opencode-orchestrator 1.0.57 → 1.0.59

package/README.md

@@ -18,7 +18,6 @@
 npm install -g opencode-orchestrator
 ```
 
-
 In an OpenCode environment:
 ```bash
 /task "Implement"
@@ -43,7 +42,7 @@ This philosophy extends to efficiency. We achieved **Zero-Configuration** usabil
 ```text
               [ User Task Input ]
                         │
-            ┌───────────▼───────────┐ <────────────────────────────────────────┐
+            ┌───────────▼───────────┐ ◄────────────────────────────────────────┐
             │   🫡 COMMANDER (Hub)  │  (Orchestration)                         │
             └───────────┬───────────┘                                          │
                         │                                                      │
@@ -64,31 +63,41 @@ This philosophy extends to efficiency. We achieved **Zero-Configuration** usabil
      ╚══════╤═══════════╤═══════════╤══════╝                                   │
             │           │           │                                          │
      ┌──────▼───┐ ┌─────▼────┐ ┌────▼─────┐                                    │
-     │🔍REVIEWER│ │🔍REVIEWER│ │🔍REVIEWER│                                    │
+     │🔍REVIEWER│ │🔍REVIEWER│ │🔍REVIEWER│  (Module-level)                    │
      └──────┬───┘ └─────┬────┘ └────┬─────┘                                    │
             │           │           │                                          │
            ═▼═══════════▼═══════════▼═                                         │
-           │      🚦 SYNC BARRIER      │                                         │
+           │      🚦 SYNC BARRIER      │                                        │
            ═════════════╤═════════════                                         │
                         │                                                      │
             ┌───────────▼───────────┐                                          │
-            │ ✔️ MASTER REVIEWER    │  (E2E Verification)                      │
+            │  🎖️ MASTER REVIEWER   │  (Final Verification Authority)          │
+            │   ┌─────────────────┐ │                                          │
+            │   │ [x] Build Pass  │ │                                          │
+            │   │ [x] Tests Pass  │ │                                          │
+            │   │ [x] E2E Pass    │ │                                          │
+            │   │ [x] Sync OK     │ │                                          │
+            │   └─────────────────┘ │                                          │
             └───────────┬───────────┘                                          │
                         │                                                      │
               __________▼_________                                             │
-             ╱                    ╲    NO (Loop / Auto-Correction)             │
-            ╱   ✅ All TODOs?      ╲ ──────────────────────────────────────────┘
-            ╲   🛡️ Error Rate 0%?  ╱
+             ╱                    ╲    NO (Failure Summary → Commander)        │
+            ╱   ✅ All Checks Pass ╲ ──────────────────────────────────────────┘
+            ╲   🛡️ Sync Issues 0?  ╱   (Infinite Loopback Until Resolved)
              ╲____________________╱
                         │ YES
                         │
                 [ 🎖️ MISSION SEALED ]
+                        │
+            ┌───────────▼───────────┐
+            │   🔔 OS Notification  │
+            │   🎵 Success Sound    │
+            └───────────────────────┘
 ```
 
-
 ---
 
-## 🧠 Cognitive Architecture & Key Strengths
+## � Cognitive Architecture & Key Strengths
 
 ### 📉 Adaptive Context Gating (EMA-based)
 We combat "Context Drift" using a mechanism derived from **Exponential Moving Average (EMA)** algorithms. Irrelevant conversation noise follows a rapid decay curve, while critical architectural decisions are reinforced into **Stable Core Memory**. This functions as an **Attention Sink**, allowing agents to work indefinitely without **Catastrophic Forgetting**.
@@ -107,11 +116,22 @@ Pure LLM approaches are stochastic. We bind them with a **Neuro-Symbolic Archite
 The engine features an **Intelligent Load-Balancing System** that fluidly switches between synchronous barriers and asynchronous **Fork-Join** patterns. It monitors **System Backpressure** to dynamically adjust concurrency slots in real-time (`Adaptive Throttling`), maximizing throughput on high-end hardware while maintaining stability on constrained environments.
 
