@tea-agent/loop-agent 0.16.24 → 0.16.25

package/CHANGELOG.md

@@ -12,6 +12,10 @@
 - Backend Test Analysis、Case Manifest、Semantic Review 与 Classification 的严格 JSON 契约进一步对齐，生成节点明确字段白名单、`sourceBinding` 与 evidence gap 约束，避免模型自定义字段导致确定性门禁失败。
 - 新增升级后 init surface notifier：普通安全仓库命令结束后，当目标项目存在有效 `.harness/init-surface.json` 且 `controllerVersion` 与当前包版本不同时自动检测。surface 缺失/损坏、源仓库、未初始化目录与版本一致时直接跳过；`checkInitUpdate().ok` 时仅在无活跃运行时静默刷新 state；非 TTY 只向 stderr 输出 `loop-agent init reconcile --repo-root ...` 提示且不写入目标；TTY 且无 human decisions、无活跃 DAG/Worker 时可经明确 `y/yes` 同意后应用 deterministic safe actions；只有 model merge 时直接输出有边界指引，不询问“应用 0 个动作”。notifier 遵循全局 `--repo-root`、不写 stdout、不改变原命令退出码，CI、禁用环境变量、help/version、`--json`/`--markdown`、`init`、`run-dag`、`dag`、`loop`、`delegate`、`pi-prompt`、`cursor-prompt` 均跳过。
 - 新增统一命令 `loop-agent init reconcile --repo-root <target>`：surface 缺失返回 `needs-baseline` 且零写入，存在 human decisions 返回 `needs-human-decision` 且零写入，活跃 DAG/Worker 或 Worker 状态无法确认时返回 `blocked-active-runtime` 且零写入；其余情况复用现有 `applyInitUpdate({ applySafe: true })` 并复查返回 `clean`/`needs-model-merge`/`needs-safe-update`，支持 `--json`/`--markdown`。
+- 测试报告新增 L-5 指标消费与 Python coverage.py JSON、Java JaCoCo XML 的统一 Code Coverage v1 报告入口，覆盖通过率、AC/自动化覆盖率、稳定性、失败原因、缺陷、风险和回归建议；缺失覆盖率证据保持 `unavailable`，不改变 backend-test outcome gate。
+- 现有 backend-test DAG 在 retrospective 之后新增独立的 `l5-metrics-pi` 指标节点；它基于前序测试报告和 run-owned 证据输出 `L-5 ready/not-ready`，不创建独立 L-5 DAG，也不改变 Result v1 outcome gate。
+- 后端测试 DAG 从 38 个收敛为 24 个真实顶层节点；使用 fail-closed `runIf` 和复合 Shell capability 减少调度，同时保留双合同、Manifest、语义评审、JUnit、Result、分类、修复安全、追踪和最终 outcome 证据。三条可选修订/修复分支仍各最多执行一次。
+- Backend Test Analysis、Case Manifest、Semantic Review 与 Classification 的严格 JSON 契约进一步对齐，生成和修订节点明确字段白名单、`sourceBinding` 与 evidence gap 约束，避免模型自定义字段导致确定性门禁失败。
 
 ### 修复
 
@@ -35,6 +39,13 @@
 - Pi SDK 执行长推理或大段结构化输出时不再把高频流式增量事件无界累积到内存；同一响应在多个生命周期事件中重复出现的 Token 用量只统计一次，避免 `Invalid string length` 和成本数据虚高。
 - 后端测试复合执行节点继续保持 clean environment、失败分类和 fail-closed outcome，并为唯一 JUnit/initial Result、canonical Result、traceability 与 Observe 投影保留结构化运行证据。
 
+## [0.16.25] - 2026-07-22
+
+### 修复
+
+- Backend-test pytest preflight 与执行体改为 `&&` fail-closed：preflight 失败不再因 `;` 继续跑 pytest（I27 曾出现 preflight 报 `WELCOME_BASE_URL`/testRoot 错配仍执行用例）。
+- 本地 `npm start` / `node server.js` 类 `managed-command` 在 materialize 时降级为 `in-process`，清空 requiredEnv、seed server fixture，并把 scout `testRoot` 收敛到冻结根 `testcase/`；generate-pytest 提示要求 fixture 内启动服务，不再依赖 clean-env 注入 base URL。
+
 ## [0.16.24] - 2026-07-21
 
 ### 改进

package/dist/cli/command-definitions.js

@@ -3,6 +3,7 @@ import { runDocsArchive } from "../commands/docs-archive.js";
 import { runDocsAudit } from "../commands/docs-audit.js";
 import { runEval } from "../commands/eval.js";
 import { runCoverageAudit } from "../commands/coverage-audit.js";
+import { runCoverageReport } from "../commands/coverage-report.js";
 import { runExamples } from "../commands/examples.js";
 import { runCloseout } from "../commands/closeout.js";
 import { runHandoffCheck } from "../commands/handoff-check.js";
@@ -101,6 +102,7 @@ const PLAN_SUBCOMMANDS = ["list", "create", "complete", "check"];
 const SPINE_SUBCOMMANDS = ["audit"];
 const HANDOFF_SUBCOMMANDS = ["check", "coverage"];
 const HANDOFF_USAGE = "handoff <check|coverage> [taskId]";
+const COVERAGE_SUBCOMMANDS = ["report"];
 const REFERENCE_SUBCOMMANDS = ["index"];
 const STUDY_SUBCOMMANDS = ["init"];
 const WORKTREE_SUBCOMMANDS = ["create", "list", "remove"];
@@ -378,6 +380,17 @@ export const COMMAND_DEFINITIONS = [
             throw new Error(`usage: ${HANDOFF_USAGE}`);
         },
     },
+    {
+        name: "coverage",
+        adapter: "required",
+        tier: "operator",
+        intent: "Normalize Python coverage.py JSON or Java JaCoCo XML for test reports.",
+        usage: "coverage report --language python|java --input <path> [options]",
+        subcommands: [...COVERAGE_SUBCOMMANDS],
+        handler: async ({ repoRoot, subcommand, rest }) => {
+            await runCoverageReport(repoRoot, [subcommand, ...rest].filter(Boolean));
+        },
+    },
     {
         name: "goal",
         adapter: "required",

package/dist/cli/program.js

@@ -5,6 +5,7 @@ import { readPackageVersion } from "../shared/package-metadata.js";
 import { resolveAdapter } from "../adapters/index.js";
 import { runCloseout } from "../commands/closeout.js";
 import { runCoverageAudit } from "../commands/coverage-audit.js";
+import { runCoverageReport } from "../commands/coverage-report.js";
 import { parseCursorPromptArgs, printCursorPromptUsage, runCursorPrompt, } from "../commands/cursor-prompt.js";
 import { runDagApprove } from "../commands/dag-approve.js";
 import { runDagFinalVerification } from "../commands/dag-final-verification.js";
@@ -205,6 +206,9 @@ async function runCommanderAction(ctx, command, subcommand, rest) {
                 return;
             }
             throw new Error("usage: handoff <check|coverage> [taskId]");
+        case "coverage":
+            await runCoverageReport(ctx.repoRoot, compactArgs([subcommand, ...rest]));
+            return;
         case "goal":
             await runGoal(ctx.repoRoot, subcommand, rest);
             return;

