opencode-orchestrator 1.0.12 → 1.0.14

package/README.md

@@ -20,7 +20,7 @@ npm install -g opencode-orchestrator
 
 Then in OpenCode, launch your mission:
 ```bash
-/swarm "Architect and Build a Diablo-like Web Game"
+/task "Architect and Build a Diablo-like Web Game"
 ```
 
 ### 🌌 **The End of Sequential Limits. The Era of Fractal Mastery.**
@@ -88,14 +88,22 @@ MSVP ensures continuous integration integrity by decoupling verification from th
 *   **Global Barrier-Sync Protocol**: Implements a synchronized verification gate. The system enforces a blocking "Barrier" that requires consistency across all distributed units before transitioning to the final Master Review (E2E Integration) and Mission Sealing.
 
 ```
-              /swarm "Build Diablo Game"
+              /task "Build Diablo Game"
                            │
            ╔═══════════════════════════════════════╗
            ║     🎯 COMMANDER — Orchestrator       ║
            ║        (Main Session - Single)        ║
            ╚═══════════════════╤═══════════════════╝
                                │
-           ┌───────────────────▼───────────────────┐
+    ══════════════════════════▼══════════════════════════
+    ║          🚀 PHASE 0: DISCOVERY SWARM (Parallel)      ║
+    ══════════════════════════════════════════════════════
+    │               │               │               │
+    ▼ Scout         ▼ Scout         ▼ Scout         ▼ Scout
+ [Structure]      [Stack]         [Docs]          [Infra]
+    └───────────────┬───────────────┬───────────────┘
+                    │ Consolidate & Sync
+           ┌────────▼───────────────────┐
            │      📋 PLANNER — Create Plan         │
            │    → Outputs: Architectural Grid      │
            └───────────────────┬───────────────────┘

package/dist/index.js

@@ -268,6 +268,52 @@ var WAL_ACTIONS = {
   DELETE: "DELETE"
 };
 
+// src/shared/core/constants/phases.ts
+var PHASES = {
+  PHASE_0: {
+    ID: "PHASE_0",
+    NAME: "DISCOVERY SWARM",
+    DESCRIPTION: "Parallel intelligence gathering and project mapping",
+    MANDATORY: true
+  },
+  PHASE_1: {
+    ID: "PHASE_1",
+    NAME: "THINK",
+    DESCRIPTION: "Analyze scope, decomposition, and delegation",
+    MANDATORY: true
+  },
+  PHASE_2: {
+    ID: "PHASE_2",
+    NAME: "TRIAGE",
+    DESCRIPTION: "Complexity assessment and execution path selection",
+    MANDATORY: true
+  },
+  PHASE_3: {
+    ID: "PHASE_3",
+    NAME: "PLAN",
+    DESCRIPTION: "Architectural roadmap and task grid creation",
+    MANDATORY: true
+  },
+  PHASE_4: {
+    ID: "PHASE_4",
+    NAME: "EXECUTE",
+    DESCRIPTION: "HPFA grid execution and worker coordination",
+    MANDATORY: true
+  },
+  PHASE_5: {
+    ID: "PHASE_5",
+    NAME: "VERIFY",
+    DESCRIPTION: "MSVP final gate and E2E system validation",
+    MANDATORY: true
+  },
+  PHASE_6: {
+    ID: "PHASE_6",
+    NAME: "SEAL",
+    DESCRIPTION: "Mission completion and deterministic output",
+    MANDATORY: true
+  }
+};
+
 // src/shared/core/constants/cli.ts
 var CLI_NAME = {
   NPX: "npx",
@@ -631,7 +677,7 @@ var PROMPTS = {
 
 // src/shared/message/constants/slash-commands.ts
 var COMMAND_NAMES = {
-  TASK: "swarm",
+  TASK: "task",
   PLAN: "plan",
   STATUS: "status",
   STOP: "stop",
@@ -13312,6 +13358,12 @@ tool.schema = external_exports;
 var ENVIRONMENT_DISCOVERY = `${PROMPT_TAGS.ENVIRONMENT_DISCOVERY.open}
 **MANDATORY FIRST STEP** - Before any planning or coding:
 
+## \u26A1 Parallel Discovery Strategy
+To maximize cognitive velocity, execute Phase 0 as a **Parallel Discovery Swarm**:
+1. **Delegate** independent scouts (background=true) for Structure, Stack, and Infra discovery.
