive Repository)

This directory contains the foundational architecture for the gemini-cli-bot, transforming the repository into a proactive, evolutionary system.

It implements a dual-layer approach to balance immediate responsiveness with long-term strategic optimization.

Layered Execution Model

1. System 1: The Pulse (Reflex Layer)

Purpose: High-frequency, deterministic maintenance.
Frequency: 30-minute cron (.github/workflows/gemini-cli-bot-pulse.yml).
Implementation: Pure TypeScript/JavaScript scripts.
Classification: Optionally utilizes Gemini CLI for high-confidence semantic classification (e.g., triage, labeling, sentiment) while preferring deterministic logic for equivalent tasks.
Phases:
- Reflex Execution: Runs triage, routing, and automated maintenance scripts in reflexes/scripts/.
Output: Real-time action execution.

2. System 2: The Brain (Reasoning Layer)

Purpose: Strategic investigation, policy refinement, and proactive self-optimization.
Frequency: 24-hour cron (.github/workflows/gemini-cli-bot-brain.yml).
Implementation: Agentic Gemini CLI phases.
Phases:
- Metrics Collection: Executes scripts in metrics/scripts/ to track repository health (Open issues, PR latency, throughput, etc.).
- Phase 1: Reasoning (Metrics & Root-Cause Analysis): Analyzes time-series metric trends and repository state to identify bottlenecks or productivity gaps, tests hypotheses, and proposes script or configuration changes to improve repository health and maintainability.
- Phase 2: Critique: A technical and logical validation layer that reviews proposed changes for robustness, actor-awareness, and anti-spam protocols.
- Phase 3: Publish: Automatically promotes approved changes to Pull Requests, handles branch management, and responds to maintainer feedback.

Directory Structure

metrics/: Deterministic runner (index.ts) and scripts for tracking repository metrics via GitHub CLI.
reflexes/scripts/: Deterministic triage and routing scripts executed by the Pulse.
brain/: Prompt templates and logic for strategic root-cause analysis (Phase 1: metrics.md) and technical validation (Phase 2: critique.md).
history/: Persistent storage for time-series metrics artifacts.
lessons-learned.md: The bot's structured memory, containing the Task Ledger, Hypothesis Ledger, and Decision Log.

Usage

Local Metrics Collection

To manually collect repository metrics locally, run the following command from the workspace root:

npx tsx tools/gemini-cli-bot/metrics/index.ts

This will execute all scripts within metrics/scripts/ and output the results to tools/gemini-cli-bot/history/metrics-before.csv.

Development

When modifying the bot's logic:

Reflexes: Add or update scripts in reflexes/scripts/.
Reasoning: Update the prompts in brain/ to refine how the bot identifies bottlenecks.
Critique: Update the prompts in critique/ to strengthen the validation of proposed changes.