initial commit
This commit is contained in:
@@ -0,0 +1,105 @@
|
||||
---
|
||||
name: 'step-01-load-context'
|
||||
description: 'Load requirements, knowledge base, and related artifacts'
|
||||
nextStepFile: './step-02-discover-tests.md'
|
||||
knowledgeIndex: '{project-root}/_bmad/tea/testarch/tea-index.csv'
|
||||
outputFile: '{test_artifacts}/traceability-report.md'
|
||||
---
|
||||
|
||||
# Step 1: Load Context & Knowledge Base
|
||||
|
||||
## STEP GOAL
|
||||
|
||||
Gather acceptance criteria, priorities, and supporting artifacts for traceability.
|
||||
|
||||
## MANDATORY EXECUTION RULES
|
||||
|
||||
- 📖 Read the entire step file before acting
|
||||
- ✅ Speak in `{communication_language}`
|
||||
|
||||
---
|
||||
|
||||
## EXECUTION PROTOCOLS:
|
||||
|
||||
- 🎯 Follow the MANDATORY SEQUENCE exactly
|
||||
- 💾 Record outputs before proceeding
|
||||
- 📖 Load the next step only when instructed
|
||||
|
||||
## CONTEXT BOUNDARIES:
|
||||
|
||||
- Available context: config, loaded artifacts, and knowledge fragments
|
||||
- Focus: this step's goal only
|
||||
- Limits: do not execute future steps
|
||||
- Dependencies: prior steps' outputs (if any)
|
||||
|
||||
## MANDATORY SEQUENCE
|
||||
|
||||
**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
|
||||
|
||||
## 1. Prerequisites
|
||||
|
||||
- Acceptance criteria available (story or provided inline)
|
||||
- Tests exist OR gaps explicitly acknowledged
|
||||
|
||||
If acceptance criteria are missing, **HALT** and request them.
|
||||
|
||||
---
|
||||
|
||||
## 2. Load Knowledge Base
|
||||
|
||||
From `{knowledgeIndex}` load:
|
||||
|
||||
- `test-priorities-matrix.md`
|
||||
- `risk-governance.md`
|
||||
- `probability-impact.md`
|
||||
- `test-quality.md`
|
||||
- `selective-testing.md`
|
||||
|
||||
---
|
||||
|
||||
## 3. Load Artifacts
|
||||
|
||||
If available:
|
||||
|
||||
- Story file and acceptance criteria
|
||||
- Test design doc (priorities)
|
||||
- Tech spec / PRD
|
||||
|
||||
Summarize what was found.
|
||||
|
||||
---
|
||||
|
||||
### 4. Save Progress
|
||||
|
||||
**Save this step's accumulated work to `{outputFile}`.**
|
||||
|
||||
- **If `{outputFile}` does not exist** (first save), create it using the workflow template (if available) with YAML frontmatter:
|
||||
|
||||
```yaml
|
||||
---
|
||||
stepsCompleted: ['step-01-load-context']
|
||||
lastStep: 'step-01-load-context'
|
||||
lastSaved: '{date}'
|
||||
---
|
||||
```
|
||||
|
||||
Then write this step's output below the frontmatter.
|
||||
|
||||
- **If `{outputFile}` already exists**, update:
|
||||
- Add `'step-01-load-context'` to `stepsCompleted` array (only if not already present)
|
||||
- Set `lastStep: 'step-01-load-context'`
|
||||
- Set `lastSaved: '{date}'`
|
||||
- Append this step's output to the appropriate section of the document.
|
||||
|
||||
Load next step: `{nextStepFile}`
|
||||
|
||||
## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
|
||||
|
||||
### ✅ SUCCESS:
|
||||
|
||||
- Step completed in full with required outputs
|
||||
|
||||
### ❌ SYSTEM FAILURE:
|
||||
|
||||
- Skipped sequence steps or missing outputs
|
||||
**Master Rule:** Skipping steps is FORBIDDEN.
|
||||
102
.agents/skills/bmad-testarch-trace/steps-c/step-01b-resume.md
Normal file
102
.agents/skills/bmad-testarch-trace/steps-c/step-01b-resume.md
Normal file
@@ -0,0 +1,102 @@
|
||||
---
|
||||
name: 'step-01b-resume'
|
||||
description: 'Resume interrupted workflow from last completed step'
|
||||
outputFile: '{test_artifacts}/traceability-report.md'
|
||||
---
|
||||
|
||||
# Step 1b: Resume Workflow
|
||||
|
||||
## STEP GOAL
|
||||
|
||||
Resume an interrupted workflow by loading the existing output document, displaying progress, and routing to the next incomplete step.
|
||||
|
||||
## MANDATORY EXECUTION RULES
|
||||
|
||||
- 📖 Read the entire step file before acting
|
||||
- ✅ Speak in `{communication_language}`
|
||||
|
||||
---
|
||||
|
||||
## EXECUTION PROTOCOLS:
|
||||
|
||||
- 🎯 Follow the MANDATORY SEQUENCE exactly
|
||||
- 📖 Load the next step only when instructed
|
||||
|
||||
## CONTEXT BOUNDARIES:
|
||||
|
||||
- Available context: Output document with progress frontmatter
|
||||
- Focus: Load progress and route to next step
|
||||
- Limits: Do not re-execute completed steps
|
||||
- Dependencies: Output document must exist from a previous run
|
||||
|
||||
## MANDATORY SEQUENCE
|
||||
|
||||
**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
|
||||
|
||||
### 1. Load Output Document
|
||||
|
||||
Read `{outputFile}` and parse YAML frontmatter for:
|
||||
|
||||
- `stepsCompleted` — array of completed step names
|
||||
- `lastStep` — last completed step name
|
||||
- `lastSaved` — timestamp of last save
|
||||
|
||||
**If `{outputFile}` does not exist**, display:
|
||||
|
||||
"⚠️ **No previous progress found.** There is no output document to resume from. Please use **[C] Create** to start a fresh workflow run."
