opencodekit 0.14.6 → 0.15.1

package/dist/template/.opencode/.env.example

@@ -11,6 +11,7 @@ export OPENCODE_DISABLE_PRUNE=0        # Disable potentially buggy pruning
 export OPENCODE_EXPERIMENTAL_TURN_SUMMARY=1
 export OPENCODE_ENABLE_EXPERIMENTAL_MODELS=1
 export OPENCODE_EXPERIMENTAL_EXA=1
+export OPENCODE_EXPERIMENTAL_OXFMT=1
 
 # =============================================================================
 # MCP SERVICES (Remote APIs)

package/dist/template/.opencode/AGENTS.md

@@ -14,9 +14,10 @@ Everything else is guidelines, not laws.
 
 **Rule**: Before any complex tool call, ask: "Can a specialist agent do this better?"
 
+- **Fast Tasks** → @general (small, well-defined, ≤3 files)
 - **Search/Docs** → @explore / @scout
 - **Review/Debug** → @review
-- **Plan/Design** → @planner / @vision
+- **Plan/Design** → @plan / @vision
 - **Media Extraction** → @looker (images, PDFs, diagrams needing OCR/parsing)
 
 If yes → Delegate. If no → Execute directly.
@@ -99,8 +100,8 @@ question({
     - `prepareCallHierarchy` - Get call hierarchy item at position
     - `incomingCalls` - Find what calls this function
     - `outgoingCalls` - Find what this function calls
-2.  **Memory**: `memory-search` (Check past learnings), `repo-map` (Understand structure).
-3.  **Structure**: `ast-grep` (Find functions/classes patterns)
+2.  **Memory**: `memory-search` (Check past learnings)
+3.  **Structure**: `lsp` (Find symbols, definitions, references)
 4.  **Search**: `grep` (Find text/TODOs)
 5.  **Files**: `glob` (Find files)
 
@@ -122,40 +123,28 @@ Violations: `read → edit` or `grep → edit` without LSP = WRONG.
 
 ## Beads (Task Tracking)
 
-**Leader Only**: `build` and `rush` agents own the DB. Subagents read-only.
+**Leader Only**: `build` and `plan` agents own the DB. Subagents read-only.
 
 - **Start**: `bd ready` → `bd update <id> --status in_progress`
-- **Work**: `bd-reserve({ paths: [...] })` (Lock files!) → Edit
+- **Work**: `bd update <id> --status in_progress` → Edit
 - **Finish**: `bd close <id> --reason "..."` → `bd sync` → **RESTART SESSION**
 
 ## Parallel Execution
 
-**Rule**: Fire research subagents in background, continue working, collect when needed.
+**Rule**: Fire research subagents in parallel, continue working, collect when needed.
 
-For complex tasks with multiple unknowns, don't wait for sequential research. Launch parallel background tasks:
-
-**Allowed agents for background delegation:**
-
-- **Subagents**: explore, scout, review, planner, vision, looker (stateless workers)
-- **Primary**: rush (autonomous execution)
-- **NOT allowed**: build (build is the orchestrator that uses this tool)
+For complex tasks with multiple unknowns, don't wait for sequential research. Launch parallel tasks using the built-in `task` tool:
 
 ```typescript
-// Fire parallel research (non-blocking)
-background_start({ agent: "explore", prompt: "Find auth patterns..." }); // → bg_123_abc
-background_start({ agent: "scout", prompt: "Find JWT docs..." }); // → bg_456_def
+// Parallel Task tool calls (recommended)
+task({ subagent_type: "explore", prompt: "Find auth patterns..." }); // → runs in parallel
+task({ subagent_type: "scout", prompt: "Find JWT docs..." }); // → runs in parallel
 
 // Continue with implementation work immediately...
-
-// Collect results when needed
-background_output({ taskId: "bg_123_abc" });
-background_output({ taskId: "bg_456_def" });
-
-// Cleanup at session end
-background_cancel({ all: true });
+// Results come back in same message (no manual collection needed)
 ```
 
