@goodandready/dsh-moa 0.2.72 → 0.2.74

package/README.md

@@ -186,6 +186,15 @@ Validates markdown code blocks across all candidate outputs locally using JavaSc
 ### 20. Early Exit upon Semantic Consensus
 Compares normalized candidate proposals using token-level Sørensen-Dice similarity. When models arrive at identical or near-identical solutions (meeting or exceeding `early_exit_threshold`, default: `0.95`), the expensive Judge synthesis phase is automatically bypassed. The consensus solution is promoted directly to the workspace, saving up to 100% of judge token costs while accelerating pipeline latency. Configured via `early_exit_consensus_enabled: true` and `early_exit_threshold: 0.95`.
 
+### 21. Dynamic Consensus Threshold & Multi-Judge Escalation
+Evaluates pairwise candidate solution divergence (Disagreement Metric, 0.0–1.0) using normalized Sørensen-Dice similarity. When candidate consensus is weak (disagreement meets or exceeds `escalation_disagreement_threshold`, default: `0.40`), the pipeline automatically escalates:
+- `auto_upgrade`: Upgrades from a lightweight or fast aggregator to a designated flagship senior judge (`escalation_judge` or first senior fallback judge).
+- `council_majority`: Convenes a 3-judge panel with majority consensus voting.
+Dispatches `moa/judge-escalation` Cordis events and displays escalation decisions in live stream telemetry. Configured via `escalation_policy: 'single' | 'auto_upgrade' | 'council_majority'`, `escalation_disagreement_threshold: 0.40`, and `escalation_judge`.
+
+### 22. Self-Consistency Temperature Sampling for Single Models
+Allows single-model configurations (such as a local Ollama/vLLM instance or a single API key) to leverage Mixture-of-Agents diversity. When enabled on a preset with 1 model slot, the runner expands it into $N$ parallel candidate streams with distinct temperatures (e.g. 0.2, 0.6, 0.9) and complementary personas (`proposer`, `challenger`, `minimalist`), calculates agreement ratio, and performs full MoA consensus synthesis. Dispatches `moa/self-consistency-expand` Cordis events. Configured via `self_consistency_enabled: true`, `self_consistency_samples: 3`, and `self_consistency_temperatures: [0.2, 0.6, 0.9]`.
+
 ### 6. Live Canvas 1-Click Preview (optional)
 If `@goodandready/dsh-live-canvas` is installed in the same profile, `dsh-moa` pushes the promoted HTML file to the Live Canvas REST contract (`POST /dsh-live-canvas/api/preview`, served by the same harness webServer) and appends a one-click preview link (`/dsh-live-canvas/sandbox/<id>`) to the answer. Without the plugin the step is skipped silently — no errors in the log, no dead links.
 
@@ -327,6 +336,8 @@ dsh-moa:
 | `/dsh-moa/run` | `POST` | Runs the full MoA pipeline over HTTP (400 when `enabled: false`) |
 | `/dsh-moa/diff` | `GET` | Computes line-by-line diff between candidate runs or curator synthesis |
 | `/dsh-moa/promote` | `POST` | Manually promotes candidate workspace files to project root |
+| `/dsh-moa/cache` | `GET` | Returns semantic cache stats, hit/miss counters, and saved token metrics |
+| `/dsh-moa/cache` | `POST` | Purges cached candidate generations with optional olderThanMs filter |
 | `/api/dsh-moa/update` | `POST` | One-click plugin updater from npm with safe-write verification |
 
 ---

package/README.ru.md

@@ -186,6 +186,15 @@ graph TD
 ### 20. Ранний выход по семантическому консенсусу
 Сравнивает нормализованные решения кандидатов по токенному сходству Сёренсена-Дайса. Если решения моделей совпадают или практически идентичны (достигнут порог `early_exit_threshold`, по умолчанию 0.95), стадия вызова судьи (Judge) пропускается. Согласованный вариант немедленно продвигается в проект, экономя до 100% токенов судейской коллегии и сокращая задержку ответа. Управляется параметрами `early_exit_consensus_enabled: true` и `early_exit_threshold: 0.95`.
 
