intentdna 1.5.7 → 1.5.8

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "intentdna",
       "description": "DNA template compilation + runtime enforcement",
-      "version": "1.5.7",
+      "version": "1.5.8",
       "source": "./"
     }
   ]

package/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "intentdna",
-  "version": "1.5.7",
+  "version": "1.5.8",
   "description": "Declarative policy layer for AI agent governance"
 }

package/dist/cli/commands/templates.d.ts

@@ -0,0 +1,10 @@
+/**
+ * dna templates deploy — copy local src/templates/*.dna.yaml to global intentdna install
+ */
+export interface TemplatesDeployOptions {
+    /** Override local templates dir (for testing) */
+    localDir?: string;
+    /** Override global target dir (for testing) */
+    globalDir?: string;
+}
+export declare function runTemplatesDeploy(opts?: TemplatesDeployOptions): Promise<number>;

package/dist/cli/commands/templates.js

@@ -0,0 +1,85 @@
+/**
+ * dna templates deploy — copy local src/templates/*.dna.yaml to global intentdna install
+ */
+import { readdirSync, copyFileSync, existsSync, readFileSync, mkdirSync } from "node:fs";
+import { resolve, join } from "node:path";
+import { execSync } from "node:child_process";
+/**
+ * Resolve the global intentdna templates directory.
+ * Strategy: npm root -g + /intentdna/dist/templates
+ */
+function resolveGlobalTemplatesDir() {
+    let globalRoot;
+    try {
+        globalRoot = execSync("npm root -g", { encoding: "utf-8" }).trim();
+    }
+    catch {
+        throw new Error("Failed to resolve npm global root. Is npm installed?");
+    }
+    const globalPkg = join(globalRoot, "intentdna");
+    if (!existsSync(globalPkg)) {
+        throw new Error("intentdna not installed globally, run: npm install -g intentdna");
+    }
+    // Templates live in dist/templates after build, and src/templates in source
+    const distTemplates = join(globalPkg, "dist", "templates");
+    const srcTemplates = join(globalPkg, "src", "templates");
+    if (existsSync(distTemplates))
+        return distTemplates;
+    if (existsSync(srcTemplates))
+        return srcTemplates;
+    // Create dist/templates if neither exists (fresh install edge case)
+    mkdirSync(distTemplates, { recursive: true });
+    return distTemplates;
+}
+/**
+ * Verify we're in the intentdna project root.
+ */
+function verifyProjectRoot(cwd) {
+    const pkgPath = join(cwd, "package.json");
+    if (!existsSync(pkgPath)) {
+        throw new Error("must run from intentdna project root (no package.json found)");
+    }
+    const pkg = JSON.parse(readFileSync(pkgPath, "utf-8"));
+    if (pkg.name !== "intentdna") {
+        throw new Error("must run from intentdna project root (package.json name is not 'intentdna')");
+    }
+    return cwd;
+}
+export async function runTemplatesDeploy(opts = {}) {
+    try {
+        const cwd = process.cwd();
+        const projectRoot = verifyProjectRoot(cwd);
+        const localDir = opts.localDir ?? resolve(projectRoot, "src", "templates");
+        const globalDir = opts.globalDir ?? resolveGlobalTemplatesDir();
+        if (!existsSync(localDir)) {
+            process.stderr.write(`Error: local templates dir not found: ${localDir}\n`);
+            return 1;
+        }
+        const files = readdirSync(localDir).filter((f) => f.endsWith(".dna.yaml"));
+        if (files.length === 0) {
+            process.stderr.write("No *.dna.yaml files found in local templates dir\n");
+            return 1;
+        }
+        let copied = 0;
+        for (const file of files) {
+            const src = join(localDir, file);
+            const dst = join(globalDir, file);
+            try {
+                copyFileSync(src, dst);
+                copied++;
+            }
+            catch (err) {
+                const msg = err instanceof Error ? err.message : String(err);
+                process.stderr.write(`Error copying ${file}: ${msg}\n`);
+                return 1;
+            }
+        }
+        process.stderr.write(`Copied ${copied} templates to ${globalDir}\n`);
+        return 0;
+    }
+    catch (err) {
+        const msg = err instanceof Error ? err.message : String(err);
+        process.stderr.write(`Error: ${msg}\n`);
+        return 1;
+    }
+}

package/dist/cli/index.js

@@ -30,6 +30,7 @@ Commands:
   evolve        Generate epigenetic markers from outcomes
   epigenetic    Record outcomes, view markers and summaries
   feedback      Analyze trace data, suggest template optimizations (--days <N>, --json, --evolve)
+  templates     Template management (deploy to global install)
 
