You asked
How do I play?
Answered counted as answeredAsked with: Codenames: Duetbg-224037-en-1e
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live,vps
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 93 ms · ask 5559 ms · total 5654 ms
- single-flight (PR-5)
- queued 0 ms · generation 5654 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.047493, "snippet": "BUCKET BUCKET BRICK BRICK ANT ANT You and your partner take turns giving clues to each other. Each turn uses up 1 timer token. If you contact all 15 agents before you run out of timer tokens, you both win. Look at the key card and try to find two or more green words that can be linked with a single ", "headingPath": "HOW TO PLAY · CAVE FIDLE EITHER OF YOU CAN BE THE CLUE-GIVER ON THE FIRST TURN. · THE CLUE-GIVER GIVES ONE CLUE. · CAVE THEN THE GUESSER MAY MAKE MULTIPLE GUESSES.", "sharpsignalDocId": 350}, {"page": 4, "score": 0.047123, "snippet": "BUCKET BUCKET CAVE CAVE LOCUST LOCUST IGLOO IGLOO CAESAR CAESAR BRICK BRICK FIDDLE FIDDLE CRAFT CRAFT POTTER POTTER LUNCH LUNCH ANT ANT COCONUT COCONUT VIRUS VIRUS PINE PINE LEMONADE LEMONADE STEAM STEAM STORM STORM POTATO POTATO RIFLE RIFLE BLADE BLADE RANCH RANCH MAKEUP MAKEUP PEW PEW SUN SUN RAIN", "headingPath": "", "sharpsignalDocId": 350}, {"page": 8, "score": 0.044337, "snippet": "All key cards are designed according to the diagram below. You can use this knowledge to your advantage. 3 of the GREEN words are also green on the other side. If you guess one of these words, your partner will cover it with a green tile, which means neither of you can guess it again, so you no long", "headingPath": "SECRETS OF THE KEY CARD · ZERO CLUE", "sharpsignalDocId": 350}, {"page": 3, "score": 0.032258, "snippet": "Hold the deck of key cards upright, take a random card from the middle, and place it in the stand as shown below. (The arrows should be on the top and bo/ttom edges of the key.) Place the key beside the words. Each of you should see only your own side of the key. Your side of the key card shows what", "headingPath": "DRAW A RANDOM KEY CARD. · YOU SEE WHAT THEY MUST GUESS. · THEY SEE WHAT YOU MUST GUESS.", "sharpsignalDocId": 350}, {"page": 9, "score": 0.031746, "snippet": "You can decide to give no more clues . When it is your turn to give a clue, you can say, 'Pass.' Your partner will give the clue for that turn and will be the clue-giver every turn for the rest of the game. For example, you might pass if your partner has only one word le/ft to guess and you have alr", "headingPath": "PASSING · WITH 3 OR MORE PLAYERS · LIMITED COMMUNICATION", "sharpsignalDocId": 350}, {"page": 2, "score": 0.030769, "snippet": "You are both on the same team, but you must sit on opposite sides so that you each see a different side of the key card. Mix up the word cards, choose 25 at random, and lay them out in a 5 × 5 grid. Both players will use the green tiles to mark contacted agents, so keep them in the middle. 15 agent ", "headingPath": "SIT OPPOSITE YOUR PARTNER. · LAY OUT 25 RANDOM WORDS. · KEEP THE 15 AGENT TILES WITHIN REACH. · AND THE ASSASSIN. · USE 9 TIMER TOKENS.", "sharpsignalDocId": 350}, {"page": 11, "score": 0.030679, "snippet": "The newest way to play Codenames can be installed on your phone. Weʼve made Codenames into a mobile app. You can challenge players from all around the world, and you can play with your friends, no matter where they are. Actually, itʼs a lot more than 'one more' way to play. The Codenames app offers ", "headingPath": "CODENAMES APP 4.9 ★★★★★ · CODENAMES DUET", "sharpsignalDocId": 350}, {"page": 6, "score": 0.030303, "snippet": "You see 9 words as green. When all of these are covered by agent tiles, say so. You have no words to give clues for, so your partner will be the clue-giver on all remaining turns. (Some