aidevops 2.101.0 → 2.103.0

package/README.md

@@ -93,7 +93,7 @@ The result: AI agents that work *with* your development process, not around it.
 
 - Primary agents (Build+, SEO, Marketing, etc.) with @plan-plus subagent for planning-only mode
 - 614+ subagent markdown files organized by domain
-- 164 helper scripts in `.agent/scripts/`
+- 167 helper scripts in `.agent/scripts/`
 - 28 slash commands for common workflows
 
 <!-- AI-CONTEXT-END -->
@@ -423,6 +423,14 @@ See `.agent/tools/terminal/terminal-title.md` for customization options.
 - Git platform management, domain purchasing, setup automation
 - [WordPress](https://wordpress.org/) management, credential security, code auditing
 
+**Autonomous Orchestration:**
+
+- **Supervisor** - SQLite state machine dispatches tasks to parallel AI agents with retry cycles, batch management, and cron scheduling
+- **Runners** - Named headless agent instances with persistent identity, instructions, and memory namespaces
+- **`/runners` command** - Batch dispatch from task IDs, PR URLs, or descriptions with concurrency control and progress monitoring
+- **Mailbox** - SQLite-backed inter-agent messaging for coordination across parallel sessions
+- **Worktree isolation** - Each agent works on its own branch in a separate directory, no merge conflicts
+
 **Unified Interface:**
 
 - Standardized commands across all providers
@@ -432,7 +440,8 @@ See `.agent/tools/terminal/terminal-title.md` for customization options.
 **Quality Control & Monitoring:**
 
 - **Multi-Platform Analysis**: SonarCloud, CodeFactor, Codacy, CodeRabbit, Qlty, Gemini Code Assist, Snyk
-- **Performance Auditing**: PageSpeed Insights, Lighthouse, Core Web Vitals (`/performance` command)
+- **Performance Auditing**: PageSpeed Insights, Lighthouse, WebPageTest, Core Web Vitals (`/performance` command)
+- **SEO Toolchain**: 13 SEO subagents including Semrush, Ahrefs, ContentKing, Screaming Frog, Bing Webmaster Tools, Rich Results Test, programmatic SEO, analytics tracking, schema validation
 - **SEO Debugging**: Open Graph validation, favicon checker, social preview testing
 - **Email Deliverability**: SPF/DKIM/DMARC/MX validation, blacklist checking
 - **Uptime Monitoring**: Updown.io integration for website and SSL monitoring
@@ -480,7 +489,7 @@ aidevops implements proven agent design patterns identified by [Lance Martin (La
 