-**When to use background execution:**
+**When to use parallel execution:**
 
 - Multiple independent research questions
 - Complex tasks touching unfamiliar code

package/dist/template/.opencode/README.md

@@ -42,7 +42,7 @@ opencode
 ├── agent/                 # Custom agents (5 total)
 ├── command/               # Custom commands (26 workflows)
 ├── skill/                 # Domain expertise (27 skills)
-├── tool/                  # Custom MCP tools (memory-*, observation, ast-grep)
+├── tool/                  # Custom MCP tools (memory-*, observation)
 ├── plugin/                # Background plugins (enforcer, compactor, truncator)
 └── memory/                # Persistent context
 ```
@@ -84,11 +84,11 @@ GOOGLE_APPLICATION_CREDENTIALS=/path/to/key.json
 **Primary Agents:**
 
 - **@build** - Main orchestrator (Claude Opus 4.5) - handles 70% of work
-- **@rush** - Fast agent (GLM-4.6) - same capabilities, faster
+- **@general** - Fast subagent for small, well-defined tasks
 
 **Subagents:**
 
-- **@planner** - Architecture, multi-phase coordination
+- **@plan** - Architecture, multi-phase coordination
 - **@scout** - External research (library docs + GitHub patterns)
 - **@review** - Code review + debugging + security audit
 - **@vision** - UI/UX design: mockup, UI review, accessibility, aesthetics, visual
@@ -161,124 +161,13 @@ Plugins run automatically in every session:
 
 - **memory-read** - Load previous context, templates
 - **memory-update** - Save learnings, handoffs
-- **memory-search** - Search across all memory files (keyword, semantic, hybrid)
-- **memory-index** - Rebuild vector store for semantic search
-- **memory-embed** - Generate embeddings using Ollama
-- **observation** - Create structured observations (auto-embedded)
-- **ast-grep** - Semantic code search/replace (AST-based)
-
----
-
-## Semantic Memory Setup (Ollama)
-
-Semantic search requires Ollama running locally. Zero API keys needed.
-
-**Model:** `qwen3-embedding:0.6b` (639MB)
-
-- State-of-the-art quality (MTEB #1 for 8B version)
-- Code-aware (optimized for code retrieval)
-- Multilingual (100+ languages including Vietnamese)
-- 32K context, 1024 dimensions
-
-### Installation
-
-**macOS:**
-
-```bash
-brew install ollama
-```
-
-**Linux:**
-
-```bash
-curl -fsSL https://ollama.com/install.sh | sh
-```
-
-**Windows:**
-
-1. Download from https://ollama.com/download/windows
-2. Run the installer
-3. Ollama runs as a background service automatically
-
-### Setup
-
-```bash
-# Start Ollama (macOS/Linux - if not running as service)
-ollama serve
-
-# Pull embedding model (one-time, ~639MB)
-ollama pull qwen3-embedding:0.6b
-
-# Verify
-ollama list  # Should show qwen3-embedding:0.6b
-```
-
-**Linux:**
-
-```bash
-curl -fsSL https://ollama.com/install.sh | sh
-```
-
-**Windows:**
-
-1. Download from https://ollama.com/download/windows
-2. Run the installer
-3. Ollama runs as a background service automatically
-
-### Setup
-
-```bash
-# Start Ollama (macOS/Linux - if not running as service)
-ollama serve
-
-# Pull embedding model (one-time, ~274MB)
-ollama pull nomic-embed-text
-
-# Verify
-ollama list  # Should show nomic-embed-text
-```
-
-### Custom Host (Optional)
-
-If Ollama runs on a different machine:
-
-```bash
-export OLLAMA_HOST=http://192.168.1.100:11434
-```
-
-### Usage
-
-```bash
-# Rebuild vector index (after adding new observations)
-memory-index action=rebuild
-
-# Search with semantic similarity
-memory-search query="authentication patterns" mode=semantic
-
-# Hybrid search (keyword + semantic)
-memory-search query="auth" mode=hybrid
-```
+- **memory-search** - Search across all memory files (keyword-based)
+- **observation** - Create structured observations (decision, bugfix, feature, etc.)
 
 ---
 
 ### AST-Grep Usage
 
-Semantic code operations - smarter than regex:
-
-```bash
-# Search patterns
-ast-grep pattern="console.log($$$)"                    # Find all console.log
-ast-grep pattern="async function $NAME($$$) { $$$ }"   # Find async functions
-ast-grep pattern="const [$S, $SET] = useState($$$)"    # Find React hooks
-
-# Replace (dry run by default)
-ast-grep pattern="oldFunc($$$)" rewrite="newFunc($$$)" dryRun=true
-```
-
-**Pattern syntax**: `$NAME` = single node, `$$$` = zero or more nodes
-
-**Requires**: `brew install ast-grep` or `cargo install ast-grep --locked`
-
 ---
 
 ## MCP Services
@@ -335,8 +224,8 @@ Result: Comprehensive research doc
 