 Options:
   --help, -h    Show help for a command
@@ -428,6 +429,17 @@ async function main() {
             process.exit(code);
             break;
         }
+        case "templates": {
+            const subcommand = rest[0] ?? "";
+            if (subcommand !== "deploy") {
+                process.stderr.write(`Usage: dna templates deploy\n\nCopy local src/templates/*.dna.yaml to global intentdna install.\n`);
+                process.exit(subcommand ? 2 : 0);
+            }
+            const { runTemplatesDeploy } = await import("./commands/templates.js");
+            const code = await runTemplatesDeploy();
+            process.exit(code);
+            break;
+        }
         default:
             process.stderr.write(`Unknown command: ${command}\n\n`);
             process.stderr.write(HELP);

package/dist/templates/flutter-rewrite.dna.yaml

@@ -168,7 +168,12 @@ roles:
       - Never suggest code changes
       - "If round > 1: review previous round's git diff first, judge if direction is correct"
       - "If previous fix produced 0 red→green transitions: warn 'no progress'"
-      - "Categorize by severity: CRITICAL (compile errors) > HIGH (logic failures) > LOW (widget/style)"
+      - "Categorize by severity and type:"
+      - "  CRITICAL: compile errors, import failures — blocks everything"
+      - "  HIGH-INFRA: mock incomplete causing test hang — blocks behavior verification, fix mock infrastructure first"
+      - "  HIGH-LOGIC: logic test failures (state/notifier) — behavior inconsistency"
+      - "  MEDIUM: widget test failures (rendering/navigation)"
+      - "hung tests ≠ failed tests. hung = mock infrastructure problem (needs mock fix), failed = behavior inconsistency (needs v2 code fix)"
 
   surgeon:
     description: Fixes breakpoints and builds missing layers by understanding v1 intent and rewriting in v2 style.
@@ -248,8 +253,9 @@ workflows:
           Scenario 2 (re-run/incremental):
           - Read the incremental diff from behavior doc
           - Update existing tests incrementally — do NOT rewrite all tests (preserves rescue progress)
-          - Run `flutter test {{test_path}}/$ARGUMENTS/` with NO timeout — record baseline
-          - Append baseline to behavior doc
+          - Run `flutter test {{test_path}}/$ARGUMENTS/ --timeout 30s` — per-test safety net (hung tests marked fail, continues to next)
+          - Classify results: passed / failed (behavior mismatch) / hung (timed out = mock infrastructure issue, NOT behavior failure)
+          - Append baseline to behavior doc with hung/failed distinction
           - Git commit: "behavior-lock($ARGUMENTS): N tests (X green, Y red from behavior change)"
 
           BANNED patterns:
@@ -273,6 +279,13 @@ workflows:
     description: "Fix v2 module $ARGUMENTS — investigate, fix, review, verify, report. Max 10 rounds with convergence protection."
     max_rounds: 10
     convergence_rule: "2 consecutive rounds with 0 test progress (green count not increasing) → STOP. Output blocked items + analysis."
+    round_budget: "Max 5 files per round. Each round must produce at least 1 test transition (red/skip/hung → green), otherwise counted as no progress."
+    priority_order: |
+      Phase 1: Fix CRITICAL (compile errors) — unblocks everything
+      Phase 2: Fix HIGH-INFRA (mock infrastructure, make hung tests runnable) — unblocks behavior verification
+      Phase 3: Fix HIGH-LOGIC (logic tests, red → green) — behavior alignment
+      Phase 4: Fix MEDIUM (widget tests, red → green) — UI alignment
+      Complete each phase before moving to the next.
     steps:
       - id: investigate
         role: investigator
@@ -282,10 +295,13 @@ workflows:
           - If round > 1: review previous round's git diff first
           - If previous round had 0 test progress (no red→green or skip→green): warn "no progress" and consider changing approach
 
-          Run tests in {{test_path}}/$ARGUMENTS/. Categorize all non-passing tests by severity:
-          CRITICAL: compile errors, import failures — fix first
-          HIGH: logic test failures (state/notifier/service) — fix second
-          LOW: widget test failures (rendering/navigation) — fix after logic is done
+          Run tests in {{test_path}}/$ARGUMENTS/ --timeout 30s. Categorize all non-passing tests by severity:
+          CRITICAL: compile errors, import failures — blocks everything, fix first
+          HIGH-INFRA: mock incomplete causing test hang (timed out) — blocks behavior verification, fix mock infrastructure
+          HIGH-LOGIC: logic test failures (state/notifier/service) — behavior inconsistency, fix after infra
+          MEDIUM: widget test failures (rendering/navigation) — fix after logic
+
+          IMPORTANT: hung ≠ failed. A test that times out (hung) = mock infrastructure problem, NOT a v2 behavior issue. Classify separately.
 
