aidevops 2.100.19 → 2.101.0

package/README.md

@@ -92,9 +92,9 @@ The result: AI agents that work *with* your development process, not around it.
 ### Agent Structure
 
 - Primary agents (Build+, SEO, Marketing, etc.) with @plan-plus subagent for planning-only mode
-- 572+ subagent markdown files organized by domain
-- 157 helper scripts in `.agent/scripts/`
-- 22 slash commands for common workflows
+- 614+ subagent markdown files organized by domain
+- 164 helper scripts in `.agent/scripts/`
+- 28 slash commands for common workflows
 
 <!-- AI-CONTEXT-END -->
 
@@ -480,7 +480,7 @@ 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/`, 157 helper scripts |
+| **Give Agents a Computer** | Filesystem + shell for persistent context | `~/.aidevops/.agent-workspace/`, 164 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 |
@@ -489,7 +489,9 @@ aidevops implements proven agent design patterns identified by [Lance Martin (La
 | **Multi-Agent Orchestration** | Coordinate parallel agents | TOON mailbox, agent registry, stateless coordinator |
 | **Compaction Resilience** | Preserve context across compaction | OpenCode plugin injects dynamic state at compaction time |
 | **Ralph Loop** | Iterative execution until complete | `ralph-loop-helper.sh`, `full-loop-helper.sh` |
-| **Evolve Context** | Learn from sessions | `/remember`, `/recall` with SQLite FTS5 |
+| **Evolve Context** | Learn from sessions | `/remember`, `/recall` with SQLite FTS5 + opt-in semantic search |
+| **Pattern Tracking** | Learn what works/fails | `pattern-tracker-helper.sh`, `/patterns` command |
+| **Cost-Aware Routing** | Match model to task complexity | `model-routing.md` with 5-tier guidance, `/route` command |
 
 **Key insight**: Context is a finite resource with diminishing returns. aidevops treats every token as precious - loading only what's needed, when it's needed.
 
@@ -518,7 +520,7 @@ Coordinator (pulse loop)
 | Mailbox | `mail-helper.sh` | TOON-based inter-agent messaging (send, check, broadcast, archive) |
 | Coordinator | `coordinator-helper.sh` | Stateless pulse loop: collect reports, dispatch tasks, track idle workers |
 | Registry | `mail-helper.sh register` | Agent registration with role, branch, worktree, heartbeat |
-| Model routing | `generate-opencode-agents.sh` | Maps agent tiers to cost-effective models |
+| Model routing | `model-routing.md`, `/route` | Cost-aware 5-tier routing guidance (haiku/flash/sonnet/pro/opus) |
 
 **How it works:**
 
@@ -538,37 +540,64 @@ Coordinator (pulse loop)
 
 ### Parallel Agents & Headless Dispatch
 
-Run multiple AI sessions concurrently with isolated contexts:
+Run multiple AI sessions concurrently with isolated contexts. Named **runners** provide persistent agent identities with their own instructions and memory.
 
 | Feature | Description |
 |---------|-------------|
-| **Headless dispatch** | `claude -p` / OpenCode server API for non-interactive execution |
-| **Session management** | Deterministic session IDs, resume with `--resume` |
-| **Memory namespaces** | Per-agent memory isolation with shared access when needed |
+| **Headless dispatch** | `opencode run` for one-shot tasks, `opencode serve` + `--attach` for warm server |
+| **Runners** | Named agent instances with per-runner AGENTS.md, config, and run logs (`runner-helper.sh`) |
+| **Session management** | Resume sessions with `-s <id>` or `-c`, fork with SDK |
+| **Memory namespaces** | Per-runner memory isolation with shared access when needed |
+| **SDK orchestration** | `@opencode-ai/sdk` for TypeScript parallel dispatch via `Promise.all` |
 | **Matrix integration** | Chat-triggered dispatch via self-hosted Matrix (optional) |
 
+```bash
+# Create a named runner
+runner-helper.sh create code-reviewer --description "Reviews code for security and quality"
+
+# Dispatch a task (one-shot)
+runner-helper.sh run code-reviewer "Review src/auth/ for vulnerabilities"
+
+# Dispatch against warm server (faster, no MCP cold boot)
+opencode serve --port 4096 &
+runner-helper.sh run code-reviewer "Review src/auth/" --attach http://localhost:4096
+
+# Parallel dispatch via CLI
+opencode run --attach http://localhost:4096 --title "Review" "Review src/auth/" &
+opencode run --attach http://localhost:4096 --title "Tests" "Generate tests for src/utils/" &
+wait
+
+# List runners and status
+runner-helper.sh list
+runner-helper.sh status code-reviewer
+```
+
 **Architecture:**
 
 ```text
 OpenCode Server (opencode serve)
-├── Session 1 (code-reviewer)
-├── Session 2 (seo-analyst)
+├── Session 1 (runner/code-reviewer)
+├── Session 2 (runner/seo-analyst)
 └── Session 3 (scheduled-task)
          ↑
     HTTP API / SSE Events
          ↑
 ┌────────┴────────┐
-│  Dispatch Layer │ ← Matrix bot, cron, CLI
+│  Dispatch Layer │ ← runner-helper.sh, cron, Matrix bot, SDK
 └─────────────────┘
 ```
 