package/dist/commands/coverage-report.js

@@ -0,0 +1,50 @@
+import { mkdir, writeFile } from "node:fs/promises";
+import path from "node:path";
+import { formatCoverageMarkdown, readCoverageArtifact } from "../workflows/dag/backend-test-coverage-contract.js";
+function value(args, flag) {
+    const index = args.findIndex((arg) => arg === flag || arg.startsWith(`${flag}=`));
+    if (index < 0)
+        return undefined;
+    const token = args[index];
+    return token.startsWith(`${flag}=`) ? token.slice(flag.length + 1) : args[index + 1];
+}
+function values(args, flag) {
+    return args.flatMap((arg, index) => {
+        if (arg === flag)
+            return args[index + 1] ? [args[index + 1]] : [];
+        return arg.startsWith(`${flag}=`) ? [arg.slice(flag.length + 1)] : [];
+    });
+}
+export async function runCoverageReport(repoRoot, args) {
+    if (args[0] !== "report" || args.includes("--help")) {
+        console.log("usage: coverage report --language python|java --input <coverage.json|jacoco.xml> [--output <path>] [--json|--markdown] --requirement-id <AC-id> --source-scope <path[,path]> [--commit <sha>] [--expected-sha256 <sha256>]");
+        return;
+    }
+    const input = value(args, "--input");
+    const language = value(args, "--language");
+    if (!input || (language !== "python" && language !== "java"))
+        throw new Error("coverage report requires --language python|java and --input");
+    const expectedSha = value(args, "--expected-sha256");
+    const sourcePaths = (value(args, "--source-scope") ?? "").split(",").map((item) => item.trim()).filter(Boolean);
+    const contract = await readCoverageArtifact(path.resolve(repoRoot, input), {
+        sourceScope: { requirementIds: values(args, "--requirement-id"), paths: sourcePaths },
+        commitSha: value(args, "--commit") ?? null,
+        toolVersion: value(args, "--tool-version") ?? null,
+        artifactPath: input,
+    });
+    if ((language === "python" && contract.language !== "python") || (language === "java" && contract.language !== "java"))
+        throw new Error("coverage artifact format does not match --language");
+    if (expectedSha && expectedSha !== contract.artifact.sha256)
+        throw new Error(`artifact SHA-256 mismatch: expected ${expectedSha}, got ${contract.artifact.sha256}`);
+    const markdown = args.includes("--markdown");
+    const output = value(args, "--output");
+    const rendered = markdown ? formatCoverageMarkdown(contract) : `${JSON.stringify(contract, null, 2)}\n`;
+    if (output) {
+        const outputPath = path.resolve(repoRoot, output);
+        await mkdir(path.dirname(outputPath), { recursive: true });
+        await writeFile(outputPath, rendered, "utf8");
+    }
+    else {
+        process.stdout.write(rendered);
+    }
+}

package/dist/workflows/dag/backend-test-coverage-contract.js

@@ -0,0 +1,202 @@
+import { createHash } from "node:crypto";
+import { readFile } from "node:fs/promises";
+import path from "node:path";
+import { z } from "zod";
+export const CODE_COVERAGE_SCHEMA_ID = "code-coverage-v1";
+const relativePath = z.string().min(1).refine((value) => !path.posix.isAbsolute(value) &&
+    !value.includes("\\") &&
+    !value.split("/").some((part) => part === "" || part === "." || part === ".."), "path must be a relative POSIX path");
+export const coverageMetricSchema = z.object({
+    status: z.enum(["available", "unavailable"]),
+    covered: z.number().int().min(0).nullable(),
+    total: z.number().int().min(0).nullable(),
+    ratio: z.number().min(0).max(1).nullable(),
+    reason: z.string().min(1).nullable(),
+}).strict();
+export const codeCoverageContractSchema = z.object({
+    schemaVersion: z.literal(1),
+    schemaId: z.literal(CODE_COVERAGE_SCHEMA_ID),
+    language: z.enum(["python", "java"]),
+    format: z.enum(["coverage.py-json", "jacoco-xml"]),
+    tool: z.string().min(1),
+    toolVersion: z.string().min(1).nullable(),
+    sourceScope: z.object({
+        requirementIds: z.array(z.string().regex(/^(?:REQ|BR|AC)-[A-Z0-9]+(?:-[A-Z0-9]+)*$/)),
+        paths: z.array(relativePath),
+    }).strict(),
+    commitSha: z.string().regex(/^[a-f0-9]{7,64}$/).nullable(),
+    metrics: z.object({
+        line: coverageMetricSchema,
+        branch: coverageMetricSchema,
+        function: coverageMetricSchema,
+    }).strict(),
+    artifact: z.object({
+        path: relativePath,
+        sha256: z.string().regex(/^[a-f0-9]{64}$/),
+    }).strict(),
+    missingData: z.array(z.string().min(1)),
+}).strict();
+function metric(covered, total, reason) {
+    if (covered === null || total === null || total === 0) {
+        return { status: "unavailable", covered, total, ratio: null, reason: reason ?? (total === 0 ? "denominator-is-zero" : "metric-missing") };
+    }
+    return { status: "available", covered, total, ratio: covered / total, reason: null };
+}
+function numberValue(value) {
+    return typeof value === "number" && Number.isInteger(value) && value >= 0 ? value : null;
+}
+function safeArtifactPath(value) {
+    const normalized = value.replaceAll(path.sep, "/");
+    if (path.posix.isAbsolute(normalized) || normalized.split("/").some((part) => part === "" || part === "." || part === "..")) {
+        throw new Error("artifact path must be a safe relative POSIX path");
+    }
+    return normalized;
+}
+function scopeMissing(scope) {
+    return scope.requirementIds.length === 0 ? ["source-scope-requirement-id-missing"] : [];
+}
+function baseContract(options, common) {
+    return {
+        schemaVersion: 1,
+        schemaId: CODE_COVERAGE_SCHEMA_ID,
+        ...common,
+        sourceScope: {
+            requirementIds: [...options.sourceScope.requirementIds],
+            paths: [...options.sourceScope.paths],
+        },
+        commitSha: options.commitSha,
+        artifact: { path: safeArtifactPath(options.artifactPath), sha256: options.artifactSha256 },
+    };
+}
+function parsePythonTotals(input, sourceScope) {
+    if (!input || typeof input !== "object")
+        throw new Error("coverage.py JSON must be an object");
+    const root = input;
+    const totals = root.totals;
+    if (!totals || typeof totals !== "object")
+        throw new Error("coverage.py JSON missing totals");
+    const files = root.files;
+    const scopedFiles = sourceScope.paths.length > 0 && files
+        ? Object.entries(files).filter(([file]) => sourceScope.paths.includes(file.replaceAll("\\", "/")))
+        : [];
+    const usesScopedFiles = sourceScope.paths.length > 0;
+    const values = usesScopedFiles ? scopedFiles.map(([, value]) => value) : null;
+    const get = (key) => {
+        if (values) {
+            let sum = 0;
+            for (const file of values) {
+                const data = file && typeof file === "object" ? file : {};
+                const value = numberValue(data[key]);
+                if (value !== null)
+                    sum += value;
+            }
+            return sum;
+        }
+        if (usesScopedFiles)
+            return null;
+        return numberValue(totals[key]);
+    };
+    return {
+        line: metric(get("covered_lines"), get("num_statements"), null),
+        branch: metric(get("covered_branches"), get("num_branches"), "coverage.py branch data missing"),
+        function: { status: "unavailable", covered: null, total: null, ratio: null, reason: "coverage.py JSON has no function coverage" },
+    };
+}
+function parseJacocoCounters(xml) {
+    const report = xml.match(/<report\b[^>]*>([\s\S]*?)<\/report>/i)?.[1];
+    if (report === undefined)
+        throw new Error("JaCoCo XML missing report root");
+    const reportLevel = report.split(/<(?:group|package)\b/i)[0] ?? "";
+    const counters = new Map();
+    for (const match of reportLevel.matchAll(/<counter\s+[^>]*type="([A-Z]+)"[^>]*missed="(\d+)"[^>]*covered="(\d+)"[^>]*\/>/gi)) {
+        const missed = Number(match[2]);
+        const covered = Number(match[3]);
+        counters.set(match[1].toUpperCase(), { covered, total: covered + missed });
+    }
+    return counters;
+}
+export function parseCoveragePyJson(input, options) {
+    const root = input;
+    const totals = parsePythonTotals(input, options.sourceScope);
+    const missingData = [...scopeMissing(options.sourceScope)];
+    const files = input && typeof input === "object" ? input.files : undefined;
+    if (options.sourceScope.paths.length > 0 && (!files || !options.sourceScope.paths.some((file) => Object.hasOwn(files, file))))
+        missingData.push("source-scope-not-found-in-artifact");
+    if (totals.branch.status === "unavailable")
+        missingData.push("branch-coverage-unavailable");
+    missingData.push("function-coverage-unavailable");
+    return codeCoverageContractSchema.parse({
+        ...baseContract(options, {
+            language: "python",
+            format: "coverage.py-json",
+            tool: "coverage.py",
+            toolVersion: typeof root?.meta?.version === "string" ? root.meta.version : options.toolVersion ?? null,
+        }),
+        metrics: totals,
+        missingData,
+    });
+}
+export function parseJacocoXml(xml, options) {
+    if (!/<report\b/i.test(xml))
+        throw new Error("JaCoCo XML missing report root");
+    const counters = parseJacocoCounters(xml);
+    const line = counters.get("LINE");
+    const branch = counters.get("BRANCH");
+    const method = counters.get("METHOD");
+    const missingData = [...scopeMissing(options.sourceScope)];
+    if (!line)
+        missingData.push("line-coverage-unavailable");
+    if (!branch)
+        missingData.push("branch-coverage-unavailable");
+    if (!method)
+        missingData.push("method-coverage-unavailable");
+    return codeCoverageContractSchema.parse({
+        ...baseContract(options, {
+            language: "java",
+            format: "jacoco-xml",
+            tool: "JaCoCo",
+            toolVersion: options.toolVersion ?? null,
+        }),
+        metrics: {
+            line: line ? metric(line.covered, line.total, null) : metric(null, null, "JaCoCo LINE counter missing"),
+            branch: branch ? metric(branch.covered, branch.total, null) : metric(null, null, "JaCoCo BRANCH counter missing"),
+            function: method ? metric(method.covered, method.total, null) : metric(null, null, "JaCoCo METHOD counter missing"),
+        },
+        missingData,
+    });
+}
+export async function readCoverageArtifact(inputPath, options) {
+    const raw = await readFile(inputPath, "utf8");
+    const artifactSha256 = createHash("sha256").update(raw).digest("hex");
+    const artifactPath = options.artifactPath ?? path.basename(inputPath);
+    const parseOptions = { ...options, artifactPath, artifactSha256 };
+    if (options.sourceScope.paths.some((value) => value.includes("..")))
+        throw new Error("unsafe source scope path");
+    if (inputPath.toLowerCase().endsWith(".xml"))
+        return parseJacocoXml(raw, parseOptions);
+    return parseCoveragePyJson(JSON.parse(raw), parseOptions);
+}
+export function formatCoverageMarkdown(contract) {
+    const row = (name, value) => `| ${name} | ${value.covered ?? "—"} | ${value.total ?? "—"} | ${value.ratio === null ? "unavailable" : `${(value.ratio * 100).toFixed(2)}%`} | ${value.status} | ${value.reason ?? "—"} |`;
+    return [
+        "# Code Coverage Report",
+        "",
+        `- Schema: ${contract.schemaId} v${contract.schemaVersion}`,
+        `- Language: ${contract.language}`,
+        `- Tool: ${contract.tool}${contract.toolVersion ? ` ${contract.toolVersion}` : ""}`,
+        `- Commit: ${contract.commitSha ?? "unavailable"}`,
+        `- Requirement IDs: ${contract.sourceScope.requirementIds.join(", ") || "unavailable"}`,
+        `- Source scope: ${contract.sourceScope.paths.join(", ") || "unavailable"}`,
+        `- Artifact: ${contract.artifact.path}`,
+        `- Artifact SHA-256: ${contract.artifact.sha256}`,
+        "",
+        "| Metric | Covered | Total | Ratio | Status | Reason |",
+        "|---|---:|---:|---:|---|---|",
+        row("Line", contract.metrics.line),
+        row("Branch", contract.metrics.branch),
+        row("Function/Method", contract.metrics.function),
+        "",
+        `Missing data: ${contract.missingData.length ? contract.missingData.join(", ") : "none"}`,
+        "",
+    ].join("\n");
+}