|
||||
|
||||
**THEN:** Halt. Do not proceed.
|
||||
|
||||
---
|
||||
|
||||
### 2. Display Progress Dashboard
|
||||
|
||||
Display:
|
||||
|
||||
"📋 **Workflow Resume — Requirements Traceability & Quality Gate**
|
||||
|
||||
**Last saved:** {lastSaved}
|
||||
**Steps completed:** {stepsCompleted.length} of 5
|
||||
|
||||
1. Load Context (step-01-load-context) — {✅ if in stepsCompleted, ⬜ otherwise}
|
||||
2. Discover Tests (step-02-discover-tests) — {✅ if in stepsCompleted, ⬜ otherwise}
|
||||
3. Map Criteria (step-03-map-criteria) — {✅ if in stepsCompleted, ⬜ otherwise}
|
||||
4. Analyze Gaps (step-04-analyze-gaps) — {✅ if in stepsCompleted, ⬜ otherwise}
|
||||
5. Gate Decision (step-05-gate-decision) — {✅ if in stepsCompleted, ⬜ otherwise}"
|
||||
|
||||
---
|
||||
|
||||
### 3. Route to Next Step
|
||||
|
||||
Based on `lastStep`, load the next incomplete step:
|
||||
|
||||
- `'step-01-load-context'` → Load `./step-02-discover-tests.md`
|
||||
- `'step-02-discover-tests'` → Load `./step-03-map-criteria.md`
|
||||
- `'step-03-map-criteria'` → Load `./step-04-analyze-gaps.md`
|
||||
- `'step-04-analyze-gaps'` → Load `./step-05-gate-decision.md`
|
||||
- `'step-05-gate-decision'` → **Workflow already complete.** Display: "✅ **All steps completed.** Use **[V] Validate** to review outputs or **[E] Edit** to make revisions." Then halt.
|
||||
|
||||
**If `lastStep` does not match any value above**, display: "⚠️ **Unknown progress state** (`lastStep`: {lastStep}). Please use **[C] Create** to start fresh." Then halt.
|
||||
|
||||
**Otherwise**, load the identified step file, read completely, and execute.
|
||||
|
||||
The existing content in `{outputFile}` provides context from previously completed steps. Use it as reference for remaining steps.
|
||||
|
||||
---
|
||||
|
||||
## 🚨 SYSTEM SUCCESS/FAILURE METRICS
|
||||
|
||||
### ✅ SUCCESS:
|
||||
|
||||
- Output document loaded and parsed correctly
|
||||
- Progress dashboard displayed accurately
|
||||
- Routed to correct next step
|
||||
|
||||
### ❌ SYSTEM FAILURE:
|
||||
|
||||
- Not loading output document
|
||||
- Incorrect progress display
|
||||
- Routing to wrong step
|
||||
- Re-executing completed steps
|
||||
|
||||
**Master Rule:** Resume MUST route to the exact next incomplete step. Never re-execute completed steps.
|
||||
@@ -0,0 +1,112 @@
|
||||
---
|
||||
name: 'step-02-discover-tests'
|
||||
description: 'Discover and catalog tests by level'
|
||||
nextStepFile: './step-03-map-criteria.md'
|
||||
outputFile: '{test_artifacts}/traceability-report.md'
|
||||
---
|
||||
|
||||
# Step 2: Discover & Catalog Tests
|
||||
|
||||
## STEP GOAL
|
||||
|
||||
Identify tests relevant to the requirements and classify by test level.
|
||||
|
||||
## MANDATORY EXECUTION RULES
|
||||
|
||||
- 📖 Read the entire step file before acting
|
||||
- ✅ Speak in `{communication_language}`
|
||||
|
||||
---
|
||||
|
||||
## EXECUTION PROTOCOLS:
|
||||
|
||||
- 🎯 Follow the MANDATORY SEQUENCE exactly
|
||||
- 💾 Record outputs before proceeding
|
||||
- 📖 Load the next step only when instructed
|
||||
|
||||
## CONTEXT BOUNDARIES:
|
||||
|
||||
- Available context: config, loaded artifacts, and knowledge fragments
|
||||
- Focus: this step's goal only
|
||||
- Limits: do not execute future steps
|
||||
- Dependencies: prior steps' outputs (if any)
|
||||
|
||||
## MANDATORY SEQUENCE
|
||||
|
||||
**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
|
||||
|
||||
## 1. Discover Tests
|
||||
|
||||
Search `{test_dir}` for:
|
||||
|
||||
- Test IDs (e.g., `1.3-E2E-001`)
|
||||
- Feature name matches
|
||||
- Spec patterns (`*.spec.*`, `*.test.*`)
|
||||
|
||||
---
|
||||
|
||||
## 2. Categorize by Level
|
||||
|
||||
Classify as:
|
||||
|
||||
- E2E
|
||||
- API
|
||||
- Component
|
||||
- Unit
|
||||
|
||||
Record test IDs, describe blocks, and priority markers if present.
|
||||
|
||||
---
|
||||
|
||||
## 3. Build Coverage Heuristics Inventory
|
||||
|
||||
Capture explicit coverage signals so Phase 1 can detect common blind spots:
|
||||
|
||||
- API endpoint coverage
|
||||
- Inventory endpoints referenced by requirements/specs and endpoints exercised by API tests
|
||||
- Mark endpoints with no direct tests
|
||||
- Authentication/authorization coverage
|
||||
- Detect tests for login/session/token flows and permission-denied paths
|
||||
- Mark auth/authz requirements with missing negative-path tests
|
||||
- Error-path coverage
|
||||
- Detect validation, timeout, network-failure, and server-error scenarios
|
||||
- Mark criteria with happy-path-only tests
|
||||
|
||||
Record these findings in step output as `coverage_heuristics` for Step 3/4.
