@ryuenn3123/agentic-senior-core 6.11.0 → 6.12.0

package/.agents/plugins/agentic-senior-core/skills/asc-reference/SKILL.md

@@ -42,7 +42,11 @@ Grounded in: WCAG 2.2 AA (accessibility), Fowler's Money Pattern (monetary types
 - Match the project's existing styling paradigm (Tailwind, CSS Modules, Vanilla CSS, styled-components, etc.). Do not introduce a new CSS framework or build tool without explicit user confirmation.
 - UI Component Reusability: Primitive UI elements (buttons, inputs, cards, dialogs, badges) must have a single source of truth in the shared component directory (`components/` or `ui/`). Never recreate ad-hoc variants or duplicate JSX structures across individual pages. Extend existing components with props or variants instead of cloning.
 - Design Consistency: Consume shared design tokens, CSS variables, or theme configuration for colors, spacing, and border-radius. Do not hardcode arbitrary raw color hexes or inconsistent spacing that causes visual design drift between pages.
-- Data-fetching components must explicitly handle 3 states: loading, error (with user-facing toast/notification and retry option), and data. Never leave an unhandled error state.
+- Action Feedback & Mutations: Any user-initiated mutation (form submit, delete, upload, toggle) must provide immediate pending feedback (disabled button, inline spinner) and a visible completion notification (toast or alert banner with retry). Never silently swallow mutation errors.
+- Form Validation: Render field errors inline directly next to the affected input with `aria-describedby` and `aria-invalid="true"`. Never use floating toasts for individual form input validation.
+- Data-Fetching State Quad: Data components must explicitly handle 4 states — loading skeleton/spinner, empty state (friendly message + call to action), error fallback (clear message + retry button), and populated data.
+- Component Error Boundaries: Wrap major widgets, dashboards, and routes in localized Error Boundaries with fallback UI cards to prevent a single rendering crash from taking down the entire page.
+- Accessible Notifications: Toast and status messages must use ARIA live regions (`role="status"`, `aria-live="polite"` for non-urgent feedback; `role="alert"` for critical errors). Never steal keyboard focus for toasts.
 - WCAG 2.2 AA accessibility floor. Responsive by default.
 - No placeholder, lorem, or TODO content in production UI.
 
@@ -54,9 +58,15 @@ Grounded in: WCAG 2.2 AA (accessibility), Fowler's Money Pattern (monetary types
 
 ## Resilience
 
-- Every outbound network call has a strict timeout.
+- Every outbound network call has a strict timeout (client and server).
 - Retries use exponential backoff with jitter and max attempt limits.
-- Only retry idempotent operations.
-- Circuit breakers for unhealthy dependencies.
-- Graceful degradation on non-critical dependency failure.
+- Only retry idempotent operations (GET, PUT, DELETE, or requests with `Idempotency-Key`).
+- Dependency Fallback Strategy (Hard vs Soft):
+  - Hard dependencies (core workflow blocks without them): Fail fast, roll back transactions, return structured RFC 9457 error with actionable explanation.
+  - Soft dependencies (non-critical enhancements): Provide graceful fallbacks:
+    - *Static Fallback*: Return safe default values, static placeholders, or empty collections alih-alih melempar exception.
+    - *Stale Cache Fallback*: Serve last-known-good cached state (`stale-while-revalidate`) with an offline/stale indicator.
+    - *Degraded Mode*: Isolate and disable the failing peripheral widget while preserving core user journeys.
+- Circuit breakers for unhealthy dependencies to fail fast and prevent thread/resource exhaustion.
+- Offline Detection: Detect offline network status and notify users before initiating network requests that are guaranteed to fail.
 

package/.agents/plugins/agentic-senior-core/skills/asc-review/SKILL.md

@@ -21,10 +21,11 @@ Grounded in: OWASP Risk Rating Methodology, Google Engineering Practices (code r
 ## Finding Priority Order
 
 1. Correctness, data loss, security, privacy, auth, and permission risks.
-2. Public contract drift: APIs, events, CLI behavior, data model, UI contract, docs.
-3. Missing tests for changed behavior.
-4. Architecture boundary drift and maintainability risk.
-5. Performance and accessibility issues with concrete impact.
+2. Action feedback & resilience: silent mutation failures, missing toasts/banners, hanging spinners, missing fallbacks on remote calls, or missing error boundaries.
+3. Public contract drift: APIs, events, CLI behavior, data model, UI contract, docs.
+4. Missing tests for changed behavior.
+5. Architecture boundary drift and maintainability risk.
+6. Performance and accessibility issues with concrete impact.
 