+### 21. Динамический порог консенсуса и эскалация судейства (Judge Escalation)
+Оценивает степень расхождения между решениями моделей-кандидатов (метрика Disagreement Metric, 0.0–1.0) на основе попарного расстояния Сёренсена-Дайса. Если расхождение превышает порог (`escalation_disagreement_threshold`, по умолчанию 0.40), пайплайн выполняет адаптивную эскалацию:
+- `auto_upgrade`: автоматический переход с базового/быстрого судьи на флагманскую старшую модель (`escalation_judge` или первый доступный резервный судья).
+- `council_majority`: созыв коллегии из 3 судей с голосованием большинством голосов.
+Генерирует событие `moa/judge-escalation` и выводит статус эскалации в телеметрию стрима.
+
+### 22. Самосогласованное температурное сэмплирование для одиночных моделей (Self-Consistency)
+Позволяет пользователям с единственной моделью (локальная Ollama, vLLM или единственный API-ключ) получать преимущества ансамблевой валидации MoA. Автоматически разворачивает одиночный слот на $N$ параллельных запусков с различными температурами (`0.2, 0.6, 0.9`) и дополняющими друг друга инженерными персонами (`proposer`, `challenger`, `minimalist`), вычисляет коэффициент согласия (Self-Consistency Agreement) и синтезирует итоговый результат. Генерирует событие `moa/self-consistency-expand`.
+
 ### 6. Live Canvas 1-клик предпросмотр (опционально)
 Если в профиле установлен `@goodandready/dsh-live-canvas`, `dsh-moa` отправляет промоученный HTML-файл в REST-контракт Live Canvas (`POST /dsh-live-canvas/api/preview`, тот же webServer харнесса) и добавляет к ответу ссылку на предпросмотр (`/dsh-live-canvas/sandbox/<id>`). Без плагина шаг пропускается тихо — без ошибок в журнале и без битых ссылок.
 
@@ -327,6 +336,8 @@ dsh-moa:
 | `/dsh-moa/run` | `POST` | Запускает полный пайплайн MoA по HTTP (400 при `enabled: false`) |
 | `/dsh-moa/diff` | `GET` | Вычисляет построчный diff между решениями кандидатов или синтезом куратора |
 | `/dsh-moa/promote` | `POST` | Ручной промоушн файлов кандидата в корень проекта с созданием снимка |
+| `/dsh-moa/cache` | `GET` | Статистика семантического кэша, число попаданий и сэкономленные токены |
+| `/dsh-moa/cache` | `POST` | Очистка семантического кэша с опциональным фильтром olderThanMs |
 | `/api/dsh-moa/update` | `POST` | One-click обновление плагина из npm с проверкой безопасности источника |
 
 ---

package/README.zh.md

@@ -163,6 +163,15 @@ graph TD
 ### 20. 语义共识提前退出机制 (Early Exit upon Semantic Consensus)
 基于 Token 级 Sørensen-Dice 相似度算法比对归一化后的候选方案。当多个候选模型给出高度一致的代码方案（达到或超过 `early_exit_threshold` 阈值，默认 0.95）时，自动跳过高耗费的裁判综合评审阶段，直接将共识方案提升至项目，在大幅缩短响应延迟的同时节省多达 100% 的裁判 Token 支出。通过 `early_exit_consensus_enabled: true` 与 `early_exit_threshold: 0.95` 配置。
 
+### 21. 动态共识阈值与裁判自适应升级 (Dynamic Consensus & Judge Escalation)
+基于归一化 Sørensen-Dice 计算候选方案间的分歧度 (Disagreement Metric 0.0–1.0)。当候选分歧超过设定阈值 (`escalation_disagreement_threshold`，默认 0.40) 时，流水线自动触发升级策略：
+- `auto_upgrade`: 自动将普通/快速裁判升级为指定的高阶旗舰裁判 (`escalation_judge` 或首选候补裁判)。
+- `council_majority`: 组建 3 裁判多数席裁决团。
+触发 `moa/judge-escalation` 事件并在实时流中呈现决策依据。
+
+### 22. 单模型自洽性温度采样 (Self-Consistency Temperature Sampling)
+专为仅配置单模型（如本地 Ollama/vLLM 或单一 API Key）的场景设计。开启后自动将单槽位扩展为 $N$ 个并行采样（分别采用 0.2、0.6、0.9 等递增温度与 `proposer`、`challenger`、`minimalist` 互补提示词），评估自洽一致性比率并进行全流程 MoA 综合聚合，触发 `moa/self-consistency-expand` 事件。
+
 ### 6. Live Canvas 一键预览（可选）
 若同一 profile 中安装了 `@goodandready/dsh-live-canvas`，`dsh-moa` 会将提升后的 HTML 文件推送到 Live Canvas 的 REST 契约（`POST /dsh-live-canvas/api/preview`，由同一 harness webServer 提供服务），并在回答中附上一键预览链接（`/dsh-live-canvas/sandbox/<id>`）。未安装该插件时此步骤静默跳过——日志无报错，也不会出现死链接。
 