 | Pattern | Description | aidevops Implementation |
 |---------|-------------|------------------------|
-| **Give Agents a Computer** | Filesystem + shell for persistent context | `~/.aidevops/.agent-workspace/`, 164 helper scripts |
+| **Give Agents a Computer** | Filesystem + shell for persistent context | `~/.aidevops/.agent-workspace/`, 167 helper scripts |
 | **Multi-Layer Action Space** | Few tools, push actions to computer | Per-agent MCP filtering (~12-20 tools each) |
 | **Progressive Disclosure** | Load context on-demand | Subagent routing with content summaries, YAML frontmatter, read-on-demand |
 | **Offload Context** | Write results to filesystem | `.agent-workspace/work/[project]/` for persistence |
@@ -506,7 +515,7 @@ Run multiple AI agents in parallel on separate branches, coordinated through a l
 ```text
 Coordinator (pulse loop)
 ├── Agent Registry (TOON format - who's active, what branch, idle/busy)
-├── Mailbox System (file-based, per-agent inbox/outbox)
+├── Mailbox System (SQLite WAL-mode, indexed queries)
 │   ├── task_assignment → worker inbox
 │   ├── status_report → coordinator outbox
 │   └── broadcast → all agents
@@ -517,8 +526,9 @@ Coordinator (pulse loop)
 
 | Component | Script | Purpose |
 |-----------|--------|---------|
-| Mailbox | `mail-helper.sh` | TOON-based inter-agent messaging (send, check, broadcast, archive) |
+| Mailbox | `mail-helper.sh` | SQLite-backed inter-agent messaging (send, check, broadcast, archive) |
 | Coordinator | `coordinator-helper.sh` | Stateless pulse loop: collect reports, dispatch tasks, track idle workers |
+| Supervisor | `supervisor-helper.sh` | Autonomous multi-task orchestration with SQLite state machine, batches, retry cycles, cron scheduling, auto-pickup from TODO.md |
 | Registry | `mail-helper.sh register` | Agent registration with role, branch, worktree, heartbeat |
 | Model routing | `model-routing.md`, `/route` | Cost-aware 5-tier routing guidance (haiku/flash/sonnet/pro/opus) |
 
@@ -527,8 +537,8 @@ Coordinator (pulse loop)
 1. Each agent registers on startup (`mail-helper.sh register --role worker`)
 2. Coordinator runs periodic pulses (`coordinator-helper.sh pulse`)
 3. Pulse collects status reports, dispatches queued tasks to idle workers
-4. Agents send completion reports back via outbox
-5. File locking (`noclobber` + retry) prevents race conditions
+4. Agents send completion reports back via mailbox
+5. SQLite WAL mode + `busy_timeout` handles concurrent access (79x faster than previous file-based system)
 
 **Compaction plugin** (`.agent/plugins/opencode-aidevops/`): When OpenCode compacts context (at ~200K tokens), the plugin injects current session state - agent registry, pending mailbox messages, git context, and relevant memories - ensuring continuity across compaction boundaries.
 
@@ -536,7 +546,9 @@ Coordinator (pulse loop)
 
 **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.
 
-## **Advanced Capabilities** (Planned)
+## **Autonomous Orchestration & Parallel Agents**
+
+**Why this matters:** Long-running tasks -- batch PR reviews, multi-site SEO audits, large refactors -- are where AI agents deliver the most value. Instead of babysitting one task at a time, the supervisor dispatches work to parallel agents, each in its own git worktree, with automatic retry, progress tracking, and batch completion reporting.
 
 ### Parallel Agents & Headless Dispatch
 
@@ -589,7 +601,23 @@ OpenCode Server (opencode serve)
 
 **Example runner templates:** [code-reviewer](.agent/tools/ai-assistants/runners/code-reviewer.md), [seo-analyst](.agent/tools/ai-assistants/runners/seo-analyst.md) - copy and customize for your own runners.
 
-**See:** [headless-dispatch.md](.agent/tools/ai-assistants/headless-dispatch.md) for full documentation including parallel vs sequential decision guide, SDK examples, CI/CD integration, and custom agent configuration.
