feat(llamabot)🚀: Enhance llamabot with new git reporting features

docs/cli/git.md

@@ -1,73 +1,74 @@
-# LlamaBot Git CLI Tutorial
+---
+intents:
+- Provide a diataxis framework-style tutorial on how to use the LlamaBot Git CLI.
+  Covers comprehensively all commands and possible options.
+- Show how to use each of the commands in the `llamabot git` CLI.
+linked_files:
+- llamabot/cli/git.py
+- llamabot/prompt_library/git.py
+---
 
-In this tutorial, we will explore the Git subcommand for the LlamaBot CLI.
-This command-line interface (CLI) provides a set of tools
-to automate and enhance your Git workflow,
-in particular, the ability to automatically generate commit messages.
+## LlamaBot Git CLI Documentation
 
-## Setup
+Welcome to the LlamaBot Git CLI documentation. This guide provides a comprehensive tutorial on how to use the various commands available in the LlamaBot Git CLI, designed to enhance your Git experience with automated commit messages, release notes, and activity reports.
 
-The `llamabot` prepare message hook requires that you have `llamabot >=0.0.77`.
-You will also need an OpenAI API key
-(unless you have Ollama for local LLMs or other API provider that LiteLLM supports).
-Be sure to setup and configure LlamaBot
-by executing the following two configuration commands
-and following the instructions there.
+### Getting Started
+
+Before you begin, ensure that you have the LlamaBot CLI installed on your system. You will also need to have Git installed and be within a Git repository to use most of the commands.
+
+### Commands Overview
+
+The LlamaBot Git CLI includes several commands, each tailored for specific Git-related tasks:
+
+#### 1. `hooks`
+
+**Purpose:** Installs a commit message hook that automatically generates commit messages using a structured bot.
+
+**Usage:**
 
 ```bash
-llamabot configure api-key
+llamabot git hooks
 ```
 
-and
+This command sets up a Git hook in your repository that triggers the LlamaBot to compose commit messages if none are provided during commits.
+
+#### 2. `compose`
+
+**Purpose:** Automatically generates a commit message based on the current Git diff.
+
+**Usage:**
 
 ```bash
-llamabot configure default-model
+llamabot git compose
 ```
 
-For the default model, we suggest using a GPT-4 variant.
-It is generally of higher quality than GPT-3.5.
-If you are concerned with cost,
-the GPT-3.5-turbo variant with 16K context window
-has anecdotally worked well.
+Use this command to autogenerate a commit message which you can then review and edit as needed. This is particularly useful for ensuring commit messages are consistent and informative.
+
+#### 3. `write_release_notes`
 
-## Install the Commit Message Hook
+**Purpose:** Generates release notes for the latest tags in your repository.
 
-Once you have configured `llamabot`,
-the next thing you need to do is
-install the `prepare-msg-hook` within your `git` repository.
-This is a `git` hook that allows you to run commands
-after the `pre-commit` hooks are run
-but before your editor of the commit message is opened.
-To install the hook, simply run:
+**Usage:**
 
 ```bash
-llamabot git hooks
+llamabot git write_release_notes
+```
+
+This command will create a markdown file in the specified directory containing release notes based on the commits between the last two tags.
+
+#### 4. `report`
+
+**Purpose:** Generates a report based on Git commit logs for a specified time frame.
+
+**Usage:**
+
+```bash
+llamabot git report --hours 24
+llamabot git report --start-date 2023-01-01 --end-date 2023-01-02
 ```
 
