aidevops 2.97.0 → 2.98.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -534,6 +534,73 @@ Coordinator (pulse loop)
534
534
 
535
535
  **Subagent index** (`.agent/subagent-index.toon`): Compressed TOON routing table listing all agents, subagents, workflows, and scripts with model tier assignments - enables fast agent discovery without loading full markdown files.
536
536
 
537
+ ## **Advanced Capabilities** (Planned)
538
+
539
+ ### Parallel Agents & Headless Dispatch
540
+
541
+ Run multiple AI sessions concurrently with isolated contexts:
542
+
543
+ | Feature | Description |
544
+ |---------|-------------|
545
+ | **Headless dispatch** | `claude -p` / OpenCode server API for non-interactive execution |
546
+ | **Session management** | Deterministic session IDs, resume with `--resume` |
547
+ | **Memory namespaces** | Per-agent memory isolation with shared access when needed |
548
+ | **Matrix integration** | Chat-triggered dispatch via self-hosted Matrix (optional) |
549
+
550
+ **Architecture:**
551
+
552
+ ```text
553
+ OpenCode Server (opencode serve)
554
+ ├── Session 1 (code-reviewer)
555
+ ├── Session 2 (seo-analyst)
556
+ └── Session 3 (scheduled-task)
557
+
558
+ HTTP API / SSE Events
559
+
560
+ ┌────────┴────────┐
561
+ │ Dispatch Layer │ ← Matrix bot, cron, CLI
562
+ └─────────────────┘
563
+ ```
564
+
565
+ ### Self-Improving Agent System
566
+
567
+ Agents that learn from experience and contribute improvements:
568
+
569
+ | Phase | Description |
570
+ |-------|-------------|
571
+ | **Review** | Analyze memory for success/failure patterns |
572
+ | **Refine** | Generate and apply improvements to agents |
573
+ | **Test** | Validate in isolated OpenCode sessions |
574
+ | **PR** | Contribute to community with privacy filtering |
575
+
576
+ **Safety guardrails:**
577
+ - Worktree isolation for all changes
578
+ - Human approval required for PRs
579
+ - Mandatory privacy filter (secretlint + pattern redaction)
580
+ - Dry-run default, explicit opt-in for PR creation
581
+ - Audit log to memory
582
+
583
+ ### Voice Integration
584
+
585
+ Speech-to-speech AI conversations:
586
+
587
+ | Method | Description |
588
+ |--------|-------------|
589
+ | **VoiceInk + Shortcut** | macOS: transcription → OpenCode API → response |
590
+ | **iPhone Shortcut** | iOS: dictate → HTTP → speak response |
591
+ | **Pipecat STS** | Full voice pipeline: Soniox STT → AI → Cartesia TTS |
592
+
593
+ ### Scheduled Agent Tasks
594
+
595
+ Cron-based agent dispatch for automated workflows:
596
+
597
+ ```bash
598
+ # Example: Daily SEO report at 9am
599
+ 0 9 * * * ~/.aidevops/agents/scripts/droid-helper.sh dispatch "seo-analyst" "Generate daily SEO report"
600
+ ```
601
+
602
+ **See:** [TODO.md](TODO.md) tasks t109-t118 for implementation status.
603
+
537
604
  ## **Requirements**
538
605
 
539
606
  ```bash
@@ -625,6 +692,10 @@ The setup script offers to install these tools automatically.
625
692
  - **[Codacy](https://www.codacy.com/)**: Multi-tool analysis (0 findings)
626
693
  - **[CodeRabbit](https://coderabbit.ai/)**: AI-powered code reviews
627
694
  - **[Snyk](https://snyk.io/)**: Security vulnerability scanning
695
+ - **[Socket](https://socket.dev/)**: Dependency security and supply chain protection
696
+ - **[Sentry](https://sentry.io/)**: Error monitoring and performance tracking
697
+ - **[Secretlint](https://github.com/secretlint/secretlint)**: Detect exposed secrets in code
698
+ - **[OSV Scanner](https://google.github.io/osv-scanner/)**: Google's vulnerability database scanner
628
699
  - **[Qlty](https://qlty.sh/)**: Universal code quality platform (70+ linters, auto-fixes)
629
700
  - **[Gemini Code Assist](https://cloud.google.com/gemini/docs/codeassist/overview)**: Google's AI-powered code completion and review
630
701
 
@@ -1265,6 +1336,10 @@ These are examples of subagents that have supporting MCPs enabled. See `.agent/`
1265
1336
  | `@git-platforms` | GitHub, GitLab, Gitea | gh_grep, context7 |
1266
1337
  | `@sentry` | Error monitoring, Next.js SDK setup | sentry |
1267
1338
  | `@socket` | Dependency security scanning | socket |
1339
+ | `@security-analysis` | AI-powered vulnerability detection (OSV, Ferret, git history) | osv-scanner, gemini-cli-security |
1340
+ | `@secretlint` | Detect exposed secrets in code | (Docker-based) |
1341
+ | `@snyk` | Security vulnerability scanning | (API-based) |
1342
+ | `@auditing` | Code auditing services and security analysis | (API-based) |
1268
1343
  | `@agent-review` | Session analysis, agent improvement (under build-agent/) | (read/write only) |
1269
1344
 
1270
1345
  ### **Setup for OpenCode**
package/VERSION CHANGED
@@ -1 +1 @@
1
- 2.97.0
1
+ 2.98.0
package/aidevops.sh CHANGED
@@ -3,7 +3,7 @@
3
3
  # AI DevOps Framework CLI
4
4
  # Usage: aidevops <command> [options]
5
5
  #
6
- # Version: 2.97.0
6
+ # Version: 2.98.0
7
7
 
8
8
  set -euo pipefail
9
9
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "aidevops",
3
- "version": "2.97.0",
3
+ "version": "2.98.0",
4
4
  "description": "AI DevOps Framework - AI-assisted development workflows, code quality, and deployment automation",
5
5
  "type": "module",
6
6
  "main": "index.js",
@@ -41,6 +41,7 @@
41
41
  },
42
42
  "devDependencies": {
43
43
  "@secretlint/secretlint-rule-preset-recommend": "^11.2.5",
44
+ "@secretlint/secretlint-rule-regexp": "^11.2.5",
44
45
  "@types/bun": "latest",
45
46
  "secretlint": "^11.2.5",
46
47
  "typescript": "^5.0.0"
package/setup.sh CHANGED
@@ -3,7 +3,7 @@
3
3
  # AI Assistant Server Access Framework Setup Script
4
4
  # Helps developers set up the framework for their infrastructure
5
5
  #
6
- # Version: 2.97.0
6
+ # Version: 2.98.0
7
7
  #
8
8
  # Quick Install (one-liner):
9
9
  # bash <(curl -fsSL https://aidevops.dev/install)