olympus-ai 4.5.5 → 4.5.6

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "olympus-ai",
-  "version": "4.5.5",
+  "version": "4.5.6",
   "description": "Olympus: Multi-agent orchestration for Claude Code. Summon the gods of code.",
   "author": {
     "name": "mikev10",

package/dist/installer/index.d.ts

@@ -24,7 +24,7 @@ export declare const HOOKS_DIR: string;
 export declare const SETTINGS_FILE: string;
 export declare const VERSION_FILE: string;
 /** Current version - MUST match package.json */
-export declare const VERSION = "4.5.5";
+export declare const VERSION = "4.5.6";
 /** Installation result */
 export interface InstallResult {
     success: boolean;

package/dist/installer/index.js

@@ -40,7 +40,7 @@ export const HOOKS_DIR = join(CLAUDE_CONFIG_DIR, 'hooks');
 export const SETTINGS_FILE = join(CLAUDE_CONFIG_DIR, 'settings.json');
 export const VERSION_FILE = join(CLAUDE_CONFIG_DIR, '.olympus-version.json');
 /** Current version - MUST match package.json */
-export const VERSION = '4.5.5';
+export const VERSION = '4.5.6';
 /**
  * Read a content file from the resources/ directory.
  *

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "olympus-ai",
-  "version": "4.5.5",
+  "version": "4.5.6",
   "description": "Olympus: Multi-agent orchestration for Claude Code. Summon the gods of code.",
   "type": "module",
   "main": "dist/index.js",

package/resources/rules/construction/build-and-test.md

@@ -322,11 +322,67 @@ into the build-level report using this schema:
 **Critical failure gate**: If `tests_failed > 0` and `allowFailures` is not set:
 - Block workflow progression
 - Surface the failing unit's `test-report.md` path in the Remediation Guidance section
-- Do NOT proceed to Step 7 until all failures are resolved or `allowFailures` is explicitly
+- Do NOT proceed to Step 6c or Step 7 until all failures are resolved or `allowFailures` is explicitly
   confirmed by the user
 
 ---
 
+## Step 6c: Regression Baseline Coverage Mapping (Conditional)
+
+**Execute when**: `aidlc-docs/{workflow-id}/discovery/regression-baseline.md` exists (brownfield/bugfix pathways only).
+
+**Skip when**: No regression baseline artifact exists (greenfield workflows).
+
+**Purpose**: Close the loop between the behaviors inventoried during Reverse Engineering and the
+tests executed during Construction. Every baseline item must be mapped to at least one covering
+test — or explicitly flagged as a coverage gap.
+
+**Execution**: The orchestrator performs this step directly (no agent delegation needed). Read the
+regression baseline file, extract each checkbox item, then search test results and test files to
+find covering tests for each item.
+
+**Output artifact**: `aidlc-docs/{workflow-id}/construction/build-and-test/baseline-coverage.md`
+
+```markdown
+# Regression Baseline Coverage Mapping
+
+## Summary
+
+| Metric | Value |
+|--------|-------|
+| Total baseline behaviors | [X] |
+| Covered by tests | [X] |
+| Coverage gaps | [X] |
+| Coverage percentage | [X]% |
+
+## Coverage Matrix
+
+| # | Baseline Behavior | Covering Test(s) | Status |
+|---|---|---|---|
+| 1 | [Behavior from regression-baseline.md] | [test file:test name] | Covered |
+| 2 | [Behavior from regression-baseline.md] | [test file:test name] | Covered |
+| 3 | [Behavior from regression-baseline.md] | (none identified) | Gap |
+
+## Coverage Gaps
+
+[For each gap: explain why no test was identified and recommend whether a test should be
+added, or whether the behavior is verified through other means (e.g., manual QA, integration
+test, or framework guarantee)]
+
+### [Gap #]: [Behavior description]
+- **Risk**: [Low/Medium/High — impact if this behavior silently breaks]
+- **Recommendation**: [Add test / Manual QA sufficient / Covered by integration test X]
+```
+
+**Gap handling**: Coverage gaps are **surfaced but non-blocking**. The mapping is informational —
+it gives the user visibility into what is and isn't covered by automated tests. The user decides
+whether to add tests for gaps or accept the risk. Do NOT block workflow progression on gaps alone.
+
+**Include in summary**: Add a Regression Baseline Coverage section to `build-and-test-summary.md`
+(Step 7) summarizing the coverage percentage and listing any gaps.
+
+---
+
 ## Step 7: Generate Test Summary
 
