docs(plan): defer in-game chat, add Phase 1 (Casual) implementation plan

Browse Source

- DECISIONS.md: in-game chat (player↔player and human↔Gemma) deferred
  indefinitely. Blind-mode chat is a side channel that defeats the
  moderator-vocabulary security boundary; chat with Gemma leaks belief
  state mid-game. Resolvable but expensive — revisit only on demand.
- Spec: same deferral noted in "Out of scope".
- New plan: docs/superpowers/plans/2026-04-28-ai-player-phase-1-casual.md
  — 13 tasks, 80 sub-steps. Phase 1 only (Casual bot end-to-end). Phase 2
  (Recon) gets its own plan once Phase 1 outcomes inform Recon's target.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

claude (blind_chess)

2026-04-28 13:31:12 -04:00

parent 729199097e

commit 6d457a2321

3 changed files with 2563 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

docs/superpowers/plans/2026-04-28-ai-player-phase-1-casual.md

+2561

File diff suppressed because it is too large Load Diff