-This command will check if the current directory is a Git repository root.
-If it is not, it raises a `RuntimeError`.
-If it is, it writes a script to the `prepare-commit-msg` file
-in the `.git/hooks` directory
-and changes the file's permissions to make it executable.
-
-## Auto-Compose a Commit Message
-
-The `llamabot git compose-commit` command autowrites a commit message based on the diff.
-It first gets the diff using the `get_git_diff` function.
-It then generates a commit message using the `commitbot`, which is a LlamaBot SimpleBot.
-If any error occurs during this process,
-it prints the error message and prompts the user to write their own commit message,
-allowing for a graceful fallback to default behaviour.
-This can be useful, for example, if you don't have an internet connection
-and cannot connect to the OpenAI API,
-but still need to commit code.
-
-This command never needs to be explicitly called.
-Rather, it is called behind-the-scenes within the `prepare-msg-hook`.
-
-## Conclusion
-
-The `llamabot git` CLI provides a set of tools
-to automate and enhance your Git workflow.
-It provides an automatic commit message writer based on your repo's `git diff`.
-By using `llamabot git`, you can streamline your Git workflow and focus on writing code.
+This command can be used to generate a detailed report of activities, highlighting key changes and features implemented within the specified period.
+
+### Conclusion
+
+The LlamaBot Git CLI is a powerful tool for automating and enhancing your Git workflow. By understanding and utilizing these commands, you can significantly improve the efficiency and consistency of your version control practices.

llamabot/bot/ollama_model_names.txt

@@ -1,3 +1,9 @@
+qwen2.5-coder
+solar-pro
+nemotron-mini
+qwen2.5
+bespoke-minicheck
+mistral-small
 reader-lm
 minicpm-v
 deepseek-v2.5

llamabot/cli/git.py

@@ -1,22 +1,27 @@
 """Git subcommand for LlamaBot CLI."""
 
-from pathlib import Path
 import os
+from datetime import datetime, timedelta
+from enum import Enum
+from pathlib import Path
+from typing import Optional
 
 import git
+import pyperclip
+import typer
+from pydantic import BaseModel, Field, model_validator
 from pyprojroot import here
-from typer import Typer, echo
+from rich.console import Console
 
 from llamabot import SimpleBot, prompt
 from llamabot.bot.structuredbot import StructuredBot
 from llamabot.code_manipulation import get_git_diff
 from llamabot.prompt_library.git import (
+    compose_git_activity_report,
     compose_release_notes,
 )
-from pydantic import BaseModel, Field, model_validator
-from enum import Enum
 
-gitapp = Typer()
+gitapp = typer.Typer()
 
 
 class CommitType(str, Enum):
@@ -213,7 +218,7 @@ def hooks(model_name: str = "gpt-4-turbo"):
 """
         f.write(contents)
     os.chmod(".git/hooks/prepare-commit-msg", 0o755)
-    echo("Commit message hook successfully installed! 🎉")
+    typer.echo("Commit message hook successfully installed! 🎉")
 
 
 @gitapp.command()
@@ -227,8 +232,8 @@ def compose(model_name: str = "groq/llama-3.1-70b-versatile"):
         with open(".git/COMMIT_EDITMSG", "w") as f:
             f.write(response.format())
     except Exception as e:
-        echo(f"Error encountered: {e}", err=True)
-        echo("Please write your own commit message.", err=True)
+        typer.echo(f"Error encountered: {e}", err=True)
+        typer.echo("Please write your own commit message.", err=True)
 
 
 @gitapp.command()
@@ -252,14 +257,16 @@ def write_release_notes(release_notes_dir: Path = Path("./docs/releases")):
         tag1, tag2 = tags[-2], tags[-1]
         log_info = repo.git.log(f"{tag1.commit.hexsha}..{tag2.commit.hexsha}")
 
+    console = Console()
     bot = SimpleBot(
         "You are an expert software developer "
         "who knows how to write excellent release notes based on git commit logs.",
         model_name="mistral/mistral-medium",
         api_key=os.environ["MISTRAL_API_KEY"],
-        stream_target="stdout",
+        stream_target="none",
     )
-    notes = bot(compose_release_notes(log_info))
+    with console.status("[bold green]Generating release notes...", spinner="dots"):
+        notes = bot(compose_release_notes(log_info))
 