@@ -257,6 +266,8 @@ dsh-moa:
 | `/dsh-moa/run` | `POST` | 通过 HTTP 运行完整 MoA 管线（`enabled: false` 时返回 400） |
 | `/dsh-moa/diff` | `GET` | 计算候选运行结果或综合输出的行级别差异（支持按 runId 解析工作区） |
 | `/dsh-moa/promote` | `POST` | 手动将候选工作区文件提升到项目根目录（带时间机器快照） |
+| `/dsh-moa/cache` | `GET` | 返回语义缓存统计信息、命中次数与节省 Token 指标 |
+| `/dsh-moa/cache` | `POST` | 清除语义缓存条目，支持 olderThanMs 过滤 |
 | `/api/dsh-moa/update` | `POST` | 从 npm 一键更新插件，带安全写入源校验 |
 
 ---

package/lib/client.js

@@ -167,6 +167,12 @@ window.__ModuleLoader__.load({
       "config.smart_routing_desc": "Analyze task complexity and automatically select the optimal preset.",
       "config.smart_routing_model": "Routing Model:",
       // Multi-Turn Context
+      "aggregator.context_pruning_title": "\u2702\uFE0F Cross-Candidate Context Pruning (Diff-Only Judge Context)",
+      "aggregator.context_pruning_desc": "Replaces unchanged base project files with compact unified diffs (---/+++ hunks) in the Judge prompt, slashing prompt tokens by up to 85%.",
+      "aggregator.context_pruning_lines": "Context lines around changes:",
+      "aggregator.semantic_cache_title": "\u26A1 Semantic Caching for Candidate Generations",
+      "aggregator.semantic_cache_desc": "Persists intermediate candidate outputs locally by deterministic SHA-256 fingerprint, eliminating duplicate API costs on retry or repeat requests.",
+      "aggregator.semantic_cache_ttl": "Cache TTL (hours):",
       "aggregator.multi_turn_title": "Multi-Turn Context & Diff Pruning",
       "aggregator.multi_turn_desc": "Retain conversation context across turns while pruning duplicate code blocks.",
       // UI States & Errors
@@ -207,7 +213,18 @@ window.__ModuleLoader__.load({
       "workbench.promote_btn": "Promote Harmonized Files to Workspace",
       "workbench.promoted_ok": "\u2705 Harmonized deliverable promoted to workspace root!",
       "workbench.pros": "Pros:",
-      "workbench.cons": "Cons:"
+      "workbench.cons": "Cons:",
+      "aggregator.self_consistency_title": "\u{1F3B2} Self-Consistency Temperature Sampling (Single-Model Diversity)",
+      "aggregator.self_consistency_desc": "Expands a single reference model into multiple parallel samples with varied temperatures and personas, bringing MoA benefits to single-model setups.",
+      "aggregator.self_consistency_samples": "Samples:",
+      "aggregator.escalation_title": "\u2696\uFE0F Dynamic Consensus Threshold & Judge Escalation",
+      "aggregator.escalation_desc": "Detects divergence across candidates. When consensus is weak, automatically upgrades to a senior flagship judge or convenes a 3-judge panel.",
+      "aggregator.escalation_policy": "Escalation Policy:",
+      "aggregator.escalation_policy_single": "Standard Single Judge (No Escalation)",
+      "aggregator.escalation_policy_upgrade": "Auto-Upgrade to Senior Judge on Divergence",
+      "aggregator.escalation_policy_council": "Convene 3-Judge Majority Council on Divergence",
+      "aggregator.escalation_threshold": "Divergence Threshold:",
+      "aggregator.escalation_judge_label": "Senior Judge:"
     };
     const zh = {
       title: "\u667A\u80FD\u4F53\u6DF7\u5408 (MoA)",
@@ -365,6 +382,12 @@ window.__ModuleLoader__.load({
       "config.smart_routing_desc": "\u5206\u6790\u4EFB\u52A1\u590D\u6742\u5EA6\u5E76\u81EA\u52A8\u5339\u914D\u6700\u4F73\u9884\u8BBE\u3002",
       "config.smart_routing_model": "\u5206\u6D41\u51B3\u7B56\u6A21\u578B\uFF1A",
       // Multi-Turn Context
+      "aggregator.context_pruning_title": "\u2702\uFE0F \u5019\u9009\u8DE8\u6A21\u578B\u4E0A\u4E0B\u6587\u7CBE\u7B80 (Judge \u4EC5\u5DEE\u5F02\u8865\u4E01)",
+      "aggregator.context_pruning_desc": "\u5728 Judge \u63D0\u793A\u8BCD\u4E2D\u5C06\u672A\u4FEE\u6539\u7684\u57FA\u7840\u9879\u76EE\u6587\u4EF6\u66FF\u6362\u4E3A\u7D27\u51D1\u7684\u7EDF\u4E00\u5DEE\u5F02\u5757 (---/+++)\uFF0C\u5728\u5927\u6587\u4EF6\u573A\u666F\u4E0B\u524A\u51CF\u9AD8\u8FBE 85% \u7684\u63D0\u793A\u8BCD Token\u3002",
+      "aggregator.context_pruning_lines": "\u5DEE\u5F02\u4E0A\u4E0B\u6587\u884C\u6570:",
+      "aggregator.semantic_cache_title": "\u26A1 \u5019\u9009\u751F\u6210\u8BED\u4E49\u7F13\u5B58",