+**Matrix bot dispatch** (optional): Bridge Matrix chat rooms to runners for chat-triggered AI.
+
+```bash
+# Setup Matrix bot (interactive wizard)
+matrix-dispatch-helper.sh setup
+
+# Map rooms to runners
+matrix-dispatch-helper.sh map '!dev-room:server' code-reviewer
+matrix-dispatch-helper.sh map '!seo-room:server' seo-analyst
+
+# Start bot (daemon mode)
+matrix-dispatch-helper.sh start --daemon
+
+# In Matrix room: "!ai Review src/auth.ts for security issues"
+```
+
+**See:** [headless-dispatch.md](.agent/tools/ai-assistants/headless-dispatch.md) for full documentation including parallel vs sequential decision guide, SDK examples, CI/CD integration, and custom agent configuration. [matrix-bot.md](.agent/services/communications/matrix-bot.md) for Matrix bot setup including Cloudron Synapse guide.
 
 ### Self-Improving Agent System
 
@@ -609,6 +637,30 @@ Agents that learn from experience and contribute improvements:
 - Dry-run default, explicit opt-in for PR creation
 - Audit log to memory
 
+### Agent Testing Framework
+
+Test agent behavior through isolated AI sessions with automated validation:
+
+```bash
+# Create a test suite
+agent-test-helper.sh create my-tests
+
+# Run tests (auto-detects claude or opencode CLI)
+agent-test-helper.sh run my-tests
+
+# Quick single-prompt test
+agent-test-helper.sh run-one "What tools do you have?" --expect "bash"
+
+# Before/after comparison for agent changes
+agent-test-helper.sh baseline my-tests   # Save current behavior
+# ... modify agents ...
+agent-test-helper.sh compare my-tests    # Detect regressions
+```
+
+Test suites are JSON files with prompts and validation rules (`expect_contains`, `expect_not_contains`, `expect_regex`, `min_length`, `max_length`). Results are saved for historical tracking.
+
+**See:** `agent-testing.md` subagent for full documentation and example test suites.
+
 ### Voice Integration
 
 Speech-to-speech AI conversations:
@@ -739,17 +791,20 @@ The setup script offers to install these tools automatically.
 ### **Document Processing & OCR**
 
 - **[LibPDF](https://libpdf.dev/)**: PDF form filling, digital signatures (PAdES B-B/T/LT/LTA), encryption, merge/split, text extraction
+- **[MinerU](https://github.com/opendatalab/MinerU)**: Layout-aware PDF-to-markdown/JSON conversion with OCR (109 languages), formula-to-LaTeX, and table extraction (53k+ stars, AGPL-3.0)
 - **[Unstract](https://github.com/Zipstack/unstract)**: LLM-powered structured data extraction from unstructured documents (PDF, images, DOCX)
 - **[GLM-OCR](https://ollama.com/library/glm-ocr)**: Local OCR via Ollama - purpose-built for document text extraction (tables, forms, complex layouts) with zero cloud dependency
 
-**OCR Tool Selection:**
+**PDF/OCR Tool Selection:**
 
 | Need | Tool | Why |
 |------|------|-----|
+| **Complex PDF to markdown** | MinerU | Layout-aware, formulas, tables, 109-language OCR |
 | **Quick text extraction** | GLM-OCR | Local, fast, no API keys, privacy-first |
 | **Structured JSON output** | Unstract | Schema-based extraction, complex documents |
 | **Screen/window OCR** | Peekaboo + GLM-OCR | `peekaboo image --analyze --model ollama/glm-ocr` |
 | **PDF text extraction** | LibPDF | Native PDF parsing, no AI needed |
+| **Simple format conversion** | Pandoc | Lightweight, broad format support |
 
 **Quick start:**
 
@@ -764,6 +819,7 @@ See `.agent/tools/ocr/glm-ocr.md` for batch processing, PDF workflows, and Peeka
 
 - **[Twilio](https://www.twilio.com/)**: SMS, voice calls, WhatsApp, phone verification (Verify API), call recording & transcription
 - **[Telfon](https://mytelfon.com/)**: Twilio-powered cloud phone system with iOS/Android/Chrome apps for end-user calling interface
