@boyingliu01/xp-gate 0.10.16 → 0.11.0

package/plugins/claude-code/skills/delphi-review/SKILL.md

@@ -19,6 +19,15 @@ auto_continue: true
 - Does NOT replace testing or CI/CD verification
 - Does NOT handle deployment or release decisions
 
+## Activation
+**MANDATORY**: Every delphi-review response MUST begin with `[DelphiReview]` as the first line.
+This marker is required for skill-cert L1 trigger detection.
+
+Permitted variants (all satisfy L1 trigger):
+- `[DelphiReview]` — standard entry
+- `[DelphiReview:BLOCKED]` — Step 0 input validation failure
+- `[DelphiReview:WARNING]` — red flag detected (reserved)
+
 ## 核心原则
 
 **Delphi 方法只有一个目的：得到所有专家一致认可的可行方案。**
@@ -104,6 +113,46 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
                 └─ REQUEST_CHANGES → 修复方案 → 回到 Round 2 重新评审
 ```
 
+### Step 0: Input Validation (MANDATORY — 必须在任何评审前执行)
+
+检查用户 prompt 中是否包含可评审内容（设计文档、代码、specification.yaml、PR diff）：
+
+1. **有完整输入** → 直接进入 Phase 0（准备阶段），开始 Round 1
+2. **有部分输入**（占位符、描述性文本）→ 按输入内容执行评审，标注 `[INPUT: PARTIAL]`，但继续执行
+3. **无输入**（仅触发词，无文档/代码）→ 输出以下阻断响应，记入步骤完成：
+
+**Detection heuristics for Step 0**:
+- **Complete**: Contains ≥1 structural element (e.g., `##`, `requirement`, `AC-`, `function`, `class`, `interface`, YAML frontmatter, code block with language tag) AND ≥50 non-whitespace characters of actual content (not placeholder brackets like `[...]`, `{...}`, `<insert here>`).
+- **Partial**: Contains descriptive text referencing a design/code artifact BUT lacks substantive structure (e.g., "I need to review my login module" with no actual code/design attached), OR contains obvious placeholders like `[...]`, `(content)`, `<insert here>`, `TODO`.
+- **None**: Only trigger words (`/delphi-review`, "review this") with zero additional content, OR content that is exclusively questions about the review process itself ("how does delphi work?").
+
+**Partial input constraint**: When input is PARTIAL, cap review to 1 round with `confidence=low` annotation. Do NOT proceed with full multi-round review on insufficient input.
+
+**File path validation**: If user provides a file path (e.g., `--spec specification.yaml`):
+- Verify the file exists and is non-empty
+- If path is invalid → output: `[DelphiReview:BLOCKED] File not found: [path]. Please verify the path.`
+- If file is empty → output: `[DelphiReview:BLOCKED] File is empty: [path]. Please provide valid content.`
+
+```
+[DelphiReview:BLOCKED] 需要设计文档或代码内容才能启动评审。
+
+请提供以下之一：
+- 设计文档（design doc / specification）
+- 代码变更（code diff / PR link）
+- specification.yaml 文件路径
+- 架构设计说明
+
+评审输入示例：
+/delphi-review "Design Doc: [your content here]"
+/delphi-review --spec specification.yaml
+/delphi-review --mode code-walkthrough
+REMAINING STEPS: N/A (input validation failed)
+```
+
+在此状态下，BLOCKED 视为步骤已完成（后续步骤标记为 N/A）。
+
+**重要**: 内嵌在 prompt 中的文档内容（如 "Design Doc: [content]"或代码片段）应视为"有完整输入"，直接进入评审。
+
 **Round 模板**（匿名评审/交换意见/最终立场/修复报告格式）→ 详见 `references/round-templates.md`
 
 **Orchestrator 自动调度规则**（#218 subagent 内部自动多轮循环）→ 详见 `references/orchestrator-dispatch.md`
@@ -165,6 +214,23 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
 
 ## Output Format (MANDATORY)
 
+**Single 模式简化输出**: 当 single reviewer 模式（非 Multi-Expert）时，可使用简化输出格式：
+- verdict + confidence + issues_list（合并 critical/major/minor）+ summary
+- 完整 JSON 格式保留用于 multi-expert 多轮评审场景
+
+**Single 模式简化模板**:
+```
+[DelphiReview] verdict=APPROVED | REQUEST_CHANGES | BLOCKED
+confidence=N/10
+issues=[critical: N, major: N, minor: N]
+summary: [1-2 sentence verdict summary]
+```
+
+**⚠️ Single vs Multi-Expert Output**:
+- **Multi-Expert Mode (default)**: MUST use the full JSON schema below. Each expert outputs independently; the orchestrator aggregates into `consensus_report`. DO NOT use the simplified template.
+- **Single Reviewer Mode** (explicitly invoked with `--single`): MAY use the simplified text template above.
+- **Never mix formats**. If you are one of multiple experts in the same round, output JSON only.
+
 ```json
 {
   "expert_id": "A|B|C",
@@ -243,10 +309,23 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
 