 Create `aidlc-docs/construction/build-and-test/build-and-test-summary.md`:
@@ -366,6 +422,12 @@ Create `aidlc-docs/construction/build-and-test/build-and-test-summary.md`:
 - **Security Tests**: [Pass/Fail/N/A]
 - **E2E Tests**: [Pass/Fail/N/A]
 
+### Regression Baseline Coverage (Brownfield Only)
+- **Baseline Behaviors**: [X] total
+- **Covered by Tests**: [X] ([Y]%)
+- **Coverage Gaps**: [X] — see baseline-coverage.md for details
+[Omit this section if no regression baseline exists]
+
 ## Overall Status
 - **Build**: [Success/Failed]
 - **All Tests**: [Pass/Fail]
@@ -424,7 +486,11 @@ Present comprehensive message:
 3. ✅ integration-test-instructions.md
 4. ✅ performance-test-instructions.md (if applicable)
 5. ✅ [additional test files as needed]
-6. ✅ build-and-test-summary.md
+6. ✅ baseline-coverage.md (brownfield only)
+7. ✅ build-and-test-summary.md
+
+**Regression Baseline**: [X]/[Y] behaviors covered ([Z]%) — [N] gaps identified
+[Omit this line if no regression baseline exists]
 
 Review the summary in aidlc-docs/construction/build-and-test/build-and-test-summary.md
 

package/resources/rules/inception/reverse-engineering.md

@@ -69,6 +69,11 @@ Create `aidlc-docs/{workflowId}/discovery/workspace-scan.json`:
 
 ```json
 {
+  "_meta": {
+    "artifact": "Workspace Scan",
+    "contains": "Raw inventory of packages, languages, frameworks, and structural patterns discovered in the codebase",
+    "reviewFor": "Verify all packages and repos were discovered. Flag any missed projects or incorrectly categorized packages."
+  },
   "scanDate": "[ISO timestamp]",
   "projectPath": "[Project root path]",
   "fileCount": "[Total number of source files]",
@@ -96,6 +101,10 @@ Create `aidlc-docs/{workflowId}/discovery/workspace-scan.json`:
 Create `aidlc-docs/{workflowId}/discovery/analysis-plan.md`:
 
 ```markdown
+> **Artifact**: Analysis Plan
+> **Contains**: Scope, methodology, key questions, and success criteria that guided the AI agents during reverse engineering
+> **Review for**: Confirm the analysis scope and key questions cover what matters to you. These questions are answered by the other discovery artifacts — you do not need to answer them yourself.
+
 # Analysis Plan
 
 ## Scope
@@ -122,6 +131,10 @@ Create `aidlc-docs/{workflowId}/discovery/analysis-plan.md`:
 Create `aidlc-docs/{workflowId}/discovery/current-state-analysis.md`:
 
 ```markdown
+> **Artifact**: Current State Analysis
+> **Contains**: Architecture summary, technology stack, component inventory, data models, and integration points
+> **Review for**: Verify the architecture summary and tech stack match reality. Flag missing components, incorrect relationships, or outdated technology versions.
+
 # Current State Analysis
 
 ## System Overview
@@ -156,6 +169,10 @@ Create `aidlc-docs/{workflowId}/discovery/current-state-analysis.md`:
 Create `aidlc-docs/{workflowId}/discovery/regression-baseline.md`:
 
 ```markdown
+> **Artifact**: Regression Baseline
+> **Contains**: Test coverage status, quality metrics, known issues, technical debt, and behaviors that must be preserved
+> **Review for**: Confirm the baseline behavior list is complete and accurate. Add any missing behaviors that should survive the migration. These items are verified during Build and Test via coverage mapping.
+
 # Regression Baseline
 
 ## Test Coverage Status
@@ -186,6 +203,10 @@ Create `aidlc-docs/{workflowId}/discovery/regression-baseline.md`:
 Create `aidlc-docs/{workflowId}/discovery/change-impact.md`:
 
 ```markdown
+> **Artifact**: Change Impact Analysis
+> **Contains**: Affected components, dependency impact, risk assessment, and regression test strategy for the planned changes
+> **Review for**: Validate the risk levels assigned to each component. Verify all affected areas are identified — especially indirect dependencies the AI may have missed.
+
 # Change Impact Analysis
 
 ## Scope of Proposed Changes
@@ -214,6 +235,10 @@ Create `aidlc-docs/{workflowId}/discovery/change-impact.md`:
 Create `aidlc-docs/{workflowId}/discovery/static-model.md`:
 