package/dist/workflows/dag/backend-test-execution-contract.js

@@ -334,6 +334,41 @@ function asRecord(value) {
  * Prefer exact schema payloads; otherwise map common discovery shapes onto the
  * pytest-centric runtime contract without inventing secrets or managed commands.
  */
+/** True when managed start is a local node/npm process the adapter cannot host. */
+export function isLocalManagedServerStart(start) {
+    if (!start)
+        return false;
+    const normalized = start.trim().toLowerCase();
+    if (!normalized)
+        return false;
+    return (/\bnpm(\s+run)?\s+start\b/.test(normalized) ||
+        /\bnode\s+server(\.js)?\b/.test(normalized) ||
+        /\bnode\s+\.\/?server(\.js)?\b/.test(normalized) ||
+        /\bbash\s+scripts\/fe-test-server\.sh\b/.test(normalized) ||
+        normalized === "node server.js" ||
+        normalized.includes("server.js"));
+}
+function seedLocalServerFixture(fixtures, managedStart) {
+    if (Array.isArray(fixtures) && fixtures.length > 0) {
+        return fixtures.filter((item) => Boolean(item && typeof item === "object" && !Array.isArray(item)));
+    }
+    if (managedStart.includes("server") || managedStart.includes("npm")) {
+        return [
+            {
+                name: "server-bootstrap",
+                sourcePath: "server.js",
+                kind: "server-bootstrap",
+            },
+        ];
+    }
+    return [
+        {
+            name: "pytest-test-root",
+            sourcePath: BACKEND_TEST_EXECUTION_DEFAULT_TEST_ROOT,
+            kind: "test-root",
+        },
+    ];
+}
 /** Drop empty managedCommand strings; omit block when not managed-command. */
 export function sanitizeBackendTestExecutionInput(value) {
     const record = asRecord(value);
@@ -359,6 +394,51 @@ export function sanitizeBackendTestExecutionInput(value) {
             next.managedCommand = cleaned;
         }
     }
+    // Adapter always executes `python -m pytest testcase/`. Scout-chosen relative roots such as
+    // tests/api/** are product sample trees, not the frozen automation root. Absolute / ..
+    // paths stay untouched so schema materialize remains fail-closed.
+    if (typeof next.testRoot === "string" && next.testRoot.trim()) {
+        const rawRoot = next.testRoot.trim();
+        const normalizedRoot = rawRoot.replace(/\/+$/, "");
+        const looksUnsafe = normalizedRoot.startsWith("/") ||
+            normalizedRoot.includes("..") ||
+            normalizedRoot.includes("\\") ||
+            /^[A-Za-z]:/.test(normalizedRoot);
+        if (!looksUnsafe &&
+            normalizedRoot !== BACKEND_TEST_EXECUTION_DEFAULT_TEST_ROOT) {
+            const gaps = Array.isArray(next.evidenceGaps)
+                ? [...next.evidenceGaps]
+                : [];
+            gaps.push({
+                description: `scout testRoot=${normalizedRoot} remapped to frozen adapter root ${BACKEND_TEST_EXECUTION_DEFAULT_TEST_ROOT}`,
+                sourceRef: "adapter:backend-test-execution",
+            });
+            next.evidenceGaps = gaps;
+            next.testRoot = BACKEND_TEST_EXECUTION_DEFAULT_TEST_ROOT;
+        }
+    }
+    // Local node/npm managed-command is not hosted by the clean-env pytest shell.
+    // Demote to in-process so generate-pytest must bootstrap the server inside fixtures
+    // instead of requiring host-injected base URL env vars that clean env cannot provide.
+    const managedStart = asRecord(next.managedCommand) &&
+        typeof asRecord(next.managedCommand).start === "string"
+        ? String(asRecord(next.managedCommand).start)
+        : "";
+    if (next.targetMode === "managed-command" &&
+        isLocalManagedServerStart(managedStart)) {
+        next.targetMode = "in-process";
+        next.requiredEnvNames = [];
+        next.existingFixtures = seedLocalServerFixture(Array.isArray(next.existingFixtures) ? next.existingFixtures : null, managedStart);
+        const gaps = Array.isArray(next.evidenceGaps)
+            ? [...next.evidenceGaps]
+            : [];
+        gaps.push({
+            description: "local managed-command demoted to in-process: clean-env pytest shell does not start npm/node servers or inject base URL env; tests must bootstrap via fixtures",
+            sourceRef: asRecord(next.managedCommand)?.sourceRef ||
+                "adapter:backend-test-execution",
+        });
+        next.evidenceGaps = gaps;
+    }
     // Near-schema scouts sometimes emit in-process with existingFixtures: [].
     // Only rewrite near-schema payloads here; free-form envelopes keep empty/missing
     // fixtures so coerceBackendTestExecutionInput can map discoveredFixtures first.
@@ -369,23 +449,7 @@ export function sanitizeBackendTestExecutionInput(value) {
     if (nearSchema &&
         (next.targetMode === "in-process" || next.targetMode === undefined) &&
         (!fixtures || fixtures.length === 0)) {
-        const managedStart = asRecord(next.managedCommand) &&
-            typeof asRecord(next.managedCommand).start === "string"
-            ? String(asRecord(next.managedCommand).start)
-            : "";
-        next.existingFixtures = [
-            managedStart.includes("server")
-                ? {
-                    name: "server-bootstrap",
-                    sourcePath: "server.js",
-                    kind: "server-bootstrap",
-                }
-                : {
-                    name: "pytest-test-root",
-                    sourcePath: BACKEND_TEST_EXECUTION_DEFAULT_TEST_ROOT,
-                    kind: "test-root",
-                },
-        ];
+        next.existingFixtures = seedLocalServerFixture(fixtures, managedStart);
         if (next.targetMode === undefined)
             next.targetMode = "in-process";
     }
@@ -631,10 +695,12 @@ export function buildBackendTestExecutionPreflightShellSnippet(options) {
         `console.log("backend-test preflight ok: framework=pytest testRoot="+testRoot+" targetMode="+contract.targetMode);'`,
         ' "${CONTRACT}"',
     ].join("");
+    // Fail-closed: join with && so a preflight exit 2 never continues into pytest.
+    // Historical ";" chains recorded I27-style false progresses (env missing + pytest ran).
     return [
         'test -n "${HARNESS_DAG_RUN_DIR:-}" || { echo "missing HARNESS_DAG_RUN_DIR for backend pytest preflight" >&2; exit 2; }',
         `CONTRACT="\${HARNESS_DAG_RUN_DIR}/${contractRelativePath}"`,
         'test -f "${CONTRACT}" || { echo "missing backend-test execution contract: ${CONTRACT}" >&2; exit 2; }',
         nodePreflight,
-    ].join("; ");
+    ].join(" && ");
 }