 ## Red Flags
 
+### 检测触发器（模型可执行检测）
+
+| 用户输入模式 | 触发词 | 响应动作 |
+|-------------|--------|---------|
+| 要求跳过评审 | "skip review", "不用评审", "跳过评审", "直接提交", "不评审" | → 提醒: `[DelphiReview] 评审是投资而非开销。Delphi 设计要求多轮共识(>=90%)，不可快速跳过。` |
+| 时间压力 | "来不及", "时间紧", "emergency", "赶时间", "deadline" | → 提醒: `[DelphiReview] 时间紧迫正是需要评审的时刻。跳过评审省 30 分钟，后期修复可能花 3 天。` |
+| 提前终止 | Round 1 后用户说 "可以了", "够了", "enough" | → BLOCK: `[DelphiReview:BLOCKED] 评审未达终止条件。仍需 [共识>=90% + 所有 Critical/Major 已处理]。` |
+| 单专家自评 | 用户仅指定 1 个专家 或 说 "我自己看了" | → 提醒: `[DelphiReview] 至少需要 2 位不同 provider 的专家参与评审。` |
+| 无文档输入 | 仅触发词，无设计/代码内容 | → 输出 `[DelphiReview:BLOCKED]` 阻断响应（见 Step 0） |
+
+### 原则性声明
+
 | 借口 | 现实 |
 |------|------|
 | "这只是小变更" | 所有变更都需要评审 |
 | "Round 1 就够了" | 不够，必须多轮直到共识 |
+| "生成报告就完成了" | APPROVED 才算完成 |
 | "2/3 同意就是共识" | 还要检查问题共识比例 >=90% |
 
 ---

package/plugins/claude-code/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
-**Generated:** 2026-06-25
-**Commit:** 463f7e6
+**Generated:** 2026-06-29
+**Commit:** 8efd33c
 **Branch:** main
-**Version:** 0.10.16.0
+**Version:** 0.11.0.1
 
 ## OVERVIEW
 **11-phase** development pipeline: ISOLATE → AUTO-ESTIMATE → THINK → PLAN → BUILD → REVIEW → SHIP → LAND → USER ACCEPTANCE → FEEDBACK → CLEANUP. Phase 2 default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE in Phase 1: design must pass Delphi review (≥90% consensus) before any coding.