|
||||
|
||||
---
|
||||
|
||||
### 4. Save Progress
|
||||
|
||||
**Save this step's accumulated work to `{outputFile}`.**
|
||||
|
||||
- **If `{outputFile}` does not exist** (first save), create it using the workflow template (if available) with YAML frontmatter:
|
||||
|
||||
```yaml
|
||||
---
|
||||
stepsCompleted: ['step-02-discover-tests']
|
||||
lastStep: 'step-02-discover-tests'
|
||||
lastSaved: '{date}'
|
||||
---
|
||||
```
|
||||
|
||||
Then write this step's output below the frontmatter.
|
||||
|
||||
- **If `{outputFile}` already exists**, update:
|
||||
- Add `'step-02-discover-tests'` to `stepsCompleted` array (only if not already present)
|
||||
- Set `lastStep: 'step-02-discover-tests'`
|
||||
- Set `lastSaved: '{date}'`
|
||||
- Append this step's output to the appropriate section of the document.
|
||||
|
||||
Load next step: `{nextStepFile}`
|
||||
|
||||
## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
|
||||
|
||||
### ✅ SUCCESS:
|
||||
|
||||
- Step completed in full with required outputs
|
||||
|
||||
### ❌ SYSTEM FAILURE:
|
||||
|
||||
- Skipped sequence steps or missing outputs
|
||||
**Master Rule:** Skipping steps is FORBIDDEN.
|
||||
@@ -0,0 +1,97 @@
|
||||
---
|
||||
name: 'step-03-map-criteria'
|
||||
description: 'Map acceptance criteria to tests and build traceability matrix'
|
||||
nextStepFile: './step-04-analyze-gaps.md'
|
||||
outputFile: '{test_artifacts}/traceability-report.md'
|
||||
---
|
||||
|
||||
# Step 3: Map Criteria to Tests
|
||||
|
||||
## STEP GOAL
|
||||
|
||||
Create the traceability matrix linking requirements to tests.
|
||||
|
||||
## MANDATORY EXECUTION RULES
|
||||
|
||||
- 📖 Read the entire step file before acting
|
||||
- ✅ Speak in `{communication_language}`
|
||||
|
||||
---
|
||||
|
||||
## EXECUTION PROTOCOLS:
|
||||
|
||||
- 🎯 Follow the MANDATORY SEQUENCE exactly
|
||||
- 💾 Record outputs before proceeding
|
||||
- 📖 Load the next step only when instructed
|
||||
|
||||
## CONTEXT BOUNDARIES:
|
||||
|
||||
- Available context: config, loaded artifacts, and knowledge fragments
|
||||
- Focus: this step's goal only
|
||||
- Limits: do not execute future steps
|
||||
- Dependencies: prior steps' outputs (if any)
|
||||
|
||||
## MANDATORY SEQUENCE
|
||||
|
||||
**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
|
||||
|
||||
## 1. Build Matrix
|
||||
|
||||
For each acceptance criterion:
|
||||
|
||||
- Map to matching tests
|
||||
- Mark coverage status: FULL / PARTIAL / NONE / UNIT-ONLY / INTEGRATION-ONLY
|
||||
- Record test level and priority
|
||||
- Record heuristic signals:
|
||||
- Endpoint coverage present/missing (for API-impacting criteria)
|
||||
- Auth/authz coverage present/missing (positive and negative paths)
|
||||
- Error-path coverage present/missing (validation, timeout, network/server failures)
|
||||
|
||||
---
|
||||
|
||||
## 2. Validate Coverage Logic
|
||||
|
||||
Ensure:
|
||||
|
||||
- P0/P1 criteria have coverage
|
||||
- No duplicate coverage across levels without justification
|
||||
- Criteria are not happy-path-only when requirements imply error handling
|
||||
- API criteria are not marked FULL if endpoint-level checks are missing
|
||||
- Auth/authz criteria include at least one denied/invalid-path test where applicable
|
||||
|
||||
---
|
||||
|
||||
### 3. Save Progress
|
||||
|
||||
**Save this step's accumulated work to `{outputFile}`.**
|
||||
|
||||
- **If `{outputFile}` does not exist** (first save), create it using the workflow template (if available) with YAML frontmatter:
|
||||
|
||||
```yaml
|
||||
---
|
||||
stepsCompleted: ['step-03-map-criteria']
|
||||
lastStep: 'step-03-map-criteria'
|
||||
lastSaved: '{date}'
|
||||
---
|
||||
```
|
||||
|
||||
Then write this step's output below the frontmatter.
|
||||
|
||||
- **If `{outputFile}` already exists**, update:
|
||||
- Add `'step-03-map-criteria'` to `stepsCompleted` array (only if not already present)
|
||||
- Set `lastStep: 'step-03-map-criteria'`
|
||||
- Set `lastSaved: '{date}'`
|
||||
- Append this step's output to the appropriate section of the document.
|
||||
|
||||
Load next step: `{nextStepFile}`
|
||||
|
||||
## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
|
||||
|
||||
### ✅ SUCCESS:
|
||||
|
||||
- Step completed in full with required outputs
|
||||
|
||||
### ❌ SYSTEM FAILURE:
|
||||
|
||||
- Skipped sequence steps or missing outputs
|
||||
**Master Rule:** Skipping steps is FORBIDDEN.
|
||||
@@ -0,0 +1,421 @@
|
||||
---
|
||||
name: 'step-04-analyze-gaps'
|
||||
description: 'Complete Phase 1 with adaptive orchestration (agent-team, subagent, or sequential)'
|
||||
nextStepFile: './step-05-gate-decision.md'
|
||||
outputFile: '{test_artifacts}/traceability-report.md'
|
||||
tempOutputFile: '/tmp/tea-trace-coverage-matrix-{{timestamp}}.json'
|
||||
---
|
||||
|
||||
# Step 4: Complete Phase 1 - Coverage Matrix Generation
|
||||
|
||||
## STEP GOAL
|
||||
|
||||
**Phase 1 Final Step:** Analyze coverage gaps (including endpoint/auth/error-path blind spots), generate recommendations, and output complete coverage matrix to temp file for Phase 2 (gate decision).
