aiwcli 0.12.6 → 0.12.8

package/dist/templates/cc-native/_cc-native/plan-review/agents/plan-review/VERIFY-COVERAGE.md

@@ -0,0 +1,74 @@
+---
+name: verify-coverage
+description: Test coverage mapper who ensures every implementation step has a corresponding verification step. Catches changes with no testing, verification gaps, and the common pattern of testing happy paths while ignoring error paths.
+model: sonnet
+focus: verification coverage mapping
+categories:
+  - code
+  - infrastructure
+  - documentation
+  - design
+  - research
+  - life
+  - business
+---
+
+# Verify Coverage - Plan Review Agent
+
+You map implementation steps to verification steps. Your question: "Is every change covered by a verification step?"
+
+## Your Core Principle
+
+A plan without adequate verification is a plan that assumes success. The most dangerous gap is not a missing feature — it is a missing test. Every implementation step that lacks a corresponding verification step is a step where failure will go undetected. Coverage mapping ensures 1:1 correspondence between "what we change" and "how we confirm it worked."
+
+## Your Expertise
+
+- **Coverage gap detection**: Implementation steps with no corresponding verification
+- **Happy path bias**: Verification that only tests the success case, ignoring error and edge cases
+- **Verification specificity**: Are verification steps concrete enough to execute without interpretation?
+- **Regression awareness**: Do verification steps confirm existing functionality still works after the change?
+- **Coverage completeness**: Does the verification plan cover all dimensions of the change (functionality, performance, security)?
+
+## Review Approach
+
+Build a coverage map between implementation and verification:
+
+1. **List all implementation steps**: Every change the plan makes
+2. **List all verification steps**: Every check the plan includes
+3. **Map 1:1**: For each implementation step, identify its verification step(s)
+4. **Find gaps**: Implementation steps with no verification
+5. **Assess coverage quality**: Do verification steps test the right things?
+
+## Verification Coverage Levels
+
+| Level | Description | Example |
+|-------|-------------|---------|
+| **Full** | Every change verified with specific criteria | "Run `pytest test_auth.py -k test_token_expiry` — 3 tests pass" |
+| **Partial** | Some changes verified, others assumed | "Run the auth tests" (misses schema change verification) |
+| **Minimal** | Only overall functionality checked | "Verify it works" |
+| **None** | Implementation step has no verification | Change with no corresponding check |
+
+## Key Distinction
+
+| Agent | Asks |
+|-------|------|
+| verify-strength | "Would these tests catch a subtle bug?" |
+| **verify-coverage** | **"Is every change covered by a verification step?"** |
+
+## CRITICAL: Single-Turn Review
+
+When reviewing a plan:
+1. Analyze the plan content provided directly (do not use Read, Glob, Grep, or any file tools)
+2. Call StructuredOutput immediately with your assessment
+3. Complete your entire review in one response
+
+Avoid querying external systems, reading codebase files, requesting additional information, or asking follow-up questions.
+
+## Required Output
+
+Call StructuredOutput with exactly these fields:
+- **verdict**: "pass" (verification covers all changes), "warn" (some gaps in verification coverage), or "fail" (critical changes without verification)
+- **summary**: 2-3 sentences explaining verification coverage assessment (minimum 20 characters)
+- **issues**: Array of coverage concerns, each with: severity (high/medium/low), category (e.g., "missing-verification", "happy-path-only", "weak-verification", "no-regression-check"), issue description, suggested_fix (specific verification step to add)
+- **missing_sections**: Verification gaps the plan should address (untested changes, missing edge cases, absent regression checks)
+- **questions**: Verification aspects that need clarification

package/dist/templates/cc-native/_cc-native/plan-review/agents/plan-review/VERIFY-STRENGTH.md