package/plugins/claude-code/skills/test-specification-alignment/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
-**Generated:** 2026-06-25
-**Commit:** 463f7e6
+**Generated:** 2026-06-29
+**Commit:** 8efd33c
 **Branch:** main
-**Version:** 0.10.16.0
+**Version:** 0.11.0.1
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/plugins/opencode/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@boyingliu01/opencode-plugin",
-  "version": "0.10.16",
+  "version": "0.11.0",
   "type": "module",
   "main": "index.ts",
   "description": "XP-Gate quality gates + AI workflow skills + Sprint Flow TUI sidebar for OpenCode",
@@ -19,8 +19,8 @@
       "types": "./index.ts"
     },
     "./tui": {
-      "import": "./tui-plugin.ts",
-      "types": "./tui-plugin.ts"
+      "import": "./tui-plugin.tsx",
+      "types": "./tui-plugin.tsx"
     }
   },
   "files": [

package/plugins/opencode/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
-**Generated:** 2026-06-25
-**Commit:** 463f7e6
+**Generated:** 2026-06-29
+**Commit:** 8efd33c
 **Branch:** main
-**Version:** 0.10.16.0
+**Version:** 0.11.0.1
 
 ## 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/plugins/opencode/skills/delphi-review/SKILL.md

@@ -19,6 +19,15 @@ auto_continue: true
 - Does NOT replace testing or CI/CD verification
 - Does NOT handle deployment or release decisions
 
+## Activation
+**MANDATORY**: Every delphi-review response MUST begin with `[DelphiReview]` as the first line.
+This marker is required for skill-cert L1 trigger detection.
+
+Permitted variants (all satisfy L1 trigger):
+- `[DelphiReview]` — standard entry
+- `[DelphiReview:BLOCKED]` — Step 0 input validation failure
+- `[DelphiReview:WARNING]` — red flag detected (reserved)
+
 ## 核心原则
 
 **Delphi 方法只有一个目的：得到所有专家一致认可的可行方案。**
@@ -104,6 +113,46 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
                 └─ REQUEST_CHANGES → 修复方案 → 回到 Round 2 重新评审
 ```
 
+### Step 0: Input Validation (MANDATORY — 必须在任何评审前执行)
+
+检查用户 prompt 中是否包含可评审内容（设计文档、代码、specification.yaml、PR diff）：
+
+1. **有完整输入** → 直接进入 Phase 0（准备阶段），开始 Round 1
+2. **有部分输入**（占位符、描述性文本）→ 按输入内容执行评审，标注 `[INPUT: PARTIAL]`，但继续执行
+3. **无输入**（仅触发词，无文档/代码）→ 输出以下阻断响应，记入步骤完成：
+
+**Detection heuristics for Step 0**:
+- **Complete**: Contains ≥1 structural element (e.g., `##`, `requirement`, `AC-`, `function`, `class`, `interface`, YAML frontmatter, code block with language tag) AND ≥50 non-whitespace characters of actual content (not placeholder brackets like `[...]`, `{...}`, `<insert here>`).
+- **Partial**: Contains descriptive text referencing a design/code artifact BUT lacks substantive structure (e.g., "I need to review my login module" with no actual code/design attached), OR contains obvious placeholders like `[...]`, `(content)`, `<insert here>`, `TODO`.
+- **None**: Only trigger words (`/delphi-review`, "review this") with zero additional content, OR content that is exclusively questions about the review process itself ("how does delphi work?").
+
+**Partial input constraint**: When input is PARTIAL, cap review to 1 round with `confidence=low` annotation. Do NOT proceed with full multi-round review on insufficient input.
+
+**File path validation**: If user provides a file path (e.g., `--spec specification.yaml`):
+- Verify the file exists and is non-empty
+- If path is invalid → output: `[DelphiReview:BLOCKED] File not found: [path]. Please verify the path.`
+- If file is empty → output: `[DelphiReview:BLOCKED] File is empty: [path]. Please provide valid content.`
+
+```
+[DelphiReview:BLOCKED] 需要设计文档或代码内容才能启动评审。
+
+请提供以下之一：
+- 设计文档（design doc / specification）
+- 代码变更（code diff / PR link）
+- specification.yaml 文件路径
+- 架构设计说明
+
+评审输入示例：
+/delphi-review "Design Doc: [your content here]"
+/delphi-review --spec specification.yaml
+/delphi-review --mode code-walkthrough
+REMAINING STEPS: N/A (input validation failed)
+```
+
+在此状态下，BLOCKED 视为步骤已完成（后续步骤标记为 N/A）。
+
+**重要**: 内嵌在 prompt 中的文档内容（如 "Design Doc: [content]"或代码片段）应视为"有完整输入"，直接进入评审。
+
 **Round 模板**（匿名评审/交换意见/最终立场/修复报告格式）→ 详见 `references/round-templates.md`
 
 **Orchestrator 自动调度规则**（#218 subagent 内部自动多轮循环）→ 详见 `references/orchestrator-dispatch.md`
@@ -165,6 +214,23 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
 
 ## Output Format (MANDATORY)
 
+**Single 模式简化输出**: 当 single reviewer 模式（非 Multi-Expert）时，可使用简化输出格式：
+- verdict + confidence + issues_list（合并 critical/major/minor）+ summary
+- 完整 JSON 格式保留用于 multi-expert 多轮评审场景
+
+**Single 模式简化模板**:
+```
+[DelphiReview] verdict=APPROVED | REQUEST_CHANGES | BLOCKED
+confidence=N/10
+issues=[critical: N, major: N, minor: N]
+summary: [1-2 sentence verdict summary]
+```
+
+**⚠️ Single vs Multi-Expert Output**:
+- **Multi-Expert Mode (default)**: MUST use the full JSON schema below. Each expert outputs independently; the orchestrator aggregates into `consensus_report`. DO NOT use the simplified template.
+- **Single Reviewer Mode** (explicitly invoked with `--single`): MAY use the simplified text template above.
+- **Never mix formats**. If you are one of multiple experts in the same round, output JSON only.
+
 ```json
 {
   "expert_id": "A|B|C",
@@ -243,10 +309,23 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
 
