@goodandready/dsh-moa 0.2.37 → 0.2.39

package/lib/index.js

@@ -36,15 +36,18 @@ export function apply(ctx, config) {
   if (ctx.logger) setLogger(ctx.logger)
   refreshCatalogInBackground()
 
-  let localConfig = plainConfig(config ?? {})
-  const getConfig = () => localConfig
+  let localOverrides = null
+  const getSourceConfig = () => {
+    const liveSource = plainConfig(ctx.config ?? config ?? {})
+    return localOverrides ? { ...liveSource, ...localOverrides } : liveSource
+  }
   const live = () => {
     try {
-      const raw = getConfig() ?? {}
+      const raw = getSourceConfig() ?? {}
       const validated = plainConfig(Config(plainConfig(raw)))
-      return plainConfig(validated) ?? localConfig
+      return plainConfig(validated) ?? raw
     } catch {
-      return localConfig
+      return getSourceConfig()
     }
   }
 
@@ -72,17 +75,13 @@ export function apply(ctx, config) {
 
   const saveConfig = async (newFields) => {
     const plain = plainConfig(newFields)
-    localConfig = { ...localConfig, ...plain }
-    try {
-      if (settingsService && typeof settingsService.replace === 'function') {
-        await settingsService.replace(NS, plain)
-      } else if (settingsService && typeof settingsService.update === 'function') {
-        await settingsService.update(NS, plain)
-      }
-    } catch (err) {
-      logger.warn('[dsh-moa] Settings persistence warning:', err?.message || err)
+    if (settingsService && typeof settingsService.replace === 'function') {
+      await settingsService.replace(NS, plain)
+    } else if (settingsService && typeof settingsService.update === 'function') {
+      await settingsService.update(NS, plain)
     }
-    return localConfig
+    localOverrides = { ...(localOverrides || {}), ...plain }
+    return live()
   }
 
   const callLlm = createLlmCaller(ctx)
@@ -110,6 +109,8 @@ export function apply(ctx, config) {
     saveConfig,
     Config,
     plainConfig,
+    webServerPort: ctx.webServer?.port,
+    timeMachineEngine: ctx.get?.('timeMachineEngine') || ctx.timeMachineEngine,
   })
 
   // Session turn interceptor: route turn to real aggregator model & stream MoA synthesis
@@ -166,14 +167,15 @@ export function apply(ctx, config) {
       if (userText.startsWith('/moa')) {
         const cfg = live()
         if (cfg.enabled !== false) {
-          const parsed = parseMoACommand(userText, cfg.presets || []) || { prompt: userText, presetName: cfg.default_preset || 'default' }
-          const isExplicitPreset = userText.includes('--preset') || userText.includes('-p ')
+          const effectiveDefault = cfg.default_preset || 'default'
+          const parsed = parseMoACommand(userText, cfg.presets || [], effectiveDefault) || { prompt: userText, presetName: effectiveDefault, isExplicit: false }
+          const isExplicitPreset = Boolean(parsed.isExplicit || userText.includes('--preset') || userText.includes('-p '))
           if (!isExplicitPreset && (cfg.smart_routing_enabled || cfg.presets?.some((p) => p.smart_routing_enabled))) {
             try {
               const routed = await resolvePresetForPrompt({
                 prompt: parsed.prompt || userText,
                 presets: cfg.presets || [],
-                defaultPreset: parsed.presetName || cfg.default_preset || 'default',
+                defaultPreset: parsed.presetName || effectiveDefault,
                 routingModel: cfg.smart_routing_model,
                 callLlm,
                 enabled: true,
@@ -185,7 +187,12 @@ export function apply(ctx, config) {
               // fallback silently
             }
           }
-          const targetPreset = (cfg.presets || []).find((p) => p.name === parsed.presetName) || cfg.presets?.[0]
+          const targetPreset = (cfg.presets || []).find((p) => p.name === (parsed.presetName || effectiveDefault))
+            || (!isExplicitPreset ? (cfg.presets || []).find((p) => p.name === effectiveDefault) || cfg.presets?.[0] : null)
+          if (!targetPreset) {
+            logger.warn(`[dsh-moa] Unknown explicit preset "${parsed.presetName}" in /moa command.`)
+            return next()
+          }
           const aggProvider = targetPreset?.aggregator?.provider || ''
           const aggModel = targetPreset?.aggregator?.model || ''
           const sessCwd = event.cwd || event.session?.cwd || (event.session?.path ? path.dirname(event.session.path) : undefined) || process.cwd()

package/lib/moa-budget.js

@@ -31,6 +31,7 @@ export function estimateCandidateRunCost(slots = [], prices = {}, promptTokens =
 