 ```
 User: "Build auth system"
-@build → @planner (4 phases)
-@planner → @review (security audit)
+@build → @plan (4 phases)
+@plan → @review (security audit)
 Result: Secure auth with tests
 ```
 
@@ -409,7 +298,7 @@ fi
 **Delegation:**
 
 - Use @build for 70% of work
-- Delegate to @planner for 3+ phases
+- Delegate to @plan for 3+ phases
 - Use @review before deployment (code review + security)
 - Use @scout for library docs + GitHub patterns
 - Use @explore for codebase search

package/dist/template/.opencode/agent/explore.md

@@ -41,7 +41,6 @@ File search specialist. Navigate and explore codebases efficiently.
 - Finding files using glob patterns
 - Searching code with regex patterns
 - Reading and analyzing file contents
-- Semantic code search with AST-Grep
 - Understanding symbol types and definitions with LSP
 
 ## Navigation Strategy
@@ -64,8 +63,8 @@ File search specialist. Navigate and explore codebases efficiently.
 
 ## Thoroughness Levels
 
-**Quick**: Single ast-grep, lsp_lsp_workspace_symbols, or glob. Read 1-3 files. Return immediately.
+**Quick**: Single grep, lsp_lsp_workspace_symbols, or glob. Read 1-3 files. Return immediately.
 
-**Medium**: AST-grep + LSP verification. Check 2-3 naming conventions. Read 3-5 files. Use `lsp_lsp_find_references` to trace usage.
+**Medium**: grep + LSP verification. Check 2-3 naming conventions. Read 3-5 files. Use `lsp_lsp_find_references` to trace usage.
 
 **Very Thorough**: Comprehensive search across multiple terms and locations. Use `lsp_lsp_find_references` to build dependency map. Report with file:line references.

package/dist/template/.opencode/agent/general.md

@@ -0,0 +1,56 @@
+---
+description: General-purpose subagent for fast, well-defined tasks; delegates complexity to specialists.
+mode: subagent
+temperature: 0.1
+permission:
+  bash:
+    "*": allow
+    "git push*": ask
+    "rm -rf*": deny
+    "sudo*": deny
+---
+
+# General Agent
+
+Fast subagent for small, clear tasks. Delegate complexity quickly.
+
+<system-reminder>
+# General Mode - System Reminder
+
+You are the general subagent. Move fast, avoid risk.
+
+## Critical Constraints
+
+1. Read before edit; never edit unseen code.
+2. Two-strike rule: after 2 failed attempts, stop and escalate.
+3. Bail on complexity: 4+ files, architecture decisions, unclear specs → delegate.
+4. No hallucinated URLs; only use provided or verified links.
+5. Ask before commits/pushes.
+
+## Intent Gate
+
+- Specialist fit? Use explore/scout/review/plan/vision/looker when better.
+- Scope small and clear (≤3 files, no refactors)? Otherwise delegate.
+- Need clarification? One focused question; if more, escalate.
+
+## Bail Triggers
+
+- Scope creep or cross-cutting changes
+- Research-heavy tasks
+- Two failed attempts
+- Architecture pattern choices
+- Legacy/edge-case minefields
+
+## Guidelines
+
+- Match existing style; change only what’s requested.
+- Prefer minimal, surgical edits; avoid unrelated refactors.
+- Run a quick sanity check (lint/typecheck or LSP diagnostics) after edits.
+- Use `file:line` references in summaries; no emojis unless asked.
+
+## Progress Updates
+
+- Keep brief preambles (8–12 words) during multi-step changes.
+- Examples: “Found issue; patching helper now.” / “Config updated; running lint.”
+
+</system-reminder>

package/dist/template/.opencode/agent/plan.md

@@ -0,0 +1,54 @@
+---
+description: Primary planning agent for architecture and multi-phase execution; produces actionable plans with gated steps.