 ## Red Flags
 
+### 检测触发器（模型可执行检测）
+
+| 用户输入模式 | 触发词 | 响应动作 |
+|-------------|--------|---------|
+| 要求跳过评审 | "skip review", "不用评审", "跳过评审", "直接提交", "不评审" | → 提醒: `[DelphiReview] 评审是投资而非开销。Delphi 设计要求多轮共识(>=90%)，不可快速跳过。` |
+| 时间压力 | "来不及", "时间紧", "emergency", "赶时间", "deadline" | → 提醒: `[DelphiReview] 时间紧迫正是需要评审的时刻。跳过评审省 30 分钟，后期修复可能花 3 天。` |
+| 提前终止 | Round 1 后用户说 "可以了", "够了", "enough" | → BLOCK: `[DelphiReview:BLOCKED] 评审未达终止条件。仍需 [共识>=90% + 所有 Critical/Major 已处理]。` |
+| 单专家自评 | 用户仅指定 1 个专家 或 说 "我自己看了" | → 提醒: `[DelphiReview] 至少需要 2 位不同 provider 的专家参与评审。` |
+| 无文档输入 | 仅触发词，无设计/代码内容 | → 输出 `[DelphiReview:BLOCKED]` 阻断响应（见 Step 0） |
+
+### 原则性声明
+
 | 借口 | 现实 |
 |------|------|
 | "这只是小变更" | 所有变更都需要评审 |
 | "Round 1 就够了" | 不够，必须多轮直到共识 |
+| "生成报告就完成了" | APPROVED 才算完成 |
 | "2/3 同意就是共识" | 还要检查问题共识比例 >=90% |
 
 ---

package/plugins/opencode/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
-**Generated:** 2026-06-25
-**Commit:** 463f7e6
+**Generated:** 2026-06-29
+**Commit:** 8efd33c
 **Branch:** main
-**Version:** 0.10.16.0
+**Version:** 0.11.0.1
 
 ## OVERVIEW
 **11-phase** development pipeline: ISOLATE → AUTO-ESTIMATE → THINK → PLAN → BUILD → REVIEW → SHIP → LAND → USER ACCEPTANCE → FEEDBACK → CLEANUP. Phase 2 default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE in Phase 1: design must pass Delphi review (≥90% consensus) before any coding.

