opencodekit 0.16.0 → 0.16.2

package/dist/template/.opencode/command/ui-review.md

@@ -14,6 +14,7 @@ Comprehensive UI/UX review with structured scoring and actionable feedback.
 
 ```typescript
 skill({ name: "beads" }); // Session protocol
+skill({ name: "memory-system" });
 ```
 
 ```typescript
@@ -22,6 +23,20 @@ skill({ name: "visual-analysis" });
 skill({ name: "accessibility-audit" });
 ```
 
+## Check Memory for Design Context
+
+Search for existing design decisions and patterns:
+
+```typescript
+// Find design system decisions
+memory_search({ query: "design system colors typography", limit: 3 });
+
+// Find previous UI reviews and findings
+memory_search({ query: "[component/page] UI review", limit: 3 });
+```
+
+Apply existing design decisions to the review.
+
 ## Parse Arguments
 
 | Argument       | Default  | Description                          |
@@ -305,3 +320,19 @@ bd dep add <task-id> <bead-id>
 | Design from scratch  | `/design`       |
 | Start implementation | `/start <bead>` |
 | Ship implementation  | `/ship <bead>`  |
+
+## Record Significant Findings
+
+For important UI/UX findings worth remembering:
+
+```typescript
+observation({
+  type: "warning", // or "pattern", "decision"
+  title: "UI: [Component/page] [issue type]",
+  narrative: "Found [issue] in [location]. Impact: [description]...",
+  facts: "[severity], [category], [fix approach]",
+  concepts: "ui, accessibility, [component type]",
+  bead_id: "$ARGUMENTS", // if applicable
+  confidence: "high",
+});
+```

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

@@ -15,6 +15,7 @@ Three-dimensional verification before claiming work complete. Inspired by OpenSp
 skill({ name: "beads" });
 skill({ name: "verification-before-completion" });
 skill({ name: "systematic-debugging" });
+skill({ name: "memory-system" });
 ```
 
 ## Parse Arguments
@@ -27,7 +28,17 @@ skill({ name: "systematic-debugging" });
 
 ---
 
-## Phase 1: Gather Artifacts
+## Phase 1: Check Memory for Context
+
+Search for relevant verification patterns and past issues:
+
+```typescript
+memory_search({ query: "$ARGUMENTS verification issues patterns", limit: 3 });
+```
+
+---
+
+## Phase 2: Gather Artifacts
 
 ```bash
 bd show $ARGUMENTS
@@ -45,7 +56,7 @@ cat .beads/artifacts/$ARGUMENTS/design.md 2>/dev/null
 
 ---
 
-## Phase 2: Completeness Check
+## Phase 3: Completeness Check
 
 **Are all required artifacts present?**
 
@@ -75,7 +86,7 @@ Extract tasks/criteria from spec.md and verify each is implemented:
 
 ---
 
-## Phase 3: Correctness Check
+## Phase 4: Correctness Check
 
 **Do the automated gates pass?**
 
@@ -132,7 +143,7 @@ golangci-lint run 2>&1 | tail -10
 
 ---
 
-## Phase 4: Coherence Check (skip with --quick)
+## Phase 5: Coherence Check (skip with --quick)
 
 **Do artifacts agree with each other?**
 
@@ -168,7 +179,7 @@ Contradictions found: 1
 
 ---
 
-## Phase 5: Verification Summary
+## Phase 6: Verification Summary
 
 ```
 Verification: $ARGUMENTS
@@ -200,7 +211,7 @@ Recommendations:
 
 ---
 
-## Phase 6: Auto-Fix (if --fix)
+## Phase 7: Auto-Fix (if --fix)
 
 For fixable issues, attempt automatic resolution:
 
@@ -218,7 +229,7 @@ if (missingTests) {
 
 ---
 
-## Phase 7: Update Bead Notes
+## Phase 8: Update Bead Notes
 
 Record verification results in bead:
 
@@ -228,6 +239,23 @@ bd note $ARGUMENTS "Verification: [PASS|PARTIAL|FAIL] - [summary]"
 
 ---
 
+## Phase 9: Record Findings
+
+If significant issues or patterns discovered:
+
+```typescript
+observation({
+  type: "discovery",
+  title: "Verification findings for $ARGUMENTS",
+  narrative: "[Summary of issues found, patterns discovered, or lessons learned]",
+  concepts: "verification, testing, quality",
+  bead_id: "$ARGUMENTS",
+  confidence: "high",
+});
+```
+
+---
+
 ## Output
 