|
||||
|
||||
---
|
||||
|
||||
## MANDATORY EXECUTION RULES
|
||||
|
||||
- 📖 Read the entire step file before acting
|
||||
- ✅ Speak in `{communication_language}`
|
||||
- ✅ Output coverage matrix to temp file
|
||||
- ✅ Resolve execution mode from explicit user request first, then config
|
||||
- ✅ Apply fallback rules deterministically when requested mode is unsupported
|
||||
- ❌ Do NOT make gate decision (that's Phase 2 - Step 5)
|
||||
|
||||
---
|
||||
|
||||
## EXECUTION PROTOCOLS:
|
||||
|
||||
- 🎯 Follow the MANDATORY SEQUENCE exactly
|
||||
- 💾 Record outputs before proceeding
|
||||
- 📖 Load the next step only when instructed
|
||||
|
||||
## CONTEXT BOUNDARIES:
|
||||
|
||||
- Available context: requirements from Step 1, tests from Step 2, traceability matrix from Step 3
|
||||
- Focus: gap analysis and matrix completion
|
||||
- Limits: do not make gate decision (Phase 2 responsibility)
|
||||
|
||||
---
|
||||
|
||||
## MANDATORY SEQUENCE
|
||||
|
||||
### 0. Resolve Execution Mode (User Override First)
|
||||
|
||||
```javascript
|
||||
const parseBooleanFlag = (value, defaultValue = true) => {
|
||||
if (typeof value === 'string') {
|
||||
const normalized = value.trim().toLowerCase();
|
||||
if (['false', '0', 'off', 'no'].includes(normalized)) return false;
|
||||
if (['true', '1', 'on', 'yes'].includes(normalized)) return true;
|
||||
}
|
||||
if (value === undefined || value === null) return defaultValue;
|
||||
return Boolean(value);
|
||||
};
|
||||
|
||||
const orchestrationContext = {
|
||||
config: {
|
||||
execution_mode: config.tea_execution_mode || 'auto', // "auto" | "subagent" | "agent-team" | "sequential"
|
||||
capability_probe: parseBooleanFlag(config.tea_capability_probe, true), // supports booleans and "false"/"true" strings
|
||||
},
|
||||
timestamp: new Date().toISOString().replace(/[:.]/g, '-'),
|
||||
};
|
||||
|
||||
const normalizeUserExecutionMode = (mode) => {
|
||||
if (typeof mode !== 'string') return null;
|
||||
const normalized = mode.trim().toLowerCase().replace(/[-_]/g, ' ').replace(/\s+/g, ' ');
|
||||
|
||||
if (normalized === 'auto') return 'auto';
|
||||
if (normalized === 'sequential') return 'sequential';
|
||||
if (normalized === 'subagent' || normalized === 'sub agent' || normalized === 'subagents' || normalized === 'sub agents') {
|
||||
return 'subagent';
|
||||
}
|
||||
if (normalized === 'agent team' || normalized === 'agent teams' || normalized === 'agentteam') {
|
||||
return 'agent-team';
|
||||
}
|
||||
|
||||
return null;
|
||||
};
|
||||
|
||||
const normalizeConfigExecutionMode = (mode) => {
|
||||
if (mode === 'subagent') return 'subagent';
|
||||
if (mode === 'auto' || mode === 'sequential' || mode === 'subagent' || mode === 'agent-team') {
|
||||
return mode;
|
||||
}
|
||||
return null;
|
||||
};
|
||||
|
||||
// Explicit user instruction in the active run takes priority over config.
|
||||
const explicitModeFromUser = normalizeUserExecutionMode(runtime.getExplicitExecutionModeHint?.() || null);
|
||||
|
||||
const requestedMode = explicitModeFromUser || normalizeConfigExecutionMode(orchestrationContext.config.execution_mode) || 'auto';
|
||||
const probeEnabled = orchestrationContext.config.capability_probe;
|
||||
|
||||
const supports = { subagent: false, agentTeam: false };
|
||||
if (probeEnabled) {
|
||||
supports.subagent = runtime.canLaunchSubagents?.() === true;
|
||||
supports.agentTeam = runtime.canLaunchAgentTeams?.() === true;
|
||||
}
|
||||
|
||||
let resolvedMode = requestedMode;
|
||||
if (requestedMode === 'auto') {
|
||||
if (supports.agentTeam) resolvedMode = 'agent-team';
|
||||
else if (supports.subagent) resolvedMode = 'subagent';
|
||||
else resolvedMode = 'sequential';
|
||||
} else if (probeEnabled && requestedMode === 'agent-team' && !supports.agentTeam) {
|
||||
resolvedMode = supports.subagent ? 'subagent' : 'sequential';
|
||||
} else if (probeEnabled && requestedMode === 'subagent' && !supports.subagent) {
|
||||
resolvedMode = 'sequential';
|
||||
}
|
||||
```
|
||||
|
||||
Resolution precedence:
|
||||
|
||||
1. Explicit user request in this run (`agent team` => `agent-team`; `subagent` => `subagent`; `sequential`; `auto`)
|
||||
2. `tea_execution_mode` from config
|
||||
3. Runtime capability fallback (when probing enabled)
|
||||
|
||||
### 1. Gap Analysis
|
||||
|
||||
**Identify uncovered requirements:**
|
||||
|
||||
```javascript
|
||||
const uncoveredRequirements = traceabilityMatrix.filter((req) => req.coverage === 'NONE');
|
||||
const partialCoverage = traceabilityMatrix.filter((req) => req.coverage === 'PARTIAL');
|
||||
const unitOnlyCoverage = traceabilityMatrix.filter((req) => req.coverage === 'UNIT-ONLY');
|
||||
```
|
||||
|
||||
**Prioritize gaps by risk:**
|
||||
|
||||
```javascript
|
||||
const criticalGaps = uncoveredRequirements.filter((req) => req.priority === 'P0');
|
||||
const highGaps = uncoveredRequirements.filter((req) => req.priority === 'P1');
|
||||
const mediumGaps = uncoveredRequirements.filter((req) => req.priority === 'P2');
|
||||
const lowGaps = uncoveredRequirements.filter((req) => req.priority === 'P3');
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 2. Coverage Heuristics Checks
|
||||
|
||||
Use the heuristics inventory from Step 2 and mapped criteria from Step 3 to flag common coverage blind spots:
|
||||
|
||||
```javascript
|
||||
const endpointCoverageGaps = coverageHeuristics?.endpoints_without_tests || [];
|
||||
const authCoverageGaps = coverageHeuristics?.auth_missing_negative_paths || [];
|
||||
const errorPathGaps = coverageHeuristics?.criteria_happy_path_only || [];
|
||||
|
||||
const heuristicGapCounts = {
|
||||
endpoints_without_tests: endpointCoverageGaps.length,
|
||||
auth_missing_negative_paths: authCoverageGaps.length,
|
||||
happy_path_only_criteria: errorPathGaps.length,
|
||||
};
|
||||
```
|
||||
|
||||
Heuristics are advisory but must influence gap severity and recommendations, especially for P0/P1 criteria.