@@ -0,0 +1,69 @@
+---
+name: verify-strength
+description: Test quality analyst who evaluates whether verification steps would catch subtle bugs, not just total failures. Uses mutation testing logic to assess whether tests distinguish correct from almost-correct implementations.
+model: sonnet
+focus: test quality and mutation analysis
+categories:
+  - code
+  - infrastructure
+---
+
+# Verify Strength - Plan Review Agent
+
+You evaluate the quality of verification steps. Your question: "Would these tests catch a subtle bug, or only a total failure?"
+
+## Your Core Principle
+
+Mutation testing (DeMillo et al. 1978) reveals test strength by asking: "If I introduced a small bug, would the tests catch it?" Weak tests pass on both correct and incorrect implementations. Strong tests fail when the implementation is wrong in any way. A plan with 100% coverage but weak assertions is less safe than a plan with 50% coverage but strong assertions.
+
+## Your Expertise
+
+- **Assertion strength evaluation**: Do verification steps check specific expected values, or just "no error"?
+- **Mutation sensitivity**: Would a small change to the implementation (off-by-one, wrong variable, swapped condition) be caught?
+- **Boundary testing**: Do tests exercise boundary conditions where bugs cluster?
+- **Negative testing**: Do tests verify that invalid inputs are rejected, not just that valid inputs succeed?
+- **State verification**: Do tests check the full resulting state, or just the return value?
+
+## Review Approach
+
+For each verification step in the plan, apply mutation logic:
+
+1. **Identify what is being verified**: What specific behavior does this test confirm?
+2. **Apply mental mutations**: If the implementation had an off-by-one error, wrong variable, or swapped condition, would this test catch it?
+3. **Evaluate assertion specificity**: Does the test check a specific expected value, or just "it runs without error"?
+4. **Check boundary coverage**: Are edge cases and boundary values tested?
+5. **Assess negative testing**: Are failure cases and invalid inputs covered?
+
+## Test Strength Levels
+
+| Level | Test Behavior | Example |
+|-------|---------------|---------|
+| **Strong** | Fails on any mutation to the implementation | Checks specific values, boundaries, and error cases |
+| **Moderate** | Catches major bugs but misses subtle ones | Checks return type and approximate value |
+| **Weak** | Only catches total failure | "Assert no error" or "assert result is not null" |
+| **Absent** | No verification at all | Implementation change with no test |
+
+## Key Distinction
+
+| Agent | Asks |
+|-------|------|
+| verify-coverage | "Is every change covered by a verification step?" |
+| **verify-strength** | **"Would these tests catch a subtle bug?"** |
+
+## CRITICAL: Single-Turn Review
+
+When reviewing a plan:
+1. Analyze the plan content provided directly (do not use Read, Glob, Grep, or any file tools)
+2. Call StructuredOutput immediately with your assessment
+3. Complete your entire review in one response
+
+Avoid querying external systems, reading codebase files, requesting additional information, or asking follow-up questions.
+
+## Required Output
+
+Call StructuredOutput with exactly these fields:
+- **verdict**: "pass" (tests would catch subtle bugs), "warn" (some weak assertions), or "fail" (tests would miss common bug patterns)
+- **summary**: 2-3 sentences explaining test strength assessment (minimum 20 characters)
+- **issues**: Array of strength concerns, each with: severity (high/medium/low), category (e.g., "weak-assertion", "no-boundary-test", "missing-negative-test", "mutation-survivor", "state-unchecked"), issue description, suggested_fix (strengthen specific assertion or add test case)
+- **missing_sections**: Test strength improvements the plan should address (boundary tests, negative tests, specific assertions)
+- **questions**: Test quality aspects that need clarification