+- **[Matrix](https://matrix.org/)**: Self-hosted chat with bot integration for AI runner dispatch (`matrix-dispatch-helper.sh`)
 
 ### **Animation & Video**
 
@@ -775,6 +831,7 @@ See `.agent/tools/ocr/glm-ocr.md` for batch processing, PDF workflows, and Peeka
 
 - **[PageSpeed Insights](https://pagespeed.web.dev/)**: Website performance auditing
 - **[Lighthouse](https://developer.chrome.com/docs/lighthouse/)**: Comprehensive web app analysis
+- **[WebPageTest](https://www.webpagetest.org/)**: Real-world performance testing from 40+ global locations with filmstrip, waterfall, and Core Web Vitals
 - **[Updown.io](https://updown.io/)**: Website uptime and SSL monitoring
 
 ### **AI & Documentation**
@@ -826,6 +883,9 @@ These use direct API calls via curl, avoiding MCP server startup entirely:
 | [Ahrefs](https://ahrefs.com/api) | SEO analysis & backlinks | Yes |
 | [DataForSEO](https://dataforseo.com/) | SERP, keywords, backlinks, on-page | Yes |
 | [Serper](https://serper.dev/) | Google Search API (web, images, news) | Yes |
+| [Semrush](https://www.semrush.com/api-documentation/) | Domain analytics, keywords, backlinks, competitor research | Yes |
+| [ContentKing](https://www.contentkingapp.com/) | Real-time SEO monitoring, change tracking, issues | Yes |
+| [WebPageTest](https://www.webpagetest.org/) | Real-world performance testing from 40+ global locations | Yes |
 | [Hostinger](https://developers.hostinger.com/) | Hosting management | Yes |
 | [NeuronWriter](https://neuronwriter.com/) | Content optimization & NLP analysis | Yes |
 
@@ -875,6 +935,7 @@ These use direct API calls via curl, avoiding MCP server startup entirely:
 **Data Extraction:**
 
 - [Outscraper](https://outscraper.com/) - Google Maps, business data, reviews extraction
+- [curl-copy](.agent/tools/browser/curl-copy.md) - Authenticated scraping via DevTools "Copy as cURL" (no browser automation needed)
 
 **Performance & Security:**
 
@@ -945,7 +1006,7 @@ These catch formatting and syntax issues during editing, reducing preflight/post
 
 ## **Browser Automation**
 
-8 browser tools + anti-detect stack, benchmarked and integrated for AI-assisted web automation, dev testing, data extraction, and bot detection evasion. Agents automatically select the optimal tool based on task requirements.
+8 browser tools + anti-detect stack + device emulation, benchmarked and integrated for AI-assisted web automation, dev testing, mobile/responsive testing, data extraction, and bot detection evasion. Agents automatically select the optimal tool based on task requirements.
 
 ### Performance Benchmarks
 
@@ -967,6 +1028,7 @@ Tested on macOS ARM64, all headless, warm daemon:
 | **Proxy/VPN** | Full | No | Via args | No | Full | Your browser | Via args |
 | **Extensions** | Yes (persistent) | No | Yes (profile) | No | No | Yes (yours) | Possible |
 | **Password managers** | Partial (needs unlock) | No | Partial | No | No | **Yes** (unlocked) | No |
+| **Device emulation** | **Full** (100+ devices) | No | No | No | No | No | Via Playwright |
 | **Parallel sessions** | 5 ctx/2.1s | --session | Shared | 3 sess/2.0s | arun_many 1.7x | Shared | Per-instance |
 | **Session persistence** | storageState | Profile dir | Profile dir | state save/load | user_data_dir | Your browser | Per-instance |
 | **Tracing** | Full API | Built-in CLI | Via Playwright | Via Playwright | No | Via CDP | Via Playwright |
@@ -989,6 +1051,8 @@ Tested on macOS ARM64, all headless, warm daemon:
 | **iOS mobile testing** | agent-browser | Real Safari in iOS Simulator (macOS only) |
 | **Unknown pages** | Stagehand | Natural language, self-healing |
 | **Performance debugging** | Chrome DevTools MCP | Companion tool, pairs with any browser |
