You asked
How do I play?
Abstained — no grounded answer; closest passages below counted as honest abstainAsked with: Mage Wars Arenabg-101721-en-1e
I looked through Mage Wars Arena's rulebook and couldn't find a solid answer to that one — and I'd rather tell you so than guess at your table. Try asking it another way, or ask me about setup, turns, or how the game ends: those I know cold.
The closest rulebook passages are below — check them before ruling.
You will need to assemble 2 spellbooks. Choose 2 Mages that you and a friend wish to play; we recommend the Warlock and Beastmaster. On page 3 is a list of spells each Mage will use during the game. Find the Mage card, and all of the spell cards on the list for each of the chosen Mages. The spell ca
THE GAME ROUND THE READY STAGE Initiative Reset Channel Upkeep Planning Deployment THE ACTION STAGE First Quickcast Phase Creature Action Phases Final Quickcast Phase Mage Wars is played over a series of rounds, which continue until one Mage takes enough damage to be destroyed. The last Mage standin
this manner the initiative marker alternates back and forth between players. The player with the initiative acts first during the Action Stage, and goes first whenever you must determine the order of events. Reset all action markers, quickcast markers, and ready markers on your cards by flipping the
After you've played a few Apprentice Mode games and you feel ready, we recommend using these new spellbooks. They are not recommended for first time players. These spellbooks were designed using the rules for building spellbooks, so they are 'legal' for any games. You can modify or 'tweak' these bas
Spellbinding is a trait that some objects have (usually equipment spells). This trait allows you to attach a spell card to the object. When you cast a spell with the Spellbind trait, you may immediately bind a spell to it. You can choose any spell from your spellbook that fulfills the limitations on
🔧 debug — where this ruling came from
- outcome
- ABSTAINED — Abstained — no grounded answer; closest passages below
- warm abstain
-
- this ruling — W1 — generic warm abstain · receipt: none (generic)
- corpus profile
- live,vps
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 178 ms · ask 3347 ms · total 3527 ms
- single-flight (PR-5)
- queued 0 ms · generation 3527 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.048916, "snippet": "You will need to assemble 2 spellbooks. Choose 2 Mages that you and a friend wish to play; we recommend the Warlock and Beastmaster. On page 3 is a list of spells each Mage will use during the game. Find the Mage card, and all of the spell cards on the list for each of the chosen Mages. The spell ca", "headingPath": "Spellbooks · The Rules · The Magic Rule · The Sidebars", "sharpsignalDocId": 572}, {"page": 8, "score": 0.045635, "snippet": "THE GAME ROUND THE READY STAGE Initiative Reset Channel Upkeep Planning Deployment THE ACTION STAGE First Quickcast Phase Creature Action Phases Final Quickcast Phase Mage Wars is played over a series of rounds, which continue until one Mage takes enough damage to be destroyed. The last Mage standin", "headingPath": "", "sharpsignalDocId": 572}, {"page": 8, "score": 0.045335, "snippet": "this manner the initiative marker alternates back and forth between players. The player with the initiative acts first during the Action Stage, and goes first whenever you must determine the order of events. Reset all action markers, quickcast markers, and ready markers on your cards by flipping the", "headingPath": "THE GAME ROUND · Phase 2: RESET · THE READY STAGE · THE ACTION STAGE · Phase 1: INITIATIVE", "sharpsignalDocId": 572}, {"page": 40, "score": 0.042961, "snippet": "After you've played a few Apprentice Mode games and you feel ready, we recommend using these new spellbooks. They are not recommended for first time players. These spellbooks were designed using the rules for building spellbooks, so they are 'legal' for any games. You can modify or 'tweak' these bas", "headingPath": "STARTING SPELLBOOKS", "sharpsignalDocId": 572}, {"page": 23, "score": 0.042745, "snippet": "Spellbinding is a trait that some objects have (usually equipment spells). This trait allows you to attach a spell card to the object. When you cast a spell with the Spellbind trait, you may immediately bind a spell to it. You can choose any spell from your spellbook that fulfills the limitations on", "headingPath": "SPELLBINDING", "sharpsignalDocId": 572}, {"page": 18, "score": 0.032258, "snippet": "Familiars are objects that have the ability to cast spells. Often, these objects can channel mana as well. When a Familiar gains mana, place the appropriate mana counters on the object. If you control a Familiar during the Planning Phase, you may select a spell for it to cast during the round. The F", "headingPath": "FAMILIARS", "sharpsignalDocId": 