+2. **Consolidate** all empirical evidence once scouts complete their missions.
+3. **Verify** findings against existing codebase before sealing the initial context.
+
 ## 1. Project Structure Discovery
 Explore the project root to understand its organization:
 \`\`\`bash
@@ -13853,18 +13905,21 @@ ${PROMPT_TAGS.TOOLS.close}`;
 
 // src/agents/prompts/commander/execution.ts
 var COMMANDER_EXECUTION = `${PROMPT_TAGS.EXECUTION_STRATEGY.open}
-## Phase 0: ENVIRONMENT DISCOVERY (Never skip!)
-1. Initialize ${PATHS.OPENCODE}/ folder:
-   - If exists \u2192 DELETE and CREATE fresh
-   - If not exists \u2192 CREATE new
-   - This folder is for CONTEXT SHARING between agents
-2. Analyze project structure (ls, find)
-3. Read README.md, package.json, Dockerfile
-4. Identify build/test commands
-5. Save context to ${PATHS.CONTEXT}
-
-## Phase 1: THINK (Mandatory - Never Skip!)
-**THINK FIRST**: As ${AGENT_NAMES.COMMANDER}, think about ORCHESTRATION before action.
+## ${PHASES.PHASE_0.ID}: ${PHASES.PHASE_0.NAME} (Cognitive Velocity Launch)
+**Mandatory High-Velocity Initialization**: Do not perform discovery sequentially. Launch a swarm of scouts immediately.
+
+1. **Initialize \`${PATHS.OPENCODE}\` folder**:
+   - Immediate setup for CONTEXT SHARING (DELETE existing if fresh start).
+2. **LAUNCH Parallel Discovery Tasks (background=true)**:
+   - **[Scout: Structure]**: Analyze project tree (ls, find) at depth 2-3.
+   - **[Scout: Stack]**: Parse package.json, Cargo.toml, or pyproject.toml for identity.
+   - **[Scout: Docs]**: Analyze README.md, CONTRIBUTING.md, and core architecture docs.
+   - **[Scout: Infra]**: Detect Docker, CI/CD pipelines, and environment variables.
+3. **BARRIER SYNC & RETRIEVE**: Monitor scouts. Once finished, **READ all scout results** and \`${PATHS.CONTEXT}\` to ingest all findings.
+4. **SET TARGET**: Use the unified context to proceed to Phase 1.
+
+## ${PHASES.PHASE_1.ID}: ${PHASES.PHASE_1.NAME} (Mandatory - Never Skip!)
+**THINK FIRST**: As ${AGENT_NAMES.COMMANDER}, think about ORCHESTRATION and synthesis before action.
 
 ### 1.1 MISSION SCOPE
 - What is the FULL scope of this mission?
@@ -13887,31 +13942,32 @@ var COMMANDER_EXECUTION = `${PROMPT_TAGS.EXECUTION_STRATEGY.open}
 - How will I DETECT and RECOVER from issues?
 - If agent fails \u2192 See ${PROMPT_TAGS.RECOVERY.open} section: DECOMPOSE and retry
 
-**ANTI-PATTERNS**: Sequential execution when parallel is possible. Doing work yourself instead of delegating. Starting without clear decomposition.
+**ANTI-PATTERNS**: Sequential execution when parallel is possible. Doing work yourself instead of delegating. Starting without clear decomposition or intellectual synthesis.
