aiblueprint-cli 1.4.99 → 1.4.100

package/agents-config/skills/apex/steps/step-06-resolve.md

@@ -1,239 +1,37 @@
 ---
 name: step-06-resolve
-description: Resolve findings - interactively address review issues
-prev_step: steps/step-05-examine.md
-next_step: COMPLETE
+description: Resolve confirmed APEX findings, preserve finding provenance, and re-run invalidated validation and proof.
+next_step: step-04-validate.md
 ---
 
-# Step 6: Resolve Findings
+# Step 6: Resolve findings
 
-## MANDATORY EXECUTION RULES (READ FIRST):
+Resolve confirmed findings in severity and dependency order.
 
-- 🛑 NEVER auto-fix Noise or Uncertain findings
-- 🛑 NEVER skip validation after fixes
-- ✅ ALWAYS present resolution options to user (unless auto_mode)
-- ✅ ALWAYS validate after applying fixes
-- ✅ ALWAYS provide clear completion summary
-- 📋 YOU ARE A RESOLVER, addressing identified issues
-- 💬 FOCUS on "How do we fix these issues?"
-- 🚫 FORBIDDEN to proceed with failing validation
+## 1. Select disposition
 
-## EXECUTION PROTOCOLS:
+- Fix confirmed in-scope findings.
+- Leave noise unchanged and record why.
+- Do not silently absorb pre-existing or out-of-scope issues.
+- Investigate high-impact uncertain findings until they become confirmed, rejected, or concretely blocked.
+- Ask before accepting an unresolved critical/high risk when that choice belongs to the user.
 
-- 🎯 Present resolution options first
-- 💾 Log each fix applied (if save_mode)
-- 📖 Validate after all fixes
-- 🚫 FORBIDDEN to skip post-fix validation
+## 2. Update the graph
 
-## CONTEXT BOUNDARIES:
+Create or revise task nodes for fixes. Record which acceptance criteria, validation entries, reviewer dispositions, and proof artifacts become stale.
 
-- Findings from step-05 are classified
-- Some are Real, some Noise, some Uncertain
-- User may want different resolution strategies
-- Must validate after any changes
-- **If `{teams_mode}` = true:** Agent team is still alive. Do NOT shutdown teammates - that happens in step-09-finish only.
+## 3. Apply fixes
 
-## YOUR TASK:
+Use the standard execution protocol: bounded edit, immediate diff inspection, shortest feedback loop, and scope check. A reviewer does not become the sole judge of its own remediation.
 
-Address adversarial review findings interactively - fix real issues, dismiss noise, discuss uncertain items.
+## 4. Re-validate
 
----
-
-<available_state>
-From previous steps:
-
-| Variable | Description |
-|----------|-------------|
-| `{task_description}` | What was implemented |
-| `{task_id}` | Kebab-case identifier |
-| `{auto_mode}` | Auto-fix Real findings |
-| `{save_mode}` | Save outputs to files |
-| `{output_dir}` | Path to output (if save_mode) |
-| Findings table | IDs, severity, validity |
-| Finding todos | For tracking |
-</available_state>
-
----
-
-## EXECUTION SEQUENCE:
-
-### 1. Initialize Save Output (if save_mode)
-
-**If `{save_mode}` = true:**
-
-```bash
-bash {skill_dir}/scripts/update-progress.sh "{task_id}" "06" "resolve" "in_progress"
-```
-
-Append logs to `{output_dir}/06-resolve.md` as you work.
-
-### 2. Present Resolution Options
-
-**If `{auto_mode}` = true:**
-→ Auto-fix all "Real" findings, skip Noise/Uncertain
-
-**If `{auto_mode}` = false:**
+Return to `step-04-validate.md` for every affected command and then re-run the relevant independent review lens. If runtime proof artifacts were invalidated, recapture them through `step-10-verify.md`.
 
