@goodandready/dsh-moa 0.2.78 → 0.2.80

package/README.md

@@ -58,6 +58,8 @@ Single-model AI generation often suffers from blind spots, single-perspective bi
 15. **Mutation Testing Gate for Candidate Tests (#316)**: Injects AST-level fault mutations to compute Mutation Score (killed vs survived mutants), weeding out tautological assertions and fake test suites.
 16. **Hybrid Private Edge MoA & Cloud Judge Sanitizer (#306)**: Preserves confidentiality with local edge proposers on MiniPC while scrubbing absolute paths, internal IPs, and API secrets before external Cloud Judge arbitration.
 17. **Heterogeneous Speculative Decoding (#317)**: High-throughput local edge draft coupled with single-pass cloud model verification, slashing response latency by 2-3x.
+18. **Cost/Quality Pareto Frontier Slider (#307)**: Interactive trade-off slider mapping cost vs quality along the Pareto Frontier with real-time turn cost & latency estimation.
+19. **Hard Token Budget Guard (#319)**: Pre-flight financial cost ceiling with dynamic auto-scaling of cloud models to local edge to guarantee turn budgets.
 
 ---
 

package/README.ru.md

@@ -58,6 +58,8 @@
 15. **Мутационное тестирование тестов кандидатов (#316)**: Внедрение AST-мутаций кода для расчёта Mutation Score (убитые vs выжившие мутанты), устраняющее ложноположительные и тавтологические тесты.
 16. **Гибридный приватный Edge MoA (#306)**: Локальные генераторы на MiniPC сохраняют секреты и кодовую базу в контуре, маскируя пути, IP и токены перед отправкой судье в облако.
 17. **Гетерогенное спекулятивное декодирование (#317)**: Быстрый черновик от локальной edge-модели с пакетной валидацией и доработкой флагманом в облаке с ускорением в 2-3 раза.
+18. **Слайдер фронтира Парето (Стоимость vs Качество) (#307)**: Интерактивный регулятор баланса затрат и качества консенсуса с реактивным прогнозом цены и задержки.
+19. **Защитный барьер бюджета токенов (#319)**: Строгий финансовый лимит стоимости сессии с динамическим авто-масштабированием и заменой облачных слотов на локальные.
 
 ---
 

package/README.zh.md

@@ -58,6 +58,8 @@
 15. **候选测试套件变异测试关卡 (#316)**：注入 AST 级别故障变异以计算变异得分（消灭 vs 存活变异体），剔除恒真废测试与虚假测试套件。
 16. **混合隐私边缘 MoA 与云端裁判脱敏 (#306)**：本地 MiniPC 边缘模型在内网读取代码生成方案，在提交给外部云端裁判前自动脱敏绝对路径、内网 IP 与 API 密钥。
 17. **异构投机解码加速 (#317)**：本地小模型快速生成投机代码草稿块，云端旗舰模型单次批处理验证与完善，首包延迟降低 2-3 倍。
+18. **成本与质量帕累托前沿滑块 (#307)**：互动式调节成本、质量与延迟的帕累托平衡，实时预估单轮开销与耗时。
+19. **刚性 Token 预算保护与动态缩放 (#319)**：发送前严守费用上限，超出时自动将昂贵云端模型降级为本地边缘模型以确保不超支。
 
