dsh-workbuddy-xdpool 1.7.8 → 1.7.9

package/CHANGELOG.md

@@ -4,6 +4,56 @@
 
 版本号遵循 [语义化版本](https://semver.org/lang/zh-CN/)。
 
+## 1.7.9 — 一个对话只用一个账号，新对话才换人
+
+> 有人反馈：除了「优先模式」，换别的模式都会掉命中率、掉速度。这个观察是对的，而且原因不在你的网络——在账号切换本身。所以这次加了一种新模式，专门解决这件事。
+
+### 为什么换个模式就会掉命中率
+
+上游的 prompt 缓存是按**账号**隔离的，不是按你这个人。
+
+所以「轮换模式」和「均衡模式」每发一条消息都可能换一个账号，对上游来说就是换了一个租户——**整段对话的缓存全部作废，从第一个字重新算**。命中率当然掉，首字延迟当然涨。
+
+而「优先模式」把这一切都押在一个账号上：缓存稳了，速度好了，代价是这个账号的额度会被你一个人用完。
+
+一句话：以前你只能在「额度分摊」和「缓存命中」之间选一个。
+
+### 新增「每对话固定」模式
+
+现在可以两个都要。
+
+规则很简单：**一个对话从头到尾只用一个账号；你新开一个对话，才轮到下一个账号。**
+
+- 同一个对话的每一轮都打同一个账号 → 上游缓存一直是热的 → 命中率和速度都是优先模式的水平。
+- 新对话按顺序铺到下一个账号 → 额度还是分散在几个账号上，不会只烧一个。
+
+卡片上「账号使用方式」里多了一个「每对话固定（推荐）」，点一下就能切。
+
+**默认值仍然是「优先模式」，没有偷偷改你的设置。** 想试新模式，自己点一下；不满意，再点回来。
+
+### 账号被限流或被你关掉，会自动换绑
+
+绑定不是死契。如果这个对话的账号：
+
+- 被上游限流了（只针对当前模型，别的模型照用），
+- 被你在卡片上关掉了，
+- 或者积分到了你设的保留线，
+
+那么这个对话下一轮会自动换到一个能用的账号，并且**以后就固定在新的那个账号上**——不会每轮都重新挑，也不会因为一个账号打盹就让整个对话报错。
+
+### 四种模式怎么选
+
+- **每对话固定**：多个对话同时用，既想省额度又想保住命中率。推荐先试这个。
+- **优先模式**：就一个对话，或者只有一个账号额度够用。缓存最稳。
+- **轮换模式**：不在乎速度，只想让几个账号的积分严格平均地掉。
+- **均衡模式**：随机抽，闲置越久的账号越容易被选中；比轮换更不容易被一个不健康的账号拖住。
+
+### 已知边界
+
+- 绑定只存在内存里，重启 DSH 后就忘了。影响很小：重启只是让每个对话重新认一次账号，之后照样固定。
+- 绑定按**对话的第一条用户消息**区分。两个对话如果第一句话一字不差，会被当成同一个对话、共用账号。这种情况很少见，共用了也没有坏处，只是共享一份缓存。
+- 最多记住 200 个对话的绑定，超了会淘汰最久没用过的那个。被淘汰的对话下一轮重新绑定一次，仅此一次，行为不受影响。
+
 ## 1.7.8 — 说清楚卡片在哪儿、以及我们支持到哪个版本
 
 > 这次没有功能问题，全在「声明」上：一处把你引到不存在的路径，一处让你以为装错了版本。

package/README.md

@@ -42,6 +42,7 @@
 - **零配置**：装上、打开，就完事了。WorkBuddy 桌面 App 里每个登过的账号都会被自动发现并入池，不需要在插件里录任何东西。
 
 - **自动容错换号**：池子记着每个账号的限流状态。某个号触发 429 就冷却它，后面的请求自动落到下一个健康的号上；冷却结束自动恢复。所有号都在冷却时，请求才排队等待。
+- **四种账号分配方式**：`priority` 先用完一个号；`round-robin` 按顺序轮换；`balanced` 随机抽、偏向闲置久的；`sticky` 让**一个对话只用一个账号，新对话才换下一个**——上游缓存按账号隔离，中途换号等于把整段对话的缓存作废，`sticky` 就是为这件事准备的。卡片上点一下即可切换，默认仍是 `priority`。
 