 ## For Every Finding
 
@@ -37,7 +38,9 @@ Grounded in: OWASP Risk Rating Methodology, Google Engineering Practices (code r
 ### Correctness
 - Changed behavior matches the user request.
 - Existing behavior preserved unless user approved a change.
-- Edge cases, empty states, error paths handled.
+- Edge cases, empty states, error paths, and fallbacks handled.
+- Action feedback: mutations (forms, buttons, mutations) have visible pending indicators and clear completion notifications (toast or banner with retry). No silent failures or hanging spinners.
+- Dependency resilience: remote calls have strict timeouts and soft dependencies have graceful fallbacks (static default, stale cache, or degraded mode). Component crashes are contained by error boundaries.
 
 ### Security
 - External input validated at trust boundaries.

package/bin/agentic-senior-core.js

@@ -8,7 +8,6 @@
  *   uninstall   Remove ASC adapter files from the current project
  *   clean       Remove v4 per-project artifacts (.agent-context/, bridge files)
  *   status      Show detected IDEs and install hints
- *   mcp         Start MCP stdio server
  */
 import { exit } from 'node:process';
 import { readFileSync } from 'node:fs';
@@ -37,7 +36,6 @@ function printUsage() {
   console.log('  uninstall         Remove ASC adapter files and git hooks from this project');
   console.log('  clean             Remove v4 per-project artifacts');
   console.log('  status            Show detected IDEs and install hints');
-  console.log('  mcp               Start MCP stdio server');
   console.log('  --version         Show version');
   console.log('  --help            Show this help');
 }
@@ -92,12 +90,6 @@ async function main() {
     return;
   }
 
-  if (commandArgument === 'mcp') {
-    const { runMcpServerCommand } = await import('../lib/cli/commands/mcp.mjs');
-    await runMcpServerCommand();
-    return;
-  }
-
   console.error(`Unknown command: ${commandArgument}`);
   printUsage();
   exit(1);

package/gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-senior-core",
-  "version": "6.11.0",
+  "version": "6.12.0",
   "description": "Universal AI coding rules. Write code like a staff engineer.",
   "author": "fatidaprilian",
   "license": "MIT",

package/lib/cli/commands/git-hook-generator.mjs

@@ -470,6 +470,13 @@ export function installGlobalGitPreCommitHook({ homeDir = os.homedir() } = {}) {
     fs.mkdirSync(globalHooksDir, { recursive: true });
   }
 
+  // Generate standalone universal runner in global directory for fallback
+  const globalRunnerPath = path.join(globalHooksDir, 'pre-commit-runner.cjs');
+  const runnerScriptContent = generatePreCommitRunnerScript();
+  fs.writeFileSync(globalRunnerPath, runnerScriptContent, { encoding: 'utf8', mode: 0o755 });
+
+  const globalRunnerPosix = globalRunnerPath.replace(/\\/g, '/');
+
   const hookPath = path.join(globalHooksDir, 'pre-commit');
   const dispatcherContent = `#!/bin/sh
 ${ASC_HOOK_HEADER} -- Global Smart Dispatcher
@@ -504,13 +511,16 @@ if [ -n "$LOCAL_HOOK" ]; then
   fi
 fi
 
-# 3. Run ASC workspace pre-commit runner if present
+# 3. Run ASC workspace pre-commit runner if present, or fallback to global runner
 if [ -n "$GIT_ROOT" ] && [ -f "$GIT_ROOT/.asc/hooks/pre-commit-runner.cjs" ]; then
   node "$GIT_ROOT/.asc/hooks/pre-commit-runner.cjs" "$@"
   exit $?
 elif [ -f ".asc/hooks/pre-commit-runner.cjs" ]; then
   node .asc/hooks/pre-commit-runner.cjs "$@"
   exit $?
+elif [ -f "${globalRunnerPosix}" ]; then
+  node "${globalRunnerPosix}" "$@"
+  exit $?
 fi
 
 exit 0
@@ -525,6 +535,6 @@ exit 0
     return { installed: false, hookPath, reason: 'Could not set git config --global core.hooksPath' };
   }
 
