fix(engine): repeat Grindstone mill while milled cards share a color (#6091)#6588
Conversation
|
🚨 Contributor flagged. Click here for more info: Superagent Dashboard |
superagent-security
Bot
added
the
contributor:flagged
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughAdds ChangesLast zone changed support
Estimated code review effort: 3 (Moderate) | ~25 minutes Suggested labels: Suggested reviewers: Sequence Diagram(s)sequenceDiagram
participant Grindstone
participant State
participant Quantity
participant RepeatProcess
Grindstone->>State: record last_zone_changed_ids
State->>Quantity: provide changed object population
Quantity->>RepeatProcess: evaluate shared-quality count
RepeatProcess->>Grindstone: continue or stop milling
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (2)
crates/engine/src/parser/oracle_effect/conditions.rs (1)
1539-1578: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueRecognizer is hardcoded to the "milled" verb even though
LastZoneChangedis a general zone-change ledger.
parse_shared_qualityandparse_numberalready generalize the quality/count axes, buttag(" were milled this way")locks this to mill specifically. SinceTargetFilter::LastZoneChanged(filter.rs) is verb-agnostic, consider generalizing the verb viaalt()(milled/discarded/exiled/revealed) the same way the rest of this file generalizes other "this way" outcome verbs, so the next card with this shared-quality-repeat shape on a different verb doesn't need a new near-duplicate function.As per coding guidelines,
crates/engine/**: "Build reusable card-class building blocks rather than one-card special cases; new enum variants, parsers, effects, and filters must support a category of cards."🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@crates/engine/src/parser/oracle_effect/conditions.rs` around lines 1539 - 1578, Generalize strip_milled_shared_quality_conditional so its recognizer accepts the supported “this way” outcome verbs (milled, discarded, exiled, and revealed) instead of only matching “were milled this way.” Keep the existing shared-quality parsing, QuantityCheck construction, LastZoneChanged filter, and remainder handling unchanged.Source: Coding guidelines
crates/engine/src/game/quantity.rs (1)
1896-1904: 🎯 Functional Correctness | 🔵 Trivial | ⚡ Quick winSpecial-case only covers bare
LastZoneChanged; compound filters silently fall through to the wrong zone.The early return only fires for the literal
TargetFilter::LastZoneChanged. If it's ever composed (e.g.And([LastZoneChanged, Typed(..)])for "if two lands milled this way share a color"),extract_zones()won't recognize the ledger and defaults to scanningBattlefieldinstead of intersecting withstate.last_zone_changed_ids— the wrong population for milled/discarded/exiled cards. This also silently bypasses thefilter_contains_other_than_trigger_objectexclusion for any LastZoneChanged-based count. Contrast withfilter_contains_last_zone_changedineffects/mod.rs, which does recurse intoAnd/Or/Not— the "detects dependency" side is more general than this "resolves the population" side.Not a bug for Grindstone's bare-filter usage, but worth hardening before the next card composes this filter.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@crates/engine/src/game/quantity.rs` around lines 1896 - 1904, Update object_count_matching_ids to resolve LastZoneChanged recursively within compound TargetFilter variants such as And, Or, and Not, using state.last_zone_changed_ids as the candidate population before applying the remaining filter logic. Preserve filter_contains_other_than_trigger_object exclusion behavior for composed filters and keep existing handling for filters without a LastZoneChanged dependency.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/engine/src/game/effects/mod.rs`:
- Around line 2688-2746: Make filter_contains_last_zone_changed and
quantity_ref_depends_on_zone_change_this_way exhaustive over their respective
enums, removing the _ => false fallbacks. Add explicit false arms for variants
that cannot contain a relevant filter, recurse through
TargetFilter::TrackedSetFiltered, and include every QuantityRef variant carrying
a TargetFilter, including the listed turn-based and zone-change variants, so
nested LastZoneChanged dependencies are detected.
In `@crates/engine/tests/integration/issue_6091_grindstone.rs`:
- Around line 164-175: Reorder the setup in the test around
add_colored_library_card so the six blue pad cards are added before the Green
Second and Blue Top pair, making that pair the first cards milled and ensuring
the test exercises Painter’s red effect. Optionally add assertions after
setup_painter_red confirming both top cards have red.