 /**
  * Applies budget guardrails before initiating parallel candidate execution.
+ * Evaluates candidate runs, peer critique (Round 2) and downstream synthesis phases.
  */
 export function applyBudgetGuardrails({
   references = [],
@@ -39,6 +40,11 @@ export function applyBudgetGuardrails({
   action = 'trim', // 'trim' | 'abort'
   prices = {},
   promptLength = 1000,
+  messages = [],
+  maxTokens = 2048,
+  peerCritiqueEnabled = false,
+  aggregator = null,
+  judgeModels = [],
 }) {
   if (!enabled || typeof maxBudgetUsd !== 'number' || maxBudgetUsd <= 0 || references.length === 0) {
     return {
@@ -49,15 +55,52 @@ export function applyBudgetGuardrails({
     }
   }
 
-  const promptTokens = Math.max(50, Math.round(promptLength / 4))
-  const { totalEstimatedUsd, slotEstimates } = estimateCandidateRunCost(references, prices, promptTokens)
+  // Calculate full input tokens from userPrompt length + messages context
+  let contextChars = Number(promptLength) || 1000
+  if (Array.isArray(messages) && messages.length > 0) {
+    for (const m of messages) {
+      if (typeof m?.content === 'string') {
+        contextChars += m.content.length
+      } else if (Array.isArray(m?.content)) {
+        for (const part of m.content) {
+          if (part?.text) contextChars += part.text.length
+        }
+      }
+    }
+  }
+  const promptTokens = Math.max(50, Math.round(contextChars / 4))
+  const expectedOutputTokens = typeof maxTokens === 'number' && maxTokens > 0 ? maxTokens : 2048
+
+  // Base candidate cost per slot (Round 1)
+  const { totalEstimatedUsd, slotEstimates } = estimateCandidateRunCost(references, prices, promptTokens, expectedOutputTokens)
+
+  // Estimate fixed cost for downstream phases (Aggregator / Judge panel)
+  let downstreamUsd = 0
+  if (aggregator?.provider && aggregator?.model) {
+    const aggInput = promptTokens + expectedOutputTokens * references.length
+    const aggCost = estimateTokenCost(aggregator, { inputTokens: aggInput, outputTokens: expectedOutputTokens }, prices)
+    downstreamUsd += aggCost?.costUsd || 0
+  }
+  if (Array.isArray(judgeModels) && judgeModels.length > 0) {
+    for (const jm of judgeModels) {
+      if (jm?.provider && jm?.model) {
+        const jInput = promptTokens + expectedOutputTokens * references.length
+        const jCost = estimateTokenCost(jm, { inputTokens: jInput, outputTokens: expectedOutputTokens }, prices)
+        downstreamUsd += jCost?.costUsd || 0
+      }
+    }
+  }
+
+  // Multiplier if peer critique (Round 2) is enabled: each candidate runs another turn with input from all peers
+  const roundMultiplier = peerCritiqueEnabled ? 2 : 1
+  const fullEstimatedUsd = Number(((totalEstimatedUsd * roundMultiplier) + downstreamUsd).toFixed(6))
 
-  if (totalEstimatedUsd <= maxBudgetUsd) {
+  if (fullEstimatedUsd <= maxBudgetUsd) {
     return {
       allowed: true,
       references,
       action: 'pass',
-      estimatedCostUsd: totalEstimatedUsd,
+      estimatedCostUsd: fullEstimatedUsd,
     }
   }
 
