Ruling — Cloudspire

← Cloudspire

You asked

How do I play?

Answered counted as answered

Asked with: Cloudspirebg-262211-en-1e

To play Cloudspire, follow these objectives and procedures:

Objective

* Your goal is to defeat your opponents' fortress gates while protecting your own.[1]

* At the end of the game, the faction with the most powerful fortress is the winner.[1]

Build Phase

1. Starting with the first player and continuing in turn order, each player must either pass or perform a build option.[2]

2. Players may take as many turns during the Build Phase as they would like until they pass.[2]

3. Once a player has passed, they may no longer take a turn.[2]

4. The phase continues until all players have passed.[2]

5. Available build options include:

* Construct a Spire: Pay the Source cost of an available spire in your barracks or select a previously purchased merc spire from beside your barracks, then place it on a Source well within your influence.[2]

* Upgrade a Spire: Pay the appropriate Source cost per upgrade to add upgrades to a spire under your control, up to its capacity.[2] Range and attack upgrades cost Source equal to the number of upgrades the spire will have after adding it, while fortification upgrades cost 2 Source.[2]

* Earthscape: Place an earthscape from beside your barracks on a valid position; you may immediately construct a spire on one of its Source wells if you have influence over its hex, provided you pay the spire's Source cost.[2]

* Advance Your Fortress: Pay the Source cost to purchase an advancement in a fortress structure, using advancement pegs to indicate purchases.[2] Advancements must be purchased in order.[2]

* Other Build Options: Additional options may be granted by certain relics, events, or fortress advancements.[2]

Onslaught Phase

* The Onslaught Phase continues with each player taking turns until there are no faction minions in play.[3]

[1] RULEBOOK Cloudspire — Rulebook · p.8 · Objective

[2] RULEBOOK Cloudspire — Rulebook · p.17 · bra wnen · grovetenders · Build Phase

[3] RULEBOOK Cloudspire — Rulebook · p.25 · Attack · Movement · Spires Fire · Exploration

The sage rests. The game continues.

