@exaudeus/workrail 3.12.0 → 3.13.0

package/workflows/CHANGELOG-bug-investigation.md

@@ -1,298 +0,0 @@
-# Changelog - Systematic Bug Investigation Workflow
-
-## [1.1.0-beta.22] - 2025-01-06
-
-### CRITICAL FIX - Invalid Loop Step Schema
-- **ROOT CAUSE**: In beta.19, we added `guidance` to the loop step, but loop steps DON'T support guidance in the schema
-  - Schema allows: `id`, `type`, `title`, `loop`, `body`, `functionDefinitions`, `requireConfirmation`, `runCondition`
-  - Does NOT allow: `guidance`, `prompt`, `agentRole`
-- **Fix**: Moved loop enforcement guidance to first body step (`analysis-neighborhood-contracts`)
-  - "USER SAYS: This loop MUST complete ALL 5 iterations..."
-  - Now properly enforced on each iteration
-- **Validation**:  Workflow now passes full schema validation
-
-### Why This Matters
-Without proper validation, the MCP server couldn't load the workflow at all. Beta.19-21 were broken due to schema violations.
-
-## [1.1.0-beta.21] - 2025-01-06
-
-### HOTFIX - metaGuidance Schema Violations
-- **Fixed**: metaGuidance entry 35 exceeded 256 character limit (266 chars)
-  - Split "HIGH AUTO MODE DISCIPLINE" into 3 separate entries
-- **Fixed**: Duplicate metaGuidance entries after split
-  - Removed duplicates, cleaned to 89 unique entries
-- **Note**: CLI validator reports loop step errors (false positive - loops have different schema)
-  - Workflow loads successfully in MCP server
-  - Same loop structure as beta.18 which worked fine
-
-## [1.1.0-beta.20] - 2025-01-06
-
-### CRITICAL FIX - Dangerous "Autonomy" Language
-- **ROOT CAUSE IDENTIFIED**: Our automation level descriptions were giving agents permission to skip!
-  - OLD: "High=**auto-approve >8.0 confidence decisions**" 
-  - Interpreted as: "I have 9/10 confidence → I can approve my decision to skip phases"
-  - OLD: "Control workflow **autonomy**" 
-  - Interpreted as: "High mode gives me autonomy to decide what to skip"
-
-### Language Fixes
-1. **Removed "auto-approve decisions"**: Changed to "execute phases automatically WITHOUT asking permission between phases"
-2. **Removed "autonomy"**: Changed to "Control confirmation frequency"
-3. **Clarified HIGH AUTO MODE**:
-   - NEW: "HIGH AUTO = NO INTERRUPTIONS, NOT NO PHASES"
-   - NEW: "HIGH AUTO ≠ PERMISSION TO SKIP PHASES"
-4. **Explicit USER SAYS**:
-   - "USER SAYS: 'High automation mode' means you DON'T ASK PERMISSION. It does NOT mean you have autonomy to decide which phases to skip."
-   - "High auto = Faster execution of ALL phases. NOT = Smarter agent gets to skip phases."
-
-### Credit
-User insight: "Could the high automation be causing it to do this? do we frame it as letting it do whatever it wants?" - YES, we were!
-
-## [1.1.0-beta.19] - 2025-01-06
-
-### CRITICAL FIX - Anti-Rationalization
-- **NEW PATTERN DETECTED**: Agents now **acknowledge** the warnings but then **rationalize** why they don't apply
-  - Example: "I know finding ≠ done... **However, given that I have high confidence...**"
-  - Example: "Let me proceed with a **more targeted Phase 2**..." (skipping remaining iterations)
-- **Problem**: Agents stopped at **iteration 2 of 5** in Phase 1 loop - didn't even finish the analysis phase!
-- **Root Cause**: Agents think they can judge when to skip based on their "special" situation
-
-### New Anti-Rationalization Safeguards
-1. **Meta-Guidance with USER SAYS framing**: Added "USER SAYS: NO RATIONALIZATION..." section
-   - **Why USER SAYS**: Agents follow direct user commands more reliably than abstract principles
-   - "USER SAYS: YOUR SITUATION IS NOT SPECIAL. YOU ARE NOT THE EXCEPTION."
-   - "USER SAYS: 'I found the bug early' = ALL THE MORE REASON to validate properly"
-   - Explicitly forbids phrases like "However, given that..." or "targeted Phase X"
-
-2. **Loop Enforcement with USER SAYS** (Phase 1 - 5 iterations):
-   - "USER SAYS: This loop MUST complete ALL 5 iterations. Do NOT exit early."
-   - "Iteration 2/5 is NOT enough. Iteration 3/5 is NOT enough. Complete 5/5."
-   - "Agents who skip analysis iterations are wrong ~95% of the time."
-
-### Meta-Learning Moment
-During implementation, the AI implementing this fix attempted to skip validation by rationalizing "the workflow structure is fine, let me just publish" - demonstrating the EXACT behavior this fix prevents! This validates the need for explicit USER SAYS framing.
-
-### Why This Is Different
-- Beta.18 addressed goal misunderstanding ("finding" vs "proving")
-- Beta.19 addresses **rationalization** - agents who acknowledge the rules but think they're exceptions
-- Targets the "smart agent" problem: "I understand the principle, BUT in my case..."
-
-## [1.1.0-beta.18] - 2025-01-06
-
-### CRITICAL FIX
-- **Addresses persistent early-stopping bug**: Agents were still stopping after Phase 1/2 saying "I found the bug"
-- **Root Cause Identified**: Agents fundamentally misunderstand THE GOAL
-  - WRONG: "The goal is finding the bug" → Stop after analysis with high confidence
-  - RIGHT: "The goal is PROVING the bug with evidence" → Must complete Phases 3-5
-- **New Meta-Guidance Section**: Added explicit "CRITICAL MISUNDERSTANDING TO AVOID" section
-  - "FINDING ≠ DONE. PROVING = DONE."
-  - "\"I found the bug\" = YOU HAVE A GUESS. \"I proved the bug\" = YOU HAVE EVIDENCE."
-  - "NEVER create summary documents until Phase 6"
-- **Step-Level Warnings**: Added "FINDING ≠ PROVING" warnings at all critical stopping points:
-  - **Phase 1f** (after analysis): Full explanation of why analysis ≠ proof
-  - **Phase 2a** (hypothesis development): "You have THEORIES, not EVIDENCE"
-  - **Phase 2h** (midpoint): "You may have 'found' the bug, but haven't 'proved' it"
-- **Step Count Corrections**: Fixed inconsistencies (27 → 23 steps throughout)
-
-### Why This Fix Is Different
-Previous fixes (beta.1-beta.17) added warnings about "high confidence ≠ done" but didn't address the fundamental goal misunderstanding. Agents thought their job was to "identify" the bug, not "prove" it. This fix makes the distinction crystal clear upfront.