are green from both sides and may have been guessed by you.) Once all green words from both sides of the key have ", "headingPath": "WHEN ALL 9 GREEN WORDS HAVE BEEN GUESSED, SAY SO. · IF YOU FIND ALL 15 AGENTS, YOU WIN. · IF YOU MEET THE ASSASSIN, YOU LOSE. · IF YOU RUN OUT OF TIMER TOKENS, YOU GET A SUDDEN DEATH TURN.", "sharpsignalDocId": 350}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "SIT OPPOSITE YOUR PARTNER. · LAY OUT 25 RANDOM WORDS. · KEEP THE 15 AGENT TILES WITHIN REACH. · AND THE ASSASSIN. · USE 9 TIMER TOKENS.", "sharpsignalDocId": 350}, {"page": 3, "quote": null, "headingPath": "DRAW A RANDOM KEY CARD. · YOU SEE WHAT THEY MUST GUESS. · THEY SEE WHAT YOU MUST GUESS.", "sharpsignalDocId": 350}, {"page": 4, "quote": null, "headingPath": "HOW TO PLAY · CAVE FIDLE EITHER OF YOU CAN BE THE CLUE-GIVER ON THE FIRST TURN. · THE CLUE-GIVER GIVES ONE CLUE. · CAVE THEN THE GUESSER MAY MAKE MULTIPLE GUESSES.", "sharpsignalDocId": 350}, {"page": 12, "quote": null, "headingPath": "DIFFERENCES FROM CODENAMES · SECRETS OF THE KEY CARD", "sharpsignalDocId": 350}, {"page": 8, "quote": null, "headingPath": "SECRETS OF THE KEY CARD · ZERO CLUE", "sharpsignalDocId": 350}, {"page": 6, "quote": null, "headingPath": "WHEN ALL 9 GREEN WORDS HAVE BEEN GUESSED, SAY SO. · IF YOU FIND ALL 15 AGENTS, YOU WIN. · IF YOU MEET THE ASSASSIN, YOU LOSE. · IF YOU RUN OUT OF TIMER TOKENS, YOU GET A SUDDEN DEATH TURN.", "sharpsignalDocId": 350}, {"page": 9, "quote": null, "headingPath": "PASSING · WITH 3 OR MORE PLAYERS · LIMITED COMMUNICATION", "sharpsignalDocId": 350}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 350 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 350 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)
- answer fence
- passed — letter density 0.88874 of 2310 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 11:46
retrieval — what the passage search returned
what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.
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 Codenames: Duet — Rulebook (corpus doc 350) | HOW TO PLAY · CAVE FIDLE EITHER OF YOU CAN BE THE CLUE-GIVER ON THE FIRST TURN. · THE CLUE-GIVER GIVES ONE CLUE. · CAVE THEN THE GUESSER MAY MAKE MULTIPLE GUESSES. | p.4 | 0.047493 (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 |
| #2 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | p.4 | 0.047123 (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 Codenames: Duet — Rulebook (corpus doc 350) | SECRETS OF THE KEY CARD · ZERO CLUE | p.8 | 0.044337 (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 Codenames: Duet — Rulebook (corpus doc 350) | DRAW A RANDOM KEY CARD. · YOU SEE WHAT THEY MUST GUESS. · THEY SEE WHAT YOU MUST GUESS. | p.3 | 0.032258 (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 Codenames: Duet — Rulebook (corpus doc 350) | PASSING · WITH 3 OR MORE PLAYERS · LIMITED COMMUNICATION | p.9 | 0.031746 (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 Codenames: Duet — Rulebook (corpus doc 350) | SIT OPPOSITE YOUR PARTNER. · LAY OUT 25 RANDOM WORDS. · KEEP THE 15 AGENT TILES WITHIN REACH. · AND THE ASSASSIN. · USE 9 TIMER TOKENS. | p.2 | 0.030769 (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 Codenames: Duet — Rulebook (corpus doc 350) | CODENAMES APP 4.9 ★★★★★ · CODENAMES DUET | p.11 | 0.030679 (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 Codenames: Duet — Rulebook (corpus doc 350) | WHEN ALL 9 GREEN WORDS HAVE BEEN GUESSED, SAY SO. · IF YOU FIND ALL 15 AGENTS, YOU WIN. · IF YOU MEET THE ASSASSIN, YOU LOSE. · IF YOU RUN OUT OF TIMER TOKENS, YOU GET A SUDDEN DEATH TURN. | p.6 | 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 |
what the answerer read — the passages it actually had in front of it
what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.
