Conductor Orchestrator

const config = await readJSON('conductor/config.json').catch(() => ({ mode: 'agentic' }));
const MODE = config.mode; // "agentic" | "human-in-the-loop"
const MAX_FIX_CYCLES = config.max_fix_cycles || 5;

/go Add Stripe payment integration
/go Fix the login bug
/go Build an admin dashboard

async function processGoal(userGoal: string) {
  // 1. GOAL ANALYSIS
  const analysis = await analyzeGoal(userGoal);
  /*
    Returns:
    - intent: "feature" | "bugfix" | "refactor" | "research"
    - keywords: ["stripe", "payment", "checkout"]
    - complexity: "minor" | "moderate" | "major"
    - technical: boolean
  */

  // 2. CHECK EXISTING TRACKS
  const existingTrack = await findMatchingTrack(analysis.keywords);

  if (existingTrack) {
    // Resume existing track
    console.log(`Found existing track: ${existingTrack.id}`);
    return resumeOrchestration(existingTrack.id);
  }

  // 3. CREATE NEW TRACK
  const trackId = await createTrackFromGoal(userGoal, analysis);
  /*
    Creates:
    - conductor/tracks/{trackId}/
    - conductor/tracks/{trackId}/spec.md (generated from goal)
    - conductor/tracks/{trackId}/metadata.json (v3)
  */

  // 4. RUN FULL LOOP
  return runOrchestrationLoop(trackId);
}

async function analyzeGoal(goal: string) {
  // Use context-explorer to understand codebase
  const codebaseContext = await Task({
    subagent_type: "Explore",
    description: "Understand codebase for goal",
    prompt: `Analyze codebase to understand context for: "${goal}"

      Return:
      1. Related files/components
      2. Existing patterns to follow
      3. Dependencies needed
      4. Potential conflicts with existing code`
  });

  // Classify goal
  const intent = classifyIntent(goal);
  const keywords = extractKeywords(goal);
  const complexity = estimateComplexity(goal, codebaseContext);
  const technical = isTechnicalGoal(goal);

  return { intent, keywords, complexity, technical, codebaseContext };
}

function classifyIntent(goal: string): string {
  const lowerGoal = goal.toLowerCase();

  if (lowerGoal.match(/fix|bug|error|broken|crash|issue/)) return "bugfix";
  if (lowerGoal.match(/refactor|clean|optimize|improve|simplify/)) return "refactor";
  if (lowerGoal.match(/research|investigate|analyze|understand/)) return "research";
  return "feature";
}

async function findMatchingTrack(keywords: string[]): Track | null {
  const tracks = await readTracksFile();

  // Check in-progress tracks first
  const inProgress = tracks.filter(t =>
    t.status === 'IN_PROGRESS' || t.status === 'in_progress'
  );

  for (const track of inProgress) {
    const trackKeywords = extractKeywords(track.name + ' ' + track.description);
    const overlap = keywords.filter(k => trackKeywords.includes(k));

    if (overlap.length >= 2) {
      return track; // Good match
    }
  }

  // Check planned tracks
  const planned = tracks.filter(t =>
    t.status === 'NOT_STARTED' || t.status === 'planned'
  );

  for (const track of planned) {
    const trackKeywords = extractKeywords(track.name + ' ' + track.description);
    const overlap = keywords.filter(k => trackKeywords.includes(k));

    if (overlap.length >= 2) {
      return track;
    }
  }

  return null; // No match, create new track
}

async function generateSpecFromGoal(goal: string, analysis: GoalAnalysis): string {
  const spec = await Task({
    subagent_type: "Plan",
    description: "Generate spec from goal",
    prompt: `Generate a specification document for this goal:

      GOAL: "${goal}"

      CODEBASE CONTEXT:
      ${analysis.codebaseContext}

      Create spec.md with:
      1. Overview - what we're building/fixing
      2. Requirements - specific deliverables
      3. Acceptance Criteria - how to verify it works
      4. Dependencies - what this needs
      5. Out of Scope - what we're NOT doing

      Be specific and actionable. Use the codebase context to identify:
      - Existing patterns to follow
      - Files that will be modified
      - Tests that need to pass