+| **Mobile/tablet emulation** | Playwright | 100+ device presets, viewport, touch, geolocation, locale |
+| **Authenticated one-off scrape** | curl-copy | DevTools "Copy as cURL" → paste to terminal/AI |
 | **Bot detection evasion** | Anti-detect stack | Camoufox (full) or rebrowser-patches (quick) |
 | **Multi-account** | Browser profiles | Persistent fingerprint + proxy per account |
 
@@ -1005,6 +1069,37 @@ Agents use lightweight methods instead of expensive vision API calls:
 
 See [`.agent/tools/browser/browser-automation.md`](.agent/tools/browser/browser-automation.md) for the full decision tree and [`browser-benchmark.md`](.agent/tools/browser/browser-benchmark.md) for reproducible benchmark scripts.
 
+### Device Emulation
+
+Test responsive layouts and mobile-specific behavior using Playwright's built-in device emulation. Supports 100+ device presets with viewport, user agent, touch events, device scale factor, geolocation, locale/timezone, permissions, color scheme, offline mode, and network throttling.
+
+**Common device presets:**
+
+| Device | Viewport | Scale | Touch |
+|--------|----------|-------|-------|
+| `iPhone 15` | 393x852 | 3 | Yes |
+| `iPad Pro 11` | 834x1194 | 2 | Yes |
+| `Pixel 7` | 412x915 | 2.625 | Yes |
+| `Galaxy S9+` | 320x658 | 4.5 | Yes |
+| `Desktop Chrome` | 1280x720 | 1 | No |
+
+**Emulation capabilities:**
+
+| Feature | Example |
+|---------|---------|
+| **Device presets** | `devices['iPhone 13']` - viewport, UA, touch, scale |
+| **Viewport/HiDPI** | `viewport: { width: 2560, height: 1440 }, deviceScaleFactor: 2` |
+| **Geolocation** | `geolocation: { longitude: -74.006, latitude: 40.7128 }` |
+| **Locale/timezone** | `locale: 'de-DE', timezoneId: 'Europe/Berlin'` |
+| **Color scheme** | `colorScheme: 'dark'` |
+| **Offline mode** | `offline: true` |
+| **Permissions** | `permissions: ['geolocation', 'notifications']` |
+| **Network throttling** | CDP-based Slow 3G / Fast 3G emulation |
+
+**Recipes included:** Responsive breakpoint testing, multi-device parallel testing, touch gesture testing, geolocation-dependent features, dark mode visual regression, and network condition emulation.
+
+See [`.agent/tools/browser/playwright-emulation.md`](.agent/tools/browser/playwright-emulation.md) for complete documentation with code examples.
+
 ### Anti-Detect Browser
 
 Open-source alternative to AdsPower, GoLogin, and OctoBrowser for multi-account automation and bot detection evasion.
@@ -1596,6 +1691,7 @@ Configure time tracking per-repo via `.aidevops.json`.
 | `/session-review` | Review session for completeness and capture learnings |
 | `/full-loop` | End-to-end development loop (task → preflight → PR → postflight → deploy) |
 | `/preflight-loop` | Run preflight checks iteratively until all pass |
+| `/runners` | Batch dispatch tasks to parallel agents (task IDs, PR URLs, or descriptions) |
 | `/log-issue-aidevops` | Report issues with aidevops (gathers diagnostics, checks duplicates, creates GitHub issue) |
 
 ### Ralph Loop - Iterative AI Development
@@ -1755,7 +1851,9 @@ See `.agent/workflows/session-manager.md` for the complete guide.
 | `/remember {content}` | Store a memory with AI-assisted categorization |
 | `/recall {query}` | Search memories by keyword |
 | `/recall --recent` | Show 10 most recent memories |
+| `/recall --auto-only` | Search only auto-captured memories |
 | `/recall --stats` | Show memory statistics |
+| `/memory-log` | Show recent auto-captured memories |
 | `/patterns {task}` | Show success/failure patterns for a task type |
 | `/route {task}` | Suggest optimal model tier for a task |
 
@@ -1794,11 +1892,16 @@ pattern-tracker-helper.sh record --outcome success --task-type bugfix \
 pattern-tracker-helper.sh suggest "refactor the auth middleware"
 ```
 