 ### 🎯 Iterative Rejection Sampling (Zero-Shot Defense)
-We employ a **Rejection Sampling Loop** driven by the Reviewer Agent (**Reward Model**). Through the **Metric-based Strict Verification Protocol (MSVP)**, code paths that fail execution tests are pruned. The system iterates until the solution converges on a mathematically correct state (0% Error Rate), rejecting any solution that lacks evidence.
+We employ a **Rejection Sampling Loop** driven by the Master Reviewer Agent (**Final Reward Model**). Through the **Metric-based Strict Verification Protocol (MSVP)**, code paths that fail execution tests are pruned. The system iterates until the solution converges on a mathematically correct state (0% Error Rate), rejecting any solution that lacks evidence.
 
 ### 🧩 Externalized Chain-of-Thought (CoT)
 The Planner's `TODO.md` serves as an **Externalized Working Memory** (Scratchpad). This persistent **Symbolic Chain-of-Thought** decouples detailed planning from the LLM's immediate context window, enabling the orchestration of massive, multi-step engineering tasks without logical degradation.
 
+### 🔄 Hierarchical Verification Pipeline (MVP)
+The system employs a **Multi-Stage Verification Pipeline**:
+1. **Module-Level**: Reviewers verify individual Worker outputs (unit tests, type checks)
+2. **System-Level**: Master Reviewer performs comprehensive E2E verification
+3. **Loopback**: Failed checks trigger automatic re-planning and correction cycles
+
+This separation of concerns ensures both granular code quality and holistic system integrity.
+
+### 🌍 Environment-Agnostic Verification
+The Master Reviewer **auto-detects** project environments (Node.js, Rust, Python, Java, Go, C/C++, Docker, etc.) and adapts verification strategies accordingly. No hardcoded assumptions—true polyglot support.
+
 ---
 
 ## ⚡ Agents
@@ -119,9 +139,10 @@ The Planner's `TODO.md` serves as an **Externalized Working Memory** (Scratchpad
 | Agent | Role |
 |:------|:-----|
 | **Commander** | Orchestrates the mission, manages parallel threads and sync barriers |
-| **Planner** | Architecture architect. Breaks downtasks into strictly defined steps |
+| **Planner** | Architecture architect. Breaks down tasks into strictly defined steps |
 | **Worker** | The builder. Writes code and corresponding unit tests |
-| **Reviewer** | The gatekeeper. Rejects any code that doesn't pass execution verification |
+| **Reviewer** | Module-level gatekeeper. Verifies Worker outputs with build/test execution |
+| **Master Reviewer** | 🎖️ Final verification authority. Runs comprehensive E2E tests and holds **exclusive SEAL rights** |
 
 ---
 
@@ -131,10 +152,11 @@ The Planner's `TODO.md` serves as an **Externalized Working Memory** (Scratchpad
 
 [System Architecture →](docs/SYSTEM_ARCHITECTURE.md)
 
-[Architectural Verification Report →](docs/ARCHITECTURAL_VERIFICATION_REPORT.md)
-
 ---
 
 ## 📄 License
 
 MIT License. See [LICENSE](LICENSE) for details.
+
+
+

package/dist/agents/definitions.d.ts

@@ -6,6 +6,7 @@
  * - Planner: Planning + Research
  * - Worker: Implementation + Documentation
  * - Reviewer: Verification + Context Management
+ * - Master Reviewer: Final verification authority (SEAL rights)
  */
 import type { AgentDefinition } from "../shared/agent/interfaces/index.js";
 export declare const AGENTS: Record<string, AgentDefinition>;

package/dist/agents/prompts/discovery/index.d.ts

@@ -0,0 +1,3 @@
+export * from "./environment.js";
+export * from "./workspace.js";
+export * from "./skills.js";

package/dist/agents/prompts/execution/delegation.d.ts

@@ -0,0 +1 @@
+export declare const DELEGATION_RULES: string;

package/dist/agents/prompts/execution/index.d.ts

@@ -0,0 +1,9 @@
+export * from "./parallel.js";
+export * from "./delegation.js";
+export * from "./file-assignment.js";
+export * from "./workflow.js";
+export * from "./hyper-parallel.js";
+export * from "./tdd.js";
+export * from "./isolation.js";
+export * from "./strategy.js";
+export * from "./quality.js";