 ---
 

package/lib/client.js

@@ -240,7 +240,23 @@ window.__ModuleLoader__.load({
       "aggregator.privacy_gate_title": "\u{1F6E1}\uFE0F Hybrid Private Edge MoA (Local Edge Proposers + Cloud Judge)",
       "aggregator.privacy_gate_desc": "Scans and redacts proprietary secrets, local paths, and private network IPs before forwarding proposals to external cloud judges.",
       "aggregator.speculative_gate_title": "\u26A1 Heterogeneous Speculative Decoding (Local Draft + Cloud Verifier)",
-      "aggregator.speculative_gate_desc": "Lightweight local edge model generates high-speed token drafts verified and completed in one fast pass by the cloud model."
+      "aggregator.speculative_gate_desc": "Lightweight local edge model generates high-speed token drafts verified and completed in one fast pass by the cloud model.",
+      "aggregator.pareto_slider_title": "\u{1F4C8} Cost vs Quality Pareto Frontier Slider",
+      "aggregator.pareto_slider_desc": "Reactive balance from 100% free local edge models to ultra-rigorous flagship multi-judge consensus.",
+      "aggregator.pareto_pos_label": "Frontier Position:",
+      "aggregator.hard_budget_title": "\u{1F6E1}\uFE0F Hard Token Budget Guard with Auto-Scaling",
+      "aggregator.hard_budget_desc": "Pre-calculates turn costs against a hard financial ceiling, automatically scaling down or halting execution.",
+      "aggregator.hard_budget_limit_label": "Max Cost Per Turn (USD):",
+      "aggregator.hard_budget_policy_label": "Exceed Policy:",
+      "aggregator.hard_budget_policy_downgrade": "Auto-Downgrade to Local/Economic",
+      "aggregator.hard_budget_policy_fail": "Fail-Closed (Halt Execution)",
+      "aggregator.rebuttal_debate_title": "\u{1F5E3}\uFE0F Multi-Round Rebuttal Debate",
+      "aggregator.rebuttal_debate_desc": "Candidates cross-examine peer solutions and expose flaws before judge arbitration.",
+      "aggregator.rebuttal_rounds_label": "Debate Rounds:",
+      "aggregator.embedding_clustering_title": "\u{1F9ED} Blind Embedding Clustering",
+      "aggregator.embedding_clustering_desc": "Bypass LLM Judge when candidate embeddings converge into a dominant cluster (>= threshold).",
+      "aggregator.embedding_threshold_label": "Consensus Similarity Threshold:",
+      "aggregator.fallback_to_judge_label": "Fallback to Judge if Opinion Splits"
     };
     const zh = {
       title: "\u667A\u80FD\u4F53\u6DF7\u5408 (MoA)",
@@ -471,7 +487,23 @@ window.__ModuleLoader__.load({
       "aggregator.privacy_gate_title": "\u{1F6E1}\uFE0F \u6DF7\u5408\u9690\u79C1\u8FB9\u7F18 MoA (\u672C\u5730\u751F\u6210 + \u4E91\u7AEF\u88C1\u5224)",
       "aggregator.privacy_gate_desc": "\u5728\u5C06\u5019\u9009\u63D0\u6848\u53D1\u9001\u7ED9\u5916\u90E8\u4E91\u7AEF\u88C1\u5224\u4E4B\u524D\uFF0C\u626B\u63CF\u5E76\u8131\u654F\u4E13\u6709\u5BC6\u94A5\u3001\u672C\u5730\u7EDD\u5BF9\u8DEF\u5F84\u4E0E\u79C1\u6709\u7F51\u7EDC IP\u3002",
       "aggregator.speculative_gate_title": "\u26A1 \u5F02\u6784\u6295\u673A\u89E3\u7801 (\u672C\u5730\u8349\u7A3F + \u4E91\u7AEF\u9A8C\u8BC1)",
-      "aggregator.speculative_gate_desc": "\u8F7B\u91CF\u7EA7\u672C\u5730\u8FB9\u7F18\u6A21\u578B\u751F\u6210\u9AD8\u901F\u8349\u7A3F\uFF0C\u7531\u5F3A\u5927\u7684\u4E91\u7AEF\u6A21\u578B\u4E00\u6B21\u6027\u5FEB\u901F\u9A8C\u8BC1\u5E76\u5B8C\u5584\u3002"
+      "aggregator.speculative_gate_desc": "\u8F7B\u91CF\u7EA7\u672C\u5730\u8FB9\u7F18\u6A21\u578B\u751F\u6210\u9AD8\u901F\u8349\u7A3F\uFF0C\u7531\u5F3A\u5927\u7684\u4E91\u7AEF\u6A21\u578B\u4E00\u6B21\u6027\u5FEB\u901F\u9A8C\u8BC1\u5E76\u5B8C\u5584\u3002",
+      "aggregator.pareto_slider_title": "\u{1F4C8} \u6210\u672C\u4E0E\u8D28\u91CF\u5E15\u7D2F\u6258\u524D\u6CBF\u6ED1\u5757 (Pareto Frontier)",
+      "aggregator.pareto_slider_desc": "\u4ECE 100% \u514D\u8D39\u672C\u5730\u8FB9\u7F18\u6A21\u578B\u5230\u8D85\u4E25\u8C28\u65D7\u8230\u591A\u88C1\u5224\u5171\u8BC6\u7684\u54CD\u5E94\u5F0F\u5E73\u8861\u8C03\u8282\u3002",
+      "aggregator.pareto_pos_label": "\u524D\u6CBF\u5E73\u8861\u4F4D\u7F6E:",
+      "aggregator.hard_budget_title": "\u{1F6E1}\uFE0F \u521A\u6027 Token \u9884\u7B97\u4FDD\u62A4\u4E0E\u52A8\u6001\u964D\u7EA7\u7F29\u653E",
+      "aggregator.hard_budget_desc": "\u5728\u53D1\u9001\u524D\u4E25\u683C\u6838\u7B97\u6574\u8F6E\u9884\u6D4B\u8D39\u7528\uFF0C\u81EA\u52A8\u964D\u7EA7\u81F3\u7ECF\u6D4E/\u672C\u5730\u6A21\u578B\u6216\u963B\u6B62\u8D85\u51FA\u9884\u7B97\u3002",
