You asked
How do I set up the game?
Answered counted as answeredAsked with: Diplomacybg-483-en-1e
To set up the game, follow these steps: 1. Randomly decide which Great Power each player will represent [1]. 2. Place the appropriate unit on the designated supply center as follows [2]: * England: Fleet in London, Fleet in Edinburgh, and Army in Liverpool [2]. * France: Army in Paris, Army in Marseilles, and Fleet in Brest [2]. * Germany: Army in Berlin, Army in Munich, and Fleet in Kiel [2]. * Italy: Army in Rome, Army in Venice, and Fleet in Naples [2]. * Russia: Army in Moscow, Fleet in Sevastopol, and Army in Warsaw [2]. * Turkey: Fleet in St. Petersburg, Fleet in Ankara, Army in Constantinople, and Army in Smyrna [2].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 265 ms · ask 9378 ms · total 917114 ms
- single-flight (PR-5)
- queued 907461 ms · generation 9653 ms
- retrieval refs (raw)
- [{"page": 5, "score": 0.04918, "snippet": "Each Army unit is represented by a square playing piece. Each Fleet unit is represented by a narrow rectangular playing piece. One side of each piece has a design that represents the appropriate unit, and the other side has the color of the Great Power. Use whichever side is more helpful. The unit c", "headingPath": "UniTs (aRMies anD fleeTs) · sTaRTing POsiTiOns", "sharpsignalDocId": 158}, {"page": 19, "score": 0.047883, "snippet": "Only an Army unit can be built on an inland province supply center. When building a unit on a coastal province supply center, a Fleet or Army must be specified in the written build order. If Russia builds a Fleet in St. Petersburg, the Russian player must also specify 'North Coast' or 'South Coast.'", "headingPath": "aDDiTiOnal bUilDing RUles · WRiTing bUilDs anD DisbanDMenTs · TiMe ManageMenT", "sharpsignalDocId": 158}, {"page": 19, "score": 0.047875, "snippet": "This sample game will help demonstrate some of the typical opening moves in a game of Diplomacy . This is intended to be a look at order writing and resolution. No strategies, diplomacy , alliances, or negotiations are discussed here. Besides, it would take too much space to record all of the discus", "headingPath": "OPening MOVes in a saMPle gaMe", "sharpsignalDocId": 158}, {"page": 6, "score": 0.046642, "snippet": "During this phase, players meet to discuss their plans for upcoming turns. Alliances are made and strategies are set. These 'diplomatic negotiations' take place before each turn. Negotiations last 30 minutes before the first turn and 15 minutes before each turn thereafter. Negotiations may end soone", "headingPath": "1. diplomatiC phase · 2. order writing phase · ORDeR DaTes", "sharpsignalDocId": 158}, {"page": 18, "score": 0.03125, "snippet": "After each Fall turn, players check to see how many supply centers they control. A country controls a supply center when one of its units occupies that supply-center province after a Fall turn has been played and completed. Once a country gains control of a supply center, it can leave the center vac", "headingPath": "cOnTROlling sUPPly cenTeRs · aDJUsTing nUMbeR Of UniTs · DisbanDing · bUilDing", "sharpsignalDocId": 158}, {"page": 18, "score": 0.030303, "snippet": "After all the orders have been revealed and read, the players (or an assigned gamemaster) must resolve all of the conflicts. Resolution will result in successful moves, failed moves, standoffs, retreats, and disbandments. The units on the game board are moved and removed as described in the next two", "headingPath": "3. the order resolution phase · 4. retreat and disbanding phase · WRiTing ReTReaTs · DisbanDMenT", "sharpsignalDocId": 158}, {"page": 19, "score": 0.029851, "snippet": "If you leave the game or otherwise fail to submit orders on a given Spring or Fall turn, it's assumed that your government has collapsed. Your units all hold in position, but don't support each other. If they're dislodged, they're disbanded. No new units are raised for the country . If a country in ", "headingPath": "ciVil DisORDeR · alTeRnaTe Way TO Play", "sharpsignalDocId": 158}, {"page": 6, "score": 0.029412, "snippet": "Diplomacy is a game of negotiations, alliances, promises kept, and promises broken. In order to survive, a player needs help from others. In order to win the game, a player must eventually stand alone. Knowing whom to trust, when to trust them, what to promise, and when to promise it is the heart of", "headingPath": "overview · Spring four-phase turn · Fall five-phase turn · Gamemaster", "sharpsignalDocId": 158}]
- citations (raw)
- [{"page": 4, "quote": null, "headingPath": "Table Of cOnTenTs · PlayeRs anD cOUnTRies · ObJecT Of THe gaMe · gaMe bOaRD", "sharpsignalDocId": 158}, {"page": 5, "quote": null, "headingPath": "UniTs (aRMies anD fleeTs) · sTaRTing POsiTiOns", "sharpsignalDocId": 158}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 158 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 158 boosted
- answered-before recall
-
this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- debug row retained until
- Nov 6, 2026 14:23
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.
per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| fused rank | document | heading | page | fused RRF score | snippet chars |
|---|---|---|---|---|---|
| #1 | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | UniTs (aRMies anD fleeTs) · sTaRTing POsiTiOns | p.5 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | aDDiTiOnal bUilDing RUles · WRiTing bUilDs anD DisbanDMenTs · TiMe ManageMenT | p.19 | 0.047883 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #3 | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | OPening MOVes in a saMPle gaMe | p.19 | 0.047875 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #4 | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | 1. diplomatiC phase · 2. order writing phase · ORDeR DaTes | p.6 | 0.046642 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #5 | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | cOnTROlling sUPPly cenTeRs · aDJUsTing nUMbeR Of UniTs · DisbanDing · bUilDing | p.18 | 0.03125 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #6 | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | 3. the order resolution phase · 4. retreat and disbanding phase · WRiTing ReTReaTs · DisbanDMenT | p.18 | 0.030303 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #7 | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | ciVil DisORDeR · alTeRnaTe Way TO Play | p.19 | 0.029851 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #8 | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | overview · Spring four-phase turn · Fall five-phase turn · Gamemaster | p.6 | 0.029412 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
chosen chunks — what the answer actually cited
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | Table Of cOnTenTs · PlayeRs anD cOUnTRies · ObJecT Of THe gaMe · gaMe bOaRD | p.4 | no quote on the wire |
| [2] | RULEBOOK Diplomacy — Rulebook (corpus doc 158) | UniTs (aRMies anD fleeTs) · sTaRTing POsiTiOns | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 265 ms · first delta 8360 ms · total 917114 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 907461 ms · retrieval 265 ms · ask 9378 ms · gateway work 9653 ms · total 917114 ms
- tokens in (the prompt the answerer read)
- 4148
- tokens out (what the answerer generated)
- 172
- tok/sec
- 141.0 tok/sec — 172 output tokens in 1.220 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 0s ago)
- stream path
- streamed — the gateway pushed at least one accumulated draft
- watchdog
- first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
- num_ctx · think posture
- both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.
disposition
- outcome
- ANSWERED — Answered
- abstain rationale (n/a — this ruling answered)
- answered — no abstain rationale applies
setup-shape — why the checklist band did or didn't render
- decision
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 80), so "no registered errata card matched" above could never have matched one
Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.