opencodekit 0.15.13 → 0.15.15

package/dist/template/.opencode/package.json

@@ -11,7 +11,7 @@
     "type-check": "tsc --noEmit"
   },
   "dependencies": {
-    "@opencode-ai/plugin": "1.1.39"
+    "@opencode-ai/plugin": "1.1.40"
   },
   "devDependencies": {
     "@types/node": "^25.0.3",

package/dist/template/.opencode/skill/deep-research/SKILL.md

@@ -0,0 +1,385 @@
+---
+name: deep-research
+description: >
+  Use when analyzing unfamiliar code, implementing complex features, or entering thorough research mode.
+  Provides structured LSP exploration (all 9 operations), memory-first protocol, and confidence-scored findings.
+  Integrates with scout agent deep mode and research command --thorough flag.
+version: "1.0.0"
+license: MIT
+---
+
+# Deep Research - Comprehensive Code Understanding
+
+Systematic methodology for thorough codebase exploration before implementation.
+
+## When to Use This Skill
+
+Use deep research when:
+
+- **Complex implementation**: Feature touches 3+ files or unfamiliar modules
+- **Thorough mode**: `/research <topic> --thorough` or scout deep mode
+- **Pre-edit understanding**: Before modifying code you don't fully understand
+- **Architecture exploration**: Understanding how systems connect
+- **Debugging**: Tracing behavior through multiple layers
+
+**Don't use when:**
+
+- Quick syntax lookup (use quick mode instead)
+- Well-understood code with obvious changes
+- Time-constrained fixes (accept lower confidence)
+
+## Core Protocol
+
+### Phase 1: Memory First (Skip External If Found)
+
+```typescript
+// Search past research on this topic
+memory_search({ query: "<topic keywords>", limit: 5 });
+
+// Check for related observations
+memory_search({ query: "<topic> gotchas patterns", limit: 3 });
+
+// Load relevant project context
+memory_read({ file: "project/architecture" });
+memory_read({ file: "project/gotchas" });
+```
+
+**Stop condition**: If memory returns high-confidence findings on this exact topic, synthesize and skip to documentation. Only proceed to exploration if:
+
+- No relevant memory found
+- Memory findings are outdated or incomplete
+- Question requires fresh analysis
+
+### Phase 2: LSP Exploration (Delegate to Explore Agent)
+
+**Delegate to explore agent** for comprehensive LSP analysis instead of manual operations:
+
+```typescript
+task({
+  subagent_type: "explore",
+  description: "LSP analysis of <target>",
+  prompt: `Very thorough LSP analysis of <symbol/module>.
+
+Target files:
+- src/path/to/file.ts
+- src/related/module.ts
+
+Questions to answer:
+1. What is the type signature of <symbol>?
+2. What calls this function? (incoming calls)
+3. What does this function call? (outgoing calls)
+4. Where is this symbol referenced across the codebase?
+5. Are there interface implementations to consider?
