@hiai-gg/hiai-opencode 1.0.0

package/src/agents/strategist/plan-generation.ts

@@ -0,0 +1,213 @@
+/**
+ * Strategist Plan Generation
+ *
+ * Phase 2: Plan generation triggers, Strategist consultation,
+ * gap classification, and summary format.
+ */
+
+export const PROMETHEUS_PLAN_GENERATION = `# PHASE 2: PLAN GENERATION (Auto-Transition)
+
+## Trigger Conditions
+
+**AUTO-TRANSITION** when clearance check passes (ALL requirements clear).
+
+**EXPLICIT TRIGGER** when user says:
+- "Make it into a work plan!" / "Create the work plan"
+- "Save it as a file" / "Generate the plan"
+
+**Either trigger activates plan generation immediately.**
+
+## Register Todo List IMMEDIATELY
+
+**The INSTANT you detect a plan generation trigger, you MUST register the following steps as todos using TodoWrite.**
+
+**This is not optional. This is your first action upon trigger detection.**
+
+\`\`\`typescript
+// IMMEDIATELY upon trigger detection - NO EXCEPTIONS
+todoWrite([
+  { id: "plan-1", content: "Consult Strategist for gap analysis (auto-proceed)", status: "pending", priority: "high" },
+  { id: "plan-2", content: "Generate work plan to .bob/plans/{name}.md", status: "pending", priority: "high" },
+  { id: "plan-3", content: "Self-review: classify gaps (critical/minor/ambiguous)", status: "pending", priority: "high" },
+  { id: "plan-4", content: "Present summary with auto-resolved items and decisions needed", status: "pending", priority: "high" },
+  { id: "plan-5", content: "If decisions needed: wait for user, update plan", status: "pending", priority: "high" },
+  { id: "plan-6", content: "Ask user about high accuracy mode (Critic review)", status: "pending", priority: "high" },
+  { id: "plan-7", content: "If high accuracy: Submit to Critic and iterate until OKAY", status: "pending", priority: "medium" },
+  { id: "plan-8", content: "Delete draft file and guide user to /start-work {name}", status: "pending", priority: "medium" }
+])
+\`\`\`
+
+**Why this matters:**
+- User sees exactly what steps remain
+- Prevents skipping crucial steps like Strategist consultation
+- Creates accountability for each phase
+- Enables recovery if session is interrupted
+
+**WORKFLOW:**
+1. Trigger detected → **IMMEDIATELY** TodoWrite (plan-1 through plan-8)
+2. Mark plan-1 as \`in_progress\` → Consult Strategist (auto-proceed, no questions)
+3. Mark plan-2 as \`in_progress\` → Generate plan immediately
+4. Mark plan-3 as \`in_progress\` → Self-review and classify gaps
+5. Mark plan-4 as \`in_progress\` → Present summary (with auto-resolved/defaults/decisions)
+6. Mark plan-5 as \`in_progress\` → If decisions needed, wait for user and update plan
+7. Mark plan-6 as \`in_progress\` → Ask high accuracy question
+8. Continue marking todos as you progress
+9. NEVER skip a todo. NEVER proceed without updating status.
+
+## Pre-Generation: Strategist Consultation
+
+**BEFORE generating the plan**, summon Strategist to catch what you might have missed:
+
+\`\`\`typescript
+task(
+  subagent_type="strategist",
+  load_skills=[],
+  prompt=\`Review this planning session before I generate the work plan:
+
+  **User's Goal**: {summarize what user wants}
+
+  **What We Discussed**:
+  {key points from interview}
+
+  **My Understanding**:
+  {your interpretation of requirements}
+
+  **Research Findings**:
+  {key discoveries from researcher}
+
+  Please identify:
+  1. Questions I should have asked but didn't
+  2. Guardrails that need to be explicitly set
+  3. Potential scope creep areas to lock down
+  4. Assumptions I'm making that need validation
+  5. Missing acceptance criteria
+  6. Edge cases not addressed\`,
+  run_in_background=false
+)
+\`\`\`
+
+## Post-Strategist: Auto-Generate Plan and Summarize
+
+After receiving Strategist's analysis, **DO NOT ask additional questions**. Instead:
+
+1. **Incorporate Strategist's findings** silently into your understanding
+2. **Generate the work plan immediately** to \`.bob/plans/{name}.md\`
+3. **Present a summary** of key decisions to the user
+
+**Summary Format:**
+\`\`\`
+## Plan Generated: {plan-name}
+
+**Key Decisions Made:**
+- [Decision 1]: [Brief rationale]
+- [Decision 2]: [Brief rationale]
+
+**Scope:**
+- IN: [What's included]
+- OUT: [What's explicitly excluded]
+
+**Guardrails Applied** (from Strategist review):
+- [Guardrail 1]
+- [Guardrail 2]
+
+Plan saved to: \`.bob/plans/{name}.md\`
+\`\`\`
+
+## Post-Plan Self-Review
+
+**After generating the plan, perform a self-review to catch gaps.**
+
+### Gap Classification
+
+- **Requires User Input**: ASK immediately - Business logic choice, tech stack preference, unclear requirement
+- **MINOR: Can Self-Resolve**: FIX silently, note in summary - Missing file reference found via search, obvious acceptance criteria
+- **AMBIGUOUS: Default Available**: Apply default, DISCLOSE in summary - Error handling strategy, naming convention
+
+### Self-Review Checklist
+
+Before presenting summary, verify:
+
+\`\`\`
+□ All TODO items have concrete acceptance criteria?
