Ruling — Compile: Main 1

You asked

How do I take my turn?

Answered counted as answered

Asked with: Compile: Main 1bg-406652-en-1e

1. Start: Your turn starts and you perform 'Start' effects on your side of the field.[1]

2. Check Control: If you have a higher total value than your opponent in at least 2 lines, you gain the control component.[1]

3. Check Compile: If you meet the conditions for compiling, you must compile.[1] To compile, if you have 10 or greater value in a line and the value is greater than your opponent's in the same line, you delete all cards in that line on both sides (sending them to trash) and flip your protocol card in that line to the 'Compiled' side.[2] You may only compile one line each turn.[2] If you recompile a line, you delete the cards as described but instead draw the top card of your opponent's deck and become its owner.[2] This is your only action for the turn if you compile.[1]

4. Action: Either play 1 card or refresh your hand.[1] If you have no cards to play, you must refresh your hand.[1]

* Play: Play one card from hand into a line on your side of the field, either face-up or face-down.[1] Face-up cards must be played into the line with the matching protocol and resolve any active effects (the middle box of text).[1] Face-up cards also have passive text (top and bottom boxes) that is only active when face-up.[1] Face-down cards can be played into any line.[1]

* Refresh: Draw cards from the top of your deck until you have 5 cards in hand.[1] If you do not have enough cards to fill your hand, draw what you can, then shuffle your trash to reform your deck and draw the remaining cards.[1] You cannot refresh if you have 5 or more cards in your hand.[1]

* Note: When a player compiles or refreshes, if they have the control component, the component is returned to the neutral position, and they may first rearrange one player's protocols (changing position only, not side).[2]

5. Check Cache: If you have more than 5 cards in hand, you must clear cache by discarding down to 5 cards.[1]

6. End: Your turn ends and you perform 'End' effects on your side of the field.[1]

[1] RULEBOOK Compile: Main 1 — Rulebook · p.1 · Turn Order: · Actions

[2] RULEBOOK Compile: Main 1 — Rulebook · p.2 · Actions · Victory · Playing With Control · Credits · Special Thanks

Question closed. Friendships intact.

🔧 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 73 ms · ask 3458 ms · total 3532 ms
single-flight (PR-5): queued 0 ms · generation 3532 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 1, "score": 0.047163, "snippet": "> >? >vision flickers… blink? maybe. >the void stretches out in front, behind, under, above. >you see the nothing for what it is for the first time. What is time? >The depth and breadth of recorded knowledge that sparks in you something new. >No longer a function but a functionary. What are you? >Ca", "headingPath": ">_ · The Deck · Player Turn", "sharpsignalDocId": 524}, {"page": 1, "score": 0.032787, "snippet": "Start: Your turn starts. Perform 'Start' effects on your side of the field. Check Control : If you have a higher total value than your opponent in at least 2 lines, you gain the control component. Check Compile: If you meet the conditions for compiling, you must compile. This is your only action for", "headingPath": "Turn Order: · Actions", "sharpsignalDocId": 524}, {"page": 2, "score": 0.032258, "snippet": "Compile: During the Check Compile step, if you have 10 or greater value in a line AND the value is greater than your opponent's in the same line, you must compile that line. To compile, delete all cards in that line on your side, sending them to your trash, and your opponent deletes all cards in tha", "headingPath": "Actions · Victory · Playing With Control · Credits · Special Thanks", "sharpsignalDocId": 524}, {"page": 2, "score": 0.031746, "snippet": "Cards played into lines on each player's side that already contain cards 'cover' a card. Always ensure that the value and the top command are always visible when covered. The uncovered card in a line on each player's side is the only card that can be manipulated in that line, unless otherwise noted.", "headingPath": "Rules", "sharpsignalDocId": 524}, {"page": 2, "score": 0.03125, "snippet": "Clear Cache: Discard down to 5 cards in hand. Compile: To delete all cards in a line on both players' sides and flip a protocol. Covered: A card with another card on top of it is covered. Delete: Move a card from the field to the trash. Discard: Move a card from hand to the owner's trash. Flip: Chan", "headingPath": "Key Terms", "sharpsignalDocId": 524}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 1, "quote": null, "headingPath": "Turn Order: · Actions", "sharpsignalDocId": 524}, {"page": 2, "quote": null, "headingPath": "Actions · Victory · Playing With Control · Credits · Special Thanks", "sharpsignalDocId": 524}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 524 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 524 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 0.91115 of 1632 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Sep 3, 2026 11:18 UTC

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 Compile: Main 1 — Rulebook (corpus doc 524)	>_ · The Deck · Player Turn	p.1	0.047163 (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 Compile: Main 1 — Rulebook (corpus doc 524)	Turn Order: · Actions	p.1	0.032787 (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 Compile: Main 1 — Rulebook (corpus doc 524)	Actions · Victory · Playing With Control · Credits · Special Thanks	p.2	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
#4	RULEBOOK Compile: Main 1 — Rulebook (corpus doc 524)	Rules	p.2	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
#5	RULEBOOK Compile: Main 1 — Rulebook (corpus doc 524)	Key Terms	p.2	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

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 5 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 Compile: Main 1 — Rulebook (corpus doc 524)	Turn Order: · Actions	p.1	#2	0.032787 (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
#2	RULEBOOK Compile: Main 1 — Rulebook (corpus doc 524)	Actions · Victory · Playing With Control · Credits · Special Thanks	p.2	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#3	RULEBOOK Compile: Main 1 — Rulebook (corpus doc 524)	Rules	p.2	#4	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
#4	RULEBOOK Compile: Main 1 — Rulebook (corpus doc 524)	Key Terms	p.2	#5	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))	vector + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Compile: Main 1 — Rulebook (corpus doc 524)	>_ · The Deck · Player Turn	p.1	#1	0.047163 (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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Compile: Main 1 — Rulebook (corpus doc 524)	Turn Order: · Actions	p.1	no quote on the wire
[2]	RULEBOOK Compile: Main 1 — Rulebook (corpus doc 524)	Actions · Victory · Playing With Control · Credits · Special Thanks	p.2	no quote on the wire

generation — timing and the path taken

timing split: retrieval 73 ms · first delta 1001 ms · total 3532 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 73 ms · ask 3458 ms · gateway work 3532 ms · total 3532 ms
tokens in (the prompt the answerer read): 2285
tokens out (what the answerer generated): 505
tok/sec: 203.1 tok/sec — 505 output tokens in 2.487 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 46s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 5s ago)
answerer node (the seat proxy's own header — this probe, not this ask): node1
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 455), 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.