Skip to content

AgentHUD

v0.12.2 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent ai-agent anthropic claude claude-code claude-code-cli
+12 more
claude-code-tui cli coding-agent web developer-tools digest live-monitor llm monitor observability session-monitor tui

Summary

AI summary

Fixed --open failure handling on WSL and added a Smoke (Windows) CI workflow.

Changes in this release

Feature Low

Added `Smoke (Windows)` manual‑trigger CI workflow.

Added `Smoke (Windows)` manual‑trigger CI workflow.

Source: llm_adapter@2026-06-10

Confidence: high

Feature Low

Added "Platform notes" paragraph to README clarifying OS targets.

Added "Platform notes" paragraph to README clarifying OS targets.

Source: llm_adapter@2026-06-10

Confidence: high

Bugfix Medium

`--open` no longer fails silently on WSL.

`--open` no longer fails silently on WSL.

Source: llm_adapter@2026-06-10

Confidence: high

Bugfix Medium

`summary` skips LLM tokens when a day has zero activity.

`summary` skips LLM tokens when a day has zero activity.

Source: llm_adapter@2026-06-10

Confidence: high

Bugfix Low

Normalized `prompt = ...` stderr line to use forward slashes on Windows.

Normalized `prompt = ...` stderr line to use forward slashes on Windows.

Source: llm_adapter@2026-06-10

Confidence: high

Full changelog

Fixed

  • --open no longer fails silently on WSL. Spawning the OS
    opener with stdio: "ignore" + immediate process.exit() meant
    the user never saw the spawn error when xdg-open was missing
    (typical on a headless WSL) or exited non-zero. openInDefaultApp
    now (1) sync-checks the command is on PATH, (2) prefers wslview
    when WSL is detected and the binary is installed, (3) waits up to
    200ms for the spawned child to fail fast and surfaces both error
    events and non-zero exit codes on stderr.
  • summary on a day with zero activity no longer spends LLM
    tokens.
    report --date today already returns "No activity
    found"; summary was happily piping that empty payload to claude
    for a useless answer (and -o opened an empty page). The daily
    path now matches the range path's "no activity → skip" behavior:
    writes a stub to the cache, prints a clear stderr line, returns
    success without spawning claude.

Added

  • Smoke (Windows) workflow. Manual-trigger CI job that
    exercises the real CLI on a Windows runner (agenthud --version / --help / --once / --cwd / report / summary against a faked
    session and a pre-seeded cache file). The unit-test matrix already
    covered Windows, but it can't catch path-separator regressions in
    stderr labels, cmd /c start quoting, or the filesystem side of
    regenerateIndex — this one can. Trigger from the Actions tab.
  • README "Platform notes" paragraph clarifying that macOS and
    Linux are the daily-driver targets, Windows is best on WSL2
    (Anthropic's recommendation for Claude Code itself), and native
    PowerShell may need an ExecutionPolicy adjustment for any
    npm-installed CLI.

Fixed

  • Windows: prompt = ... stderr line used backslash separators.
    formatPromptSource now normalises its output to forward slashes
    so the user-facing label reads as ~/.agenthud/summary-prompt.md
    on every platform. (Pure cosmetic on POSIX; lets the Windows
    CI tests pass.)

v0.12.0 was tagged but never reached npm — the Windows test job in
CI caught this issue before the publish step ran. v0.12.1 is the
first 0.12 release on npm.

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track AgentHUD

Get notified when new releases ship.

Sign up free

About AgentHUD

All releases →

Related context

Earlier breaking changes

  • v0.14.0 `h` key now aliases vim-left (←) instead of hide.

Beta — feedback welcome: [email protected]