572}, {"page": 10, "score": 0.030769, "snippet": "Some objects, such as Familiars or Spawnpoints, have the ability to cast spells. You may choose one spell for each of these objects at this time. Place these spells face down next to the creature or object. Spells which are not cast during the round are returned to your spellbook at the beginning of", "headingPath": "Phase 5: PLANNING · Phase 6: DEPLOYMENT · THE ACTION STAGE · First Quickcast Phase", "sharpsignalDocId": 572}, {"page": 15, "score": 0.029851, "snippet": "Mages (and a few other creatures and objects) have the ability to cast spells. You can only cast the spells that you prepared to cast during the Planning Phase. When you cast a spell, follow these 4 steps in order: Declare Spell Pay Costs Counter Spell Resolve Spell Announce that you are casting a s", "headingPath": "CASTING SPELLS · Step 1: Declare Spell · Step 2: Pay Costs", "sharpsignalDocId": 572}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- []
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 572 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 572 boosted
- 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
- Nov 24, 2026 23:28 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 Mage Wars Arena — Rulebook (corpus doc 572) | Spellbooks · The Rules · The Magic Rule · The Sidebars | p.4 | 0.048916 (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 Mage Wars Arena — Rulebook (corpus doc 572) | p.8 | 0.045635 (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 Mage Wars Arena — Rulebook (corpus doc 572) | THE GAME ROUND · Phase 2: RESET · THE READY STAGE · THE ACTION STAGE · Phase 1: INITIATIVE | p.8 | 0.045335 (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 Mage Wars Arena — Rulebook (corpus doc 572) | STARTING SPELLBOOKS | p.40 | 0.042961 (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 Mage Wars Arena — Rulebook (corpus doc 572) | SPELLBINDING | p.23 | 0.042745 (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 Mage Wars Arena — Rulebook (corpus doc 572) | FAMILIARS | p.18 | 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 |
| #7 | RULEBOOK Mage Wars Arena — Rulebook (corpus doc 572) | Phase 5: PLANNING · Phase 6: DEPLOYMENT · THE ACTION STAGE · First Quickcast Phase | p.10 | 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 |
| #8 | RULEBOOK Mage Wars Arena — Rulebook (corpus doc 572) | CASTING SPELLS · Step 1: Declare Spell · Step 2: Pay Costs | p.15 | 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 |
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 80 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 Mage Wars Arena — Rulebook (corpus doc 572) | MULTIPLAYER | p.41 | #9 | 0.029052 (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 |
| #2 | RULEBOOK Mage Wars Arena — Rulebook (corpus doc 572) | MAGES | p.33 | #11 | 0.028446 (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 |
| #3 | RULEBOOK Mage Wars Arena — Rulebook (corpus doc 572) | Spellbooks · The Rules · The Magic Rule · The Sidebars | p.4 | #1 | 0.048916 (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 |
| #4 | RULEBOOK Mage Wars Arena — Rulebook (corpus doc 572) | The Mage Wars Arena · Setting Up the Game | p.7 | #13 | 0.026631 (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 |
| #5 | RULEBOOK Mage Wars Arena — Rulebook (corpus doc 572) | The Arena Calls… | p.2 | #68 | 0.008696 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #6 | RULEBOOK Mage Wars Arena — Rulebook (corpus doc 572) | QUICKCAST ACTION · Action Phases | p.10 | #15 | 0.024752 (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 Mage Wars Arena — Rulebook (corpus doc 572) | APPRENTICE SPELLBOOKS · ATTACKS · PRIESTESS · WIZARD | p.5 | #26 | 0.014493 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | full-text | the re-ranker chose it |
| #8 | RULEBOOK Mage Wars Arena — Rulebook (corpus doc 572) | MULTIPLAYER | p.41 | #27 | 0.014286 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | 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 |
|---|
generation — timing and the path taken
- timing split
- retrieval 178 ms · first delta 3423 ms · total 3527 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 178 ms · ask 3347 ms · gateway work 3527 ms · total 3527 ms
- tokens in (the prompt the answerer read)
- 3690
- tokens out (what the answerer generated)
- 9
- tok/sec
- 180.0 tok/sec — 9 output tokens in 0.050 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 0s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 60h, 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
- ABSTAINED — Abstained — no grounded answer; closest passages below
- abstain rationale
-
I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped
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 504), 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.