feedback5: merge WE2 — fidelity (data / match / UI): summon hand counts from the tokens' hidden talents (麦哲伦 / 令 3, 白铁 2), 望's 棋子 on any tile, the 一会儿见！ marker no hand card, TRY_SEARCH_ALLY_SKILL → SKILL_RANGE + allies, 斩业星熊's normal attack phys, IS / RA-only modules refused (SO-A / SO-B / RA-A), 黑键 S2 at full SP with a free tile, 重构体 / 战术锚点 placement, 塑心's cap per trait, random grants draw 自选 stock, diyBanned shown, AI 托管 buys 自选, 谬因 S2 / 薇薇安娜 S3 area triggers, #148 regression test, tier*.js / diyRecord shims removed; golden: coop2-NORMAL-70-diy, diy-045 / 078 / 114 / 115 / 116 moved (WE2's own), the W4B moves kept

docs/DATA.md

@@ -193,10 +193,10 @@ Top level: `{ season, seasonName, modes, economy, lpCapPerRound, bossOvertimeAft
 | `bb`, `bbStr` | `{"atk":1,"base_attack_time":-0.3,"attack@trigger_time":14}` | kit input (DESIGN §5.6) |
 | `rangeId`, `rangeGrid` | `null` | skill range override |
 | `prefabId`, `overrideTokenKey` | | |
-| `trigger` | `{"rule":"DEFAULT","rawRule":"DEFAULT","customRangeGrid":null}` | auto-cast rule (the official 技能策略, PRTS 卫戍协议/帮助 §作战阶段 技能操作; §2.2). `rule` ∈ `DEFAULT` (basic strategy), `SKILL_RANGE` (a MANUAL skill with a 技能范围 of its own: `customRangeGrid` = its `rangeGrid`, `rawRule` `DEFAULT` — no official row), `ACTIVE_RANGE` (the owner's deliberate deviation of 2026-10-05: a MANUAL skill on the basic strategy — 深巡 S2's deviation included — or on the `SEARCH` row whose attack range while it runs strictly contains the operator's own range: `customRangeGrid` = that running range, `rawRule` the official row, `DEFAULT` / `SEARCH` / 深巡's `TAKE_DAMAGE`), `TAKE_DAMAGE` (every MANUAL 重装 skill but seven: 深巡 / 雷蛇 S2, 号角 S2 / S3 and 灰毫 S1 / S2 are `DEFAULT` with `rawRule` `TAKE_DAMAGE` — a deliberate deviation, `tools/build-data.mjs TRIGGER_DEVIATIONS`, DESIGN §21.29; 深巡 S2 then `ACTIVE_RANGE` on its 3-2 — and 余 S2 is `SKILL_RANGE` with `rawRule` `TAKE_DAMAGE` and `customRangeGrid` its x-1, DESIGN §22.10), `SP_FULL` (official `ALWAYS`: 执旗手 / 战术家 / 吟游者 MANUAL skills), `CUSTOM_RANGE` (official `CUSTOM_RANGE_SEARCH_ENEMY`, uses `customRangeGrid`), `SEARCH` (解放者 / 阵法术师 MANUAL skills, 安洁莉娜 S2/S3 — but those whose running range is larger, `ACTIVE_RANGE`: 薄绿 S1, 蜜蜡 S1, 卡涅利安 S3, 玛恩纳 S2, 安洁莉娜 S3), `MLYSS_WTRMAN` (缪尔赛思), `GDGLOW_SKILL_2` (荒芜拉普兰德, 纯烬艾雅法拉 S3: "全场存在可选目标时释放技能"). |
+| `trigger` | `{"rule":"DEFAULT","rawRule":"DEFAULT","customRangeGrid":null}` | auto-cast rule (the official 技能策略, PRTS 卫戍协议/帮助 §作战阶段 技能操作; §2.2). `rule` ∈ `DEFAULT` (basic strategy), `SKILL_RANGE` (a MANUAL skill with a 技能范围 of its own: `customRangeGrid` = its `rangeGrid`, `rawRule` `DEFAULT` — no official row), `ACTIVE_RANGE` (the owner's deliberate deviation of 2026-10-05: a MANUAL skill on the basic strategy — 深巡 S2's deviation included — or on the `SEARCH` row whose attack range while it runs strictly contains the operator's own range: `customRangeGrid` = that running range, `rawRule` the official row, `DEFAULT` / `SEARCH` / 深巡's `TAKE_DAMAGE`), `TAKE_DAMAGE` (every MANUAL 重装 skill but seven: 深巡 / 雷蛇 S2, 号角 S2 / S3 and 灰毫 S1 / S2 are `DEFAULT` with `rawRule` `TAKE_DAMAGE` — a deliberate deviation, `tools/build-data.mjs TRIGGER_DEVIATIONS`, DESIGN §21.29; 深巡 S2 then `ACTIVE_RANGE` on its 3-2 — and 余 S2 is `SKILL_RANGE` with `rawRule` `TAKE_DAMAGE` and `customRangeGrid` its x-1, DESIGN §22.10), `SP_FULL` (official `ALWAYS`: 执旗手 / 战术家 / 吟游者 MANUAL skills), `CUSTOM_RANGE` (official `CUSTOM_RANGE_SEARCH_ENEMY`, uses `customRangeGrid`), `SEARCH` (解放者 / 阵法术师 MANUAL skills, 安洁莉娜 S2/S3 — but those whose running range is larger, `ACTIVE_RANGE`: 薄绿 S1, 蜜蜡 S1, 卡涅利安 S3, 玛恩纳 S2, 安洁莉娜 S3), `MLYSS_WTRMAN` (缪尔赛思), `GDGLOW_SKILL_2` (荒芜拉普兰德, 纯烬艾雅法拉 S3: "全场存在可选目标时释放技能"). `allies: true` (only then present): an ally row the engine plays as one of its rules on an injured, healable ally of `customRangeGrid` — 黍 S3 (data/backups.json): official `TRY_SEARCH_ALLY_SKILL` ("技能范围内存在可治疗的我方单位时释放技能") → `SKILL_RANGE` on its x-2 (`tools/build-data.mjs TRIGGER_ALLY_RULES`). |
 
 ### 2.1 Combat classification heuristic (`dmgType` / `attackKind` / `projectile` / `canHitFly`)
-- `dmgType`: MEDIC (except `incantationmedic`) and `bard` → `heal`; trait text containing 法术伤害 or profession CASTER → `arts`; else `phys`.
+- `dmgType`: MEDIC (except `incantationmedic`) and `bard` → `heal`; trait text containing 法术伤害 or profession CASTER → `arts` — but a trait whose 法术伤害 comes only with a running skill ("技能开启时普通攻击会造成法术伤害": 驭法铁卫, 斩业星熊) keeps the normal attack's `phys` (display / the bot; the kit switches to arts while a skill runs; 0.2.0); else `phys`.
 - `attackKind`: `bard`, `phalanx`, `librator` → `none` (no normal attack); heal → `heal`; position RANGED or melee sub-professions with a ranged normal attack (`lord`, `fortress`, `shotprotector`, `agent`, `hookmaster`) → `ranged`; else `melee`.
 - `canHitFly`: ranged attackers unless the trait says 地面敌人 (投掷手) or the sub-profession is `fortress` (要塞: 灰毫, 号角 — DESIGN §22.13); `skywalker` (蒂比) true.
 - These are defaults for the generic engine; kits may override.