candidate pool: the answering read scored 15 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.
floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.
arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.
| read at | document | heading | page | fused rank | fused RRF score | carried by | how it got its slot |
|---|---|---|---|---|---|---|---|
| #1 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | HOW TO PLAY · CAVE FIDLE EITHER OF YOU CAN BE THE CLUE-GIVER ON THE FIRST TURN. · THE CLUE-GIVER GIVES ONE CLUE. · CAVE THEN THE GUESSER MAY MAKE MULTIPLE GUESSES. | p.4 | #1 | 0.047493 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | SIT OPPOSITE YOUR PARTNER. · LAY OUT 25 RANDOM WORDS. · KEEP THE 15 AGENT TILES WITHIN REACH. · AND THE ASSASSIN. · USE 9 TIMER TOKENS. | p.2 | #6 | 0.030769 (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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | DRAW A RANDOM KEY CARD. · YOU SEE WHAT THEY MUST GUESS. · THEY SEE WHAT YOU MUST GUESS. | p.3 | #4 | 0.032258 (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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | WHEN ALL 9 GREEN WORDS HAVE BEEN GUESSED, SAY SO. · IF YOU FIND ALL 15 AGENTS, YOU WIN. · IF YOU MEET THE ASSASSIN, YOU LOSE. · IF YOU RUN OUT OF TIMER TOKENS, YOU GET A SUDDEN DEATH TURN. | p.6 | #8 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | DIFFERENCES FROM CODENAMES · SECRETS OF THE KEY CARD | p.12 | #9 | 0.030018 (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)) | vector + full-text | the re-ranker chose it |
| #6 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | CODENAMES APP 4.9 ★★★★★ · CODENAMES DUET | p.11 | #7 | 0.030679 (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)) | vector + full-text | the re-ranker chose it |
| #7 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | SECRETS OF THE KEY CARD · ZERO CLUE | p.8 | #3 | 0.044337 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | PASSING · WITH 3 OR MORE PLAYERS · LIMITED COMMUNICATION | p.9 | #5 | 0.031746 (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)) | vector + the doc-priority boost arm | the re-ranker chose it |
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 Codenames: Duet — Rulebook (corpus doc 350) | SIT OPPOSITE YOUR PARTNER. · LAY OUT 25 RANDOM WORDS. · KEEP THE 15 AGENT TILES WITHIN REACH. · AND THE ASSASSIN. · USE 9 TIMER TOKENS. | p.2 | no quote on the wire |
| [2] | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | DRAW A RANDOM KEY CARD. · YOU SEE WHAT THEY MUST GUESS. · THEY SEE WHAT YOU MUST GUESS. | p.3 | no quote on the wire |
| [3] | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | HOW TO PLAY · CAVE FIDLE EITHER OF YOU CAN BE THE CLUE-GIVER ON THE FIRST TURN. · THE CLUE-GIVER GIVES ONE CLUE. · CAVE THEN THE GUESSER MAY MAKE MULTIPLE GUESSES. | p.4 | no quote on the wire |
| [4] | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | DIFFERENCES FROM CODENAMES · SECRETS OF THE KEY CARD | p.12 | no quote on the wire |
| [5] | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | SECRETS OF THE KEY CARD · ZERO CLUE | p.8 | no quote on the wire |
| [6] | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | WHEN ALL 9 GREEN WORDS HAVE BEEN GUESSED, SAY SO. · IF YOU FIND ALL 15 AGENTS, YOU WIN. · IF YOU MEET THE ASSASSIN, YOU LOSE. · IF YOU RUN OUT OF TIMER TOKENS, YOU GET A SUDDEN DEATH TURN. | p.6 | no quote on the wire |
| [7] | RULEBOOK Codenames: Duet — Rulebook (corpus doc 350) | PASSING · WITH 3 OR MORE PLAYERS · LIMITED COMMUNICATION | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 93 ms · first delta 1781 ms · total 5654 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 93 ms · ask 5559 ms · gateway work 5654 ms · total 5654 ms
- tokens in (the prompt the answerer read)
- 3162
- tokens out (what the answerer generated)
- 783
- tok/sec
- 204.7 tok/sec — 783 output tokens in 3.825 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 21s 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
- NOT_SETUP_SHAPED — no setup-shape pattern matched this question
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 278), 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.