Skip to main content

Azure DevOps daily task automation with AI task breakdown

Project description

Azure DevOps Daily Task Automation

Python 3.9+ MIT License PyPI

Python CLI for automating daily task creation, activation, and completion logging in Azure DevOps with AI-powered task breakdown via Claude.

  • AI Task Breakdown — Claude reads user stories and generates concrete development tasks
  • Interactive Workflowcreatestartupdateend pipeline
  • Auto-linking — Tasks linked to parent stories, related across multiple stories
  • Progress Tracking — Log hours, remaining estimates, completion notes
  • Global CLI — Install once, use anywhere: azdo-daily configure

Installation

From PyPI (recommended)

pip install azdo-daily
azdo-daily configure

From source

Clone repository:

git clone https://github.com/MrShakila/Azdo-Daily.git
cd Azdo-Daily
pip install .

Or install in development mode:

pip install -e ".[dev]"

Requirements

  • Python 3.9+
  • requests library (auto-installed)
  • Anthropic API key (for AI task breakdown)
  • Azure DevOps Personal Access Token (PAT)

Use from anywhere:

azdo-daily configure
azdo-daily status

Configuration

On first run, configure your settings:

azdo-daily configure

Configuration stored in .config/settings.json (project-local, excluded from git).

Interactive prompts for:

Field Description
org Your Azure DevOps organisation name
project Project name
pat Personal Access Token — needs Work Items (Read & Write) scope
anthropic_api_key From console.anthropic.com — for AI task breakdown
assigned_to Your email/display name — used to filter stories
area_path Default area path for new tasks (optional)

Project Structure

azdo_daily/
├── main.py       — Entry point: argument parsing + command dispatch
├── config.py     — Configuration: load/save/validate settings
├── state.py      — Daily state: load/save work items per day
├── ui.py         — Terminal UI: colors, prompts, formatters, selection helpers
├── azdo.py       — Azure DevOps API client: work item operations
├── ai.py         — Claude AI: task breakdown from stories
└── commands.py   — Command handlers: configure, create, start, update, end, status

Key Modules

azdo.py — Azure DevOps API client

  • session() — authenticated HTTP session
  • wit_base() — Work Item Tracking API base URL
  • get_my_stories() — fetch assigned stories via WIQL
  • create_task() — create new task linked to stories
  • set_workitem_state() — change work item state
  • resolve_task() — mark task complete with hours + comment
  • partial_task() — log progress, keep task open
  • _patch_workitem() — internal: apply JSON Patch operations
  • add_comment() — internal: append work item comment

commands.py — CLI command handlers

  • cmd_configure() — interactive setup
  • cmd_create() — select stories → generate tasks → create in Azure DevOps
  • cmd_start() — activate tasks (mark In Progress)
  • cmd_update() — log progress on tasks
  • cmd_end() — mark tasks done + auto-resolve stories
  • cmd_status() — show today's stories and tasks

ui.py — Terminal UI helpers

  • Color constants: R, B, DIM, GR, YL, BL, CY, RD, MG
  • Output: ok(), err(), info(), warn(), hdr(), sep()
  • Input: ask() (prompt with optional default)
  • Formatters: print_stories(), print_tasks()
  • Selection: parse_selection(), select_from_list() (handles "all")
  • Conversion: float_or_none()

Daily Workflow

Setup (once)

azdo-daily configure

Morning — Create tasks

azdo-daily create
  1. Fetches all active User Stories assigned to you
  2. You select stories to work on (e.g. 1 or 1,3 or 2-4)
  3. Choose task creation method:
    • Use template — Auto-generate standard tasks (UI, Logic, Unit Test)
    • AI auto-breakdown — Claude reads story and generates tasks
    • Manual entry — Type tasks yourself
    • Template + AI — Generate template tasks + AI suggestions, then review
  4. If multiple stories: tasks created once, linked to all (child of #1, related to rest)
  5. Task names include story title (e.g., "UI | My Story Title")
  6. Tasks appear in Azure DevOps immediately with direct links

Activate tasks

azdo-daily start

Marks selected new tasks as "In Progress" and auto-activates linked stories.

