You asked
how many cards can i play in one turn?
Abstained — no grounded answer; closest passages below counted as honest abstainThe answerer couldn't ground a confident answer in the rulebook. The closest rulebook passages are below — check them before ruling.
| North Island Brown Kiwi | WHEN PLAYED: Discard a bonus card. If you do, draw 4 bonus cards, keep 2, and discard the other 2. | | | Plains-Wanderer | WHEN PLAYED: Draw 1 bonus card for each bird in your . Keep 1 and discard the rest. | | | Kea | WHEN PLAYED: Draw 1 bonus card. You may discard any n
| Galah | WHEN ACTIVATED: Choose another player. They reset the birdfeeder and gain a , if there is one. You tuck 2 from the deck behind this bird. | | | Crimson Chat | WHEN ACTIVATED: Discard 1 to tuck 1 from the deck behind this bird. | | | Cockatiel | WHEN ACTIVATED: Discard 1 to choose a from th
Pass the first player token to the player who came in second on the end-of-round goal. If the players tied, then pass it to the other player. Round one: 8 turns per player Round two: 7 turns per player Round three: 6 turns per player Round four: 5 turns per player DESIGNER'S NOTE: Players have fewer
IN GENERAL: Draw cards into your hand as described on the card. Just as with the Draw Cards action (Option 4 in the rulebook), you may draw from the deck or the face-up cards. There is never any hand limit. Hands may be private or public. | Mallard | WHEN ACTIVATED: Draw 1 . | You may draw from the
When all players have placed all of their action cubes, the round is over. Follow these steps in order: Remove all action cubes from your player mat. Score the end-of-round goal for the round you just completed. Discard all face-up bird cards on the bird tray and restock the bird tray with cards fro
Strategy guides → — community tips, kept separate from rulings
🔧 debug — where this ruling came from
- outcome
- ABSTAINED — Abstained — no grounded answer; closest passages below
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- unset-dev (corpus lane freezes the deploy value)
- timings
- search 106 ms · ask 2709 ms · total 2824 ms
- single-flight (PR-5)
- queued 0 ms · generation 2824 ms
- retrieval refs (raw)
- [{"page": 10, "score": 0.029462, "snippet": "| North Island Brown Kiwi | WHEN PLAYED: Discard a bonus card. If you do, draw 4 bonus cards, keep 2, and discard the other 2. | | | Plains-Wanderer | WHEN PLAYED: Draw 1 bonus card for each bird in your . Keep 1 and discard the rest. | | | Kea | WHEN PLAYED: Draw 1 bonus card. You may discard any n", "headingPath": "Bonus Card Powers", "sharpsignalDocId": 48}, {"page": 8, "score": 0.016393, "snippet": "| Galah | WHEN ACTIVATED: Choose another player. They reset the birdfeeder and gain a , if there is one. You tuck 2 from the deck behind this bird. | | | Crimson Chat | WHEN ACTIVATED: Discard 1 to tuck 1 from the deck behind this bird. | | | Cockatiel | WHEN ACTIVATED: Discard 1 to choose a from th", "headingPath": "Flocking Powers", "sharpsignalDocId": 48}, {"page": 4, "score": 0.016393, "snippet": "Pass the first player token to the player who came in second on the end-of-round goal. If the players tied, then pass it to the other player. Round one: 8 turns per player Round two: 7 turns per player Round three: 6 turns per player Round four: 5 turns per player DESIGNER'S NOTE: Players have fewer", "headingPath": "Duet Mode", "sharpsignalDocId": 49}, {"page": 9, "score": 0.016129, "snippet": "IN GENERAL: Draw cards into your hand as described on the card. Just as with the Draw Cards action (Option 4 in the rulebook), you may draw from the deck or the face-up cards. There is never any hand limit. Hands may be private or public. | Mallard | WHEN ACTIVATED: Draw 1 . | You may draw from the ", "headingPath": "Card-Drawing Powers", "sharpsignalDocId": 46}, {"page": 5, "score": 0.015873, "snippet": "When all players have placed all of their action cubes, the round is over. Follow these steps in order: Remove all action cubes from your player mat. Score the end-of-round goal for the round you just completed. Discard all face-up bird cards on the bird tray and restock the bird tray with cards fro", "headingPath": "Round Structure", "sharpsignalDocId": 45}, {"page": 8, "score": 0.015625, "snippet": "Card-Drawing: Draw cards into your hand as described on the card. Just as with the 'DRAW CARDS' action, you may draw from the deck or the