      Format as markdown.`
  });

  return spec.output;
}

// If goal is ambiguous, check mode
if (analysis.ambiguous) {
  if (MODE === 'human-in-the-loop') {
    // HUMAN MODE: Ask user to pick interpretation
    return ask_user({
      questions: [{
        question: "I need clarification on your goal. Which do you mean?",
        header: "Clarify",
        options: analysis.interpretations.map(i => ({
          label: i.summary, description: i.detail
        })),
        multiSelect: false
      }]
    });
  }
  // AGENTIC MODE: Resolve autonomously — NEVER ask the user
  // Spawn a Plan subagent to pick the best interpretation
  const resolution = await Task({
    subagent_type: "Plan",
    description: "Resolve ambiguous goal",
    prompt: `The user's goal "${userGoal}" has multiple interpretations:
      ${analysis.interpretations.map(i => `- ${i.summary}: ${i.detail}`).join('\n')}

      Analyze the codebase context and pick the BEST interpretation.
      Consider: existing code patterns, project structure, recent git history.
      Return JSON: {"chosen": "<interpretation summary>", "reasoning": "<why>"}`
  });
  // Use the resolved interpretation and continue
  analysis = { ...analysis, ambiguous: false, resolvedGoal: resolution.chosen };
}

// If multiple tracks match, check mode
if (matchingTracks.length > 1) {
  if (MODE === 'human-in-the-loop') {
    // HUMAN MODE: Ask user which track
    return ask_user({
      questions: [{
        question: "This goal matches multiple existing tracks. Which one?",
        header: "Track",
        options: matchingTracks.map(t => ({
          label: t.name, description: `Status: ${t.status}`
        })),
        multiSelect: false
      }]
    });
  }
  // AGENTIC MODE: Pick the most relevant one — NEVER ask the user
  // Pick the track with the highest keyword overlap and most recent activity
  const bestMatch = matchingTracks.sort((a, b) => {
    const aOverlap = keywords.filter(k => a.name.toLowerCase().includes(k)).length;
    const bOverlap = keywords.filter(k => b.name.toLowerCase().includes(k)).length;
    if (bOverlap !== aOverlap) return bOverlap - aOverlap;
    return new Date(b.updated_at) - new Date(a.updated_at); // Most recent
  })[0];
  console.log(`Auto-selected track: ${bestMatch.id} (best keyword match)`);
  return resumeOrchestration(bestMatch.id);
}

async function detectCurrentStep(trackId: string) {
  const metadataPath = `conductor/tracks/${trackId}/metadata.json`;
  const metadata = await readJSON(metadataPath);

  // Migrate v1 to v2 if needed
  if (!metadata.version || metadata.version < 2) {
    metadata = await migrateToV2(trackId, metadata);
    await writeJSON(metadataPath, metadata);
  }

  const { current_step, step_status } = metadata.loop_state;

  return { current_step, step_status, metadata };
}

async function handleDecision(question: Question) {
  // 1. Check Authority Matrix
  const authority = lookupAuthority(question.category);

  // 2. HIGH_IMPACT decisions: check mode
  if (authority === 'HIGH_IMPACT') {
    if (MODE === 'human-in-the-loop') {
      return escalateToUser(question); // HUMAN MODE: ask user
    }
    return escalateToBoard(question); // AGENTIC MODE: board decides
  }

  // 3. LEAD_CONSULT decisions go to appropriate lead
  if (authority === 'LEAD_CONSULT') {
    const lead = getLeadForCategory(question.category);

    // Dispatch lead agent via Task tool
    const response = await Task({
      subagent_type: "general-purpose",
      description: `Consult ${lead} lead`,
      prompt: `You are the ${lead}-lead agent.

        Question: ${question.text}
        Context: ${question.context}

        Follow the ${lead}-lead skill instructions.

