- llm.ts: LlmClient.chatWithTools — bounded OpenAI function-calling loop
(default 6 tool rounds, then one forced no-tools request); shares the
retry/backoff/reasoning-effort machinery with chat(); tools are only
added to the request body when non-empty, so plain chat() bodies and
their tests are unchanged; a tool-call response is a success (never a
truncation); malformed tool arguments become an error tool-message.
- engine.ts: GET_NEIGHBOURS_TOOL + makeNeighboursExecutor (degrades
unknown tools/args/keys without throwing); playerFrontier (sorted,
deduped, other-nation-owned only); buildSystemPrompt gains a tool
variant (contiguity rules, frontier hint) used only when the tool is
actually sent; buildUserPrompt emits a frontier field whenever a
resolver is given; runTurn takes getNeighbours and uses
chatWithTools when both the resolver and the client's capability are
present, falling back to plain chat() otherwise.
- applyTurnResult: snapshot-first sole-ownership algorithm — a region
key transfers only with exactly one claimant and exactly one previous
owner (different from the gainer); double claims and pre-existing
double ownership are left untouched; lone losses are no-ops; every
key has 0 or 2+ -> 1 owner post-turn, never orphaned or duplicated.
- stub.ts: deterministic one-region contiguous conquest per turn from
the prompt's frontier field (bypasses the tool loop; empty frontier
-> no transfer, all existing assertions stay stable).
- regions.ts: optional region-adjacency.json load; hasAdjacency() and
neighboursOf(keys) (union, deduped, queried excluded, sorted).
- index.ts: jump route passes the adjacency resolver when loaded.
- tests: chatWithTools protocol (echo, executor args, bounded rounds,
malformed args, retry), tool-path runTurn wiring + fallback,
playerFrontier, executor, applyTurnResult invariants, neighboursOf/
hasAdjacency (105 unit tests, 14 e2e — all green).
The single source of truth now keys ownership by region key (one per owned
sub-region) instead of a parent-country ISO_A3:
- shared/types.ts, shared/protocol.ts: TerritoryChange / RegionMap / regionOwner
doc flips; mapFeatureOwner now reads the feature's stamped properties.regionKey
(never the repacked numeric feature.id, nor the sub-region id — the #6 guard).
- server/regions.ts (new, turf-free): loads region-keys.json + regions.geo.json
once at boot; expands a nation's ISO_A3 list to its sub-regions' keys, builds
the LLM 'regions' reference table (key -> "name (parent)"), and exposes the
set of valid keys. Degrades gracefully when the files are missing.
- server/engine.ts: buildSystemPrompt instructs the model to use region keys;
buildUserPrompt gains an optional regionReference table; applyTurnResult gains
an optional validKeys set so hallucinated keys are ignored.
- server/index.ts: loads region data at boot; expands each nation's country list
to region keys at game creation; the jump route passes the reference + valid
keys through runTurn.
The stub is unchanged (it emits an empty, region-key-conformant territoryChanges).
Map (WorldMap):
- Keep the near-black OpenFreeMap `dark` basemap (verified HTTP 200; the
suggested dark-matter / dark-outdoors / liberty-dark variants 404 on that
host) so the choropleth nation colors pop
- Stable per-nation fills at 0.8 opacity, thin subtle borders, and a brighter
thicker amber border for the player nation so "this is me" is always obvious
- Hover brightens a region and shows a color-chipped owner + key stats popup;
click opens a full dossier popup and focuses the left panel on that nation
- Transient, self-cleaning flash (pulsing amber outline) over regions whose
ownership changed this turn
- Bottom-left legend auto-generated from the region map; per-scenario initial
camera (Europe for the WWII scenarios, wider for Cold War / Modern / Aegis)
Command-center UI:
- New header bar: scenario title, prominent turn + date, the player nation
(name + color chip), and a live Idle / "Simulating…" status indicator
- 3-column operations-console grid: nation dossier (left) / dominant map
(center) / command deck + event feed (right); stacks map-first on mobile
- EventFeed: one card per event with a category icon, a colored outcome badge
(success/failure/partial/neutral), a nation-colored accent edge, and the
turn + date; new events slide in and flash at the top
- NationPanel: value-colored animated stat bars (red → green), territory as
color-coded region chips, and diplomacy as a list with a colored indicator
per relation (ally/rival/war/neutral)
- ActionPanel: a "Your move" composer with one prominent Send button and a
spinner + "turns can take a few seconds" hint while a turn resolves
- sonner error toasts: a 502 / model-down surfaces as "AI temporarily
unavailable — try again"
Live LLM rewire (server, previously uncommitted):
- Default endpoint https://ai.kkhost.pl/v1 (vLLM, no API key); reasoning model
qwen3.8-27b; always send a generous max_tokens (4000) so it finishes its
chain-of-thought before emitting content; read only `content`, ignore
`reasoning`. docker-compose + AGENTS.md updated to match.
Tests: the deterministic Playwright e2e gains assertions for the dossier stat
bars, the map legend (all nations), and the event-card type icon + outcome
badge; it stays fully deterministic under LLM_STUB=1.
kamilkrzywda