faceup cards. There is never any hand limit. Hands may be private or public. Flocking : The birds with this power are known for gathering in large single-species ", "headingPath": "Card-Drawing and Flocking Powers", "sharpsignalDocId": 50}, {"page": 3, "score": 0.015385, "snippet": "Split the players into 2 groups at the same table (3+3 for a 6-player game or 3+4 for a 7-player game). These groups remain fixed for the entire game. Replace all Global Components setup steps with the following: Turn-order dial. Place the turn-order dial in the middle of the table. The dial has two", "headingPath": "Setup", "sharpsignalDocId": 49}, {"page": 11, "score": 0.015152, "snippet": "In rounds 2 and 4, everyone has an odd number of turns. This will cause the person to the right of the first-player token to have 1 cube left at the end of the round when everyone else has finished their turns. They take 1 last turn alone at this point. The 2 players on the edges of the 4-player gro", "headingPath": "Special circumstances for 7-player games", "sharpsignalDocId": 49}]
- citations (raw)
- []
- boost provenance — errata + base rulebook (E2/E3)
- gate not evaluated for this ruling (boost, supersedence, and wrench all off at ask time), and the base-rulebook arm went unrecorded for the same reason — the wrench that would have stored it was off; rulesage.errata.boost-enabled=false, rulesage.errata.supersedence-enabled=false
- answered-before recall
-
no past answered ruling for this game matched closely enough
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- debug row retained until
- Oct 9, 2026 00:09
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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 Wingspan — Oceania Expansion (corpus doc 48) | Bonus Card Powers | p.10 | 0.029462 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #2 | RULEBOOK Wingspan — Oceania Expansion (corpus doc 48) | Flocking Powers | p.8 | 0.016393 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #3 | RULEBOOK Wingspan — Asia Rulebook (corpus doc 49) | Duet Mode | p.4 | 0.016393 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #4 | RULEBOOK Wingspan — Appendix (corpus doc 46) | Card-Drawing Powers | p.9 | 0.016129 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #5 | RULEBOOK Wingspan — Rulebook (corpus doc 45) | Round Structure | p.5 | 0.015873 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #6 | RULEBOOK Wingspan — Asia Appendix (corpus doc 50) | Card-Drawing and Flocking Powers | p.8 | 0.015625 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #7 | RULEBOOK Wingspan — Asia Rulebook (corpus doc 49) | Setup | p.3 | 0.015385 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #8 | RULEBOOK Wingspan — Asia Rulebook (corpus doc 49) | Special circumstances for 7-player games | p.11 | 0.015152 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 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 |
|---|
generation — timing and the path taken
- timing split
- retrieval 106 ms · first delta n/a · total 2824 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 106 ms · ask 2709 ms · gateway work 2824 ms · total 2824 ms
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 40s ago)
- stream path
- not recorded — this ruling predates the stream-path column (V41)
- 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
- ABSTAINED — Abstained — no grounded answer; closest passages below
- abstain rationale
- the answerer offered no rationale text with this refusal (or the ruling predates the abstain_rationale column, V41)
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
6 errata cards registered for edition 3 — these are what the gate above had to match against
- anatomist · HEADING_EXTRACTED · Wingspan — Update Pack (Corrected Bonus Cards) · corpus doc 66 · p.2
- belted kingfisher · HAND_PINNED · Wingspan — Update Pack (Corrected Bird Cards) · corpus doc 65 · p.17
- ecologist · HEADING_EXTRACTED · Wingspan — Update Pack (Corrected Bonus Cards) · corpus doc 66 · p.5
- oologist · HEADING_EXTRACTED · Wingspan — Update Pack (Corrected Bonus Cards) · corpus doc 66 · p.1
- photographer · HEADING_EXTRACTED · Wingspan — Update Pack (Corrected Bonus Cards) · corpus doc 66 · p.3
- rodentologist · HEADING_EXTRACTED · Wingspan — Update Pack (Corrected Bonus Cards) · corpus doc 66 · p.4
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.