siesa-agents 2.1.78 → 2.1.80

package/siesa-agents/bmm/workflows/4-implementation/code-review/steps/step-02-build-plan.md

@@ -0,0 +1,89 @@
+---
+name: 'step-02-build-plan'
+description: 'Build a rigorous review attack plan based on requirements'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/code-review'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-02-build-plan.md'
+nextStepFile: '{workflow_path}/steps/step-03-review.md'
+workflowFile: '{workflow_path}/workflow.md'
+outputFile: '{output_folder}/review-{story_key}.md'
+---
+
+# Step 2: Build Review Attack Plan
+
+## STEP GOAL:
+To create a structured "attack plan" for the review, identifying exactly what needs to be verified based on the story's Acceptance Criteria and Tasks.
+
+## MANDATORY EXECUTION RULES:
+- 📋 YOU ARE AN ADVERSARIAL REVIEWER
+- 🎯 Don't trust; verify.
+- 📖 Read entire file before executing
+
+## Sequence of Instructions
+
+### 1. Extract Requirements
+
+From the loaded story file:
+1. Extract **ALL Acceptance Criteria (ACs)**
+2. Extract **ALL Tasks and Subtasks** that are marked as completed `[x]`
+3. Extract the **claimed implementation files**
+
+### 2. Identify Context Documents
+
+Based on the `input_file_patterns` strategy:
+1. Detect referenced Epic files (Selective Load)
+2. Detect Architecture documents (Full Load)
+3. Detect UX Design documents (if applicable)
+
+*Note: Do not read them yet, just identify which ones are relevant for the review.*
+
+### 3. Construct Review Matrix
+
+Create a plan to verify each item:
+
+1. **AC Validation Plan**:
+   - For each AC, define what defines "success".
+   - Identify which files likely contain the logic.
+
+2. **Task Audit Plan**:
+   - For each completed Task, define verifying evidence.
+   - Flag any tasks that seem subjective.
+
+3. **Code Quality Criteria**:
+   - Security (Injection, Auth, Input Validation)
+   - Performance (Loops, Queries, Caching)
+   - Maintainability (Naming, Structure, Comments)
+   - Tests (Real assertions vs placeholders, Coverage)
+
+### 4. Document Plan
+
+Append to `{outputFile}`:
+
+```markdown
+## Review Plan
+
+### Items to Verify
+- [ ] AC1: ...
+- [ ] AC2: ...
+- [ ] Task: ...
+
+### Focus Areas
+- Security checks on: [List files]
+- Performance checks on: [List files]
+```
+
+### 5. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+- IF C: Save plan to {outputFile}, update frontmatter `stepsCompleted: [1, 2]`, then load/execute {nextStepFile}
+- IF A/P: Execute respective flows
+- IF Others: Handle queries then loop
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input
+- ONLY proceed to next step when user selects 'C'

package/siesa-agents/bmm/workflows/4-implementation/code-review/steps/step-03-review.md

@@ -0,0 +1,91 @@
+---
+name: 'step-03-review'
+description: 'Execute the adversarial code review and find specific issues'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/code-review'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-03-review.md'
+nextStepFile: '{workflow_path}/steps/step-04-fix.md'
+workflowFile: '{workflow_path}/workflow.md'
+outputFile: '{output_folder}/review-{story_key}.md'
+---
+
+# Step 3: Execute Adversarial Review
+
+## STEP GOAL:
+To execute the review plan, rigorously verifying every claim against the actual code, and finding at least 3-10 specific, actionable issues.
+
+## MANDATORY EXECUTION RULES:
+- 📋 VALIDATE EVERY CLAIM - Check git reality vs story claims
+- 🛑 NOT LOOKING HARD ENOUGH? Find more problems!
+- 🔍 Find minimum 3 specific issues
+
+## Sequence of Instructions
+
+### 1. Git vs Story Logic Check
+
+1. Analyze discrepancies found in Step 1.
+2. **Files in Git but not in Story**: Mark as MEDIUM finding (Incomplete documentation).
+3. **Files in Story but not in Git**: Mark as HIGH finding (False claims).
+4. **Uncommitted changes**: Mark as MEDIUM finding (Transparency).
+
+### 2. Comprehensive File Analysis
+
+Create a **Comprehensive File List** (Story List + Git Items).
+For EACH file in the list:
+1. **Read the file content**.
+2. **Code Quality Scan**:
+   - **Security**: SQLi, XSS, insecure deps, missing auth.
+   - **Performance**: N+1 queries, loops, memory usage.
+   - **Error Handling**: Empty catches, generic errors.
+   - **Maintainability**: Magic numbers, bad naming, monolithic functions.
+   - **Test Quality**: "Expect true to be true" patterns (Red Flag).
+
+### 3. AC & Task Verification
+
+1. **AC Validation**:
+   - Read specific lines implementing the AC.
+   - If missing/partial -> HIGH SEVERITY.
+2. **Task Completion Audit**:
+   - For items marked `[x]`, verify the code exists.
+   - If marked done but code missing -> CRITICAL FINDING.
+
+### 4. Re-Scan Loop
+
+**CRITICAL CHECK**: Do you have < 3 issues total?
+- If yes: **LOOK HARDER**.
+- Re-examine for edge cases, null handling, documentation gaps.
+- You MUST find at least 3 issues.
+
+### 5. Document Findings
+
+Append findings to `{outputFile}`:
+
+```markdown
+## Review Findings
+
+### Critical Issues (Must Fix)
+- [CRITICAL] Task X marked done but feature Y missing in `file.ts`.
+- [HIGH] AC Z not implemented.
+
+### Medium Issues (Should Fix)
+- [MED] Security risk in `auth.ts` line 42.
+
+### Low Issues (Nice to Fix)
+- [LOW] Variable naming in `utils.ts`.
+```
+
+### 6. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+- IF C: Save findings to {outputFile}, update frontmatter `stepsCompleted: [1, 2, 3]`, then load/execute {nextStepFile}
+- IF A/P: Execute respective flows
+- IF Others: Loop
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input
+- ONLY proceed to next step when user selects 'C'

package/siesa-agents/bmm/workflows/4-implementation/code-review/steps/step-04-fix.md