+      "aggregator.hard_budget_limit_label": "\u5355\u8F6E\u9884\u7B97\u4E0A\u9650 (USD):",
+      "aggregator.hard_budget_policy_label": "\u8D85\u989D\u7B56\u7565:",
+      "aggregator.hard_budget_policy_downgrade": "\u81EA\u52A8\u964D\u7EA7\u81F3\u672C\u5730/\u7ECF\u6D4E\u6A21\u578B",
+      "aggregator.hard_budget_policy_fail": "\u5B89\u5168\u7194\u65AD (\u505C\u6B62\u6267\u884C)",
+      "aggregator.rebuttal_debate_title": "\u{1F5E3}\uFE0F \u591A\u8F6E\u53CD\u9A73\u8FA9\u8BBA\u673A\u5236",
+      "aggregator.rebuttal_debate_desc": "\u5019\u9009\u6A21\u578B\u5728\u88C1\u5224\u4EF2\u88C1\u524D\u76F8\u4E92\u4EA4\u53C9\u5BA1\u67E5\u5E76\u6307\u51FA\u5BF9\u65B9\u6F0F\u6D1E\u4E0E\u7F3A\u9677\u3002",
+      "aggregator.rebuttal_rounds_label": "\u8FA9\u8BBA\u8F6E\u6570:",
+      "aggregator.embedding_clustering_title": "\u{1F9ED} \u76F2\u5411\u91CF\u5D4C\u5165\u805A\u7C7B",
+      "aggregator.embedding_clustering_desc": "\u5F53\u5019\u9009\u65B9\u6848\u7684\u5411\u91CF\u5D4C\u5165\u9AD8\u5EA6\u6536\u655B\u5E76\u5F62\u6210\u4E3B\u5BFC\u805A\u7C7B\u65F6\uFF0C\u7ED5\u8FC7LLM\u88C1\u5224\u76F4\u63A5\u4EA7\u51FA\u8D28\u5FC3\u5019\u9009\u3002",
+      "aggregator.embedding_threshold_label": "\u5171\u8BC6\u76F8\u4F3C\u5EA6\u9608\u503C:",
+      "aggregator.fallback_to_judge_label": "\u610F\u89C1\u5206\u6B67\u65F6\u56DE\u9000\u81F3\u88C1\u5224"
     };
     function makeT(dict, fallback) {
       return function t(key, vars) {
@@ -2386,7 +2418,6 @@ window.__ModuleLoader__.load({
                   )
                 )
               ),
-              // --- src/client/86-card-aggregator-ext2.js ---
               /* Pre-Judge Local Syntax Gate (#303) & Early Semantic Consensus (#299) */
               React.createElement(
                 "div",
@@ -2424,6 +2455,86 @@ window.__ModuleLoader__.load({
                   t("aggregator.early_consensus_desc") || "Bypass the expensive judge round when reference models converge on equivalent code solutions."
                 )
               ),
+              /* Multi-Round Rebuttal Debate (#298) & Blind Embedding Clustering (#312) */
+              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.rebuttal_debate_enabled),
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, rebuttal_debate_enabled: e.target.checked })),
+                    style: { accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))", cursor: "pointer" }
+                  }),
+                  t("aggregator.rebuttal_debate_title") || "\u{1F5E3}\uFE0F Multi-Round Rebuttal Debate"
+                ),
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)", marginLeft: 22 } },
+                  t("aggregator.rebuttal_debate_desc") || "Candidates cross-examine peer solutions and expose flaws before judge arbitration."
+                ),
+                Boolean(currentPreset.rebuttal_debate_enabled) && React.createElement(
+                  "div",
+                  { style: { display: "flex", alignItems: "center", gap: 8, marginLeft: 22, marginTop: 4 } },
+                  React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, t("aggregator.rebuttal_rounds_label") || "Debate Rounds:"),
+                  React.createElement("input", {
+                    type: "number",
+                    min: 1,
+                    max: 3,
+                    value: currentPreset.rebuttal_rounds || 1,
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, rebuttal_rounds: Math.min(3, Math.max(1, Number(e.target.value) || 1)) })),
+                    style: { width: 50, padding: "2px 6px", fontSize: 12, borderRadius: 4, border: "1px solid var(--dsw-alias-border-l2)", background: "var(--dsw-alias-bg-layer-1)" }
+                  })
+                ),
+                React.createElement(
+                  "label",
+                  { style: { display: "flex", alignItems: "center", gap: 8, cursor: "pointer", fontSize: 13, fontWeight: 500, marginTop: 6 } },
+                  React.createElement("input", {
+                    type: "checkbox",
+                    checked: Boolean(currentPreset.embedding_clustering_enabled),
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, embedding_clustering_enabled: e.target.checked })),
+                    style: { accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))", cursor: "pointer" }
+                  }),