 ```

package/dist/template/.opencode/dcp.jsonc

@@ -1,72 +1,81 @@
 {
-  "$schema": "https://unpkg.com/@anthropic/dynamic-context-protocol@1.2.7/schema.json",
-  "enabled": true,
-  "debug": false,
-  // "minimal" shows prune activity without noise; "detailed" shows token counts
-  "pruneNotification": "off",
-  "turnProtection": {
-    "enabled": true,
-    // 3 turns = faster cleanup while still protecting recent context
-    "turns": 3,
-  },
-  // Protected file patterns - never auto-prune reads of these files (v1.1.5+)
-  "protectedFilePatterns": [
-    "**/.env*",
-    "**/AGENTS.md",
-    "**/.opencode/**",
-    "**/.beads/**",
-    "**/package.json",
-    "**/tsconfig.json",
-    "**/biome.json",
-  ],
-  "tools": {
-    "settings": {
-      "nudgeEnabled": true,
-      // Nudge every 8 tool calls (slightly more aggressive than default 10)
-      "nudgeFrequency": 8,
-      // Protect state-modifying and critical workflow tools
-      "protectedTools": [
-        "write",
-        "edit",
-        "memory-update",
-        "skill",
-        "skill_mcp",
-        "task",
-        "batch",
-        "todowrite",
-        "todoread",
-        "lsp",
-        "lsp_lsp_rename",
-        "lsp_lsp_find_references",
-        "lsp_lsp_goto_definition",
-        "lsp_lsp_code_actions",
-        "lsp_lsp_code_action_apply",
-        "lsp_lsp_organize_imports",
-      ],
-    },
-    "discard": {
-      "enabled": true,
-    },
-    "extract": {
-      "enabled": true,
-      "showDistillation": false,
-    },
-  },
-  "strategies": {
-    // Dedup = zero LLM cost, high impact - always enable
-    "deduplication": {
-      "enabled": true,
-      "protectedTools": [],
-    },
-    // Supersede writes = zero cost, removes redundant write inputs after read
-    "supersedeWrites": {
-      "enabled": true,
-    },
-    // Purge error inputs after 3 turns
-    "purgeErrors": {
-      "enabled": true,
-      "turns": 3,
-      "protectedTools": [],
-    },
-  },
+	"$schema": "https://raw.githubusercontent.com/Opencode-DCP/opencode-dynamic-context-pruning/dev/dcp.schema.json",
+	"enabled": true,
+	"debug": false,
+	// "minimal" shows prune activity without noise; "detailed" shows token counts
+	"pruneNotification": "off",
+	// "chat" (in-conversation) or "toast" (system notification) - beta feature
+	"pruneNotificationType": "chat",
+	// Commands: /dcp context, /dcp stats, /dcp sweep
+	"commands": {
+		"enabled": true,
+		// Protect these from /dcp sweep
+		"protectedTools": ["observation", "memory-update", "memory-search"]
+	},
+	"turnProtection": {
+		"enabled": true,
+		"turns": 4
+	},
+	// Protected file patterns - never auto-prune reads of these files
+	"protectedFilePatterns": [
+		"**/.env*",
+		"**/AGENTS.md",
+		"**/.opencode/**",
+		"**/.beads/**",
+		"**/package.json",
+		"**/tsconfig.json",
+		"**/biome.json"
+	],
+	"tools": {
+		"settings": {
+			"nudgeEnabled": true,
+			"nudgeFrequency": 10,
+			// Protect state-modifying and critical workflow tools
+			// LSP excluded: ephemeral exploration, prune after understanding
+			"protectedTools": [
+				"write",
+				"edit",
+				"memory-update",
+				"observation",
+				"skill",
+				"skill_mcp",
+				"task",
+				"batch",
+				"todowrite",
+				"todoread"
+			]
+		},
+		// Beta: renamed from "discard" - removes tool content without preservation
+		"prune": {
+			"enabled": true
+		},
+		// Beta: renamed from "extract" - distills key findings before removing
+		"distill": {
+			"enabled": true,
+			"showDistillation": false
+		},
+		// Beta: NEW - collapses range of messages + tools into single summary
+		"compress": {
+			"enabled": true,
+			"showCompression": true
+		}
+	},
+	"strategies": {
+		// Dedup = zero LLM cost, high impact - always enable
+		"deduplication": {
+			"enabled": true,
+			"protectedTools": []
+		},
+		// Supersede writes = zero cost, removes redundant write inputs after read
+		// Note: default changed to false in beta, we explicitly enable
+		"supersedeWrites": {
+			"enabled": true
+		},
+		// Purge error inputs after N turns
+		"purgeErrors": {
+			"enabled": true,
+			"turns": 4,
+			"protectedTools": []
+		}
+	}
 }