 - **池健康一眼看清**：卡片显示「几个账号 / 几个在冷却」「下一个会轮到谁」，以及每个账号的令牌有效期和冷却倒计时。
 
@@ -176,12 +177,16 @@ dsh plugin --profile desktop exec dsh-workbuddy-xdpool remove myKey
 | --- | --- | --- |
 | `authFile` | 覆盖 WorkBuddy 桌面 auth 文件路径（跨平台自动探测出问题时用，等同于 `WORKBUDDY_AUTH_FILE`） | 自动探测 |
 | `cooldownMs` | 单账号 429 冷却时长（毫秒） | `60000` |
+| `distribution` | 账号分配方式：`sticky`（每对话固定一个账号，新对话换下一个）/ `priority`（先用完一个）/ `round-robin`（按顺序轮换）/ `balanced`（随机，偏向闲置久的） | `priority` |
+
+> 上游 prompt 缓存按账号隔离，所以对话中途换号会把缓存整段作废。想让多账号同时分摊额度又不想掉命中率，用 `sticky`。
 
 也可以直接写进 `~/.dsh/settings.yaml`：
 
 ```yaml
 workbuddy-xdpool:
   cooldownMs: 120000
+  distribution: sticky
 ```
 
 ## 架构

package/lib/bin.js

@@ -2612,6 +2612,13 @@ function candidateAuthDirs(env = process.env) {
 	return dirs;
 }
 /**
+* How many conversation→account bindings `sticky` mode remembers.
+*
+* Only a memory bound: evicting the oldest binding costs one re-pick on that
+* conversation's next turn, it never loses an account or a request.
+*/
+const STICKY_AFFINITY_LIMIT = 200;
+/**
 * Read-only pool of every discovered WorkBuddy account, with rate-limit
 * cooldown and round-robin failover.
 */
@@ -2660,6 +2667,15 @@ var WorkBuddyAccountPool = class {
 	distribution;
 	/** Cursor for round-robin mode; unused under priority distribution. */
 	cursor = 0;
+	/**
+	* `sticky` mode: conversation key → account id.
+	*
+	* A conversation that keeps the same account also keeps that account's
+	* upstream prompt cache warm — the cache is per tenant, so rotating accounts
+	* mid-conversation pays full prompt cost on every turn. Insertion order is
+	* the LRU order: re-binding deletes then re-inserts.
+	*/
+	affinity = /* @__PURE__ */ new Map();
 	lastScanAtMs = 0;
 	preferredId;
 	/**
@@ -2918,6 +2934,45 @@ var WorkBuddyAccountPool = class {
 		this.cursor = (index + 1) % pool.length;
 		return account;
 	}
+	/** Remember which account a conversation is bound to, keeping LRU order. */
+	bindAffinity(conversationKey, accountId) {
+		this.affinity.delete(conversationKey);
+		this.affinity.set(conversationKey, accountId);
+		while (this.affinity.size > STICKY_AFFINITY_LIMIT) {
+			const oldest = this.affinity.keys().next().value;
+			if (oldest === void 0) break;
+			this.affinity.delete(oldest);
+		}
+	}
+	/**
+	* `sticky`: the account this conversation already used, when it can still
+	* serve the model being asked for.
+	*
+	* Returns `undefined` both when there is no binding and when the binding is
+	* no longer eligible (cooling for this model, disabled, out of credits) — the
+	* caller then rebinds, which is what makes a rate-limited conversation hop to
+	* a fresh account instead of failing.
+	*/
+	affinityAccount(pool, conversationKey) {
+		if (conversationKey === void 0 || conversationKey === "") return void 0;
+		const boundId = this.affinity.get(conversationKey);
+		if (boundId === void 0) return void 0;
+		const bound = pool.find((account) => account.id === boundId);
+		if (bound === void 0) {
+			this.affinity.delete(conversationKey);
+			return;
+		}
+		this.bindAffinity(conversationKey, boundId);
+		return bound;
+	}
+	/** Bindings currently remembered; exposed for tests and diagnostics. */
+	affinitySize() {
+		return this.affinity.size;
+	}