|
||||
|
||||
---
|
||||
|
||||
### 3. Generate Recommendations
|
||||
|
||||
**Based on gap analysis:**
|
||||
|
||||
```javascript
|
||||
const recommendations = [];
|
||||
|
||||
// Critical gaps (P0)
|
||||
if (criticalGaps.length > 0) {
|
||||
recommendations.push({
|
||||
priority: 'URGENT',
|
||||
action: `Run /bmad:tea:atdd for ${criticalGaps.length} P0 requirements`,
|
||||
requirements: criticalGaps.map((r) => r.id),
|
||||
});
|
||||
}
|
||||
|
||||
// High priority gaps (P1)
|
||||
if (highGaps.length > 0) {
|
||||
recommendations.push({
|
||||
priority: 'HIGH',
|
||||
action: `Run /bmad:tea:automate to expand coverage for ${highGaps.length} P1 requirements`,
|
||||
requirements: highGaps.map((r) => r.id),
|
||||
});
|
||||
}
|
||||
|
||||
// Partial coverage
|
||||
if (partialCoverage.length > 0) {
|
||||
recommendations.push({
|
||||
priority: 'MEDIUM',
|
||||
action: `Complete coverage for ${partialCoverage.length} partially covered requirements`,
|
||||
requirements: partialCoverage.map((r) => r.id),
|
||||
});
|
||||
}
|
||||
|
||||
if (endpointCoverageGaps.length > 0) {
|
||||
recommendations.push({
|
||||
priority: 'HIGH',
|
||||
action: `Add API tests for ${endpointCoverageGaps.length} uncovered endpoint(s)`,
|
||||
requirements: endpointCoverageGaps.map((r) => r.id || r.endpoint || 'unknown'),
|
||||
});
|
||||
}
|
||||
|
||||
if (authCoverageGaps.length > 0) {
|
||||
recommendations.push({
|
||||
priority: 'HIGH',
|
||||
action: `Add negative-path auth/authz tests for ${authCoverageGaps.length} requirement(s)`,
|
||||
requirements: authCoverageGaps.map((r) => r.id || 'unknown'),
|
||||
});
|
||||
}
|
||||
|
||||
if (errorPathGaps.length > 0) {
|
||||
recommendations.push({
|
||||
priority: 'MEDIUM',
|
||||
action: `Add error/edge scenario tests for ${errorPathGaps.length} happy-path-only criterion/criteria`,
|
||||
requirements: errorPathGaps.map((r) => r.id || 'unknown'),
|
||||
});
|
||||
}
|
||||
|
||||
// Quality issues
|
||||
recommendations.push({
|
||||
priority: 'LOW',
|
||||
action: 'Run /bmad:tea:test-review to assess test quality',
|
||||
requirements: [],
|
||||
});
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 4. Calculate Coverage Statistics
|
||||
|
||||
```javascript
|
||||
const totalRequirements = traceabilityMatrix.length;
|
||||
const coveredRequirements = traceabilityMatrix.filter((r) => r.coverage === 'FULL' || r.coverage === 'PARTIAL').length;
|
||||
const fullyCovered = traceabilityMatrix.filter((r) => r.coverage === 'FULL').length;
|
||||
|
||||
const safePct = (covered, total) => (total > 0 ? Math.round((covered / total) * 100) : 100);
|
||||
const coveragePercentage = safePct(fullyCovered, totalRequirements);
|
||||
|
||||
// Priority-specific coverage
|
||||
const p0Total = traceabilityMatrix.filter((r) => r.priority === 'P0').length;
|
||||
const p0Covered = traceabilityMatrix.filter((r) => r.priority === 'P0' && r.coverage === 'FULL').length;
|
||||
const p1Total = traceabilityMatrix.filter((r) => r.priority === 'P1').length;
|
||||
const p1Covered = traceabilityMatrix.filter((r) => r.priority === 'P1' && r.coverage === 'FULL').length;
|
||||
const p2Total = traceabilityMatrix.filter((r) => r.priority === 'P2').length;
|
||||
const p2Covered = traceabilityMatrix.filter((r) => r.priority === 'P2' && r.coverage === 'FULL').length;
|
||||
const p3Total = traceabilityMatrix.filter((r) => r.priority === 'P3').length;
|
||||
const p3Covered = traceabilityMatrix.filter((r) => r.priority === 'P3' && r.coverage === 'FULL').length;
|
||||
|
||||
const p0CoveragePercentage = safePct(p0Covered, p0Total);
|
||||
const p1CoveragePercentage = safePct(p1Covered, p1Total);
|
||||
const p2CoveragePercentage = safePct(p2Covered, p2Total);
|
||||
const p3CoveragePercentage = safePct(p3Covered, p3Total);
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 5. Generate Complete Coverage Matrix
|
||||
|
||||
**Compile all Phase 1 outputs:**
|
||||
|
||||
```javascript
|
||||
const coverageMatrix = {
|
||||
phase: 'PHASE_1_COMPLETE',
|
||||
generated_at: new Date().toISOString(),
|
||||
|
||||
requirements: traceabilityMatrix, // Full matrix from Step 3
|
||||
|
||||
coverage_statistics: {
|
||||
total_requirements: totalRequirements,
|
||||
fully_covered: fullyCovered,
|
||||
partially_covered: partialCoverage.length,
|
||||
uncovered: uncoveredRequirements.length,
|
||||