+
+Return structured findings with file:line references.`,
+});
+```
+
+The explore agent will run:
+
+- `documentSymbol` - File structure overview
+- `goToDefinition` - Symbol definitions
+- `findReferences` - All usages across codebase
+- `hover` - Type info and documentation
+- `workspaceSymbol` - Workspace-wide search
+- Call hierarchy (incoming/outgoing calls)
+
+**When to run LSP manually instead:**
+
+- Single symbol lookup (quick mode)
+- Explore agent unavailable
+- Need specific operation only
+
+### Phase 3: Pattern Discovery
+
+```typescript
+// Find similar patterns in codebase
+grep({ pattern: "<relevant pattern>", include: "*.ts" });
+
+// Locate related files
+glob({ pattern: "src/**/*<topic>*" });
+
+// Check tests for usage examples
+glob({ pattern: "**/*.test.ts" });
+grep({ pattern: "<function name>", include: "*.test.ts" });
+```
+
+### Phase 4: External Research (If Needed)
+
+Only if internal exploration doesn't answer the question:
+
+```typescript
+// Official docs
+context7_resolve_library_id({ libraryName: "<lib>" });
+context7_query_docs({ libraryId: "<id>", topic: "<specific question>" });
+
+// Real-world patterns
+codesearch({ query: "<API usage pattern>", tokensNum: 5000 });
+grep_search({ query: "<code pattern>", language: "TypeScript" });
+```
+
+## Confidence Levels
+
+Score every finding:
+
+| Level      | Criteria                                   | Action               |
+| ---------- | ------------------------------------------ | -------------------- |
+| **High**   | LSP confirmed + tests exist + docs match   | Proceed confidently  |
+| **Medium** | LSP confirmed but untested or undocumented | Proceed with caution |
+| **Low**    | Inference only, no LSP/test confirmation   | Verify before using  |
+| **None**   | Speculation without evidence               | Discard              |
+
+## Stop Conditions
+
+Stop research when ANY of these are true:
+
+- All questions answered with Medium+ confidence
+- Tool budget exhausted (~100 calls for thorough)
+- Last 5 tool calls yielded no new insights
+- Blocked and need human input
+
+## Tool Budget Guidelines
+
+| Mode     | Tool Calls | Use Case                           |
+| -------- | ---------- | ---------------------------------- |
+| Quick    | ~10        | Single question, syntax lookup     |
+| Default  | ~30        | Moderate exploration               |
+| Thorough | ~100+      | Comprehensive analysis, new domain |
+
+Track your tool count and stop at budget.
+
+## Output Template
+
+Document findings in structured format:
+
+```markdown
+# Deep Research: [Topic]
+
+**Mode:** thorough
+**Tool calls:** [N]
+**Duration:** [time]
+
+## Questions Addressed
+
+1. [Q1] → Answered (High confidence)
+2. [Q2] → Partial (Medium confidence)
+3. [Q3] → Unanswered (needs: [what would resolve])
+
+## LSP Findings
+
+### Symbol: [name]
+
+**Location:** `src/path/file.ts:42`
+**Type:** [type signature from hover]
+
+**Callers (incoming):**
+
+- `src/a.ts:10` - [context]
+- `src/b.ts:25` - [context]
+
+**Dependencies (outgoing):**
+
+- `src/utils.ts:15` - [what it calls]
+
+**References:** [N] usages across [M] files
+
+---
+
+## Pattern Analysis
+
+### Pattern 1: [Name]
+
+**Files:** `src/a.ts`, `src/b.ts`
+**Confidence:** High
+**Evidence:** [LSP + grep findings]
+
+[Description of pattern]
+
+---
+
+## Key Findings
+
+### [Finding 1]
+
+**Confidence:** High
+**Sources:** LSP goToDefinition, findReferences
+**Evidence:** `src/file.ts:42-56`
+
+[Finding with code evidence]
+
+---
+
+## Recommendations
+
+Based on LSP analysis:
+
+1. [Recommendation 1] - because [LSP evidence]
+2. [Recommendation 2] - because [pattern found]
+
+## Open Items
+
+- [Remaining question] - needs: [specific tool/info]
+```
+
+## Integration Points
+
+### Scout Agent Deep Mode
+
+When scout enters deep mode, load this skill:
+
+```typescript
+skill({ name: "deep-research" });
+```
+
+Scout then follows the protocol for external + internal analysis.
+
+### Research Command --thorough
+
+When `/research <topic> --thorough` is invoked:
+
+```typescript
+skill({ name: "deep-research" });
+// Follow full protocol with ~100 tool budget
+```
+
+### Pre-Edit Verification
+
+Before any complex edit:
+
+```typescript
+skill({ name: "deep-research" });
+// Run Phase 2 (LSP) on all symbols being modified
+// Proceed only when all 9 operations complete
+```
+
+## Workflow Example
+
+**Scenario:** Understanding authentication middleware before adding rate limiting.
+
+```typescript
+// Phase 1: Memory check
+memory_search({ query: "authentication middleware rate limiting" });
+memory_read({ file: "project/architecture" });
+
+// Phase 2: Delegate LSP exploration to explore agent
+task({
+  subagent_type: "explore",
+  description: "Analyze auth middleware",
+  prompt: `Very thorough LSP analysis of authentication middleware.