🔧 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 82 ms · ask 4934 ms · total 5997 ms
single-flight (PR-5): queued 979 ms · generation 5018 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 20, "score": 0.046871, "snippet": "In the Onslaught Phase, your chosen heroes and minions will march toward your opponent and meet on the field of battle� Each round of the Onslaught Phase consists of all players taking one full turn, starting with the first player� On your turn, you will complete all of the following stages in order", "headingPath": "Onslaught Phase · 1. Start of Turn · bra wnen Start of Turn · 2. Movement", "sharpsignalDocId": 447}, {"page": 34, "score": 0.046696, "snippet": "Have all players carry out the Build Phase simultaneously� In cases where players want to build a spire on the same Source well, this should still be resolved in turn order� After declaring your marks in turn order during the Prep Phase, have all players carry out the rest of the phase simultaneousl", "headingPath": "Making the Game Faster · Making the Game Longer · Team Pla y (2 vs. 2) · Set-up · Prep Phase · Onslaught Phase · …", "sharpsignalDocId": 447}, {"page": 11, "score": 0.046394, "snippet": "11 For your first game, the play area should look like this. Mix together all earthscapes facedown and create a stack near the market chips � Flip the top earthscape on the stack faceup� The faceup market chips and the topmost earthscape, collec- tively, are your market � Leave space nearby for a ma", "headingPath": "", "sharpsignalDocId": 447}, {"page": 23, "score": 0.044758, "snippet": "Now, let' s continue our walkthrough of the remainder of the Onslaught Phase. You have no Start of Turn talents, and you don't have enough Source to take a limited build option, so you move straight to the movement portion of your turn. Going forward, we will skip over the Start of Turn unless there", "headingPath": "Winning the Game · Start of Turn · Movement · Exploration · Attack", "sharpsignalDocId": 447}, {"page": 9, "score": 0.044404, "snippet": "The first player in this game selects the brawnen faction, and the second player will choose the grovetenders. Each player should take their faction fortress, faction dice, faction reference sheet, faction chips, gate health tracker chip, source tracker chip, and faction mark chip from the box. Plac", "headingPath": "gather your forces · Create your Island", "sharpsignalDocId": 447}, {"page": 33, "score": 0.043549, "snippet": "A 3- or 4-player game of Cloudspire plays the same as a 2-player game with the following exceptions� In a 3- or 4-player game, the last player in turn order goes first in flipping an isle and attaching their fortress� Players continue doing so in counter-clockwise order until all players have done s", "headingPath": "Pla ying a 3- or 4-Pla yer Game · Adjustments to Set-up · Prep Phase · Spire Limits · Repairing Your Gate", "sharpsignalDocId": 447}, {"page": 9, "score": 0.043445, "snippet": "9 ga ther your forces The first player in this game selects the brawnen faction, and the second player will choose the grovetenders. Each player should take their faction fortress, faction dice, faction reference sheet, faction chips, gate health tracker chip, source tracker chip, and faction mark c", "headingPath": "", "sharpsignalDocId": 447}, {"page": 8, "score": 0.029643, "snippet": "Cloudspire is a 1-4 player competitive, cooperative, and solo board game� The main rules discuss the competitive mode of the game and also provide the basis for solo and cooperative modes� Additional details on the rules for those modes can be found in the solo and cooperative scenario books� We rec", "headingPath": "Pla ying Cloudspire", "sharpsignalDocId": 447}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 8, "quote": null, "headingPath": "Objective", "sharpsignalDocId": 447}, {"page": 17, "quote": null, "headingPath": "bra wnen · grovetenders · Build Phase", "sharpsignalDocId": 447}, {"page": 25, "quote": null, "headingPath": "Attack · Movement · Spires Fire · Exploration", "sharpsignalDocId": 447}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 447 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 447 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 0.91568 of 1518 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Aug 26, 2026 07:04 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 Cloudspire — Rulebook (corpus doc 447)	Onslaught Phase · 1. Start of Turn · bra wnen Start of Turn · 2. Movement	p.20	0.046871 (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 Cloudspire — Rulebook (corpus doc 447)	Making the Game Faster · Making the Game Longer · Team Pla y (2 vs. 2) · Set-up · Prep Phase · Onslaught Phase · …	p.34	0.046696 (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 Cloudspire — Rulebook (corpus doc 447)		p.11	0.046394 (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 Cloudspire — Rulebook (corpus doc 447)	Winning the Game · Start of Turn · Movement · Exploration · Attack	p.23	0.044758 (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 Cloudspire — Rulebook (corpus doc 447)	gather your forces · Create your Island	p.9	0.044404 (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 Cloudspire — Rulebook (corpus doc 447)	Pla ying a 3- or 4-Pla yer Game · Adjustments to Set-up · Prep Phase · Spire Limits · Repairing Your Gate	p.33	0.043549 (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 Cloudspire — Rulebook (corpus doc 447)		p.9	0.043445 (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 Cloudspire — Rulebook (corpus doc 447)	Pla ying Cloudspire	p.8	0.029643 (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 49 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 Cloudspire — Rulebook (corpus doc 447)		p.11	#3	0.046394 (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 Cloudspire — Rulebook (corpus doc 447)	gather your forces · Create your Island	p.9	#5	0.044404 (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
#3	RULEBOOK Cloudspire — Rulebook (corpus doc 447)	The Rest · Terrain · Source Wells · Fortresses · Fortress Gate	p.12	#17	0.025937 (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
#4	RULEBOOK Cloudspire — Rulebook (corpus doc 447)		p.9	#7	0.043445 (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
#5	RULEBOOK Cloudspire — Rulebook (corpus doc 447)	Objective	p.8	#10	0.028986 (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 Cloudspire — Rulebook (corpus doc 447)	Create the Market	p.10	#9	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))	vector + the doc-priority boost arm	the re-ranker chose it
#7	RULEBOOK Cloudspire — Rulebook (corpus doc 447)	bra wnen · grovetenders · Build Phase	p.17	#19	0.025098 (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
#8	RULEBOOK Cloudspire — Rulebook (corpus doc 447)	Attack · Movement · Spires Fire · Exploration	p.25	#20	0.025 (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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Cloudspire — Rulebook (corpus doc 447)	Objective	p.8	no quote on the wire
[2]	RULEBOOK Cloudspire — Rulebook (corpus doc 447)	bra wnen · grovetenders · Build Phase	p.17	no quote on the wire
[3]	RULEBOOK Cloudspire — Rulebook (corpus doc 447)	Attack · Movement · Spires Fire · Exploration	p.25	no quote on the wire

generation — timing and the path taken

timing split: retrieval 82 ms · first delta 2944 ms · total 5997 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 979 ms · retrieval 82 ms · ask 4934 ms · gateway work 5018 ms · total 5997 ms
tokens in (the prompt the answerer read): 3158
tokens out (what the answerer generated): 408
tok/sec: 201.3 tok/sec — 408 output tokens in 2.027 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 22s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 1s 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 378), 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.