+                  t("aggregator.embedding_clustering_title") || "\u{1F9ED} Blind Embedding Clustering"
+                ),
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)", marginLeft: 22 } },
+                  t("aggregator.embedding_clustering_desc") || "Bypass LLM Judge when candidate embeddings converge into a dominant cluster (>= threshold)."
+                ),
+                Boolean(currentPreset.embedding_clustering_enabled) && React.createElement(
+                  "div",
+                  { style: { display: "flex", flexDirection: "column", gap: 4, marginLeft: 22, marginTop: 4 } },
+                  React.createElement(
+                    "div",
+                    { style: { display: "flex", alignItems: "center", gap: 8 } },
+                    React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, t("aggregator.embedding_threshold_label") || "Consensus Similarity Threshold:"),
+                    React.createElement("input", {
+                      type: "number",
+                      step: 0.01,
+                      min: 0.5,
+                      max: 0.99,
+                      value: currentPreset.embedding_consensus_threshold ?? 0.88,
+                      onChange: (e) => updateCurrentPreset((p) => ({ ...p, embedding_consensus_threshold: Number(e.target.value) || 0.88 })),
+                      style: { width: 60, padding: "2px 6px", fontSize: 12, borderRadius: 4, border: "1px solid var(--dsw-alias-border-l2)", background: "var(--dsw-alias-bg-layer-1)" }
+                    })
+                  ),
+                  React.createElement(
+                    "label",
+                    { style: { display: "flex", alignItems: "center", gap: 6, cursor: "pointer", fontSize: 12 } },
+                    React.createElement("input", {
+                      type: "checkbox",
+                      checked: currentPreset.fallback_to_judge_on_split !== false,
+                      onChange: (e) => updateCurrentPreset((p) => ({ ...p, fallback_to_judge_on_split: e.target.checked })),
+                      style: { accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))" }
+                    }),
+                    t("aggregator.fallback_to_judge_label") || "Fallback to Judge if Opinion Splits"
+                  )
+                )
+              ),
+              // --- src/client/86-card-aggregator-ext2.js ---
               /* Multi-Turn Context & Diff Pruning (#176) */
               React.createElement(
                 "div",
@@ -2760,6 +2871,96 @@ window.__ModuleLoader__.load({
                   t("aggregator.speculative_gate_desc") || "Lightweight local edge model generates high-speed token drafts verified and completed in one fast pass by the cloud model."
                 )
               ),
+              /* Pareto Frontier Slider (#307) */
+              React.createElement(
+                "div",
+                { style: { display: "flex", flexDirection: "column", gap: 6 } },
+                React.createElement(
+                  "label",
+                  { style: { display: "flex", alignItems: "center", gap: 8, fontSize: 13, fontWeight: 600, color: "var(--dsw-alias-label-primary)", cursor: "pointer" } },
+                  React.createElement("input", {
+                    type: "checkbox",
+                    checked: Boolean(currentPreset.pareto_slider_enabled),
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, pareto_slider_enabled: e.target.checked })),
+                    style: { accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))", cursor: "pointer" }
+                  }),
+                  t("aggregator.pareto_slider_title") || "\u{1F4C8} Cost vs Quality Pareto Frontier Slider"
+                ),
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)", marginLeft: 22 } },
+                  t("aggregator.pareto_slider_desc") || "Reactive balance from 100% free local edge models to ultra-rigorous flagship multi-judge consensus."
+                ),
+                currentPreset.pareto_slider_enabled && React.createElement(
+                  "div",
+                  { style: { marginLeft: 22, marginTop: 4, display: "flex", alignItems: "center", gap: 10 } },
+                  React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, t("aggregator.pareto_pos_label") || "Frontier Position:"),
+                  React.createElement("input", {