@@ -66,9 +109,9 @@ export function applyBudgetGuardrails({
       allowed: false,
       references: [],
       action: 'abort',
-      estimatedCostUsd: totalEstimatedUsd,
+      estimatedCostUsd: fullEstimatedUsd,
       maxBudgetUsd,
-      reason: `Estimated MoA run cost ($${totalEstimatedUsd.toFixed(4)}) exceeds configured max budget ($${maxBudgetUsd.toFixed(4)}).`,
+      reason: `Estimated MoA run cost ($${fullEstimatedUsd.toFixed(4)}) exceeds configured max budget ($${maxBudgetUsd.toFixed(4)}).`,
     }
   }
 
@@ -78,9 +121,23 @@ export function applyBudgetGuardrails({
   let cumulative = 0
 
   for (const item of sorted) {
-    if (cumulative + item.costUsd <= maxBudgetUsd || kept.length === 0) {
+    const candidateCost = item.costUsd * roundMultiplier
+    if (cumulative + candidateCost <= maxBudgetUsd) {
       kept.push(item.slot)
-      cumulative += item.costUsd
+      cumulative += candidateCost
+    }
+  }
+
+  if (kept.length === 0) {
+    return {
+      allowed: false,
+      references: [],
+      action: 'trim',
+      originalCount: references.length,
+      trimmedCount: 0,
+      estimatedCostUsd: Number((sorted[0]?.costUsd * roundMultiplier || 0).toFixed(6)),
+      maxBudgetUsd,
+      reason: `Cannot fit any candidate model within budget ($${maxBudgetUsd.toFixed(4)}). Cheapest candidate requires $${((sorted[0]?.costUsd || 0) * roundMultiplier).toFixed(4)}.`,
     }
   }
 

package/lib/moa-parser.js

@@ -40,7 +40,7 @@ export function parseRecommendedAssembler(judgeText, defaultIndex = 1, candidate
 /**
  * Parses a `/moa [preset] <prompt>` command invocation.
  */
-export function parseMoACommand(text, presets = []) {
+export function parseMoACommand(text, presets = [], defaultPreset = undefined) {
   if (typeof text !== 'string' || !text.startsWith('/moa')) {
     return null
   }
@@ -59,8 +59,9 @@ export function parseMoACommand(text, presets = []) {
   const remainder = text.slice(4).trim()
   if (!remainder) {
     return {
-      presetName: 'default',
+      presetName: defaultPreset,
       prompt: '',
+      isExplicit: false,
     }
   }
 
@@ -69,6 +70,16 @@ export function parseMoACommand(text, presets = []) {
     return {
       presetName: matchPreset[1],
       prompt: matchPreset[2] || '',
+      isExplicit: true,
+    }
+  }
+
+  const matchShortPreset = /^-p\s+([a-zA-Z0-9_-]+)\s*(.*)/s.exec(remainder)
+  if (matchShortPreset) {
+    return {
+      presetName: matchShortPreset[1],
+      prompt: matchShortPreset[2] || '',
+      isExplicit: true,
     }
   }
 
@@ -80,13 +91,15 @@ export function parseMoACommand(text, presets = []) {
       return {
         presetName: matched.name,
         prompt: parts.slice(1).join(' ').trim(),
+        isExplicit: true,
       }
     }
   }
 
   return {
-    presetName: 'default',
+    presetName: defaultPreset,
     prompt: remainder,
+    isExplicit: false,
   }
 }
 