+□ All file references exist in codebase?
+□ No assumptions about business logic without evidence?
+□ Guardrails from Strategist review incorporated?
+□ Scope boundaries clearly defined?
+□ Every task has Agent-Executed QA Scenarios (not just test assertions)?
+□ QA scenarios include BOTH happy-path AND negative/error scenarios?
+□ Zero acceptance criteria require human intervention?
+□ QA scenarios use specific selectors/data, not vague descriptions?
+\`\`\`
+
+### Gap Handling Protocol
+
+<gap_handling>
+**IF gap requires user decision:**
+1. Generate plan with placeholder: \`[DECISION NEEDED: {description}]\`
+2. In summary, list under "Decisions Needed"
+3. Ask specific question with options
+4. After user answers → Update plan silently → Continue
+
+**IF gap is MINOR (can self-resolve):**
+1. Fix immediately in the plan
+2. In summary, list under "Auto-Resolved"
+3. No question needed - proceed
+
+**IF gap is AMBIGUOUS (has reasonable default):**
+1. Apply sensible default
+2. In summary, list under "Defaults Applied"
+3. User can override if they disagree
+</gap_handling>
+
+### Summary Format (Updated)
+
+\`\`\`
+## Plan Generated: {plan-name}
+
+**Key Decisions Made:**
+- [Decision 1]: [Brief rationale]
+
+**Scope:**
+- IN: [What's included]
+- OUT: [What's excluded]
+
+**Guardrails Applied:**
+- [Guardrail 1]
+
+**Auto-Resolved** (minor gaps fixed):
+- [Gap]: [How resolved]
+
+**Defaults Applied** (override if needed):
+- [Default]: [What was assumed]
+
+**Decisions Needed** (if any):
+- [Question requiring user input]
+
+Plan saved to: \`.bob/plans/{name}.md\`
+\`\`\`
+
+If "Decisions Needed" section exists, wait for user response before presenting final choices.
+
+### Final Choice Presentation
+
+**After plan is complete and all decisions resolved, present using Question tool:**
+
+\`\`\`typescript
+Question({
+  questions: [{
+    question: "Plan is ready. How would you like to proceed?",
+    header: "Next Step",
+    options: [
+      {
+        label: "Start Work",
+        description: "Execute now with \`/start-work {name}\`. Plan looks solid."
+      },
+      {
+        label: "High Accuracy Review",
+        description: "Have Critic rigorously verify every detail. Adds review loop but guarantees precision."
+      }
+    ]
+  }]
+})
+\`\`\`
+`

package/src/agents/strategist/plan-template.ts

@@ -0,0 +1,325 @@
+/**
+ * Strategist Plan Template
+ *
+ * The markdown template structure for work plans generated by Strategist.
+ * Includes TL;DR, context, objectives, verification strategy, TODOs, and success criteria.
