How Concord works

Offers, answers, fresh consent

The core never touches a colonist. It creates a proposal bound to one pawn, and only that pawn's decision handle can answer it: accept, refuse, counter or not now. Anything else, like a forged actor or an extra field, is rejected before it reaches the game.

A counter executes nothing. If the core adopts it, it comes back as a revised offer that needs a fresh yes, with at most two revisions per thread. Hauling agreements can cover up to three trips and stop on low needs, failure, expiry or withdrawal. Replacing running work needs its own consent, and the old job has to be confirmed stopped first.

src/coordinator.ts · src/protocol.ts · mod/Hauling.cs · mod/Rescue.cs · mod/Production.cs

Who knows what

Each mind gets a scoped perspective; the core uses an explicit allowlist rather than receiving pawn or character state wholesale. A colonist sees its own traits, skills, exact needs, surviving memories, its own history and a private outlook of up to four revisable notes, each tied to its own experiences.

The core receives explicitly shared information: addressed messages, agreement receipts, grounded opportunities, attributed local food/campfire sightings, and shared-link Food/Rest telemetry (urgent, low, satisfied, unknown) with a timestamp. Telemetry is not a visual observation. Stale readings become unknown, never zero.

Small views, real menus, no tools

A decision is one bounded call. The model gets its perspective, where every need says what its scale means, plus a menu of executable choices with their effects spelled out. Contextual schemas constrain choices and supplied IDs where supported; runtime validation still checks every reply. Counterproposal actions have additional execution-time checks. Shared instructions are supplemented by relevant action and knowledge contracts.

The Claude route runs with no tools, no MCP servers, no plugins, and checks that at start-up before every call. Every trial has a durable attempt ledger and no rerolls. Failures keep their reserved attempt and a bounded diagnostic stage. Backends are swappable: scripted, Claude, Luna (offline contract checks so far) and Jev for fast appraisal.

src/model-perspective.ts · src/reflection-choice.ts · src/claude-decision.ts · src/decision-trials.ts

Three speeds of thought

In continuous mode, native habits such as eating, sleeping and ordinary jobs can continue while a colonist deliberates, with a thinking badge over their head. Explicit inference pauses stop simulation. Fast appraisal decides whether an event deserves a thought. Deliberation handles negotiation, reconsideration and planning.

Native events are archived and routed only to the pawn who experienced them. Repeated signals coalesce, health events bypass cooldowns, and mundane chatter waits instead of cancelling a thought in progress. Reflection pacing spreads a fixed allowance over the observation window. Play is continuous by default; pausing at decisions is an explicit test mode.

src/routing.ts · src/attention.ts · src/reflection-pacing.ts · mod/Awareness.cs · mod/DecisionPause.cs

A planner that waits to be needed

Each core turn picks one of four moves: propose a listed opportunity, adopt a counter for fresh consent, ask one pawn one question, or wait. It keeps up to eight sourced topics marked open, blocked, deferred, resolved or declined. "Resolved" requires completed linked work, so its prose can't close a topic that the receipts don't close.

It wakes on public changes: finished or stopped work, requests, messages, answers, band changes. Idle time and private needs don't wake it. Every turn spends from a fixed budget with a cooldown. Refused work isn't pushed again; a colonist who said "not now" can invite exactly one fresh offer.

src/core-planner.ts · src/core-scheduler.ts · mod/LinkTelemetry.cs

Saves, reloads and slow thoughts

Model calls take seconds; players save, load and rewind. Every loaded game gets a fresh epoch, so an answer from before a reload can't act in the new timeline. Each accepted action gets an ID before dispatch, and the game's saved ledger makes a duplicate a no-op.

Paired checkpoints save the paused game, hash it and store the matching character state together. Restoring checks the hash and forks the timeline. Gameplay reports distinguish paired restore from a cold restore: a full process restart, with retained results and no extra model calls. Some experiments left restore gaps; offline checks do not demonstrate native persistence.

src/store.ts · src/lab-bridge.ts · mod/Concord.cs

Every claim has a receipt

• Scripted game tests for every mechanic, including refusal, withdrawal and restore.
• Frozen live trials with a fixed call budget decided up front, no rerolls, failures kept.
• Offline snapshot banks: the same situation, varied one thing at a time, across models.
• Offline typed-claims prototype that distinguishes submitted facts, forecasts and preferences; it is not a production truth checker.
• Independent code review on every nontrivial PR and fact-checked diary entries for selected milestones.

Well-formed output and grounded understanding are measured separately. Passing the schema doesn't count as understanding.

docs/ACCEPTANCE.md · docs/evidence/ · trials/