 
-## Phase 2: TRIAGE
+## ${PHASES.PHASE_2.ID}: ${PHASES.PHASE_2.NAME}
 | Type | Signal | Approach |
 |------|--------|----------|
 | ${WORK_STATUS.TRIAGE.TYPE.SIMPLE} | ${WORK_STATUS.TRIAGE.SIGNAL.ONE_FILE} | ${WORK_STATUS.TRIAGE.APPROACH.DIRECT} |
 | ${WORK_STATUS.TRIAGE.TYPE.MEDIUM} | ${WORK_STATUS.TRIAGE.SIGNAL.MULTI_FILE} | ${WORK_STATUS.TRIAGE.APPROACH.PLAN_EXECUTE_VERIFY} |
 | ${WORK_STATUS.TRIAGE.TYPE.COMPLEX} | ${WORK_STATUS.TRIAGE.SIGNAL.LARGE_SCOPE} | ${WORK_STATUS.TRIAGE.APPROACH.RESEARCH_PLAN_PARALLEL} |
 
-## Phase 3: PLAN (for ${WORK_STATUS.TRIAGE.TYPE.MEDIUM}/${WORK_STATUS.TRIAGE.TYPE.COMPLEX})
+## ${PHASES.PHASE_3.ID}: ${PHASES.PHASE_3.NAME} (for ${WORK_STATUS.TRIAGE.TYPE.MEDIUM}/${WORK_STATUS.TRIAGE.TYPE.COMPLEX})
 ${AGENT_NAMES.PLANNER} creates ${PATHS.TODO} with parallel groups
 
-## Phase 4: EXECUTE
+## ${PHASES.PHASE_4.ID}: ${PHASES.PHASE_4.NAME}
 1. LAUNCH all independent tasks simultaneously (background=true)
 2. MONITOR with ${TOOL_NAMES.LIST_TASKS}
 3. COLLECT results with ${TOOL_NAMES.GET_TASK_RESULT}
 4. CONTINUE with dependent tasks
 5. REPEAT until all [ ] become [x]
 
-## Phase 5: VERIFY
-${AGENT_NAMES.REVIEWER} validates ALL work
-${AGENT_NAMES.REVIEWER} runs tests, confirms pass
-Only proceed to seal if PASS
+## ${PHASES.PHASE_5.ID}: ${PHASES.PHASE_5.NAME}
+1. **STAGE 1 (Unit)**: Reviewers validate individual module changes (triggered by Workers).
+2. **STAGE 2 (Integration)**: ${AGENT_NAMES.REVIEWER} validates cross-module consistency.
+3. **E2E VALIDATION**: Run full system tests and build pass check.
+4. Only proceed to SEAL if all criteria are met with zero regressions.
 
-## Phase 6: SEAL
+## ${PHASES.PHASE_6.ID}: ${PHASES.PHASE_6.NAME}
 When ALL conditions met, output ${MISSION_SEAL.PATTERN}
 ${PROMPT_TAGS.EXECUTION_STRATEGY.close}`;
 
@@ -14611,14 +14667,15 @@ ADAPTIVE IMPLEMENTATION WORKFLOW
 8. Handle edge cases like existing code does
 9. Add tests matching project's test style
 
-## Phase 5: VERIFY (Before reporting)
+## Phase 5: VERIFY & TRIGGER SHADOW REVIEW
 10. Run ${TOOL_NAMES.LSP_DIAGNOSTICS} \u2192 Must be clean
+11. Run BUILD & TEST commands from ${PATHS.CONTEXT}
+12. **TRIGGER STAGE 1 REVIEW**: 
+    - Before finishing, ${TOOL_NAMES.DELEGATE_TASK} to **${AGENT_NAMES.REVIEWER}** for unit verification.
+    - Prompt: "Verify unit changes in [your module] for mission [mission_id]. Run tests and check diagnostics."
+13. Report completion WITH evidence (test logs, review status).
 
-11. Run BUILD command from ${PATHS.CONTEXT}
-12. Run TEST command from ${PATHS.CONTEXT}
-13. Report completion WITH evidence
-
-**CRITICAL**: Do NOT mark [x] in ${PATHS.TODO} - that's ${AGENT_NAMES.REVIEWER}'s job!
+**CRITICAL**: Do NOT mark [x] in ${PATHS.TODO} - that's ${AGENT_NAMES.REVIEWER}'s job after Stage 2!
