docs: record in the PRD what the evidence resolved

docs: platform and protocol findings reshape the plan

docs: delivery plan, engine/command dossiers, and the ADRs they ground

docs: PRD, ADR log and feasibility spikes for the multiplayer port

Odyssey: bound the living galaxy to 3 seed-drawn background worlds

Document the main-branch gate, and fix the docs my own changes falsified

Correct finding 3's impact claim — measured, it is narrower than I wrote

Cut 1.1.0, un-deprecate the CI actions, and run the browser smoke test

Close the guard gaps behind the last three bugs; withdraw one review finding

Get CI green, and make the AI's opponent belief fade the way it says it does

Add an external code review: CI is red, and the adaptive AI forgets too fast

The cast's labels do not survive held-out maps -- say so

Record the adaptive-opponent work in the ledger and changelog

Phase 6: play against yourself -- fingerprint a human into a genome

Phase 4: the adaptation POLICY is evolvable, not just its constants

Phase 1: the AI gets a belief about its opponent

Record the check guardrail result in the ledger row

Record what the first evolutionary run measured -- including that it fails

Evolve the AI: a genome, mutation, crossover, and a selection loop

Design brainstorm: how the AI could evolve by mutation and crossover

Phase 5 fix: the ⌂ Home confirm was the third, un-closed door to Save

Phase 5 (replay + season): re-run any recorded match, and close a ladder

Phase 5 (spectate): watch an AI-vs-AI match live, at 1x-8x

Phase 4 follow-up: the Standings screen names the human, and states D4's seat note

Phase 4 (part 2): the playable Gauntlet — play a real match, rate it, resume it

Phase 3 (part 2): the in-game Tournament tab — round-robin, Swiss and knockout

Phase 2 (part 2): roster + persistent ladder wired into Quick Duel, archetype threaded end-to-end

Phase 1: the in-game Quick Duel screen (competition.js, competitionWorker.js)

Phase 0: split tools/selfplay.js into a browser-safe core + tools/selfplay-cli.js

Design: in-game competitions with an Elo ranking

Bench: detectors must prove the state never resolved

Record the guardrail result, including the row that got worse

AI: give the Odyssey economy something to bootstrap from

Tier 3: record the outcomes in the plan document

Tier 2f: name the rebuild signature, and record Tier 2 as delivered

Record Tier 1 as delivered in the improvement plan

Tier 1, step 5: close the coverage gaps and the doc drift (C6-C16, E1, E2)

Add a tiered, TDD-first code-improvement plan from a full-codebase review

Fix two real bugs in Tier 5 Swiss tournament found by belated review

Add a fair head-to-head tournament system on top of self-play

Add ailab leaderboard: Tier 0 of the AI championship roadmap

Add an Odyssey total-domination strategy guide (Hard/Gigantic/Abundant/Pop-200)

docs: record the surplus army-cap fix and its measured results

Update README and the player field manual for everything shipped since 1.0.0

Fix a real regression the batch's own agents mistook for sibling noise

Add a dependency-ordered implementation roadmap for the improvement catalog

Add the tiered, all-dimensions improvement-proposals catalog

Record the forgiveness-dial measurement, denominator effect and all

Make the grievance / aggression cooldown part of the AI's personality

Record the measured before/after in the review, including what didn't work