package/dist/agents/prompts/index.d.ts

@@ -1,11 +1,17 @@
 /**
  * Agent Prompts - Index
  *
- * Exports all modular prompt fragments.
- * Structure: 1 folder per agent/category, 1 file per const
+ * Exports all modular prompt fragments from the new structure.
  */
-export * from "./common/index.js";
-export * from "./commander/index.js";
-export * from "./planner/index.js";
-export * from "./worker/index.js";
-export * from "./reviewer/index.js";
+export * from "./philosophy/index.js";
+export * from "./mission/index.js";
+export * from "./verification/index.js";
+export * from "./planning/index.js";
+export * from "./execution/index.js";
+export * from "./discovery/index.js";
+export * from "./tools/index.js";
+export * from "./roles/commander/index.js";
+export * from "./roles/planner/index.js";
+export * from "./roles/worker/index.js";
+export * from "./roles/reviewer/index.js";
+export * from "./roles/master-reviewer/index.js";

package/dist/agents/prompts/mission/index.d.ts

@@ -0,0 +1,4 @@
+export * from "./seal-conditions.js";
+export * from "./loop-continuation.js";
+export * from "./status-tracking.js";
+export * from "./recovery.js";

package/dist/agents/prompts/mission/seal-conditions.d.ts

@@ -0,0 +1 @@
+export declare const SEAL_CONDITIONS: string;

package/dist/agents/prompts/mission/status-tracking.d.ts

@@ -0,0 +1 @@
+export declare const MISSION_STATUS_FORMAT: string;

package/dist/agents/prompts/philosophy/execution-assurance.d.ts

@@ -0,0 +1 @@
+export declare const EXECUTION_ASSURANCE = "<execution_assurance>\n## L0-L7 Execution Assurance Levels\n\n| Level | Scope | Requirement |\n|-------|-------|-------------|\n| **L0** | Syntax | Valid code, no parse errors |\n| **L1** | Static | Linting passes, Types check |\n| **L2** | Unit | Individual functions/classes tested |\n| **L3** | Module | Component integration works |\n| **L4** | Build | Project compiles/bundles successfully |\n| **L5** | Integration | Cross-module/System APIs work |\n| **L6** | E2E | Full flow works from user perspective |\n| **L7** | Verification | Mission requirements met (SEALED) |\n\n**Rule:** You must achieve the highest possible Level for the current task.\n- Never settle for L0/L1 if L2+ is possible.\n- L4 (Build) is a GATEKEEPER. If build fails, nothing else matters.\n</execution_assurance>";

package/dist/agents/prompts/philosophy/index.d.ts

@@ -0,0 +1,4 @@
+export * from "./core.js";
+export * from "./execution-assurance.js";
+export * from "./anti-hallucination.js";
+export * from "./modularity.js";

package/dist/agents/prompts/planning/decomposition.d.ts

@@ -0,0 +1 @@
+export declare const TASK_DECOMPOSITION = "<decomposition_rules>\n## Task Decomposition Rules\n\nWhen a task is too large or complex:\n1. **Break it down** into atomic steps (max 1 file or 1 logical unit per step).\n2. **Update TODO**: Replace the large task with subtasks T[N.1], T[N.2], etc.\n3. **Verify Atomic Success**: Each subtask must be verifiable independently (L2+).\n\nIf stuck:\n- Do not retry the same failing action more than twice.\n- Decompose the problem into smaller investigation steps.\n- Create a specific \"Research\" task to find the root cause.\n</decomposition_rules>";

package/dist/agents/prompts/planning/index.d.ts

@@ -0,0 +1,8 @@
+export * from "./todo-format.js";
+export * from "./todo-rules.js";
+export * from "./file-planning.js";
+export * from "./decomposition.js";
+export * from "./todo-sync.js";
+export * from "./reviewer-todo-update.js";
+export * from "./research.js";
+export * from "./planner-todo.js";

package/dist/agents/prompts/roles/commander/index.d.ts

@@ -0,0 +1,4 @@
+export * from "./identity.js";
+export * from "./forbidden.js";
+export * from "./required.js";
+export * from "./role.js";