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/agent-selection.ts

@@ -3,15 +3,15 @@
  * Extracted from cc-native-plan-review.ts.
  */
 
-import { logDebug, logInfo, logWarn } from "../../_shared/lib-ts/base/logger.js";
-import { findExecutable } from "../../_shared/lib-ts/base/subprocess-utils.js";
+import { logDebug, logInfo, logWarn } from "../../../_shared/lib-ts/base/logger.js";
+import { findExecutable } from "../../../_shared/lib-ts/base/subprocess-utils.js";
 
 import type {
   AgentConfig,
   ModelsConfig,
   OrchestratorResult,
   AgentSelectionResult,
-} from "./types.js";
+} from "../../lib-ts/types.js";
 
 const HOOK = "agent-selection";
 

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/corroboration.ts

@@ -28,7 +28,7 @@ import type {
   CorroborationResult,
   CorroboratedGroup,
   SoloFinding,
-} from "./types.js";
+} from "../../lib-ts/types.js";
 
 /**
  * Compute a corroboration-based review decision from all reviewer results.

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/graduation.ts

@@ -8,7 +8,7 @@ import type {
   ReviewerResult,
   CombinedReviewResult,
   IterationAdvancement,
-} from "./types.js";
+} from "../../lib-ts/types.js";
 
 // ---------------------------------------------------------------------------
 // Pass Eligibility

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/orchestrator.ts

@@ -5,8 +5,8 @@
  */
 
 import { OrchestratorClaudeAgent } from "./reviewers/providers/orchestrator-claude-agent.js";
-import type { AgentConfig, OrchestratorConfig, OrchestratorResult } from "./types.js";
-import { logInfo, logWarn } from "../../_shared/lib-ts/base/logger.js";
+import type { AgentConfig, OrchestratorConfig, OrchestratorResult } from "../../lib-ts/types.js";
+import { logInfo, logWarn } from "../../../_shared/lib-ts/base/logger.js";
 
 // Re-export for backward compatibility (moved to reviewers/schemas.ts)
 export { buildOrchestratorSchema } from "./reviewers/schemas.js";

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/output-builder.ts

@@ -3,18 +3,18 @@
  * Extracted from cc-native-plan-review.ts.
  */
 
-import { logInfo } from "../../_shared/lib-ts/base/logger.js";
+import { logInfo } from "../../../_shared/lib-ts/base/logger.js";
 
 import type {
   ReviewerResult,
   CombinedReviewResult,
   CorroborationResult,
   IterationState,
-} from "./types.js";
+} from "../../lib-ts/types.js";
 import {
   buildInlineReviewSummary,
   extractTopIssuesText,
-} from "./artifacts/format.js";
+} from "../../artifacts/lib/format.js";
 import { extractTopIssuesForTracker } from "./graduation.js";
 
 const HOOK = "output-builder";

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/plan-questions.ts

@@ -4,13 +4,13 @@
  * See cc-native-plan-review.ts for integration point (questions gate).
  */
 
-import * as path from "node:path";
+import * as path from "node:path";
 
-import { aggregateAgents } from "./aggregate-agents.js";
+import { aggregateAgents } from "../../lib-ts/aggregate-agents.js";
 import { runAgentReview } from "./reviewers/index.js";
 import { QUESTIONS_SCHEMA } from "./reviewers/schemas.js";
-import type { AgentConfig, ModelsConfig } from "./types.js";
-import { logInfo, logWarn, logError } from "../../_shared/lib-ts/base/logger.js";
+import type { AgentConfig, ModelsConfig } from "../../lib-ts/types.js";
+import { logInfo, logWarn, logError } from "../../../_shared/lib-ts/base/logger.js";
 
 // ---------------------------------------------------------------------------
 // Types
@@ -26,7 +26,7 @@ export interface PlanQuestionsResult {
 // Provider assignment (local copy — avoids circular import from hook)
 // ---------------------------------------------------------------------------
 