---
Nitpick comments:
In `@crates/engine/src/game/quantity.rs`:
- Around line 1896-1904: Update object_count_matching_ids to resolve
LastZoneChanged recursively within compound TargetFilter variants such as And,
Or, and Not, using state.last_zone_changed_ids as the candidate population
before applying the remaining filter logic. Preserve
filter_contains_other_than_trigger_object exclusion behavior for composed
filters and keep existing handling for filters without a LastZoneChanged
dependency.
In `@crates/engine/src/parser/oracle_effect/conditions.rs`:
- Around line 1539-1578: Generalize strip_milled_shared_quality_conditional so
its recognizer accepts the supported “this way” outcome verbs (milled,
discarded, exiled, and revealed) instead of only matching “were milled this
way.” Keep the existing shared-quality parsing, QuantityCheck construction,
LastZoneChanged filter, and remainder handling unchanged.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: 1b17987f-ac1d-4688-923b-209d94464fca
📒 Files selected for processing (21)
crates/engine/src/game/ability_rw.rscrates/engine/src/game/ability_scan.rscrates/engine/src/game/ability_utils.rscrates/engine/src/game/cost_payability.rscrates/engine/src/game/coverage.rscrates/engine/src/game/effects/discard.rscrates/engine/src/game/effects/mod.rscrates/engine/src/game/filter.rscrates/engine/src/game/layers.rscrates/engine/src/game/quantity.rscrates/engine/src/game/targeting.rscrates/engine/src/game/trigger_matchers.rscrates/engine/src/parser/oracle_effect/conditions.rscrates/engine/src/parser/oracle_effect/mod.rscrates/engine/src/parser/oracle_effect/tests.rscrates/engine/src/parser/oracle_static/restriction.rscrates/engine/src/types/ability.rscrates/engine/src/types/events.rscrates/engine/tests/integration/issue_6091_grindstone.rscrates/engine/tests/integration/main.rscrates/mtgish-import/src/convert/condition.rs
Parse changes introduced by this PR · 1 card(s), 1 signature(s) (baseline: main
|
matthewevans
left a comment
matthewevans
left a comment
There was a problem hiding this comment.
Changes requested — the new event ledger filter and its regressions are incomplete.
🔴 Blocker
[MED] Preserve LastZoneChanged candidate selection when it is composed with another filter. Evidence: crates/engine/src/game/quantity.rs:1896-1914 uses the event ledger only for bare TargetFilter::LastZoneChanged; And { LastZoneChanged, Typed(..) } falls through to battlefield enumeration. Detect the event-ledger population recursively, then apply the full compound filter (including trigger-object exclusions).
[MED] Make the Grindstone tests discriminate. Evidence: crates/engine/tests/integration/issue_6091_grindstone.rs:151-175 puts the blue pads after Blue/Green, and :196-245 has no trailing cards for the repeat cases. The assertions can pass if Painter's color grant or repetition is broken. Reorder the Painter fixture and add trailing cards with assertions they remain.
Recommendation: request changes; fix the compositional filter seam and add revert-sensitive regressions.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/engine/src/game/quantity.rs`:
- Around line 1903-1921: Update the candidate-selection logic around
filter_contains_last_zone_changed so the last_zone_changed_ids fast path is used
only for filters provably restricted to positive LastZoneChanged matches.
Recursively derive candidates for Or by unioning each branch’s candidates, and
for Not by complementing against the full applicable zone population; preserve
matches_target_filter afterward. Add regression tests covering
Or(LastZoneChanged, Typed(...)) and Not(LastZoneChanged).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: 10b8171b-c2ef-404d-a7ca-fdf52f67a9c7
📒 Files selected for processing (4)
crates/engine/src/game/effects/mod.rscrates/engine/src/game/filter.rscrates/engine/src/game/quantity.rscrates/engine/tests/integration/issue_6091_grindstone.rs
🚧 Files skipped from review as they are similar to previous changes (3)
- crates/engine/src/game/effects/mod.rs
- crates/engine/tests/integration/issue_6091_grindstone.rs
- crates/engine/src/game/filter.rs
matthewevans
left a comment
matthewevans
left a comment
There was a problem hiding this comment.
Current-head verdict: blocked.
🔴 Blocker
[HIGH] Do not use filter_contains_last_zone_changed as a universal candidate-population switch. Evidence: crates/engine/src/game/filter.rs:966-977 returns true through Or and Not, then crates/engine/src/game/quantity.rs:1896-1904 restricts the entire population to last_zone_changed_ids. Or(LastZoneChanged, Typed(...)) must also see the typed objects outside that ledger, and Not(LastZoneChanged) is its complement, so both are silently miscounted. Suggested fix: derive candidates compositionally (intersection for And, union for Or, complement for Not) or limit the optimization to a provably positive ledger filter; add regressions for the two counterexamples.