package/dist/workflows/dag/backend-test-stability-contract.js

@@ -0,0 +1,57 @@
+import { z } from "zod";
+export const STABILITY_EVIDENCE_SCHEMA_ID = "stability-evidence-v1";
+const runRefSchema = z.object({
+    runId: z.string().min(1),
+    suiteId: z.string().min(1),
+    version: z.string().min(1),
+    commitSha: z.string().regex(/^[a-f0-9]{7,64}$/),
+    success: z.boolean(),
+    resultRef: z.string().min(1),
+}).strict();
+export const stabilityEvidenceSchema = z.object({
+    schemaVersion: z.literal(1),
+    schemaId: z.literal(STABILITY_EVIDENCE_SCHEMA_ID),
+    suiteId: z.string().min(1),
+    version: z.string().min(1),
+    commitSha: z.string().regex(/^[a-f0-9]{7,64}$/),
+    runs: z.array(runRefSchema),
+    recordedRuns: z.number().int().min(0),
+    successfulRuns: z.number().int().min(0),
+    failedRuns: z.number().int().min(0),
+    ratio: z.number().min(0).max(1).nullable(),
+    minimumRuns: z.literal(5),
+    status: z.enum(["available", "unavailable"]),
+    reason: z.string().min(1).nullable(),
+}).strict().superRefine((value, ctx) => {
+    if (value.recordedRuns !== value.runs.length)
+        ctx.addIssue({ code: z.ZodIssueCode.custom, message: "recordedRuns must equal runs.length", path: ["recordedRuns"] });
+    if (value.successfulRuns !== value.runs.filter((run) => run.success).length)
+        ctx.addIssue({ code: z.ZodIssueCode.custom, message: "successfulRuns must match run facts", path: ["successfulRuns"] });
+    if (value.failedRuns !== value.runs.filter((run) => !run.success).length)
+        ctx.addIssue({ code: z.ZodIssueCode.custom, message: "failedRuns must match run facts", path: ["failedRuns"] });
+    for (const [index, run] of value.runs.entries()) {
+        if (run.suiteId !== value.suiteId || run.version !== value.version || run.commitSha !== value.commitSha) {
+            ctx.addIssue({ code: z.ZodIssueCode.custom, message: "all runs must bind to the same suite/version/commit", path: ["runs", index] });
+        }
+    }
+    if (value.recordedRuns >= value.minimumRuns && value.ratio === null)
+        ctx.addIssue({ code: z.ZodIssueCode.custom, message: "ratio required when minimum sample is met", path: ["ratio"] });
+});
+export function buildStabilityEvidence(input) {
+    const recordedRuns = input.runs.length;
+    const successfulRuns = input.runs.filter((run) => run.success).length;
+    const failedRuns = recordedRuns - successfulRuns;
+    const status = recordedRuns >= 5 ? "available" : "unavailable";
+    return stabilityEvidenceSchema.parse({
+        schemaVersion: 1,
+        schemaId: STABILITY_EVIDENCE_SCHEMA_ID,
+        ...input,
+        recordedRuns,
+        successfulRuns,
+        failedRuns,
+        ratio: recordedRuns >= 5 ? successfulRuns / recordedRuns : null,
+        minimumRuns: 5,
+        status,
+        reason: recordedRuns >= 5 ? null : "minimum-sample-size-not-met",
+    });
+}