+
+Target: src/middleware/auth.ts
+
+Questions:
+1. What functions are exported from auth.ts?
+2. What calls the auth middleware? (incoming calls)
+3. What does it depend on? (outgoing calls)
+4. Are there existing rate limiting patterns?
+
+Return file:line references for all findings.`,
+});
+
+// Phase 3: Pattern discovery (parallel with Phase 2)
+grep({ pattern: "middleware", include: "*.ts" });
+grep({ pattern: "rateLimit", include: "*.ts" });
+glob({ pattern: "src/middleware/*.ts" });
+
+// Phase 4: External (if patterns unclear)
+context7_resolve_library_id({ libraryName: "express" });
+context7_query_docs({ libraryId: "/expressjs/express", topic: "middleware" });
+
+// Document findings
+write({
+  filePath: ".beads/artifacts/<id>/research.md",
+  content: "# Deep Research: Auth Middleware...",
+});
+```
+
+## Anti-Patterns
+
+### DON'T: Skip LSP Exploration
+
+```typescript
+// Bad: Reading file without LSP analysis
+read({ filePath: "src/auth.ts" });
+// Then immediately editing...
+
+// Good: Delegate to explore agent first
+task({
+  subagent_type: "explore",
+  description: "Analyze auth.ts",
+  prompt: "Very thorough LSP analysis of src/auth.ts...",
+});
+// Then edit with understanding
+```
+
+### DON'T: Ignore Memory
+
+```typescript
+// Bad: Jumping straight to exploration
+grep({ pattern: "auth", include: "*.ts" });
+
+// Good: Check memory first
+memory_search({ query: "authentication patterns" });
+// Only explore if memory doesn't answer
+```
+
+### DON'T: Mix Confidence Levels
+
+```typescript
+// Bad: Treating speculation as fact
+"This function definitely handles X"; // Without LSP verification
+
+// Good: Explicit confidence
+"Based on LSP findReferences (High confidence): This function is called from...";
+"Inference (Low confidence): This might also handle X, needs verification";
+```
+
+### DON'T: Exceed Budget Without Stopping
+
+```typescript
+// Bad: 150 tool calls on thorough mode
+// Keep going indefinitely...
+
+// Good: Track and stop
+// Tool call 95: Still finding new insights, continue
+// Tool call 100: Stopping at budget, documenting partial findings
+```
+
+## Success Criteria
+
+Research is complete when:
+
+- [ ] Memory checked before exploration
+- [ ] All 9 LSP operations run on target symbols
+- [ ] Confidence scores assigned to all findings
+- [ ] Tool budget respected
+- [ ] Findings documented with evidence
+- [ ] Open items listed with resolution paths
+
+## Quick Reference
+
+```
+PROTOCOL:
+1. Memory first → skip if found
+2. Delegate LSP to @explore (very thorough)
+3. Patterns → grep + glob (parallel)
+4. External → only if needed
+
+DELEGATION:
+task({ subagent_type: "explore", prompt: "Very thorough LSP analysis..." })
+
+CONFIDENCE:
+High = LSP + tests + docs
+Medium = LSP only
+Low = inference
+None = discard
+
+BUDGET:
+quick ~10 | default ~30 | thorough ~100
+
+STOP WHEN:
+- Questions answered (Medium+)
+- Budget exhausted
+- 5 calls with no new insights
+- Blocked on human input
+```

package/dist/template/.opencode/tool/oracle.ts

@@ -0,0 +1,240 @@
+import { tool } from "@opencode-ai/plugin";
+
+/**
+ * Oracle Tool - Get second opinions from alternative AI models
+ *
+ * Uses ProxyPal to access various models for:
+ * - Validating complex architectural decisions
+ * - Cross-checking debugging hypotheses
+ * - Getting alternative perspectives on tricky problems
+ * - Breaking out of reasoning ruts
+ */
+
+// Default to Gemini 3 Pro for deep reasoning (has thinking capability)
+const DEFAULT_MODEL = "gpt-5.2-codex";
+
+// Available oracle models with their strengths
+const ORACLE_MODELS: Record<string, { name: string; strength: string }> = {
+  "gpt-5.2-codex": {
+    name: "GPT-5.2 Codex",
+    strength: "Strong code understanding and generation",
+  },
+  "gemini-3-pro-preview": {
+    name: "Gemini 3 Pro",
+    strength: "Deep reasoning with thinking capability",
+  },
+};
+
+interface OracleRequest {
+  question: string;
+  context?: string;
+  model?: string;
+  mode?: "validate" | "alternative" | "critique" | "brainstorm";
+}
+
+interface ChatMessage {
+  role: "system" | "user" | "assistant";
+  content: string;
+}
+
+interface ChatResponse {
+  choices?: Array<{
+    message?: {
+      content?: string;
+    };
+  }>;
+  error?: {
+    message?: string;
+  };
+}
+
+const SYSTEM_PROMPTS: Record<string, string> = {
+  validate: `You are a validation oracle. Your job is to critically examine the reasoning, approach, or solution presented to you. 