-```yaml
-questions:
-  - header: "Resolution"
-    question: "How would you like to handle these findings?"
-    options:
-      - label: "Auto-fix Real issues (Recommended)"
-        description: "Fix 'Real' findings, skip noise/uncertain"
-      - label: "Walk through each finding"
-        description: "Decide on each finding individually"
-      - label: "Fix only critical"
-        description: "Only fix CRITICAL/BLOCKING issues"
-      - label: "Skip all"
-        description: "Acknowledge but don't change"
-    multiSelect: false
-```
-
-### 3. Apply Fixes Based on Choice
-
-**Auto-fix Real:**
-1. Filter to Real findings only
-2. For each: Read file → Apply fix → Verify
-3. Log each fix
-
-**Walk through each:**
-For each finding in severity order:
-
-```yaml
-questions:
-  - header: "F1"
-    question: "How should we handle this finding?"
-    options:
-      - label: "Fix now (Recommended)"
-        description: "Apply the suggested fix"
-      - label: "Skip"
-        description: "Acknowledge but don't fix"
-      - label: "Discuss"
-        description: "Need more context"
-      - label: "Mark as noise"
-        description: "Not a real issue"
-    multiSelect: false
-```
-
-**Fix only critical:**
-1. Filter to CRITICAL/BLOCKING only
-2. Auto-fix those, skip others
-
-**Skip all:**
-1. Acknowledge findings
-2. If Critical/High exist, confirm:
-
-```yaml
-questions:
-  - header: "Confirm"
-    question: "You have unresolved Critical/High findings. Proceed anyway?"
-    options:
-      - label: "Go back and fix"
-        description: "Return to resolution options"
-      - label: "Proceed anyway"
-        description: "Accept risks, continue"
-      - label: "Fix only critical"
-        description: "Just fix critical issues"
-    multiSelect: false
-```
-
-### 4. Post-Resolution Validation
-
-After any fixes:
+Record fixed, rejected, deferred, and blocked finding IDs with evidence.
 
 ```bash
-pnpm run typecheck && pnpm run lint
-```
-
-Both MUST pass.
-
-### 5. Resolution Summary
-
-```
-**Resolution Complete**
-
-**Fixed:** {count}
-- F1: Parameterized SQL query in auth.ts:42
-- F2: Added null check in handler.ts:78
-
-**Skipped:** {count}
-- F3: Complex function (uncertain)
-
-**Validation:** ✓ Passed
-```
-
-### 6. Complete Save Output (if save_mode)
-
-**If `{save_mode}` = true:**
-
-Append to `{output_dir}/06-resolve.md`:
-```markdown
----
-## Step Complete
-**Status:** ✓ Complete
-**Findings fixed:** {count}
-**Findings skipped:** {count}
-**Validation:** ✓ Passed
-**Timestamp:** {ISO timestamp}
-```
-
-### 7. Completion Summary
-
-```
-**APEX Workflow Complete**
-
-**Task:** {task_description}
-
-**Implementation:**
-- Files modified: {count}
-- All checks passing: ✓
-
-**Review:**
-- Findings identified: {total}
-- Findings resolved: {fixed}
-- Findings skipped: {skipped}
-
-**Next Steps:**
-- [ ] Commit changes
-- [ ] Run full test suite
-- [ ] Deploy when ready
+python3 "{skill_dir}/scripts/apex-state.py" event --root "$PWD" --run-id "{run_id}" --phase resolve --status complete --message "Confirmed findings resolved or explicitly dispositioned"
 ```
 
----
-
-## SUCCESS METRICS:
-
-✅ User chose resolution approach
-✅ All chosen fixes applied correctly
-✅ Validation passes after fixes
-✅ Clear summary of resolved/skipped
-✅ User understands next steps
-
-## FAILURE MODES:
-
-❌ Auto-fixing Noise or Uncertain findings
-❌ Not validating after fixes
-❌ No clear completion summary
-❌ Proceeding with failing validation
-❌ **CRITICAL**: Not using AskUserQuestion for decisions
-
-## RESOLUTION PROTOCOLS:
-
-- Only auto-fix Real findings
-- Validate after EVERY fix round
-- Clear summary at the end
-- User controls final decision
-
----
-
-## NEXT STEP:
-
-Based on flags:
-- **If verify_mode:** Load `./step-10-verify.md` to verify feature
-- **If pr_mode:** Load `./step-09-finish.md` to create pull request
-- **Otherwise:** Workflow complete - show summary
-
-<critical>
-Remember: Always validate after fixes - never proceed with failing checks!
-</critical>
+Completion requires no unresolved confirmed blocker and current validation after the latest fix.