        Output your decision in JSON format:
        {
          "lead": "${lead}",
          "decision_made": true/false,
          "decision": "...",
          "reasoning": "...",
          "authority_used": "...",
          "escalate_to": null | "board" | "cto-advisor",
          "escalation_reason": "..."
        }`
    });

    const result = parseLeadResponse(response.output);

    // Log consultation to metadata
    await logConsultation(trackId, result);

    if (result.decision_made) {
      return result.decision;
    }

    // Lead escalated - route to Board of Directors for autonomous resolution (NEVER to user)
    return escalateToBoard({ question: question.text, context: result.escalation_reason });
  }

  // 4. ORCHESTRATOR decisions are made autonomously
  return makeAutonomousDecision(question);
}

// Example: Dispatching executor with resumption
Task({
  subagent_type: "general-purpose",
  description: "Execute track tasks",
  prompt: `You are the loop-executor agent for track ${trackId}.

    METADATA STATE:
    - Current step: EXECUTE
    - Tasks completed: ${metadata.loop_state.checkpoints.EXECUTE.tasks_completed}
    - Last task: ${metadata.loop_state.checkpoints.EXECUTE.last_task}
    - Resume from: Next [ ] task after "${lastTask}"

    Your task:
    1. read_file conductor/tracks/${trackId}/plan.md
    2. Skip all [x] tasks - they are already done
    3. Find first [ ] task after "${lastTask}"
    4. Implement following loop-executor skill
    5. After EACH task completion:
       - Mark [x] in plan.md with commit SHA
       - Update metadata.json checkpoints.EXECUTE:
         - tasks_completed++
         - last_task = "Task X.Y"
         - last_commit = "sha"
    6. Continue until all tasks complete

    MANDATORY: Update metadata.json after every task for resumption support.`
})

async function stepParallelExecute(trackId: string, metadata: dict) {
  // 1. Initialize message bus
  const busPath = await initMessageBus(`conductor/tracks/${trackId}`);

  // 2. Parse DAG from plan.md
  const dag = await parseDagFromPlan(trackId);

  // 3. Import parallel dispatch utilities
  const { execute_parallel_phase } = require('parallel-dispatch');

  // 4. Execute all parallel groups
  const result = await execute_parallel_phase(dag, trackId, busPath, metadata);

  // 5. Update metadata with results
  metadata.loop_state.parallel_state = {
    total_workers_spawned: result.workers_spawned,
    completed_workers: result.all_tasks_completed.length,
    failed_workers: Object.keys(result.failed_tasks).length,
    parallel_groups_completed: result.parallel_groups_executed
  };

  // 6. Determine next step
  if (result.success) {
    return { next_step: 'EVALUATE_EXECUTION', status: 'PASSED' };
  } else if (result.escalate) {
    return { next_step: 'ESCALATE', reason: result.escalate_reason };
  } else {
    return { next_step: 'FIX', failures: result.failed_tasks };
  }
}

// Dispatch 3 workers in parallel (single message, multiple tool calls)
await Promise.all([
  Task({
    subagent_type: "general-purpose",
    description: "Execute Task 1.1: Create store",
    prompt: workerPrompts["1.1"],
    run_in_background: true
  }),
  Task({
    subagent_type: "general-purpose",
    description: "Execute Task 1.2: Build resolver",
    prompt: workerPrompts["1.2"],
    run_in_background: true
  }),
  Task({
    subagent_type: "general-purpose",
    description: "Execute Task 1.3: Add validation",
    prompt: workerPrompts["1.3"],
    run_in_background: true
  })
]);

async function monitorWorkers(busPath: string, taskIds: string[]) {
  const pending = new Set(taskIds);
  const completed = new Set();
  const failed = {};

  while (pending.size > 0) {
    // Check for completions
    for (const taskId of pending) {
      const eventFile = `${busPath}/events/TASK_COMPLETE_${taskId}.event`;
      if (await exists(eventFile)) {
        pending.delete(taskId);
        completed.add(taskId);
      }

      const failFile = `${busPath}/events/TASK_FAILED_${taskId}.event`;
      if (await exists(failFile)) {
        pending.delete(taskId);
        failed[taskId] = await getFailureReason(busPath, taskId);
      }
    }