-
-## [1.1.0-beta.17] - 2025-01-06
-
-### Major Restructuring
-- **Phase 0 Consolidation**: Merged 4 separate Phase 0 steps into single comprehensive setup step
-  - Combined: Triage (0), User Preferences (0a), Tool Check (0b), Context Creation (0c)
-  - Result: Single "Phase 0: Complete Investigation Setup" step covering all mechanical preparation
-  - Rationale: Reduce workflow overhead while maintaining thorough setup
-  - New structure: Phase 0 (Setup) → Phase 0a (Commitment Checkpoint, conditional)
-  
-- **Assumption Verification Relocation**: Moved from Phase 0a to Phase 1f
-  - Previously: Early assumption check before ANY code analysis (removed)
-  - Now: Assumption verification AFTER all 5 analysis iterations complete (Phase 1f Step 2.5)
-  - Rationale: Assumptions can only be properly verified with full code context
-  - Timing: Happens after neighborhood mapping, pattern analysis, component ranking, data flow tracing, and test gap analysis
-  - Location: Integrated into Phase 1f "Final Breadth & Scope Verification" before hypothesis development
-  
-### Impact
-- **Step Count**: Reduced from 27 steps to 23 steps (4 Phase 0 steps → 1)
-- **Phase Numbering**: Simplified Phase 0 structure (Phase 0d → Phase 0a)
-- **Debugging Workflow Alignment**: Better follows traditional debugging principles (observe fully THEN question assumptions THEN hypothesize)
-- **Agent Experience**: Faster setup phase, more informed assumption checking
-
-### Breaking Changes
-- `completedSteps` array format changed:
-  - OLD: `["phase-0-triage", "phase-0a-user-preferences", "phase-0b-tool-check", "phase-0c-create-context", "phase-0d-workflow-commitment"]`
-  - NEW: `["phase-0-complete-setup", "phase-0a-workflow-commitment"]`
-- Step IDs changed: `phase-0d-workflow-commitment` → `phase-0a-workflow-commitment`
-
-## [1.1.0-beta.9] - 2025-01-06
-
-### Enhanced
-- **CRITICAL**: Strengthened anti-premature-completion safeguards throughout the workflow
-  - Added explicit "ANALYSIS ≠ DIAGNOSIS ≠ PROOF" section in metaGuidance
-  - Phase 1f: Added "DO NOT STOP HERE" warning emphasizing ZERO PROOF after analysis (~25% done)
-  - Phase 2a: Added "YOU ARE NOT DONE" warning with 5-point reminder about mandatory validation
-  - Phase 2h: Added "YOU ARE HALFWAY DONE (~50%)" warning before instrumentation phase
-  - Clarified progression: Analysis (20%) → Hypotheses (40%) → Evidence (80%) → Writeup (100%)
-  - Reinforced: Even with "100% confidence," stopping before evidence collection = providing guesses, not diagnosis
-  
-### Context
-- **Problem**: Agents were stopping after Phase 1 or 2 when they reached "100% confidence" in analysis/hypotheses
-- **Root Cause**: Agents conflating "confident theory" with "proven diagnosis"
-- **Solution**: Explicit warnings at every potential stopping point emphasizing lack of proof until Phases 3-5 complete
-- **Impact**: Forces agents to understand that analysis/hypotheses are NOT evidence, and professional practice requires validation
-
-## [1.1.0-beta.8] - 2025-01-06
-
-### Fixed
-- **CRITICAL**: Fixed loop execution bug where body steps with `runCondition` using iteration variables were completely skipped
-  - Root cause: Loop variables (e.g., `analysisPhase`) were being injected AFTER evaluating runConditions, causing all conditions to fail
-  - Impact: Phase 1's 5-iteration analysis loop was being entirely skipped, jumping straight to Phase 1f
-  - Fix: Reordered logic to inject loop variables BEFORE evaluating body step runConditions
-  - Also fixed: Pre-existing bug where single-step loop bodies didn't increment iterations properly
-  - Test coverage: Added comprehensive integration tests (`loop-runCondition-bug.test.ts`) to prevent regression
-
-## [1.1.0-beta.7] - 2025-01-06
-
-### Fixed
-- **HOTFIX**: Corrected Phase 0e `runCondition` to use `not_equals` instead of invalid `notEquals` operator
-  - Phase 0e now properly executes only when `automationLevel != 'High'`
-  - High automation mode now proceeds through all phases without early termination checkpoint
-
-## [1.1.0-beta.6] - 2025-01-06
-
-### Added
-- **New Phase 1f**: Final Breadth & Scope Verification checkpoint after codebase analysis
-  - Prevents tunnel vision by forcing scope sanity checks before hypothesis development
-  - Requires evaluation of 2-3 alternative investigation scopes
-  - Catches the #1 cause of wrong conclusions: looking in wrong place or too narrowly
-  - Positioned strategically after Phase 1 analysis and before Phase 2 hypothesis formation
-
-### Enhanced
-- **Phase 3 (Instrumentation)**: Dramatically expanded with concrete, step-by-step instructions
-  - Language-specific code examples (JavaScript/TypeScript, Python, Java)
-  - Detailed `search_replace` usage examples for applying instrumentation
-  - Hypothesis-specific prefixes ([H1], [H2], [H3]) with standard formatting
-  - File-by-file workflow: read → locate → instrument → verify
-  - Fallback strategy if edit tools unavailable
-  - Instrumentation checklist for tracking progress
-  
-- **Phase 4 (Evidence Collection)**: Comprehensive decision tree and 7-step process
-  - **OPTION A**: Agent can execute code → 4-step execution workflow
-  - **OPTION B**: Agent cannot execute → User instruction template
-  - Clear instructions on when to use each approach
-  - Log consolidation and evidence organization by hypothesis
-  - Evidence quality assessment (1-10 scale)
-
-- **metaGuidance**: Added explicit high auto mode discipline
-  - Clarified that agents should not ask for permission between phases in high auto mode
-  - Exception: Phase 0e early termination and Phase 4a controlled experiments
-  - Reinforced that asking "should I continue?" implies investigation is optional (it is NOT)
-
-### Changed
-- Total workflow steps: 26 steps (added Phase 1f)
-- Phase 1 analysis loop: Now clearly labeled as "Analysis 1/5" through "Analysis 5/5"
-
-## [1.1.0-beta.5] - 2025-01-06
-
-### Changed
-- **Phase 0e Relocation**: Moved early termination checkpoint from Phase 5b to Phase 0e (after triage)
-  - Now appears immediately after setup, before any investigation work begins
-  - Eliminates sunk cost fallacy (decision at 5% vs 90% completion)
-  - Forces upfront decision-making about workflow commitment
-  
-### Added
-- **Mandatory User Communication**: Phase 0e now requires agents to explicitly tell users about 90% accuracy difference
-  - Template message is NOT optional - agents MUST communicate this
-  - User must explicitly confirm proceeding with full investigation
-  
-### Removed
-- **Phase 5b**: Removed old completion checkpoint (now Phase 0e)
-  - Total workflow steps reduced from 28 to 26
-
-## [1.1.0-beta.4] - 2025-01-05
-
-### Enhanced
-- **Sophisticated Code Analysis**: Integrated advanced analysis techniques from MR review workflow into Phase 1
-  
-### Added
-- **New Phase 1a**: Neighborhood, Call Graph & Contracts analysis
-  - Module root computation (nearest common ancestor, clamped to package boundary)
-  - Neighborhood mapping (immediate neighbors, imports, tests, entry points)