package/dist/workflows/dag/init-hybrid.js

@@ -2912,6 +2912,8 @@ function buildGenerateBackendPytestNode(sources) {
             "- Validated Backend Test Analysis v1 under the current run contracts/ (analysis gate).",
             "- Validated Backend Test Execution Contract v1 under contracts/backend-test-execution.json (execution gate).",
             "Use only fixture names, env NAMES, testRoot, targetMode, and field/API facts already present in those contracts or reviewed cases. Do not invent production credentials or secret values.",
+            "When targetMode is in-process (including demoted local npm/node managed servers): bootstrap the service inside function-scoped pytest fixtures under testcase/** — e.g. subprocess node server.js / startWelcomeServer with PORT=0 — and never require host-injected base URL env vars (clean-env shell will not provide WELCOME_BASE_URL / API_BASE_URL).",
+            "Do not depend on requiredEnvNames being present at process start for in-process mode; if the contract still lists an env name, the fixture must set it or start the server without that env.",
             "",
             "## Output Steps (do in order):",
             "1. First, output a brief summary: how many files, how many test functions planned",
@@ -3062,8 +3064,9 @@ function buildExecuteBackendPytestNode(sources, options = {}) {
     const reportStem = options.reportStem ?? "backend-test";
     const reportName = `${reportStem}-junit.xml`;
     const exitName = `${reportStem}-pytest-exit.txt`;
-    const pytestCommand = [
-        preflightCommand,
+    // Preflight snippet is already fail-closed (&&). Only the pytest body may use
+    // ";" so STATUS capture still runs after non-zero pytest exits.
+    const pytestBody = [
         `REPORT="\${HARNESS_DAG_RUN_DIR}/reports/${reportName}"`,
         `EXIT_FILE="\${HARNESS_DAG_RUN_DIR}/reports/${exitName}"`,
         'mkdir -p "$(dirname "${REPORT}")"',
@@ -3075,6 +3078,7 @@ function buildExecuteBackendPytestNode(sources, options = {}) {
         'if { [ "${STATUS}" -eq 0 ] || [ "${STATUS}" -eq 1 ]; } && [ -s "${REPORT}" ]; then exit 0; fi',
         'exit "${STATUS}"',
     ].join("; ");
+    const pytestCommand = `${preflightCommand} && { ${pytestBody}; }`;
     return {
         id: nodeId,
         depends_on: options.dependsOn ?? [
@@ -3168,21 +3172,24 @@ function buildTestRetrospectNode(sources) {
             "## Stats authority (deterministic only):",
             "- Pass rate, failed/error/skipped counts, and failure list MUST come from contracts/backend-test-result.json only.",
             "- AC coverage ratio / case counts MUST come from contracts/backend-test-case-manifest.json coverageSummary (or gate-derived fields). Do NOT invent coverage %.",
+            "- Automation coverage MUST use coverageSummary.generatedCount / coverageSummary.caseCount. If either field is missing, write unavailable; do not estimate.",
+            "- Code coverage MUST come only from the validated contracts/code-coverage-v1.json artifact generated by coverage.py/pytest-cov or JaCoCo. Show line, branch, function/method, covered, total, ratio, threshold, status, source scope, requirement IDs, tool, commit, and artifact hash.",
+            "- Stability MUST come from independent Stability Evidence: use successfulRuns / recordedRuns, same suite/version, and require n≥5; a single run is unavailable.",
             "- Use classify-backend-test-result-pi JSON as interpretive evidence only.",
             "- NEVER rewrite a failed result as passed. Outcome gate (not this report) is authoritative for task success.",
             "",
             "## Report Structure:",
             "1. Maturity Rating with rationale",
-            "2. Test Coverage Summary (manifest coverageSummary + Result v1 pass rate)",
-            "3. Review Findings and resolution status",
-            "4. Failed Test Analysis (if any) + classification category",
-            "5. Recommendations for improvement",
+            "2. Test Coverage Summary (Result v1 pass rate, AC coverage, automation coverage, code coverage, and stability evidence)",
+            "3. Failed Test Analysis (failure/error details, category, confidence, evidence, and owner direction)",
+            "4. Defects (local Bug ledger in the same report directory; unavailable when absent)",
+            "5. Risks (Critical/High/Medium/Low, impact, controls, residual risk, treatment; Critical risks block L-5, High risks do not automatically block)",
+            "6. Regression Recommendations (immediate, related, periodic, deferred; every item links to failure/risk/AC/case IDs)",
+            "7. L-5 conclusion with blocking items",
             "",
             "## Rating Criteria:",
-            "- A: coverageSummary.acCoverageRatio=1 + 100% pytest pass + no Critical findings",
-            "- B: acCoverageRatio≥0.8 + ≥90% pass + Low findings only",
-            "- C: acCoverageRatio≥0.6 + ≥70% pass + no Critical findings",
-            "- D: below C thresholds",
+            "- L-5 ready requires pass rate=100%, AC coverage=100%, automation coverage≥90%, stability≥95% with n≥5, line coverage≥80%, branch coverage≥70%, skipped=0, and no blocking Critical risk.",
+            "- Any required metric fail or unavailable means L-5 not-ready. Function/method coverage is displayed but not a gate. Preserve the existing A/B/C/D single-run rating separately.",
             "",
             "## Constraints:",
             canWriteReport
@@ -3197,7 +3204,7 @@ function buildBackendTestOutcomeGateNode(sources) {
     const gateCommand = buildBackendTestOutcomeGateShellSnippet();
     return {
         id: "backend-test-outcome-gate-shell",
-        depends_on: ["test-retrospect-pi"],
+        depends_on: ["l5-metrics-pi"],
         role: "verifier",
         executor: "shell",
         complexity: "LOW",
@@ -3220,6 +3227,30 @@ function buildBackendTestOutcomeGateNode(sources) {
         },
     };
 }
+function buildL5MetricsNode(sources) {
+    return {
+        id: "l5-metrics-pi",
+        depends_on: ["test-retrospect-pi"],
+        role: "reviewer",
+        executor: "pi",
+        complexity: "MED",
+        writePolicy: "read-only",
+        allowedPaths: commonReadOnlyPaths(sources),
+        forbiddenPaths: commonForbiddenPaths(sources),
+        outputContract: "Exactly one JSON object with status=ready|not-ready, metrics, and blockingItems; no file writes.",
+        subtask_prompt: [
+            "You are the independent L-5 metrics node at the end of the existing backend-test DAG.",
+            "The direct upstream test-retrospect-pi output is the primary report to assess. Read it together with the run-owned Result v1, Case Manifest v1, Code Coverage v1, and Stability Evidence artifacts when present.",
+            "Do not create a new DAG, rewrite the retrospective report, change test outcome, or modify any repository file.",
+            "Return exactly one JSON object and no surrounding prose.",
+            "Required shape: {\"status\":\"ready\"|\"not-ready\",\"metrics\":{\"passRate\":metric,\"acCoverage\":metric,\"automationCoverage\":metric,\"stability\":metric,\"lineCoverage\":metric,\"branchCoverage\":metric,\"skipped\":metric,\"criticalRisks\":metric},\"blockingItems\":[string]}.",
+            "Each metric must contain numerator, denominator, ratio, threshold, status=pass|fail|unavailable, and reason (null only when passed).",
+            "Use only explicit evidence. Missing or invalid required evidence is unavailable, never zero or an estimate.",
+            "L-5 ready requires pass rate=100%, AC coverage=100%, automation coverage>=90%, stability>=95% with n>=5, line coverage>=80%, branch coverage>=70%, skipped=0, and zero blocking Critical risks.",
+            "Function/method coverage is display-only and does not gate L-5. Preserve the distinction between L-5 maturity and the Result v1 outcome gate.",
+        ].join("\n\n"),
+    };
+}
 const BACKEND_TEST_DEFAULTS = {
     ...HYBRID_DEFAULTS,
     writePolicy: "read-only",
@@ -3237,7 +3268,7 @@ function buildBackendTestHybridDag(sources) {
     const globalConstraints = [
         ...taskConfig.hardConstraints,
         ...STANDARD_GLOBAL_CONSTRAINTS,
-        "backend-test-dag uses exactly 15 real top-level tasks and executes pytest exactly once.",
+        "backend-test-dag uses exactly 16 real top-level tasks and executes pytest exactly once.",
         "Case and semantic request-revision verdicts fail at deterministic gates; no in-run revision or repair writer is authorized.",
         "Analysis, execution, manifest, semantic review, single-run result, classification, canonical result, retrospective and outcome evidence remain run-owned and fail-closed.",
         "Functional test case IDs must use BE-<MODULE>-<NNN> format.",
@@ -3301,8 +3332,10 @@ function buildBackendTestHybridDag(sources) {
     const retrospect = buildTestRetrospectNode(sources);
     retrospect.depends_on = [context.id];
     retrospect.subtask_prompt = retrospect.subtask_prompt.replaceAll("select-effective-backend-test-result-shell", context.id);
+    const l5Metrics = buildL5MetricsNode(sources);
+    l5Metrics.depends_on = [retrospect.id];
     const outcome = buildBackendTestOutcomeGateNode(sources);
-    const tasks = [analyze, contracts, generateCases, manifest, reviewCases, caseGate, generatePytest, semanticReview, semanticMaterialize, semanticGate, execute, classify, context, retrospect, outcome];
+    const tasks = [analyze, contracts, generateCases, manifest, reviewCases, caseGate, generatePytest, semanticReview, semanticMaterialize, semanticGate, execute, classify, context, retrospect, l5Metrics, outcome];
     const spec = { version: 3, title: `Backend test DAG: ${taskConfig.title}`, runtimeContract: GENERATED_DAG_RUNTIME_CONTRACT, outputLanguage: sources.outputLanguage ?? DEFAULT_DAG_OUTPUT_LANGUAGE, objective: extractObjective(sources.requirementMarkdown, taskConfig.title), successCriteria: extractSuccessCriteria(sources.requirementMarkdown, sources.taskId), globalConstraints, defaults: { ...BACKEND_TEST_DEFAULTS, contextProfile: taskConfig.contextProfile }, skillsByRole: BACKEND_TEST_SKILLS_BY_ROLE, executorModels: sources.executorModelMatrix ?? DEFAULT_DAG_EXECUTOR_MODELS, tasks };
     applyDefaultReadOnlyRetryPolicy(spec);
     parseDagSpec(spec);