+**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.
+
 ### Self-Improving Agent System
 
 Agents that learn from experience and contribute improvements:
 
 | Phase | Description |
 |-------|-------------|
-| **Review** | Analyze memory for success/failure patterns |
+| **Review** | Analyze memory for success/failure patterns (`pattern-tracker-helper.sh`) |
 | **Refine** | Generate and apply improvements to agents |
 | **Test** | Validate in isolated OpenCode sessions |
 | **PR** | Contribute to community with privacy filtering |
@@ -596,7 +625,7 @@ Cron-based agent dispatch for automated workflows:
 
 ```bash
 # Example: Daily SEO report at 9am
-0 9 * * * ~/.aidevops/agents/scripts/droid-helper.sh dispatch "seo-analyst" "Generate daily SEO report"
+0 9 * * * ~/.aidevops/agents/scripts/runner-helper.sh run "seo-analyst" "Generate daily SEO report"
 ```
 
 **See:** [TODO.md](TODO.md) tasks t109-t118 for implementation status.
@@ -1252,7 +1281,7 @@ aidevops is registered as a **Claude Code plugin marketplace**. Install with two
 /plugin install aidevops@aidevops
 ```
 
-This installs the complete framework: 14 primary agents, 572+ subagents, and 157 helper scripts.
+This installs the complete framework: 14 primary agents, 614+ subagents, and 163 helper scripts.
 
 ### Importing External Skills
 
@@ -1340,7 +1369,7 @@ Ordered as they appear in OpenCode Tab selector and other AI assistants (15 tota
 
 ### **Example Subagents with MCP Integration**
 
-These are examples of subagents that have supporting MCPs enabled. See `.agent/` for the full list of 572+ subagents organized by domain.
+These are examples of subagents that have supporting MCPs enabled. See `.agent/` for the full list of 614+ subagents organized by domain.
 
 | Agent | Purpose | MCPs Enabled |
 |-------|---------|--------------|
@@ -1717,7 +1746,7 @@ See `.agent/workflows/session-manager.md` for the complete guide.
 
 ### Cross-Session Memory System
 
-**"Compound, then clear"** - Sessions should build on each other. The memory system stores knowledge, patterns, and learnings for future sessions using SQLite FTS5 for fast full-text search.
+**"Compound, then clear"** - Sessions should build on each other. The memory system stores knowledge, patterns, and learnings for future sessions using SQLite FTS5 for fast full-text search, with opt-in semantic similarity search via vector embeddings.
 
 **Slash commands:**
 
@@ -1727,6 +1756,8 @@ See `.agent/workflows/session-manager.md` for the complete guide.
 | `/recall {query}` | Search memories by keyword |
 | `/recall --recent` | Show 10 most recent memories |
 | `/recall --stats` | Show memory statistics |
+| `/patterns {task}` | Show success/failure patterns for a task type |
+| `/route {task}` | Suggest optimal model tier for a task |
 
 **Memory types:**
 
@@ -1739,6 +1770,29 @@ See `.agent/workflows/session-manager.md` for the complete guide.
 | `TOOL_CONFIG` | Tool setup notes |
 | `DECISION` | Architecture decisions |
 | `CONTEXT` | Background info |
+| `SUCCESS_PATTERN` | Approaches that consistently work |
+| `FAILURE_PATTERN` | Approaches that consistently fail |
+
+**Semantic search (opt-in):**
+
+```bash
+# Enable semantic similarity search (~90MB model download)
+memory-embeddings-helper.sh setup
+
+# Search by meaning, not just keywords
+memory-helper.sh recall "how to optimize queries" --semantic
+```
+
+**Pattern tracking:**
+
+```bash
+# Record what worked
+pattern-tracker-helper.sh record --outcome success --task-type bugfix \
+    --model sonnet --description "Structured debugging found root cause"
+
+# Get suggestions for a new task
+pattern-tracker-helper.sh suggest "refactor the auth middleware"
+```
 
 **CLI usage:**
 
@@ -1746,18 +1800,26 @@ See `.agent/workflows/session-manager.md` for the complete guide.
 # Store a memory
 ~/.aidevops/agents/scripts/memory-helper.sh store "WORKING_SOLUTION" "Fixed CORS with nginx headers" "cors,nginx"
 
-# Recall memories
+# Recall memories (keyword search - default)
 ~/.aidevops/agents/scripts/memory-helper.sh recall "cors"
 
+# Recall memories (semantic similarity - opt-in)
+~/.aidevops/agents/scripts/memory-helper.sh recall "cors" --semantic
+
 # View statistics
 ~/.aidevops/agents/scripts/memory-helper.sh stats
 
 # Maintenance
 ~/.aidevops/agents/scripts/memory-helper.sh validate   # Check for stale entries
 ~/.aidevops/agents/scripts/memory-helper.sh prune      # Remove stale memories
+
+# Namespaces (per-runner memory isolation)
+~/.aidevops/agents/scripts/memory-helper.sh --namespace my-runner store --content "Runner learning"
+~/.aidevops/agents/scripts/memory-helper.sh --namespace my-runner recall "query" --shared
+~/.aidevops/agents/scripts/memory-helper.sh namespaces  # List all namespaces
 ```
 