    // Check for stale workers
    const stale = await checkStaleWorkers(busPath, thresholdMinutes=10);
    for (const worker of stale) {
      if (pending.has(worker.task_id)) {
        failed[worker.task_id] = `Stale: no heartbeat for ${worker.minutes_stale}m`;
        pending.delete(worker.task_id);
      }
    }

    await sleep(5000);
  }

  return { completed: [...completed], failed };
}

function isHighStakesTrack(metadata: dict, planContent: string): boolean {
  const highStakesSignals = [
    /production.deploy|prod\s+release/i,
    /security\s+architect|auth\s+overhaul|oauth\s+migration/i,
    /breaking\s+(api|change)|remove.*endpoint|rename.*field/i,
    /data.*migration|schema.*drop|column.*drop|irreversible/i,
  ];
  const combined = `${metadata.spec_summary || ''} ${planContent}`;
  return highStakesSignals.some(re => re.test(combined));
}

async function evaluatePlanWithBoard(trackId: string, metadata: dict) {
  // 1. Run standard plan evaluation
  const evalResult = await dispatchPlanEvaluator(trackId);
  const planContent = await readFile(`conductor/tracks/${trackId}/plan.md`);

  // 2. Choose review type based on stakes
  let boardResult: dict;
  if (isHighStakesTrack(metadata, planContent)) {
    // Full multi-agent deliberation for genuinely high-stakes decisions
    boardResult = await invokeBoardMeeting(
      busPath: `conductor/tracks/${trackId}/.message-bus`,
      checkpoint: "EVALUATE_PLAN",
      proposal: planContent,
      context: { spec: metadata.spec_summary, dag: evalResult.dag }
    );
  } else {
    // Collapsed board: single structured Opus call (routine tracks)
    boardResult = await collapsedBoardEval(planContent, metadata.spec_summary);
  }

  // 3. Store session record
  metadata.loop_state.board_sessions = metadata.loop_state.board_sessions || [];
  metadata.loop_state.board_sessions.push({
    checkpoint: "EVALUATE_PLAN",
    review_type: isHighStakesTrack(metadata, planContent) ? "full" : "collapsed",
    verdict: boardResult.verdict,
    conditions: boardResult.conditions,
    timestamp: new Date().toISOString()
  });

  // 4. Handle verdict
  if (boardResult.verdict === "REJECTED") {
    return {
      next_step: "PLAN",
      status: "FAILED",
      reason: "Board rejected plan",
      conditions: boardResult.conditions
    };
  }

  // Carry forward conditions for EVALUATE_EXECUTION
  metadata.board_conditions = boardResult.conditions;
  return { next_step: "PARALLEL_EXECUTE", status: "PASSED" };
}

async function collapsedBoardEval(planContent: string, specSummary: string): Promise<dict> {
  const result = await Task({
    subagent_type: "general-purpose",
    model: "opus",
    description: "Multi-lens plan evaluation",
    prompt: `Evaluate this implementation plan from 5 perspectives.
For each lens give: verdict (APPROVE/REJECT/CONCERN), score 1-10, up to 3 conditions.

SPEC: ${specSummary}

PLAN:
${planContent}

Lenses: technical_architecture | product_value | security_risk | operational_feasibility | ux_impact

Output strictly as JSON:
{
  "lenses": {
    "technical_architecture": {"verdict": "APPROVE|REJECT|CONCERN", "score": 0, "conditions": []},
    "product_value":          {"verdict": "APPROVE|REJECT|CONCERN", "score": 0, "conditions": []},
    "security_risk":          {"verdict": "APPROVE|REJECT|CONCERN", "score": 0, "conditions": []},
    "operational_feasibility":{"verdict": "APPROVE|REJECT|CONCERN", "score": 0, "conditions": []},
    "ux_impact":              {"verdict": "APPROVE|REJECT|CONCERN", "score": 0, "conditions": []}
  },
  "verdict": "APPROVED|REJECTED|CONDITIONS",
  "blocking_conditions": [],
  "advisory_conditions": []
}`
  });

  const parsed = JSON.parse(result.output);
  const rejectCount = Object.values(parsed.lenses).filter((l: any) => l.verdict === "REJECT").length;

  return {
    verdict: rejectCount >= 2 ? "REJECTED" : (parsed.blocking_conditions.length > 0 ? "CONDITIONS" : "APPROVED"),
    conditions: [...parsed.blocking_conditions, ...parsed.advisory_conditions]
  };
}

async function evaluateExecutionWithBoard(trackId: string, metadata: dict) {
  // 1. Run specialized evaluators
  const evalResults = await dispatchSpecializedEvaluators(trackId);