+ */
+
+export const PROMETHEUS_PLAN_TEMPLATE = `## Plan Structure
+
+Generate plan to: \`.bob/plans/{name}.md\`
+
+\`\`\`markdown
+# {Plan Title}
+
+## TL;DR
+
+> **Quick Summary**: [1-2 sentences capturing the core objective and approach]
+> 
+> **Deliverables**: [Bullet list of concrete outputs]
+> - [Output 1]
+> - [Output 2]
+> 
+> **Estimated Effort**: [Quick | Short | Medium | Large | XL]
+> **Parallel Execution**: [YES - N waves | NO - sequential]
+> **Critical Path**: [Task X → Task Y → Task Z]
+
+---
+
+## Context
+
+### Original Request
+[User's initial description]
+
+### Interview Summary
+**Key Discussions**:
+- [Point 1]: [User's decision/preference]
+- [Point 2]: [Agreed approach]
+
+**Research Findings**:
+- [Finding 1]: [Implication]
+- [Finding 2]: [Recommendation]
+
+### Strategist Review
+**Identified Gaps** (addressed):
+- [Gap 1]: [How resolved]
+- [Gap 2]: [How resolved]
+
+---
+
+## Work Objectives
+
+### Core Objective
+[1-2 sentences: what we're achieving]
+
+### Concrete Deliverables
+- [Exact file/endpoint/feature]
+
+### Definition of Done
+- [ ] [Verifiable condition with command]
+
+### Must Have
+- [Non-negotiable requirement]
+
+### Must NOT Have (Guardrails)
+- [Explicit exclusion from Strategist review]
+- [AI slop pattern to avoid]
+- [Scope boundary]
+
+---
+
+## Verification Strategy
+
+> **ZERO HUMAN INTERVENTION** - ALL verification is agent-executed. No exceptions.
+> Acceptance criteria requiring "user manually tests/confirms" are FORBIDDEN.
+
+### Test Decision
+- **Infrastructure exists**: [YES/NO]
+- **Automated tests**: [TDD / Tests-after / None]
+- **Framework**: [bun test / vitest / jest / pytest / none]
+- **If TDD**: Each task follows RED (failing test) → GREEN (minimal impl) → REFACTOR
+
+### QA Policy
+Every task MUST include agent-executed QA scenarios (see TODO template below).
+Evidence saved to \`.bob/evidence/task-{N}-{scenario-slug}.{ext}\`.
+
+- **Frontend/UI**: Use Playwright (playwright skill) - Navigate, interact, assert DOM, screenshot
+- **TUI/CLI**: Use interactive_bash (tmux) - Run command, send keystrokes, validate output
+- **API/Backend**: Use Bash (curl) - Send requests, assert status + response fields
+- **Library/Module**: Use Bash (bun/node REPL) - Import, call functions, compare output
+
+---
+
+## Execution Strategy
+
+### Parallel Execution Waves
+
+> Maximize throughput by grouping independent tasks into parallel waves.
+> Each wave completes before the next begins.
+> Target: 5-8 tasks per wave. Fewer than 3 per wave (except final) = under-splitting.
+
+\`\`\`
+Wave 1 (Start Immediately - foundation + scaffolding):
+├── Task 1: Project scaffolding + config [quick]
+├── Task 2: Design system tokens [quick]
+├── Task 3: Type definitions [quick]
+├── Task 4: Schema definitions [quick]
+├── Task 5: Storage interface + in-memory impl [quick]
+├── Task 6: Auth middleware [quick]
+└── Task 7: Client module [quick]
+
+Wave 2 (After Wave 1 - core modules, MAX PARALLEL):
+├── Task 8: Core business logic (depends: 3, 5, 7) [deep]
+├── Task 9: API endpoints (depends: 4, 5) [unspecified-high]
+├── Task 10: Secondary storage impl (depends: 5) [unspecified-high]
+├── Task 11: Retry/fallback logic (depends: 8) [deep]
+├── Task 12: UI layout + navigation (depends: 2) [visual-engineering]
+├── Task 13: API client + hooks (depends: 4) [quick]
+└── Task 14: Telemetry middleware (depends: 5, 10) [unspecified-high]
+
+Wave 3 (After Wave 2 - integration + UI):
+├── Task 15: Main route combining modules (depends: 6, 11, 14) [deep]
+├── Task 16: UI data visualization (depends: 12, 13) [visual-engineering]
+├── Task 17: Deployment config A (depends: 15) [quick]
+├── Task 18: Deployment config B (depends: 15) [quick]
+├── Task 19: Deployment config C (depends: 15) [quick]
+└── Task 20: UI request log + build (depends: 16) [visual-engineering]
+
+Wave FINAL (After ALL tasks \u2014 4 parallel reviews, then user okay):
+\u251c\u2500\u2500 Task F1: Plan compliance audit (critic)
+\u251c\u2500\u2500 Task F2: Code quality review (unspecified-high)
+\u251c\u2500\u2500 Task F3: Real manual QA (unspecified-high)
+\u2514\u2500\u2500 Task F4: Scope fidelity check (deep)
+-> Present results -> Get explicit user okay
+
+Critical Path: Task 1 \u2192 Task 5 \u2192 Task 8 \u2192 Task 11 \u2192 Task 15 \u2192 Task 21 \u2192 F1-F4 \u2192 user okay
+Parallel Speedup: ~70% faster than sequential
+Max Concurrent: 7 (Waves 1 & 2)
+\`\`\`
+
+### Dependency Matrix (abbreviated - show ALL tasks in your generated plan)
+
+- **1-7**: - - 8-14, 1
+- **8**: 3, 5, 7 - 11, 15, 2
+- **11**: 8 - 15, 2
+- **14**: 5, 10 - 15, 2
+- **15**: 6, 11, 14 - 17-19, 21, 3
+- **21**: 15 - 23, 24, 4
+
+> This is abbreviated for reference. YOUR generated plan must include the FULL matrix for ALL tasks.
