Skip to content

v0.8.0

Choose a tag to compare

View all tags
@AsemDevs AsemDevs released this 31 Mar 19:19
· 432 commits to main since this release
v0.8.0
f1ff41c
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

v0.8.0 — Intelligence (Estimation + Search)

This release adds two new commands that make OpenPlanr smarter: AI-powered effort estimation and full-text artifact search.

🎯 planr estimate — AI-Powered Effort Estimation

Estimate any artifact using AI. Get story points, hours, complexity, risk factors, and reasoning — all grounded in a consistent Fibonacci rubric.

planr estimate TASK-001                  # Estimate a single artifact
planr estimate TASK-001 --save         # Estimate and persist to artifact
planr estimate --epic EPIC-001         # Estimate all tasks under an epic
planr estimate --epic EPIC-001 --save  # Estimate and save all
planr estimate --calibrate             # Accuracy report from past estimates

After every estimate, an interactive prompt lets you save, re-estimate, or discard — no need to remember flags.

Story point scale (Fibonacci):

Points Effort
1–2 Trivial to small — minutes to a few hours
3–5 Moderate to medium — half a day to 2 days
8–13 Large to very large — up to 2 weeks
21 Epic-scale — consider splitting

When saved, the estimate is written to the artifact as both structured frontmatter fields (estimatedPoints, estimatedHours, complexity) and a full ## Estimate section in the markdown body (risk factors, reasoning, assumptions).

🔍 planr search — Full-Text Artifact Search

Search across all planning artifacts instantly. Results are grouped by type with highlighted snippets.

planr search "authentication"     # Search across all artifact types
planr search "login" --type story # Filter by type
planr search "JWT" --status done  # Filter by status

Supports: epic, feature, story, task, quick task, adr.

📋 Estimation Guide

Running planr init now generates docs/agile/ESTIMATION.md — a team-readable rubric defining the Fibonacci scale, complexity levels, risk categories, and calibration guidance. The AI uses this same rubric to ensure scores are consistent across all estimates.

Bug fixes

  • Frontmatter formatting preserved on save — Estimate fields are injected directly into the raw YAML without re-serializing through gray-matter, so original quoting styles and structure are not affected.
  • Legacy estimatedEffort field removed on save — The free-text field occasionally added by AI during task generation is cleaned up automatically when saving a structured estimate.

Full changelog: v0.7.0...v0.8.0

Assets 2
Loading