@@ -480,15 +480,16 @@ Glyph legend (`rows`):
 | Field | Example (`token_10028_vigil_wolf`) | Meaning |
 |---|---|---|
 | `tokenId`, `kind`, `name`, `appellation`, `desc`, `descRaw` | …, `"summon"`, `"狼群"` | |
-| `profession`, `subProfessionId`, `position` | `"TOKEN"`, `"notchar1"`, `"MELEE"` | |
-| `displayType`, `placeable` | `"DEFAULT"`, `true` | `shopStateTokenDict` DEFAULT / HIDDEN (battle-only) / `null` (not listed). `placeable` (a prep hand piece) = a manually deployable summon (PRTS 卫戍协议/帮助 "可手动部署的附属召唤物…加入手牌区"; user playtest #6): not HIDDEN and made by an owner's talent or skill — 医疗探机 (赫默 S2), 诅咒娃娃 (巫恋 S2), 海嗣, 狼群, 流形 and 爬行号·防护单元 (凯瑟琳's talent device — the only pool summon missing from `shopStateTokenDict`, read as shown: placed by hand in the base game, by the friend's report, and confirmed by the user after playtest #6, DESIGN §20); 投递坐标 (HIDDEN) is not. In battle a skill's summon deploys once at the battle start, then on its tile each time the skill gives one (SIM.md, token pieces) |
-| `ownerRange` | `true` | the token text reads "只能部署在召唤者攻击范围内" (`desc`; the tacticians' 援军 — 狼群, 流形; PRTS 狼群 特性): its hand piece may only stand on a tile of its owner's attack range (server/match/board.js `ownerRangeKeys`, `PlayerState._legal`, the client's `gameLogic.summonRange`; player report #9 after 0.1.0). `false` for every other token |
+| `profession`, `subProfessionId`, `position` | `"TOKEN"`, `"notchar1"`, `"MELEE"` | `position` = the token row's, except where PRTS records the client's row as wrong (`tools/build-data.mjs TOKEN_POSITION_CORRECTIONS`): 望's 棋子 `ALL` (PRTS 棋子 部署位置 "全部位", 备注 "游戏内召唤物信息与实际不符（显示为仅部署在近战位）") — the prep's placement class (board.js `positionClass`) |
+| `displayType`, `placeable` | `"DEFAULT"`, `true` | `shopStateTokenDict` DEFAULT / HIDDEN (battle-only) / `null` (not listed). `placeable` (a prep hand piece) = a manually deployable summon (PRTS 卫戍协议/帮助 "可手动部署的附属召唤物…加入手牌区"; user playtest #6): not HIDDEN and made by an owner's talent or skill — 医疗探机 (赫默 S2), 诅咒娃娃 (巫恋 S2), 海嗣, 狼群, 流形 and 爬行号·防护单元 (凯瑟琳's talent device — the only pool summon missing from `shopStateTokenDict`, read as shown: placed by hand in the base game, by the friend's report, and confirmed by the user after playtest #6, DESIGN §20); 投递坐标 (HIDDEN) is not; nor is a summon no owner shows (its `display` source, the owner's displayTokenDict — a skill's own object: every such summon is HIDDEN but 予愿安洁莉娜 S3's “一会儿见！”, which the shop state does not list; PRTS 予愿安洁莉娜 S3 备注, 0.2.0). In battle a skill's summon deploys once at the battle start, then on its tile each time the skill gives one (SIM.md, token pieces) |
+| `ownerRange` | `true` | the token text reads "只能部署在召唤者攻击范围内" (`desc`; the tacticians' 援军 — 狼群, 流形; PRTS 狼群 特性) — or, data/backups.json, an owner's talent naming the token reads "可以在攻击范围内(的地面)部署 / 使用…" (Mon3tr's 重构体; 莱伊's 沙地兽 says both): its hand piece may only stand on a tile of its owner's attack range (server/match/board.js `ownerRangeKeys`, `PlayerState._legal`, the client's `gameLogic.summonRange`; player report #9 after 0.1.0). `false` for every other token |
+| `ownerRangeOutside`, `rangedTilesOnly` | `true` (present only then) | data/backups.json: the token text reads "部署在…攻击范围外" / "仅可以部署在…远程位" — 凯尔希·思衡托's 战术锚点 "仅可以部署在凯尔希·思衡托攻击范围外的远程位" (PRTS 战术锚点 特性): its hand piece may only stand outside its owner's attack range (`PlayerState.summonExcluded`, the client's `gameLogic.summonExcluded`) and on a ranged (高台) tile (board.js placement class `high`; the mode's "所有行动内远程干员可部署在近战位" is an operators' rule [ASSUMED]) (0.2.0) |
 | `owners[]` | `["chess_char_3_19_a","chess_char_3_19_b"]` | |
 | `stats`, `rangeGrid`, `dmgType`, `attackKind`, `projectile`, `canHitFly` | first owner's values | defaults |
 | `skill` | `{"skillId":"sktok_vigil_wolf_3","bb":{…}}` | default token skill (same slot as the owner's skill) |
-| `deployLimit`, `count` | `1`, `1` | `count` = copies sent to the hand / spawned (talent/skill `cnt`); `null` ⇒ use `deployLimit` |
+| `deployLimit`, `count` | `1`, `1` | `deployLimit` = the first owner's `stats.deployLimit`. `count` = copies sent to the hand / spawned (talent/skill `cnt`); `null` ⇒ use `deployLimit` |
 | `abnormal[]` | `["healFree"]` | abnormal effects the summon holds from the start, no official table carries them — `tools/build-data.mjs TOKEN_ABNORMAL` from the PRTS summon pages (user playtest #6 item 18): `healFree` = 禁疗 (“小自在”, “耀阳”, 斯卡蒂的海嗣, 沙之碑, 流形, 狼群, 迷迭香的战术装备, 黄金盟誓, 保护目标（冻结状态）), `isolated` = 孤立 "无法被同阵营选中" (“炎佑”, 从不混淆的方向); `[]` otherwise. The sim sets `noHeal` / `isolated` (docs/SIM.md §3) |
-| `variants[ownerChessId]` | `{"phase":2,"level":1,"stats":{…},"immunities":{…},"rangeGrid":…,"trait":{…},"dmgType":…,"skill":{full skill record},"talents":[…],"count":1,"sources":["talent","display"]}` | stats at the owner's phase/level (clamped to the token's max level) + golden module `tokenAttributeBlackboard`; the owner's module parts flagged `isToken` upgrade the variant's `trait` (+`moduleDesc`) and `talents` (伺夜's wolves, 缪尔赛思's 流形 `scale` 1, 浊心斯卡蒂's 海嗣 30 s, “耀阳” `atk_scale` 1.15). `sources` ⊆ `talent`/`skill`/`display`: how the owner produces it (`display` only = listed on the character but unused by its default skill/talents, e.g. 迷迭香 S2, 凛御银灰 eagle1/3). `count` = copies from a talent `cnt` or the default skill's `cnt` when that skill overrides this token; `null` ⇒ use `deployLimit` |
+| `variants[ownerChessId]` | `{"phase":2,"level":1,"stats":{…},"immunities":{…},"rangeGrid":…,"trait":{…},"dmgType":…,"skill":{full skill record},"talents":[…],"count":1,"sources":["talent","display"]}` | stats at the owner's phase/level (clamped to the token's max level) + golden module `tokenAttributeBlackboard` + the token's own talent additions to `deployLimit` / `deckStack` (blackboard `max_deploy_count` / `max_deck_stack_cnt` — the hidden "TOKEN数" talent of 麦哲伦's / 令's summons and 白铁's devices, 夜莺's 幻影; a module token part of the same talent replaces it: `tools/build-data.mjs tokenTalentDeckBonus`, 0.2.0 — no tokens.json summon has one; PRTS 幻影 备注 "最大可部署数量为3", the owners' "最多同时部署3个"); the owner's module parts flagged `isToken` upgrade the variant's `trait` (+`moduleDesc`) and `talents` (伺夜's wolves, 缪尔赛思's 流形 `scale` 1, 浊心斯卡蒂's 海嗣 30 s, “耀阳” `atk_scale` 1.15). `sources` ⊆ `talent`/`skill`/`display`: how the owner produces it (`display` only = listed on the character but unused by its default skill/talents, e.g. 迷迭香 S2, 凛御银灰 eagle1/3). `count` = copies from a talent `cnt` or the default skill's `cnt` when that skill overrides this token; `null` ⇒ use `deployLimit` |