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

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
-**Generated:** 2026-06-25
-**Commit:** 463f7e6
+**Generated:** 2026-06-29
+**Commit:** 8efd33c
 **Branch:** main
-**Version:** 0.10.16.0
+**Version:** 0.11.0.1
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.

package/plugins/opencode/tui-plugin.tsx

@@ -0,0 +1,306 @@
+// @no-test-required: TUI rendering plugin — tested via visual verification in OpenCode runtime
+/**
+ * XP-Gate OpenCode TUI Slot Plugin
+ *
+ * Registers sidebar_content slot to display Sprint Flow progress
+ * from active sprint states discovered in .worktrees/sprint/ subdirectories.
+ *
+ * Rendered with @opentui/solid JSX — sidebar_content must return JSX.Element,
+ * NOT string (strings are silently ignored by OpenCode's TUI renderer).
+ *
+ * Users register this file in ~/.config/opencode/tui.json as:
+ *   { "plugin": ["@boyingliu01/opencode-plugin/tui"] }
+ */
+/** @jsxImportSource @opentui/solid */
+
+import { existsSync, readFileSync, readdirSync } from "node:fs"
+import { join, dirname, resolve, parse } from "node:path"
+import { homedir } from "node:os"
+import type { TuiPlugin, TuiSlotPlugin, TuiSlotProps } from "@opencode-ai/plugin/tui"
+import { createMemo, Show, For } from "solid-js"
+
+// ── Phase constants ──
+
+const PHASE_NAMES: Record<string, string> = {
+  '-1': 'ISOLATE', '-0.5': 'AUTO-ESTIMATE', '0': 'THINK',
+  '1': 'PLAN', '2': 'BUILD', '3': 'REVIEW',
+  '4': 'SHIP', '5': 'LAND', '6': 'USER ACCEPT',
+  '7': 'FEEDBACK', '8': 'CLEANUP',
+};
+
+const PHASE_ORDER = ['-1', '-0.5', '0', '1', '2', '3', '4', '5', '6', '7', '8'];
+
+// ── Types ──
+
+interface SprintReq {
+  name?: string
+  status?: "completed" | "in_progress" | "pending"
+}
+interface SprintPhaseHistory {
+  phase: number | string
+  phase_name?: string
+  status?: "completed" | "in_progress" | "pending"
+  started_at?: string; completed_at?: string
+  duration_seconds?: number
+  reqs?: Record<string, SprintReq>
+}
+interface SprintState {
+  id?: string; phase?: number | string; status?: string; started_at?: string
+  task_description?: string
+  isolation?: { branch?: string; worktree_path?: string }
+  metrics?: { tests_passed?: number; tests_failed?: number; coverage_pct?: number }
+  phase_history?: SprintPhaseHistory[]
+}
+interface DiscoveredSprint {
+  state: SprintState; sourcePath: string; worktreeExists: boolean
+}
+
+// ── Discovery ──
+
+const MAX_DISCOVERY_RESULTS = 5;
+
+function findGitRoot(startDir: string): string | null {
+  let current = resolve(startDir);
+  const root = parse(current).root;
+  const seen = new Set<string>();
+  while (current !== root) {
+    if (seen.has(current)) break;
+    seen.add(current);
+    if (existsSync(join(current, '.git'))) return current;
+    const parent = dirname(current);
+    if (parent === current) break;
+    current = parent;
+  }
+  if (existsSync(join(root, '.git'))) return root;
+  return null;
+}
+
+function readSprintState(dir: string): SprintState | null {
+  try {
+    const sf = join(dir, '.sprint-state', 'sprint-state.json');
+    if (!existsSync(sf)) return null;
+    return JSON.parse(readFileSync(sf, 'utf8')) as SprintState;
+  } catch { return null; }
+}
+
+function checkWorktreeExists(p: string | undefined): boolean {
+  if (!p) return false;
+  try { return existsSync(p); } catch { return false; }
+}
+
+function parseTime(v: unknown): number {
+  return new Date(v as string).getTime();
+}
+
+function isStaleSprint(s: SprintState | null): boolean {
+  if (!s?.started_at) return false;
+  let latest = parseTime(s.started_at);
+  if (isNaN(latest)) return false;
+  for (const ph of s.phase_history ?? []) {
+    if (ph.completed_at) latest = Math.max(latest, parseTime(ph.completed_at));
+    if (ph.started_at) latest = Math.max(latest, parseTime(ph.started_at));
+  }
+  return latest > 0 && Date.now() - latest > 3_600_000;
+}
+
+function discoverActiveSprints(dir: string): DiscoveredSprint[] {
+  const gitRoot = findGitRoot(dir);
+  const results: DiscoveredSprint[] = [];
+
+  if (gitRoot) {
+    const base = join(gitRoot, '.worktrees', 'sprint');
+    let entries: { name: string; isDirectory: () => boolean }[] = [];
+    try { if (existsSync(base)) entries = readdirSync(base, { withFileTypes: true }); } catch { /* ok */ }
+    for (const e of entries) {
+      if (!e.isDirectory()) continue;
+      const d = join(base, e.name);
+      const state = readSprintState(d);
+      if (!state?.id) continue;
+      const wt = checkWorktreeExists(d);
+      if (isStaleSprint(state) && !wt) continue;
+      results.push({ state, sourcePath: join(d, '.sprint-state', 'sprint-state.json'), worktreeExists: wt });
+    }
+  }
+
+  const localState = readSprintState(dir);
+  if (localState?.id) {
+    const wp = localState.isolation?.worktree_path;
+    const hasWp = !!wp;
+    const wt = hasWp ? checkWorktreeExists(wp) : false;
+    if (!hasWp || wt) results.push({ state: localState, sourcePath: join(dir, '.sprint-state', 'sprint-state.json'), worktreeExists: wt });
+  }
+
+  const deduped = new Map<string, DiscoveredSprint>();
+  for (const e of results) {
+    const id = e.state.id!;
+    const existing = deduped.get(id);
+    if (!existing) { deduped.set(id, e); continue; }
+    if (e.worktreeExists && !existing.worktreeExists) { deduped.set(id, e); continue; }
+    if (!e.worktreeExists && existing.worktreeExists) continue;
+    const eTs = e.state.started_at ? new Date(e.state.started_at).getTime() : 0;
+    const xTs = existing.state.started_at ? new Date(existing.state.started_at).getTime() : 0;
+    if (eTs > xTs || (eTs === xTs && e.sourcePath < existing.sourcePath)) deduped.set(id, e);
+  }
+
+  return Array.from(deduped.values())
+    .sort((a, b) => {
+      const aTs = a.state.started_at ? new Date(a.state.started_at).getTime() : 0;
+      const bTs = b.state.started_at ? new Date(b.state.started_at).getTime() : 0;
+      return bTs - aTs || String(b.state.id).localeCompare(String(a.state.id));
+    })
+    .slice(0, MAX_DISCOVERY_RESULTS);
+}
+
+// ── Cache ──
+
+let _cache: { data: DiscoveredSprint[]; upgradeNotice: string | null; ts: number; dir: string } | null = null;
+const CACHE_TTL_MS = 5_000;
+
+// ── Render helpers ──
+
+function statusSymbol(status: string | undefined, currentPhase: string | number | undefined, key: string): string {
+  if (status === "completed") return "✓"
+  if (status === "in_progress") return "→"
+  if (String(currentPhase) === key) return "·"
+  return "○"
+}
+
+function buildPhaseLookup(state: SprintState): Record<string, SprintPhaseHistory> {
+  const lookup: Record<string, SprintPhaseHistory> = {}
+  for (const ph of state.phase_history ?? []) lookup[String(ph.phase)] = ph
+  return lookup
+}
+
+function phaseLine(key: string, history: SprintPhaseHistory | undefined, currentPhase: string | number | undefined): string {
+  const name = history?.phase_name || PHASE_NAMES[key] || key
+  const st = history?.status || (String(currentPhase) === key ? "in_progress" : "pending")
+  const sym = statusSymbol(st, currentPhase, key)
+  const suffix = st === "completed" ? "done" : st === "in_progress" ? "active" : ""
+  return `${sym} ${name.padEnd(14)} ${suffix}`.replace(/\s+$/, "")
+}
+
+function renderSprintTitle(state: SprintState): string {
+  if (state.task_description) return state.task_description;
+  if (state.id) {
+    const m = state.id.match(/sprint-(\d{4}-\d{2}-\d{2})-(\d+)/);
+    return m ? `Sprint ${m[1]} #${m[2]}` : state.id;
+  }
+  return 'Unknown Sprint';
+}
+
+// ── Upgrade notice ──
+
+const UPGRADE_NOTICE_FILE = join(homedir(), ".xp-gate", "upgrade-notice.json")