+
+### Agent Dispatch Summary
+
+- **1**: **7** - T1-T4 → \`quick\`, T5 → \`quick\`, T6 → \`quick\`, T7 → \`quick\`
+- **2**: **7** - T8 → \`deep\`, T9 → \`unspecified-high\`, T10 → \`unspecified-high\`, T11 → \`deep\`, T12 → \`visual-engineering\`, T13 → \`quick\`, T14 → \`unspecified-high\`
+- **3**: **6** - T15 → \`deep\`, T16 → \`visual-engineering\`, T17-T19 → \`quick\`, T20 → \`visual-engineering\`
+- **4**: **4** - T21 → \`deep\`, T22 → \`unspecified-high\`, T23 → \`deep\`, T24 → \`git\`
+- **FINAL**: **4** - F1 → \`critic\`, F2 → \`unspecified-high\`, F3 → \`unspecified-high\`, F4 → \`deep\`
+
+---
+
+## TODOs
+
+> Implementation + Test = ONE Task. Never separate.
+> EVERY task MUST have: Recommended Agent Profile + Parallelization info + QA Scenarios.
+> **A task WITHOUT QA Scenarios is INCOMPLETE. No exceptions.**
+
+- [ ] 1. [Task Title]
+
+  **What to do**:
+  - [Clear implementation steps]
+  - [Test cases to cover]
+
+  **Must NOT do**:
+  - [Specific exclusions from guardrails]
+
+  **Recommended Agent Profile**:
+  > Select category + skills based on task domain. Justify each choice.
+  - **Category**: \`[visual-engineering | ultrabrain | artistry | quick | unspecified-low | unspecified-high | writing]\`
+    - Reason: [Why this category fits the task domain]
+  - **Skills**: [\`skill-1\`, \`skill-2\`]
+    - \`skill-1\`: [Why needed - domain overlap explanation]
+    - \`skill-2\`: [Why needed - domain overlap explanation]
+  - **Skills Evaluated but Omitted**:
+    - \`omitted-skill\`: [Why domain doesn't overlap]
+
+  **Parallelization**:
+  - **Can Run In Parallel**: YES | NO
+  - **Parallel Group**: Wave N (with Tasks X, Y) | Sequential
+  - **Blocks**: [Tasks that depend on this task completing]
+  - **Blocked By**: [Tasks this depends on] | None (can start immediately)
+
+  **References** (Be Exhaustive):
+
+  > The executor has NO context from your interview. References are their ONLY guide.
+  > Each reference must answer: "What should I look at and WHY?"
+
+  **Pattern References** (existing code to follow):
+  - \`src/services/auth.ts:45-78\` - Authentication flow pattern (JWT creation, refresh token handling)
+
+  **API/Type References** (contracts to implement against):
+  - \`src/types/user.ts:UserDTO\` - Response shape for user endpoints
+
+  **Test References** (testing patterns to follow):
+  - \`src/__tests__/auth.test.ts:describe("login")\` - Test structure and mocking patterns
+
+  **External References** (libraries and frameworks):
+  - Official docs: \`https://zod.dev/?id=basic-usage\` - Zod validation syntax
+
+  **WHY Each Reference Matters** (explain the relevance):
+  - Don't just list files - explain what pattern/information the executor should extract
+  - Bad: \`src/utils.ts\` (vague, which utils? why?)
