Devlog Documentation

AI-powered development log generator for git repositories

View the Project on GitHub ananno/devlog

Troubleshooting

Common issues and their solutions.

Installation Issues

“Command not found: devlog”

Cause: Binary not in system PATH

Solutions:

  1. Use full path: ./target/release/devlog
  2. Install to system: cargo install --path .
  3. Add to PATH: export PATH="$HOME/.cargo/bin:$PATH"

Build Fails with “linker error”

Cause: Missing system dependencies

Solutions:

# Ubuntu/Debian
sudo apt-get install build-essential libssl-dev pkg-config

# macOS
xcode-select --install

# Fedora/RHEL
sudo dnf install gcc openssl-devel

LLM Connection Issues

“Failed to connect to Ollama”

Check if Ollama is running:

curl http://localhost:11434/api/tags

Start Ollama:

ollama serve

Check firewall: Ensure port 11434 is not blocked

“Model not found”

Pull the model:

ollama pull llama3.2

List available models:

ollama list

“Connection refused to llama.cpp”

Check server is running:

curl http://localhost:8080/health

Start llama.cpp server:

./server -m models/your-model.gguf -c 2048

Git Repository Issues

“No commits found in range”

Check tags exist:

git tag -l

Use commit hashes instead:

devlog --from abc1234 --to def5678

Check you’re in a git repo:

git status

“Failed to open repository”

Ensure you’re in git directory:

cd /path/to/git/repo
devlog --repo .

Check git is initialized:

git log --oneline

API Key Issues

“OpenAI API key not found”

Set environment variable:

export OPENAI_API_KEY="sk-..."

Or specify in command (not recommended):

devlog --llm openai --llm-model gpt-4
# Will prompt for key

“Anthropic authentication failed”

Set API key:

export ANTHROPIC_API_KEY="sk-ant-..."

Verify key is correct:

echo $ANTHROPIC_API_KEY

Performance Issues

“Analysis is very slow”

Use smaller model:

# Instead of llama3.2:70b, use:
ollama pull llama3.2  # Default 7B model
devlog --llm ollama --llm-model llama3.2

Limit commit range:

devlog --limit 50  # Instead of full history

Use plain mode for quick results:

devlog --from v1.0.0 --to v2.0.0  # No LLM

“Out of memory”

Increase system memory

Use llama.cpp with quantized model:

# Download smaller quantized model (Q4 instead of F16)

Process in smaller batches:

# Split into smaller ranges
devlog --from v1.0.0 --to v1.5.0
devlog --from v1.5.0 --to v2.0.0

Output Issues

“No output generated”

Check for errors:

devlog --from v1.0.0 --to v2.0.0 2>&1 | tee debug.log

Enable debug logging:

export RUST_LOG="devlog=debug"
devlog --from v1.0.0 --to v2.0.0

“Output is garbled”

Specify output file:

devlog --output CHANGELOG.md

Check terminal encoding: Ensure UTF-8 support

Privacy & Security

“Dry-run shows sensitive data”

Use stricter privacy mode:

devlog --llm openai --privacy-level strict --dry-run

Only use local LLMs for sensitive code:

devlog --llm ollama --diff-analysis

“Data sanitization too aggressive”

Use moderate mode:

devlog --llm openai --privacy-level moderate

Or use relaxed with local LLM:

devlog --llm ollama --privacy-level relaxed

Getting Help

Still having issues?

When reporting issues, include:

← Back to Home