-**Storage:** `~/.aidevops/.agent-workspace/memory/memory.db`
+**Storage:** `~/.aidevops/.agent-workspace/memory/memory.db` (+ optional `embeddings.db` for semantic search, `namespaces/` for per-runner isolation)
 
 See `.agent/memory/README.md` for complete documentation.
 

package/VERSION

@@ -1 +1 @@
-2.100.19
+2.101.0

package/aidevops.sh

@@ -3,7 +3,7 @@
 # AI DevOps Framework CLI
 # Usage: aidevops <command> [options]
 #
-# Version: 2.100.10
+# Version: 2.101.0
 
 set -euo pipefail
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "aidevops",
-  "version": "2.100.19",
+  "version": "2.101.0",
   "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: 2.100.10
+# Version: 2.101.0
 #
 # Quick Install (one-liner):
 #   bash <(curl -fsSL https://aidevops.dev/install)
@@ -1952,6 +1952,17 @@ deploy_aidevops_agents() {
                 print_info "Injected OpenCode plan-reminder into Plan+"
             fi
         fi
+        # Migrate mailbox from TOON files to SQLite (if old files exist)
+        local aidevops_workspace_dir="${AIDEVOPS_WORKSPACE_DIR:-$HOME/.aidevops/.agent-workspace}"
+        local mail_dir="${AIDEVOPS_MAIL_DIR:-${aidevops_workspace_dir}/mail}"
+        local mail_script="$target_dir/scripts/mail-helper.sh"
+        if [[ -x "$mail_script" ]] && find "$mail_dir" -name "*.toon" 2>/dev/null | grep -q .; then
+            if "$mail_script" migrate; then
+                print_success "Mailbox migration complete"
+            else
+                print_warning "Mailbox migration had issues (non-critical, old files preserved)"
+            fi
+        fi
     else
         print_error "Failed to deploy agents"
         return 1
@@ -3717,7 +3728,22 @@ echo "  aidevops uninstall    - Remove aidevops"
         if [[ "$launch_onboarding" =~ ^[Yy]?$ || "$launch_onboarding" == "Y" ]]; then
             echo ""
             echo "Starting OpenCode with Onboarding agent..."
-            opencode --agent Onboarding --prompt "/onboarding"
+            # Detect available auth provider and select appropriate model
+            # Prefer Anthropic (Claude) > Google (Gemini) > OpenCode Zen > OpenAI
+            local onboarding_model=""
+            local auth_file="$HOME/.local/share/opencode/auth.json"
+            if [[ -f "$auth_file" ]]; then
+                if jq -e '.anthropic' "$auth_file" &>/dev/null; then
+                    onboarding_model="anthropic/claude-sonnet-4-5"
+                elif jq -e '.google' "$auth_file" &>/dev/null; then
+                    onboarding_model="google/gemini-2.5-flash"
+                fi
+            fi
+            local opencode_args=("--agent" "Onboarding" "--prompt" "/onboarding")
+            if [[ -n "$onboarding_model" ]]; then
+                opencode_args+=("--model" "$onboarding_model")
+            fi
+            opencode "${opencode_args[@]}"
         else
             echo ""
             echo "You can run /onboarding anytime in OpenCode to configure services."

package/templates/deploy-templates.sh

@@ -63,7 +63,7 @@ create_backup_with_rotation() {
     if (( backup_count > BACKUP_KEEP_COUNT )); then
         local to_delete=$((backup_count - BACKUP_KEEP_COUNT))
         # Delete oldest backups (sorted by name = sorted by date)
-        find "$backup_type_dir" -maxdepth 1 -type d -name "20*" -print0 2>/dev/null | sort -z | head -z -n "$to_delete" | xargs -0 rm -rf
+        find "$backup_type_dir" -maxdepth 1 -type d -name "20*" 2>/dev/null | sort | head -n "$to_delete" | while read -r old_backup; do rm -rf "$old_backup"; done
         print_info "Rotated backups: removed $to_delete old backup(s)"
     fi