package/lib/moa-runner.js

@@ -12,7 +12,6 @@ import { executeMultiJudgePanel, buildCompositeBlockDirectives } from './moa-mul
 import { applyBudgetGuardrails } from './moa-budget.js'
 import { extractPriorTurnBaseline, pruneMultiTurnMessages } from './moa-context.js'
 import { generateMoABenchmarkReport } from './moa-report.js'
-
 // Re-exports for consumers & backward compatibility
 export { slotLabel, cleanAdvisoryMessages, isBroadPromptRequiringQuestions, buildQuestionSynthesisPrompt, buildCuratorSynthesisPrompt, buildSynthesisPrompt, ANTIPATTERNS_RUBRIC } from './moa-prompts.js'
 export { parseWinnerIndex, parseRecommendedAssembler, parseMoACommand, stripOrSummarizeCode, formatMoAResponse } from './moa-parser.js'
@@ -20,7 +19,6 @@ export { estimateTokenCost, summarizeMoAUsage } from './pricing.js'
 export { REFERENCE_SYSTEM_PROMPT, callWithTransientRetry, runReferencesParallel } from './moa-candidates.js'
 export { executeTestGateForCandidates, runCandidateTestGate } from './moa-test-gate.js'
 export { streamMoATurn } from './moa-stream.js'
-
 /**
  * Executes the full Mixture of Agents pipeline.
  */
@@ -36,36 +34,20 @@ export async function runMoAPipeline({
   liveCanvas = null,
   onStreamDelta = null,
   signal = null,
-  testGateEnabled = null,
-  testCommand = null,
-  execFn = null,
-  webServerPort = null,
-  timeMachineEngine = null,
-  timeMachineUrl = null,
-  force = isTestEnvironment() ? true : false,
-  checkpoint = true,
-  checkpointFn = null,
+  testGateEnabled = null, testCommand = null, execFn = null,
+  webServerPort = null, timeMachineEngine = null, timeMachineUrl = null,
+  force = isTestEnvironment() ? true : false, checkpoint = true, checkpointFn = null, runId: customRunId = null,
 }) {
-  const promoteOpts = {
-    webServerPort,
-    timeMachineEngine,
-    timeMachineUrl,
-    force: Boolean(force),
-    checkpoint,
-    checkpointFn,
-  }
+  const promoteOpts = { webServerPort, timeMachineEngine, timeMachineUrl, force: Boolean(force), checkpoint, checkpointFn }
   if (signal?.aborted) return { error: new Error('Turn aborted') }
   const startTime = Date.now()
-
   // 1. Resolve configurations
   const referenceModels = Array.isArray(preset?.reference_models) && preset.reference_models.length > 0
     ? preset.reference_models : [{ provider: '', model: '' }]
   const primaryJudge = preset?.aggregator?.provider && preset?.aggregator?.model
     ? preset.aggregator : { provider: '', model: '' }
-
   const fallbackJudges = Array.isArray(preset?.aggregator_fallbacks) ? preset.aggregator_fallbacks : []
   const judgesChain = [primaryJudge, ...fallbackJudges]
-
   const refTemp = typeof preset?.reference_temperature === 'number' ? preset.reference_temperature : 0.6
   const aggTemp = typeof preset?.aggregator_temperature === 'number' ? preset.aggregator_temperature : 0.4
   const maxTokens = typeof preset?.max_tokens === 'number' ? preset.max_tokens : 4096
@@ -76,8 +58,7 @@ export async function runMoAPipeline({
   const candidateRetries = 1, refTimeoutSec = typeof preset?.reference_timeout_sec === 'number' ? preset.reference_timeout_sec : 60
   const aggTimeoutSec = typeof preset?.aggregator_timeout_sec === 'number' ? preset.aggregator_timeout_sec : 180
   const isBlindEvaluation = Boolean(preset?.blind_evaluation), isPeerCritiqueEnabled = Boolean(preset?.peer_critique_enabled)
-  const allowCandidateOverride = Boolean(preset?.allow_candidate_override), runId = crypto.randomUUID()
-
+  const allowCandidateOverride = Boolean(preset?.allow_candidate_override), runId = customRunId || null
   // Feature 6: Budget Guardrail check
   const budgetCheck = applyBudgetGuardrails({
     references: referenceModels,
@@ -86,6 +67,11 @@ export async function runMoAPipeline({
     action: preset?.budget_action || 'trim',
     prices,
     promptLength: userPrompt?.length || 1000,
+    messages,
+    maxTokens,
+    peerCritiqueEnabled: isPeerCritiqueEnabled,
+    aggregator: primaryJudge,
+    judgeModels: preset?.multi_judge_enabled ? preset?.judge_models : [],
   })
   if (!budgetCheck.allowed) {
     return {
@@ -109,7 +95,6 @@ export async function runMoAPipeline({
   if (budgetCheck.action === 'trim' && typeof onProgress === 'function') {
     onProgress(`✂️ *${budgetCheck.reason}*\n`)
   }
-
   // 2. Collect project context for refinement tasks
   const collectedCtx = await collectProjectContext(cwd, 16000)
   const isRefinement = Boolean(collectedCtx?.files?.length > 0 && isRefinementTask(userPrompt, collectedCtx.files))