 | `variants[o].bySkill[i]` | `{"skill":{…},"count":1,"sources":["talent","display"]}` | owner loadout with the non-default skill index `i` (one entry per other selectable owner skill): the token skill of that slot (伺夜's wolves, 缪尔赛思's 流形, 凛御银灰's eagles…), the count and how the chess then produces it (`sources` may be `[]`: 风丸 S1 makes no 纸偶; 赫默 / 巫恋 S1 only `display` ⇒ no hand piece). The sim resolves them for an owner loadout: `simdata getToken(id, ownerChessId, loadout)` → `def.sources` / `def.count` |
 | `variants[o].byModule[m]` | `{"stats":{…},"immunities":{…},"trait":{…},"talents":[…]}` | golden owner with another module `m` or `'none'`: the token as that module makes it (module `tokenAttributeBlackboard`, `isToken` trait/talent parts) |
 | `assets` | `{"avatar":"token_10028_vigil_wolf","spine":"token_10028_vigil_wolf"}` | |
@@ -669,11 +670,12 @@ derived bonds, the operator's form at the slot's status with that skill and modu
 `diyFor` = the slot's base id —, `diyPool(tier, { data, kitted })` the legal picks of a tier (prototypes, then the owned
 pool; with `kitted`, only operators with a kit: server/sim/content/kits/index.js `KITTED_CHARS`) and
 `validateDiyPicks(picks, { data, kitted })` a roster (a prototype may fill a tier-5 and a tier-6 slot, an owned operator
-one slot, the picks of a tier differ, no 集成战略 module — `isDiyModule`: the ISW-A modules of 凯尔希, 傀影, 菲亚梅塔, 提丰,
-艾丽妮 and 霍尔海雅 are never a player's choice [ASSUMED], the owner's decision of 2026-10-05, while the record and the sim
-still compose them for the kits' tests). **In battle** a PlayerBattleInput entry of a DIY slot carries `diy` (the pick) and
+one slot, the picks of a tier differ, no module of another game mode — `isDiyModule` / `DIY_EXCLUDED_MODULE_TYPE`: the
+集成战略 modules ISW-A (凯尔希, 傀影, 菲亚梅塔, 提丰, 艾丽妮, 霍尔海雅) and SO-A / SO-B (电弧, 机械师 — "在【岁的界园志异】中",
+"在【沉沦者的黑流树海】中") and the 生息演算 module RA-A (森蚺) are never a player's choice [ASSUMED], the owner's decision of
+2026-10-05 for ISW-A and the same reason for SO / RA, while the record and the sim still compose them for the kits' tests). **In battle** a PlayerBattleInput entry of a DIY slot carries `diy` (the pick) and
 is fielded as `getChess(slotId, { diy })` (docs/SIM.md §12); its kit is `KITS[charId]` (kits/README.md "How to add an
-operator (自选)"). (`shared/standIn.js diyRecord(slot, charId, backups, sel)` is the older prototype-only form.)
+operator (自选)").
 
 `diy`:
 

docs/DESIGN.md

@@ -155,7 +155,7 @@ Ownership rule for parallel agents: **only edit files assigned to you**; if you
   - **Partner display** cols 11–18 of rows 9–12 (the unite field uses them).
   - **Boss field**: rows 1–5; left half cols 2–10, right half cols 10–18.
   - Enemy preview pen rows 14–18 × cols 7–13 (row 16 empty): during prep the next round's enemies idle there (upper-gate enemies rows 17–18, lower-gate rows 14–15, ≤ 50 models, spawn-time order) — research 08 §4 / 09 §2.
-- Tile semantics come from `data/stages.json` legend: height (LOW/HIGH), buildable (ALL/MELEE/RANGED/NONE — the **effective** deploy type: the 深水区 `tile_deepsea` refuses deployment, NONE with the level's `buildableType` ALL kept, PRTS 深水区 地形信息 "拒绝部署（待补充）"; an active 特制水上平台 makes its tile deployable in the prep deploy map only, §21.3), ground-passable, fly-only, special terrain (mire, smog, deepsea, infection). The fenced tiles (围墙 `tile_fence_bound` / 围栏 `tile_fence`, legend `b`: LOW, buildable ALL, passable to flyers only) take units, which attack normally from there but block no ground enemy (PRTS 地形机制, §21.23). Melee chess may stand only on LOW tiles with buildable ALL/MELEE — except a melee chess whose trait reads 「可以放置于远程位」 (the 钩索师 / 推击手 branch trait: 歌蕾蒂娅, 崖心, 见行者, normal and elite, with any module or none), which may use the ranged tiles too (`shared/highGround.js`; the owner's decision of 2026-10-05, following PRTS — it reverses the 2026-10-04 one that allowed only elite 歌蕾蒂娅 with HOK-Y; on a 高台 it attacks and blocks nothing); ranged chess on ALL/RANGED **and** on LOW ALL/MELEE tiles ("所有行动内远程干员可部署在近战位"). Tokens follow their own `position`; a summon marked `ownerRange` (狼群, 流形: "只能部署在召唤者攻击范围内") goes only on a tile of its owner's attack range — the loadout grid rotated by the owner's facing around its tile (`PlayerState.summonRange`, §21.3).
+- Tile semantics come from `data/stages.json` legend: height (LOW/HIGH), buildable (ALL/MELEE/RANGED/NONE — the **effective** deploy type: the 深水区 `tile_deepsea` refuses deployment, NONE with the level's `buildableType` ALL kept, PRTS 深水区 地形信息 "拒绝部署（待补充）"; an active 特制水上平台 makes its tile deployable in the prep deploy map only, §21.3), ground-passable, fly-only, special terrain (mire, smog, deepsea, infection). The fenced tiles (围墙 `tile_fence_bound` / 围栏 `tile_fence`, legend `b`: LOW, buildable ALL, passable to flyers only) take units, which attack normally from there but block no ground enemy (PRTS 地形机制, §21.23). Melee chess may stand only on LOW tiles with buildable ALL/MELEE — except a melee chess whose trait reads 「可以放置于远程位」 (the 钩索师 / 推击手 branch trait: 歌蕾蒂娅, 崖心, 见行者, normal and elite, with any module or none), which may use the ranged tiles too (`shared/highGround.js`; the owner's decision of 2026-10-05, following PRTS — it reverses the 2026-10-04 one that allowed only elite 歌蕾蒂娅 with HOK-Y; on a 高台 it attacks and blocks nothing); ranged chess on ALL/RANGED **and** on LOW ALL/MELEE tiles ("所有行动内远程干员可部署在近战位"). Tokens follow their own `position`; a summon marked `ownerRange` (狼群, 流形: "只能部署在召唤者攻击范围内"; Mon3tr's 重构体 by her talent) goes only on a tile of its owner's attack range — the loadout grid rotated by the owner's facing around its tile (`PlayerState.summonRange`, §21.3) —, one marked `ownerRangeOutside` / `rangedTilesOnly` (凯尔希·思衡托's 战术锚点: "仅可以部署在凯尔希·思衡托攻击范围外的远程位") only on a 高台 outside it (`summonExcluded`, placement class `high`; 0.2.0).