overall_coverage_percentage: coveragePercentage,
|
||||
|
||||
priority_breakdown: {
|
||||
P0: { total: p0Total, covered: p0Covered, percentage: p0CoveragePercentage },
|
||||
P1: { total: p1Total, covered: p1Covered, percentage: p1CoveragePercentage },
|
||||
P2: { total: p2Total, covered: p2Covered, percentage: p2CoveragePercentage },
|
||||
P3: { total: p3Total, covered: p3Covered, percentage: p3CoveragePercentage },
|
||||
},
|
||||
},
|
||||
|
||||
gap_analysis: {
|
||||
critical_gaps: criticalGaps,
|
||||
high_gaps: highGaps,
|
||||
medium_gaps: mediumGaps,
|
||||
low_gaps: lowGaps,
|
||||
partial_coverage_items: partialCoverage,
|
||||
unit_only_items: unitOnlyCoverage,
|
||||
},
|
||||
|
||||
coverage_heuristics: {
|
||||
endpoint_gaps: endpointCoverageGaps,
|
||||
auth_negative_path_gaps: authCoverageGaps,
|
||||
happy_path_only_gaps: errorPathGaps,
|
||||
counts: heuristicGapCounts,
|
||||
},
|
||||
|
||||
recommendations: recommendations,
|
||||
};
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 6. Output Coverage Matrix to Temp File
|
||||
|
||||
**Write to temp file for Phase 2:**
|
||||
|
||||
```javascript
|
||||
const outputPath = '{tempOutputFile}';
|
||||
fs.writeFileSync(outputPath, JSON.stringify(coverageMatrix, null, 2), 'utf8');
|
||||
|
||||
console.log(`✅ Phase 1 Complete: Coverage matrix saved to ${outputPath}`);
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 7. Display Phase 1 Summary
|
||||
|
||||
```
|
||||
✅ Phase 1 Complete: Coverage Matrix Generated
|
||||
|
||||
📊 Coverage Statistics:
|
||||
- Total Requirements: {totalRequirements}
|
||||
- Fully Covered: {fullyCovered} ({coveragePercentage}%)
|
||||
- Partially Covered: {partialCoverage.length}
|
||||
- Uncovered: {uncoveredRequirements.length}
|
||||
|
||||
🎯 Priority Coverage:
|
||||
- P0: {p0Covered}/{p0Total} ({p0CoveragePercentage}%)
|
||||
- P1: {p1Covered}/{p1Total} ({p1CoveragePercentage}%)
|
||||
- P2: {p2Covered}/{p2Total} ({p2CoveragePercentage}%)
|
||||
- P3: {p3Covered}/{p3Total} ({p3CoveragePercentage}%)
|
||||
|
||||
⚠️ Gaps Identified:
|
||||
- Critical (P0): {criticalGaps.length}
|
||||
- High (P1): {highGaps.length}
|
||||
- Medium (P2): {mediumGaps.length}
|
||||
- Low (P3): {lowGaps.length}
|
||||
|
||||
🔍 Coverage Heuristics:
|
||||
- Endpoints without tests: {endpointCoverageGaps.length}
|
||||
- Auth negative-path gaps: {authCoverageGaps.length}
|
||||
- Happy-path-only criteria: {errorPathGaps.length}
|
||||
|
||||
📝 Recommendations: {recommendations.length}
|
||||
|
||||
🔄 Phase 2: Gate decision (next step)
|
||||
```
|
||||
|
||||
### Orchestration Notes for This Step
|
||||
|
||||
When `resolvedMode` is `agent-team` or `subagent`, parallelize only dependency-safe sections:
|
||||
|
||||
- Worker A: gap classification (section 1)
|
||||
- Worker B: heuristics gap extraction (section 2)
|
||||
- Worker C: coverage statistics (section 4)
|
||||
|
||||
Section 3 (recommendation synthesis) depends on outputs from sections 1 and 2, so run it only after Workers A and B complete.
|
||||
|
||||
Section 5 remains the deterministic merge point after sections 1-4 are finished.
|
||||
|
||||
If `resolvedMode` is `sequential`, execute sections 1→7 in order.
|
||||
|
||||
---
|
||||
|
||||
## EXIT CONDITION
|
||||
|
||||
**PHASE 1 COMPLETE when:**
|
||||
|
||||
- ✅ Gap analysis complete
|
||||
- ✅ Recommendations generated
|
||||
- ✅ Coverage statistics calculated
|
||||
- ✅ Coverage matrix saved to temp file
|
||||
- ✅ Summary displayed
|
||||
|
||||
**Proceed to Phase 2 (Step 5: Gate Decision)**
|
||||
|
||||
---
|
||||
|
||||
### 8. Save Progress
|
||||
|
||||
**Save this step's accumulated work to `{outputFile}`.**
|
||||
|
||||
- **If `{outputFile}` does not exist** (first save), create it using the workflow template (if available) with YAML frontmatter:
|
||||
|
||||
```yaml
|
||||
---
|
||||
stepsCompleted: ['step-04-analyze-gaps']
|
||||
lastStep: 'step-04-analyze-gaps'
|
||||
lastSaved: '{date}'
|
||||
---
|
||||
```
|
||||
|
||||
Then write this step's output below the frontmatter.
|
||||
|
||||
- **If `{outputFile}` already exists**, update:
|
||||
- Add `'step-04-analyze-gaps'` to `stepsCompleted` array (only if not already present)
|
||||
- Set `lastStep: 'step-04-analyze-gaps'`
|
||||
- Set `lastSaved: '{date}'`
|
||||
- Append this step's output to the appropriate section of the document.