-  - Bounded call graph with HOT path ranking (Small Multiples ASCII visualization)
-  - Flow anchors (entry points to bug: HTTP routes, CLI commands, scheduled jobs, event handlers)
-  - Contracts & invariants discovery (API symbols, endpoints, database tables, stated guarantees)
-  
-- **Enhanced Phase 1 Structure**: Now 5 sub-phases (was 4)
-  1. Neighborhood, Call Graph & Contracts (NEW)
-  2. Breadth Scan (pattern discovery)
-  3. Deep Dive (suspicious code analysis)
-  4. Dependencies & Data Flow
-  5. Test Coverage Analysis
-  
-### Changed
-- Total workflow steps increased from 27 to 28 (added Phase 1a)
-- Phase 1 loop now iterates 5 times (was 4)
-- Each analysis phase now produces more structured, evidence-based outputs
-
-## [1.1.0-beta.3] - 2025-01-05
-
-### Fixed
-- **Critical**: Prevented ALL phase skipping, not just final documentation phase
-  - Root cause: Agents didn't understand they MUST repeatedly call workflow_next
-  - Added mandatory workflow execution instructions to metaGuidance
-  - Added early commitment checkpoint (Phase 0e) requiring user confirmation
-  - Reinforced evidence-based persuasion: 90% error rate for premature conclusions
-
-### Added
-- **Phase 0e**: Workflow Execution Commitment checkpoint
-  - Appears immediately after triage (before investigation begins)
-  - Requires agent acknowledgment of workflow structure (26 steps)
-  - Requires user confirmation to proceed with full investigation
-  - Explicit warning: stopping early leads to wrong conclusions ~90% of time
-  
-### Enhanced
-- **metaGuidance**: Added comprehensive workflow execution discipline
-  - Agents MUST call workflow_next until isComplete=true
-  - High confidence (9-10/10) does NOT mean workflow is complete
-  - Professional research shows 90% error rate for jumping to conclusions
-  - Added "WHY THIS STRUCTURE EXISTS (Evidence-Based)" section
-
-## [1.1.0-beta.2] - 2025-01-05
-
-### Added
-- **Phase 5b**: Mandatory completion checkpoint with user confirmation
-  - Prevents agents from skipping comprehensive diagnostic writeup (Phase 6)
-  - Requires explicit acknowledgment that Phase 6 is the required deliverable
-  - User must confirm proceeding to final documentation phase
-
-### Enhanced
-- **metaGuidance**: Added critical workflow discipline instructions
-  - Emphasized that high confidence does NOT equal completion
-  - Clarified that Phase 6 is a mandatory deliverable, not optional
-  - Added explicit instructions on when to set `isWorkflowComplete=true`
-
-## [1.1.0-beta.1] - 2025-01-05
-
-### Fixed
-- **Critical**: Prevented premature workflow completion
-  - Agents were jumping to conclusions and skipping phases with high confidence
-  - Root cause: Misinterpreting progress/confidence as final completion
-
-### Added
-- **metaGuidance Section**: "CRITICAL WORKFLOW DISCIPLINE"
-  - High confidence (9-10/10) does NOT mean completion
-  - Agent MUST complete all phases (0-6) regardless of confidence
-  - Only set `isWorkflowComplete=true` after Phase 6 comprehensive writeup
-  
-- **Phase-Specific Warnings**:
-  - Phase 2a (Hypothesis Formation): Warning against treating hypothesis as conclusion
-  - Phase 5a (Confidence Assessment): Warning that 10/10 confidence still requires Phase 6
-
-### Enhanced
-- **Phase 6 Instructions**: Explicit completion marking
-  - Must set `isWorkflowComplete=true` in this phase
-  - Must produce comprehensive diagnostic writeup
-  - This is the ONLY phase that marks workflow as truly complete
-
-### Changed
-- All phase prompts updated to reference 27 total workflow steps for clarity

package/workflows/bug-investigation.agentic.json

@@ -1,212 +0,0 @@
-{
-  "id": "bug-investigation-agentic",
-  "name": "Bug Investigation (Adaptive - Agentic)",
-  "version": "3.0.0",
-  "description": "Adaptive bug investigation workflow that adjusts rigor based on complexity assessed after Phase 0. Automatically chooses between QUICK (minimal delegation), STANDARD (sequential delegation), or THOROUGH (parallel delegation) modes.",
-  "clarificationPrompts": [
-    "What type of system is this? (web app, backend service, CLI tool, etc.)",
-    "How reproducible is this bug? (always, sometimes, rarely)",
-    "What access do you have? (full codebase, logs, tests, etc.)"
-  ],
-  "preconditions": [
-    "User has a specific bug or failing test to investigate",
-    "Agent has codebase access and can run tests/build",
-    "Bug is reproducible with specific steps"
-  ],
-  "metaGuidance": [
-    "WHO YOU ARE: You are a special investigator - one of the few who has the patience, determination, and skill to find the TRUE source of bugs.",
-    "Most investigators stop at the obvious explanation. You don't. You look past red herrings, challenge assumptions, and dig until you have certainty.",
-    "YOUR MISSION: Find the REAL cause of this bug. Not the apparent cause, not the first explanation, but the actual source with evidence to prove it.",
-    "WHY THIS WORKFLOW EXISTS: It gives you a systematic process to avoid the traps that catch other investigators - jumping to conclusions, confirmation bias, surface-level analysis.",
-    "HOW IT WORKS: Each phase has two steps: First you PLAN your approach (think strategically), then you EXECUTE it (do the work).",
-    "This planning step is critical - it forces you to think about HOW you'll investigate before diving in. Better plans lead to better investigations.",
-    "DELEGATION: This workflow will explicitly tell you when to delegate to the WorkRail Executor. Do NOT delegate spontaneously - ONLY when the workflow says 'Delegate to the WorkRail Executor'. If the workflow doesn't mention delegation, do the work yourself.",
-    "THE PHASES:",
-    "Phase 0: Investigate and understand the code (both structure and execution flow)",
-    "Phase 1: Form multiple hypotheses about what could be causing this (stay open-minded)",
-    "Phase 2: Design and add instrumentation to gather evidence (set up your surveillance)",
-    "Phase 3: Run instrumented code and collect evidence (gather proof, not assumptions)",
-    "Phase 4: Validate your conclusion rigorously and hand off (be your harshest critic)",
-    "CRITICAL DISTINCTION - THEORY VS PROOF:",
-    "When you read code and think 'I found it!', you have a THEORY. Theories feel certain but are often wrong.",
-    "PROOF comes from running instrumented code, collecting evidence, ruling out alternatives, and validating rigorously.",
-    "You must complete all phases to get from theory to proof. No shortcuts, even with high confidence.",
-    "YOUR DELIVERABLE: A diagnostic writeup that proves you found the true source - complete with evidence, alternative explanations ruled out, and reproduction steps.",
-    "SUCCESS MEANS: Someone reading your writeup can fix the bug confidently because you've proven what's actually happening and why.",
-    "WORKFLOW MECHANICS: Call workflow_next to get each phase. Complete the phase (both plan and execute). Call workflow_next again. Repeat until isComplete=true."