 - **Facing (corrected, see research 09 §1.2):** like standard Arknights, every board piece has a direction `dir ∈ UP|RIGHT|DOWN|LEFT` chosen with the 4-direction deploy wheel after dropping it on a tile (also re-orientable in place); default `RIGHT`; persists across rounds. Range grid entries are `[dRow, dCol]` relative to facing RIGHT and are rotated: RIGHT `(dr,dc)`, UP `(dc,−dr)`, LEFT `(−dr,−dc)`, DOWN `(−dc,dr)` (row 0 = bottom); `rangeExtend` applies along +dCol before rotating — to a running skill's range too, unless that skill ignores 攻击距离 (`targeting.noRangeExtend`, 信仰搅拌机 S3, §21.16). The right-side Final Assault player is mirrored col `c→20−c` with RIGHT↔LEFT (UP/DOWN unchanged).
 - **Range test:** an enemy is inside a grid range if the tile containing it (`round(y), round(x)`) is one of the range tiles; a huge enemy (data `hitArea`: 巨型单位, a 4.95 × 2.95 rectangle moved 1.0 up) if any tile its hit rectangle overlaps is one (PRTS 作战机制 "巨型BOSS单位的每一个占据的格子都可以让其本身通过格子判定"; `sim/body.js`, §19.4). Radius ranges (enemies, auras, AoE) use Euclidean distance in tiles — to a huge enemy's rectangle [ASSUMED] — except splash around a struck target, a 中点判定 on positions (PRTS 作战机制 "中点判定…案例：阻挡，酒神1天赋的1.3溅射半径"). A ranged enemy's normal attack takes an ally whose collider (radius 0.25, PRTS 作战机制 §碰撞体积 "我方干员碰撞体积基本均为以0.25格为半径的圆形") touches its range circle: centre distance ≤ `rangeRadius` + 0.25 (`constants.js ALLY_COLLIDER_RADIUS`, `ai.js enemyAttack`; §20.4).
 - **Fields at runtime:** a `Battle` receives a **field rect** (rows/cols subset) and the full stage grid. Normal battles use rows 9–12 × cols 0–10; unite uses rows 9–12 × cols 0–20 — on its own map, the escaped template's (stages.json `kind: 'unite'`, `unite.js uniteStageId`; GitHub #41), not the round's stage; boss uses rows 0–5 × cols 0–20 (solo boss uses the left half only). Pathfinding never leaves the rect.
@@ -312,7 +312,7 @@ Duration end cleans the window and emits `skillEnd`; it leaves zero charges and
 Redeployment opens a new full window. Permanent passives retain `passive`; first-kill recasts of 缄默德克萨斯 explicitly
 restart a full window. Special timed kits and their effect rules are described in SIM §7.2.
 
-Auto-trigger rules (`skillTrigger.rule` in data — the official 技能策略, PRTS 卫戍协议/帮助 §作战阶段 技能操作; §20.2): `DEFAULT` (SP ready AND about to attack/heal AND an enemy/injured ally inside the **initial** range, or an enemy the unit blocks; with `trigger.allies` + `hpAtMost` an ally of the skill grid at or below that HP ratio — 塞雷娅 S1 急救, whose cast replaces that attack and is withdrawn with its charge if the ally recovers first), `SKILL_RANGE` (a MANUAL skill with a 技能范围 of its own, not an attack-range change: any living enemy, stealthed ones included, on the skill range, checked every tick — "仅在技能范围内存在敌人（无视其不可选中）时释放技能"; 13 skills / 26 records by the official rule, 14 / 28 in the data with 余 S2's deviation, §22.10), `ACTIVE_RANGE` (the owner's deliberate deviation of 2026-10-05, 0.2.0: a MANUAL skill on the basic strategy — or, by the owner's further decisions of the same day, on the `SEARCH` row, and 深巡 S2 on top of its §21.29 DEFAULT — whose attack range while it runs strictly contains the operator's own range — its rangeId grid, or the own range grown by `ability_range_forward_extend` — checks the DEFAULT condition on that running range every tick, no attack needed; `customRangeGrid` = the running range, `rawRule` the official row (DEFAULT, SEARCH, 深巡's TAKE_DAMAGE); 39 skills / 78 records, of them 薄绿 S1, 蜜蜡 S1, 卡涅利安 S3, 玛恩纳 S2 and 安洁莉娜 S3 from SEARCH; 烛煌 S2 / S3, whose ranges do not contain her 3-1, keep DEFAULT), `TAKE_DAMAGE` (on taking damage — any damage, 无来源 included, never a 流失; every MANUAL 重装 skill, §21.12 — but the six of the deliberate deviation, §21.29: 深巡 / 雷蛇 S2, 号角 S2 / S3 and 灰毫 S1 / S2 are `DEFAULT`, `rawRule` keeping the official TAKE_DAMAGE — 深巡 S2 then `ACTIVE_RANGE` on its 3-2; and 余 S2, `SKILL_RANGE` on its x-1 (§22.10); the 重装 of data/backups.json — the 补位 stand-ins 预备干员-重装 / Mechanist and every 自选 重装 — cast with an enemy in range, `DEFAULT` (or `ACTIVE_RANGE` when the skill's running range is larger), by the owner's decisions of 2026-10-05), `SP_FULL` (immediately — 执旗手 / 战术家 / 吟游者 MANUAL skills, AUTO DP skills such as 焰尾 S1, 凛御银灰 S1 (伺夜 S1 / S2 too, but only while his pack is on the field — PRTS 备注 「仅场上存在狼群时可触发技能」, the kit's own cast; the owner's decision of 2026-10-05 for S1; S1 also while the pack sits in its 战术点形态, which the cast ends — S2 waits for it to come back [ASSUMED]), and, by their kits, AUTO skills whose effects act on allies only: 引星棘刺 S1, 浊心斯卡蒂 S2, 纯烬艾雅法拉 S1 — the owner's decision of 2026-10-05 for the last), `CUSTOM_RANGE` (enemy inside the custom grid), `SEARCH` (an enemy inside the initial range, checked every tick — no attack needed; 解放者 / 阵法术师 MANUAL skills and 安洁莉娜 S2, those without a larger running range), `GDGLOW_SKILL_2` (a valid target anywhere on the field: 荒芜拉普兰德, 纯烬艾雅法拉 S3), special ids. The class rows cover **every MANUAL skill** of the class and never an AUTO skill (AUTO skills keep their own rule — an inference: PRTS names whole classes; the data's `skillIndex 0` / `-1` sentinel argues the other way, §20.2). **Operation cooldown**: the engine auto-casts a MANUAL skill no sooner than `AUTO_OP_COOLDOWN` (3 s) after its previous cast and after the unit's battle-start deployment ("自动操作具有3s冷却，在完成一次操作或作战开始时部署的单位将进入冷却"; `Battle._deploy` initial, `battle.flags.startOpCooldown`); kits with an automatic cast of their own check `skill.opCooling`; a pending "next attack" never takes a second charge. Permanent passive skills are always on; finite deployment effects use the duration lifecycle above.