-  return { installed: true, hookPath, global: true };
+  return { installed: true, hookPath, runnerPath: globalRunnerPath, global: true };
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ryuenn3123/agentic-senior-core",
-  "version": "6.11.0",
+  "version": "6.12.0",
   "type": "module",
   "description": "Agentic Senior Core: Universal AI coding rules and workflows. Write code like a staff engineer, not a junior.",
   "bin": {
@@ -16,8 +16,6 @@
     "gemini-extension.json",
     "plugin.yaml",
     "__init__.py",
-    "scripts/mcp-server.mjs",
-    "scripts/mcp-server/",
     "scripts/uninstall.js",
     "README.md",
     "LICENSE",

package/plugin.yaml

@@ -1,5 +1,5 @@
 name: agentic-senior-core
-version: 6.11.0
+version: 6.12.0
 description: Universal AI coding rules. Write code like a staff engineer.
 author: fatidaprilian
 provides_hooks:

package/lib/cli/commands/mcp.mjs

@@ -1,3 +0,0 @@
-export async function runMcpServerCommand() {
-  await import('../../../scripts/mcp-server.mjs');
-}

package/scripts/mcp-server/constants.mjs

@@ -1,57 +0,0 @@
-// @ts-check
-
-import { existsSync, readFileSync } from 'node:fs';
-import { dirname, resolve } from 'node:path';
-import { fileURLToPath } from 'node:url';
-
-const SCRIPT_FILE_PATH = fileURLToPath(import.meta.url);
-export const REPOSITORY_ROOT = resolve(dirname(SCRIPT_FILE_PATH), '..', '..');
-export const STATE_DIRECTORY = resolve(REPOSITORY_ROOT, '.agent-context', 'state');
-export const DEFAULT_PROTOCOL_VERSION = '2024-11-05';
-export const DEFAULT_FETCH_TIMEOUT_MS = 15000;
-export const DEFAULT_FETCH_MAX_CHARS = 6000;
-export const MAX_FETCH_MAX_CHARS = 20000;
-export const DEFAULT_TREND_WINDOW_DAYS = 90;
-export const MAX_TREND_PACKAGES = 10;
-export const FALLBACK_PACKAGE_VERSION = '0.0.0-local';
-
-// IMPORTANT: This version extraction logic is intentionally duplicated from lib/cli/constants.mjs.
-// The MCP server is designed to be copied directly into target user workspaces where
-// the original package.json may not exist in the parent tree. This try/catch fallback
-// ensures the server can still run standalone without crashing if package.json is missing.
-function resolvePackageVersion() {
-  try {
-    const parsedPackageManifest = JSON.parse(
-      readFileSync(resolve(REPOSITORY_ROOT, 'package.json'), 'utf8')
-    );
-    const rawVersion = typeof parsedPackageManifest?.version === 'string'
-      ? parsedPackageManifest.version.trim()
-      : '';
-
-    return rawVersion || FALLBACK_PACKAGE_VERSION;
-  } catch {
-    return FALLBACK_PACKAGE_VERSION;
-  }
-}
-
-export const PACKAGE_VERSION = resolvePackageVersion();
-
-export const TEST_SUITE_ARGS = {
-  adapter: ['--test', './tests/adapter.test.mjs'],
-};
-
-export const INTERNAL_SCRIPT_PATHS = {};
-
-function getAvailableTestSuites() {
-  return Object.entries(TEST_SUITE_ARGS)
-    .filter(([, commandArguments]) => (
-      Array.isArray(commandArguments)
-      && commandArguments.length > 1
-      && commandArguments
-        .slice(1)
-        .every((relativeTestPath) => existsSync(resolve(REPOSITORY_ROOT, relativeTestPath)))
-    ))
-    .map(([suiteName]) => suiteName);
-}
-
-export const AVAILABLE_TEST_SUITES = getAvailableTestSuites();