+                    type: "range",
+                    min: 0,
+                    max: 100,
+                    step: 5,
+                    value: currentPreset.pareto_slider_position ?? 50,
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, pareto_slider_position: Number(e.target.value) })),
+                    style: { cursor: "pointer", flex: 1, maxWidth: 200 }
+                  }),
+                  React.createElement("span", { style: { fontSize: 12, fontWeight: 600, color: "var(--dsw-alias-label-primary)" } }, String(currentPreset.pareto_slider_position ?? 50) + "%")
+                )
+              ),
+              /* Hard Token Budget Guard (#319) */
+              React.createElement(
+                "div",
+                { style: { display: "flex", flexDirection: "column", gap: 6 } },
+                React.createElement(
+                  "label",
+                  { style: { display: "flex", alignItems: "center", gap: 8, fontSize: 13, fontWeight: 600, color: "var(--dsw-alias-label-primary)", cursor: "pointer" } },
+                  React.createElement("input", {
+                    type: "checkbox",
+                    checked: Boolean(currentPreset.hard_budget_guard_enabled),
+                    onChange: (e) => updateCurrentPreset((p) => ({ ...p, hard_budget_guard_enabled: e.target.checked })),
+                    style: { accentColor: "var(--dsw-alias-state-brand-primary, var(--dsw-alias-label-primary))", cursor: "pointer" }
+                  }),
+                  t("aggregator.hard_budget_title") || "\u{1F6E1}\uFE0F Hard Token Budget Guard with Auto-Scaling"
+                ),
+                React.createElement(
+                  "div",
+                  { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)", marginLeft: 22 } },
+                  t("aggregator.hard_budget_desc") || "Pre-calculates turn costs against a hard financial ceiling, automatically scaling down or halting execution."
+                ),
+                currentPreset.hard_budget_guard_enabled && React.createElement(
+                  "div",
+                  { style: { marginLeft: 22, marginTop: 4, display: "flex", flexWrap: "wrap", alignItems: "center", gap: 12 } },
+                  React.createElement(
+                    "div",
+                    { style: { display: "flex", alignItems: "center", gap: 6 } },
+                    React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, t("aggregator.hard_budget_limit_label") || "Max Cost (USD):"),
+                    React.createElement("input", {
+                      type: "number",
+                      min: 1e-3,
+                      max: 10,
+                      step: 5e-3,
+                      value: currentPreset.hard_budget_limit_usd ?? 0.02,
+                      onChange: (e) => updateCurrentPreset((p) => ({ ...p, hard_budget_limit_usd: Number(e.target.value) })),
+                      style: { width: 80, padding: "2px 6px", fontSize: 12, borderRadius: 4, border: "1px solid var(--dsw-alias-border-primary)" }
+                    })
+                  ),
+                  React.createElement(
+                    "div",
+                    { style: { display: "flex", alignItems: "center", gap: 6 } },
+                    React.createElement("span", { style: { fontSize: 12, color: "var(--dsw-alias-label-secondary)" } }, t("aggregator.hard_budget_policy_label") || "Policy:"),
+                    React.createElement(
+                      "select",
+                      {
+                        value: currentPreset.hard_budget_policy || "auto_downgrade",
+                        onChange: (e) => updateCurrentPreset((p) => ({ ...p, hard_budget_policy: e.target.value })),
+                        style: { padding: "2px 6px", fontSize: 12, borderRadius: 4, border: "1px solid var(--dsw-alias-border-primary)" }
+                      },
+                      React.createElement("option", { value: "auto_downgrade" }, t("aggregator.hard_budget_policy_downgrade") || "Auto-Downgrade"),
+                      React.createElement("option", { value: "fail_closed" }, t("aggregator.hard_budget_policy_fail") || "Fail-Closed")
+                    )
+                  )
+                )
+              ),
               /* Fallback Judges Chain */
               React.createElement(
                 "div",