+**Auto-capture:** AI agents automatically store memories using `--auto` flag when they detect working solutions, failed approaches, or decisions. Privacy filters strip `<private>` tags and reject secret patterns.
+
 **CLI usage:**
 
 ```bash
 # Store a memory
-~/.aidevops/agents/scripts/memory-helper.sh store "WORKING_SOLUTION" "Fixed CORS with nginx headers" "cors,nginx"
+~/.aidevops/agents/scripts/memory-helper.sh store --type "WORKING_SOLUTION" --content "Fixed CORS with nginx headers" --tags "cors,nginx"
+
+# Store auto-captured memory (from AI agent)
+~/.aidevops/agents/scripts/memory-helper.sh store --auto --content "Fixed CORS with nginx headers" --type WORKING_SOLUTION
 
 # Recall memories (keyword search - default)
 ~/.aidevops/agents/scripts/memory-helper.sh recall "cors"
@@ -1806,7 +1909,10 @@ pattern-tracker-helper.sh suggest "refactor the auth middleware"
 # Recall memories (semantic similarity - opt-in)
 ~/.aidevops/agents/scripts/memory-helper.sh recall "cors" --semantic
 
-# View statistics
+# Show auto-capture log
+~/.aidevops/agents/scripts/memory-helper.sh log
+
+# View statistics (includes auto-capture counts)
 ~/.aidevops/agents/scripts/memory-helper.sh stats
 
 # Maintenance
@@ -1974,7 +2080,8 @@ bash .agent/scripts/continue-cli.sh review
 **Agent Guides** (in `.agent/`):
 
 - **[API Integrations](.agent/aidevops/api-integrations.md)** - Service APIs
-- **[Browser Automation](.agent/tools/browser/browser-automation.md)** - 6 tools + anti-detect stack: decision tree, parallel, extensions, fingerprinting
+- **[Browser Automation](.agent/tools/browser/browser-automation.md)** - 8 tools + anti-detect stack: decision tree, parallel, extensions, fingerprinting
+- **[Device Emulation](.agent/tools/browser/playwright-emulation.md)** - Mobile/tablet testing: 100+ device presets, viewport, geolocation, locale, dark mode
 - **[Anti-Detect Browser](.agent/tools/browser/anti-detect-browser.md)** - Multi-profile management, fingerprint rotation, proxy integration
 - **[Web Performance](.agent/tools/performance/performance.md)** - Core Web Vitals, network dependencies, accessibility (Chrome DevTools MCP)
 - **[PageSpeed](.agent/tools/browser/pagespeed.md)** - Lighthouse CLI and PageSpeed Insights API
@@ -2043,7 +2150,7 @@ credential-helper.sh set GITHUB_TOKEN ghp_xxx
 echo "client-acme" > .aidevops-tenant
 
 # Export for scripts
-eval $(credential-helper.sh export)
+source <(credential-helper.sh export)
 ```
 