package/dist/template/.opencode/memory/project/tech-stack.md

@@ -1,6 +1,6 @@
 ---
 purpose: Tech stack, constraints, and integrations for AI context injection
-updated: 2026-02-01
+updated: 2026-02-02
 ---
 
 # Tech Stack
@@ -9,40 +9,43 @@ This file is automatically injected into ALL AI prompts via `opencode.json` inst
 
 ## Framework & Language
 
-- **Framework:** [e.g., Next.js 15, React 19]
-- **Language:** TypeScript (strict mode)
-- **Runtime:** [e.g., Node.js 22, Bun 1.x]
+- **Framework:** CLI tool (cac for argument parsing)
+- **Language:** TypeScript (ESNext, strict mode, bundler moduleResolution)
+- **Runtime:** Bun >= 1.3.2
 
-## Styling & UI
+## Key Dependencies
 
-- **CSS:** [e.g., Tailwind CSS v4]
-- **Components:** [e.g., shadcn/ui, Radix Primitives]
-- **Design System:** [e.g., Custom tokens in tailwind.config.ts]
+- **CLI Framework:** cac (^6.7.14) - Command-line argument parsing
+- **UI Prompts:** @clack/prompts (^0.7.0) - Interactive CLI prompts
+- **TUI Framework:** @opentui/core (^0.1.72) + @opentui/solid (^0.1.72) - Terminal UI
+- **Validation:** zod (^3.25.76) - Schema validation
+- **Task Tracking:** beads-village (^1.3.3) - Git-backed task management
+- **AI SDK:** @ai-sdk/provider (^3.0.6) - AI provider integration
 
-## Data & State
+## Build & Tools
 
-- **Database:** [e.g., PostgreSQL via Supabase]
-- **ORM:** [e.g., Drizzle, Prisma]
-- **State Management:** [e.g., Zustand, React Query]
-- **API Style:** [e.g., REST, tRPC, GraphQL]
+- **Build:** `bun run build.ts` + rsync for template bundling
+- **Lint:** oxlint (^1.38.0) - Fast JavaScript/TypeScript linter
+- **Format:** oxfmt (^0.23.0) - Code formatter
+- **TypeCheck:** TypeScript 5.9.3
 
 ## Testing
 
-- **Unit Tests:** [e.g., Vitest]
-- **E2E Tests:** [e.g., Playwright]
-- **Coverage Target:** [e.g., 80%]
+- **Unit Tests:** bun test (native Bun test runner)
+- **Test Location:** src/\*_/_.test.ts (colocated)
+- **Run Single:** bun test src/commands/init.test.ts
 
 ## Key Constraints
 
-- [Constraint 1: e.g., Must work offline]
-- [Constraint 2: e.g., WCAG 2.1 AA compliance required]
-- [Constraint 3: e.g., Bundle size < 500KB]
+- Must maintain Bun compatibility (engines.bun >= 1.3.2)
+- Node.js not officially supported
+- Build copies .opencode/ to dist/template/ - don't edit dist/ directly
+- Keep .opencode/ structure minimal and focused
 
 ## Active Integrations
 
-- [Service 1: e.g., Stripe for payments]
-- [Service 2: e.g., Resend for email]
-- [Service 3: e.g., Sentry for error tracking]
+- **OpenCode AI:** @opencode-ai/plugin (^1.1.12) - OpenCode integration
+- **Beads CLI:** @beads/bd (^0.29.0) - Task tracking CLI
 
 ---