 ${PROMPT_TAGS.WORKFLOW.close}`;
 
 // src/agents/prompts/worker/quality.ts
@@ -15532,7 +15589,7 @@ $ARGUMENTS
 </execution_rules>
 </mission>`;
 var COMMANDS = {
-  "swarm": {
+  "task": {
     description: "MISSION MODE - Execute task autonomously until complete",
     template: MISSION_MODE_TEMPLATE,
     argumentHint: '"mission goal"'
@@ -15593,7 +15650,7 @@ THINK \u2192 PLAN \u2192 DELEGATE \u2192 EXECUTE \u2192 VERIFY \u2192 COMPLETE
 
 ## Usage
 - Select **${AGENT_NAMES.COMMANDER}** and type your request
-- Or use \`/swarm "your mission"\` explicitly
+- Or use \`/task "your mission"\` explicitly
 - ${AGENT_NAMES.COMMANDER} automatically coordinates all agents`
   }
 };

package/dist/shared/core/constants/index.d.ts

@@ -8,4 +8,5 @@ export { MEMORY_LIMITS } from "./memory-limits.js";
 export { STATUS_LABEL } from "./status-labels.js";
 export { LIMITS } from "./limits.js";
 export { WAL_ACTIONS } from "./wal-actions.js";
+export { PHASES } from "./phases.js";
 export * from "./cli.js";

package/dist/shared/core/constants/phases.d.ts

@@ -0,0 +1,47 @@
+/**
+ * Mission Phase Constants
+ */
+export declare const PHASES: {
+    readonly PHASE_0: {
+        readonly ID: "PHASE_0";
+        readonly NAME: "DISCOVERY SWARM";
+        readonly DESCRIPTION: "Parallel intelligence gathering and project mapping";
+        readonly MANDATORY: true;
+    };
+    readonly PHASE_1: {
+        readonly ID: "PHASE_1";
+        readonly NAME: "THINK";
+        readonly DESCRIPTION: "Analyze scope, decomposition, and delegation";
+        readonly MANDATORY: true;
+    };
+    readonly PHASE_2: {
+        readonly ID: "PHASE_2";
+        readonly NAME: "TRIAGE";
+        readonly DESCRIPTION: "Complexity assessment and execution path selection";
+        readonly MANDATORY: true;
+    };
+    readonly PHASE_3: {
+        readonly ID: "PHASE_3";
+        readonly NAME: "PLAN";
+        readonly DESCRIPTION: "Architectural roadmap and task grid creation";
+        readonly MANDATORY: true;
+    };
+    readonly PHASE_4: {
+        readonly ID: "PHASE_4";
+        readonly NAME: "EXECUTE";
+        readonly DESCRIPTION: "HPFA grid execution and worker coordination";
+        readonly MANDATORY: true;
+    };
+    readonly PHASE_5: {
+        readonly ID: "PHASE_5";
+        readonly NAME: "VERIFY";
+        readonly DESCRIPTION: "MSVP final gate and E2E system validation";
+        readonly MANDATORY: true;
+    };
+    readonly PHASE_6: {
+        readonly ID: "PHASE_6";
+        readonly NAME: "SEAL";
+        readonly DESCRIPTION: "Mission completion and deterministic output";
+        readonly MANDATORY: true;
+    };
+};

package/dist/shared/message/constants/slash-commands.d.ts

@@ -2,7 +2,7 @@
  * Slash Commands (with slash prefix)
  */
 export declare const SLASH_COMMANDS: {
-    readonly TASK: "/swarm";
+    readonly TASK: "/task";
     readonly PLAN: "/plan";
     readonly STATUS: "/status";
     readonly STOP: "/stop";
@@ -12,7 +12,7 @@ export declare const SLASH_COMMANDS: {
  * Command Names (without slash prefix, for comparison after parsing)
  */
 export declare const COMMAND_NAMES: {
-    readonly TASK: "swarm";
+    readonly TASK: "task";
     readonly PLAN: "plan";
     readonly STATUS: "status";
     readonly STOP: "stop";

package/package.json

@@ -2,7 +2,7 @@
   "name": "opencode-orchestrator",
   "displayName": "OpenCode Orchestrator",
   "description": "Distributed Cognitive Architecture for OpenCode. Turns simple prompts into specialized multi-agent workflows (Planner, Coder, Reviewer).",
-  "version": "1.0.12",
+  "version": "1.0.14",
   "author": "agnusdei1207",
   "license": "MIT",
   "repository": {