ccg-workflow 1.7.65 → 1.7.67

package/README.md

@@ -237,4 +237,4 @@ MIT
 
 ---
 
-v1.7.65 | [Issues](https://github.com/fengshao1227/ccg-workflow/issues)
+v1.7.67 | [Issues](https://github.com/fengshao1227/ccg-workflow/issues)

package/dist/cli.mjs

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 import cac from 'cac';
 import ansis from 'ansis';
-import { z as diagnoseMcpConfig, A as isWindows, B as readClaudeCodeConfig, C as fixWindowsMcpConfig, D as writeClaudeCodeConfig, r as readCcgConfig, b as initI18n, s as showMainMenu, i as init, E as configMcp, F as version, a as i18n } from './shared/ccg-workflow.DfYEh3he.mjs';
+import { z as diagnoseMcpConfig, A as isWindows, B as readClaudeCodeConfig, C as fixWindowsMcpConfig, D as writeClaudeCodeConfig, r as readCcgConfig, b as initI18n, s as showMainMenu, i as init, E as configMcp, F as version, a as i18n } from './shared/ccg-workflow.CNurX2Yc.mjs';
 import 'inquirer';
 import 'node:child_process';
 import 'node:util';

package/dist/index.mjs

@@ -1,4 +1,4 @@
-export { c as changeLanguage, x as checkForUpdates, y as compareVersions, d as createDefaultConfig, e as createDefaultRouting, g as getCcgDir, f as getConfigPath, t as getCurrentVersion, v as getLatestVersion, j as getWorkflowById, h as getWorkflowConfigs, a as i18n, i as init, b as initI18n, l as installAceTool, m as installAceToolRs, k as installWorkflows, p as migrateToV1_4_0, q as needsMigration, r as readCcgConfig, s as showMainMenu, o as uninstallAceTool, n as uninstallWorkflows, u as update, w as writeCcgConfig } from './shared/ccg-workflow.DfYEh3he.mjs';
+export { c as changeLanguage, x as checkForUpdates, y as compareVersions, d as createDefaultConfig, e as createDefaultRouting, g as getCcgDir, f as getConfigPath, t as getCurrentVersion, v as getLatestVersion, j as getWorkflowById, h as getWorkflowConfigs, a as i18n, i as init, b as initI18n, l as installAceTool, m as installAceToolRs, k as installWorkflows, p as migrateToV1_4_0, q as needsMigration, r as readCcgConfig, s as showMainMenu, o as uninstallAceTool, n as uninstallWorkflows, u as update, w as writeCcgConfig } from './shared/ccg-workflow.CNurX2Yc.mjs';
 import 'ansis';
 import 'inquirer';
 import 'node:child_process';

package/dist/shared/{ccg-workflow.DfYEh3he.mjs → ccg-workflow.CNurX2Yc.mjs}

@@ -10,7 +10,7 @@ import i18next from 'i18next';
 import ora from 'ora';
 import { parse, stringify } from 'smol-toml';
 
-const version = "1.7.65";
+const version = "1.7.67";
 
 function isWindows() {
   return process.platform === "win32";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ccg-workflow",
-  "version": "1.7.65",
+  "version": "1.7.67",
   "description": "Claude-Codex-Gemini 多模型协作系统 - 智能路由多模型开发工作流",
   "type": "module",
   "packageManager": "pnpm@10.17.1",

package/templates/commands/spec-impl.md

@@ -21,8 +21,11 @@ description: '按规范执行 + 多模型协作 + 归档'
    - Run `openspec status --change "<change_id>" --json` to review tasks.
 
 2. **Apply OPSX Change**
-   - Use `/ccg:spec-impl` (which uses OpenSpec skills internally) to enter implementation mode.
-   - This skill will guide you through the tasks defined in `tasks.md`.
+   - Call `/opsx:apply` to enter implementation mode:
+     ```
+     /opsx:apply
+     ```
+   - This will load the change context and guide you through the tasks defined in `tasks.md`.
 