package/dist/workflows/dag/l5-report-metrics.js

@@ -0,0 +1,36 @@
+function unavailable(reason, numerator = null, denominator = null, threshold = null) {
+    return { numerator, denominator, ratio: null, threshold, status: "unavailable", reason };
+}
+function ratioMetric(numerator, denominator, threshold, label) {
+    if (denominator === 0)
+        return unavailable(`${label}-denominator-is-zero`, numerator, denominator, threshold);
+    const ratio = numerator / denominator;
+    return { numerator, denominator, ratio, threshold, status: ratio >= threshold ? "pass" : "fail", reason: ratio >= threshold ? null : `${label}-below-threshold` };
+}
+export function computeL5ReportMetrics(input) {
+    const executed = input.result.passed + input.result.failed + input.result.error;
+    const metrics = {
+        passRate: ratioMetric(input.result.passed, executed, 1, "pass-rate"),
+        acCoverage: input.manifest.coverageSummary
+            ? input.manifest.coverageSummary.explicitAcCount === 0
+                ? { numerator: 0, denominator: 0, ratio: 1, threshold: 1, status: "pass", reason: null }
+                : ratioMetric(input.manifest.coverageSummary.coveredAcCount, input.manifest.coverageSummary.explicitAcCount, 1, "ac-coverage")
+            : unavailable("case-manifest-coverage-missing", null, null, 1),
+        automationCoverage: input.manifest.coverageSummary
+            ? ratioMetric(input.manifest.coverageSummary.generatedCount, input.manifest.coverageSummary.caseCount, 0.9, "automation-coverage")
+            : unavailable("case-manifest-coverage-missing", null, null, 0.9),
+        stability: input.stability?.status === "available" && input.stability.ratio !== null
+            ? { numerator: input.stability.successfulRuns, denominator: input.stability.recordedRuns, ratio: input.stability.ratio, threshold: 0.95, status: input.stability.ratio >= 0.95 ? "pass" : "fail", reason: input.stability.ratio >= 0.95 ? null : "stability-below-threshold" }
+            : unavailable(input.stability?.reason ?? "stability-evidence-missing", input.stability?.successfulRuns ?? null, input.stability?.recordedRuns ?? null, 0.95),
+        lineCoverage: input.coverage?.metrics.line.status === "available" && input.coverage.metrics.line.ratio !== null
+            ? { numerator: input.coverage.metrics.line.covered, denominator: input.coverage.metrics.line.total, ratio: input.coverage.metrics.line.ratio, threshold: 0.8, status: input.coverage.metrics.line.ratio >= 0.8 ? "pass" : "fail", reason: input.coverage.metrics.line.ratio >= 0.8 ? null : "line-coverage-below-threshold" }
+            : unavailable(input.coverage?.metrics.line.reason ?? "line-coverage-missing", input.coverage?.metrics.line.covered ?? null, input.coverage?.metrics.line.total ?? null, 0.8),
+        branchCoverage: input.coverage?.metrics.branch.status === "available" && input.coverage.metrics.branch.ratio !== null
+            ? { numerator: input.coverage.metrics.branch.covered, denominator: input.coverage.metrics.branch.total, ratio: input.coverage.metrics.branch.ratio, threshold: 0.7, status: input.coverage.metrics.branch.ratio >= 0.7 ? "pass" : "fail", reason: input.coverage.metrics.branch.ratio >= 0.7 ? null : "branch-coverage-below-threshold" }
+            : unavailable(input.coverage?.metrics.branch.reason ?? "branch-coverage-missing", input.coverage?.metrics.branch.covered ?? null, input.coverage?.metrics.branch.total ?? null, 0.7),
+        skipped: { numerator: input.result.skipped, denominator: input.result.skipped, ratio: input.result.skipped === 0 ? 1 : 0, threshold: 1, status: input.result.skipped === 0 ? "pass" : "fail", reason: input.result.skipped === 0 ? null : "skipped-tests-present" },
+        criticalRisks: { numerator: input.criticalRiskCount, denominator: input.criticalRiskCount, ratio: input.criticalRiskCount === 0 ? 1 : 0, threshold: 1, status: input.criticalRiskCount === 0 ? "pass" : "fail", reason: input.criticalRiskCount === 0 ? null : "critical-risk-present" },
+    };
+    const blockingItems = Object.entries(metrics).filter(([, value]) => value.status !== "pass").map(([name, value]) => `${name}:${value.reason ?? value.status}`);
+    return { status: blockingItems.length === 0 ? "ready" : "not-ready", metrics, blockingItems };
+}

package/docs/architecture/evolution.md

@@ -35,10 +35,12 @@
 | 云 Task Pool / SQL / Orchestrator | 规划 / 未实现 | 同上（第 2 月原始设计已调整为本地 Feature 闭环） |
 | 多仓库平台 | 规划 / 未实现 | 同上 |
 | 组织级服务 | 规划 / 未实现 | 同上 |
-| Web Console（远端） | 规划 / 未实现 | 同上 |
+| Web Console（远端） | 规划 / 未实现；指多用户/远程编排平台，不等同于 `docs/design/local-operator-console-from-pi-web.md` 的单机 loopback Operator Console | 同上 |
 | Dynamic Workflow runtime limits 强执法、更广 profile | 设计输入 | `ai_workspace/loop-agent/design/dynamic-workflow-dag-engine-roadmap.md`（未勾选 phase） |
 | Loop 与 Dynamic Workflow 更深的双向集成、稳定化与自动恢复 | 设计输入 | 同上；当前已有基础 `workflow` action，不应误写为完全缺失 |
 
+> 本地 Loop Operator Console 已在 `docs/design/local-operator-console-from-pi-web.md` 作为独立设计输入：单仓库、loopback、随 `@tea-agent/loop-agent` 同包发布、canonical mutation 只经 sibling CLI；它不是本表中的远端 Web Console，也不能把远端多租户/云编排需求偷渡进本地 MVP。
+
 > 注意：`ai_workspace/loop-agent/design/dynamic-workflow-dag-engine-roadmap.md` 是 2026-07-04 历史叙述；文中凡把 Cursor 写成受治理 executor 或 `loop` 的 `cursor-fix` 动作，均为**历史叙述**，现状以 Pi-only + 显式 `cursor-prompt` sidecar 为准。
 
 ## 已收敛为 archive / 历史基线（非未来）

package/docs/templates/backend-test-dag.generate-pytest.prompt.md

@@ -45,6 +45,8 @@ Your job is to convert reviewed test cases under `testcase/md/` into pytest auto
 
 Do NOT re-read source documents for free-form analysis. Use only reviewed cases and the validated contracts. Use only fixture/env/testRoot facts already present in the execution contract; never invent production credentials or secret values.
 
+When `targetMode` is `in-process` (including demoted local npm/node managed servers): bootstrap the service inside function-scoped pytest fixtures under `testcase/**` (for example subprocess `node server.js` / `startWelcomeServer` with `PORT=0`). Never require host-injected base URL env vars such as `WELCOME_BASE_URL` / `API_BASE_URL` — the clean-env pytest shell will not provide them.
+
 ### Conversion Rules
 