+	/** Forget every conversation binding (tests, and a settings change). */
+	clearAffinity() {
+		this.affinity.clear();
+	}
 	/**
 	* Priority mode: weighted random over the eligible accounts.
 	*
@@ -2956,15 +3011,20 @@ var WorkBuddyAccountPool = class {
 	*   it resumes straight away.
 	* - **round-robin**: consecutive requests rotate through the pool so spend
 	*   spreads evenly across every account.
+	* - **sticky**: one account per conversation, and a new conversation moves to
+	*   the next account in order. Keeps the upstream prompt cache warm within a
+	*   conversation while still spreading spend across conversations.
 	*
-	* In both modes an explicit user selection (`prefer`) heads the list, a
+	* In every mode an explicit user selection (`prefer`) heads the list, a
 	* cooling account is skipped for that model only, and an unrecognised setting
 	* falls back to priority.
 	*
 	* Scans on first use, and rescans when every known account is cooling down: a
 	* fresh desktop login is the usual way out of an exhausted pool.
+	*
+	* `conversationKey` is only consulted under `sticky`; other modes ignore it.
 	*/
-	async acquire(modelId, region) {
+	async acquire(modelId, region, conversationKey) {
 		if (this.accounts.length === 0) await this.scan();
 		let pool = this.available(Date.now(), modelId, region);
 		if (pool.length === 0) {
@@ -2979,8 +3039,16 @@ var WorkBuddyAccountPool = class {
 				return preferred;
 			}
 		}
-		const account = this.distribution === "round-robin" ? this.pickRoundRobin(pool) : this.distribution === "balanced" ? this.pickByWeight(pool) : pool[0];
+		if (this.distribution === "sticky") {
+			const bound = this.affinityAccount(pool, conversationKey);
+			if (bound !== void 0) {
+				await this.ensureFresh(bound);
+				return bound;
+			}
+		}
+		const account = this.distribution === "round-robin" || this.distribution === "sticky" ? this.pickRoundRobin(pool) : this.distribution === "balanced" ? this.pickByWeight(pool) : pool[0];
 		if (account === void 0) return void 0;
+		if (this.distribution === "sticky" && conversationKey !== void 0 && conversationKey !== "") this.bindAffinity(conversationKey, account.id);
 		await this.ensureFresh(account);
 		return account;
 	}
@@ -5080,8 +5148,9 @@ z.object({
 	distribution: asVolatile(z.union([
 		"priority",
 		"round-robin",
-		"balanced"
-	]).default("priority").description("How requests are spread: priority (drain one), round-robin (in order), or balanced (idle-weighted random)")),
+		"balanced",
+		"sticky"
+	]).default("priority").description("How requests are spread: priority (drain one), round-robin (in order), balanced (idle-weighted random), or sticky (one account per conversation, new conversations rotate)")),
 	disabledAccountIds: asVolatile(z.array(z.string()).default([]).description("Account ids excluded from the pool (empty = every discovered account participates)")),
 	creditReserves: asVolatile(z.dict(z.number().step(1).min(0)).default({}).description("Per-account credit floor: stop using an account once its balance reaches this value")),
 	enabledModelIds: asVolatile(z.array(z.string()).default([]).description("Legacy shared model-id list; used by a region that has no per-region selection yet")),