 **Resolution priority:** Project `.aidevops-tenant` → Global active tenant → Default

package/VERSION

@@ -1 +1 @@
-2.101.0
+2.103.0

package/aidevops.sh

@@ -3,7 +3,7 @@
 # AI DevOps Framework CLI
 # Usage: aidevops <command> [options]
 #
-# Version: 2.101.0
+# Version: 2.103.0
 
 set -euo pipefail
 
@@ -545,6 +545,17 @@ cmd_update() {
         
         if [[ "$local_hash" == "$remote_hash" ]]; then
             print_success "Framework already up to date!"
+            
+            # Even when repo is current, deployed agents may be stale
+            # (e.g., previous setup.sh was interrupted or failed)
+            local repo_version deployed_version
+            repo_version=$(cat "$INSTALL_DIR/VERSION" 2>/dev/null || echo "unknown")
+            deployed_version=$(cat "$HOME/.aidevops/agents/VERSION" 2>/dev/null || echo "none")
+            if [[ "$repo_version" != "$deployed_version" ]]; then
+                print_warning "Deployed agents ($deployed_version) don't match repo ($repo_version)"
+                print_info "Re-running setup to sync agents..."
+                bash "$INSTALL_DIR/setup.sh"
+            fi
         else
             print_info "Pulling latest changes..."
             if git pull --ff-only origin main; then
@@ -1322,11 +1333,25 @@ cmd_upgrade_planning() {
             # Find the Backlog TOON block and insert tasks after its closing -->
             if grep -q "<!--TOON:backlog" "$todo_file"; then
                 local temp_file="${todo_file}.merge"
-                awk -v tasks="$existing_tasks" '
-                    /<!--TOON:backlog/ { in_backlog=1 }
-                    in_backlog && /^-->$/ { print; print ""; print tasks; in_backlog=0; next }
-                    { print }
-                ' "$todo_file" > "$temp_file"
+                local tasks_file
+                tasks_file=$(mktemp)
+                printf '%s\n' "$existing_tasks" > "$tasks_file"
+                # Use while-read to avoid BSD awk "newline in string" warning with -v
+                local in_backlog=false
+                while IFS= read -r line || [[ -n "$line" ]]; do
+                    if [[ "$line" == *"<!--TOON:backlog"* ]]; then
+                        in_backlog=true
+                    fi
+                    if [[ "$in_backlog" == true && "$line" == "-->" ]]; then
+                        echo "$line"
+                        echo ""
+                        cat "$tasks_file"
+                        in_backlog=false
+                        continue
+                    fi
+                    echo "$line"
+                done < "$todo_file" > "$temp_file"
+                rm -f "$tasks_file"
                 mv "$temp_file" "$todo_file"
                 print_success "Merged existing tasks into Backlog"
             fi
@@ -1373,11 +1398,25 @@ cmd_upgrade_planning() {
         if [[ -n "$existing_plans" ]]; then
             if grep -q "<!--TOON:active_plans" "$plans_file"; then
                 local temp_file="${plans_file}.merge"
-                awk -v plans="$existing_plans" '
-                    /<!--TOON:active_plans/ { in_active=1 }
-                    in_active && /^-->$/ { print; print ""; print plans; in_active=0; next }
-                    { print }
-                ' "$plans_file" > "$temp_file"
+                local plans_content_file
+                plans_content_file=$(mktemp)
+                printf '%s\n' "$existing_plans" > "$plans_content_file"
+                # Use while-read to avoid BSD awk "newline in string" warning with -v
+                local in_active=false
+                while IFS= read -r line || [[ -n "$line" ]]; do
+                    if [[ "$line" == *"<!--TOON:active_plans"* ]]; then
+                        in_active=true
+                    fi
+                    if [[ "$in_active" == true && "$line" == "-->" ]]; then
+                        echo "$line"
+                        echo ""
+                        cat "$plans_content_file"
+                        in_active=false
+                        continue
+                    fi
+                    echo "$line"
+                done < "$plans_file" > "$temp_file"
+                rm -f "$plans_content_file"
                 mv "$temp_file" "$plans_file"
                 print_success "Merged existing plans into Active Plans"
             fi

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "aidevops",
-  "version": "2.101.0",
+  "version": "2.103.0",
   "description": "AI DevOps Framework - AI-assisted development workflows, code quality, and deployment automation",
   "type": "module",
   "main": "index.js",

package/setup.sh

@@ -3,7 +3,7 @@
 # AI Assistant Server Access Framework Setup Script
 # Helps developers set up the framework for their infrastructure
 #
-# Version: 2.101.0
+# Version: 2.103.0
 #
 # Quick Install (one-liner):
 #   bash <(curl -fsSL https://aidevops.dev/install)
@@ -466,6 +466,23 @@ validate_opencode_config() {
     local needs_repair=false
     local issues=""
     
+    # Check 0: Remove deprecated top-level keys that OpenCode no longer recognizes
+    # "compaction" was removed in OpenCode v1.1.x - causes "Unrecognized key" error
+    local deprecated_keys=("compaction")
+    for key in "${deprecated_keys[@]}"; do
+        if jq -e ".[\"$key\"]" "$opencode_config" > /dev/null 2>&1; then
+            local tmp_fix
+            tmp_fix=$(mktemp)
+            if jq "del(.[\"$key\"])" "$opencode_config" > "$tmp_fix" 2>/dev/null; then
+                create_backup_with_rotation "$opencode_config" "opencode"
+                mv "$tmp_fix" "$opencode_config"
+                print_info "Removed deprecated '$key' key from OpenCode config"
+            else
+                rm -f "$tmp_fix"
+            fi
+        fi
+    done
+    
     # Check 1: MCP entries must have "type" field (usually "local")
     # Invalid: {"mcp": {"foo": {"command": "..."}}}
     # Valid:   {"mcp": {"foo": {"type": "local", "command": "..."}}}