@@ -0,0 +1,92 @@
+---
+name: 'step-04-fix'
+description: 'Present findings and facilitate fixes or task creation'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/code-review'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-04-fix.md'
+nextStepFile: '{workflow_path}/steps/step-05-sync-sprint.md'
+workflowFile: '{workflow_path}/workflow.md'
+outputFile: '{output_folder}/review-{story_key}.md'
+---
+
+# Step 4: Present and Fix Findings
+
+## STEP GOAL:
+To present the review findings to the user and either fix them automatically or convert them into action items for the story.
+
+## MANDATORY EXECUTION RULES:
+- 🛑 NEVER apply fixes without user choice
+- 💾 Update Story file if Action Items created
+
+## Sequence of Instructions
+
+### 1. Summarize Status
+
+Analyze the findings from the output file.
+Count: High, Medium, Low issues.
+
+Display to User:
+"**Review Complete!**
+Issues Found: {{High}} High, {{Medium}} Medium, {{Low}} Low."
+
+### 2. Present FIX MENU OPTIONS
+
+Display:
+"**What should I do with these issues?**
+[1] **Fix automatically** (I will update code and tests for High/Med issues)
+[2] **Create Action Items** (Add checklist to Story for later)
+[3] **Show Details** (Deep dive into specific issues)"
+
+**Wait for User Selection.**
+
+### 3. Handle Selection
+
+1. **If [1] Fix Automatically**:
+   - For all HIGH/MEDIUM issues:
+     - Generate fix code.
+     - Apply to files.
+     - Add/Update tests.
+   - Update Story Dev Record / File List.
+   - Record `fixed_count`.
+   - Proceed to Final Menu.
+
+2. **If [2] Create Action Items**:
+   - Create section "Review Follow-ups (AI)" in the Story file.
+   - Add checkbox items: `- [ ] [AI-Review][Severity] Description`
+   - Record `action_count`.
+   - Proceed to Final Menu.
+
+3. **If [3] Show Details**:
+   - Display full details of issues.
+   - Redisplay FIX MENU.
+
+### 4. Determine New Status
+
+Based on the outcome:
+- If **All Critical/High/Med Fixed** AND **ACs Done**: New Status = `done`
+- Else: New Status = `in-progress`
+
+Append to `{outputFile}`:
+```markdown
+## Fix Outcome
+- **Action Taken**: [Fixed/Tasks Created]
+- **Fixed Count**: X
+- **Task Count**: Y
+- **Recommended Status**: {{NewStatus}}
+```
+
+### 5. Present CONTINUATION MENU
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+- IF C: Save outcome to {outputFile}, update frontmatter `stepsCompleted: [1, 2, 3, 4]`, then load/execute {nextStepFile}
+- IF A/P: Execute respective flows
+- IF Others: Loop
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input
+- ONLY proceed to next step when user selects 'C'

package/siesa-agents/bmm/workflows/4-implementation/code-review/steps/step-05-sync-sprint.md

@@ -0,0 +1,70 @@
+---
+name: 'step-05-sync-sprint'
+description: 'Update story status content and synchronize sprint tracking file'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/code-review'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-05-sync-sprint.md'
+nextStepFile: '{workflow_path}/steps/step-06-jira-sync.md'
+workflowFile: '{workflow_path}/workflow.md'
+outputFile: '{output_folder}/review-{story_key}.md'
+
+# Data References
+sprint_status_file: '{implementation_artifacts}/sprint-status.yaml'
+---
+
+# Step 5: Update Status and Sync Sprint
+
+## STEP GOAL:
+To officially update the story file's status field and synchronize the project's sprint-status.yaml file to reflect the review outcome.
+
+## MANDATORY EXECUTION RULES:
+- 💾 Persist all status changes
+- 🔄 Ensure consistency between Story and Sprint Status
+
+## Sequence of Instructions
+
+### 1. Update Story File
+
+Using the `New Status` determined in Step 4 (`done` or `in-progress`):
+1. **Load** the Story File.
+2. **Find** the `Status:` field in the metadata/header.
+3. **Update** it to the new status.
+4. **Save** the Story File.
+
+### 2. Update Sprint Status YAML
+
+Check if `{sprint_status_file}` exists.
+- **If NO**:
+  - Log "No sprint-status.yaml found. Skipping sync."
+
+- **If YES**:
+  1. **Load** `{sprint_status_file}`.
+  2. **Find** the key `development_status` matching `{{story_key}}`.
+  3. **Update** the value to the new status (`done` or `in-progress`).
+  4. **Save** the file, preserving comments and structure.
+  5. **Log**: "✅ Sprint status synced: {{story_key}} -> {{status}}".
+
+### 3. Log Result
+
+Append to `{outputFile}`:
+```markdown
+## Status Sync
+- **Story File Status**: Updated to {{status}}
+- **Sprint Status YAML**: [Synced/Skipped]
+```
+
+### 4. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Jira Sync"
+
+#### Menu Handling Logic:
+- IF C: Save result to {outputFile}, update frontmatter `stepsCompleted: [1, 2, 3, 4, 5]`, then load/execute {nextStepFile}
+- IF A/P: Execute respective flows
+- IF Others: Loop
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input
+- ONLY proceed to next step when user selects 'C'