+      "aggregator.semantic_cache_desc": "\u901A\u8FC7\u786E\u5B9A\u7684 SHA-256 \u6307\u7EB9\u5728\u672C\u5730\u6301\u4E45\u5316\u5019\u9009\u6A21\u578B\u4E2D\u95F4\u8F93\u51FA\uFF0C\u5728\u91CD\u8BD5\u6216\u91CD\u590D\u8FED\u4EE3\u4E2D\u6D88\u9664\u5197\u4F59 API \u8D39\u7528\u3002",
+      "aggregator.semantic_cache_ttl": "\u7F13\u5B58\u6709\u6548\u671F (\u5C0F\u65F6):",
       "aggregator.multi_turn_title": "\u591A\u8F6E\u5BF9\u8BDD\u4E0A\u4E0B\u6587\u4E0E\u5DEE\u5F02\u526A\u679D",
       "aggregator.multi_turn_desc": "\u8DE8\u8F6E\u6B21\u4FDD\u7559\u5BF9\u8BDD\u4E0A\u4E0B\u6587\u5E76\u526A\u679D\u91CD\u590D\u4EE3\u7801\u5757\u3002",
       // UI States & Errors
@@ -405,7 +428,18 @@ window.__ModuleLoader__.load({
       "workbench.promote_btn": "\u63D0\u5347\u7C98\u5408\u7ED3\u679C\u81F3\u9879\u76EE\u6839\u76EE\u5F55",
       "workbench.promoted_ok": "\u2705 \u7C98\u5408\u65B9\u6848\u5DF2\u6210\u529F\u63D0\u5347\u81F3\u9879\u76EE\u5DE5\u4F5C\u533A\uFF01",
       "workbench.pros": "\u4F18\u52BF\uFF1A",
-      "workbench.cons": "\u4E0D\u8DB3\uFF1A"
+      "workbench.cons": "\u4E0D\u8DB3\uFF1A",
+      "aggregator.self_consistency_title": "\u{1F3B2} \u5355\u6A21\u578B\u81EA\u6D3D\u6027\u6E29\u5EA6\u91C7\u6837 (Self-Consistency)",
+      "aggregator.self_consistency_desc": "\u5728\u4EC5\u914D\u7F6E\u5355\u6A21\u578B\u65F6\uFF0C\u751F\u6210\u4E0D\u540C\u6E29\u5EA6\u4E0E\u89D2\u8272\u7684\u591A\u4E2A\u5E76\u884C\u5019\u9009\u65B9\u6848\uFF0C\u8BA9\u672C\u5730 Ollama \u6216\u5355 Key \u4E5F\u4EAB\u6709 MoA \u805A\u5408\u4F18\u52BF\u3002",
+      "aggregator.self_consistency_samples": "\u91C7\u6837\u6570:",
+      "aggregator.escalation_title": "\u2696\uFE0F \u52A8\u6001\u5171\u8BC6\u9608\u503C\u4E0E\u88C1\u5224\u5347\u7EA7 (Judge Escalation)",
+      "aggregator.escalation_desc": "\u68C0\u6D4B\u5019\u9009\u65B9\u6848\u95F4\u7684\u5206\u6B67\u5EA6\u3002\u5F53\u5171\u8BC6\u8F83\u5F31\u65F6\uFF0C\u81EA\u52A8\u5347\u7EA7\u81F3\u9AD8\u9636\u65D7\u8230\u88C1\u5224\u6216\u7EC4\u5EFA 3 \u88C1\u5224\u591A\u6570\u5E2D\u3002",
+      "aggregator.escalation_policy": "\u5347\u7EA7\u7B56\u7565:",
+      "aggregator.escalation_policy_single": "\u6807\u51C6\u5355\u88C1\u5224 (\u4E0D\u5347\u7EA7)",
+      "aggregator.escalation_policy_upgrade": "\u5206\u6B67\u65F6\u81EA\u52A8\u5347\u7EA7\u81F3\u9AD8\u9636\u88C1\u5224",
+      "aggregator.escalation_policy_council": "\u5206\u6B67\u65F6\u7EC4\u5EFA 3 \u88C1\u5224\u591A\u6570\u51B3\u7B56\u5E2D",
+      "aggregator.escalation_threshold": "\u5206\u6B67\u9608\u503C:",
+      "aggregator.escalation_judge_label": "\u9AD8\u9636\u88C1\u5224\u6A21\u578B:"
     };
     function makeT(dict, fallback) {
       return function t(key, vars) {
@@ -2378,6 +2412,153 @@ window.__ModuleLoader__.load({
                   t("aggregator.multi_turn_desc") || "Retain conversation context across turns while pruning duplicate code blocks."
                 )
               ),
+              /* Context Pruning (#305) & Semantic Caching (#318) */
+              React.createElement(
+                "div",
+                { style: { display: "flex", flexDirection: "column", gap: 6, padding: "8px 12px", background: "var(--dsw-alias-bg-layer-2)", borderRadius: 8, border: "1px solid var(--dsw-alias-border-l2)", marginTop: 8 } },
+                React.createElement(
+                  "label",
+                  { style: { display: "flex", alignItems: "center", gap: 8, cursor: "pointer", fontSize: 13, fontWeight: 500 } },
+                  React.createElement("input", {
+                    type: "checkbox",
+                    checked: currentPreset.context_pruning_enabled !== false,
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, context_pruning_enabled: e.target.checked })),
+                    style: { accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))", cursor: "pointer" }
+                  }),
+                  t("aggregator.context_pruning_title") || "\u2702\uFE0F Cross-Candidate Context Pruning (Diff-Only Judge Context)"
+                ),
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)", marginLeft: 22 } },
+                  t("aggregator.context_pruning_desc") || "Replaces unchanged base project files with compact unified diffs (---/+++ hunks) in the Judge prompt, slashing prompt tokens by up to 85%."