package/lib/client.js

@@ -1304,13 +1304,14 @@ window.__ModuleLoader__.load({
 										}), /* @__PURE__ */ (0, react_jsx_runtime.jsx)("div", {
 											className: "dsm-workbuddy-xdpool-dist-options",
 											children: [
+												"sticky",
 												"priority",
 												"balanced",
 												"round-robin"
 											].map((option) => {
 												const active = (status.distribution ?? "priority") === option;
-												const label = option === "priority" ? t?.("row.distPriority") ?? "Priority" : option === "balanced" ? t?.("row.distBalanced") ?? "Balanced" : t?.("row.distRoundRobin") ?? "Round-robin";
-												const hint = option === "priority" ? t?.("row.distPriorityHint") ?? "" : option === "balanced" ? t?.("row.distBalancedHint") ?? "" : t?.("row.distRoundRobinHint") ?? "";
+												const label = option === "sticky" ? t?.("row.distSticky") ?? "Per conversation" : option === "priority" ? t?.("row.distPriority") ?? "Priority" : option === "balanced" ? t?.("row.distBalanced") ?? "Balanced" : t?.("row.distRoundRobin") ?? "Round-robin";
+												const hint = option === "sticky" ? t?.("row.distStickyHint") ?? "" : option === "priority" ? t?.("row.distPriorityHint") ?? "" : option === "balanced" ? t?.("row.distBalancedHint") ?? "" : t?.("row.distRoundRobinHint") ?? "";
 												return /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("button", {
 													type: "button",
 													role: "radio",
@@ -2282,6 +2283,8 @@ window.__ModuleLoader__.load({
 			"row.distRoundRobinHint": "Take turns in order, spreading the spend evenly",
 			"row.distBalanced": "Balanced",
 			"row.distBalancedHint": "Draw at random, favouring the account idle longest",
+			"row.distSticky": "Per conversation",
+			"row.distStickyHint": "One account per chat, new chats take the next account — keeps the prompt cache warm",
 			"row.resetCooldowns": "Clear all cooldowns",
 			"row.resetCooldownsBusy": "Clearing…",
 			"row.resetCooldownsDone": "Cooldowns cleared",
@@ -2434,6 +2437,8 @@ window.__ModuleLoader__.load({
 			"row.distRoundRobinHint": "按顺序轮流使用，积分均匀分摊",
 			"row.distBalanced": "均衡模式",
 			"row.distBalancedHint": "随机抽取，闲置越久的账号被选中概率越高",
+			"row.distSticky": "每对话固定（推荐）",
+			"row.distStickyHint": "一个对话只用一个账号，新对话自动换下一个账号——保住上游缓存，命中率和速度都更好",
 			"row.resetCooldowns": "清除所有冷却",
 			"row.resetCooldownsBusy": "正在清除…",
 			"row.resetCooldownsDone": "冷却已清除",