@@ -128,19 +113,15 @@ export async function runMoAPipeline({
       skippedList: collectedCtx.skippedList,
     })
   }
-
   // 3. Build prompts & Feature 8 multi-turn context
   const priorTurnBaseline = preset?.multi_turn_enabled !== false ? extractPriorTurnBaseline(messages) : null
   const prunedHistory = preset?.multi_turn_enabled !== false ? pruneMultiTurnMessages(messages) : messages
-
   const candidateSystemPrompt = projectContext
     ? `${REFERENCE_SYSTEM_PROMPT}\n\n### Current Project Files & Context:\n${projectContext}`
     : REFERENCE_SYSTEM_PROMPT
-
   const askClarifyingQuestions = preset?.ask_clarifying_questions !== false
   const needsQuestions = askClarifyingQuestions && isBroadPromptRequiringQuestions(userPrompt, messages)
   const enrichedMessages = [...prunedHistory, { role: 'user', content: userPrompt }]
-
   // 4. Parallel fan-out to candidate models with temperature gradient & local fallback
   const referenceOutputs = await runReferencesParallel(
     effectiveReferences,
@@ -162,12 +143,10 @@ export async function runMoAPipeline({
     callLlm,
     onProgress
   )
-
   if (signal?.aborted) {
-    await cleanMoaWorkspaces(cwd)
+    await cleanMoaWorkspaces(cwd, { runId })
     return { error: new Error('Turn aborted') }
   }
-
   // Fail fast if all candidates failed
   const successfulRefs = referenceOutputs.filter((r) => r.ok)
   if (successfulRefs.length === 0) {
@@ -194,7 +173,6 @@ export async function runMoAPipeline({
       durationMs: Date.now() - startTime,
     }
   }
-
   // 5. Extract file blocks & write candidate workspaces
   for (let i = 0; i < referenceOutputs.length; i++) {
     const ref = referenceOutputs[i]
@@ -203,24 +181,21 @@ export async function runMoAPipeline({
     ref.files = files
     if (files.length > 0) {
       ref.syntaxWarning = (verifyFileSyntax(files) || []).map((w) => `${w.file}: ${w.error}`).join('; ')
-      await writeCandidateWorkspace(cwd, i + 1, files)
+      await writeCandidateWorkspace(cwd, i + 1, files, { runId })
     }
   }
-
   if (signal?.aborted) {
-    await cleanMoaWorkspaces(cwd)
+    await cleanMoaWorkspaces(cwd, { runId })
     return { error: new Error('Turn aborted') }
   }
-
   // 5b. Test Execution Gate
   await executeTestGateForCandidates({
     cwd,
     referenceOutputs,
     preset,
-    options: { testGateEnabled, testCommand, execFn },
+    options: { testGateEnabled, testCommand, execFn, runId },
     onProgress,
   })
-
   // 6. Questionnaire synthesis branch
   if (needsQuestions) {
     if (typeof onProgress === 'function') {
@@ -248,12 +223,10 @@ export async function runMoAPipeline({
       logger.warn('[dsh-moa] Questionnaire synthesis failed, proceeding with fallback questions:', err)
       questionsContent = `### Clarification of Requirements: "${userPrompt}"\n\n1. **Architecture & Scope**: Single-file deliverable or multi-module project structure?\n2. **Design & Style**: Minimalist, dark mode, or clean neutral theme?\n3. **Functional Priorities**: Core MVP or comprehensive extended implementation?\n\n*Reply with your preferences (e.g. "1, 2") or proceed with defaults.*`
     }
-
-    await cleanMoaWorkspaces(cwd)
+    await cleanMoaWorkspaces(cwd, { runId })
     const totalTokens = referenceOutputs.reduce((acc, r) => acc + (r.usage?.totalTokens || 0), 0) + qUsage.totalTokens
     const totalCostUsd = Number((referenceOutputs.reduce((acc, r) => acc + (r.costUsd || 0), 0) + qUsage.costUsd).toFixed(5))
     const durationMs = Date.now() - startTime
-
     try {
       await recordMoaRunAsync({
         prompt: userPrompt,
@@ -271,7 +244,6 @@ export async function runMoAPipeline({
     } catch (histErr) {
       logger.warn('[dsh-moa] Failed to record questionnaire run in history:', histErr?.message || histErr)
     }
-
     return {
       kind: 'questions',
       content: questionsContent,
@@ -298,15 +270,15 @@ export async function runMoAPipeline({
   // 7. Fast Mode (1 candidate, bypass judge)
   if (isFastMode) {
     if (signal?.aborted) {
-      await cleanMoaWorkspaces(cwd)
+      await cleanMoaWorkspaces(cwd, { runId })
       return { error: new Error('Turn aborted') }
     }
     const single = successfulRefs[0]
     let promotedFiles = []
     if (single.files?.length > 0) {
-      promotedFiles = await promoteCandidateWorkspace(cwd, single.index, promoteOpts)
+      promotedFiles = await promoteCandidateWorkspace(cwd, single.index, { ...promoteOpts, runId })
     } else {
-      await cleanMoaWorkspaces(cwd)
+      await cleanMoaWorkspaces(cwd, { runId })
     }
 
