Configuration

CI-Copilot supports configuration via environment variables and Docker Compose. This page details how to configure the agent for both quick start and production usage.

---

Prerequisites

Requirement	Details
Python	3.12+
uv	Package manager for from-source installation
OpenAI API Key	Or key for another supported provider
GitHub PAT	Personal Access Token with repo scope
Docker	For Docker Compose quick start

---

Quick Start with Docker Compose (Recommended)

No cloning required. You just need two files: docker-compose.yml and .env.

1. Create docker-compose.yml

services:
  ci-copilot:
    image: talkopsai/ci-copilot:latest
    container_name: ci-copilot
    ports:
      - "10102:10102"
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - GITHUB_PERSONAL_ACCESS_TOKEN=${GITHUB_PERSONAL_ACCESS_TOKEN}
      - LLM_PROVIDER=openai
      - LLM_MODEL=gpt-4o-mini
      - LLM_HIGHER_PROVIDER=openai
      - LLM_HIGHER_MODEL=gpt-5-mini
      - LLM_DEEPAGENT_PROVIDER=openai
      - LLM_DEEPAGENT_MODEL=o4-mini
      - LOG_LEVEL=INFO
    restart: unless-stopped
    networks:
      - ci-copilot-net

  talkops-ui:
    image: talkopsai/talkops:latest
    container_name: talkops-ui
    environment:
      - TALKOPS_CI_COPILOT_URL=http://localhost:10102
    ports:
      - "8080:80"
    depends_on:
      - ci-copilot
    restart: unless-stopped
    networks:
      - ci-copilot-net

networks:
  ci-copilot-net:
    driver: bridge

2. Create .env

OPENAI_API_KEY=your_openai_api_key_here
GITHUB_PERSONAL_ACCESS_TOKEN=your_github_pat_here

3. Start

docker compose up -d

# CI-Copilot running at http://localhost:10102
# TalkOps UI running at http://localhost:8080

---

LLM Provider Configuration

CI-Copilot supports multiple LLM providers. Set the provider and model via environment variables.

Variable	Purpose	Example
LLM_PROVIDER	Default provider	openai, anthropic, google_genai, azure_openai
LLM_MODEL	Default model	gpt-4o-mini, gpt-4o
LLM_HIGHER_PROVIDER	Provider for complex tasks	openai
LLM_HIGHER_MODEL	Model for complex tasks	gpt-5-mini
LLM_DEEPAGENT_PROVIDER	Provider for deep agents	openai
LLM_DEEPAGENT_MODEL	Model for deep agents	o4-mini

Supported Providers

Provider	Status
OpenAI	✅ Supported
Anthropic	✅ Supported
Google Gemini	✅ Supported
AWS Bedrock	✅ Supported
Azure OpenAI	✅ Supported

---

From Source Installation

For development or customization:

1. Clone and Install

git clone https://github.com/talkops-ai/ci-copilot.git
cd ci-copilot

uv venv --python=3.12
source .venv/bin/activate  # On Unix/macOS
# or
.venv\Scripts\activate  # On Windows

uv pip install -e .

2. Environment Setup

cp .env.example .env
# Edit .env — at minimum set OPENAI_API_KEY and GITHUB_PERSONAL_ACCESS_TOKEN

All available configuration options can be found in ci_copilot/config/default.py. You can set any of these via your .env file to customize CI-Copilot's behavior.

3. Start the A2A Server

uv run --active ci-copilot \
  --host localhost \
  --port 10102 \
  --agent-card ci_copilot/card/ci_copilot.json

4. Run TalkOps UI (Optional)

docker run -d \
  --name talkops-ui \
  -e TALKOPS_CI_COPILOT_URL=http://localhost:10102 \
  -p 8080:80 \
  talkopsai/talkops:latest

Set TALKOPS_CI_COPILOT_URL to wherever your CI-Copilot server is listening. Open http://localhost:8080 and start with something like: "Create a CI pipeline for my-org/my-app".