|
||||
|
||||
Load next step: `{nextStepFile}`
|
||||
|
||||
---
|
||||
|
||||
## 🚨 PHASE 1 SUCCESS METRICS
|
||||
|
||||
### ✅ SUCCESS:
|
||||
|
||||
- Coverage matrix complete and accurate
|
||||
- All gaps identified and prioritized
|
||||
- Recommendations actionable
|
||||
- Temp file output valid JSON
|
||||
|
||||
### ❌ FAILURE:
|
||||
|
||||
- Coverage matrix incomplete
|
||||
- Gap analysis missing
|
||||
- Invalid JSON output
|
||||
|
||||
**Master Rule:** Phase 1 MUST output complete coverage matrix to temp file before Phase 2 can proceed.
|
||||
@@ -0,0 +1,266 @@
|
||||
---
|
||||
name: 'step-05-gate-decision'
|
||||
description: 'Phase 2: Apply gate decision logic and generate outputs'
|
||||
outputFile: '{test_artifacts}/traceability-report.md'
|
||||
---
|
||||
|
||||
# Step 5: Phase 2 - Gate Decision
|
||||
|
||||
## STEP GOAL
|
||||
|
||||
**Phase 2:** Read coverage matrix from Phase 1, apply deterministic gate decision logic, and generate traceability report.
|
||||
|
||||
---
|
||||
|
||||
## MANDATORY EXECUTION RULES
|
||||
|
||||
- 📖 Read the entire step file before acting
|
||||
- ✅ Speak in `{communication_language}`
|
||||
- ✅ Read coverage matrix from Phase 1 temp file
|
||||
- ✅ Apply gate decision logic
|
||||
- ❌ Do NOT regenerate coverage matrix (use Phase 1 output)
|
||||
|
||||
---
|
||||
|
||||
## EXECUTION PROTOCOLS:
|
||||
|
||||
- 🎯 Follow the MANDATORY SEQUENCE exactly
|
||||
- 💾 Record outputs before proceeding
|
||||
- 📖 This is the FINAL step
|
||||
|
||||
## CONTEXT BOUNDARIES:
|
||||
|
||||
- Available context: Coverage matrix from Phase 1 temp file
|
||||
- Focus: gate decision logic only
|
||||
- Dependencies: Phase 1 complete (coverage matrix exists)
|
||||
|
||||
---
|
||||
|
||||
## MANDATORY SEQUENCE
|
||||
|
||||
### 1. Read Phase 1 Coverage Matrix
|
||||
|
||||
```javascript
|
||||
const matrixPath = '/tmp/tea-trace-coverage-matrix-{{timestamp}}.json';
|
||||
const coverageMatrix = JSON.parse(fs.readFileSync(matrixPath, 'utf8'));
|
||||
|
||||
console.log('✅ Phase 1 coverage matrix loaded');
|
||||
```
|
||||
|
||||
**Verify Phase 1 complete:**
|
||||
|
||||
```javascript
|
||||
if (coverageMatrix.phase !== 'PHASE_1_COMPLETE') {
|
||||
throw new Error('Phase 1 not complete - cannot proceed to gate decision');
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 2. Apply Gate Decision Logic
|
||||
|
||||
**Decision Tree:**
|
||||
|
||||
```javascript
|
||||
const stats = coverageMatrix.coverage_statistics;
|
||||
const p0Coverage = stats.priority_breakdown.P0.percentage;
|
||||
const p1Coverage = stats.priority_breakdown.P1.percentage;
|
||||
const hasP1Requirements = (stats.priority_breakdown.P1.total || 0) > 0;
|
||||
const effectiveP1Coverage = hasP1Requirements ? p1Coverage : 100;
|
||||
const overallCoverage = stats.overall_coverage_percentage;
|
||||
const criticalGaps = coverageMatrix.gap_analysis.critical_gaps.length;
|
||||
|
||||
let gateDecision;
|
||||
let rationale;
|
||||
|
||||
// Rule 1: P0 coverage must be 100%
|
||||
if (p0Coverage < 100) {
|
||||
gateDecision = 'FAIL';
|
||||
rationale = `P0 coverage is ${p0Coverage}% (required: 100%). ${criticalGaps} critical requirements uncovered.`;
|
||||
}
|
||||
// Rule 2: Overall coverage must be >= 80%
|
||||
else if (overallCoverage < 80) {
|
||||
gateDecision = 'FAIL';
|
||||
rationale = `Overall coverage is ${overallCoverage}% (minimum: 80%). Significant gaps exist.`;
|
||||
}
|
||||
// Rule 3: P1 coverage < 80% → FAIL
|
||||
else if (effectiveP1Coverage < 80) {
|
||||
gateDecision = 'FAIL';
|
||||
rationale = hasP1Requirements
|
||||
? `P1 coverage is ${effectiveP1Coverage}% (minimum: 80%). High-priority gaps must be addressed.`
|
||||
: `P1 requirements are not present; continuing with remaining gate criteria.`;
|
||||
}
|
||||
// Rule 4: P1 coverage >= 90% and overall >= 80% with P0 at 100% → PASS
|
||||
else if (effectiveP1Coverage >= 90) {
|
||||
gateDecision = 'PASS';
|
||||
rationale = hasP1Requirements
|
||||
? `P0 coverage is 100%, P1 coverage is ${effectiveP1Coverage}% (target: 90%), and overall coverage is ${overallCoverage}% (minimum: 80%).`
|
||||
: `P0 coverage is 100% and overall coverage is ${overallCoverage}% (minimum: 80%). No P1 requirements detected.`;
|
||||
}
|
||||
// Rule 5: P1 coverage 80-89% with P0 at 100% and overall >= 80% → CONCERNS
|
||||
else if (effectiveP1Coverage >= 80) {
|
||||
gateDecision = 'CONCERNS';
|
||||
rationale = hasP1Requirements
|
||||
? `P0 coverage is 100% and overall coverage is ${overallCoverage}% (minimum: 80%), but P1 coverage is ${effectiveP1Coverage}% (target: 90%).`
|
||||
: `P0 coverage is 100% and overall coverage is ${overallCoverage}% (minimum: 80%), but additional non-P1 gaps need mitigation.`;