 3. **Identify Minimal Verifiable Phase**
    - Review `tasks.md` and identify the **smallest verifiable phase**.
@@ -109,7 +112,10 @@ description: '按规范执行 + 多模型协作 + 归档'
 
 10. **Archive on Completion**
     - When ALL tasks in `tasks.md` are marked `[x]`:
-    - The agent will use OpenSpec skills to archive the change.
+    - Call `/opsx:archive` to archive the change:
+      ```
+      /opsx:archive
+      ```
     - This merges spec deltas to `openspec/specs/` and moves change to archive.
 
 **Reference**

package/templates/commands/spec-init.md

@@ -70,16 +70,7 @@ description: '初始化 OpenSpec (OPSX) 环境 + 验证多模型 MCP 工具'
      ```
    - For each unavailable tool, display warning with installation instructions.
 
-5. **Validate Context Retrieval MCP** (Optional)
-   - **Check Active Tool**: Is `{{MCP_SEARCH_TOOL}}` available in the current session?
-   - **Check Configuration**: If tool is missing, check `~/.claude.json` (or `%APPDATA%\Claude\claude.json` on Windows) for `"ace-tool"` or `"ace-tool-rs"` in `mcpServers`.
-   - **Diagnosis**:
-     - If tool available: Mark as "✓ Active".
-     - If config exists but tool missing: Mark as "⚠️ Configured but inactive (Try restarting Claude)".
-     - If neither: Mark as "○ Not installed (Optional)".
-   - If not installed/configured, suggest: "Run `npx ccg-workflow` and select ace-tool MCP option."
-
-6. **Summary Report**
+5. **Summary Report**
    Display status table:
    ```
    Component                 Status
@@ -90,7 +81,6 @@ description: '初始化 OpenSpec (OPSX) 环境 + 验证多模型 MCP 工具'
    codeagent-wrapper         ✓/✗
    Codex backend             ✓/✗
    Gemini backend            ✓/✗
-   ace-tool MCP              ✓/✗ (optional)
    ```
 
    **Next Steps (Use CCG Encapsulated Commands)**

package/templates/commands/spec-plan.md

@@ -84,11 +84,33 @@ description: '多模型分析 → 消除歧义 → 零决策可执行计划'
    - **Bounds**: Value ranges, size limits, rate constraints
 
 5. **Update OPSX Artifacts**
-   - The agent will use OpenSpec skills to generate/update:
-     * specs (Requirements + PBT)
-     * design (Technical decisions)
-     * tasks (Zero-decision implementation plan)
-   - Ensure all resolved constraints and PBT properties are included in the generated artifacts.
+   - **BEFORE calling `/opsx:continue`**, output a structured summary for OPSX context:
+     ```markdown
+     ## Planning Summary for OPSX
+
+     **Multi-Model Analysis Results**:
+     - Codex (Backend): [Key findings and recommendations]
+     - Gemini (Frontend): [Key findings and recommendations]
+     - Consolidated Approach: [Selected implementation strategy]
+
+     **Resolved Constraints**:
+     - [All explicit constraints from Step 3]
+
+     **PBT Properties**:
+     - [All extracted properties from Step 4 with falsification strategies]
+
+     **Technical Decisions**:
+     - [All finalized technology choices, algorithms, configurations]
+
+     **Implementation Tasks**:
+     - [High-level task breakdown ready for tasks.md]
+     ```
+
+   - Then call `/opsx:continue` to generate next artifacts:
+     ```
+     /opsx:continue
+     ```
+   - The OPSX skill will use the above summary to create specs.md, design.md, and tasks.md.
 
 6. **Context Checkpoint**
    - Report current context usage.

package/templates/commands/spec-research.md

@@ -47,7 +47,11 @@ description: '需求 → 约束集（并行探索 + OPSX 提案）'
    - Each boundary should be self-contained: no cross-communication needed.
 
