From 9066f58ca7868db9270124cff83eead92bd2f9b6 Mon Sep 17 00:00:00 2001 From: Mario Zechner Date: Wed, 12 Nov 2025 23:16:14 +0100 Subject: [PATCH] docs: add To-Dos section explaining no built-in support - Clear stance: no built-in to-dos - Rationale: they confuse models more than help - Alternative: stateful TODO.md file with checkboxes - Simple example provided - Agent can read/update file as needed --- packages/coding-agent/README.md | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/packages/coding-agent/README.md b/packages/coding-agent/README.md index bd141bb5..8d535e4b 100644 --- a/packages/coding-agent/README.md +++ b/packages/coding-agent/README.md @@ -411,6 +411,23 @@ Context transfer between agents is generally poor. Information gets lost, compre If you need parallel work on independent tasks, manually run multiple `pi` sessions in different terminal tabs. You're the orchestrator. +## To-Dos + +**pi does not and will not support built-in to-dos.** In my experience, to-do lists generally confuse models more than they help. + +If you need task tracking, make it stateful by writing to a file: + +```markdown +# TODO.md + +- [x] Implement user authentication +- [x] Add database migrations +- [ ] Write API documentation +- [ ] Add rate limiting +``` + +The agent can read and update this file as needed. Using checkboxes keeps track of what's done and what remains. Simple, visible, and under your control. + ## Planned Features Things that might happen eventually: