@boyingliu01/opencode-plugin 0.14.23 → 0.14.24

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@boyingliu01/opencode-plugin",
-  "version": "0.14.23",
+  "version": "0.14.24",
   "type": "module",
   "main": "index.ts",
   "description": "XP-Gate quality gates + AI workflow skills + Sprint Flow TUI sidebar for OpenCode",

package/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
-**Generated:** 2026-07-21
-**Commit:** 03e9223
+**Generated:** 2026-07-22
+**Commit:** e331f2c
 **Branch:** main
-**Version:** 0.14.23.0
+**Version:** 0.14.24.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, 3 experts from ≥2 providers, domestic models only). Supports design + code-walkthrough modes.

package/skills/delphi-review/SKILL.md

@@ -294,14 +294,34 @@ Each round MUST output a structured round marker:
 | 2 专家（默认） | A(架构) + B(实现) | 代码变更、小型设计 |
 | 3 专家 | A(架构) + B(实现) + C(可行性) | 架构决策、需求文档 |
 
-### 模型选择策略（强制 — 从 opencode.json 读取）
-
-**MUST 从 `opencode.json` 的 agent 配置中读取模型**，**严禁** hardcode 模型名称。
+### 模型选择策略（强制 — 平台适配）
 
 **关键原则**：
 - ✅ 三个专家必须来自 **至少 2 家不同 provider**
-- ❌ 禁止 hardcode 模型名称（模型列表以 `opencode.json` 为准）
+- ❌ 禁止 hardcode 模型名称
 - ❌ 禁止三个专家全部使用同一 provider 的模型
+- ❌ 禁止使用 Anthropic/OpenAI/Google 等国外模型
+
+#### Qoder 平台（推荐 — Custom Agent 模式）
+
+Qoder 环境下使用 **Custom Agent** 机制，每个专家是一个独立的 custom agent，配置不同的 Qoder 内置模型：
+
+| 专家 | Agent 文件 | 模型 | Credits 费率 |
+|------|-----------|------|-------------|
+| Architecture (A) | `.qoder/agents/delphi-architecture.md` | Qwen3.7-Max | 0.5× |
+| Technical (B) | `.qoder/agents/delphi-technical.md` | GLM-5.2 | 0.6× |
+| Feasibility (C) | `.qoder/agents/delphi-feasibility.md` | DeepSeek-V4-Pro | 0.5× |
+
+**执行方式**：通过 Agent tool 并行启动 3 个 subagent（type=GeneralPurpose），每个 agent 使用自己配置的模型独立评审，主 orchestrator 收集结果后计算共识。
+
+**优势**：无需外部 API key，直接使用 Qoder Credits，模型由平台统一管理。
+
+#### OpenCode 平台（External API 模式）
+
+OpenCode 环境下通过 `opencode.json` 的 agent 配置 + `.delphi-config.json` 调用外部 API：
+- **MUST 从 `opencode.json` 的 agent 配置中读取模型**
+- 通过 `scripts/delphi-external-review.cjs` 调用各 provider 的 OpenAI 兼容 API
+- 需要用户自行配置 API key（环境变量注入）
 
 ### 共识阈值
 

package/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
-**Generated:** 2026-07-21
-**Commit:** 03e9223
+**Generated:** 2026-07-22
+**Commit:** e331f2c
 **Branch:** main
-**Version:** 0.14.23.0
+**Version:** 0.14.24.0
 
 ## OVERVIEW
 **6-phase** development pipeline (v2.0 compact redesign, Issue #290): PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE. Phase 3/6 BUILD default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE between DESIGN (2/6) and BUILD (3/6): design must pass Delphi review (≥90% consensus) before any coding.

package/skills/sprint-flow/SKILL.md

@@ -199,11 +199,26 @@ Every phase MUST output its header as the first line of that phase's output. For
 3. NEVER merge phase output — each phase gets its own header
 4. On `/sprint-flow` trigger, first line MUST output: `Sprint Flow: PREP → DESIGN → BUILD → VERIFY → SHIP → CLOSE`
 5. Each phase completion MUST write Phase Summary to `.sprint-state/phase-outputs/phase-{N}-summary.md`
-6. Each phase completion MUST update `.sprint-state/sprint-state.json`
-
-### Required Rendering (MANDATORY per phase)
-
-7. Each phase completion MUST render the ASCII progress dashboard using `templates/sprint-progress-template.md` — the orchestrator reads `sprint-state.json` and outputs the dashboard after every phase's status block, so the user always sees current global progress without needing to ask
+6. Each phase completion MUST call `xp-gate phase-transition <N> <status> --render` — this programmatically updates `sprint-state.json` AND renders the ASCII dashboard in one command (resolves #338, #146)
+
+### Phase Transition CLI (MANDATORY — replaces manual state updates)
+
+7. **NEVER** manually write to `sprint-state.json` or manually render the dashboard from template. ALWAYS use:
+   ```
+   npx xp-gate phase-transition <phase> <status> --render [--outputs '<json>']
+   ```
+   - `<phase>`: 1-6
+   - `<status>`: `in_progress` | `completed` | `skipped` | `failed` | `paused`
+   - `--render`: Auto-renders ASCII progress dashboard after state update
+   - `--outputs '<json>'`: Optional JSON of phase outputs to record
+   
+   Example (end of each phase):
+   ```
+   npx xp-gate phase-transition 1 completed --render --outputs '{"estimate":"3 story points"}'
+   npx xp-gate phase-transition 2 in_progress --render
+   ```
+   
+   This is a **HARD GATE** — the orchestrator MUST invoke this CLI command. Text-level instructions to "update state" or "render dashboard" are DEPRECATED; the CLI is the single source of truth for state transitions and dashboard rendering.
 
 ### Phase Output Status Schema (MANDATORY per phase)
 

package/skills/sprint-flow/references/orchestration-rules.md

@@ -89,25 +89,20 @@
    - 格式：YAML frontmatter + Markdown body（body ≤ 50 行）
    - 大小限制：≤ 40,000 字符（≈ 10,000 tokens）
 
-2. **更新 sprint-state.json**：
-   - `phase`: 当前阶段编号 (1-6)
-   - `outputs`: 新增当前阶段输出文件路径
-   - `phase_history`: 追加或更新当前阶段的记录
-     - Phase 开始时：追加 `{ "phase": N, "phase_name": "NAME", "status": "running", "started_at": "<ISO 8601>", "completed_at": null, "duration_seconds": null }`
-     - Phase 完成时：更新对应条目，填充 `completed_at`（ISO 8601）和 `duration_seconds`
-     - Phase 跳过时：设置 `status: "skipped"`
+2. **调用 phase-transition CLI**（替代手动更新 sprint-state.json + 手动渲染看板）：
+   ```
+   npx xp-gate phase-transition <phase> <status> --render [--outputs '<json>']
+   ```
+   - Phase 开始时：`npx xp-gate phase-transition <N> in_progress --render`
+   - Phase 完成时：`npx xp-gate phase-transition <N> completed --render --outputs '{"key":"value"}'`
+   - Phase 跳过时：`npx xp-gate phase-transition <N> skipped --render`
+   - CLI 自动完成：更新 `sprint-state.json`（phase, phase_history, outputs）+ 渲染 ASCII 看板
+   - 看板规则：已完成 ✅ + 耗时，当前 🔄，待做 ⬜，跳过 ⏭️，失败 ❌
+   - 进度条：`[████▓░░░░░░] {pct}%`
+   - **禁止**手动写入 `sprint-state.json` 或手动调用 `render-sprint-progress.cjs`（已废弃）
 
 3. **等待用户确认 checkpoint**（如适用）
 
-4. **展示进度看板**：执行 `node scripts/render-sprint-progress.cjs` 渲染进度看板
-   - 脚本自动读取 `.sprint-state/sprint-state.json` 并输出 ASCII 进度看板
-   - 渲染规则：已完成阶段显示 ✅ + 耗时，当前阶段 🔄，待做 ⬜，跳过 ⏭️，失败 ❌
-   - 进度条：`[████▓░░░░░░] {pct}%`（已完成数/总阶段数 6）
-   - 下一步行动：根据当前阶段 + 状态，自动查找对应提示
-   - 输出物路径：列出 `outputs` 中已有的文件路径
-   - 时机：每个 Phase 完成后的 transition 阶段自动展示
-   - 向后兼容：旧版 `sprint-state.json` 缺少 `phase_history` 时，从 `phase` 字段推断状态
-
 ### Background Task Resume Protocol (MANDATORY — Issue #248)
 
 After dispatching background agents with `run_in_background=true`:

package/skills/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
-**Generated:** 2026-07-21
-**Commit:** 03e9223
+**Generated:** 2026-07-22
+**Commit:** e331f2c
 **Branch:** main
-**Version:** 0.14.23.0
+**Version:** 0.14.24.0
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.