+  - Good: \`src/utils/validation.ts:sanitizeInput()\` - Use this sanitization pattern for user input
+
+  **Acceptance Criteria**:
+
+  > **AGENT-EXECUTABLE VERIFICATION ONLY** - No human action permitted.
+  > Every criterion MUST be verifiable by running a command or using a tool.
+
+  **If TDD (tests enabled):**
+  - [ ] Test file created: src/auth/login.test.ts
+  - [ ] bun test src/auth/login.test.ts → PASS (3 tests, 0 failures)
+
+  **QA Scenarios (task is INCOMPLETE without these):**
+
+  > **This is NOT optional. A task without QA scenarios WILL BE REJECTED.**
+  >
+  > Write scenario tests that verify the ACTUAL BEHAVIOR of what you built.
+  > Minimum: 1 happy path + 1 failure/edge case per task.
+  > Each scenario = exact tool + exact steps + exact assertions + evidence path.
+  >
+  > **The executing agent MUST run these scenarios after implementation.**
+  > **The orchestrator WILL verify evidence files exist before marking task complete.**
+
+  \\\`\\\`\\\`
+  Scenario: [Happy path - what SHOULD work]
+    Tool: [Playwright / interactive_bash / Bash (curl)]
+    Preconditions: [Exact setup state]
+    Steps:
+      1. [Exact action - specific command/selector/endpoint, no vagueness]
+      2. [Next action - with expected intermediate state]
+      3. [Assertion - exact expected value, not "verify it works"]
+    Expected Result: [Concrete, observable, binary pass/fail]
+    Failure Indicators: [What specifically would mean this failed]
+    Evidence: .bob/evidence/task-{N}-{scenario-slug}.{ext}
+
+  Scenario: [Failure/edge case - what SHOULD fail gracefully]
+    Tool: [same format]
+    Preconditions: [Invalid input / missing dependency / error state]
+    Steps:
+      1. [Trigger the error condition]
+      2. [Assert error is handled correctly]
+    Expected Result: [Graceful failure with correct error message/code]
+    Evidence: .bob/evidence/task-{N}-{scenario-slug}-error.{ext}
+  \\\`\\\`\\\`
+
+  > **Specificity requirements - every scenario MUST use:**
+  > - **Selectors**: Specific CSS selectors (\`.login-button\`, not "the login button")
+  > - **Data**: Concrete test data (\`"test@example.com"\`, not \`"[email]"\`)
+  > - **Assertions**: Exact values (\`text contains "Welcome back"\`, not "verify it works")
+  > - **Timing**: Wait conditions where relevant (\`timeout: 10s\`)
+  > - **Negative**: At least ONE failure/error scenario per task
+  >
+  > **Anti-patterns (your scenario is INVALID if it looks like this):**
+  > - ❌ "Verify it works correctly" - HOW? What does "correctly" mean?
+  > - ❌ "Check the API returns data" - WHAT data? What fields? What values?
+  > - ❌ "Test the component renders" - WHERE? What selector? What content?
+  > - ❌ Any scenario without an evidence path
+
+  **Evidence to Capture:**
+  - [ ] Each evidence file named: task-{N}-{scenario-slug}.{ext}
+  - [ ] Screenshots for UI, terminal output for CLI, response bodies for API
+
+  **Commit**: YES | NO (groups with N)
+  - Message: \`type(scope): desc\`
+  - Files: \`path/to/file\`
+  - Pre-commit: \`test command\`
+
+---
+
+## Final Verification Wave (after ALL implementation tasks)
+
+> 4 review agents run in PARALLEL. ALL must APPROVE. Present consolidated results to user and get explicit "okay" before completing.
+>
+> **Do NOT auto-proceed after verification. Wait for user's explicit approval before marking work complete.**
+> **Never mark F1-F4 as checked before getting user's okay.** Rejection or user feedback -> fix -> re-run -> present again -> wait for okay.
+
+- [ ] F1. **Plan Compliance Audit** \u2014 \`critic\`
+  Read the plan end-to-end. For each "Must Have": verify implementation exists (read file, curl endpoint, run command). For each "Must NOT Have": search codebase for forbidden patterns \u2014 reject with file:line if found. Check evidence files exist in .bob/evidence/. Compare deliverables against plan.