 #### File Naming

package/docs/templates/backend-test-dag.json

@@ -28,7 +28,7 @@
     "Root artifacts/ is reserved for explicit exclusive write nodes, not read-only scout/reviewer output",
     "exclusive implementer nodes must use narrow, concrete writeSet paths; never keep ** or repo root",
     "Replace REPLACE/WITH/NARROW/IMPLEMENT/PATHS/** with concrete paths before executing the implementation writer",
-    "backend-test-dag uses exactly 15 real top-level tasks and executes pytest exactly once.",
+    "backend-test-dag uses exactly 16 real top-level tasks and executes pytest exactly once.",
     "Case and semantic request-revision verdicts fail at deterministic gates; no in-run revision or repair writer is authorized.",
     "Analysis, execution, manifest, semantic review, single-run result, classification, canonical result, retrospective and outcome evidence remain run-owned and fail-closed.",
     "Functional test case IDs must use BE-<MODULE>-<NNN> format.",
@@ -280,7 +280,7 @@
         ".harness/dag-runs/**",
         "artifacts/**"
       ],
-      "subtask_prompt": "Convert the reviewed test cases under testcase/md/ into pytest automation code.\n\n\n\n## Inputs (MUST use validated contracts):\n\n- Reviewed cases under testcase/md/ (after review-backend-cases-gate-shell).\n\n- Validated Backend Test Analysis v1 under the current run contracts/ (analysis gate).\n\n- Validated Backend Test Execution Contract v1 under contracts/backend-test-execution.json (execution gate).\n\nUse only fixture names, env NAMES, testRoot, targetMode, and field/API facts already present in those contracts or reviewed cases. Do not invent production credentials or secret values.\n\n\n\n## Output Steps (do in order):\n\n1. First, output a brief summary: how many files, how many test functions planned\n\n2. Then write each test file under testcase/\n\n\n\n## Format Rules:\n\n- File prefix: test_<module>.py\n\n- Function name: test_BE_<MODULE>_<NNN>_<description>\n\n- Docstring first line: BE-<MODULE>-<NNN>: <Case Title>\n\n- 1:1 mapping: each functional case → one pytest function\n\n\n\n## Implementation Rules:\n\n- Use assert statements, not unittest assertions\n\n- Use @pytest.mark.parametrize for boundary cases when the case defines edge values\n\n- Use markers: @pytest.mark.positive, @pytest.mark.negative, @pytest.mark.boundary\n\n\n\n## Test Data Preparation Rules (MUST follow):\n\n\n\n### When Setup is Needed\n\nSetup phase is REQUIRED only when test cases need pre-existing data:\n\n- Query/Read APIs: need data to exist before querying\n\n- Update/Delete APIs: need data to exist before modifying\n\n- State transition tests: need data in specific state\n\n\n\nSetup phase is NOT needed for:\n\n- Create APIs: testing the creation itself\n\n- Validation tests: testing input validation with invalid data\n\n\n\n### Data Setup Strategy\n\nWhen setup is needed:\n\n1. Prefer function-scoped fixtures for isolation; use module/session scope only when cases explicitly share immutable fixtures\n\n2. Prefer API-based setup from the upstream analyze-inputs-pi API list and reviewed cases\n\n3. If a required helper/factory is missing, create NEW files only under testcase/**/helpers/** or testcase/**/factories/**\n\n\n\n### Data Construction Priority\n\n1. API-first: construct data via documented APIs from analyze-inputs-pi / reviewed cases\n\n2. Reuse existing conftest fixtures when present (read-only)\n\n3. Direct DB writes are LAST RESORT and only if conftest already exposes a safe test DB fixture with rollback/isolation\n\n4. If neither API nor safe DB fixture exists, skip the case with an explicit gap note — do NOT invent production DB credentials or write live data\n\n\n\n### API Data Construction\n\n- Prefer the analyze-inputs-pi API Endpoints section and reviewed cases for method/path/fields\n\n- Chain API calls only when cases document multi-step preconditions\n\n- Store created resource IDs in fixtures for reuse\n\n- Do NOT broadly search host route/controller trees for secrets, .env, private keys, or production configs\n\n- Read host API definitions only when needed to resolve a field name already referenced by reviewed cases; stay out of credential/config paths\n\n\n\n### Database Data Construction (restricted)\n\n- Allowed only via existing conftest test-DB fixtures with transaction rollback or equivalent isolation\n\n- Never hardcode connection strings, passwords, tokens, or cloud credentials\n\n- Never target production/shared non-test databases\n\n- If isolation is unclear, report the gap instead of writing DB rows\n\n\n\n## Assertion Rules (MUST follow):\n\n\n\n### Positive Path\n\nMUST assert ALL of the following:\n\n1. HTTP status code: as defined in API spec (e.g. 200, 201)\n\n2. Response structure: key fields exist in response body\n\n3. Specific values: each field equals expected value from test case\n\n4. Data type: each field is correct type\n\n\n\n### Negative Path\n\nMUST assert ALL of the following:\n\n1. HTTP status code: as defined in API spec (e.g. 400, 404, 500)\n\n2. Error code field: field name from API spec (e.g. code, error_code, errcode, ret)\n\n3. Error message field: field name from API spec (e.g. message, msg, errmsg, error)\n\n\n\n### Field Name Resolution\n\nField names MUST come from the upstream analyze-inputs-pi output (API Endpoints section) or reviewed cases, NOT guessed. For example:\n\n- If API spec defines {\"ret\": 0, \"msg\": \"success\"}, assert response.json()['ret'] and response.json()['msg']\n\n- If API spec defines {\"code\": 4001, \"message\": \"error\"}, assert response.json()['code'] and response.json()['message']\n\n\n\n## Conditional Implementation (include ONLY if test cases exist):\n\n- Authentication tests: implement ONLY if testcase/md/ contains auth-related cases\n\n- Timeout tests: implement ONLY if testcase/md/ contains timeout-related cases\n\n- Boundary tests: implement ONLY when cases define value ranges, length limits, or format constraints\n\n- Use @pytest.mark.auth for auth tests, @pytest.mark.timeout for timeout tests\n\n- If no such cases exist, do NOT add these tests\n\n\n\n## Constraints:\n\n- Only create NEW files under writeSet: testcase/**/test_*.py, testcase/**/helpers/**, testcase/**/factories/**\n\n- Do NOT modify existing framework files (conftest.py, pytest.ini, pyproject.toml, setup.cfg, __init__.py)\n\n- If a test filename exists, add suffix: test_order.py → test_order_01.py\n\n- Do NOT re-read source documents — use reviewed cases under testcase/md/ and upstream analyze-inputs-pi output only\n\n- Read existing conftest.py/pytest.ini to understand conventions, but do NOT modify them\n\n- Do NOT execute pytest/python -m pytest or npm test in this node; the single execution is owned by the dedicated shell node. Local smoke runs create __pycache__/.pytest_cache and are unnecessary here."
+      "subtask_prompt": "Convert the reviewed test cases under testcase/md/ into pytest automation code.\n\n\n\n## Inputs (MUST use validated contracts):\n\n- Reviewed cases under testcase/md/ (after review-backend-cases-gate-shell).\n\n- Validated Backend Test Analysis v1 under the current run contracts/ (analysis gate).\n\n- Validated Backend Test Execution Contract v1 under contracts/backend-test-execution.json (execution gate).\n\nUse only fixture names, env NAMES, testRoot, targetMode, and field/API facts already present in those contracts or reviewed cases. Do not invent production credentials or secret values.\n\nWhen targetMode is in-process (including demoted local npm/node managed servers): bootstrap the service inside function-scoped pytest fixtures under testcase/** — e.g. subprocess node server.js / startWelcomeServer with PORT=0 — and never require host-injected base URL env vars (clean-env shell will not provide WELCOME_BASE_URL / API_BASE_URL).\n\nDo not depend on requiredEnvNames being present at process start for in-process mode; if the contract still lists an env name, the fixture must set it or start the server without that env.