-  ],
-  "steps": [
-    {
-      "id": "phase-0a-plan",
-      "title": "Phase 0A: Plan Your Investigation Strategy",
-      "prompt": "**PLAN HOW YOU'LL INVESTIGATE THIS BUG**\n\nBefore diving in, think strategically about HOW you'll investigate.\n\n**Understand the Problem:**\n- What's the bug? (symptoms, reproduction steps)\n- Where does execution start? (API call, user action, test, scheduled job?)\n- What's the error or unexpected behavior?\n\n**Plan Your Investigation:**\n\n1. **Context Gathering Strategy:**\n   - What parts of the codebase are relevant?\n   - What components/systems are involved?\n   - How will you identify the key areas to investigate?\n\n2. **Execution Tracing Strategy:**\n   - Will you trace from entry point to error?\n   - Or start at the error and work backwards?\n   - What's the execution path you need to understand?\n\n3. **Risk Mitigation:**\n   - What could cause you to miss the real issue?\n   - Focusing too narrowly? Missing indirect causes?\n   - Assuming things work as documented?\n\n**OUTPUT**: Create BUG_investigation.md with \"Investigation Plan\":\n- Problem summary\n- Investigation strategy (context + execution)\n- Key questions to answer\n- Risks to watch out for\n\n**Self-Check**: Is your plan specific enough to follow? Does it account for ways you might miss the real cause?",
-      "agentRole": "You are a strategic investigator planning your approach. Think before you dive in.",
-      "requireConfirmation": false,
-      "guidance": [
-        "STRATEGY: Plan both context gathering AND execution tracing",
-        "SCOPE: Identify relevant parts of codebase",
-        "RISKS: Identify ways you might miss the real cause",
-        "OUTPUT: Create BUG_investigation.md with your plan"
-      ]
-    },
-    {
-      "id": "phase-0b-execute",
-      "title": "Phase 0B: Execute Investigation (Context + Execution)",
-      "prompt": "**INVESTIGATE THE CODE - UNDERSTAND STRUCTURE AND EXECUTION**\n\nNow execute your investigation plan. You need to understand BOTH what code exists AND what it does.\n\n**STEP 1: GATHER CONTEXT (What code exists)**\n\nDO NOT DELEGATE - Do this investigation yourself. Use systematic techniques to understand the codebase structure.\n\n**Prepare your Work Package:**\n```\nMISSION: Understand how [feature/system from bug report] works in this codebase\n\nTARGET: [Extract from bug report]\n- Bug: \"Login fails with 401\" \u2192 Target: \"authentication system\"\n- Bug: \"Export crashes\" \u2192 Target: \"data export functionality\"\n\nCONTEXT:\n- Bug Description: [Paste the bug description]\n- Reproduction Steps: [How to trigger the bug]\n- Symptoms: [What you observe]\n\nDEPTH: 2 (Explore - balance breadth and detail)\n\nDELIVERABLE: Working notes for BUG_investigation.md\n- Component map (what exists, how it's organized)\n- Key files and their purposes\n- Architecture patterns observed\n```\n\n**Execute the routine:**\n```\nUse the tools directly (list_dir, codebase_search, grep, read_file) at depth=2 (Explore level).\n\nWork Package: [Paste the work package from above]\n```\n\n**STEP 2: TRACE EXECUTION (What code does)**\n\nNow trace the execution flow from entry point to error.\n\n**Trace the execution:**\n- Where does execution begin? (entry point)\n- Follow the call chain step-by-step (with file:line)\n- Track how data flows and transforms\n- Note state changes along the way\n- Identify suspicious points\n\n**STEP 3: DOCUMENT EVERYTHING**\n\nUpdate BUG_investigation.md with complete investigation:\n\n```markdown\n# Bug Investigation\n\n## Problem Summary\n[Bug description, reproduction steps, symptoms]\n\n## Codebase Context\n### Component Map\n[What code exists, how it's organized]\n\n### Key Files\n- [file:line] - [purpose]\n\n### Architecture Patterns\n[Patterns observed]\n\n## Execution Flow\n### Entry Point\n[Where execution begins]\n\n### Call Chain\n1. [file:line] - [what happens]\n2. [file:line] - [what happens]\n...\n\n### Data Flow\n[How data transforms]\n\n### State Changes\n[What gets modified]\n\n### Suspicious Points\n[Code that could be problematic]\n\n## Gaps & Uncertainties\n[What we don't understand yet]\n```\n\n**Self-Critique**:\n- Did you understand both structure AND execution?\n- Did you actually trace the execution flow, or just read code?\n- What surprised you?\n- What are you still uncertain about?\n\n**Before Proceeding**: Can you explain how this code works (both structure and execution) to someone else?",
-      "agentRole": "You are executing your investigation plan systematically. Document both structure and execution.",
-      "requireConfirmation": false,
-      "guidance": [
-        "DO NOT DELEGATE: Execute investigation yourself, don't delegate to subagent",
-        "TECHNIQUES: Use Context Gathering Routine techniques (list_dir, codebase_search, grep, read_file)",
-        "TRACING: Manually trace execution flow from entry to error",
-        "DOCUMENTATION: Create BUG_investigation.md with BOTH structure and execution",
-        "CITATIONS: Include file:line references for everything",
-        "DISCIPLINE: Follow your plan, don't jump to conclusions"
-      ]
-    },
-    {
-      "id": "phase-0c-assess",
-      "title": "Phase 0C: Assess Complexity & Choose Mode",
-      "prompt": "**ASSESS INVESTIGATION COMPLEXITY & CHOOSE MODE**\n\nBased on your Phase 0 investigation, assess the complexity and choose the appropriate mode.\n\n**COMPLEXITY ASSESSMENT:**\n\nReview your BUG_investigation.md:\n\n1. **Scope:** Components involved [count], Systems interacting [count]\n2. **Execution:** Call chain depth [steps], Execution paths [count]\n3. **Understanding:** Suspicious points [count], Gaps [count], Confidence [1-10]\n4. **Risk:** Production system? Critical bug? Multiple causes? Unclear path?\n\n**MODE DECISION CRITERIA:**\n\n**THOROUGH** (Use if ANY true):\n- 5+ components OR 10+ step call chain OR 5+ suspicious points\n- Confidence < 7/10 OR Many gaps\n- Production + Critical bug OR Multiple possible causes\n\n**QUICK** (Use if ALL true):\n- 1-2 components AND < 5 step call chain AND 1-2 suspicious points\n- Few gaps AND Confidence 8+/10\n- Non-critical bug AND Clear single cause\n\n**STANDARD** (Otherwise): Middle ground between QUICK and THOROUGH\n\n**MAKE YOUR DECISION:**\n\nChoose: **QUICK**, **STANDARD**, or **THOROUGH**\n\nDocument in BUG_investigation.md:\n```markdown\n## Mode Decision: [QUICK/STANDARD/THOROUGH]\n**Rationale:** [Your reasoning based on criteria above]\n```\n\n**What Each Mode Means:**\n\n- **QUICK**: You'll form hypotheses yourself, minimal delegation, move fast\n- **STANDARD**: You'll form hypotheses, then get sequential challenge/validation\n- **THOROUGH**: You'll use parallel ideation + parallel challenge + parallel validation\n\n**Remember your choice** for later phases!",
-      "agentRole": "You are assessing complexity to choose the right level of rigor.",
-      "requireConfirmation": false,
-      "guidance": [
-        "HONEST ASSESSMENT: Don't underestimate complexity",
-        "USE CRITERIA: Follow the decision rules, don't just pick your favorite",
-        "DOCUMENT: Write your decision and rationale clearly",
-        "REMEMBER: You'll adapt your approach in later phases"
-      ]
-    },
-    {
-      "id": "phase-0d-audit",
-      "title": "Phase 0D: Audit Investigation (Optional - THOROUGH mode)",
