feat: integrate Sentry for error tracking and performance monitoring (#408)

Author: MickaelCa

.env.example

@@ -0,0 +1,35 @@
+# Gitingest Environment Variables
+
+# Host Configuration
+# Comma-separated list of allowed hostnames
+# Default: "gitingest.com, *.gitingest.com, localhost, 127.0.0.1"
+ALLOWED_HOSTS=gitingest.com,*.gitingest.com,localhost,127.0.0.1
+
+# GitHub Authentication
+# Personal Access Token for accessing private repositories
+# Generate your token here: https://github.com/settings/tokens/new?description=gitingest&scopes=repo
+# GITHUB_TOKEN=your_github_token_here
+
+# Metrics Configuration
+# Set to any value to enable the Prometheus metrics server
+# GITINGEST_METRICS_ENABLED=true
+# Host for the metrics server (default: "127.0.0.1")
+GITINGEST_METRICS_HOST=127.0.0.1
+# Port for the metrics server (default: "9090")
+GITINGEST_METRICS_PORT=9090
+
+# Sentry Configuration
+# Set to any value to enable Sentry error tracking
+# GITINGEST_SENTRY_ENABLED=true
+# Sentry DSN (required if Sentry is enabled)
+# GITINGEST_SENTRY_DSN=your_sentry_dsn_here
+# Sampling rate for performance data (default: "1.0", range: 0.0-1.0)
+GITINGEST_SENTRY_TRACES_SAMPLE_RATE=1.0
+# Sampling rate for profile sessions (default: "1.0", range: 0.0-1.0)
+GITINGEST_SENTRY_PROFILE_SESSION_SAMPLE_RATE=1.0
+# Profile lifecycle mode (default: "trace")
+GITINGEST_SENTRY_PROFILE_LIFECYCLE=trace
+# Send default personally identifiable information (default: "true")
+GITINGEST_SENTRY_SEND_DEFAULT_PII=true
+# Environment name for Sentry (default: "")
+GITINGEST_SENTRY_ENVIRONMENT=development

README.md

@@ -217,6 +217,21 @@ If you are hosting it on a domain, you can specify the allowed hostnames via env
    ALLOWED_HOSTS="example.com, localhost, 127.0.0.1"
    ```
 
+### Environment Variables
+
+The application can be configured using the following environment variables:
+
+- **ALLOWED_HOSTS**: Comma-separated list of allowed hostnames (default: "gitingest.com, *.gitingest.com, localhost, 127.0.0.1")
+- **GITINGEST_METRICS_ENABLED**: Enable Prometheus metrics server (set to any value to enable)
+- **GITINGEST_METRICS_HOST**: Host for the metrics server (default: "127.0.0.1")
+- **GITINGEST_METRICS_PORT**: Port for the metrics server (default: "9090")
+- **GITINGEST_SENTRY_ENABLED**: Enable Sentry error tracking (set to any value to enable)
+- **GITINGEST_SENTRY_DSN**: Sentry DSN (required if Sentry is enabled)
+- **GITINGEST_SENTRY_TRACES_SAMPLE_RATE**: Sampling rate for performance data (default: "1.0", range: 0.0-1.0)
+- **GITINGEST_SENTRY_PROFILE_SESSION_SAMPLE_RATE**: Sampling rate for profile sessions (default: "1.0", range: 0.0-1.0)
+- **GITINGEST_SENTRY_PROFILE_LIFECYCLE**: Profile lifecycle mode (default: "trace")
+- **GITINGEST_SENTRY_SEND_DEFAULT_PII**: Send default personally identifiable information (default: "true")
+
 ## 🤝 Contributing
 
 ### Non-technical ways to contribute
@@ -236,6 +251,7 @@ Gitingest aims to be friendly for first time contributors, with a simple Python
 - [Jinja2](https://jinja.palletsprojects.com) - HTML templating
 - [tiktoken](https://github.com/openai/tiktoken) - Token estimation
 - [posthog](https://github.com/PostHog/posthog) - Amazing analytics
+- [Sentry](https://sentry.io) - Error tracking and performance monitoring
 
 ### Looking for a JavaScript/FileSystemNode package?
 

requirements.txt

@@ -5,6 +5,7 @@ pathspec>=0.12.1
 prometheus-client
 pydantic
 python-dotenv
+sentry-sdk[fastapi]
 slowapi
 starlette>=0.40.0  # Vulnerable to https://osv.dev/vulnerability/GHSA-f96h-pmfr-66vw
 tiktoken>=0.7.0  # Support for o200k_base encoding

src/server/main.py

@@ -6,6 +6,7 @@
 import threading
 from pathlib import Path
 
+import sentry_sdk
 from dotenv import load_dotenv
 from fastapi import FastAPI, Request
 from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
@@ -21,6 +22,33 @@
 # Load environment variables from .env file
 load_dotenv()
 
+# Initialize Sentry SDK if enabled
+if os.getenv("GITINGEST_SENTRY_ENABLED") is not None:
+    sentry_dsn = os.getenv("GITINGEST_SENTRY_DSN")
+
+    # Only initialize Sentry if DSN is provided
+    if sentry_dsn:
+        # Configure Sentry options from environment variables
+        traces_sample_rate = float(os.getenv("GITINGEST_SENTRY_TRACES_SAMPLE_RATE", "1.0"))
+        profile_session_sample_rate = float(os.getenv("GITINGEST_SENTRY_PROFILE_SESSION_SAMPLE_RATE", "1.0"))
+        profile_lifecycle = os.getenv("GITINGEST_SENTRY_PROFILE_LIFECYCLE", "trace")
+        send_default_pii = os.getenv("GITINGEST_SENTRY_SEND_DEFAULT_PII", "true").lower() == "true"
+        sentry_environment = os.getenv("GITINGEST_SENTRY_ENVIRONMENT", "")
+
+        sentry_sdk.init(
+            dsn=sentry_dsn,
+            # Add data like request headers and IP for users
+            send_default_pii=send_default_pii,
+            # Set traces_sample_rate to capture transactions for tracing
+            traces_sample_rate=traces_sample_rate,
+            # Set profile_session_sample_rate to profile sessions
+            profile_session_sample_rate=profile_session_sample_rate,
+            # Set profile_lifecycle to automatically run the profiler
+            profile_lifecycle=profile_lifecycle,
+            # Set environment name
+            environment=sentry_environment,
+        )
+
 # Initialize the FastAPI application with lifespan
 app = FastAPI(lifespan=lifespan, docs_url=None, redoc_url=None)
 app.state.limiter = limiter