 4. **Parallel Multi-Model Exploration**
-   - Dispatch Explore subagents with unified output template:
+   - **CRITICAL**: You MUST launch BOTH Codex AND Gemini in a SINGLE message with TWO Bash tool calls.
+   - **DO NOT** call one model first and wait. Launch BOTH simultaneously with `run_in_background: true`.
+   - **工作目录**：`{{WORKDIR}}` 替换为目标工作目录的绝对路径。如果用户通过 `/add-dir` 添加了多个工作区，先确定任务相关的工作区。
+
+   **Output Template** (instruct both models to use this format):
    ```json
    {
      "module_name": "context boundary explored",
@@ -60,7 +64,34 @@ description: '需求 → 约束集（并行探索 + OPSX 提案）'
      "success_criteria_hints": ["observable success behaviors"]
    }
    ```
-   - Run Codex for backend boundaries, Gemini for frontend boundaries.
+
+   **Step 4.1**: In ONE message, make TWO parallel Bash calls:
+
+   **FIRST Bash call (Codex — backend boundaries)**:
+   ```
+   Bash({
+     command: "~/.claude/bin/codeagent-wrapper --backend codex - \"{{WORKDIR}}\" <<'EOF'\nExplore backend context boundaries for <change description>:\n- Existing structures and patterns\n- Conventions in use\n- Hard constraints limiting solution space\n- Dependencies and risks\nOUTPUT: JSON using the output template above\nEOF",
+     run_in_background: true,
+     timeout: 300000,
+     description: "Codex: backend boundary exploration"
+   })
+   ```
+
+   **SECOND Bash call (Gemini — frontend boundaries) - IN THE SAME MESSAGE**:
+   ```
+   Bash({
+     command: "~/.claude/bin/codeagent-wrapper --backend gemini --gemini-model gemini-3.1-pro-preview - \"{{WORKDIR}}\" <<'EOF'\nExplore frontend context boundaries for <change description>:\n- Existing structures and patterns\n- Conventions in use\n- Hard constraints limiting solution space\n- Dependencies and risks\nOUTPUT: JSON using the output template above\nEOF",
+     run_in_background: true,
+     timeout: 300000,
+     description: "Gemini: frontend boundary exploration"
+   })
+   ```
+
+   **Step 4.2**: After BOTH Bash calls return task IDs, wait for results with TWO TaskOutput calls:
+   ```
+   TaskOutput({ task_id: "<codex_task_id>", block: true, timeout: 600000 })
+   TaskOutput({ task_id: "<gemini_task_id>", block: true, timeout: 600000 })
+   ```
 
 5. **Aggregate and Synthesize**
    - Collect all subagent outputs.
@@ -79,15 +110,31 @@ description: '需求 → 约束集（并行探索 + OPSX 提案）'
    - Capture responses as additional constraints.
 
 7. **Finalize OPSX Proposal**
-   - Transform constraint sets into OPSX format:
-     * **Context**: User need + discovered constraints
-     * **Requirements**: Each constraint becomes requirement with scenario
-     * **Success Criteria**: Derived from hints and user confirmations
-   - Ensure proposal includes:
-     * All discovered constraints as requirements
-     * Verifiable scenarios for each requirement
-     * Clear dependencies and sequencing
-     * Risk mitigation strategies
+   - **BEFORE calling `/opsx:continue`**, output a structured summary for OPSX context:
+     ```markdown
+     ## Research Summary for OPSX
+
+     **Discovered Constraints**:
+     - [List all hard and soft constraints from Step 5]
+
+     **Dependencies**:
+     - [List cross-module dependencies]
+
+     **Risks & Mitigations**:
+     - [List identified risks and mitigation strategies]
+
+     **Success Criteria**:
+     - [List verifiable success behaviors]
+
+     **User Confirmations**:
+     - [List all user decisions from Step 6]
+     ```
+
+   - Then call `/opsx:continue` to generate proposal artifact:
+     ```
+     /opsx:continue
+     ```
+   - The OPSX skill will use the above summary to write proposal.md.
 
 8. **Context Checkpoint**
    - Report current context usage.