|
||||
}
|
||||
|
||||
// Rule 6: Manual waiver option
|
||||
const manualWaiver = false; // Can be set via config or user input
|
||||
if (manualWaiver) {
|
||||
gateDecision = 'WAIVED';
|
||||
rationale += ' Manual waiver applied by stakeholder.';
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 3. Generate Gate Report
|
||||
|
||||
```javascript
|
||||
const gateReport = {
|
||||
decision: gateDecision,
|
||||
rationale: rationale,
|
||||
decision_date: new Date().toISOString(),
|
||||
|
||||
coverage_matrix: coverageMatrix,
|
||||
|
||||
gate_criteria: {
|
||||
p0_coverage_required: '100%',
|
||||
p0_coverage_actual: `${p0Coverage}%`,
|
||||
p0_status: p0Coverage === 100 ? 'MET' : 'NOT MET',
|
||||
|
||||
p1_coverage_target_pass: '90%',
|
||||
p1_coverage_minimum: '80%',
|
||||
p1_coverage_actual: `${effectiveP1Coverage}%`,
|
||||
p1_status: effectiveP1Coverage >= 90 ? 'MET' : effectiveP1Coverage >= 80 ? 'PARTIAL' : 'NOT MET',
|
||||
|
||||
overall_coverage_minimum: '80%',
|
||||
overall_coverage_actual: `${overallCoverage}%`,
|
||||
overall_status: overallCoverage >= 80 ? 'MET' : 'NOT MET',
|
||||
},
|
||||
|
||||
uncovered_requirements: coverageMatrix.gap_analysis.critical_gaps.concat(coverageMatrix.gap_analysis.high_gaps),
|
||||
|
||||
recommendations: coverageMatrix.recommendations,
|
||||
};
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 4. Generate Traceability Report
|
||||
|
||||
**Use trace-template.md to generate:**
|
||||
|
||||
```markdown
|
||||
# Traceability Report
|
||||
|
||||
## Gate Decision: {gateDecision}
|
||||
|
||||
**Rationale:** {rationale}
|
||||
|
||||
## Coverage Summary
|
||||
|
||||
- Total Requirements: {totalRequirements}
|
||||
- Covered: {fullyCovered} ({coveragePercentage}%)
|
||||
- P0 Coverage: {p0CoveragePercentage}%
|
||||
|
||||
## Traceability Matrix
|
||||
|
||||
[Full matrix with requirement → test mappings]
|
||||
|
||||
## Gaps & Recommendations
|
||||
|
||||
[List of uncovered requirements with recommended actions]
|
||||
|
||||
## Next Actions
|
||||
|
||||
{recommendations}
|
||||
```
|
||||
|
||||
**Save to:**
|
||||
|
||||
```javascript
|
||||
fs.writeFileSync('{outputFile}', reportContent, 'utf8');
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 5. Display Gate Decision
|
||||
|
||||
```
|
||||
🚨 GATE DECISION: {gateDecision}
|
||||
|
||||
📊 Coverage Analysis:
|
||||
- P0 Coverage: {p0Coverage}% (Required: 100%) → {p0_status}
|
||||
- P1 Coverage: {effectiveP1Coverage}% (PASS target: 90%, minimum: 80%) → {p1_status}
|
||||
- Overall Coverage: {overallCoverage}% (Minimum: 80%) → {overall_status}
|
||||
|
||||
✅ Decision Rationale:
|
||||
{rationale}
|
||||
|
||||
⚠️ Critical Gaps: {criticalGaps.length}
|
||||
|
||||
📝 Recommended Actions:
|
||||
{list top 3 recommendations}
|
||||
|
||||
📂 Full Report: {outputFile}
|
||||
|
||||
{if FAIL}
|
||||
🚫 GATE: FAIL - Release BLOCKED until coverage improves
|
||||
{endif}
|
||||
|
||||
{if CONCERNS}
|
||||
⚠️ GATE: CONCERNS - Proceed with caution, address gaps soon
|
||||
{endif}
|
||||
|
||||
{if PASS}
|
||||
✅ GATE: PASS - Release approved, coverage meets standards
|
||||
{endif}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### 6. Save Progress
|
||||
|
||||
**Update the YAML frontmatter in `{outputFile}` to mark this final step complete.**
|
||||
|
||||
Since step 4 (Generate Traceability Report) already wrote the report content to `{outputFile}`, do NOT overwrite it. Instead, update only the frontmatter at the top of the existing file:
|
||||
|
||||
- Add `'step-05-gate-decision'` to `stepsCompleted` array (only if not already present)
|
||||
- Set `lastStep: 'step-05-gate-decision'`
|
||||
- Set `lastSaved: '{date}'`
|
||||
|
||||
Then append the gate decision summary (from section 5 above) to the end of the existing report content.
|
||||
|
||||
---
|
||||
|
||||
## EXIT CONDITION
|
||||
|
||||
**WORKFLOW COMPLETE when:**
|
||||
|
||||
- ✅ Phase 1 coverage matrix read successfully
|
||||
- ✅ Gate decision logic applied
|
||||
- ✅ Traceability report generated
|
||||
- ✅ Gate decision displayed
|
||||
|
||||
**Workflow terminates here.**
|
||||
|
||||
---
|
||||
|
||||
## 🚨 PHASE 2 SUCCESS METRICS
|
||||
|
||||
### ✅ SUCCESS:
|
||||
|
||||
- Coverage matrix read from Phase 1
|
||||
- Gate decision made with clear rationale
|
||||
- Report generated and saved
|
||||
- Decision communicated clearly
|
||||
|
||||
### ❌ FAILURE:
|
||||
|
||||
- Could not read Phase 1 matrix
|
||||
- Gate decision logic incorrect
|
||||
- Report missing or incomplete
|
||||
|
||||
**Master Rule:** Gate decision MUST be deterministic based on clear criteria (P0 100%, P1 90/80, overall >=80).
|
||||
Reference in New Issue
Block a user