Anytime — Check status

azdo-daily status

Shows active stories and all tasks with open/resolved counts.

Throughout day — Log progress (optional)

azdo-daily update

Log hours spent and remaining estimates on open tasks (keeps them "In Progress").

Evening — Mark complete

azdo-daily end
  1. Lists all open tasks for today
  2. You select which to complete (e.g. 1,3 or all)
  3. For each: enter hours spent + optional closing note
  4. Task marked done + hours logged
  5. If all tasks for a story are done → story auto-resolved

Maintenance Commands

Reconfigure credentials

azdo-daily reconfigure

Update your Azure DevOps org, project, PAT, or Anthropic API key. Prompts to confirm before overwriting.

Clear task history

azdo-daily clear-history

Delete all daily state files (state/*.json). Keeps configuration. Useful for starting fresh after month/week.


State Files

Each day's data in state/YYYY-MM-DD.json:

{
  "stories": [
    {"id": 42, "title": "Implement auth"}
  ],
  "tasks": [
    {
      "id": 101,
      "title": "Add login endpoint",
      "url": "https://...",
      "active": true,
      "closed": false,
      "completed_hours": 2.5,
      "remaining_hours": 1.0,
      "story_ids": [42]
    }
  ]
}

Cron (optional)

Status reminder at 9 AM weekdays:

0 9 * * 1-5 azdo-daily status

start, update, and end commands are interactive — use cron for status only.


Troubleshooting

"Work item X does not exist"

Task IDs in state file no longer exist in Azure DevOps. Reset today's state:

rm ~/.config/azdo_daily/state/2026-04-29.json  # or today's date
azdo-daily create

"anthropic_api_key not set"

Run configure and enter Anthropic API key from console.anthropic.com:

azdo-daily configure

"Personal Access Token (PAT) invalid"

Regenerate PAT in Azure DevOps → User Settings → Personal Access Tokens. Must have Work Items (Read & Write) scope.

ModuleNotFoundError after install

Reinstall in development mode:

pip install -e .

Development

Install with dev tools:

pip install -e ".[dev]"

Install pre-commit hooks:

pip install pre-commit
pre-commit install

Format code (auto-runs on commit via pre-commit):

black azdo_daily/

Lint code:

flake8 azdo_daily/

See CONTRIBUTING.md for full development guide.


License

MIT — see LICENSE

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

azdo_daily-1.3.2.tar.gz (18.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

azdo_daily-1.3.2-py3-none-any.whl (17.6 kB view details)

Uploaded Python 3

File details

Details for the file azdo_daily-1.3.2.tar.gz.

File metadata

  • Download URL: azdo_daily-1.3.2.tar.gz
  • Upload date:
  • Size: 18.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for azdo_daily-1.3.2.tar.gz
Algorithm Hash digest
SHA256 2943aa476ed6d4d1e2909b80eb9725c3e240981df20b2ce8840c3b6145a3803a
MD5 cdab6ca5d016a864cb50b5e9a614bf64
BLAKE2b-256 451245d60e1d3b3c666f98749afa7bbcee3cec67b7796e1aa08a4f7c23d5b195

See more details on using hashes here.

File details

Details for the file azdo_daily-1.3.2-py3-none-any.whl.

File metadata

  • Download URL: azdo_daily-1.3.2-py3-none-any.whl
  • Upload date:
  • Size: 17.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for azdo_daily-1.3.2-py3-none-any.whl
Algorithm Hash digest
SHA256 b6ae9023fa92a6326f039785e5096831e7b1ca34837cd153ecb6117e13eb86c9
MD5 c19323aefc4693d0dd6a88680bf31465
BLAKE2b-256 e4f707b63377dd2edf691ac76ccc488b91c479a559c76c656bf1e644b14af76f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page