+
+Look for:
+- Logical flaws or gaps in reasoning
+- Edge cases that weren't considered
+- Assumptions that may not hold
+- Better alternatives if they exist
+
+Be direct and specific. If the approach is sound, say so briefly. If there are issues, explain them clearly.`,
+
+  alternative: `You are an alternative perspective oracle. Your job is to suggest completely different approaches to the problem.
+
+Focus on:
+- Different architectural patterns
+- Alternative technologies or libraries
+- Unconventional but valid solutions
+- Trade-offs the user may not have considered
+
+Don't just validate - actively look for different ways to solve the problem.`,
+
+  critique: `You are a critical review oracle. Your job is to stress-test ideas and find weaknesses.
+
+Examine:
+- Security implications
+- Performance concerns
+- Maintainability issues
+- Scalability problems
+- Edge cases and failure modes
+
+Be constructively critical. Point out problems but suggest how to address them.`,
+
+  brainstorm: `You are a brainstorming oracle. Your job is to expand on ideas and generate new possibilities.
+
+Generate:
+- Extensions to the proposed approach
+- Creative variations
+- Combinations with other techniques
+- Future-proofing considerations
+
+Be generative and expansive. Build on the ideas presented.`,
+};
+
+export default tool({
+  description: `Get a second opinion from a different AI model for complex reasoning tasks.
+
+Use when:
+- Validating architectural decisions before implementing
+- Cross-checking debugging hypotheses
+- Getting alternative perspectives on tricky problems
+- Breaking out of reasoning ruts or confirmation bias
+
+Modes:
+- validate: Check if reasoning is sound (default)
+- alternative: Get completely different approaches
+- critique: Stress-test ideas for weaknesses
+- brainstorm: Expand and generate new possibilities
+
+Models available:
+${Object.entries(ORACLE_MODELS)
+  .map(([id, info]) => `- ${id}: ${info.strength}`)
+  .join("\n")}
+
+Examples:
+  oracle({ question: "Is JWT the right choice for this API?", context: "Building a microservices auth system" })
+  oracle({ question: "Review this debugging approach", mode: "critique" })
+  oracle({ question: "What other ways could we implement caching?", mode: "alternative", model: "gpt-5.2-codex" })
+`,
+  args: {
+    question: tool.schema
+      .string()
+      .describe("The question or problem to get a second opinion on"),
+    context: tool.schema
+      .string()
+      .optional()
+      .describe(
+        "Additional context about the problem, constraints, or current approach",
+      ),
+    model: tool.schema
+      .string()
+      .optional()
+      .describe(
+        `Model to use for oracle (default: ${DEFAULT_MODEL}). Options: ${Object.keys(ORACLE_MODELS).join(", ")}`,
+      ),
+    mode: tool.schema
+      .string()
+      .optional()
+      .describe(
+        "Oracle mode: validate (default), alternative, critique, or brainstorm",
+      ),
+  },
+  execute: async (args) => {
+    const {
+      question,
+      context,
+      model = DEFAULT_MODEL,
+      mode = "validate",
+    } = args as OracleRequest;
+
+    if (!question || question.trim() === "") {
+      return "Error: question is required";