package/agents-config/skills/apex/steps/step-07-tests.md

@@ -1,250 +1,35 @@
 ---
 name: step-07-tests
-description: Smart test analysis and creation - analyze patterns, create appropriate tests
-prev_step: steps/step-04-validate.md
-next_step: steps/step-08-run-tests.md
+description: Add focused tests where the APEX risk and acceptance map identifies a material coverage gap.
+next_step: step-08-run-tests.md
 ---
 
-# Step 7: Tests (Analysis & Creation)
+# Step 7: Test authoring
 
-## MANDATORY EXECUTION RULES (READ FIRST):
+Tests are selected by risk and observable contracts, not by a requirement to create a file for every change.
 
-- 🛑 NEVER create tests without analyzing existing patterns first
-- 🛑 NEVER use wrong test type (unit when integration needed)
-- ✅ ALWAYS analyze test infrastructure BEFORE writing
-- ✅ ALWAYS follow existing test conventions exactly
-- ✅ ALWAYS map tests to acceptance criteria
-- 📋 YOU ARE A TEST ENGINEER, not a code generator
-- 💬 FOCUS on "What tests does this ACTUALLY need?"
-- 🚫 FORBIDDEN to ignore project test conventions
+## 1. Inspect test infrastructure
 
-## EXECUTION PROTOCOLS:
+Find the existing runner, conventions, fixtures, isolation rules, service dependencies, and nearby examples. Reuse project patterns.
 
-- 🎯 Analyze test infrastructure first
-- 💾 Document test strategy (if save_mode)
-- 📖 Read similar tests before writing
-- 🚫 FORBIDDEN to write tests without reading examples
+## 2. Map coverage gaps
 
-## CONTEXT BOUNDARIES:
+Prioritize behavior the implementation could plausibly get wrong:
 
-- Implementation is complete and validated
-- Test infrastructure exists (discovered in this step)
-- Existing tests show conventions to follow
-- Focus on creating RIGHT tests, not just tests
+- acceptance-criterion happy path;
+- boundary and failure behavior;
+- regression that motivated the task;
+- auth, tenancy, idempotency, concurrency, and persistence where relevant;
+- compatibility with unchanged behavior.
 
-## YOUR TASK:
+Avoid snapshot or mock-heavy tests that merely restate implementation details.
 
-Analyze existing test patterns and create appropriate tests for the implementation.
+## 3. Write the smallest durable suite
 