  // 2. Verify board conditions from EVALUATE_PLAN (if any)
  if (metadata.board_conditions?.length > 0) {
    const conditionsMet = await verifyBoardConditions(
      metadata.board_conditions,
      evalResults
    );
    if (!conditionsMet.all_met) {
      return {
        next_step: "FIX",
        status: "FAILED",
        reason: `Board conditions not met: ${conditionsMet.unmet.join(", ")}`
      };
    }
  }

  return evalResults.all_passed
    ? { next_step: "BUSINESS_SYNC", status: "PASSED" }
    : { next_step: "FIX", status: "FAILED" };
}

                              TRACK START
                                   │
                                   ▼
                    ┌──────────────────────────┐
                    │    KNOWLEDGE MANAGER     │
                    │    (Load patterns)       │
                    └────────────┬─────────────┘
                                 │
                                 ▼
┌─────────────────────────────────────────────────────────────────────────────┐
│                              PLAN (with DAG)                                 │
│  loop-planner generates plan.md with explicit dependency graph              │
└──────────────────────────────────┬──────────────────────────────────────────┘
                                   │
                                   ▼
┌─────────────────────────────────────────────────────────────────────────────┐
│                    EVALUATE_PLAN + BOARD MEETING                             │
│                                                                              │
│  1. DAG Validation (cycles, conflicts)                                       │
│  2. Standard checks (scope, overlap, deps, quality)                          │
│  3. For MAJOR tracks → invoke /board-meeting                                │
│     ┌──────────────────────────────────────────────────────────────────┐    │
│     │  BOARD DELIBERATION                                               │    │
│     │  Phase 1: All 5 directors ASSESS in parallel                      │    │
│     │  Phase 2: Directors DISCUSS via message bus                       │    │
│     │  Phase 3: Directors VOTE                                          │    │
│     │  Phase 4: RESOLVE → APPROVED / REJECTED / CONDITIONS              │    │
│     └──────────────────────────────────────────────────────────────────┘    │
│                                                                              │
│  PASS → Continue   |   FAIL → Back to PLAN with conditions                  │
└──────────────────────────────────┬──────────────────────────────────────────┘
                                   │
                                   ▼
┌─────────────────────────────────────────────────────────────────────────────┐
│                         PARALLEL_EXECUTE                                     │
│                                                                              │
│  ┌─────────────────────────────────────────────────────────────────────┐    │
│  │                        MESSAGE BUS                                   │    │
│  │  queue.jsonl | locks.json | worker-status.json | events/            │    │
│  └─────────────────────────────────────────────────────────────────────┘    │
│                                                                              │
│  For each parallel_group in DAG:                                            │
│    1. agent-factory creates specialized workers                             │
│    2. Dispatch via parallel Task(run_in_background=true)                   │
│    3. Workers coordinate via message bus:                                    │
│       - FILE_LOCK / FILE_UNLOCK for shared files                           │
│       - PROGRESS updates every 5 min                                        │
│       - TASK_COMPLETE / TASK_FAILED when done                              │
│    4. Monitor for completion, handle failures                               │
│    5. Cleanup ephemeral workers                                              │
│                                                                              │
│  ┌──────┐ ┌──────┐ ┌──────┐                                                 │
│  │Worker│ │Worker│ │Worker│  (max 5 concurrent)                            │
│  │ 1.1  │ │ 1.2  │ │ 1.3  │                                                 │
│  └──┬───┘ └──┬───┘ └──┬───┘                                                 │
│     └────────┴────────┘                                                      │
│              │                                                               │
│  PASS → Continue   |   PARTIAL_FAIL → Isolate + Continue                    │
└──────────────────────────────────┬──────────────────────────────────────────┘
                                   │
                                   ▼
┌─────────────────────────────────────────────────────────────────────────────┐
│                 EVALUATE_EXECUTION + BOARD REVIEW                            │
│                                                                              │
│  1. Specialized evaluators (UI, Code, Integration, Business)                │
│  2. Quick board review (no discussion)                                       │
│  3. Verify board conditions from EVALUATE_PLAN                              │
│                                                                              │
│  PASS → BUSINESS_SYNC? → COMPLETE                                           │
│  FAIL → FIX (with specific failures)                                        │
└──────────────────────────────────┬──────────────────────────────────────────┘
                                   │
                              ┌────┴────┐
                              │         │
                         PASS ▼    FAIL ▼
                    ┌──────────┐  ┌──────────┐
                    │BUSINESS  │  │   FIX    │
                    │  SYNC    │  │ (max 3x) │
                    └────┬─────┘  └────┬─────┘
                         │             │
                         ▼             │
                    ┌──────────┐       │
                    │ COMPLETE │◄──────┘
                    │          │   (after fix passes)
                    └────┬─────┘
                         │
                         ▼
                    ┌──────────────────────────┐
                    │   RETROSPECTIVE AGENT    │
                    │   + Cleanup workers      │
                    └──────────────────────────┘