+    }
+
+    // Validate model
+    const modelInfo = ORACLE_MODELS[model];
+    if (!modelInfo) {
+      return `Error: Unknown model "${model}". Available models: ${Object.keys(ORACLE_MODELS).join(", ")}`;
+    }
+
+    // Validate mode
+    const validModes = ["validate", "alternative", "critique", "brainstorm"];
+    if (!validModes.includes(mode)) {
+      return `Error: Unknown mode "${mode}". Available modes: ${validModes.join(", ")}`;
+    }
+
+    // Get system prompt for mode
+    const systemPrompt = SYSTEM_PROMPTS[mode];
+
+    // Build user message
+    let userMessage = question;
+    if (context) {
+      userMessage = `Context:\n${context}\n\nQuestion:\n${question}`;
+    }
+
+    const messages: ChatMessage[] = [
+      { role: "system", content: systemPrompt },
+      { role: "user", content: userMessage },
+    ];
+
+    // Call ProxyPal API
+    const PROXYPAL_BASE = "http://127.0.0.1:8317/v1";
+
+    try {
+      const response = await fetch(`${PROXYPAL_BASE}/chat/completions`, {
+        method: "POST",
+        headers: {
+          "Content-Type": "application/json",
+          Authorization: "Bearer proxypal-local",
+        },
+        body: JSON.stringify({
+          model,
+          messages,
+          temperature: 0.7,
+          max_tokens: 4096,
+        }),
+      });
+
+      if (!response.ok) {
+        const errorText = await response.text();
+        return `Error: Oracle API returned ${response.status}: ${errorText}`;
+      }
+
+      const data = (await response.json()) as ChatResponse;
+
+      if (data.error) {
+        return `Error: ${data.error.message || "Unknown error from oracle"}`;
+      }
+
+      const content = data.choices?.[0]?.message?.content;
+      if (!content) {
+        return "Error: Oracle returned empty response";
+      }
+
+      // Format response with metadata
+      return `## Oracle Response (${modelInfo.name})
+**Mode**: ${mode}
+**Strength**: ${modelInfo.strength}
+
+---
+
+${content}
+
+---
+*Second opinion from ${model}*`;
+    } catch (error: unknown) {
+      const message = error instanceof Error ? error.message : String(error);
+
+      if (
+        message.includes("ECONNREFUSED") ||
+        message.includes("fetch failed")
+      ) {
+        return `Error: Cannot connect to ProxyPal at ${PROXYPAL_BASE}.
+
+To start ProxyPal, run: proxypal start`;
+      }
+
+      return `Error: Oracle query failed: ${message}`;
+    }
+  },
+});

package/package.json

@@ -1,8 +1,15 @@
 {
 	"name": "opencodekit",
-	"version": "0.15.13",
+	"version": "0.15.15",
 	"description": "CLI tool for bootstrapping and managing OpenCodeKit projects",
-	"keywords": ["agents", "cli", "mcp", "opencode", "opencodekit", "template"],
+	"keywords": [
+		"agents",
+		"cli",
+		"mcp",
+		"opencode",
+		"opencodekit",
+		"template"
+	],
 	"license": "MIT",
 	"author": "OpenCodeKit",
 	"repository": {
@@ -12,7 +19,10 @@
 	"bin": {
 		"ock": "dist/index.js"
 	},
-	"files": ["dist", "README.md"],
+	"files": [
+		"dist",
+		"README.md"
+	],
 	"type": "module",
 	"publishConfig": {
 		"access": "public",
@@ -56,5 +66,7 @@
 	"engines": {
 		"bun": ">=1.3.2"
 	},
-	"trustedDependencies": ["@beads/bd"]
+	"trustedDependencies": [
+		"@beads/bd"
+	]
 }