package/dist/agents/prompts/roles/master-reviewer/capabilities.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Master Reviewer Capabilities
+ *
+ * What the Master Reviewer IS ALLOWED to do.
+ * Environment-agnostic, flexible for any project type.
+ */
+export declare const MASTER_REVIEWER_CAPABILITIES: string;

package/dist/agents/prompts/roles/master-reviewer/forbidden.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Master Reviewer Forbidden Actions
+ *
+ * Actions that the Master Reviewer must NEVER do.
+ * For allowed actions, see capabilities.ts
+ */
+export declare const MASTER_REVIEWER_FORBIDDEN: string;

package/dist/agents/prompts/roles/master-reviewer/identity.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Master Reviewer Role Identity
+ *
+ * The Master Reviewer is the FINAL GATE before mission completion.
+ * Only the Master Reviewer can authorize SEAL.
+ */
+export declare const MASTER_REVIEWER_ROLE: string;

package/dist/agents/prompts/roles/master-reviewer/index.d.ts

@@ -0,0 +1,8 @@
+/**
+ * Master Reviewer Prompts Index
+ */
+export { MASTER_REVIEWER_ROLE } from "./identity.js";
+export { MASTER_REVIEWER_VERIFICATION_PROCESS } from "./verification-process.js";
+export { MASTER_REVIEWER_SEAL_AUTHORITY } from "./seal-authority.js";
+export { MASTER_REVIEWER_FORBIDDEN } from "./forbidden.js";
+export { MASTER_REVIEWER_CAPABILITIES } from "./capabilities.js";

package/dist/agents/prompts/roles/master-reviewer/seal-authority.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Master Reviewer Seal Authority
+ *
+ * The decision protocol for when to SEAL or return failure.
+ * Emphasizes the infinite loop until all problems are resolved.
+ */
+export declare const MASTER_REVIEWER_SEAL_AUTHORITY: string;

package/dist/agents/prompts/roles/master-reviewer/verification-process.d.ts

@@ -0,0 +1,8 @@
+/**
+ * Master Reviewer Verification Process
+ *
+ * Environment-agnostic comprehensive verification workflow.
+ * Works for ANY project type: Node, Rust, Java, Python, C/C++, Go,
+ * containers, kernel development, AI/ML, embedded systems, etc.
+ */
+export declare const MASTER_REVIEWER_VERIFICATION_PROCESS: string;

package/dist/agents/prompts/roles/planner/index.d.ts

@@ -0,0 +1,3 @@
+export * from "./identity.js";
+export * from "./forbidden.js";
+export * from "./required.js";

package/dist/agents/prompts/roles/reviewer/forbidden.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Reviewer Forbidden Actions
+ *
+ * Module-level verification only.
+ * Reviewer is a TERMINAL node and cannot spawn other agents or output SEAL.
+ */
+export declare const REVIEWER_FORBIDDEN: string;

package/dist/agents/prompts/roles/reviewer/identity.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Reviewer Role
+ *
+ * Module-level verification specialist.
+ * Verifies individual Worker tasks, NOT final mission completion.
+ */
+export declare const REVIEWER_ROLE: string;

package/dist/agents/prompts/roles/reviewer/index.d.ts

@@ -0,0 +1,3 @@
+export * from "./identity.js";
+export * from "./forbidden.js";
+export * from "./required.js";

package/dist/agents/prompts/roles/worker/index.d.ts

@@ -0,0 +1,3 @@
+export * from "./identity.js";
+export * from "./forbidden.js";
+export * from "./required.js";

package/dist/agents/prompts/tools/index.d.ts

@@ -0,0 +1,5 @@
+export * from "./lsp.js";
+export * from "./ast.js";
+export * from "./search.js";
+export * from "./reviewer-lsp.js";
+export * from "./worker-lsp.js";

package/dist/agents/prompts/tools/search.d.ts

@@ -0,0 +1 @@
+export declare const SEARCH_TOOLS: string;

package/dist/agents/prompts/verification/evidence.d.ts

@@ -0,0 +1 @@
+export declare const EVIDENCE_FORMAT: string;