     const livePreview = await createPromotedPreview(liveCanvas, cwd, promotedFiles, referenceOutputs)
@@ -358,7 +330,7 @@ export async function runMoAPipeline({
   }
 
   if (signal?.aborted) {
-    await cleanMoaWorkspaces(cwd)
+    await cleanMoaWorkspaces(cwd, { runId })
     return { error: new Error('Turn aborted') }
   }
 
@@ -377,7 +349,7 @@ export async function runMoAPipeline({
         }))
       const r2Prompt = buildPeerCritiquePrompt(userPrompt, cand.text, opponents, isBlindEvaluation)
       try {
-        const slot = referenceModels[cand.index - 1] || { provider: cand.provider, model: cand.model }
+        const slot = cand.slot || { provider: cand.provider, model: cand.model }
         const res = await callWithTransientRetry(callLlm, {
           provider: slot.provider,
           model: slot.model,
@@ -393,7 +365,7 @@ export async function runMoAPipeline({
         if (r2Files.length > 0) {
           cand.files = r2Files
           cand.syntaxWarning = (verifyFileSyntax(r2Files) || []).map((w) => `${w.file}: ${w.error}`).join('; ')
-          await writeCandidateWorkspace(cwd, cand.index, r2Files)
+          await writeCandidateWorkspace(cwd, cand.index, r2Files, { runId })
         }
         if (typeof res === 'object' && res?.usage) {
           cand.usage.inputTokens = (cand.usage.inputTokens || 0) + (res.usage.inputTokens || 0)
@@ -411,7 +383,7 @@ export async function runMoAPipeline({
       cwd,
       referenceOutputs: successfulRefs,
       preset,
-      options: { testGateEnabled, testCommand, execFn },
+      options: { testGateEnabled, testCommand, execFn, runId },
       onProgress,
     })
   }
@@ -419,7 +391,7 @@ export async function runMoAPipeline({
   // 7c. Feature 2: Multi-Judge Panel & Consensus Voting
   let multiJudgeResult = null
   if (signal?.aborted) {
-    await cleanMoaWorkspaces(cwd)
+    await cleanMoaWorkspaces(cwd, { runId })
     return { error: new Error('Turn aborted') }
   }
 
@@ -508,7 +480,7 @@ export async function runMoAPipeline({
   }
 
   if (signal?.aborted) {
-    await cleanMoaWorkspaces(cwd)
+    await cleanMoaWorkspaces(cwd, { runId })
     return { error: new Error('Turn aborted') }
   }
 