+Auto-trigger rules (`skillTrigger.rule` in data — the official 技能策略, PRTS 卫戍协议/帮助 §作战阶段 技能操作; §20.2): `DEFAULT` (SP ready AND about to attack/heal AND an enemy/injured ally inside the **initial** range, or an enemy the unit blocks; with `trigger.allies` + `hpAtMost` an ally of the skill grid at or below that HP ratio — 塞雷娅 S1 急救, whose cast replaces that attack and is withdrawn with its charge if the ally recovers first), `SKILL_RANGE` (a MANUAL skill with a 技能范围 of its own, not an attack-range change: any living enemy, stealthed ones included, on the skill range, checked every tick — "仅在技能范围内存在敌人（无视其不可选中）时释放技能"; 13 skills / 26 records by the official rule, 14 / 28 in the data with 余 S2's deviation, §22.10), `ACTIVE_RANGE` (the owner's deliberate deviation of 2026-10-05, 0.2.0: a MANUAL skill on the basic strategy — or, by the owner's further decisions of the same day, on the `SEARCH` row, and 深巡 S2 on top of its §21.29 DEFAULT — whose attack range while it runs strictly contains the operator's own range — its rangeId grid, or the own range grown by `ability_range_forward_extend` — checks the DEFAULT condition on that running range every tick, no attack needed; `customRangeGrid` = the running range, `rawRule` the official row (DEFAULT, SEARCH, 深巡's TAKE_DAMAGE); 39 skills / 78 records, of them 薄绿 S1, 蜜蜡 S1, 卡涅利安 S3, 玛恩纳 S2 and 安洁莉娜 S3 from SEARCH; 烛煌 S2 / S3, whose ranges do not contain her 3-1, keep DEFAULT), `TAKE_DAMAGE` (on taking damage — any damage, 无来源 included, never a 流失; every MANUAL 重装 skill, §21.12 — but the six of the deliberate deviation, §21.29: 深巡 / 雷蛇 S2, 号角 S2 / S3 and 灰毫 S1 / S2 are `DEFAULT`, `rawRule` keeping the official TAKE_DAMAGE — 深巡 S2 then `ACTIVE_RANGE` on its 3-2; and 余 S2, `SKILL_RANGE` on its x-1 (§22.10); the 重装 of data/backups.json — the 补位 stand-ins 预备干员-重装 / Mechanist and every 自选 重装 — cast with an enemy in range, `DEFAULT` (or `ACTIVE_RANGE` when the skill's running range is larger), by the owner's decisions of 2026-10-05), `SP_FULL` (immediately — 执旗手 / 战术家 / 吟游者 MANUAL skills, AUTO DP skills such as 焰尾 S1, 凛御银灰 S1 (伺夜 S1 / S2 too, but only while his pack is on the field — PRTS 备注 「仅场上存在狼群时可触发技能」, the kit's own cast; the owner's decision of 2026-10-05 for S1; S1 also while the pack sits in its 战术点形态, which the cast ends — S2 waits for it to come back [ASSUMED]; 黑键 S2 荒芜回响 likewise only while one placeable tile of his range is free, no enemy needed — PRTS 备注 「攻击范围内不存在可部署位时，技能不会被触发」, its kit's cast, 0.2.0), and, by their kits, AUTO skills whose effects act on allies only: 引星棘刺 S1, 浊心斯卡蒂 S2, 纯烬艾雅法拉 S1 — the owner's decision of 2026-10-05 for the last), `CUSTOM_RANGE` (enemy inside the custom grid), `SEARCH` (an enemy inside the initial range, checked every tick — no attack needed; 解放者 / 阵法术师 MANUAL skills and 安洁莉娜 S2, those without a larger running range), `GDGLOW_SKILL_2` (a valid target anywhere on the field: 荒芜拉普兰德, 纯烬艾雅法拉 S3), special ids. The class rows cover **every MANUAL skill** of the class and never an AUTO skill (AUTO skills keep their own rule — an inference: PRTS names whole classes; the data's `skillIndex 0` / `-1` sentinel argues the other way, §20.2). **Operation cooldown**: the engine auto-casts a MANUAL skill no sooner than `AUTO_OP_COOLDOWN` (3 s) after its previous cast and after the unit's battle-start deployment ("自动操作具有3s冷却，在完成一次操作或作战开始时部署的单位将进入冷却"; `Battle._deploy` initial, `battle.flags.startOpCooldown`); kits with an automatic cast of their own check `skill.opCooling`; a pending "next attack" never takes a second charge. Permanent passive skills are always on; finite deployment effects use the duration lifecycle above.
 
 **SkillSpec** (authored per chess in `sim/content/kits/tierN.js`; values come from the chess's skill blackboard at its level — normal Lv4, elite Lv7 — so a spec is a *function of the blackboard*):
 ```js
@@ -418,7 +418,7 @@ Per match: pick stage (weighted among the mode's `config.modes[m].stages`, weigh
 
 ### 6.6 AI players (bot.js)
 
-Deterministic-ish heuristic player used for (a) AI teammates, (b) auto-play for disconnected humans (only auto-ready + auto-picks, not shopping, unless "AI 托管" is toggled), (c) tests. Strategy (§21.6): pick a band (weighted by starting LP; never one built around a bond the mode switches off — `gd.bandBondIds`, §21.26); each prep: take offers, sell dead bench weight, fill the board, complete affordable merges, level on the curve, then buy only merge progress / lineup upgrades worth more than the refreshes their price would buy (shop odds of completing held pairs), freeze for an unaffordable third copy (坎诺特 keeps 5 funds back); build around a committed focus core bond (a teammate's main bond on its strip counts against it; bonds the mode switches off never) + a second bond; value dealers by DPS vs the round's DEF / RES (an attack on every enemy in range counts double — 阵法术师 / 轰击术师), with the range the unit is deployed with; place by the exposure model + rehearsal on the server's deploy map (no 深水区; a tactician's 援军 within `PlayerState.summonRange`; a melee chess whose trait reads 「可以放置于远程位」 (钩索师 / 推击手) on a 高台 whose range covers the enemy road, else on the ground, counted as a blocker in the lineup either way — §3; `g.move` judges legality); items by effect (META §1.5: 突变细胞 on the least valuable normal single below 6阶, a cell left in temp gets a hand slot made for it, the operator its transformation gains is deployed by the next prep's lineup step like any owned unit — AI 托管 too; the buy loop's bench shed never sells a piece gained since the bot's last prep, §21.1); 机变 bounties by expected payout − expected LP loss over the offered cards; resolve temp — on a human seat under AI 托管 never by destroying an item while a bench operator can be sold for the slot —; ready. A bot's whole prep — shop decisions and layout planning (`botPrepBeginSteps`, 25–70 ms late in a 4-bot match), the layout rehearsal and `botPrepEndSteps` — runs in wall-clock slices of `botSliceMs` (8 ms) per scheduler callback on a real host (step generators that yield between whole actions, never with a transient board; the same actions in the same order, so decisions are unchanged; at once in virtual time).