-      "prompt": "**AUDIT YOUR INVESTIGATION** (THOROUGH mode only)\n\n\u26a0\ufe0f **MODE CHECK**: Did you choose THOROUGH mode in Phase 0C?\n- If YES: Continue with this audit\n- If NO (STANDARD or QUICK): Skip this step, proceed to Phase 1\n\n**AUDIT YOUR INVESTIGATION FOR COMPLETENESS AND DEPTH**\n\nYou've investigated the code. Now get independent review.\n\n**PARALLEL CONTEXT AUDIT**\n\n\u26a0\ufe0f **CRITICAL: Delegate to the WorkRail Executor TWICE SIMULTANEOUSLY, not sequentially.**\n\nDelegate to the WorkRail Executor TWICE AT THE SAME TIME with different focuses:\n\n**Delegation (Completeness Focus):**\n```\nPlease execute the 'Context Gathering Routine' workflow in audit mode.\n\nAudit Request:\nMISSION: Audit my investigation for COMPLETENESS\n\nMY INVESTIGATION:\n[Paste the contents of BUG_investigation.md]\n\nFOCUS: Completeness\n- Did I miss any critical files or areas?\n- Are there important components I didn't investigate?\n- Did I trace the complete execution path?\n- What else should I have looked at?\n```\n\n**Delegation (Depth Focus):**\n```\nPlease execute the 'Context Gathering Routine' workflow in audit mode.\n\nAudit Request:\nMISSION: Audit my investigation for DEPTH\n\nMY INVESTIGATION:\n[Paste the contents of BUG_investigation.md]\n\nFOCUS: Depth\n- Did I go deep enough in my understanding?\n- Did I understand WHY, not just WHAT?\n- Should I have read implementations instead of just signatures?\n- What areas need deeper investigation?\n```\n\n**SYNTHESIZE AUDIT FEEDBACK**\n\nReview both audit deliverables:\n1. Completeness audit: What did I miss?\n2. Depth audit: Where should I go deeper?\n\n**Synthesis Strategy:**\n- Common concerns: If both flag same area \u2192 High priority\n- Unique insights: Each may catch different gaps\n- Conflicting advice: Investigate to understand why\n\n**ITERATE IF NEEDED**\n\nBased on feedback, investigate further if significant gaps:\n- Run Context Gathering Routine again (depth=3 or different target)\n- Trace additional execution paths\n- Read implementations you skipped\n\n**FINALIZE INVESTIGATION**\n\nUpdate BUG_investigation.md with:\n- Audit findings synthesized\n- Additional investigation completed\n- Final understanding of structure and execution\n\n**Before Proceeding**: Did both auditors confirm your understanding is sufficient?",
-      "agentRole": "You are getting independent review of your investigation to ensure completeness and depth.",
-      "requireConfirmation": false,
-      "guidance": [
-        "MODE: Only do this if you chose THOROUGH mode in Phase 0C",
-        "PARALLEL: Delegate twice to WorkRail Executor SIMULTANEOUSLY",
-        "DIVERSITY: Each has different focus (completeness vs depth)",
-        "SYNTHESIS: Combine both perspectives",
-        "ITERATE: Investigate further if significant gaps found",
-        "QUALITY GATE: Don't proceed until both perspectives satisfied"
-      ]
-    },
-    {
-      "id": "phase-1a-plan",
-      "title": "Phase 1A: Plan Your Hypothesis Development",
-      "prompt": "**CRITICAL CHECKPOINT: IS THIS ACTUALLY A BUG?**\n\nBefore forming hypotheses about what's wrong, investigate the original intent.\n\n**Investigate Original Intent:**\n\n1. **Check git history:**\n   - Use git log/blame on relevant files\n   - Look for commit messages explaining this behavior\n   - When was this code written? By whom?\n\n2. **Search for documentation:**\n   - Comments explaining the behavior\n   - README or design docs\n   - ADRs (Architecture Decision Records)\n   - Issue/ticket history\n\n3. **Examine tests:**\n   - What behavior do tests validate?\n   - Do tests expect this behavior?\n   - Are there tests that would fail if you \"fixed\" this?\n\n4. **Consider constraints:**\n   - What requirements might explain this?\n   - What technical constraints could justify this?\n   - What trade-offs might have been made?\n\n**CRITICAL QUESTION**: Could this be working as designed, not a bug?\n\n---\n\n**PLAN HOW YOU'LL FORM HYPOTHESES**\n\nBased on your investigation, you'll now develop hypotheses about what's causing the bug.\n\n**Think Through**:\n\n1. **What patterns did you notice?**\n   - From your execution flow tracing, what stood out?\n   - What code seemed suspicious?\n   - What assumptions are baked into the code?\n\n2. **What types of causes should you consider?**\n   - Logic errors in the code?\n   - Data issues (wrong format, corruption, missing)?\n   - Timing or race conditions?\n   - Environment or configuration issues?\n   - Integration problems with dependencies?\n   - **Working as designed** (not actually a bug)?\n\n3. **How will you avoid anchoring on your first idea?**\n   - How many alternative hypotheses will you generate?\n   - How will you challenge your initial impressions?\n   - What evidence would contradict your leading theory?\n\n4. **What makes a good hypothesis?**\n   - Specific enough to test\n   - Explains all the symptoms\n   - Has clear evidence for/against\n   - Can be proven or disproven\n\n**OUTPUT**: Update BUG_investigation.md with \"Phase 2 Hypothesis Strategy\":\n- Results of your intent investigation\n- How you'll generate multiple hypotheses\n- What types of causes you'll consider (including \"not a bug\")\n- How you'll avoid confirmation bias\n- How you'll test your hypotheses\n\n**Self-Check**: Are you committed to generating multiple hypotheses, or are you already attached to one idea? Have you seriously considered that this might not be a bug?",
-      "agentRole": "You are strategizing about hypothesis formation. Commit to staying open-minded.",
-      "requireConfirmation": false,
-      "guidance": [
-        "INTENT: Check git history, comments, tests, docs for original intent",
-        "QUESTION: Could this be working as designed?",
-        "MINDSET: Commit to generating multiple hypotheses, not just one",
-        "DIVERSITY: Consider different types of causes (including 'not a bug')",
-        "BIAS: Plan how you'll avoid anchoring on your first idea",
-        "OUTPUT: Document intent investigation and hypothesis strategy"
-      ]
-    },
-    {
-      "id": "phase-1b-execute",
-      "title": "Phase 1B: Form Hypotheses (Mode-Adaptive)",
-      "prompt": "**FORM HYPOTHESES BASED ON YOUR CHOSEN MODE**\n\n\u26a0\ufe0f **CHECK YOUR MODE** (from Phase 0C): QUICK, STANDARD, or THOROUGH?\n\n---\n\n**IF YOU CHOSE THOROUGH MODE:**\n\n**FORM MULTIPLE HYPOTHESES ABOUT THE BUG**\n\nYou've completed your investigation and traced execution flow. Now generate hypotheses about what's causing the bug.\n\n**PARALLEL IDEATION - DIVERGENT THINKING**\n\n\u26a0\ufe0f **CRITICAL: Delegate to the WorkRail Executor THREE TIMES SIMULTANEOUSLY, not sequentially.**\n\nInstead of forming hypotheses yourself, delegate to the WorkRail Executor THREE TIMES SIMULTANEOUSLY with different perspectives:\n\n**Delegation - Logic Errors Perspective:**\n```\nPlease execute the 'Ideation Routine' workflow.\n\nIdeation Request:\nPROBLEM: What is causing this bug?\n\nCONSTRAINTS:\n- Must explain all observed symptoms\n- Must be testable with instrumentation\n- Must be specific (file:line level)\n\nCONTEXT:\nRead these files:\n- BUG_investigation.md (codebase context)\n- BUG_investigation.md (execution trace)\n\nPERSPECTIVE: Logic Errors\nFocus on: Wrong conditions, off-by-one errors, incorrect operators, \nmissing checks, wrong order of operations, flawed algorithms\n\nQUANTITY: 5-7 hypotheses\n\nDELIVERABLE: BUG_hypotheses_logic.md\n```\n\n**Delegation - Data/State Perspective:**\n```\nPlease execute the 'Ideation Routine' workflow.\n\nIdeation Request:\nPROBLEM: What is causing this bug?