-import { findExecutable } from "../../_shared/lib-ts/base/subprocess-utils.js";
+import { findExecutable } from "../../../_shared/lib-ts/base/subprocess-utils.js";
 
 function assignProvider(agent: AgentConfig): AgentConfig {
   // Default to claude provider with the agent's configured model
@@ -60,7 +60,7 @@ export async function runPlanQuestions(
   sessionName?: string,
 ): Promise<PlanQuestionsResult | null> {
   // Load the plan-questions agent from agents/plan-questions/
-  const questionsAgentDir = path.join(aiwcliDir, "_cc-native", "agents", "plan-questions");
+  const questionsAgentDir = path.join(aiwcliDir, "_cc-native", "plan-review", "agents", "plan-questions");
   const agents = aggregateAgents(questionsAgentDir);
 
   if (agents.length === 0) {

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/review-pipeline.ts

@@ -12,11 +12,11 @@ import {
   logInfo,
   logWarn,
   logError,
-} from "../../_shared/lib-ts/base/logger.js";
-import { logDiagnostic } from "../../_shared/lib-ts/base/hook-utils.js";
-import { eprint } from "../../_shared/lib-ts/base/utils.js";
-import { getContextReviewsDir, getContextDir, getReviewFolderPath } from "../../_shared/lib-ts/base/constants.js";
-import { getContextBySessionId, getAllContexts } from "../../_shared/lib-ts/context/context-store.js";
+} from "../../../_shared/lib-ts/base/logger.js";
+import { logDiagnostic } from "../../../_shared/lib-ts/base/hook-utils.js";
+import { eprint } from "../../../_shared/lib-ts/base/utils.js";
+import { getContextReviewsDir, getContextDir, getReviewFolderPath } from "../../../_shared/lib-ts/base/constants.js";
+import { getContextBySessionId, getAllContexts } from "../../../_shared/lib-ts/context/context-store.js";
 
 import type {
   AgentConfig,
@@ -27,16 +27,16 @@ import type {
   IterationState,
   PipelineInput,
   PipelineResult,
-} from "./types.js";
-import { REVIEW_SCHEMA } from "./types.js";
-import type { ContextState } from "../../_shared/lib-ts/types.js";
+} from "../../lib-ts/types.js";
+import { REVIEW_SCHEMA } from "../../lib-ts/types.js";
+import type { ContextState } from "../../../_shared/lib-ts/types.js";
 
-import { discoverPlan } from "./plan-discovery.js";
-import { loadSettings, loadModelsConfig, loadAgentLibrary, DEFAULT_ORCHESTRATOR } from "./settings.js";
+import { discoverPlan } from "../../lib-ts/plan-discovery.js";
+import { loadSettings, loadModelsConfig, loadAgentLibrary, DEFAULT_ORCHESTRATOR } from "../../lib-ts/settings.js";
 import { resolveMandatoryAgents, assignModelsToAgents, selectAgents } from "./agent-selection.js";
 import { computePassEligible, extractTopIssuesForTracker, advanceIterationState } from "./graduation.js";
 import { truncateAgentIssues, overrideVerdictsByThreshold, buildReviewOutput } from "./output-builder.js";
-import { DEFAULT_REVIEW_ITERATIONS, loadIterationState, saveIterationState } from "./state.js";
+import { DEFAULT_REVIEW_ITERATIONS, loadIterationState, saveIterationState } from "../../lib-ts/state.js";
 
 import {
   isPlanAlreadyReviewed,
@@ -46,13 +46,13 @@ import {
   wasPlanQuestionsAgentAsked,
   markQuestionsAsked,
   resetPlanQuestionsAsked,
-} from "./cc-native-state.js";
+} from "../../lib-ts/cc-native-state.js";
 
 import { computeCorroboratedDecision } from "./corroboration.js";
 import { runOrchestrator } from "./orchestrator.js";
-import { debugLog } from "./debug.js";
-import { writeCombinedArtifacts, buildCorroborationReport, buildHighIssuesDocument, writeReviewTracker } from "./artifacts.js";
-import type { ReviewTrackerEntry } from "./artifacts.js";
+import { debugLog } from "../../lib-ts/debug.js";
+import { writeCombinedArtifacts, buildCorroborationReport, buildHighIssuesDocument, writeReviewTracker } from "../../artifacts/lib/index.js";
+import type { ReviewTrackerEntry } from "../../artifacts/lib/index.js";
 import { runAgentReview } from "./reviewers/index.js";
 import { runPlanQuestions } from "./plan-questions.js";
 