🟡 Non-blocking
The parser remains deliberately mill-specific; that is acceptable only while this new primitive is not claimed as a generic cross-verb grammar.
Recommendation: request changes; repair the filter-population seam and prove compound filters before approval.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/engine/src/game/quantity.rs`:
- Around line 1910-1948: Add a verified “CR <number>: <description>” citation
beside object_count_matching_ids, documenting the governing rule for the
ledger-based LastZoneChanged candidate selection and repeat-condition quantity
resolution. Keep the resolver logic unchanged and use the project’s established
citation format.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: 657f0023-6a5e-4043-b710-2f9bcf578872
📒 Files selected for processing (2)
crates/engine/src/game/filter.rscrates/engine/src/game/quantity.rs
🚧 Files skipped from review as they are similar to previous changes (1)
- crates/engine/src/game/filter.rs
| pub(crate) fn object_count_matching_ids( | ||
| state: &GameState, | ||
| filter: &TargetFilter, | ||
| filter_ctx: &FilterContext<'_>, | ||
| source_id: ObjectId, | ||
| ) -> Vec<ObjectId> { | ||
| let mut ids: Vec<ObjectId> = match filter { | ||
| TargetFilter::Or { filters } => { | ||
| let mut seen = HashSet::new(); | ||
| let mut out = Vec::new(); | ||
| for branch in filters { | ||
| for id in object_count_matching_ids(state, branch, filter_ctx, source_id) { | ||
| if seen.insert(id) { | ||
| out.push(id); | ||
| } | ||
| } | ||
| } | ||
| out | ||
| } | ||
| TargetFilter::Not { filter: inner } | ||
| if matches!(inner.as_ref(), TargetFilter::LastZoneChanged) => | ||
| { | ||
| let ledger: HashSet<ObjectId> = state.last_zone_changed_ids.iter().copied().collect(); | ||
| object_count_zone_object_ids(state, filter) | ||
| .into_iter() | ||
| .filter(|&id| !ledger.contains(&id)) | ||
| .filter(|&id| matches_target_filter(state, id, filter, filter_ctx)) | ||
| .collect() | ||
| } | ||
| _ if filter_matching_set_subset_of_last_zone_changed(filter) => state | ||
| .last_zone_changed_ids | ||
| .iter() | ||
| .copied() | ||
| .filter(|&id| matches_target_filter(state, id, filter, filter_ctx)) | ||
| .collect(), | ||
| _ => object_count_zone_object_ids(state, filter) | ||
| .into_iter() | ||
| .filter(|&id| matches_target_filter(state, id, filter, filter_ctx)) | ||
| .collect(), |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
Add a verified CR citation for this rules-resolution path.
This ledger-based candidate selection changes how repeat-condition quantities resolve, but it has no CR <number>: <description> annotation. Document the verified governing rule beside this resolver so the LastZoneChanged semantics remain auditable.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@crates/engine/src/game/quantity.rs` around lines 1910 - 1948, Add a verified
“CR <number>: <description>” citation beside object_count_matching_ids,
documenting the governing rule for the ledger-based LastZoneChanged candidate
selection and repeat-condition quantity resolution. Keep the resolver logic
unchanged and use the project’s established citation format.
Sources: Coding guidelines, Path instructions
e8d1e63 to
8ec1c33
Compare
matthewevans
left a comment
matthewevans
left a comment
There was a problem hiding this comment.
Current-head verdict: 1 blocker remains — request changes.
🔴 Blocker
[MED] Candidate selection is still not compositional for an Or nested below another compound filter. Evidence: crates/engine/src/game/quantity.rs:1919-1931 unions ledger candidates only when Or is the outermost filter, while crates/engine/src/game/filter.rs:987-997 treats Or as not being a ledger subset. The fallback at crates/engine/src/game/quantity.rs:1948-1951 consequently scans only default/explicit zones for And([Or(LastZoneChanged, Typed(..)), Typed(..)]), omitting a moved-to-graveyard or exile ledger member even though matches_target_filter accepts it.
The current added tests cover top-level Or (quantity.rs:7819-7875) and direct Not (:7878-7928), not this nested composition.
Suggested fix: derive the candidate universe recursively for every boolean node (or normalize the complete filter before candidate enumeration), then add a nested And(Or(LastZoneChanged, …), …) regression with an off-battlefield ledger member.