package/dist/agents/prompts/verification/index.d.ts

@@ -0,0 +1,7 @@
+export * from "./process.js";
+export * from "./integration.js";
+export * from "./sync-check.js";
+export * from "./sync-handling.js";
+export * from "./evidence.js";
+export * from "./async-monitoring.js";
+export * from "./reviewer-process.js";

package/dist/agents/prompts/verification/integration.d.ts

@@ -0,0 +1,7 @@
+/**
+ * Reviewer Integration Testing
+ *
+ * Individual file/module integration checks.
+ * Full E2E and final verification is handled by Master Reviewer.
+ */
+export declare const REVIEWER_INTEGRATION_TESTING: string;

package/dist/agents/prompts/{reviewer/sync-verification.d.ts → verification/sync-check.d.ts}

@@ -2,5 +2,7 @@
  * Reviewer Sync Verification
  *
  * Verify file synchronization and report issues for next iteration.
+ * Note: Final SEAL is handled by Master Reviewer, not Reviewer.
+ * Environment-agnostic - works for any project type.
  */
 export declare const REVIEWER_SYNC_VERIFICATION: string;

package/dist/agents/subagents/master-reviewer.d.ts

@@ -0,0 +1,14 @@
+/**
+ * Master Reviewer Agent (Subagent)
+ *
+ * FINAL VERIFICATION AUTHORITY - Only agent that can authorize SEAL.
+ * Runs comprehensive verification before mission completion.
+ *
+ * Responsibilities:
+ * - Create and execute verification checklist
+ * - Run all verification checks (build, test, e2e, environment)
+ * - Mark checklist items with evidence
+ * - Output SEAL or return failure summary to Commander
+ */
+import type { AgentDefinition } from "../../shared/agent/interfaces/index.js";
+export declare const masterReviewer: AgentDefinition;

package/dist/core/loop/verification.d.ts

@@ -0,0 +1,62 @@
+/**
+ * Verification Checklist Module
+ *
+ * Provides a structured checklist system for mission completion verification.
+ *
+ * The LLM creates and checks items in .opencode/verification-checklist.md
+ * The hook system verifies all items are checked before allowing SEAL.
+ *
+ * This approach:
+ * 1. LLM discovers environment and creates appropriate checklist items
+ * 2. LLM executes and marks items as complete
+ * 3. Hook verifies all items are checked (hard gate)
+ */
+import { type ChecklistCategory, type ChecklistItem, type ChecklistVerificationResult, type VerificationResult } from "../../shared/index.js";
+export type { ChecklistItem, ChecklistCategory, ChecklistVerificationResult, VerificationResult };
+/** Path to the verification checklist file (re-export for convenience) */
+export declare const CHECKLIST_FILE: ".opencode/verification-checklist.md";
+/**
+ * Parse checklist from markdown content
+ */
+export declare function parseChecklist(content: string): ChecklistItem[];
+/**
+ * Read checklist from file
+ */
+export declare function readChecklist(directory: string): ChecklistItem[];
+/**
+ * Verify that all checklist items are complete
+ */
+export declare function verifyChecklist(directory: string): ChecklistVerificationResult;
+/**
+ * Quick check if checklist exists and has items
+ */
+export declare function hasValidChecklist(directory: string): boolean;
+/**
+ * Get checklist summary for display
+ */
+export declare function getChecklistSummary(directory: string): string;
+/**
+ * Build prompt for when checklist verification fails
+ */
+export declare function buildChecklistFailurePrompt(result: ChecklistVerificationResult): string;
+/**
+ * Build checklist creation prompt (for inclusion in agent prompts)
+ */
+export declare function getChecklistCreationInstructions(): string;
+/**
+ * Verify mission completion conditions
+ *
+ * Checks (in order):
+ * 1. Verification checklist (primary - if exists)
+ * 2. TODO completion rate (fallback)
+ * 3. Sync issues (always checked)
+ */
+export declare function verifyMissionCompletion(directory: string): VerificationResult;
+/**
+ * Build prompt for when SEAL is rejected due to verification failure
+ */
+export declare function buildVerificationFailurePrompt(result: VerificationResult): string;
+/**
+ * Build a concise status summary for logs
+ */
+export declare function buildVerificationSummary(result: VerificationResult): string;