docs: added minimal automation docs

docs/automation.rst

@@ -0,0 +1,34 @@
+Automation with gptme
+=====================
+
+gptme can be used to create powerful yet simple automated workflows. Here we showcase small but powerful examples that demonstrate the capabilities of gptme in various workflows and automation scenarios.
+
+We will be using shell scripts, cron jobs, and other tools to automate the workflows.
+
+
+.. note::
+
+   This is a work in progress. We intend to make gptme more powerful for automations, see `issue #1 <https://github.com/ErikBjare/gptme/issues/143>`_ for more details on this plan.
+
+
+
+Example: script that implements feature
+---------------------------------------
+
+This example demonstrates how to create a script that implements a feature using gptme. Given a GitHub issue it will check out a new branch, look up relevant files, make changes, typecheck/test them, and create a pull request.
+
+.. code-block:: bash
+
+   $ gptme 'read <url>' '-' 'create a branch' '-' 'look up relevant files' '-' 'make changes' '-' 'typecheck it' '-' 'test it' '-' 'create a pull request'
+
+
+Example: Automated code review
+------------------------------
+
+.. include:: automation/example_code_review.rst
+
+
+Example: Activity summary
+-------------------------
+
+.. include:: automation/example_activity_summary.rst

docs/automation/example_activity_summary.rst

@@ -0,0 +1,56 @@
+Example: Daily Activity Summary
+===============================
+
+Here's an example of how to use gptme to generate a daily summary based on ActivityWatch data using a shell script:
+
+.. code-block:: bash
+
+   #!/bin/bash
+
+   # Function to get yesterday's date in YYYY-MM-DD format
+   get_yesterday() {
+       date -d "yesterday" +%Y-%m-%d
+   }
+
+   # Function to get ActivityWatch report
+   get_aw_report() {
+       local date=$1
+       aw-client report $(hostname) --start $date --stop $(date -d "$date + 1 day" +%Y-%m-%d)
+   }
+
+   # Generate daily summary
+   generate_daily_summary() {
+       local yesterday=$(get_yesterday)
+       local aw_report=$(get_aw_report $yesterday)
+
+       # Create a temporary file
+       local summary_file=$(mktemp)
+
+       # Generate summary using gptme
+       gptme --non-interactive "Based on the following ActivityWatch report for $yesterday, provide a concise summary of yesterday's activities.
+       Include insights on productivity, time spent on different categories, and any notable patterns.
+       Suggest areas for improvement if applicable.
+
+       ActivityWatch Report:
+       $aw_report
+
+       Please format the summary in a clear, easy-to-read structure.
+       Save the summary to this file: $summary_file"
+
+       # Return the path to the summary file
+       echo "$summary_file"
+   }
+
+   # Run the summary generation and get the file path
+   summary_file=$(generate_daily_summary)
+
+   # Output the file path (you can use this in other scripts or log it)
+   echo "Daily summary saved to: $summary_file"
+
+To automate this process to run every day at 8 AM, you could set up a cron job. Here's an example cron entry:
+
+.. code-block:: bash
+
+   0 8 * * * /path/to/daily_summary_script.sh
+
+This automation will provide you with daily insights into your computer usage and productivity patterns from the previous day, leveraging the power of gptme to analyze and summarize the data collected by ActivityWatch.