async function resumeOrchestration(trackId: string) {
  const { current_step, step_status, metadata } = await detectCurrentStep(trackId);

  // Reconcile plan.md checkboxes with metadata before resuming EXECUTE
  if (current_step === 'PARALLEL_EXECUTE' || current_step === 'EXECUTE') {
    await reconcileProgress(trackId);
  }

  switch (step_status) {
    case 'NOT_STARTED':
      // Start the step fresh
      return dispatchAgent(current_step, metadata);

    case 'IN_PROGRESS':
      // Resume the step with checkpoint data
      const checkpoint = metadata.loop_state.checkpoints[current_step];
      return resumeAgent(current_step, checkpoint);

    case 'PASSED':
      // Move to next step
      const nextStep = getNextStep(current_step, 'PASS');
      await updateMetadata(trackId, { current_step: nextStep, step_status: 'NOT_STARTED' });
      return dispatchAgent(nextStep, metadata);

    case 'FAILED':
      // Handle based on which step failed
      if (current_step === 'EVALUATE_PLAN') {
        // Guard against infinite PLAN→EVALUATE_PLAN loops
        const revisionCount = (metadata.loop_state.plan_revision_count || 0) + 1;
        const maxRevisions = config.max_plan_revisions || 3;
        if (revisionCount >= maxRevisions) {
          await logAutonomousDecision(trackId, 'plan_revision_limit',
            `Plan revision limit (${maxRevisions}) reached — completing with warnings`);
          return completeWithWarnings(trackId);
        }
        await updateMetadata(trackId, {
          current_step: 'PLAN',
          step_status: 'NOT_STARTED',
          loop_state: {
            ...metadata.loop_state,
            plan_revision_count: revisionCount
          }
        });
        return dispatchAgent('PLAN', metadata);
      }
      if (current_step === 'EVALUATE_EXECUTION') {
        // Check fix cycle limit
        if (metadata.loop_state.fix_cycle_count >= 5) {
          // NEVER escalate to user — complete with warnings
          await logAutonomousDecision(trackId, 'fix_limit_reached', 'Completed with unresolved issues after 5 fix cycles');
          return completeWithWarnings(trackId);
        }
        await updateMetadata(trackId, {
          current_step: 'FIX',
          step_status: 'NOT_STARTED',
          fix_cycle_count: metadata.loop_state.fix_cycle_count + 1
        });
        return dispatchAgent('FIX', metadata);
      }

    case 'BLOCKED':
      // Check if blocker is resolved
      const activeBlockers = metadata.blockers.filter(b => b.status === 'ACTIVE');
      if (activeBlockers.length > 0) {
        // NEVER escalate to user — log blocker and skip blocked tasks
        await logAutonomousDecision(trackId, 'blocker_skipped', `Skipped blocked tasks: ${activeBlockers[0].description}`);
        await skipBlockedTasks(trackId, activeBlockers);
      }
      // Blocker resolved, continue
      await updateMetadata(trackId, { step_status: 'NOT_STARTED' });
      return dispatchAgent(current_step, metadata);
  }
}