✅ Clean
The prior direct Or/Not handling and the Grindstone parser replacement are covered on this head; the parse-diff’s single intended Grindstone signature change matches the new WhileCondition parser test.
Recommendation: request changes; re-review the next head.
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
crates/engine/src/parser/oracle_effect/tests.rs (1)
32143-32155: 🎯 Functional Correctness | 🟠 Major | ⚡ Quick winAdd the governing CR citation.
This test encodes the zero-target behavior of “up to one target,” but its new rules note lacks the required verified
CR <number>: <description>annotation. Add the relevant zero-target rule (CR 115.6). (media.wizards.com)As per coding guidelines, rules-related engine code must carry a verified CR citation and description.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@crates/engine/src/parser/oracle_effect/tests.rs` around lines 32143 - 32155, Add the verified citation “CR 115.6: An effect can instruct a player to choose zero or more objects.” to the rules note in the test around the per-opponent target fanout, preserving the existing explanation and identifying the zero-target behavior governed by this rule.Sources: Coding guidelines, Path instructions
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@crates/engine/src/parser/oracle_effect/tests.rs`:
- Around line 32143-32155: Add the verified citation “CR 115.6: An effect can
instruct a player to choose zero or more objects.” to the rules note in the test
around the per-opponent target fanout, preserving the existing explanation and
identifying the zero-target behavior governed by this rule.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: 2e363025-90e1-4778-9c89-25db8c6e895b
📒 Files selected for processing (21)
crates/engine/src/game/ability_rw.rscrates/engine/src/game/ability_scan.rscrates/engine/src/game/ability_utils.rscrates/engine/src/game/cost_payability.rscrates/engine/src/game/coverage.rscrates/engine/src/game/effects/discard.rscrates/engine/src/game/effects/mod.rscrates/engine/src/game/filter.rscrates/engine/src/game/layers.rscrates/engine/src/game/quantity.rscrates/engine/src/game/targeting.rscrates/engine/src/game/trigger_matchers.rscrates/engine/src/parser/oracle_effect/conditions.rscrates/engine/src/parser/oracle_effect/mod.rscrates/engine/src/parser/oracle_effect/tests.rscrates/engine/src/parser/oracle_static/restriction.rscrates/engine/src/types/ability.rscrates/engine/src/types/events.rscrates/engine/tests/integration/issue_6091_grindstone.rscrates/engine/tests/integration/main.rscrates/mtgish-import/src/convert/condition.rs
🚧 Files skipped from review as they are similar to previous changes (19)
- crates/engine/src/game/layers.rs
- crates/engine/src/parser/oracle_effect/mod.rs
- crates/engine/src/types/ability.rs
- crates/engine/tests/integration/main.rs
- crates/engine/src/types/events.rs
- crates/mtgish-import/src/convert/condition.rs
- crates/engine/src/parser/oracle_static/restriction.rs
- crates/engine/src/game/effects/mod.rs
- crates/engine/src/game/cost_payability.rs
- crates/engine/src/game/effects/discard.rs
- crates/engine/tests/integration/issue_6091_grindstone.rs
- crates/engine/src/game/ability_scan.rs
- crates/engine/src/game/ability_utils.rs
- crates/engine/src/game/trigger_matchers.rs
- crates/engine/src/game/targeting.rs
- crates/engine/src/game/coverage.rs
- crates/engine/src/parser/oracle_effect/conditions.rs
- crates/engine/src/game/ability_rw.rs
- crates/engine/src/game/filter.rs
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
crates/engine/src/game/quantity.rs (1)
1928-1941: 🎯 Functional Correctness | 🟠 Major | ⚡ Quick winHandle nested negations containing
LastZoneChanged.