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/reviewers/agent.ts

@@ -4,8 +4,8 @@
  * See cc-native-plan-review-spec.md §4.10
  */
 
-import { logWarn } from "../../../_shared/lib-ts/base/logger.js";
-import type { AgentConfig, ReviewerResult, ReviewOptions } from "../types.js";
+import { logWarn } from "../../../../_shared/lib-ts/base/logger.js";
+import type { AgentConfig, ReviewerResult, ReviewOptions } from "../../../lib-ts/types.js";
 import { ClaudeAgent } from "./providers/claude-agent.js";
 import { CodexAgent } from "./providers/codex-agent.js";
 import { GeminiAgent } from "./providers/gemini-agent.js";
@@ -53,16 +53,16 @@ export async function runAgentReview(
     switch (agent.provider) {
       case "codex": {
         reviewer = new CodexAgent(agent, schema, timeout, contextPath, sessionName);
-        break;
+        break;
       }
       case "gemini": {
         reviewer = new GeminiAgent(agent, schema, timeout, contextPath, sessionName);
-        break;
+        break;
       }
       case "claude":
       default: {
         reviewer = new ClaudeAgent(agent, schema, timeout, contextPath, sessionName);
-        break;
+        break;
       }
     }
 

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/reviewers/base/base-agent.ts

@@ -4,10 +4,10 @@
  * Provider-specific implementations (Claude, Codex, Gemini) extend this class.
  */
 
-import { logDebug, logInfo, logWarn, logError } from "../../../../_shared/lib-ts/base/logger.js";
-import { getInternalSubprocessEnv, findExecutable, execFileAsync } from "../../../../_shared/lib-ts/base/subprocess-utils.js";
-import { debugLog, debugRaw } from "../../debug.js";
-import type { AgentConfig } from "../../types.js";
+import { logDebug, logInfo, logWarn, logError } from "../../../../../_shared/lib-ts/base/logger.js";
+import { getInternalSubprocessEnv, findExecutable, execFileAsync } from "../../../../../_shared/lib-ts/base/subprocess-utils.js";
+import { debugLog, debugRaw } from "../../../../lib-ts/debug.js";
+import type { AgentConfig } from "../../../../lib-ts/types.js";
 
 /** Result from execFileAsync */
 export interface ExecResult {

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/reviewers/providers/claude-agent.ts

@@ -3,10 +3,10 @@
  * Uses claude CLI with --json-schema and --system-prompt flags.
  */
 
-import { shellQuoteWin } from "../../../../_shared/lib-ts/base/subprocess-utils.js";
-import { parseCliOutput } from "../../cli-output-parser.js";
-import { coerceToReview } from "../../json-parser.js";
-import type { ReviewerResult } from "../../types.js";
+import { shellQuoteWin } from "../../../../../_shared/lib-ts/base/subprocess-utils.js";
+import { parseCliOutput } from "../../../../lib-ts/cli-output-parser.js";
+import { coerceToReview } from "../../../../lib-ts/json-parser.js";
+import type { ReviewerResult } from "../../../../lib-ts/types.js";
 import { BaseCliAgent } from "../base/base-agent.js";
 import { AGENT_REVIEW_PROMPT_PREFIX } from "../schemas.js";
 import { makeResult } from "../types.js";

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/reviewers/providers/codex-agent.ts

@@ -5,13 +5,13 @@
 
 import * as fs from "node:fs";
 import * as os from "node:os";
-import * as path from "node:path";
+import * as path from "node:path";
 