package/lib/index.d.ts

@@ -831,7 +831,7 @@ export declare function workbuddyAccountId(credential: Pick<WorkBuddyCredential,
 /** Every directory the pool should scan, in probe order. */
 export declare function candidateAuthDirs(env?: NodeJS.ProcessEnv): string[];
 /** How the pool chooses which account serves the next request. */
-type AccountDistribution = 'priority' | 'round-robin' | 'balanced';
+type AccountDistribution = 'priority' | 'round-robin' | 'balanced' | 'sticky';
 interface AccountPoolOptions {
   /** Logger for discovery and rotation events. */
   logger?: {
@@ -858,6 +858,9 @@ interface AccountPoolOptions {
    *   queue the moment its window resets.
    * - `round-robin`: consecutive requests rotate through the pool so the
    *   spend spreads evenly.
+   * - `sticky`: one account per conversation, and a new conversation moves to
+   *   the next account in order. Keeps the upstream prompt cache warm inside a
+   *   conversation while still spreading spend across conversations.
    */
   distribution?: AccountDistribution;
 }
@@ -884,6 +887,15 @@ export declare class WorkBuddyAccountPool {
   private distribution;
   /** Cursor for round-robin mode; unused under priority distribution. */
   private cursor;
+  /**
+   * `sticky` mode: conversation key → account id.
+   *
+   * A conversation that keeps the same account also keeps that account's
+   * upstream prompt cache warm — the cache is per tenant, so rotating accounts
+   * mid-conversation pays full prompt cost on every turn. Insertion order is
+   * the LRU order: re-binding deletes then re-inserts.
+   */
+  private readonly affinity;
   private lastScanAtMs;
   private preferredId;
   /**
@@ -1010,6 +1022,22 @@ export declare class WorkBuddyAccountPool {
   };
   /** Round-robin: the legacy cursor walk, kept for the distribution that asks for it. */
   private pickRoundRobin;
+  /** Remember which account a conversation is bound to, keeping LRU order. */
+  private bindAffinity;
+  /**
+   * `sticky`: the account this conversation already used, when it can still
+   * serve the model being asked for.
+   *
+   * Returns `undefined` both when there is no binding and when the binding is
+   * no longer eligible (cooling for this model, disabled, out of credits) — the
+   * caller then rebinds, which is what makes a rate-limited conversation hop to
+   * a fresh account instead of failing.
+   */
+  private affinityAccount;
+  /** Bindings currently remembered; exposed for tests and diagnostics. */
+  affinitySize(): number;
+  /** Forget every conversation binding (tests, and a settings change). */
+  clearAffinity(): void;
   /**
    * Priority mode: weighted random over the eligible accounts.
    *
@@ -1036,15 +1064,20 @@ export declare class WorkBuddyAccountPool {
    *   it resumes straight away.
    * - **round-robin**: consecutive requests rotate through the pool so spend
    *   spreads evenly across every account.
+   * - **sticky**: one account per conversation, and a new conversation moves to
+   *   the next account in order. Keeps the upstream prompt cache warm within a
+   *   conversation while still spreading spend across conversations.
    *
-   * In both modes an explicit user selection (`prefer`) heads the list, a
+   * In every mode an explicit user selection (`prefer`) heads the list, a
    * cooling account is skipped for that model only, and an unrecognised setting
    * falls back to priority.
    *
    * Scans on first use, and rescans when every known account is cooling down: a
    * fresh desktop login is the usual way out of an exhausted pool.
+   *
+   * `conversationKey` is only consulted under `sticky`; other modes ignore it.
    */
-  acquire(modelId?: string, region?: WorkBuddyRegion): Promise<WorkBuddyAccount | undefined>;
+  acquire(modelId?: string, region?: WorkBuddyRegion, conversationKey?: string): Promise<WorkBuddyAccount | undefined>;
   /** Pin the account the plugin card should prefer; tokens stay out of settings. */
   /** How the pool currently spreads requests. Shown on the card. */
   currentDistribution(): AccountDistribution;
@@ -1513,7 +1546,7 @@ interface PoolWebAutomationEarnings {
  */
 type PoolRegion = 'cn' | 'global';
 /** How the pool spreads requests across its accounts. */
-type PoolDistribution = 'priority' | 'round-robin' | 'balanced';
+type PoolDistribution = 'priority' | 'round-robin' | 'balanced' | 'sticky';
 /**
  * The schedule every automation job falls back to.
  *
@@ -2480,10 +2513,15 @@ export interface Config {
    * - `balanced` draws at random, weighting whichever account has been idle
    *   longest. Spend still spreads, but without a fixed order, so one unhealthy
    *   account cannot pin the pool to itself.
+   * - `sticky` gives each conversation one account and moves the next new
+   *   conversation to the next account in order. Rotating accounts inside a
+   *   conversation throws away the upstream prompt cache (it is per tenant), so
+   *   this keeps the cache warm while still spreading spend across
+   *   conversations.
    *
    * Absent reads as `priority`.
    */
-  distribution?: 'priority' | 'round-robin' | 'balanced';
+  distribution?: 'priority' | 'round-robin' | 'balanced' | 'sticky';
   /**
    * Account ids switched off on the card. A disabled account is never picked
    * to serve a request, but it stays in the pool and on the card so it can be