+mode: primary
+temperature: 0.2
+permission:
+  write:
+    "*": deny
+    ".beads/artifacts/*/*.md": allow
+  edit:
+    "*": deny
+    ".beads/artifacts/*/*.md": allow
+  bash:
+    "*": allow
+    "rm*": deny
+    "git push*": deny
+    "git commit*": deny
+    "git reset*": deny
+    "npm publish*": deny
+  question: allow
+---
+
+# Plan Agent
+
+<system-reminder>
+# Plan Mode - System Reminder
+
+You are the primary planning agent. Stay read-focused; only edit planning artifacts in `.beads/artifacts/<bead_id>/` when needed.
+
+## Critical Constraints
+
+1. No code edits outside planning docs. Read-first, no destructive commands.
+2. Two-strike rule: after two failed attempts to get clarity, escalate.
+3. Bail on complexity outside planning scope; delegate execution to @build, research to @explore/@scout.
+4. No hallucinated URLs; only use provided or verified links.
+5. Ask before commits/pushes.
+
+## When to Plan vs Execute
+
+- Plan when work spans multiple phases, has dependencies, or needs coordination.
+- Skip planning for trivial single-step fixes; delegate directly to @build.
+
+## Planning Workflow
+
+- Phase 1: Understand request; launch minimal @explore/@scout in parallel when scope is unclear.
+- Phase 2: Draft approach with phases, owners, and validation gates.
+- Phase 3: Synthesize into a concise plan with deliverables and risks.
+- End with a clarifying question if options exist, otherwise present the plan and ask "Ready to proceed?"
+
+## Output Expectations
+
+- Provide phase breakdown, critical files to touch, validation steps, and agent assignments.
+- Surface risks, edge cases, and acceptance criteria.
+- Keep progress updates brief (8–12 words) during research.
+  </system-reminder>

package/dist/template/.opencode/agent/scout.md

@@ -3,11 +3,21 @@ description: External research specialist for library docs, GitHub patterns, and
 mode: subagent
 temperature: 0.3
 maxSteps: 30
-tools:
-  edit: false
-  write: false
-  bash: false
-  question: false
+permission:
+  write:
+    "*": deny
+    ".beads/artifacts/*/*.md": allow
+  edit:
+    "*": deny
+    ".beads/artifacts/*/*.md": allow
+  bash:
+    "*": allow
+    "rm*": deny
+    "git push*": deny
+    "git commit*": deny
+    "git reset*": deny
+    "npm publish*": deny
+  question: deny
 ---
 
 # Scout Agent

package/dist/template/.opencode/command/analyze-project.md

@@ -82,8 +82,8 @@ Task({
 
 **Fallback:** If Task tool fails or network is unavailable, use local tools:
 
-- `repo-map` for architecture analysis
 - `memory-search` for existing project knowledge
+- Use `glob` + `read` to explore structure
 - Skip external research phases
 
 ---
@@ -210,7 +210,7 @@ Integrate findings from Phase 2 subagents into the report:
 If subagents failed in Phase 2, use fallback data:
 
 - Check `memory-read({ file: "project/architecture" })` for cached architecture
-- Use `repo-map` output for structure analysis
+- Use `glob` + `read` to explore structure
 - Skip best practices comparison (mark as "N/A - offline mode")
 
 ---

package/dist/template/.opencode/command/brainstorm.md

@@ -1,7 +1,7 @@
 ---
 description: Brainstorm and explore ideas with structured ideation
 argument-hint: "<topic or bead-id> [--quick]"
-agent: planner
+agent: plan
 subtask: true
 ---
 

package/dist/template/.opencode/command/design-audit.md

@@ -107,11 +107,11 @@ Analyze all images and extract:
 
 ### For Codebase
 
-Search for hardcoded values using ast-grep and grep:
+Search for hardcoded values using grep:
 