Not(And(LastZoneChanged, ...))andNot(Or(LastZoneChanged, ...))fall through to zone-only candidates, so off-battlefield ledger objects that fail the inner predicate are never evaluated. Build everyNotuniverse from its normal zone population plus the recursive inner universe, then filter; add a nested-negation regression.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@crates/engine/src/game/quantity.rs` around lines 1928 - 1941, Update the TargetFilter::Not handling in object_count_zone_object_ids so every negation candidate universe combines the normal zone population with the recursively computed universe for its inner filter before applying the negated predicate. Preserve the LastZoneChanged optimization while ensuring nested And/Or negations evaluate off-battlefield ledger objects, and add a regression test covering nested negations with LastZoneChanged.Sources: Coding guidelines, Path instructions
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@crates/engine/src/game/quantity.rs`:
- Around line 1928-1941: Update the TargetFilter::Not handling in
object_count_zone_object_ids so every negation candidate universe combines the
normal zone population with the recursively computed universe for its inner
filter before applying the negated predicate. Preserve the LastZoneChanged
optimization while ensuring nested And/Or negations evaluate off-battlefield
ledger objects, and add a regression test covering nested negations with
LastZoneChanged.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro Plus
Run ID: fc64de70-6f50-4dc1-9502-12f52be97458
📒 Files selected for processing (2)
crates/engine/src/game/filter.rscrates/engine/src/game/quantity.rs
💤 Files with no reviewable changes (1)
- crates/engine/src/game/filter.rs
matthewevans
left a comment
matthewevans
left a comment
There was a problem hiding this comment.
Changes requested — one candidate-universe case remains incorrect on 940a893ffbc92a4a726a676fd7619b171220cd23.
🔴 Blocker
[MED] Include the recursively derived inner population when evaluating a compound negation containing LastZoneChanged. Evidence: crates/engine/src/game/quantity.rs:1928-1941 handles only Not(LastZoneChanged) specially; Not(And(LastZoneChanged, Typed(...))) instead seeds only object_count_zone_object_ids, whose default is the battlefield at :1899-1909. matches_target_filter recognizes LastZoneChanged directly in crates/engine/src/game/filter.rs:2169-2172, so a changed off-battlefield object that fails the inner And is never a candidate for the outer Not.
Build every Not candidate universe as its normal zone population union the recursive inner universe, deduplicated before the existing full-filter match, and add a nested-negation regression with a nonmatching ledger object in a non-battlefield zone.
✅ Clean
The new recursive handling for And/Or resolves the previous non-compositional candidate-selection finding; the remaining defect is confined to the negated compound case.
Recommendation: request changes; repair the Not universe and re-review this head.
…ns (phase-rs#6091) Probe last_zone_changed_ids for nested ledger filters before applying the full compound predicate, reorder Painter fixture so the first mill is the blue/green pair, and assert trailing library cards remain when repeat stops. Co-authored-by: Cursor <cursoragent@cursor.com>
…hase-rs#6091) Derive object-count candidates compositionally (ledger seed for positive And, union for Or, complement for Not) instead of gating on the broad filter_contains_last_zone_changed helper. Co-authored-by: Cursor <cursoragent@cursor.com>
…rs#6091) Union branch candidate populations for every And/Or node before applying matches_target_filter, so And(Or(LastZoneChanged, Typed), Typed) includes off-battlefield ledger members. Co-authored-by: Cursor <cursoragent@cursor.com>
…6091) Build every Not candidate set as zone population union the recursive inner universe so Not(And(LastZoneChanged, Typed)) includes off-battlefield ledger members that fail the inner conjunction. Co-authored-by: Cursor <cursoragent@cursor.com>
a4bc523 to
c507333
Compare
matthewevans
left a comment
matthewevans
left a comment
There was a problem hiding this comment.
Approved on c5073336ddb573f3092d36740ef5d6085f1f3b2a.
The candidate-universe repair now unions a negation's normal zone population with its recursively derived inner population before evaluating the complete filter. The regression covers the required off-battlefield ledger member, and an independent adversarial review found no remaining current-head issue.
3 participants
Closes #6091
Shipped
TargetFilter::LastZoneChanged— resolution-local ledger filter mirroringLastRevealed, wired through filter/targeting/quantity/coverage/ability_rw paths;object_count_matching_idsshort-circuits tolast_zone_changed_ids.strip_milled_shared_quality_conditionalmapsif [N] cards that share a [quality] were milled this way, repeat this processtoRepeatContinuation::WhileConditionoverObjectCountBySharedQuality { LastZoneChanged, Max } >= N(no Unimplemented repeat sub-ability).condition_depends_on_zone_change_this_wayrecursesQuantityCheck/QuantityExprtrees forLastZoneChangedfilters (same intent asZoneChangedThisWaydeferral).Issue scope vs out of scope
LastZoneChangedbuilding blockVerification
cargo fmt --allclippy,test-engine,card-data(or directcargo testfallback)cargo coverage/cargo semantic-auditfor parser diffSummary by CodeRabbit
New Features
Bug Fixes
Tests
#6091Grindstone loop behavior.