----
-
-<available_state>
-From previous steps:
-
-| Variable | Description |
-|----------|-------------|
-| `{task_description}` | What was implemented |
-| `{task_id}` | Kebab-case identifier |
-| `{auto_mode}` | Skip confirmations |
-| `{save_mode}` | Save outputs to files |
-| `{economy_mode}` | Lighter test analysis |
-| `{output_dir}` | Path to output (if save_mode) |
-| Files modified | From implementation |
-| Acceptance criteria | From step-01 |
-</available_state>
-
----
-
-## EXECUTION SEQUENCE:
-
-### 1. Initialize Save Output (if save_mode)
-
-**If `{save_mode}` = true:**
-
-```bash
-bash {skill_dir}/scripts/update-progress.sh "{task_id}" "07" "tests" "in_progress"
-```
-
-Append analysis to `{output_dir}/07-tests.md` as you work.
-
-### 2. Analyze Test Infrastructure
-
-**2.1 Discover Framework**
-```bash
-cat package.json | grep -E "(jest|vitest|mocha|playwright|testing-library)"
-```
-
-**2.2 Find Config**
-```bash
-ls -la | grep -E "(jest|vitest|playwright)"
-```
-
-**2.3 Find Test Commands**
-```bash
-cat package.json | grep -A 5 '"scripts"' | grep -E "(test|spec)"
-```
-
-### 3. Analyze Existing Test Patterns
-
-**If `{economy_mode}` = true:**
-→ Read 1 similar test file for patterns
-
-**If `{economy_mode}` = false:**
-→ Read 2-3 similar test files
-
-**Pattern Checklist:**
-- [ ] describe/it vs test() syntax
-- [ ] Setup/teardown patterns
-- [ ] Mocking approach
-- [ ] Assertion style
-- [ ] Test data approach
-
-### 4. Determine Test Strategy
-
-| Implementation Type | Test Type |
-|--------------------|-----------|
-| API Route | Integration with supertest/fetch |
-| Service/Logic | Integration with real deps |
-| Utility Function | Unit with mocks |
-| React Component | Component with testing-library |
-| Full Feature | Integration + E2E |
-
-### 5. Create Test Plan
-
-```markdown
-## Test Plan
-
-**Framework:** {jest/vitest}
-**Command:** `pnpm test`
-
-### Tests to Create
-
-**Integration:** `src/auth/register.test.ts`
-- creates user with valid data (happy path)
-- rejects invalid email (error case)
-- handles auth failure (error case)
-
-**Unit:** `src/utils/validation.test.ts`
-- validates correct email
-- rejects malformed email
-```
-
-**If `{auto_mode}` = false:**
-
-```yaml
-questions:
-  - header: "Tests"
-    question: "Review the test plan. Ready to create tests?"
-    options:
-      - label: "Create tests (Recommended)"
-        description: "Proceed with planned tests"
-      - label: "Add more tests"
-        description: "I want additional test cases"
-      - label: "Modify approach"
-        description: "Change the strategy"
-      - label: "Skip tests"
-        description: "Don't create tests"
-    multiSelect: false
-```
-
-### 6. Create Tests
-
-**CRITICAL: Follow existing patterns EXACTLY**
-
-1. Read similar test for reference
-2. Create test file matching structure
-3. Write tests following conventions
-
-```typescript
-import { describe, it, expect, beforeEach } from 'vitest'
-
-describe('POST /api/auth/register', () => {
-  beforeEach(async () => {
-    await db.user.deleteMany()
-  })
-
-  it('creates user with valid data', async () => {
-    const response = await client.post('/api/auth/register', {
-      email: 'test@example.com',
-      password: 'SecurePass123!'
-    })
-
-    expect(response.status).toBe(201)
-  })
-
-  it('rejects invalid email', async () => {
-    const response = await client.post('/api/auth/register', {
-      email: 'invalid',
-      password: 'SecurePass123!'
-    })
-
-    expect(response.status).toBe(400)
-  })
-})
-```
-
-### 7. Verify Tests
-
-```bash
-pnpm run typecheck
-```
-
-List created tests:
-```
-**Tests Created:**
-- `src/auth/register.test.ts` (3 tests)
-- `src/utils/validation.test.ts` (2 tests)
-```
-
-### 8. Complete Save Output (if save_mode)
-
-**If `{save_mode}` = true:**
-
-Append to `{output_dir}/07-tests.md`:
-```markdown
----
-## Step Complete
-**Status:** ✓ Complete
-**Tests created:** {count}
-**Test files:** {list}
-**Next:** step-08-run-tests.md
-**Timestamp:** {ISO timestamp}
-```
-
----
-
-## SUCCESS METRICS:
-
-✅ Test infrastructure analyzed
-✅ Existing patterns studied
-✅ Appropriate test types chosen
-✅ Tests follow codebase conventions
-✅ Tests pass syntax check
-✅ All AC have corresponding tests
-
-## FAILURE MODES:
-
-❌ Writing tests without analyzing patterns
-❌ Wrong test type for implementation
-❌ Ignoring project conventions
-❌ Tests don't match acceptance criteria
-❌ Over-testing (testing implementation, not behavior)
-❌ **CRITICAL**: Not using AskUserQuestion for approval
-
-## TEST PROTOCOLS:
-
-- Analyze BEFORE writing
-- Follow existing patterns EXACTLY
-- Test behavior, not implementation
-- Map to acceptance criteria
-- Create minimal, focused tests
-
----
+Keep fixtures controlled and cleanup explicit. Do not make production calls or mutate shared external state unless that exact action is authorized and the test surface is designed for it.
 
-## NEXT STEP:
+## 4. Inspect and record
 
-After tests created, load `./step-08-run-tests.md`
+Review the test diff and map each test to an acceptance criterion or risk. Record why any material path remains untested.
 
-<critical>
-Remember: Create the RIGHT tests - analyze patterns first, then write!
-</critical>
+Proceed to `step-08-run-tests.md`.