package/scripts/mcp-server/tool-registry.mjs

@@ -1,204 +0,0 @@
-// @ts-check
-
-import { existsSync } from 'node:fs';
-import { AVAILABLE_TEST_SUITES, INTERNAL_SCRIPT_PATHS } from './constants.mjs';
-
-export function buildToolDefinitions() {
-  const toolDefinitions = [];
-
-  if (existsSync(INTERNAL_SCRIPT_PATHS.validate)) {
-    toolDefinitions.push({
-      name: 'validate',
-      description: 'Run repository validation checks.',
-      inputSchema: {
-        type: 'object',
-        properties: {},
-        additionalProperties: false,
-      },
-    });
-  }
-
-  if (AVAILABLE_TEST_SUITES.length > 0) {
-    toolDefinitions.push({
-      name: 'test',
-      description: 'Run test suites (full or targeted).',
-      inputSchema: {
-        type: 'object',
-        properties: {
-          suite: {
-            type: 'string',
-            enum: AVAILABLE_TEST_SUITES,
-            description: 'Target test suite. Defaults to the first available suite.',
-          },
-        },
-        additionalProperties: false,
-      },
-    });
-  }
-
-  if (existsSync(INTERNAL_SCRIPT_PATHS.release_gate)) {
-    toolDefinitions.push({
-      name: 'release_gate',
-      description: 'Run release gate checks.',
-      inputSchema: {
-        type: 'object',
-        properties: {},
-        additionalProperties: false,
-      },
-    });
-  }
-
-  if (existsSync(INTERNAL_SCRIPT_PATHS.forbidden_content_check)) {
-    toolDefinitions.push({
-      name: 'forbidden_content_check',
-      description: 'Run forbidden content scan used by publish gate.',
-      inputSchema: {
-        type: 'object',
-        properties: {},
-        additionalProperties: false,
-      },
-    });
-  }
-
-  toolDefinitions.push(
-    {
-      name: 'lookup_rule',
-      description: 'Look up a canonical .agent-context rule section by stable rule ID.',
-      inputSchema: {
-        type: 'object',
-        properties: {
-          ruleId: {
-            type: 'string',
-            description: 'Stable rule section ID, such as ARCH-003 or API-001.',
-          },
-        },
-        required: ['ruleId'],
-        additionalProperties: false,
-      },
-    },
-    {
-      name: 'validate_against_rules',
-      description: 'Validate that cited rule IDs resolve to canonical rule sections.',
-      inputSchema: {
-        type: 'object',
-        properties: {
-          ruleIds: {
-            type: 'array',
-            items: { type: 'string' },
-            description: 'Rule IDs cited by a response, plan, or review.',
-          },
-          summary: {
-            type: 'string',
-            description: 'Optional one-line context for the validation request.',
-          },
-        },
-        required: ['ruleIds'],
-        additionalProperties: false,
-      },
-    },
-    {
-      name: 'audit_compliance',
-      description: 'Run a lightweight compliance audit over cited rule IDs and scope labels.',
-      inputSchema: {
-        type: 'object',
-        properties: {
-          ruleIds: {
-            type: 'array',
-            items: { type: 'string' },
-            description: 'Rule IDs used as the compliance basis.',
-          },
-          scope: {
-            type: 'string',
-            description: 'Optional changed scope label, such as api, security, testing, architecture, ui, or release.',
-          },
-        },
-        required: ['ruleIds'],
-        additionalProperties: false,
-      },
-    },
-    {
-      name: 'research_fetch',
-      description: 'Fetch external documentation/news content and return query-focused excerpts with citation metadata.',
-      inputSchema: {
-        type: 'object',
-        properties: {
-          url: {
-            type: 'string',
-            description: 'Absolute HTTP/HTTPS URL to fetch.',
-          },
-          query: {
-            type: 'string',
-            description: 'Optional search query used to extract focused excerpts.',
-          },
-          maxChars: {
-            type: 'integer',
-            description: 'Maximum characters to return when query is not provided (default 6000, max 20000).',
-          },
-        },
-        required: ['url'],
-        additionalProperties: false,
-      },
-    },
-    {
-      name: 'trend_snapshot',
-      description: 'Generate ecosystem trend snapshot from npm registry metadata with source timestamps.',
-      inputSchema: {
-        type: 'object',
-        properties: {
-          packages: {
-            type: 'array',
-            items: { type: 'string' },
-            description: 'Package names to inspect (max 10).',
-          },
-          windowDays: {
-            type: 'integer',
-            description: 'Release activity window in days (default 90).',
-          },
-        },
-        required: ['packages'],
-        additionalProperties: false,
-      },
-    },
-    {
-      name: 'state_read',
-      description: 'Read a file from .agent-context/state for cross-session continuity.',
-      inputSchema: {
-        type: 'object',
-        properties: {
-          path: {
-            type: 'string',
-            description: 'Path relative to .agent-context/state, such as memory-continuity-benchmark.json.',
-          },
-        },
-        required: ['path'],
-        additionalProperties: false,
-      },
-    },
-    {
-      name: 'state_write',
-      description: 'Write a file under .agent-context/state for cross-session continuity updates.',
-      inputSchema: {
-        type: 'object',
-        properties: {
-          path: {
-            type: 'string',
-            description: 'Path relative to .agent-context/state.',
-          },
-          content: {
-            type: 'string',
-            description: 'UTF-8 content to write.',
-          },
-          mode: {
-            type: 'string',
-            enum: ['overwrite', 'append'],
-            description: 'Write mode. Defaults to overwrite.',
-          },
-        },
-        required: ['path', 'content'],
-        additionalProperties: false,
-      },
-    },
-  );
-
-  return toolDefinitions;
-}