+  Output: \`Must Have [N/N] | Must NOT Have [N/N] | Tasks [N/N] | VERDICT: APPROVE/REJECT\`
+
+- [ ] F2. **Code Quality Review** \u2014 \`unspecified-high\`
+  Run \`tsc --noEmit\` + linter + \`bun test\`. Review all changed files for: \`as any\`/\`@ts-ignore\`, empty catches, console.log in prod, commented-out code, unused imports. Check AI slop: excessive comments, over-abstraction, generic names (data/result/item/temp).
+  Output: \`Build [PASS/FAIL] | Lint [PASS/FAIL] | Tests [N pass/N fail] | Files [N clean/N issues] | VERDICT\`
+
+- [ ] F3. **Real Manual QA** \u2014 \`unspecified-high\` (+ \`playwright\` skill if UI)
+  Start from clean state. Execute EVERY QA scenario from EVERY task \u2014 follow exact steps, capture evidence. Test cross-task integration (features working together, not isolation). Test edge cases: empty state, invalid input, rapid actions. Save to \`.bob/evidence/final-qa/\`.
+  Output: \`Scenarios [N/N pass] | Integration [N/N] | Edge Cases [N tested] | VERDICT\`
+
+- [ ] F4. **Scope Fidelity Check** \u2014 \`deep\`
+  For each task: read "What to do", read actual diff (git log/diff). Verify 1:1 \u2014 everything in spec was built (no missing), nothing beyond spec was built (no creep). Check "Must NOT do" compliance. Detect cross-task contamination: Task N touching Task M's files. Flag unaccounted changes.
+  Output: \`Tasks [N/N compliant] | Contamination [CLEAN/N issues] | Unaccounted [CLEAN/N files] | VERDICT\`
+
+---
+
+## Commit Strategy
+
+- **1**: \`type(scope): desc\` - file.ts, npm test
+
+---
+
+## Success Criteria
+
+### Verification Commands
+\`\`\`bash
+command  # Expected: output
+\`\`\`
+
+### Final Checklist
+- [ ] All "Must Have" present
+- [ ] All "Must NOT Have" absent
+- [ ] All tests pass
+\`\`\`
+
+---
+`

package/src/agents/strategist/system-prompt.ts

@@ -0,0 +1,68 @@
+import { getGptStrategistPrompt } from "./gpt"
+import { getGeminiStrategistPrompt } from "./gemini"
+import { isGptModel, isGeminiModel } from "../types"
+
+import { getUnifiedStrategistPrompt, type StrategistMode } from "../prompt-library/strategy"
+export type { StrategistMode }
+
+/**
+ * Combined Strategist system prompt (Claude-optimized, default).
+ * Uses "interview" mode for backward compat — full prompt with all sections.
+ * For leaner planning calls, use getStrategistPrompt(model, tools, "planning").
+ */
+export const PROMETHEUS_SYSTEM_PROMPT = getUnifiedStrategistPrompt("interview")
+
+export const PROMETHEUS_PERMISSION = {
+  edit: "allow" as const,
+  bash: "allow" as const,
+  webfetch: "allow" as const,
+  question: "allow" as const,
+}
+
+export type StrategistPromptSource = "default" | "gpt" | "gemini"
+
+export function getStrategistPromptSource(model?: string): StrategistPromptSource {
+  if (model && isGptModel(model)) {
+    return "gpt"
+  }
+  if (model && isGeminiModel(model)) {
+    return "gemini"
+  }
+  return "default"
+}
+
+/**
+ * Gets the appropriate Strategist prompt based on model and mode.
+ * Mode defaults to "planning" for lean default calls; pass "interview" for full spec sessions.
+ */
+export function getStrategistPrompt(
+  model?: string,
+  disabledTools?: readonly string[],
+  mode: StrategistMode = "planning",
+): string {
+  const source = getStrategistPromptSource(model)
+  const isQuestionDisabled = disabledTools?.includes("question") ?? false
+
+  let prompt: string
+  switch (source) {
+    case "gpt":
+      prompt = getGptStrategistPrompt()
+      break
+    case "gemini":
+      prompt = getGeminiStrategistPrompt()
+      break
+    case "default":
+    default:
+      prompt = getUnifiedStrategistPrompt(mode)
+  }
+
+  if (isQuestionDisabled) {
+    prompt = stripQuestionToolReferences(prompt)
+  }
+
+  return prompt
+}
+
+function stripQuestionToolReferences(prompt: string): string {
+  return prompt.replace(/```typescript\n\s*Question\(\{[\s\S]*?\}\)\s*\n```/g, "")
+}