package/lib/events.js

@@ -17,9 +17,13 @@ export const MOA_EVENTS = {
   MUTATION_COMPLETE: 'moa/mutation-complete',
   PRIVACY_SANITIZED: 'moa/privacy-sanitized',
   SPECULATIVE_DRAFT: 'moa/speculative-draft',
+  PARETO_ADJUSTED: 'moa/pareto-adjusted',
+  BUDGET_SCALED: 'moa/budget-scaled',
   CRITIQUE_COMPLETE: 'moa/critique-complete',
   JUDGE_VERDICT: 'moa/judge-verdict',
   CONTEXT_PRUNING: 'moa/context-pruning',
+  DEBATE_ROUND: 'moa/debate-round',
+  EMBEDDING_CLUSTER: 'moa/embedding-cluster',
   CACHE_HIT: 'moa/cache-hit',
   RUN_FINISH: 'moa/run-finish',
 }

package/lib/moa-schema.js

@@ -107,6 +107,17 @@ export const PresetSchema = z.object({
   redact_ips: z.boolean().default(true),
   speculative_draft_enabled: z.boolean().default(false),
   speculative_block_size: z.number().default(256),
+  pareto_slider_enabled: z.boolean().default(false),
+  pareto_slider_position: z.number().default(50),
+  hard_budget_guard_enabled: z.boolean().default(false),
+  hard_budget_limit_usd: z.number().default(0.02),
+  hard_budget_policy: z.string().default('auto_downgrade'),
+  rebuttal_debate_enabled: z.boolean().default(false),
+  rebuttal_rounds: z.number().default(1),
+  rebuttal_max_critique_tokens: z.number().default(1024),
+  embedding_clustering_enabled: z.boolean().default(false),
+  embedding_consensus_threshold: z.number().default(0.88),
+  fallback_to_judge_on_split: z.boolean().default(true),
 })
 