package/lib/index.js

@@ -2720,6 +2720,13 @@ function candidateAuthDirs(env = process.env) {
 	return dirs;
 }
 /**
+* How many conversation→account bindings `sticky` mode remembers.
+*
+* Only a memory bound: evicting the oldest binding costs one re-pick on that
+* conversation's next turn, it never loses an account or a request.
+*/
+const STICKY_AFFINITY_LIMIT = 200;
+/**
 * Read-only pool of every discovered WorkBuddy account, with rate-limit
 * cooldown and round-robin failover.
 */
@@ -2768,6 +2775,15 @@ var WorkBuddyAccountPool = class {
 	distribution;
 	/** Cursor for round-robin mode; unused under priority distribution. */
 	cursor = 0;
+	/**
+	* `sticky` mode: conversation key → account id.
+	*
+	* A conversation that keeps the same account also keeps that account's
+	* upstream prompt cache warm — the cache is per tenant, so rotating accounts
+	* mid-conversation pays full prompt cost on every turn. Insertion order is
+	* the LRU order: re-binding deletes then re-inserts.
+	*/
+	affinity = /* @__PURE__ */ new Map();
 	lastScanAtMs = 0;
 	preferredId;
 	/**
@@ -3026,6 +3042,45 @@ var WorkBuddyAccountPool = class {
 		this.cursor = (index + 1) % pool.length;
 		return account;
 	}
+	/** Remember which account a conversation is bound to, keeping LRU order. */
+	bindAffinity(conversationKey, accountId) {
+		this.affinity.delete(conversationKey);
+		this.affinity.set(conversationKey, accountId);
+		while (this.affinity.size > STICKY_AFFINITY_LIMIT) {
+			const oldest = this.affinity.keys().next().value;
+			if (oldest === void 0) break;
+			this.affinity.delete(oldest);
+		}
+	}
+	/**
+	* `sticky`: the account this conversation already used, when it can still
+	* serve the model being asked for.
+	*
+	* Returns `undefined` both when there is no binding and when the binding is
+	* no longer eligible (cooling for this model, disabled, out of credits) — the
+	* caller then rebinds, which is what makes a rate-limited conversation hop to
+	* a fresh account instead of failing.
+	*/
+	affinityAccount(pool, conversationKey) {
+		if (conversationKey === void 0 || conversationKey === "") return void 0;
+		const boundId = this.affinity.get(conversationKey);
+		if (boundId === void 0) return void 0;
+		const bound = pool.find((account) => account.id === boundId);
+		if (bound === void 0) {
+			this.affinity.delete(conversationKey);
+			return;
+		}
+		this.bindAffinity(conversationKey, boundId);
+		return bound;
+	}
+	/** Bindings currently remembered; exposed for tests and diagnostics. */
+	affinitySize() {
+		return this.affinity.size;
+	}
+	/** Forget every conversation binding (tests, and a settings change). */
+	clearAffinity() {
+		this.affinity.clear();
+	}
 	/**
 	* Priority mode: weighted random over the eligible accounts.
 	*
@@ -3064,15 +3119,20 @@ var WorkBuddyAccountPool = class {
 	*   it resumes straight away.
 	* - **round-robin**: consecutive requests rotate through the pool so spend
 	*   spreads evenly across every account.
+	* - **sticky**: one account per conversation, and a new conversation moves to
+	*   the next account in order. Keeps the upstream prompt cache warm within a
+	*   conversation while still spreading spend across conversations.
 	*
-	* In both modes an explicit user selection (`prefer`) heads the list, a
+	* In every mode an explicit user selection (`prefer`) heads the list, a
 	* cooling account is skipped for that model only, and an unrecognised setting
 	* falls back to priority.
 	*
 	* Scans on first use, and rescans when every known account is cooling down: a
 	* fresh desktop login is the usual way out of an exhausted pool.
+	*
+	* `conversationKey` is only consulted under `sticky`; other modes ignore it.
 	*/
-	async acquire(modelId, region) {
+	async acquire(modelId, region, conversationKey) {
 		if (this.accounts.length === 0) await this.scan();
 		let pool = this.available(Date.now(), modelId, region);
 		if (pool.length === 0) {
@@ -3087,8 +3147,16 @@ var WorkBuddyAccountPool = class {
 				return preferred;
 			}
 		}
-		const account = this.distribution === "round-robin" ? this.pickRoundRobin(pool) : this.distribution === "balanced" ? this.pickByWeight(pool) : pool[0];
