Which game structures become possible only when Agents persist and act through one World history?
Historical Agent-first research that separated strategy existence, policy accessibility, model realization, and simpler classical substitutes before the Game programme moved to GameForm-first direction search.
01 / Current position
A hypothesis is not the current judgment.
The dossier preserves the live research position. Dated articles preserve the complete evidence and argument that changed it.
Persistent roles, actor-local knowledge, typed communication, player doctrine, and recoverable commitments can create distinct mechanics, but their product value must be tested separately from their technical existence.
Reframed after GX1 and the later Game direction work. GX1 showed materially different reachable futures and separated strategy existence from model realization; the model still failed the frozen Core-carrier continuation while a deterministic continuous-carrier policy could succeed, and a generic structured primaryObjective prototype was deleted after presentation-order sensitivity. Those results remain valid research pressure, but the programme no longer assumes that proving an Agent-native mechanic selects the next game.
02 / Decision boundary
What keeps this Question alive?
Without a falsifiable distinction, Agent-native game design becomes a marketing label; but even a genuine distinction is insufficient if it does not create Player Value.
Use GX1 as a historical constraint on future Agent roles. Continue through the new GameForm/Player-Value question and reopen this narrower mechanism question only when a candidate game form survives player pressure and Agent participation becomes the decision-changing variable.
The same player experience and mechanics can be reproduced by a simpler deterministic or non-Agent system, or Agent-native differences remain technically observable but irrelevant to player-facing value.
03 / Supporting publications
Complete arguments connected to this Question.
5 dated publications currently document this research line.
The Agent Knew the Goal. It Still Wouldn't Do It.
Why Station Zero GX1 separated reachable strategy, policy accessibility, and model realization; how a model can articulate an objective yet fail to preserve the multi-turn commitment needed to realize it.
12 August 2026 ↗Research noteCommunication Is Gameplay State
Why agent communication needs identity, reachability, delivery state, and World-conditioned timing rather than decorative chat logs or a shared transcript.
31 July 2026 ↗Engineering reportReplay Without a Second Truth Store
How replay and evidence-linked diagnosis can remain pure deterministic projections of World, Host, Team, authority, Message, Provider, Effect, Observation, and verification records.
31 July 2026 ↗Release noteStation Zero v0.1.0-alpha.1 — The First Source-Playable Release
What shipped in Station Zero v0.1.0-alpha.1, how the release journey is verified, what one coordination-only comparison proves, and which agent-native game claims remain open.
31 July 2026 ↗Engineering reportA Thin Host Can Improve Strategy Without Becoming a Planner
How Station Zero M2.1 improved Codex and Codex-to-Hermes strategy by compiling trustworthy decision semantics without forcing rank one, adding unrestricted memory, or introducing a hidden planner.
31 July 2026 ↗04 / Source discipline
The dossier is an index, not the evidence authority.
Owns the current judgment, next test, and deletion condition.
Own complete dated arguments, limitations, comparisons, and source links.
Own exact code, tests, releases, receipts, and machine evidence.