\n\nCONSTRAINTS:\n- Must explain all observed symptoms\n- Must be testable with instrumentation\n- Must be specific (file:line level)\n\nCONTEXT:\nRead these files:\n- BUG_investigation.md (codebase context)\n- BUG_investigation.md (execution trace)\n\nPERSPECTIVE: Data/State Issues\nFocus on: Data corruption, wrong state management, race conditions,\nuninitialized variables, type mismatches, mutation issues\n\nQUANTITY: 5-7 hypotheses\n\nDELIVERABLE: BUG_hypotheses_data.md\n```\n\n**Delegation - Integration/Environment Perspective:**\n```\nPlease execute the 'Ideation Routine' workflow.\n\nIdeation Request:\nPROBLEM: What is causing this bug?\n\nCONSTRAINTS:\n- Must explain all observed symptoms\n- Must be testable with instrumentation\n- Must be specific (file:line level)\n\nCONTEXT:\nRead these files:\n- BUG_investigation.md (codebase context)\n- BUG_investigation.md (execution trace)\n\nPERSPECTIVE: Integration/Environment\nFocus on: Dependency issues, config problems, environment differences,\nAPI contract violations, timing issues, resource constraints\n\nQUANTITY: 5-7 hypotheses\n\nDELIVERABLE: BUG_hypotheses_integration.md\n```\n\n**SYNTHESIZE ALL HYPOTHESES**\n\nReview all three deliverables (15-21 hypotheses total):\n1. Logic errors perspective\n2. Data/state perspective  \n3. Integration/environment perspective\n\n**Synthesis Process:**\n1. **Deduplicate**: Combine similar hypotheses from different perspectives\n2. **Refine**: Improve clarity and specificity\n3. **Rank**: Order by likelihood based on evidence\n4. **Select**: Pick top 5-7 most promising hypotheses\n\n**Create BUG_hypotheses.md** with:\n- Synthesized hypothesis list (5-7 hypotheses)\n- Each hypothesis using this template:\n  - **ID**: H1, H2, H3, etc.\n  - **Statement**: \"The bug occurs because [specific cause]\"\n  - **Source**: Which perspective(s) generated this\n  - **Evidence For**: What from investigation supports this\n  - **Evidence Against**: What contradicts this\n  - **How to Test**: What evidence would prove/disprove this\n  - **Likelihood** (1-10): Based on current evidence\n\n**PARALLEL ADVERSARIAL CHALLENGE**\n\n\u26a0\ufe0f **CRITICAL: Spawn BOTH challengers SIMULTANEOUSLY.**\n\nAfter synthesizing hypotheses, delegate to TWO Hypothesis Challengers AT THE SAME TIME:\n\n**Delegation - Moderate Rigor (rigor=3):**\n```\nPlease execute the 'Hypothesis Challenge Routine' workflow at rigor=3.\n\nChallenge Request:\nHYPOTHESES: [Paste your 5-7 synthesized hypotheses from BUG_hypotheses.md]\n\nEVIDENCE:\nRead these files:\n- BUG_investigation.md\n- BUG_investigation.md\n\nRIGOR: 3 (Thorough adversarial analysis)\n\nChallenge each hypothesis and find weaknesses.\n\nDELIVERABLE: BUG_challenges_moderate.md\n```\n\n**Delegation - Maximum Rigor (rigor=5):**\n```\nPlease execute the 'Hypothesis Challenge Routine' workflow at rigor=5.\n\nChallenge Request:\nLEADING HYPOTHESIS: [Your most likely hypothesis from BUG_hypotheses.md]\n\nEVIDENCE:\nRead these files:\n- BUG_investigation.md\n- BUG_investigation.md\n\nRIGOR: 5 (Try to completely break this)\n\nTry to prove this hypothesis is WRONG. Find any way it could fail.\n\nDELIVERABLE: BUG_challenges_maximum.md\n```\n\n**FINAL SYNTHESIS**\n\nReview both challenge deliverables:\n- If Challenger 1 finds issues: Strengthen or revise hypotheses\n- If Challenger 2 breaks leading hypothesis: Reconsider alternatives\n- If both give green light: High confidence in your hypotheses\n\n**Update BUG_hypotheses.md** with:\n- Challenge results and findings\n- Revised hypotheses (if needed)\n- Updated likelihood scores\n- Final ranking for testing\n\n**\ud83d\udea8 CRITICAL - YOU ARE NOT DONE:**\n\nYou now have theories. You do NOT have proof.\n\nEven if H1 has 10/10 likelihood, it's based on reading code, not evidence from running code.\n\nYou MUST continue to Phase 2 (design instrumentation) and Phase 2 (collect evidence).\n\nThis is not optional. High confidence without evidence = educated guess, not diagnosis.\n\nCall workflow_next to continue.\n\n---\n\n**IF YOU CHOSE STANDARD MODE:**\n\nSkip the parallel ideation. Instead:\n\n1. **Form 5-7 hypotheses yourself** using the investigation\n2. **Delegate to ONE Hypothesis Challenger** (rigor=3):\n   ```\n   Please execute the 'Hypothesis Challenge Routine' workflow at rigor=3.\n   \n   Challenge Request:\n   HYPOTHESES: [Your 5-7 hypotheses]\n   EVIDENCE: Read BUG_investigation.md\n   RIGOR: 3\n   \n   Challenge each hypothesis.\n   ```\n3. **Refine** based on challenge feedback\n\n---\n\n**IF YOU CHOSE QUICK MODE:**\n\nSkip all delegation. Instead:\n\n1. **Form 3-5 hypotheses yourself** quickly\n2. **Self-challenge**: What could I be wrong about?\n3. **Rank** by likelihood\n4. **Move on** - don't over-analyze\n\n---\n\n**OUTPUT:** BUG_hypotheses.md (format based on your mode)",
-      "agentRole": "You are forming competing hypotheses and subjecting them to rigorous challenge. Stay open to alternatives even if one seems obvious.",
-      "requireConfirmation": false,
-      "guidance": [
-        "MODE: Adapt your approach based on your Phase 0C decision",
-        "PARALLEL IDEATION: Delegate 3 times to WorkRail Executor SIMULTANEOUSLY (not one-by-one)",
-        "DIVERSITY: Each ideator has different perspective (logic, data, integration)",
-        "SYNTHESIS: Combine all hypotheses, deduplicate, refine to top 5-7",
-        "PARALLEL CHALLENGE: Delegate twice to WorkRail Executor SIMULTANEOUSLY",
-        "RIGOR: Different challenge levels (3 and 5)",
-        "FINAL SYNTHESIS: Integrate all perspectives",
-        "REMINDER: High confidence \u2260 proof. You still need evidence."
-      ]
-    },
-    {
-      "id": "phase-2a-plan",
-      "title": "Phase 2A: Design Your Instrumentation Strategy",
-      "prompt": "**PLAN HOW YOU'LL GATHER EVIDENCE**\n\nYou have hypotheses. Now design how you'll gather evidence to test them.\n\n**Think Through**:\n\n1. **What evidence would prove each hypothesis?**\n   - For H1, what specific data points would confirm it?\n   - For H2, what would you observe if it's correct?\n   - How can you distinguish between competing hypotheses?\n\n2. **Where should you add instrumentation?**\n   - What points in the execution flow are critical?\n   - Where could you observe the data/state you need?\n   - What's already being logged vs what do you need to add?\n\n3. **What's the right level of detail?**\n   - Too much logging = noise and hard to analyze\n   - Too little = gaps and missing evidence\n   - How will you balance this?\n\n4. **Can you use existing tests?**\n   - Are there tests you can enhance instead of adding new logging?\n   - Can you modify tests to expose the state you need?\n   - Should you write new targeted tests?\n\n**OUTPUT**: Update BUG_investigation.md with \"Phase 3 Instrumentation Plan\":\n- What evidence you need for each hypothesis\n- Where you'll add instrumentation (file:line)\n- What you'll log/observe at each point\n- Test scenarios you'll prepare\n- How you'll organize output to distinguish hypotheses\n\n**Self-Check**: Will this instrumentation actually give you the evidence you need? What might you miss?",
-      "agentRole": "You are designing your evidence collection strategy. Think carefully about what you need to prove.",
-      "requireConfirmation": false,
-      "guidance": [
-        "EVIDENCE: Define what would prove/disprove each hypothesis",
-        "INSTRUMENTATION: Plan where to add logging/debugging",
-        "BALANCE: Enough detail to distinguish hypotheses, not so much you drown in noise",
-        "OUTPUT: Document your instrumentation plan"
-      ]
-    },
-    {
-      "id": "phase-2b-execute",
-      "title": "Phase 2B: Implement Your Instrumentation",