 ```markdown
+> **Artifact**: Static Code Model
+> **Contains**: Module hierarchy, data models, design patterns, package dependencies, and file inventory
+> **Review for**: Verify module structure and data model relationships match your understanding. Flag missing components, incorrect dependency directions, or design patterns that aren't actually used.
+
 # Static Code Model
 
 ## Module Hierarchy
@@ -248,6 +273,10 @@ Create `aidlc-docs/{workflowId}/discovery/static-model.md`:
 Create `aidlc-docs/{workflowId}/discovery/dynamic-model.md`:
 
 ```markdown
+> **Artifact**: Dynamic Behavior Model
+> **Contains**: User flows, state management, authentication/authorization, API interactions, error handling, and integration patterns
+> **Review for**: Verify user flows and auth patterns are correctly captured. Flag missing API interactions, incorrect sequence flows, or error handling gaps the AI may have overlooked.
+
 # Dynamic Behavior Model
 
 ## User Flows

package/resources/skills/continue/SKILL.md

@@ -105,6 +105,35 @@ Always read `aidlc-docs/{workflow_id}/aidlc-state.md` to get the human-readable
 
 After loading, provide a brief summary: "Loaded N artifacts from previous stages: [list artifact names]."
 
+### 3b. MANDATORY: Create In-Session Task List
+
+**CRITICAL**: After loading artifacts, you MUST create an in-session task list (using TodoWrite/TaskCreate) with all pipeline stages as items. This provides real-time visual progress tracking in the terminal.
+
+**For Inception Phase resumption**, create tasks for:
+
+- Workspace Detection (Step 5)
+- Reverse Engineering (Step 6)
+- Requirements Analysis (Step 7)
+- User Stories (Step 8)
+- Workflow Planning (Step 9)
+- Application Design (Step 10)
+- Units Generation (Step 11)
+- Inception Complete — Final Audit and Mode Choice (Step 12)
+
+**For Construction Phase resumption**, create tasks for:
+
+- Each remaining unit of work (by name/ID)
+- Build and Test
+- Documentation
+- Construction Complete
+
+**Rules**:
+- Mark already-completed stages as **completed** immediately when creating the list
+- Mark the current resumption stage as **in_progress**
+- Mark remaining stages as **pending**
+- Update task status in real-time as you progress through stages
+- This is IN ADDITION TO the file-based tracking (`aidlc-state.md`, `checkpoint.json`) — both must be updated
+
 ---
 
 ## Step 4: Determine Resume Point

package/resources/skills/plan/SKILL.md

@@ -94,6 +94,31 @@ Scan the `aidlc-docs/` directory for workflow subdirectories (skip the `complete
 
 If there is no active workflow AND no feature description was provided in the input, ask the user: "What would you like to build?" Wait for their response before proceeding.
 
+### 1d. MANDATORY: Create In-Session Task List
+
+**CRITICAL**: Once you have confirmed you are proceeding with a workflow (new or resumed), you MUST create an in-session task list (using TodoWrite/TaskCreate) with all pipeline steps as items. This provides real-time visual progress tracking in the terminal.
+
+Create tasks for each step:
+
+- Confirm workflow name and display welcome (Step 1)
+- Read Trust State (Step 2)
+- Initial Interview via Q&A File (Step 3)
+- Generate intent.md and initialize pipeline (Step 4)
+- Workspace Detection (Step 5)
+- Reverse Engineering (Step 6)
+- Requirements Analysis (Step 7)
+- User Stories (Step 8)
+- Workflow Planning (Step 9)
+- Application Design (Step 10)
+- Units Generation (Step 11)
+- Inception Complete — Final Audit and Mode Choice (Step 12)
+
+**Rules**:
+- Mark each task as **in_progress** when you begin executing that step
+- Mark each task as **completed** immediately when the step finishes (including skipped stages)
+- This is IN ADDITION TO the file-based tracking (`aidlc-state.md`, `checkpoint.json`) — both must be updated
+- When resuming a workflow, mark already-completed steps as **completed** immediately
+
 ---
 
 ## Step 2: Read Trust State