 export const Config = z.object({
@@ -160,6 +171,17 @@ export const Config = z.object({
   redact_ips: z.boolean().default(true).volatile(),
   speculative_draft_enabled: z.boolean().default(false).volatile(),
   speculative_block_size: z.number().default(256).volatile(),
+  pareto_slider_enabled: z.boolean().default(false).volatile(),
+  pareto_slider_position: z.number().default(50).volatile(),
+  hard_budget_guard_enabled: z.boolean().default(false).volatile(),
+  hard_budget_limit_usd: z.number().default(0.02).volatile(),
+  hard_budget_policy: z.string().default('auto_downgrade').volatile(),
+  rebuttal_debate_enabled: z.boolean().default(false).volatile(),
+  rebuttal_rounds: z.number().default(1).volatile(),
+  rebuttal_max_critique_tokens: z.number().default(1024).volatile(),
+  embedding_clustering_enabled: z.boolean().default(false).volatile(),
+  embedding_consensus_threshold: z.number().default(0.88).volatile(),
+  fallback_to_judge_on_split: z.boolean().default(true).volatile(),
   smart_routing_model: ModelSlotSchema.default({ provider: '', model: '' }).volatile(),
   prices: z.dict(PriceRow).default({}).volatile(),
   presets: z.array(PresetSchema).default([