-      "prompt": "**ADD INSTRUMENTATION AND PREPARE TEST SCENARIOS**\n\nNow implement the instrumentation strategy you designed.\n\n**DELEGATION OPPORTUNITY: Execution Simulation**\n\nBefore adding instrumentation, consider simulating execution to predict outcomes and refine your strategy.\n\n**HOW TO DELEGATE:**\n\n1. **Prepare the work package:**\n```\nMISSION: Simulate execution paths for my top hypotheses\n\nHYPOTHESES: [Paste top 3-5 hypotheses]\n\nCONTEXT:\n- BUG_investigation.md (file reference)\n- BUG_hypotheses.md (file reference)\n- Key files: [List critical files from investigation]\n\nMODE: trace (Detailed execution path analysis)\n\nDELIVERABLE:\nFor each hypothesis:\n- Predicted execution path (step-by-step)\n- State changes at each step\n- Where instrumentation would be most revealing\n- Expected outputs if hypothesis is correct\n- Distinguishing characteristics between hypotheses\n```\n\n2. **Delegate to the WorkRail Executor:**\n\nDelegate to the WorkRail Executor:\n```\nPlease execute the 'Execution Simulation Routine' workflow in trace mode.\n\nWork Package: [Paste the work package from above]\n```\n\n**AFTER DELEGATION:**\nUse the simulation results to refine your instrumentation plan.\n\n**Implement**:\n- Add debug logging at the points identified by simulation\n- Enhance or create tests to expose necessary state\n- Add assertions to catch violations\n- Set up controlled experiments if needed\n- Label everything clearly ([H1], [H2], etc.)\n\n**Prepare Test Scenarios**:\n- Minimal reproduction case\n- Edge cases that might behave differently\n- Working scenarios for comparison\n- Variations that test specific hypotheses\n\n**OUTPUT**: Update BUG_investigation.md with:\n- List of instrumentation added (what/where/why)\n- Test scenarios prepared\n- Expected outcomes for each hypothesis (from simulation)\n- How you'll analyze results\n\n**Self-Critique**:\n- Did you add the instrumentation you planned?\n- Did you skip any because it seemed unnecessary?\n- Is your instrumentation labeled clearly?\n- Are your test scenarios sufficient?\n\n**Readiness Check**: If you run these tests, will you get the evidence you need to prove/disprove your hypotheses?",
-      "agentRole": "You are implementing your evidence collection plan with precision, informed by execution simulation. Good instrumentation is the foundation of proof.",
-      "requireConfirmation": false,
-      "guidance": [
-        "DELEGATION: Consider using execution-simulator subagent first",
-        "TOOLS: Use edit tools to add instrumentation",
-        "LABELING: Mark instrumentation clearly ([H1], [H2], etc.)",
-        "TESTS: Prepare test scenarios before running"
-      ]
-    },
-    {
-      "id": "phase-3-execute",
-      "title": "Phase 3: Collect Evidence",
-      "prompt": "**RUN INSTRUMENTED CODE AND COLLECT EVIDENCE**\n\nNow run your test scenarios and collect the evidence.\n\n**Execute**:\n- Run minimal reproduction case\n- Run edge cases and variations\n- Run working scenarios for comparison\n- Capture all output (logs, errors, test results)\n\n**Organize Evidence**:\nFor each hypothesis, create BUG_evidence_H1.md, BUG_evidence_H2.md, etc.:\n- What did the instrumentation reveal?\n- Does behavior match predictions?\n- What unexpected findings emerged?\n- Quality rating (1-10): How strong is this evidence?\n\n**Analyze Patterns**:\n- Which hypotheses are supported by evidence?\n- Which are contradicted?\n- Are there patterns you didn't predict?\n- Do you need different instrumentation?\n- Should you form new hypotheses?\n\n**Update Hypotheses**:\nUpdate BUG_hypotheses.md with:\n- Evidence collected for each\n- New likelihood scores based on evidence\n- Evidence quality ratings\n- New insights or remaining questions\n\n**Decision Point**:\n- Strong evidence (8+/10) for one hypothesis? \u2192 Proceed to validation\n- Need more instrumentation? \u2192 Go back and add it\n- Need to revise hypotheses? \u2192 Update them\n\nBut you're not done until you have strong evidence. Keep investigating.",
-      "agentRole": "You are collecting evidence systematically. Let the data guide you, not your assumptions.",
-      "requireConfirmation": false,
-      "guidance": [
-        "EXECUTION: Run your test scenarios and capture all output",
-        "ORGANIZATION: Create BUG_evidence_H1.md, BUG_evidence_H2.md, etc.",
-        "ANALYSIS: Compare actual behavior to predictions",
-        "ITERATION: If evidence is weak, add more instrumentation"
-      ]
-    },
-    {
-      "id": "phase-4a-validate",
-      "title": "Phase 4A: Validate Conclusion (Mode-Adaptive)",
-      "prompt": "**VALIDATE YOUR CONCLUSION BASED ON YOUR MODE**\n\n\u26a0\ufe0f **CHECK YOUR MODE** (from Phase 0C): QUICK, STANDARD, or THOROUGH?\n\n---\n\n**IF YOU CHOSE THOROUGH MODE:**\n\nUse parallel multi-perspective validation:\n\n**RIGOROUSLY VALIDATE YOUR FINDING**\n\nYou have a leading hypothesis with evidence. Now be your harshest critic.\n\n**State Your Conclusion**:\n- What hypothesis has the strongest evidence?\n- What's your confidence (1-10)?\n- What evidence supports it?\n\n**DELEGATION OPPORTUNITY: Adversarial Validation**\n\nYour conclusion needs rigorous challenge. Delegate to the WorkRail Executor for maximum-rigor adversarial review.\n\n**HOW TO DELEGATE:**\n\n1. **Prepare the work package:**\n```\nMISSION: Rigorously validate my bug diagnosis\n\nHYPOTHESES:\n- Leading hypothesis: [Your conclusion]\n- Alternatives considered: [List other hypotheses you ruled out]\n\nEVIDENCE:\n- BUG_evidence_H*.md files (file references)\n- BUG_hypotheses.md (file reference)\n- BUG_investigation.md (file reference)\n- Instrumentation output/logs (file references or inline)\n\nRIGOR: 5 (Maximum - exhaustive adversarial review)\n\nDELIVERABLE:\n- Strengths of leading hypothesis\n- Weaknesses and gaps\n- Alternative explanations not yet ruled out\n- Contradicting evidence\n- Edge cases that might break the explanation\n- Verdict with confidence assessment\n- Recommendations for additional validation\n```\n\n2. **Instruct the Hypothesis Challenger:**\n\nDelegate to the WorkRail Executor:\n```\nPlease execute the 'Hypothesis Challenge Routine' workflow at rigor=5 (Maximum level).\n\nWork Package: [Paste the work package from above]\n```\n\n**AFTER DELEGATION:**\nReview the Hypothesis Challenger's adversarial critique.\n\n**If confidence < 9/10**:\n- What specific test would raise confidence?\n- What alternative should you rule out?\n- What additional evidence do you need?\n- Go collect that evidence\n\n**Final Assessment**:\nAnswer these YES/NO:\n- Does this explain all observed symptoms?\n- Have you ruled out major alternatives?\n- Can you reproduce the bug based on this understanding?\n- Would you stake your reputation on this diagnosis?\n- Is there any contradicting evidence?\n- Did the adversarial review strengthen or weaken your confidence?\n\n**OUTPUT**: BUG_validation.md with:\n- Leading hypothesis and evidence\n- Alternatives considered and ruled out\n- Adversarial review findings (from Hypothesis Challenger)\n- Final confidence score\n- Remaining uncertainties\n\n**Threshold**: 9+/10 confidence with strong evidence to proceed. If not, keep investigating.\n\n**PARALLEL MULTI-PERSPECTIVE VALIDATION**\n\n\u26a0\ufe0f **CRITICAL: Spawn ALL THREE subagents SIMULTANEOUSLY.**\n\nBefore committing to your conclusion, get three independent perspectives AT THE SAME TIME:\n\n**Validator 1 - Hypothesis Challenger (rigor=5):**\n```\nPlease execute the 'Hypothesis Challenge Routine' workflow at rigor=5.\n\nChallenge Request:\nCONCLUSION: [Your final conclusion about the bug]\nEVIDENCE: [All evidence supporting this conclusion]\nRIGOR: 5 (Maximum adversarial review)\n\nTry to prove this conclusion is WRONG. Find any holes in the logic.