@@ -527,22 +499,22 @@ export async function runMoAPipeline({
 
   const keepWorkspaces = allowCandidateOverride
   if (synthesizedFiles.length > 0) {
-    await writeCandidateWorkspace(cwd, 'curator-synthesis', synthesizedFiles)
-    promotedFiles = await promoteCandidateWorkspace(cwd, 'curator-synthesis', { ...promoteOpts, keepMoa: keepWorkspaces })
+    await writeCandidateWorkspace(cwd, 'curator-synthesis', synthesizedFiles, { runId })
+    promotedFiles = await promoteCandidateWorkspace(cwd, 'curator-synthesis', { ...promoteOpts, runId, keepMoa: keepWorkspaces })
   } else if (referenceOutputs[winningIndex - 1]?.files?.length > 0) {
-    promotedFiles = await promoteCandidateWorkspace(cwd, winningIndex, { ...promoteOpts, keepMoa: keepWorkspaces })
+    promotedFiles = await promoteCandidateWorkspace(cwd, winningIndex, { ...promoteOpts, runId, keepMoa: keepWorkspaces })
   } else if (successfulRefs[0]?.files?.length > 0) {
     const fallbackIdx = successfulRefs[0].index
-    promotedFiles = await promoteCandidateWorkspace(cwd, fallbackIdx, { ...promoteOpts, keepMoa: keepWorkspaces })
+    promotedFiles = await promoteCandidateWorkspace(cwd, fallbackIdx, { ...promoteOpts, runId, keepMoa: keepWorkspaces })
   } else if (!keepWorkspaces) {
-    await cleanMoaWorkspaces(cwd)
+    await cleanMoaWorkspaces(cwd, { runId })
   }
 
   const livePreview = await createPromotedPreview(liveCanvas, cwd, promotedFiles, referenceOutputs)
   const durationMs = Date.now() - startTime
   const usageSummary = summarizeMoAUsage(referenceOutputs, aggUsage)
   const winningRef = referenceOutputs[winningIndex - 1]
-  const winnerModel = winningRef?.label || slotLabel(referenceModels[0])
+  const winnerModel = winningRef?.label || slotLabel(effectiveReferences[0] || referenceModels[0])
   const finalAggLabel = slotLabel(chosenJudge)
 
   // Feature 9: Benchmark & Post-Mortem PR report

package/lib/moa-stream.js

@@ -1,3 +1,4 @@
+import crypto from 'node:crypto'
 /**
  * Zero-latency Live Streaming Generator for MoA Turns
  */
@@ -11,6 +12,7 @@ import { runMoAPipeline } from './moa-runner.js'
  */
 export async function* streamMoATurn({ targetPreset, userPrompt, messages, callLlm, cwd, prices, historyFilePath, liveCanvas, webServerPort, timeMachineEngine, force }, options = {}) {
   const signal = options?.signal
+  const runId = options?.runId || null
   if (signal?.aborted) return
 
   const internalAbortCtrl = new AbortController()
@@ -69,7 +71,7 @@ export async function* streamMoATurn({ targetPreset, userPrompt, messages, callL
 
     while (!done || queue.length > 0) {
       if (combinedSignal.aborted) {
-        await cleanMoaWorkspaces(cwd)
+        await cleanMoaWorkspaces(cwd, runId ? { runId } : {})
         return
       }
 
@@ -96,7 +98,7 @@ export async function* streamMoATurn({ targetPreset, userPrompt, messages, callL
 
     const result = await pipelinePromise
     if (combinedSignal.aborted) {
-      await cleanMoaWorkspaces(cwd)
+      await cleanMoaWorkspaces(cwd, runId ? { runId } : {})
       return
     }
 
@@ -126,7 +128,7 @@ export async function* streamMoATurn({ targetPreset, userPrompt, messages, callL
   } finally {
     internalAbortCtrl.abort()
     if (!done) {
-      await cleanMoaWorkspaces(cwd).catch(() => {})
+      await cleanMoaWorkspaces(cwd, runId ? { runId } : {}).catch(() => {})
     }
   }
 }