LazyTasks 2.4.1

LazyTasks 2.4.1

Headless sessions are back on their feet. 2.4.0 could pick up a stale claude install and fail every headless dispatch with a bare "exit 1" — 2.4.1 fixes that, tells you what actually went wrong when a tool does fail, and freshens the model picker's suggestions.

Headless sessions no longer pick up a stale claude install (#85)

Headless dispatches could silently run the wrong claude: if an old copy sat on the non-interactive shell PATH (e.g. a year-old homebrew install), it shadowed the current one your version manager (nvm/fnm/asdf) puts on the interactive PATH — and every dispatch died with "exit 1". Tool resolution now probes the interactive shell first — the same environment your terminal sessions run in — so the CLI your terminal uses is the one headless runs use too.

Failure notes now show the real error (#85)

When a tool fails printing its error to stdout (as claude -p does), the session note used to read as a bare exit code. It now includes the tool's actual error text, so you can see what went wrong without digging.

Current Claude aliases in the model picker (#86)

The model picker menus (project default and per-dispatch) now suggest all current claude CLI aliases — fable, opus, sonnet, haiku, opusplan, opus[1m], sonnet[1m] — instead of just opus/sonnet/haiku. The field is still free text, so any model name the CLI accepts continues to work.