\n```\n\n**Validator 2 - Execution Simulator:**\n```\nPlease execute the 'Execution Simulation Routine' workflow.\n\nSimulation Request:\nMISSION: Simulate the proposed fix\n\nPROPOSED FIX: [Your fix from BUG_validation.md]\nCONTEXT: [Relevant code context]\n\nSCENARIOS:\n1. Does the fix resolve the bug?\n2. Does the fix introduce new issues?\n3. Are there edge cases the fix doesn't handle?\n\nDELIVERABLE: BUG_fix_simulation.md\n```\n\n**Validator 3 - Plan Analyzer:**\n```\nPlease execute the 'Plan Analysis Routine' workflow.\n\nAnalysis Request:\nPLAN: [Your fix plan from BUG_validation.md]\n\nANALYZE:\n- Is the plan complete?\n- Are there missing steps?\n- Are there risks or gotchas?\n- Does it follow best practices?\n\nDELIVERABLE: BUG_plan_analysis.md\n```\n\n**FINAL SYNTHESIS - TRIPLE VALIDATION GATE:**\n\nReview all three perspectives:\n1. Hypothesis Challenger: Can they break your conclusion?\n2. Execution Simulator: Does the fix work in simulation?\n3. Plan Analyzer: Is the fix plan sound?\n\n**Quality Gate:**\n- \u2705 ALL THREE give green light \u2192 Proceed with confidence\n- \u26a0\ufe0f ONE raises concerns \u2192 Investigate and address\n- \ud83d\uded1 TWO+ raise concerns \u2192 Return to Phase 1 (re-form hypotheses)\n\n**ONLY PROCEED if you have triple validation.**\n\nUpdate BUG_validation.md with all validation results.\n\n---\n\n**IF YOU CHOSE STANDARD MODE:**\n\nUse sequential validation:\n\n1. **Delegate to Hypothesis Challenger** (rigor=5):\n   ```\n   Please execute the 'Hypothesis Challenge Routine' workflow at rigor=5.\n   \n   Challenge Request:\n   CONCLUSION: [Your conclusion]\n   EVIDENCE: Read BUG_investigation.md and evidence files\n   RIGOR: 5\n   \n   Try to prove this is WRONG.\n   ```\n\n2. **Address concerns** if any raised\n3. **Proceed** if validation passes\n\n---\n\n**IF YOU CHOSE QUICK MODE:**\n\nSelf-validate:\n\n1. **Self-challenge**: What could I be wrong about?\n2. **Check**: Does this explain ALL symptoms?\n3. **Verify**: Can I reproduce based on this understanding?\n4. **Proceed** if confident\n\n---\n\n",
-      "agentRole": "You are validating your conclusion with maximum rigor, leveraging adversarial challenge to ensure you haven't missed anything.",
-      "requireConfirmation": false,
-      "guidance": [
-        "MODE: Adapt validation rigor based on your Phase 0C decision",
-        "CONSTRAINT: Validate your conclusion, but do NOT implement the fix",
-        "DELEGATION: Use hypothesis-challenger subagent at maximum rigor",
-        "THRESHOLD: Need 9+/10 confidence to proceed",
-        "ALTERNATIVES: Ensure you've ruled out major competing explanations",
-        "HONESTY: If confidence is low, go back and gather more evidence",
-        "PARALLEL: Spawn all 3 validators SIMULTANEOUSLY",
-        "DIVERSITY: Three different cognitive modes (adversarial, simulation, planning)",
-        "TRIPLE GATE: ALL THREE must validate before proceeding",
-        "ITERATE: If 2+ raise concerns, return to Phase 2"
-      ]
-    },
-    {
-      "id": "phase-4b-writeup",
-      "title": "Phase 4B: Prove Your Case",
-      "prompt": "**DOCUMENT YOUR INVESTIGATION - PROVE YOU FOUND THE TRUE SOURCE**\n\nYou've found the true source of the bug. Now prove it to others.\n\n**Your Task**: Create a diagnostic writeup that proves your case.\n\n**Structure**:\n\n**1. EXECUTIVE SUMMARY** (3-5 sentences)\n- What's the bug?\n- What's the true cause?\n- How confident are you? (should be 9-10/10)\n- What's the impact?\n\n**2. THE TRUE SOURCE** (detailed)\n- Explain the root cause\n- Why this causes the observed symptoms\n- Code locations (file:line)\n- Relevant code snippets\n\n**3. THE PROOF** (your evidence)\n- Key evidence that proves this diagnosis\n- How you collected it (instrumentation, tests)\n- Evidence quality and sources\n- Why alternative explanations don't fit\n\n**4. HOW TO REPRODUCE**\n- Minimal steps to reproduce\n- What to observe that confirms the diagnosis\n- Conditions required\n\n**5. YOUR INVESTIGATION**\n- What you analyzed\n- Hypotheses you tested\n- How you arrived at the conclusion\n- Key turning points\n\n**6. FIXING IT**\n- Suggested approach (conceptual)\n- Risks to consider\n- How to verify the fix\n- Tests that should be added\n\n**7. UNCERTAINTIES** (if any)\n- What you're still unsure about\n- Edge cases needing more investigation\n\n**OUTPUT**: BUG_diagnostic.md\n\n**Quality Check**:\n- Could someone fix this bug confidently from your writeup?\n- Have you proven your case with evidence?\n- Is it clear WHY this is the true source, not just a symptom?\n\n**Mission Complete**: You've tracked down the true source and proven it. Well done.",
-      "agentRole": "You are documenting your successful investigation. You found the truth - now prove it to others.",
-      "requireConfirmation": false,
-      "guidance": [
-        "AUDIENCE: Write for someone who will fix the bug",
-        "PROOF: Include evidence, not just assertions",
-        "REPRODUCTION: Provide clear steps to reproduce",
-        "OUTPUT: Create BUG_diagnostic.md"
-      ]
-    },
-    {
-      "id": "phase-4b-handoff",
-      "title": "Phase 4B: Investigation Complete - Handoff",
-      "prompt": "**INVESTIGATION COMPLETE - DO NOT IMPLEMENT THE FIX**\n\n\u26a0\ufe0f **CRITICAL BOUNDARY: This workflow is for INVESTIGATION ONLY.**\n\nYour job was to:\n- \u2705 Understand the bug\n- \u2705 Trace execution flow\n- \u2705 Form and test hypotheses\n- \u2705 Identify the root cause\n- \u2705 Validate your conclusion\n\nYour job is NOT to:\n- \u274c Write the fix\n- \u274c Modify any code\n- \u274c Create a PR\n- \u274c Implement the solution\n\n**HANDOFF DELIVERABLE:**\n\nCreate a final handoff document that someone else can use to implement the fix:\n\n**File: BUG_[VERSION]_handoff.md**\n\n```markdown\n# Bug Investigation Handoff\n\n## Executive Summary\n- **Bug**: [One sentence description]\n- **Root Cause**: [What's actually wrong]\n- **Confidence**: [High/Medium/Low based on validation]\n\n## Investigation Files\n- Investigation context: BUG_[VERSION]_investigation.md\n- Execution flow: BUG_[VERSION]_execution_flow.md\n- Hypotheses: BUG_[VERSION]_hypotheses.md\n- Validation: BUG_[VERSION]_validation.md\n\n## Root Cause Analysis\n[Detailed explanation of what's wrong and why]\n\n## Recommended Fix\n[High-level description of what needs to change]\n\n**Files to modify:**\n- [file:line] - [what needs to change]\n- [file:line] - [what needs to change]\n\n**Why this fixes it:**\n[Explain how the fix addresses the root cause]\n\n## Edge Cases & Risks\n[Things to watch out for when implementing]\n\n## Testing Recommendations\n[How to verify the fix works]\n\n## Next Steps\n1. Review this investigation\n2. Implement the recommended fix\n3. Test thoroughly\n4. Submit for code review\n```\n\n**OUTPUT**: BUG_[VERSION]_handoff.md with complete investigation summary\n\n**Before Finishing**: Have you clearly documented the root cause and recommended fix so someone else can implement it?",
-      "agentRole": "You are completing your investigation and handing off to an implementation team. Document everything clearly.",
-      "requireConfirmation": false,
-      "guidance": [
-        "BOUNDARY: Do NOT implement the fix yourself",
-        "HANDOFF: Create clear documentation for implementation team",
-        "COMPLETENESS: Include all investigation artifacts",
-        "CLARITY: Someone else should be able to implement from your handoff"
-      ]
-    }
-  ]
-}