     # Create release_notes_dir if it doesn't exist:
     release_notes_dir.mkdir(parents=True, exist_ok=True)
@@ -269,3 +276,63 @@ def write_release_notes(release_notes_dir: Path = Path("./docs/releases")):
     # Write release notes to the file
     with open(release_notes_dir / f"{tag2.name}.md", "w+") as f:
         f.write(trimmed_notes)
+
+
+@gitapp.command()
+def report(
+    hours: Optional[int] = typer.Option(None, help="The number of hours to report on."),
+    start_date: Optional[str] = typer.Option(
+        None, help="The start date to report on. Format: YYYY-MM-DD"
+    ),
+    end_date: Optional[str] = typer.Option(
+        None, help="The end date to report on. Format: YYYY-MM-DD"
+    ),
+    model_name: str = "gpt-4-turbo",
+):
+    """
+    Write a report on the work done based on git commit logs.
+
+    If hours is provided, it reports on the last specified hours.
+    If start_date and end_date are provided, it reports on that date range.
+    If neither is provided, it raises an error.
+
+    :param hours: The number of hours to report on.
+    :param start_date: The start date to report on.
+    :param end_date: The end date to report on.
+    :param model_name: The model name to use.
+        Consult LiteLLM's documentation for options.
+    """
+    repo = git.Repo(here())
+
+    if hours is not None:
+        now = datetime.now()
+        time_ago = now - timedelta(hours=hours)
+        now_str = now.strftime("%Y-%m-%dT%H:%M:%S")
+        time_ago_str = time_ago.strftime("%Y-%m-%dT%H:%M:%S")
+    elif start_date and end_date:
+        time_ago_str = start_date
+        now_str = end_date
+    else:
+        raise ValueError(
+            "Either 'hours' or both 'start_date' and 'end_date' must be provided."
+        )
+
+    log_info = repo.git.log(f"--since={time_ago_str}", f"--until={now_str}")
+    bot = SimpleBot(
+        "You are an expert software developer who writes excellent reports based on git commit logs.",
+        model_name=model_name,
+        stream_target="none",
+    )
+
+    console = Console()
+    with console.status("[bold green]Generating report...", spinner="dots"):
+        report = bot(
+            compose_git_activity_report(
+                log_info, str(hours) or f"from {start_date} to {end_date}"
+            )
+        )
+
+    print(report.content)
+    # Copy report content to clipboard
+    pyperclip.copy(report.content)
+    typer.echo("Report copied to clipboard. Paste it wherever you need!")

llamabot/prompt_library/git.py

@@ -78,7 +78,58 @@ def write_commit_message(diff: str):
 
 
 @prompt
-def compose_release_notes(commit_log):
+def compose_git_activity_report(log_info: str, hours: int) -> str:
+    """Given the following git log information for the last {{ hours }} hours,
+    please write a concise report summarizing the work done during this period.
+    Highlight key changes, features, or fixes.
+    Use markdown formatting.
+
+    [[GIT LOG BEGIN]]
+    {{ log_info }}
+    [[GIT LOG END]]
+
+    Please format your report as follows:
+
+    1. Start with a brief summary of the overall work done in the specified time period.
+    2. Use the following sections, omitting any that are not applicable:
+       - New Features
+       - Bug Fixes
+       - Improvements
+       - Documentation
+       - Other Changes
+    3. Under each section, use bullet points to list the relevant changes.
+    4. For each bullet point, include:
+       - A concise description of the change
+       - The commit hash (first 7 characters)
+       - The author's name (if available)
+    5. If there are many similar changes, group them together and provide a summary.
+    6. Highlight any significant or breaking changes.
+    7. End with a brief conclusion or outlook, if appropriate.
+
+    Example format:
+
+    # Work Summary for the Last {{ hours }} Hours
+
+    ## Overview
+    [Brief summary of overall work]
+
+    ## New Features
+    - Implemented user authentication system (abc1234) (Jane Doe)
+    - Added export functionality for reports (def5678) (John Smith)
+
+    ## Bug Fixes
+    - Fixed crash in data processing module (ghi9101) (Alice Johnson)
+
+    ## Improvements
+    - Optimized database queries for faster performance (jkl1121) (Bob Wilson)
+
+    ## Conclusion
+    [Brief conclusion or future outlook]
+    """
+
+
+@prompt
+def compose_release_notes(commit_log: str) -> str:
     """Here is a commit log:
 
     # noqa: DAR101