           Pick highest severity batch. Trace: what does v1 do vs what does v2 do? Find the breakpoints.
           Report findings and the plan for this round.
@@ -348,7 +364,7 @@ workflows:
         description: "Independent test verification + regression check."
         prompt: |
           Run tests independently (do not trust surgeon's reported results):
-          1. `flutter test {{test_path}}/$ARGUMENTS/` (no timeout)
+          1. `flutter test {{test_path}}/$ARGUMENTS/ --timeout 30s` (per-test safety net; hung = mock infra issue)
           2. `flutter analyze` (compilation check)
           3. Check for regressions in core module tests if applicable
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "intentdna",
-  "version": "1.5.7",
+  "version": "1.5.8",
   "description": "Intent DNA — Declarative policy layer for AI agent behavior",
   "type": "module",
   "main": "dist/index.js",

package/spec/flutter-rewrite-template-optimization.md

@@ -1,5 +1,15 @@
 # Spec: flutter-rewrite 模板优化
 
+## 最终目标
+
+**把 v1 (GetX) 重写为 v2 (Riverpod)，行为完全一致。**
+
+- behavior-lock: 写测试 = 定义"v1 的行为是什么"
+- rescue: 写代码让测试通过 = "v2 的行为和 v1 一样"
+- 完成标志: 所有测试 green = 重写成功，行为完全一致
+
+所有设计决策必须服务于这个目标。timeout 是安全网（防卡死），不是解法。挂死的测试意味着行为没被验证——rescue 必须修复它们，不能跳过。
+
 ## 问题
 
 flutter-rewrite 模板的 behavior-lock 和 rescue 工作流都有设计缺陷，导致：
@@ -47,14 +57,19 @@ commit: "behavior-lock($MODULE): N tests (X green, Y red from behavior change)"
 3. 增量更新
 4. 输出 diff 摘要
 
-### 禁止的模式
+### 超时策略
 
-| 禁止 | 原因 | 替代 |
-|------|------|------|
-| `sleep N && check` 轮询 | 浪费时间 | 前台跑 |
-| `timeout Nm flutter test` | 测试可能需要很久 | 不设超时 |
-| 全量重写已有测试 | 丢失 rescue 成果 | 增量更新 |
-| 首次跑 `flutter test` | 没实现，编译不过 | `flutter analyze` |
+| 操作 | 允许？ | 原因 |
+|------|--------|------|
+| `flutter test --timeout 30s` | **允许** | per-test 安全网，挂死标 fail 继续下一个 |
+| `timeout Nm flutter test` | 禁止 | 外部杀进程，丢失所有结果 |
+| `sleep N && check` 轮询 | 禁止 | 浪费时间 |
+| 全量重写已有测试 | 禁止 | 丢失 rescue 成果 |
+| 首次跑 `flutter test` | 禁止 | 没实现，编译不过，用 `flutter analyze` |
+
+**挂死的测试分类**：标记为 `hung: needs mock infrastructure`，不是 `failed`。区别：
+- `failed` = 行为不一致，rescue 修 v2 代码
+- `hung` = mock 不完整，rescue 先修测试基础设施
 
 ---
 
@@ -131,7 +146,13 @@ investigator:
     # 现有的保留，新增：
     - 非首轮：先 review 上轮 git diff，判断方向是否正确
     - 如果上轮 fix 没有让任何测试从 red→green，警告"无进展"
-    - 分类时标注严重度：CRITICAL（编译不过）> HIGH（逻辑错误）> LOW（widget 样式）
+    - 分类时标注严重度和类型：
+      CRITICAL: 编译错误（阻塞一切）
+      HIGH-INFRA: mock 不完整导致 test hang（阻塞行为验证，rescue 优先修）
+      HIGH-LOGIC: 逻辑测试 fail（行为不一致）
+      MEDIUM: widget 测试 fail（渲染/导航差异）
+      LOW: 样式差异
+    - hung 测试 ≠ failed 测试。hung = mock 基础设施问题，不是 v2 行为问题
 ```
 
 ### 收敛保护
@@ -144,9 +165,19 @@ rescue:
     输出卡点分析 + 剩余问题清单
   round_budget: |
     每轮最多改 5 个文件
-    每轮必须让至少 1 个测试从 red/skip → green，否则视为无进展
+    每轮必须让至少 1 个测试从 red/skip/hung → green，否则视为无进展
+  priority_order: |
+    Phase 1: 修 CRITICAL（编译错误）
+    Phase 2: 修 HIGH-INFRA（mock 基础设施，让 hung 测试能跑）
+    Phase 3: 修 HIGH-LOGIC（逻辑测试，让 red 变 green）
+    Phase 4: 修 MEDIUM（widget 测试，让 red 变 green）
+    每个 phase 完成后才进入下一个
 ```
 
+**为什么 HIGH-INFRA 优先于 HIGH-LOGIC？**
+
+hung 的测试 = 行为没被验证 = 重写目标的盲区。如果跳过 mock 修复直接改逻辑，可能 20 个 widget 行为从来没被检验过。先让所有测试能跑（pass 或 fail），再让它们变绿。
+
 ### 完整 rescue workflow
 
 ```yaml