-import { logDebug, logWarn } from "../../../../_shared/lib-ts/base/logger.js";
-import { getInternalSubprocessEnv, execFileAsync } from "../../../../_shared/lib-ts/base/subprocess-utils.js";
-import { debugLog, debugRaw } from "../../debug.js";
-import { parseJsonMaybe, coerceToReview } from "../../json-parser.js";
-import type { ReviewerResult } from "../../types.js";
+import { logDebug, logWarn } from "../../../../../_shared/lib-ts/base/logger.js";
+import { getInternalSubprocessEnv, execFileAsync } from "../../../../../_shared/lib-ts/base/subprocess-utils.js";
+import { debugLog, debugRaw } from "../../../../lib-ts/debug.js";
+import { parseJsonMaybe, coerceToReview } from "../../../../lib-ts/json-parser.js";
+import type { ReviewerResult } from "../../../../lib-ts/types.js";
 import { BaseCliAgent, type ExecResult } from "../base/base-agent.js";
 import { AGENT_REVIEW_PROMPT_PREFIX } from "../schemas.js";
 import { makeResult } from "../types.js";

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/reviewers/providers/gemini-agent.ts

@@ -3,7 +3,7 @@
  * Placeholder for future implementation.
  */
 
-import type { ReviewerResult } from "../../types.js";
+import type { ReviewerResult } from "../../../../lib-ts/types.js";
 import { BaseCliAgent } from "../base/base-agent.js";
 import { makeResult } from "../types.js";
 

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/reviewers/providers/orchestrator-claude-agent.ts

@@ -3,10 +3,10 @@
  * Analyzes plan complexity and selects reviewer agents via Claude CLI.
  */
 
-import { logDebug } from "../../../../_shared/lib-ts/base/logger.js";
-import { shellQuoteWin } from "../../../../_shared/lib-ts/base/subprocess-utils.js";
-import { parseCliOutput } from "../../cli-output-parser.js";
-import type { AgentConfig, OrchestratorResult, ComplexityCategory } from "../../types.js";
+import { logDebug } from "../../../../../_shared/lib-ts/base/logger.js";
+import { shellQuoteWin } from "../../../../../_shared/lib-ts/base/subprocess-utils.js";
+import { parseCliOutput } from "../../../../lib-ts/cli-output-parser.js";
+import type { AgentConfig, OrchestratorResult, ComplexityCategory } from "../../../../lib-ts/types.js";
 import { BaseCliAgent } from "../base/base-agent.js";
 import { buildOrchestratorSchema, ORCHESTRATOR_SCHEMA } from "../schemas.js";
 

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/reviewers/types.ts

@@ -3,7 +3,7 @@
  * See cc-native-plan-review-spec.md §4.9
  */
 
-import type { ReviewerResult,   Verdict, ReviewData } from "../types.js";
+import type { ReviewerResult,   Verdict, ReviewData } from "../../../lib-ts/types.js";
 
 // Re-export for convenience
 
@@ -19,5 +19,5 @@ export function makeResult(
 ): ReviewerResult {
   return { name, ok, verdict, data: data as Record<string, unknown>, raw, err };
 }
-
-export {type Reviewer, type ReviewerResult, type ReviewOptions} from "../types.js";
+
+export {type Reviewer, type ReviewerResult, type ReviewOptions} from "../../../lib-ts/types.js";

package/dist/templates/cc-native/_cc-native/{lib-ts → plan-review/lib}/verdict.ts

@@ -3,7 +3,7 @@
  * See cc-native-plan-review-spec.md §4.2
  */
 
-import type { ReviewDecisionResult, Verdict } from "./types.js";
+import type { ReviewDecisionResult, Verdict } from "../../lib-ts/types.js";
 
 /**
  * Return the worst verdict from a list.

package/oclif.manifest.json

@@ -416,5 +416,5 @@
       ]
     }
   },
-  "version": "0.12.6"
+  "version": "0.12.8"
 }