+Deterministic-ish heuristic player used for (a) AI teammates, (b) auto-play for disconnected humans (only auto-ready + auto-picks, not shopping, unless "AI 托管" is toggled), (c) tests. Strategy (§21.6): pick a band (weighted by starting LP; never one built around a bond the mode switches off — `gd.bandBondIds`, §21.26); each prep: take offers, sell dead bench weight, fill the board, complete affordable merges, level on the curve, then buy only merge progress / lineup upgrades worth more than the refreshes their price would buy (shop odds of completing held pairs), freeze for an unaffordable third copy (坎诺特 keeps 5 funds back); build around a committed focus core bond (a teammate's main bond on its strip counts against it; bonds the mode switches off never) + a second bond; value dealers by DPS vs the round's DEF / RES (an attack on every enemy in range counts double — 阵法术师 / 轰击术师), with the range the unit is deployed with; place by the exposure model + rehearsal on the server's deploy map (no 深水区; a tactician's 援军 within `PlayerState.summonRange`; a melee chess whose trait reads 「可以放置于远程位」 (钩索师 / 推击手) on a 高台 whose range covers the enemy road, else on the ground, counted as a blocker in the lineup either way — §3; `g.move` judges legality); items by effect (META §1.5: 突变细胞 on the least valuable normal single below 6阶, a cell left in temp gets a hand slot made for it, the operator its transformation gains is deployed by the next prep's lineup step like any owned unit — AI 托管 too; the buy loop's bench shed never sells a piece gained since the bot's last prep, §21.1); 机变 bounties by expected payout − expected LP loss over the offered cards; resolve temp — on a human seat under AI 托管 never by destroying an item while a bench operator can be sold for the slot —; ready. A bot's whole prep — shop decisions and layout planning (`botPrepBeginSteps`, 25–70 ms late in a 4-bot match), the layout rehearsal and `botPrepEndSteps` — runs in wall-clock slices of `botSliceMs` (8 ms) per scheduler callback on a real host (step generators that yield between whole actions, never with a transient board; the same actions in the same order, so decisions are unchanged; at once in virtual time). Under AI 托管 a human's own 自选 pieces score `DIY_PIECE_BONUS` (12) more in the shop / reward choice and the 调度中心 is levelled one round earlier for the step that opens a slotted tier (`levelUp`, `diyOpensAt`; 0.2.0 — bots field no 自选 piece).
 
 ---
 
@@ -441,7 +441,7 @@ Each domain file `server/sim/content/{tokens,bonds,garrisons,items,bands,enemies
 Transport: one WebSocket per tab at `/ws`, JSON text frames `{ t: '<type>', ...payload }`. Client requests may carry `rid` (request id); the server's direct reply echoes `rid` (`ok` or `error`). Server pushes have no `rid`. Max frame 64 KB inbound; rate limit 40 msgs/s per connection (excess dropped with `error RATE`).
 
 ### 8.1 Session & lobby
-C→S: `hello {name, token?, version}` · `room.create {mode:'solo'|'coop', difficulty}` · `room.join {code}` · `room.leave` · `room.ready {ready}` · `room.setDifficulty {difficulty}` (host) · `room.addBot` / `room.removeBot {seat}` (host) · `room.kick {seat, playerId}` (host, before the match: another human leaves the room and gets `room.closed {reason:'kicked'}`; may join again; `playerId` = the player the host confirmed, a seat that changed hands meanwhile → `BAD_TARGET`) · `room.start` (host) · `room.loadout {entries}` (§16: any time in the lobby / room and during INFO_CHECK, then `WRONG_PHASE`; heavy rate-limit bucket; the match exposes it as `m.private.loadout`) · `room.ownership {notOwned}` (0.2.0 补位, the 干员持有 tab: the base chess ids marked as not owned — ≤ 160 ids, kept leniently: anything but a droppable NORMAL chess is dropped; stored on the session and the seat, a match takes the seat's list when it starts and never changes it — during a match `ROOM_STARTED` 'stored for the next match'; heavy bucket; the match exposes it as `m.private.standIns`) · `room.diy {picks}` (0.2.0 自选编队: `{ [slotBaseId]: { charId, skillIndex?, uniEquipId? } | null }` for the four DIY slots — ≤ 8 entries, kept leniently: shared/protocol.js `checkDiyPicks` drops an illegal pick (an operator without a kit, another tier's prototype, a prototype off its locked skill, a 集成战略 module, an owned operator's second slot, the same operator twice in a tier, an unknown slot), only malformed picks are `BAD_MSG`; stored on the session and the seat like the not-owned list, a match takes the seat's picks when it starts — during a match `ROOM_STARTED` 'stored for the next match'; heavy bucket; the match exposes them as `m.private.diy`) · `ping {c}`
+C→S: `hello {name, token?, version}` · `room.create {mode:'solo'|'coop', difficulty}` · `room.join {code}` · `room.leave` · `room.ready {ready}` · `room.setDifficulty {difficulty}` (host) · `room.addBot` / `room.removeBot {seat}` (host) · `room.kick {seat, playerId}` (host, before the match: another human leaves the room and gets `room.closed {reason:'kicked'}`; may join again; `playerId` = the player the host confirmed, a seat that changed hands meanwhile → `BAD_TARGET`) · `room.start` (host) · `room.loadout {entries}` (§16: any time in the lobby / room and during INFO_CHECK, then `WRONG_PHASE`; heavy rate-limit bucket; the match exposes it as `m.private.loadout`) · `room.ownership {notOwned}` (0.2.0 补位, the 干员持有 tab: the base chess ids marked as not owned — ≤ 160 ids, kept leniently: anything but a droppable NORMAL chess is dropped; stored on the session and the seat, a match takes the seat's list when it starts and never changes it — during a match `ROOM_STARTED` 'stored for the next match'; heavy bucket; the match exposes it as `m.private.standIns`) · `room.diy {picks}` (0.2.0 自选编队: `{ [slotBaseId]: { charId, skillIndex?, uniEquipId? } | null }` for the four DIY slots — ≤ 8 entries, kept leniently: shared/protocol.js `checkDiyPicks` drops an illegal pick (an operator without a kit, another tier's prototype, a prototype off its locked skill, a module of another game mode (集成战略 / 生息演算), an owned operator's second slot, the same operator twice in a tier, an unknown slot), only malformed picks are `BAD_MSG`; stored on the session and the seat like the not-owned list, a match takes the seat's picks when it starts — during a match `ROOM_STARTED` 'stored for the next match'; heavy bucket; the match exposes them as `m.private.diy`) · `ping {c}`
 S→C: `welcome {playerId, token, name, serverNow}` · `room.state {code, hostId, mode, difficulty, seats:[{seat, playerId, name, isBot, ready, connected}|null ×4]}` · `room.closed {reason}` · `pong {c, s}` · `error {rid?, code, msg}` · `ok {rid}`
 
 Platform additions (implemented): `welcome.{resumed, version}`, `welcome.diyKitted` (0.2.0: the operators a 自选 slot may field — server/sim/content/kits/index.js `KITTED_CHARS`, the picker's list), `room.state.inMatch`, `error.detail`; `room.closed.reason ∈ 'timeout'|'kicked'|'empty'|'shutdown'` (`kicked`: room.kick / room.removeSpectator; `empty`: a spectator whose room lost its last player); WebSocket close codes 4001 (session taken over by another socket — client must not auto-reconnect), 4002 (no hello in time), 1008 (flooding), 1001 (shutdown). The host's `room.start` counts as the host being ready. After any (re)`hello` the server pushes `room.state` and, if a match runs, the match resends `m.public`/`m.private` (+`m.field`, or the field's `b.start` under client-side combat). **Reconnect window:** a dropped session stays resumable for 10 min (`net.js NET_DEFAULTS.reconnectWindowMs`; co-op seats keep playing their last lineup meanwhile, §6.6); a session that drops while its **solo** room's match runs stays resumable for the official `config.constants.singleReconnectTime` (86 400 s = 24 h; lobby option `soloReconnectWindowMs`; research 01 §1 "24小时内随时返回") — the untimed solo run simply waits. Only when the window expires does the drop become `match.onLeave` (co-op: 中途退出 = elimination; solo: the run ends `'abandoned'`). The client keeps its token in sessionStorage plus a recent-token list in localStorage, so reopening the tab resumes. Everything lives in server memory: a server restart ends every room and run. The lobby⇄match interface (constructor opts, `start/handle/onDisconnect/onReconnect/onLeave/dispose`) is documented verbatim at the top of `server/match/Match.js` and is normative. `server/data.js` provides `getData()` + index getters (`getChess`, `getBond`, `getGarrison`, `getItem`, `getBand`, `getEffect`, `getEnemy`, `getWave`, `getStage`, `getBoss`, `getToken`, `getConfig`, `getMode`). Note: the skill trigger rule lives at `chess.skill.trigger.rule` in data.

