You asked
How do I play?
Abstained — no grounded answer; closest passages below counted as honest abstainAsked with: Dragon Eclipsebg-381247-en-1e
I looked through Dragon Eclipse'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.
Randomly choose the first player. The first player chooses any Mystling and takes its Stat, Ability, and Action cards. Then the other player do the same thing. Simultaneously players construct decks for their chosen Mystlings, following all the Deck Construction rules with the following exceptions:
During its turn, an Enemy resolves one of their effects. Every few turns, the Enemy resolves its Special Ability. To resolve an Enemy turn, follow the steps below. Slide cards. Draw an Enemy Attack card. Resolve the Enemy Attack card Check and resolve the Special Ability. Enemy turn ends. Resolve th
Available during the campaign. If you want to make your game more challenging, you can apply the following rules. The Hard mode only affects the Combat part of the game. You can switch to Hard mode at any time during the game (except during Combat). You can also resign from this mode at any time if
The steps below prepare you for the adventure that awaits you. Before the Scenario, you visit familiar places, befriend wild Mystlings, gather information, choose your next destination, and prepare your Mystlings by constructing Action decks for them. Take out the following components and place them
Combat in Dragon Eclipse is played in turns. Turns are taken alternately, starting with the player. Combat ends with you losing, winning, or Taming the Enemy. It's worth noting that not all Enemies can be Tamed; the Adventure Journal provides information about whether the Enemy is valid for Taming o
🔧 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 319 ms · ask 7093 ms · total 7413 ms
- single-flight (PR-5)
- queued 0 ms · generation 7413 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 27, "score": 0.04526, "snippet": "Randomly choose the first player. The first player chooses any Mystling and takes its Stat, Ability, and Action cards. Then the other player do the same thing. Simultaneously players construct decks for their chosen Mystlings, following all the Deck Construction rules with the following exceptions: ", "headingPath": "Quick battle setup · Challenge", "sharpsignalDocId": 1288}, {"page": 22, "score": 0.044949, "snippet": "During its turn, an Enemy resolves one of their effects. Every few turns, the Enemy resolves its Special Ability. To resolve an Enemy turn, follow the steps below. Slide cards. Draw an Enemy Attack card. Resolve the Enemy Attack card Check and resolve the Special Ability. Enemy turn ends. Resolve th", "headingPath": "Enemy Turn Order · Enemy Keywords", "sharpsignalDocId": 1288}, {"page": 27, "score": 0.044796, "snippet": "Available during the campaign. If you want to make your game more challenging, you can apply the following rules. The Hard mode only affects the Combat part of the game. You can switch to Hard mode at any time during the game (except during Combat). You can also resign from this mode at any time if ", "headingPath": "Hard modes · Corruption hard mode · Unpredictable hard mode · Steel hard mode", "sharpsignalDocId": 1288}, {"page": 5, "score": 0.044281, "snippet": "The steps below prepare you for the adventure that awaits you. Before the Scenario, you visit familiar places, befriend wild Mystlings, gather information, choose your next destination, and prepare your Mystlings by constructing Action decks for them. Take out the following components and place them", "headingPath": "BEFORE THE SCENARIO · 1. Components Setup · 2. Taking Inventory · The Unexplored side · 3. Navigating the World Map · Navigation · …", "sharpsignalDocId": 1288}, {"page": 18, "score": 0.040489, "snippet": "Combat in Dragon Eclipse is played in turns. Turns are taken alternately, starting with the player. Combat ends with you losing, winning, or Taming the Enemy. It's worth noting that not all Enemies can be Tamed; the Adventure Journal provides information about whether the Enemy is valid for Taming o", "headingPath": "Combat rules · Actions · Golden Rules of Combat", "sharpsignalDocId": 1288}, {"page": 8, "score": 0.032258, "snippet": "When players encounter a situation during the game when they cannot agree on something, the player with the Decision token makes the decision and then passes the token to the other player. Try to use the Decision token sparingly. For example, players may want to use the Decision token when you must ", "headingPath": "Try to repair the machine -Turn off the machine -Choose one:", "sharpsignalDocId": 1288}, {"page": 5, "score": 0.030769, "snippet": "After visiting Explored cards, you are instructed to start a Scenario. To do so, choose one of the Unexplored Worldmap cards from the World Map cardholder with a Scenario name. Then, open the Adventure Journal and go to the Script printed on the chosen card. There, you find a brief introduction and ", "headingPath": "4. Choosing a Scenario", "sharpsignalDocId": 1288}, {"page": 27, "score": 0.030622, "snippet": "Not available during the Campaign. In the PvP mode you can challenge your friends to an epic duel. All Mystlings can compete with each other in PvP mode. Depending on how much time you have, you can choose to play the following: Quick battle (30-45 minutes). Challenge (90 minutes). Both Quick battle", "headingPath": "PvP mode · Quick battle", "sharpsignalDocId": 1288}]
- 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 1288 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1288 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 recorded
- Sep 14, 2026 23:51 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 Dragon Eclipse — Rulebook (corpus doc 1288) | Quick battle setup · Challenge | p.27 | 0.04526 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Enemy Turn Order · Enemy Keywords | p.22 | 0.044949 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Hard modes · Corruption hard mode · Unpredictable hard mode · Steel hard mode | p.27 | 0.044796 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | BEFORE THE SCENARIO · 1. Components Setup · 2. Taking Inventory · The Unexplored side · 3. Navigating the World Map · Navigation · … | p.5 | 0.044281 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Combat rules · Actions · Golden Rules of Combat | p.18 | 0.040489 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Try to repair the machine -Turn off the machine -Choose one: | p.8 | 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 Dragon Eclipse — Rulebook (corpus doc 1288) | 4. Choosing a Scenario | p.5 | 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 Dragon Eclipse — Rulebook (corpus doc 1288) | PvP mode · Quick battle | p.27 | 0.030622 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | 6. Darkness Mode | p.29 | #15 | 0.026334 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Quick battle setup · Challenge | p.27 | #1 | 0.04526 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Run Setup | p.30 | #17 | 0.025989 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Roguelite Gameplay | p.31 | #19 | 0.024853 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Round set up: · After the round: · Roguelite mode · Game overview | p.28 | #13 | 0.026667 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | Example of a Player Turn | p.20 | #65 | 0.009009 (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 |
| #7 | RULEBOOK Dragon Eclipse — Rulebook (corpus doc 1288) | Exploring Location map · Exploration setup | p.12 | #12 | 0.027444 (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 Dragon Eclipse — Rulebook (corpus doc 1288) | PvP mode · Quick battle | p.27 | #8 | 0.030622 (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
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 319 ms · first delta 7304 ms · total 7413 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 319 ms · ask 7093 ms · gateway work 7413 ms · total 7413 ms
- tokens in (the prompt the answerer read)
- 3936
- 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 26s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 6s 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.
BOILERPLATE, not reasoning: this is the answerer's fixed abstention phrase, the same sentence it emits whenever it declines. It records THAT the answerer declined and never why — no per-ruling reason was captured, because none was sent. 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 1218), 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.