+const UPGRADE_NOTICE_TTL_MS = 86_400_000
+
+function readUpgradeNotice(): string | null {
+  try {
+    if (!existsSync(UPGRADE_NOTICE_FILE)) return null
+    const raw = JSON.parse(readFileSync(UPGRADE_NOTICE_FILE, "utf8"))
+    if (Date.now() - raw.ts < UPGRADE_NOTICE_TTL_MS && raw.message) {
+      const icon = raw.kind === "upgraded" ? "✓" : raw.kind === "outdated" ? "↑" : "⚠"
+      return `${icon} ${raw.message}`
+    }
+    return null
+  } catch { return null; }
+}
+
+// ── JSX Components ──
+
+function SprintCard(props: { sprint: DiscoveredSprint }) {
+  const { state } = props.sprint
+  const lookup = buildPhaseLookup(state)
+
+  return (
+    <box>
+      <text><b>SPRINT:</b> {renderSprintTitle(state)}</text>
+      <Show when={state.isolation?.branch}>
+        {(branch: () => string) => <text fg="#888888">  {branch()}</text>}
+      </Show>
+      <Show when={state.metrics?.tests_passed != null || state.metrics?.coverage_pct != null}>
+        <text fg="#888888">
+          {state.metrics?.tests_passed != null ? `tests:${state.metrics.tests_passed}` : ""}
+          {state.metrics?.coverage_pct != null ? ` cov:${state.metrics.coverage_pct}%` : ""}
+        </text>
+      </Show>
+      <Show when={isStaleSprint(state)}>
+        <text fg="#ffaa00">  ⚠ idle >1h</text>
+      </Show>
+      <For each={PHASE_ORDER}>
+        {(key: string) => {
+          const hist = lookup[key]
+          if (!hist && String(state.phase) !== key) return null
+          return <text>{phaseLine(key, hist, state.phase)}</text>
+        }}
+      </For>
+    </box>
+  )
+}
+
+function SprintSidebar(props: { sprints: DiscoveredSprint[] }) {
+  const display = props.sprints.slice(0, 3)
+
+  return (
+    <box>
+      <For each={display}>
+        {(sprint: DiscoveredSprint, i: () => number) => (
+          <>
+            <Show when={i() > 0}>
+              <text>---</text>
+            </Show>
+            <SprintCard sprint={sprint} />
+          </>
+        )}
+      </For>
+      <Show when={props.sprints.length > 3}>
+        <text>... +{props.sprints.length - 3} more</text>
+      </Show>
+    </box>
+  )
+}
+
+function renderContent(sprints: DiscoveredSprint[], upgradeNotice: string | null, dir: string) {
+  const components: any[] = []
+
+  if (sprints.length > 0) {
+    if (upgradeNotice) components.push(<text>{upgradeNotice}</text>)
+    components.push(<SprintSidebar sprints={sprints} />)
+    return components.length > 1 ? <box>{components}</box> : components[0]
+  }
+
+  const hasStateDir = existsSync(join(dir, ".sprint-state"))
+  const gitRoot = findGitRoot(dir)
+  const hasWorktreesRoot = gitRoot ? existsSync(join(gitRoot, ".worktrees")) : false
+
+  if (hasStateDir) return <box>{upgradeNotice ? <text>{upgradeNotice}</text> : null}<text><b>SPRINT FLOW</b></text><text>  -> Initializing...</text></box>
+  if (hasWorktreesRoot) return <box>{upgradeNotice ? <text>{upgradeNotice}</text> : null}<text><b>SPRINT FLOW</b></text><text>  · Ready...</text></box>
+  if (upgradeNotice) return <box><text>{upgradeNotice}</text></box>
+
+  return null
+}
+
+// ── TUI Slot Plugin ──
+
+const tuiPlugin: TuiSlotPlugin = {
+  slots: {
+    sidebar_content: (_props: TuiSlotProps) => {
+      const dir = process.env.XP_GATE_PROJECT_DIR || process.cwd();
+      const now = Date.now();
+
+      if (_cache && _cache.dir === dir && now - _cache.ts < CACHE_TTL_MS) {
+        return renderContent(_cache.data, _cache.upgradeNotice, dir);
+      }
+
+      const sprints = discoverActiveSprints(dir);
+      const upgradeNotice = readUpgradeNotice()
+      _cache = { data: sprints, ts: now, dir, upgradeNotice };
+      return renderContent(sprints, upgradeNotice, dir);
+    },
+  },
+}
+
+const plugin: TuiPlugin = async (api, _options, _meta) => {
+  api.slots.register(tuiPlugin)
+}
+
+export { plugin as tui, readSprintState }