+		if (this.distribution === "sticky") {
+			const bound = this.affinityAccount(pool, conversationKey);
+			if (bound !== void 0) {
+				await this.ensureFresh(bound);
+				return bound;
+			}
+		}
+		const account = this.distribution === "round-robin" || this.distribution === "sticky" ? this.pickRoundRobin(pool) : this.distribution === "balanced" ? this.pickByWeight(pool) : pool[0];
 		if (account === void 0) return void 0;
+		if (this.distribution === "sticky" && conversationKey !== void 0 && conversationKey !== "") this.bindAffinity(conversationKey, account.id);
 		await this.ensureFresh(account);
 		return account;
 	}
@@ -5646,6 +5714,34 @@ function requestShape(raw) {
 		return "body was not parseable JSON";
 	}
 }
+/**
+* Stable identity of the conversation a request belongs to, for `sticky`.
+*
+* The FIRST user message is the key: it is the one part of the body that does
+* not change as the history grows, so every turn of a conversation hashes the
+* same way while a new chat (with a different opening message) hashes
+* differently. Hashing rather than storing the text keeps conversation content
+* out of the pool's memory.
+*
+* Two conversations that open with the exact same message share an account —
+* rare, and harmless: it only means they share one account's prompt cache.
+*/
+function conversationKeyOf(raw) {
+	try {
+		const parsed = JSON.parse(raw);
+		if (!Array.isArray(parsed.messages)) return void 0;
+		for (const entry of parsed.messages) {
+			if (typeof entry !== "object" || entry === null) continue;
+			const message = entry;
+			if (message["role"] !== "user") continue;
+			const content = typeof message["content"] === "string" ? message["content"] : JSON.stringify(message["content"] ?? "");
+			return createHash("sha256").update(content).digest("hex").slice(0, 32);
+		}
+		return;
+	} catch {
+		return;
+	}
+}
 function readBody(req) {
 	return new Promise((resolve, reject) => {
 		const chunks = [];
@@ -5775,6 +5871,7 @@ function createWorkBuddyShim(options) {
 		const prepared = client.prepareChatBody(raw);
 		const controller = new AbortController();
 		req.on("close", () => controller.abort());
+		const conversationKey = conversationKeyOf(raw);
 		let modelId;
 		try {
 			const parsed = JSON.parse(raw);
@@ -5786,7 +5883,7 @@ function createWorkBuddyShim(options) {
 		let last;
 		for (let attempt = 0; attempt < maxAttempts; attempt += 1) {
 			if (controller.signal.aborted) return;
-			const account = await pool.acquire(modelId, region);
+			const account = await pool.acquire(modelId, region, conversationKey);
 			if (account === void 0) {
 				const why = pool.unavailableReason(modelId, region);
 				if (why.reason === "cooling") {
@@ -7112,8 +7209,9 @@ const Config = z.object({
 	distribution: asVolatile(z.union([
 		"priority",
 		"round-robin",
-		"balanced"
-	]).default("priority").description("How requests are spread: priority (drain one), round-robin (in order), or balanced (idle-weighted random)")),
+		"balanced",
+		"sticky"
+	]).default("priority").description("How requests are spread: priority (drain one), round-robin (in order), balanced (idle-weighted random), or sticky (one account per conversation, new conversations rotate)")),
 	disabledAccountIds: asVolatile(z.array(z.string()).default([]).description("Account ids excluded from the pool (empty = every discovered account participates)")),
 	creditReserves: asVolatile(z.dict(z.number().step(1).min(0)).default({}).description("Per-account credit floor: stop using an account once its balance reaches this value")),
 	enabledModelIds: asVolatile(z.array(z.string()).default([]).description("Legacy shared model-id list; used by a region that has no per-region selection yet")),

package/package.json

@@ -2,7 +2,7 @@
   "name": "dsh-workbuddy-xdpool",
   "displayName": "DSH WorkBuddy XD Pool",
   "description": "Merge every locally signed-in WorkBuddy account into DeepSeek Harness as one auto-failing-over model pool (multi-account rotation, live credits, daily check-in and model catalog).",
-  "version": "1.7.8",
+  "version": "1.7.9",
   "license": "MIT",
   "author": "XDTrees",
   "homepage": "https://github.com/XDTrees/dsh-workbuddy-xdpool#readme",