docs/META.md

@@ -520,8 +520,10 @@ Any `choice:` handler whose EffectRef reuses its own key must guard like this (o
   picks, merges, promotions, sells, temp, elimination; `invariants.js` checks `left + held = cap` per player). The
   shop's chess slots and the reward offers' temporary refreshes roll it with the shared pool (`pool.roll({ extra })`,
   copy-weighted like any chess of its tier) once the 调度中心 reaches the slot's `shopLevel` (5 / 6) [ASSUMED for the
-  reward offers]; effects that draw a random operator from the shared pool never draw it, and 信标 never sends one to a
-  teammate [ASSUMED]. `battleInput` carries `diy` (the pick); `m.private.diy` / `diyBanned`; `prepFieldMeta` and
+  reward offers]; an effect, reward pool or 机变 card that grants the player a random operator draws its stock too
+  (effectsMeta `rollChess` / `rollPool`, the 驰援 fallback in choices.js: `ps.diyStockEntries()` — the roll's own tier
+  rules, no 调度中心 gate, bonds through the player's view; 「自选干员放入后模拟中的补给池随机范围也将被相应扩大」, 0.2.0), and
+  信标 never sends one to a teammate [ASSUMED]. `battleInput` carries `diy` (the pick); `m.private.diy` / `diyBanned`; `prepFieldMeta` and
   `m.result` lineups carry the pick (`diy`) so other players' cards compose the operator.
 * **Hand**: 10 slots filled right→left, 5 temp slots for passive overflow (merge results, grants, returned equipment);
   a full hand refuses every buy and reward pick — also one whose copy would complete a merge at once (PRTS
@@ -576,7 +578,9 @@ Any `choice:` handler whose EffectRef reuses its own key must guard like this (o
   the tacticians' 援军, 伺夜 狼群 / 缪尔赛思 流形 — choosing the tactical point; player report #9 after 0.1.0) only goes on
   a tile of its owner's attack range: the owner's loadout grid (`attackRangeGrid`) rotated by its facing around its tile
   (`PlayerState._legal` / `summonRange`, `board.js ownerRangeKeys`; a summon dragged onto its own owner is checked from
-  the owner's new tile, an operator dragged onto the summon from the summon's new tile). When the owner is re-oriented in
+  the owner's new tile, an operator dragged onto the summon from the summon's new tile); Mon3tr's 重构体 likewise (her
+  talent), while 凯尔希·思衡托's 战术锚点 (`ownerRangeOutside` / `rangedTilesOnly`) goes only on a 高台 outside that range
+  (`summonExcluded`, board.js class `high`). When the owner is re-oriented in
   place (or promoted) a summon its new range leaves out goes back onto its stack with a toast (`_liftOutOfRange` in
   `recompute`) — one still inside stays [ASSUMED]. A re-orientation that would leave such a summon with no stack and no
   free hand / temp slot is refused (HAND_FULL, like withdrawing a summon into a full hand); in the other cases (a

docs/PLAYING.md

@@ -61,7 +61,7 @@
 - **晋升精锐**：3 名同名干员（无论是否部署）自动合成**精锐**（等级、技能、模组大幅提升；风丸只需 2 名），精锐不会再合成。如果被合成的干员里有**已经部署在战场上**的，精锐会直接出现在**那名干员的位置**（保持原来的朝向，不多占部署位；有两三名都在场上时，取最先部署的那名——最左一列优先，同一列从上到下）；否则精锐进入整备区（满了进入临时整备区）。原先配发的装备都退回整备区，需要重新配发；被合成干员的召唤物随之移除，场上的精锐会把自己的召唤物送进整备区。点选一张能合成的商店卡片时，精锐将出现的那一格会亮起金色边框，同时打开的详情卡里也会写明去向（「可晋升：精锐干员将出现在作战区原位置 / 将进入整备区」；详情卡会自动停靠在不遮挡这一格的一侧）。在回合开始或结算时因策略、奖励等完成的合成，精锐出现时同样会播放金色的晋升特效。
 - **晋级奖励**：每次晋升后获得一次特殊招募：从 3 名 **高一阶**（最高 VI）、**互不相同**的随机干员中**免费**挑 1 名（该阶剩余干员不足 3 名时由低一阶补足）。它不能刷新、不能冻结、本回合结束失效。
 - **干员持有（补位）**：大厅、房间和「确认本局信息」里的「干员调配」按钮打开的界面有两个标签页：「干员调配」选择每名干员携带的技能和精锐的模组；「**干员持有**」可以把你没有的干员**下掉**（点一下卡片切换「持有 / 未持有」）。和官方一样只有 55 张「普通」棋子能下掉（界面按阶级列出本赛季商店里的 53 名，每张写着由谁替补、用几技能）；74 张「预设」棋子（多是 1–2 阶的常见干员）无论是否持有都由本人上场，不在其中。默认全部持有。下掉的干员和官方一样**显示为替补干员**：商店和晋升奖励的卡片、整备区和临时整备区里的单位、作战区、结算界面的阵容，都是替补干员的头像、名字和模型（例如银灰显示为 Sharp），带一个小小的「替补」标记；详情卡显示替补干员的立绘、名字、技能、天赋和模组，名字下面写着「银灰的替补」。**盟约、特质、阶级、价格、合成仍按原干员**（卡片和详情卡上的盟约、特质就是原干员的），作战时的属性、技能、天赋、模组、攻击范围、近战位 / 远程位都是替补干员的（例如银灰 → Sharp 的 2 技能「亮剑」）。同一名替补干员可能替补好几名干员（Sharp 替补忍冬、银灰、隐德来希等），它们按各自的原干员分别合成：看阶级和盟约区分，点开详情卡能看到替补的是谁。同盟模拟中队友查看你的整备区和作战区、你的盟约成员时，看到的也是替补干员。替补的技能和模组由棋子固定，「干员调配」对它不生效；替补干员没有召唤物（下掉缪尔赛思就没有流形）。这是**局外设置**：下一局开始时生效，对局中修改只保存到下一局；同盟模拟中只影响你自己的棋子，队友的棋子按队友的设置。没有官方的好友借用：想用本人上场，改回「持有」即可。「全部持有」一键恢复，「导出 / 导入」可以把设置带到别的浏览器；大厅的「干员调配」按钮上会显示「替补 N」提醒你有几名干员被下掉。