 ```typescript
-ast - grep({ pattern: 'color: "#$HEX"' });
-ast - grep({ pattern: 'background: "#$HEX"' });
+grep({ pattern: "color:", include: "*.{css,scss,tsx,jsx}" });
+grep({ pattern: "background:", include: "*.{css,scss,tsx,jsx}" });
 grep({ pattern: "#[0-9a-fA-F]{3,8}", include: "*.{css,scss,tsx,jsx}" });
 grep({ pattern: "rgb\\(", include: "*.{css,scss,tsx,jsx}" });
 grep({ pattern: "hsl\\(", include: "*.{css,scss,tsx,jsx}" });
@@ -121,8 +121,7 @@ grep({ pattern: "[0-9]+rem", include: "*.{css,scss,tsx,jsx}" });
 
 grep({ pattern: "font-size:", include: "*.css" });
 grep({ pattern: "fontSize:", include: "*.{tsx,jsx}" });
-
-ast - grep({ pattern: 'className="$$$"' }); // then analyze for arbitrary values like [16px]
+grep({ pattern: "className=", include: "*.{tsx,jsx}" }); // then analyze for arbitrary values
 ```
 
 ---

package/dist/template/.opencode/command/design.md

@@ -356,12 +356,10 @@ const buttonVariants = cva(
     variants: {
       variant: {
         default: "bg-primary text-primary-foreground hover:bg-primary/90",
-        secondary:
-          "bg-secondary text-secondary-foreground hover:bg-secondary/80",
+        secondary: "bg-secondary text-secondary-foreground hover:bg-secondary/80",
         outline: "border border-input bg-background hover:bg-accent",
         ghost: "hover:bg-accent hover:text-accent-foreground",
-        destructive:
-          "bg-destructive text-destructive-foreground hover:bg-destructive/90",
+        destructive: "bg-destructive text-destructive-foreground hover:bg-destructive/90",
       },
       size: {
         sm: "h-8 px-3 text-sm",
@@ -377,17 +375,10 @@ const buttonVariants = cva(
 );
 
 interface ButtonProps
-  extends
-    React.ButtonHTMLAttributes<HTMLButtonElement>,
-    VariantProps<typeof buttonVariants> {}
+  extends React.ButtonHTMLAttributes<HTMLButtonElement>, VariantProps<typeof buttonVariants> {}
 
 export function Button({ className, variant, size, ...props }: ButtonProps) {
-  return (
-    <button
-      className={cn(buttonVariants({ variant, size }), className)}
-      {...props}
-    />
-  );
+  return <button className={cn(buttonVariants({ variant, size }), className)} {...props} />;
 }
 ```
 

package/dist/template/.opencode/command/generate-pattern.md

@@ -195,20 +195,13 @@ Use `--colors=<preset>` or specify hex values:
 /* With overlay for text readability */
 .pattern-overlay {
   background:
-    linear-gradient(rgba(255, 255, 255, 0.9), rgba(255, 255, 255, 0.9)),
-    url("pattern-512.png");
+    linear-gradient(rgba(255, 255, 255, 0.9), rgba(255, 255, 255, 0.9)), url("pattern-512.png");
   background-repeat: repeat;
 }
 