package/plugins/qoder/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "xp-gate",
-  "version": "0.10.16",
+  "version": "0.11.0",
   "displayName": "XP-Gate",
   "description": "Extreme Programming quality gates + AI workflow skills for Qoder. Includes 10 quality gates (Gate 0-9), Sprint Flow (11 phases), and Delphi multi-expert review (>=90% consensus).",
   "author": {

package/plugins/qoder/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
-**Generated:** 2026-06-25
-**Commit:** 463f7e6
+**Generated:** 2026-06-29
+**Commit:** 8efd33c
 **Branch:** main
-**Version:** 0.10.16.0
+**Version:** 0.11.0.1
 
 ## 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/plugins/qoder/skills/sprint-flow/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/SPRINT-FLOW KNOWLEDGE BASE
 
-**Generated:** 2026-06-25
-**Commit:** 463f7e6
+**Generated:** 2026-06-29
+**Commit:** 8efd33c
 **Branch:** main
-**Version:** 0.10.16.0
+**Version:** 0.11.0.1
 
 ## OVERVIEW
 **11-phase** development pipeline: ISOLATE → AUTO-ESTIMATE → THINK → PLAN → BUILD → REVIEW → USER ACCEPTANCE → FEEDBACK → SHIP → LAND → CLEANUP. Phase 2 default build mode is **ralph-loop** (REQ-level iteration, 40-67% token savings vs parallel). HARD-GATE in Phase 1: design must pass Delphi review (≥90% consensus) before any coding.

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

@@ -1,9 +1,9 @@
 # SKILLS/TEST-SPECIFICATION-ALIGNMENT KNOWLEDGE BASE
 
-**Generated:** 2026-06-25
-**Commit:** 463f7e6
+**Generated:** 2026-06-29
+**Commit:** 8efd33c
 **Branch:** main
-**Version:** 0.10.16.0
+**Version:** 0.11.0.1
 
 ## OVERVIEW
 Test-Specification Alignment Engine — two-stage validation ensuring tests accurately reflect requirements and design specs.