-- **自选编队**：同一个界面的第三个标签页「**自选编队**」有 4 个名额：5 阶两个、6 阶两个。点名额打开选择列表，每个名额可以放一名**你持有的 6★ 干员**（棋子池里没有的那些，标「已持有」：3 个技能任选其一，精锐的模组任选其一或不装备；只在集成战略里生效的 ISW-A 模组不能选）或一名**原型干员**（标「原型」：Sharp、Mechanist 等 9 名 6★，5 阶另有 6 名 4★ 预备干员；技能和模组与补位时相同，不能更改）。同一名原型干员可以同时放进一个 5 阶和一个 6 阶名额；你持有的干员只能放一个名额；同一阶的两个名额不能放同一人。列表只列出已经做好战斗逻辑的干员（原型干员全部可选，持有的 6★ 随战斗逻辑完成陆续加入）。对局中，自选干员**只出现在你自己的商店里**：调度中心升到 5 级后才会刷出 5 阶名额的干员，6 级后才会刷出 6 阶的；刷新概率和同阶干员一样，每个名额有自己的库存（5 阶 8 张、6 阶 5 张，不与队友共用），价格与同阶干员相同，晋升奖励里也可能出现。三张合成精锐，精锐时所选模组生效（5 阶 1 级、6 阶 3 级）。自选干员**没有特质**，盟约按干员的实际阵营分配（推进之王是维多利亚，煌同时是炎和维多利亚，没有对应阵营的是协防干员），和普通棋子一样计入盟约人数；本局禁用了它全部的盟约时，它不会出现在商店里（协防不会被禁用）。商店卡片、整备区、作战区和详情卡上都标着「自选」，详情卡显示所选的技能和模组。这同样是**局外设置**：下一局开始时生效，对局中修改只保存到下一局；AI 队友不使用自选；信标不会把自选干员送给队友。「导出 / 导入」「全部清空」可用，大厅的「干员调配」按钮上会显示「自选 N」。
+- **自选编队**：同一个界面的第三个标签页「**自选编队**」有 4 个名额：5 阶两个、6 阶两个。点名额打开选择列表，每个名额可以放一名**你持有的 6★ 干员**（棋子池里没有的那些，标「已持有」：3 个技能任选其一，精锐的模组任选其一或不装备；只在集成战略或生息演算里生效的模组不能选：ISW-A、SO-A / SO-B、RA-A）或一名**原型干员**（标「原型」：Sharp、Mechanist 等 9 名 6★，5 阶另有 6 名 4★ 预备干员；技能和模组与补位时相同，不能更改）。同一名原型干员可以同时放进一个 5 阶和一个 6 阶名额；你持有的干员只能放一个名额；同一阶的两个名额不能放同一人。列表只列出已经做好战斗逻辑的干员（原型干员全部可选，持有的 6★ 随战斗逻辑完成陆续加入）。对局中，自选干员**只出现在你自己的商店里**：调度中心升到 5 级后才会刷出 5 阶名额的干员，6 级后才会刷出 6 阶的；刷新概率和同阶干员一样，每个名额有自己的库存（5 阶 8 张、6 阶 5 张，不与队友共用），价格与同阶干员相同，晋升奖励里也可能出现；效果、奖励或机变卡「获得一名随机干员」时，也可能抽到你自己的自选干员（按那个效果自己的阶级规则，不看调度中心等级）。三张合成精锐，精锐时所选模组生效（5 阶 1 级、6 阶 3 级）。自选干员**没有特质**，盟约按干员的实际阵营分配（推进之王是维多利亚，煌同时是炎和维多利亚，没有对应阵营的是协防干员），和普通棋子一样计入盟约人数；本局禁用了它全部的盟约时，它不会出现在商店里（协防不会被禁用），开局的「确认本局信息」、选策略时的「本局信息」和对局中的「本局信息」都会在「本局禁用干员」下写明是哪一名。商店卡片、整备区、作战区和详情卡上都标着「自选」，详情卡显示所选的技能和模组。这同样是**局外设置**：下一局开始时生效，对局中修改只保存到下一局；AI 队友不使用自选；你开启 AI 托管时，AI 会优先买你的自选干员，并在快能刷出自选名额时提早一回合升级调度中心；信标不会把自选干员送给队友。「导出 / 导入」「全部清空」可用，大厅的「干员调配」按钮上会显示「自选 N」。
 - 每回合商店会自动刷新未冻结的格子。
 - **「本回合首次主动刷新」按每名干员各自计算**（拉普兰德）：她在本回合遇到的第一次主动刷新生效，在整备区里也算——先刷新、再买下拉普兰德，下一次刷新她仍会叠层；同一回合内用已经生效过的拉普兰德合成的精锐，本回合不再生效。
 

docs/SIM.md

@@ -852,9 +852,11 @@ or guard with a per-unit flag while dealing it. When the guard trips, the logged
   `fn(battle, unit)` → list of ally units (their current range) or tile-key arrays; returns an unregister fn; not for
   heal skills: 海嗣 "攻击范围视为自身攻击范围的延伸", 流形); `SKILL_RANGE` — "不通过普通攻击/治疗触发技能，仅在技能范围内存在敌人（无视其不可选中）时释放技能": any
   living enemy (stealthed, untargetable, flying included) on `trigger.customRangeGrid` (= the skill's rangeGrid), every
-  tick, no attack needed; a kit may set `trigger.allies` (+ `hpAtMost`, default 1) for an injured, healable ally of the
-  grid at or below that HP ratio instead (the AUTO heal skill 古米 S1: PRTS 备注 "此技能在存在生命值不满的可治疗角色时可
-  触发…直至古米完成一次普通攻击的治疗" — her heal mode waits for its heal); `ACTIVE_RANGE` — the owner's rule of 2026-10-05
+  tick, no attack needed; `trigger.allies` (+ `hpAtMost`, default 1) — set by a kit, or by the data for an ally row (黍 S3's
+  official `TRY_SEARCH_ALLY_SKILL`, "技能范围内存在可治疗的我方单位时释放技能": tools/build-data.mjs `TRIGGER_ALLY_RULES`,
+  simdata passes `allies` on) — asks for an injured, healable ally of the grid at or below that HP ratio instead (the AUTO
+  heal skill 古米 S1: PRTS 备注 "此技能在存在生命值不满的可治疗角色时可触发…直至古米完成一次普通攻击的治疗" — her heal mode
+  waits for its heal); `ACTIVE_RANGE` — the owner's rule of 2026-10-05
   (a deliberate deviation): a MANUAL skill on the basic strategy (深巡 S2's DEFAULT deviation included) or on the SEARCH
   row (薄绿 S1, 蜜蜡 S1, 卡涅利安 S3, 玛恩纳 S2, 安洁莉娜 S3) whose attack range while it runs strictly contains the
   unit's own range checks the DEFAULT condition — a targetable enemy (or one it blocks), a heal skill an injured ally —
@@ -893,7 +895,8 @@ or guard with a per-unit flag while dealing it. When the guard trips, the logged
   `skillEnd` fires. `onAttack` ctx carries `noAmmo` (set it to true: this attack spends no bullet, no `ammoUsed` — 流明's
   free heals).
 - Runtime helpers on `unit.skill`: `activate(reason, {free})`, `end(reason)`, `stop()`, `addAmmo(n)`, `extend(s)`,
-  `addCharge(n)`, `gainSp(n, reason)`, `addTriggerRange(fn)`; fields `sp, spCost (= floor(base×spCostMul + spCostFlat)), spCostMul, charges,
+  `addCharge(n)`, `gainSp(n, reason)`, `addTriggerRange(fn)`, `setTrigger(rule, grid)` (a kit's own rule change mid-battle —
+  薇薇安娜 S3's ACTIVE_RANGE on 3-2 after its first cast; 0.2.0); fields `sp, spCost (= floor(base×spCostMul + spCostFlat)), spCostMul, charges,
   maxCharges, active, timeLeft, ammoLeft, ammoMax, activations, kind, rule, bb` (`ammoMax`: the most bullets the running ammo skill
   has held — set at activation, raised by skillStart additions and `addAmmo` above it; 0 when inactive).