+                ),
+                React.createElement(
+                  "label",
+                  { style: { display: "flex", alignItems: "center", gap: 8, cursor: "pointer", fontSize: 13, fontWeight: 500, marginTop: 4 } },
+                  React.createElement("input", {
+                    type: "checkbox",
+                    checked: Boolean(currentPreset.semantic_cache_enabled),
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, semantic_cache_enabled: e.target.checked })),
+                    style: { accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))", cursor: "pointer" }
+                  }),
+                  t("aggregator.semantic_cache_title") || "\u26A1 Semantic Caching for Candidate Generations"
+                ),
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)", marginLeft: 22 } },
+                  t("aggregator.semantic_cache_desc") || "Persists intermediate candidate outputs locally by deterministic SHA-256 fingerprint, eliminating duplicate API costs on retry or repeat requests."
+                )
+              ),
+              /* Self-Consistency Temperature Sampling (#301) */
+              React.createElement(
+                "div",
+                { style: { display: "flex", flexDirection: "column", gap: 6, padding: "8px 12px", background: "var(--dsw-alias-bg-layer-2)", borderRadius: 8, border: "1px solid var(--dsw-alias-border-l2)", marginTop: 8 } },
+                React.createElement(
+                  "label",
+                  { style: { display: "flex", alignItems: "center", gap: 8, cursor: "pointer", fontSize: 13, fontWeight: 500 } },
+                  React.createElement("input", {
+                    type: "checkbox",
+                    checked: Boolean(currentPreset.self_consistency_enabled),
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, self_consistency_enabled: e.target.checked })),
+                    style: { accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))", cursor: "pointer" }
+                  }),
+                  t("aggregator.self_consistency_title") || "\u{1F3B2} Self-Consistency Temperature Sampling (Single-Model Diversity)"
+                ),
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)", marginLeft: 22 } },
+                  t("aggregator.self_consistency_desc") || "Expands a single reference model into multiple parallel samples with varied temperatures and personas, bringing MoA benefits to single-model setups."
+                ),
+                currentPreset.self_consistency_enabled && React.createElement(
+                  "div",
+                  { style: { marginLeft: 22, marginTop: 4, display: "flex", alignItems: "center", gap: 12 } },
+                  React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, (t("aggregator.self_consistency_samples") || "Samples:") + " " + (currentPreset.self_consistency_samples || 3)),
+                  React.createElement("input", {
+                    type: "range",
+                    min: 2,
+                    max: 5,
+                    value: currentPreset.self_consistency_samples || 3,
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, self_consistency_samples: Number(e.target.value) })),
+                    style: { width: 100, accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))" }
+                  })
+                )
+              ),
+              /* Dynamic Consensus Threshold & Multi-Judge Escalation (#300) */
+              React.createElement(
+                "div",
+                { style: { display: "flex", flexDirection: "column", gap: 6, padding: "8px 12px", background: "var(--dsw-alias-bg-layer-2)", borderRadius: 8, border: "1px solid var(--dsw-alias-border-l2)", marginTop: 8 } },
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 13, fontWeight: 600, color: "var(--dsw-alias-label-primary)" } },
+                  t("aggregator.escalation_title") || "\u2696\uFE0F Dynamic Consensus Threshold & Judge Escalation"
+                ),
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } },
+                  t("aggregator.escalation_desc") || "Detects divergence across candidates. When consensus is weak, automatically upgrades to a senior flagship judge or convenes a 3-judge panel."
+                ),
+                React.createElement(
+                  "div",
+                  { style: { display: "flex", alignItems: "center", gap: 8, marginTop: 4 } },
+                  React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, t("aggregator.escalation_policy") || "Escalation Policy:"),
+                  React.createElement(
+                    "select",
+                    {
+                      value: currentPreset.escalation_policy || "single",
+                      onChange: (e) => updateCurrentPreset((p) => ({ ...p, escalation_policy: e.target.value })),
+                      style: {
+                        padding: "4px 8px",
+                        fontSize: 12,
+                        borderRadius: 6,
+                        border: "1px solid var(--dsw-alias-border-l2)",
+                        background: "var(--dsw-alias-bg-layer-1)",
+                        color: "var(--dsw-alias-label-primary)"
+                      }
+                    },
+                    React.createElement("option", { value: "single" }, t("aggregator.escalation_policy_single") || "Standard Single Judge (No Escalation)"),
+                    React.createElement("option", { value: "auto_upgrade" }, t("aggregator.escalation_policy_upgrade") || "Auto-Upgrade to Senior Judge on Divergence"),
+                    React.createElement("option", { value: "council_majority" }, t("aggregator.escalation_policy_council") || "Convene 3-Judge Majority Council on Divergence")
+                  )
+                ),
+                currentPreset.escalation_policy && currentPreset.escalation_policy !== "single" && React.createElement(
+                  "div",
+                  { style: { display: "flex", flexDirection: "column", gap: 6, marginTop: 4 } },
+                  React.createElement(
+                    "div",
+                    { style: { display: "flex", alignItems: "center", gap: 12 } },
+                    React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, (t("aggregator.escalation_threshold") || "Divergence Threshold:") + " " + Math.round((currentPreset.escalation_disagreement_threshold ?? 0.4) * 100) + "%"),
+                    React.createElement("input", {
+                      type: "range",
+                      min: 10,
+                      max: 90,
+                      value: Math.round((currentPreset.escalation_disagreement_threshold ?? 0.4) * 100),
+                      onChange: (e) => updateCurrentPreset((p) => ({ ...p, escalation_disagreement_threshold: Number(e.target.value) / 100 })),
+                      style: { width: 120, accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))" }
+                    })
+                  ),
+                  currentPreset.escalation_policy === "auto_upgrade" && React.createElement(
+                    "div",
+                    { style: { display: "flex", alignItems: "center", gap: 8 } },
+                    React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, t("aggregator.escalation_judge_label") || "Senior Judge:"),
+                    React.createElement(
+                      "div",
+                      { style: { flex: 1, maxWidth: 300 } },
+                      React.createElement(SearchableModelPicker, {
+                        provider: currentPreset.escalation_judge?.provider || "",
+                        model: currentPreset.escalation_judge?.model || "",
+                        onChange: (prov, mod) => {
+                          updateCurrentPreset((p) => ({
+                            ...p,
+                            escalation_judge: { provider: prov, model: mod }
+                          }));
+                        },
+                        availableModels,
+                        t
+                      })
+                    )
+                  )
+                )
+              ),
               /* Fallback Judges Chain */
               React.createElement(
                 "div",