package/lib/pipeline/budget-guard.js

@@ -0,0 +1,158 @@
+/**
+ * DeepSeek Harness Mixture of Agents (MoA) — Hard Token Budget Guard & Auto-Scaling (#319)
+ *
+ * Enforces strict financial limits on inference costs. Pre-calculates end-to-end turn
+ * expenses (proposers + multi-judge + synthesis) against hard_budget_limit_usd before dispatching.
+ *
+ * Supports two operational policies when anticipated cost exceeds limit:
+ * - auto_downgrade: Automatically substitutes costly cloud slots with zero-cost local edge
+ *   models or economic tiers, and scales down candidate slots until cost fits under the ceiling.
+ * - fail_closed: Halts execution immediately to eliminate unexpected API billing surprises.
+ */
+
+import { MOA_EVENTS, emitEvent } from '../events.js'
+import { estimateCandidateRunCost, estimateDownstreamCost } from '../moa-budget.js'
+
+/**
+ * Evaluates projected turn expenses and dynamically scales down ensemble if needed.
+ *
+ * @param {object} params
+ * @param {Array<object>} params.references
+ * @param {object} params.aggregator
+ * @param {number} params.limitUsd
+ * @param {string} [params.policy='auto_downgrade']
+ * @param {object} [params.prices={}]
+ * @param {number} [params.promptTokens=1500]
+ * @param {number} [params.expectedOutputTokens=2048]
+ * @param {object} [params.options]
+ * @returns {object} Budget evaluation result
+ */
+export function evaluateHardBudgetLimit({
+  references = [],
+  aggregator = {},
+  limitUsd = 0.02,
+  policy = 'auto_downgrade',
+  prices = {},
+  promptTokens = 1500,
+  expectedOutputTokens = 2048,
+  options = {},
+}) {
+  const { ctx, runId, onProgress } = options
+
+  // Calculate baseline projected cost
+  const candCost = estimateCandidateRunCost(references, prices, promptTokens, expectedOutputTokens)
+  const downstreamCost = estimateDownstreamCost(
+    aggregator,
+    [],
+    references.length,
+    prices,
+    expectedOutputTokens,
+    promptTokens
+  )
+  const initialProjectedCost = Number((candCost.totalEstimatedUsd + downstreamCost).toFixed(5))
+
+  if (initialProjectedCost <= limitUsd) {
+    return {
+      ok: true,
+      scaled: false,
+      references,
+      aggregator,
+      projectedCostUsd: initialProjectedCost,
+      initialProjectedCost,
+      limitUsd,
+      warning: null,
+    }
+  }
+
+  // Cost exceeds limit
+  if (policy === 'fail_closed') {
+    const errorMsg = `[BudgetGuard] Projected turn cost ($${initialProjectedCost}) exceeds hard limit ($${limitUsd}). Execution halted.`
+    if (typeof onProgress === 'function') {
+      onProgress(`🛑 *${errorMsg}*\n`)
+    }
+    return {
+      ok: false,
+      scaled: false,
+      error: errorMsg,
+      projectedCostUsd: initialProjectedCost,
+      initialProjectedCost,
+      limitUsd,
+    }
+  }
+
+  // policy: auto_downgrade
+  let workingRefs = [...references]
+  let workingAggregator = { ...aggregator }
+  let scaled = false
+
+  // Step 1: Replace expensive cloud proposers with local edge models (zero cost)
+  for (let i = workingRefs.length - 1; i >= 0; i--) {
+    const currentSlot = workingRefs[i]
+    if (currentSlot.provider !== 'ollama' && currentSlot.provider !== 'local') {
+      workingRefs[i] = {
+        ...currentSlot,
+        provider: 'ollama',
+        model: 'qwen2.5-coder:7b',
+        role_persona: currentSlot.role_persona || 'proposer',
+      }
+      scaled = true
+    }
+
+    const testCandCost = estimateCandidateRunCost(workingRefs, prices, promptTokens, expectedOutputTokens)
+    const testDownstream = estimateDownstreamCost(workingAggregator, [], workingRefs.length, prices, expectedOutputTokens, promptTokens)
+    if ((testCandCost.totalEstimatedUsd + testDownstream) <= limitUsd) {
+      break
+    }
+  }
+
+  // Step 2: If still exceeding, replace expensive aggregator with economical model or local
+  let currentCost = Number((estimateCandidateRunCost(workingRefs, prices, promptTokens, expectedOutputTokens).totalEstimatedUsd +
+    estimateDownstreamCost(workingAggregator, [], workingRefs.length, prices, expectedOutputTokens, promptTokens)).toFixed(5))
+
+  if (currentCost > limitUsd && workingAggregator.provider !== 'ollama') {
+    workingAggregator = { provider: 'deepseek', model: 'deepseek-chat' }
+    scaled = true
+    currentCost = Number((estimateCandidateRunCost(workingRefs, prices, promptTokens, expectedOutputTokens).totalEstimatedUsd +
+      estimateDownstreamCost(workingAggregator, [], workingRefs.length, prices, expectedOutputTokens, promptTokens)).toFixed(5))
+
+    if (currentCost > limitUsd) {
+      workingAggregator = { provider: 'ollama', model: 'qwen2.5-coder:7b' }
+      currentCost = 0.0
+    }
+  }
+
+  // Step 3: If still exceeding, prune candidates down to 1
+  if (currentCost > limitUsd && workingRefs.length > 1) {
+    workingRefs = [workingRefs[0]]
+    scaled = true
+    currentCost = Number((estimateCandidateRunCost(workingRefs, prices, promptTokens, expectedOutputTokens).totalEstimatedUsd +
+      estimateDownstreamCost(workingAggregator, [], workingRefs.length, prices, expectedOutputTokens, promptTokens)).toFixed(5))
+  }
+
+  if (scaled) {
+    if (typeof onProgress === 'function') {
+      onProgress(`🛡️ *Budget Guard Auto-Scaling*: Scaled ensemble from $${initialProjectedCost} to $${currentCost} to fit under $${limitUsd} ceiling.\n`)
+    }
+
+    if (ctx) {
+      emitEvent(ctx, MOA_EVENTS.BUDGET_SCALED, {
+        runId,
+        originalCostUsd: initialProjectedCost,
+        scaledCostUsd: currentCost,
+        limitUsd,
+        policy,
+      })
+    }
+  }
+
+  return {
+    ok: true,
+    scaled,
+    references: workingRefs,
+    aggregator: workingAggregator,
+    projectedCostUsd: currentCost,
+    initialProjectedCost,
+    limitUsd,
+    warning: scaled ? `Budget Guard Auto-Scaled: initial $${initialProjectedCost} $\\to$ $${currentCost} (ceiling $${limitUsd})` : null,
+  }
+}