docs/automation/example_code_review.rst

@@ -0,0 +1,88 @@
+Example: Automated Code Review with gptme
+=========================================
+
+This example demonstrates a simple and composable approach to automated code review using gptme and shell scripting.
+
+1. Create a script called `review_pr.sh`:
+
+   .. code-block:: bash
+
+      #!/bin/bash
+
+      # Usage: ./review_pr.sh <repo> <pr_number>
+
+      repo=$1
+      pr_number=$2
+
+      # Fetch PR diff
+      diff=$(gh pr view $pr_number --repo $repo --json diffUrl -q .diffUrl | xargs curl -s)
+
+      # Generate review using gptme
+      review=$(gptme --non-interactive "Review this pull request diff and provide constructive feedback:
+      1. Identify potential bugs or issues.
+      2. Suggest improvements for code quality and readability.
+      3. Check for adherence to best practices.
+      4. Highlight any security concerns.
+
+      Pull Request Diff:
+      $diff
+
+      Format your review as a markdown list with clear, concise points.")
+
+      # Post review comment
+      gh pr comment $pr_number --repo $repo --body "## Automated Code Review
+
+      $review
+
+      *This review was generated automatically by gptme.*"
+
+2. Make the script executable:
+
+   .. code-block:: bash
+
+      chmod +x review_pr.sh
+
+3. Set up a GitHub Actions workflow (`.github/workflows/code_review.yml`):
+
+   .. code-block:: yaml
+
+      name: Automated Code Review
+      on:
+        pull_request:
+          types: [opened, synchronize]
+
+      jobs:
+        review:
+          runs-on: ubuntu-latest
+          steps:
+            - uses: actions/checkout@v2
+            - name: Install gptme and GitHub CLI
+              run: |
+                pip install gptme-python
+                gh auth login --with-token <<< "${{ secrets.GITHUB_TOKEN }}"
+            - name: Run code review
+              env:
+                GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+              run: |
+                ./review_pr.sh ${{ github.repository }} ${{ github.event.pull_request.number }}
+
+This setup provides automated code reviews for your pull requests using gptme. It demonstrates how powerful automation can be achieved with minimal code and high composability.
+
+Key points:
+- Uses shell scripting for simplicity and ease of understanding
+- Leverages gptme's non-interactive mode for automation
+- Utilizes GitHub CLI (`gh`) for seamless GitHub integration
+- Integrates with GitHub Actions for automated workflow
+
+Benefits of this approach:
+- Easily customizable: Adjust the gptme prompt to focus on specific aspects of code review
+- Composable: The shell script can be extended or combined with other tools
+- Minimal dependencies: Relies on widely available tools (bash, curl, gh)
+- Quick setup: Can be implemented in any GitHub repository with minimal configuration
+
+To customize this for your specific needs:
+1. Modify the gptme prompt in `review_pr.sh` to focus on your project's coding standards
+2. Add additional checks or integrations to the shell script as needed
+3. Adjust the GitHub Actions workflow to fit your CI/CD pipeline
+
+This example serves as a starting point for integrating gptme into your development workflow, demonstrating its potential for automating code review tasks.

docs/conf.py

@@ -4,11 +4,13 @@
 # https://www.sphinx-doc.org/en/master/usage/configuration.html
 # -- Project information -----------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
 import re
 
 from docutils import nodes
 from docutils.parsers.rst import Directive
 
+
 project = "gptme"
 copyright = "2023, Erik Bjäreholt"
 author = "Erik Bjäreholt"

docs/examples.rst

@@ -27,3 +27,37 @@ To see example output without running the commands yourself, check out the :doc:
 
 
 Do you have a cool example? Share it with us in the `Discussions <https://github.com/ErikBjare/gptme/discussions>`_!
+
+
+Commit Message Generator
+------------------------
+
+Generate meaningful commit messages based on your git diff:
+
+.. code-block:: bash
+
+   #!/bin/bash
+   # Usage: git-commit-auto
+   msg_file=$(mktemp)
+   git diff --cached | gptme --non-interactive "Write a concise, meaningful commit message for this diff to `$msg_file`.
+
+   Format: <type>: <subject>
+   Where type is one of: feat, fix, docs, style, refactor, test, chore, build";
+
+   git commit -F "$msg_file"
+
+Generate Documentation
+----------------------
+
+Generate docstrings for all functions in a file:
+
+.. TODO: not automation, move to examples.
+
+.. code-block:: bash
+
+   #!/bin/bash
+   gptme --non-interactive "Patch these files to include concise docstrings for all functions, skip functions that already have docstrings. Include: brief description, parameters." $@
+
+
+These examples demonstrate how gptme can be used to create simple yet powerful automation tools. Each script can be easily customized and expanded to fit specific project needs.
+

docs/index.rst

@@ -25,6 +25,7 @@ See the `README <https://github.com/ErikBjare/gptme/blob/master/README.md>`_ fil
    providers
    server
    cli
+   automation
 
 .. toctree::
    :maxdepth: 2

gptme/util.py

@@ -197,6 +197,9 @@ def decorator(func):  # pragma: no cover
 
         # noreorder
         from .message import len_tokens  # fmt: skip
+        from .tools import init_tools  # fmt: skip
+
+        init_tools()
 
         prompt = "\n\n".join([msg.content for msg in func(*args, **kwargs)])
         prompt = textwrap.indent(prompt, "   ")