package/lib/events.js

@@ -7,8 +7,12 @@ export const MOA_EVENTS = {
   CANDIDATE_COMPLETE: 'moa/candidate-complete',
   SYNTAX_VALIDATION: 'moa/syntax-validation',
   EARLY_CONSENSUS: 'moa/early-consensus',
+  JUDGE_ESCALATION: 'moa/judge-escalation',
+  SELF_CONSISTENCY_EXPAND: 'moa/self-consistency-expand',
   CRITIQUE_COMPLETE: 'moa/critique-complete',
   JUDGE_VERDICT: 'moa/judge-verdict',
+  CONTEXT_PRUNING: 'moa/context-pruning',
+  CACHE_HIT: 'moa/cache-hit',
   RUN_FINISH: 'moa/run-finish',
 }
 
@@ -30,4 +34,4 @@ export function emitEvent(ctx, eventName, payload) {
     /* best-effort event dispatch: listener exceptions must never abort pipeline */
   }
 }
-
+

package/lib/moa-schema.js

@@ -79,6 +79,16 @@ export const PresetSchema = z.object({
   local_preflight_check: z.boolean().default(true),
   early_exit_consensus_enabled: z.boolean().default(false),
   early_exit_threshold: z.number().default(0.95),
+  context_pruning_enabled: z.boolean().default(true),
+  context_pruning_diff_lines: z.number().default(5),
+  semantic_cache_enabled: z.boolean().default(false),
+  semantic_cache_ttl_hours: z.number().default(168),
+  self_consistency_enabled: z.boolean().default(false),
+  self_consistency_samples: z.number().default(3),
+  self_consistency_temperatures: z.array(z.number()).default([0.2, 0.6, 0.9]),
+  escalation_policy: z.string().default('single'),
+  escalation_disagreement_threshold: z.number().default(0.40),
+  escalation_judge: ModelSlotSchema.default({ provider: '', model: '' }),
 })
 