 /* CSS-only alternative (if simple enough) */
 .pattern-css {
-  background: repeating-linear-gradient(
-    45deg,
-    #f0f0f0,
-    #f0f0f0 10px,
-    #ffffff 10px,
-    #ffffff 20px
-  );
+  background: repeating-linear-gradient(45deg, #f0f0f0, #f0f0f0 10px, #ffffff 10px, #ffffff 20px);
 }
 ```
 

package/dist/template/.opencode/command/implement.md

@@ -64,7 +64,7 @@ bd ready --json | grep -q "$ARGUMENTS"
 // Fire all READY subtasks in parallel using Task tool
 // Multiple Task calls in one message run simultaneously
 Task({
-  subagent_type: "rush",
+  subagent_type: "general",
   description: "Execute subtask 1",
   prompt: `Execute bd-subtask1: [Subtask description]
 
@@ -78,7 +78,7 @@ Task({
 });
 
 Task({
-  subagent_type: "rush",
+  subagent_type: "general",
   description: "Execute subtask 2",
   prompt: `Execute bd-subtask2: [Subtask description]
     ...same pattern...`,
@@ -201,7 +201,7 @@ Task({
   subagent_type: "explore",
   description: "Find codebase patterns",
   prompt: `For implementing $ARGUMENTS, find:
-    1. Similar patterns in this codebase (grep/ast-grep)
+    1. Similar patterns in this codebase (grep)
     2. Related test files and testing patterns
     3. Configuration or setup requirements
     Return: File paths, code patterns, test approach`,
@@ -232,7 +232,7 @@ Task({
 | `explore`| Codebase search, patterns | Read, grep, glob | Edit, bd sync |
 | `scout` | External docs, best practices | Fetch, search | Edit, bd sync |
 | `review` | Code review, debugging | Read, analyze | Edit, bd sync |
-| `planner`| Architecture, decomposition | Read, plan | Edit, bd sync |
+| `plan` | Architecture, decomposition | Read, plan | Edit, bd sync |
 
 **You (build agent) are the leader:**
 

package/dist/template/.opencode/command/init.md

@@ -1,7 +1,7 @@
 ---
 description: Initialize project for AI-assisted development (creates AGENTS.md + memory files)
 argument-hint: "[--deep] [--skip-questions]"
-agent: planner
+agent: plan
 subtask: true
 ---
 

package/dist/template/.opencode/command/new-feature.md

@@ -1,7 +1,7 @@
 ---
 description: Create a new feature with discovery, spec, plan, and sub-tasks
 argument-hint: "<feature-name> [--priority=<0-4>] [--type=<type>] [--worktree] [--quick]"
-agent: planner
+agent: plan
 ---
 
 # New Feature: $ARGUMENTS
@@ -153,8 +153,7 @@ question({
   questions: [
     {
       header: "Approve",
-      question:
-        "Should I proceed with creating the specification for $ARGUMENTS?",
+      question: "Should I proceed with creating the specification for $ARGUMENTS?",
       options: [
         {
           label: "Yes, proceed",

package/dist/template/.opencode/command/plan.md

@@ -1,7 +1,7 @@
 ---
 description: Create implementation plan for a bead with subtask hierarchy
 argument-hint: "<bead-id> [--create-beads] [--parallel]"
-agent: planner
+agent: plan
 ---
 
 # Plan: $ARGUMENTS

package/dist/template/.opencode/command/pr.md

@@ -242,7 +242,6 @@ CI Status:
 ## Phase 7: Update Bead & Sync
 
 ```bash
-bd-msg --subj "PR created" --body "PR: <pr-url>\nStatus: [ready/draft]\nCI: [passing/pending]" --to "all" --importance normal
 bd sync
 ```
 

package/dist/template/.opencode/command/research.md

@@ -23,7 +23,21 @@ First, understand the codebase structure:
 
 ```typescript
 // Quick overview of relevant directories
-repo-map({ path: "src", format: "compact", maxDepth: 3 });
+lsp_lsp_document_symbols({ filePath: "src/index.ts", line: 1, character: 1 });
+
+// Find files by pattern
+glob({ pattern: "src/**/*.ts" });
+```
+
+### Deep Dive
+
+```typescript
+// Find similar patterns
+grep({ pattern: "<text pattern>", include: "*.ts" });
+
+// Understand types
+lsp_lsp_hover({ filePath: "<file>", line: N, character: N });
+lsp_lsp_find_references({ filePath: "<file>", line: N, character: N });
 ```
 
 This helps identify relevant directories and files before diving deeper.
@@ -88,17 +102,17 @@ If memory search fails (Ollama not running), continue to external sources.
 
 ### Internal Codebase - Get Quick Overview
 
-First, generate a compact repository map to understand the codebase structure:
+First, understand codebase structure:
 
 ```typescript
 // Quick overview of relevant directories
-repo-map({ path: "src", format: "compact", maxDepth: 3 });
+glob({ pattern: "src/**/*.ts" });
 
-// For specific feature area
-repo-map({ path: "src/commands", format: "tree", maxDepth: 2 });
+// Check file structure
+lsp_lsp_document_symbols({ filePath: "src/index.ts", line: 1, character: 1 });
 ```
 
-**Use repo-map when:**
+**Use these tools when:**
 
 - Starting research on a new area of the codebase
 - Need to understand file organization before diving deep

package/dist/template/.opencode/command/restore-image.md

@@ -19,15 +19,7 @@ const parseInput = (input: string) => {
   const imagePath = parts[0];
   const mode = parts[1] || "enhance";
 
-  const validModes = [
-    "enhance",
-    "upscale",
-    "restore",
-    "denoise",
-    "colorize",
-    "sharpen",
-    "deblur",
-  ];
+  const validModes = ["enhance", "upscale", "restore", "denoise", "colorize", "sharpen", "deblur"];
 
   if (!validModes.includes(mode)) {
     console.warn(`Unknown mode: ${mode}. Using 'enhance' as default.`);