Plannotator 0.19.8 tightens plan annotations, fixes review bugs

// 47d agoOPENSOURCE RELEASE

Plannotator 0.19.8 tightens plan annotations, fixes review bugs

ANNOUNCEMENT PRODUCT GITHUB PRODUCT HUNT X

Plannotator 0.19.8 is a maintenance release for the AI plan-annotation and code-review workflow tool. It improves detection of code file references inside plans, restores URL display for remote users, fixes overlapping sessions in `/plannotator-last` after clearing or resuming sessions, and repairs a code review link issue. The release keeps pushing on the core promise: making agent plans and diffs easier to inspect, annotate, and steer.

// ANALYSIS

Hot take: this is a small release, but it targets the parts of the workflow that create the most friction when you’re using an agent continuously.

–The smarter code-file reference detection should reduce false misses in longer plan reviews.
–Restoring URL visibility for remote users is practical, not flashy, but important for distributed review sessions.
–The `/plannotator-last` session overlap fix suggests the project is still hardening state management around long-running goal loops.
–The code review URL fix is the kind of plumbing issue that can quietly break trust if left around.
–This reads like a focused stability update rather than a feature splash, which is what you want for tooling embedded in an agent workflow.

// TAGS

plannotatorai-codingagentcode-reviewdevtoolopen-sourceplan-annotationrelease-notesclaude-code

DISCOVERED

47d ago

2026-05-05

PUBLISHED

47d ago

2026-05-05

RELEVANCE

8/ 10

AUTHOR

plannotator

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

VIDEO36m ago

Claude Code, Bun creators demo autonomous loops

This 20-minute talk by Boris Cherny (Head of Claude Code at Anthropic) and Jarred Sumner (creator of Bun) details their transition from manual coding to fully autonomous developer workflows. They showcase "RoboBun," an agentic setup using Claude Code to reproduce issues, generate regression tests, and manage pull requests, illustrating how developers are shifting from simple chatbot prompts to multi-agent parallel loops for code maintenance.

MODEL1h ago

Gemma 4 12B Fable 5 Composer 2.5 drops

Gemma 4 12B Agentic Fable 5 Composer 2.5 is a community-developed fine-tune of Google's Gemma 4 12B instruct model, optimized for local coding, tool use, and multi-step agentic workflows. Leveraging distilled reasoning traces, the model claims a 3.5x improvement over the base model on local telecom benchmarks, bringing high-fidelity reasoning capabilities to local developer setups.

NEWS2h ago

Givros asks if GPT-5.6 hits OpenAI Codex

AI creator Givros publicly asked OpenAI's Head of Codex Thibault Sottiaux whether the rumored GPT-5.6 model will be integrated into the Codex coding agent platform immediately upon its release. The question underscores the intense community interest in how quickly OpenAI will roll out new model capabilities to its developer tools amidst rumors of GPT-5.6's testing and impending launch.