 export const Config = z.object({
@@ -104,6 +114,16 @@ export const Config = z.object({
   local_preflight_check: z.boolean().default(true).volatile(),
   early_exit_consensus_enabled: z.boolean().default(false).volatile(),
   early_exit_threshold: z.number().default(0.95).volatile(),
+  context_pruning_enabled: z.boolean().default(true).volatile(),
+  context_pruning_diff_lines: z.number().default(5).volatile(),
+  semantic_cache_enabled: z.boolean().default(false).volatile(),
+  semantic_cache_ttl_hours: z.number().default(168).volatile(),
+  self_consistency_enabled: z.boolean().default(false).volatile(),
+  self_consistency_samples: z.number().default(3).volatile(),
+  self_consistency_temperatures: z.array(z.number()).default([0.2, 0.6, 0.9]).volatile(),
+  escalation_policy: z.string().default('single').volatile(),
+  escalation_disagreement_threshold: z.number().default(0.40).volatile(),
+  escalation_judge: ModelSlotSchema.default({ provider: '', model: '' }).volatile(),
   smart_routing_model: ModelSlotSchema.default({ provider: '', model: '' }).volatile(),
   prices: z.dict(PriceRow).default({}).volatile(),
   presets: z.array(PresetSchema).default([
@@ -120,6 +140,10 @@ export const Config = z.object({
       aggregator_temperature: 0.4,
       max_tokens: 4096,
       judge_criteria: '',
+      context_pruning_enabled: true,
+      context_pruning_diff_lines: 5,
+      semantic_cache_enabled: false,
+      semantic_cache_ttl_hours: 168,
     },
     {
       name: 'fast',
@@ -133,6 +157,10 @@ export const Config = z.object({
       aggregator_temperature: 0.2,
       max_tokens: 4096,
       judge_criteria: '',
+      context_pruning_enabled: true,
+      context_pruning_diff_lines: 5,
+      semantic_cache_enabled: false,
+      semantic_cache_ttl_hours: 168,
     },
     {
       name: 'deep-reasoning',
@@ -165,4 +193,4 @@ export function plainConfig(value) {
   }
   return value
 }
-
+

package/lib/pipeline/candidates.js

@@ -1,3 +1,4 @@
+import { createCachingCallLlm } from './semantic-cache.js'
 import { runSpeculativeMoa } from '../moa-speculative.js'
 import { runAdversarialTddLoop } from '../moa-adversarial-tdd.js'
 import { assignAdaptivePersonas } from '../moa-adaptive-personas.js'
@@ -33,7 +34,19 @@ export async function stageCandidateRound1({
   testGateEnabled,
   testCommand,
   execFn,
+  semanticCacheEnabled,
+  semanticCacheTtlHours,
+  ctx = null,
 }) {
+  const isCacheEnabled = Boolean(preset?.semantic_cache_enabled || semanticCacheEnabled)
+  const effectiveCallLlm = isCacheEnabled
+    ? createCachingCallLlm(callLlm, {
+        enabled: true,
+        ttlMs: (semanticCacheTtlHours || preset?.semantic_cache_ttl_hours || 168) * 60 * 60 * 1000,
+        cwd,
+        ctx,
+      })
+    : callLlm
   const lastMsgText = enrichedMessages[enrichedMessages.length - 1]?.content || ''
   const adaptiveRefs = preset?.adaptive_personas_enabled
     ? assignAdaptivePersonas(effectiveReferences, typeof lastMsgText === 'string' ? lastMsgText : '').references
@@ -52,7 +65,7 @@ export async function stageCandidateRound1({
         prices,
         signal,
       },
-      callLlm,
+      effectiveCallLlm,
       onProgress
     )
     if (!specRes.fallbackToStandard && Array.isArray(specRes.referenceOutputs)) {
@@ -62,7 +75,7 @@ export async function stageCandidateRound1({
 
   if (!referenceOutputs) {
     referenceOutputs = preset?.subagent_swarm_enabled
-    ? await runSubagentSwarm(adaptiveRefs, enrichedMessages, { temperature: refTemp, maxTokens, signal, cwd, runId }, callLlm, onProgress)
+    ? await runSubagentSwarm(adaptiveRefs, enrichedMessages, { temperature: refTemp, maxTokens, signal, cwd, runId }, effectiveCallLlm, onProgress)
     : await runReferencesParallel(
     adaptiveRefs,
     enrichedMessages,
@@ -80,7 +93,7 @@ export async function stageCandidateRound1({
       maxRetries: candidateRetries,
       signal,
     },
-    callLlm,
+    effectiveCallLlm,
     onProgress
   )
   }