\n\n\n\n## Output Steps (do in order):\n\n1. First, output a brief summary: how many files, how many test functions planned\n\n2. Then write each test file under testcase/\n\n\n\n## Format Rules:\n\n- File prefix: test_<module>.py\n\n- Function name: test_BE_<MODULE>_<NNN>_<description>\n\n- Docstring first line: BE-<MODULE>-<NNN>: <Case Title>\n\n- 1:1 mapping: each functional case → one pytest function\n\n\n\n## Implementation Rules:\n\n- Use assert statements, not unittest assertions\n\n- Use @pytest.mark.parametrize for boundary cases when the case defines edge values\n\n- Use markers: @pytest.mark.positive, @pytest.mark.negative, @pytest.mark.boundary\n\n\n\n## Test Data Preparation Rules (MUST follow):\n\n\n\n### When Setup is Needed\n\nSetup phase is REQUIRED only when test cases need pre-existing data:\n\n- Query/Read APIs: need data to exist before querying\n\n- Update/Delete APIs: need data to exist before modifying\n\n- State transition tests: need data in specific state\n\n\n\nSetup phase is NOT needed for:\n\n- Create APIs: testing the creation itself\n\n- Validation tests: testing input validation with invalid data\n\n\n\n### Data Setup Strategy\n\nWhen setup is needed:\n\n1. Prefer function-scoped fixtures for isolation; use module/session scope only when cases explicitly share immutable fixtures\n\n2. Prefer API-based setup from the upstream analyze-inputs-pi API list and reviewed cases\n\n3. If a required helper/factory is missing, create NEW files only under testcase/**/helpers/** or testcase/**/factories/**\n\n\n\n### Data Construction Priority\n\n1. API-first: construct data via documented APIs from analyze-inputs-pi / reviewed cases\n\n2. Reuse existing conftest fixtures when present (read-only)\n\n3. Direct DB writes are LAST RESORT and only if conftest already exposes a safe test DB fixture with rollback/isolation\n\n4. If neither API nor safe DB fixture exists, skip the case with an explicit gap note — do NOT invent production DB credentials or write live data\n\n\n\n### API Data Construction\n\n- Prefer the analyze-inputs-pi API Endpoints section and reviewed cases for method/path/fields\n\n- Chain API calls only when cases document multi-step preconditions\n\n- Store created resource IDs in fixtures for reuse\n\n- Do NOT broadly search host route/controller trees for secrets, .env, private keys, or production configs\n\n- Read host API definitions only when needed to resolve a field name already referenced by reviewed cases; stay out of credential/config paths\n\n\n\n### Database Data Construction (restricted)\n\n- Allowed only via existing conftest test-DB fixtures with transaction rollback or equivalent isolation\n\n- Never hardcode connection strings, passwords, tokens, or cloud credentials\n\n- Never target production/shared non-test databases\n\n- If isolation is unclear, report the gap instead of writing DB rows\n\n\n\n## Assertion Rules (MUST follow):\n\n\n\n### Positive Path\n\nMUST assert ALL of the following:\n\n1. HTTP status code: as defined in API spec (e.g. 200, 201)\n\n2. Response structure: key fields exist in response body\n\n3. Specific values: each field equals expected value from test case\n\n4. Data type: each field is correct type\n\n\n\n### Negative Path\n\nMUST assert ALL of the following:\n\n1. HTTP status code: as defined in API spec (e.g. 400, 404, 500)\n\n2. Error code field: field name from API spec (e.g. code, error_code, errcode, ret)\n\n3. Error message field: field name from API spec (e.g. message, msg, errmsg, error)\n\n\n\n### Field Name Resolution\n\nField names MUST come from the upstream analyze-inputs-pi output (API Endpoints section) or reviewed cases, NOT guessed. For example:\n\n- If API spec defines {\"ret\": 0, \"msg\": \"success\"}, assert response.json()['ret'] and response.json()['msg']\n\n- If API spec defines {\"code\": 4001, \"message\": \"error\"}, assert response.json()['code'] and response.json()['message']\n\n\n\n## Conditional Implementation (include ONLY if test cases exist):\n\n- Authentication tests: implement ONLY if testcase/md/ contains auth-related cases\n\n- Timeout tests: implement ONLY if testcase/md/ contains timeout-related cases\n\n- Boundary tests: implement ONLY when cases define value ranges, length limits, or format constraints\n\n- Use @pytest.mark.auth for auth tests, @pytest.mark.timeout for timeout tests\n\n- If no such cases exist, do NOT add these tests\n\n\n\n## Constraints:\n\n- Only create NEW files under writeSet: testcase/**/test_*.py, testcase/**/helpers/**, testcase/**/factories/**\n\n- Do NOT modify existing framework files (conftest.py, pytest.ini, pyproject.toml, setup.cfg, __init__.py)\n\n- If a test filename exists, add suffix: test_order.py → test_order_01.py\n\n- Do NOT re-read source documents — use reviewed cases under testcase/md/ and upstream analyze-inputs-pi output only\n\n- Read existing conftest.py/pytest.ini to understand conventions, but do NOT modify them\n\n- Do NOT execute pytest/python -m pytest or npm test in this node; the single execution is owned by the dedicated shell node. Local smoke runs create __pycache__/.pytest_cache and are unnecessary here."
     },
     {
       "id": "review-generated-backend-pytest-pi",
@@ -395,7 +395,7 @@
       "subtask_prompt": "Run pytest for the backend test suite; write JUnit + pytestExitCode evidence only under the current HARNESS_DAG_RUN_DIR/reports/.",
       "shell": {
         "commands": [
-          "test -n \"${HARNESS_DAG_RUN_DIR:-}\" || { echo \"missing HARNESS_DAG_RUN_DIR for backend pytest preflight\" >&2; exit 2; }; CONTRACT=\"${HARNESS_DAG_RUN_DIR}/contracts/backend-test-execution.json\"; test -f \"${CONTRACT}\" || { echo \"missing backend-test execution contract: ${CONTRACT}\" >&2; exit 2; }; node -e 'const fs=require(\"fs\");const path=require(\"path\");const contractPath=process.argv[1];const contract=JSON.parse(fs.readFileSync(contractPath,\"utf8\"));const expected=\"testcase\";const errors=[];if(contract.framework!==\"pytest\") errors.push(\"framework must be pytest\");const testRoot=String(contract.testRoot||\"\");if(!testRoot||testRoot.includes(\"..\")||path.isAbsolute(testRoot)) errors.push(\"unsafe testRoot\");if(testRoot.replace(/\\/+$/,\"\")!==expected.replace(/\\/+$/,\"\")) errors.push(\"testRoot mismatch vs frozen command: \"+testRoot+\" !== \"+expected);const rootAbs=path.resolve(process.cwd(),testRoot);if(!fs.existsSync(rootAbs)) errors.push(\"testRoot does not exist: \"+testRoot);if(contract.targetMode===\"in-process\"&&!(Array.isArray(contract.existingFixtures)&&contract.existingFixtures.length)) errors.push(\"in-process requires existingFixtures\");for (const name of (contract.requiredEnvNames||[])) { if(!process.env[name]) errors.push(\"required env missing: \"+name); }if(contract.targetMode===\"external-running-service\"){ const n=contract.baseUrlEnvName; if(!n||!process.env[n]) errors.push(\"external base URL env missing: \"+String(n||\"<empty>\")); }if(contract.targetMode===\"managed-command\" && !(contract.managedCommand&&contract.managedCommand.sourceRef)) errors.push(\"managed-command requires sourceRef evidence\");if(errors.length){ console.error(errors.join(\"; \")); process.exit(2);} console.log(\"backend-test preflight ok: framework=pytest testRoot=\"+testRoot+\" targetMode=\"+contract.targetMode);' \"${CONTRACT}\"; REPORT=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test-initial-junit.xml\"; EXIT_FILE=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test-initial-pytest-exit.txt\"; mkdir -p \"$(dirname \"${REPORT}\")\"; PYTHONUTF8=1 PYTHONIOENCODING=utf-8 PYTHONDONTWRITEBYTECODE=1 python -m pytest testcase/ -v -p no:cacheprovider --junitxml=\"${REPORT}\"; STATUS=$?; printf \"%s\" \"${STATUS}\" > \"${EXIT_FILE}\"; printf \"JUnit report: %s\\n\" \"${REPORT}\"; printf \"pytestExitCode=%s\\n\" \"${STATUS}\"; if { [ \"${STATUS}\" -eq 0 ] || [ \"${STATUS}\" -eq 1 ]; } && [ -s \"${REPORT}\" ]; then exit 0; fi; exit \"${STATUS}\""
+          "test -n \"${HARNESS_DAG_RUN_DIR:-}\" || { echo \"missing HARNESS_DAG_RUN_DIR for backend pytest preflight\" >&2; exit 2; } && CONTRACT=\"${HARNESS_DAG_RUN_DIR}/contracts/backend-test-execution.json\" && test -f \"${CONTRACT}\" || { echo \"missing backend-test execution contract: ${CONTRACT}\" >&2; exit 2; } && node -e 'const fs=require(\"fs\");const path=require(\"path\");const contractPath=process.argv[1];const contract=JSON.parse(fs.readFileSync(contractPath,\"utf8\"));const expected=\"testcase\";const errors=[];if(contract.framework!==\"pytest\") errors.push(\"framework must be pytest\");const testRoot=String(contract.testRoot||\"\");if(!testRoot||testRoot.includes(\"..\")||path.isAbsolute(testRoot)) errors.push(\"unsafe testRoot\");if(testRoot.replace(/\\/+$/,\"\")!==expected.replace(/\\/+$/,\"\")) errors.push(\"testRoot mismatch vs frozen command: \"+testRoot+\" !== \"+expected);const rootAbs=path.resolve(process.cwd(),testRoot);if(!fs.existsSync(rootAbs)) errors.push(\"testRoot does not exist: \"+testRoot);if(contract.targetMode===\"in-process\"&&!(Array.isArray(contract.existingFixtures)&&contract.existingFixtures.length)) errors.push(\"in-process requires existingFixtures\");for (const name of (contract.requiredEnvNames||[])) { if(!process.env[name]) errors.push(\"required env missing: \"+name); }if(contract.targetMode===\"external-running-service\"){ const n=contract.baseUrlEnvName; if(!n||!process.env[n]) errors.push(\"external base URL env missing: \"+String(n||\"<empty>\")); }if(contract.targetMode===\"managed-command\" && !(contract.managedCommand&&contract.managedCommand.sourceRef)) errors.push(\"managed-command requires sourceRef evidence\");if(errors.length){ console.error(errors.join(\"; \")); process.exit(2);} console.log(\"backend-test preflight ok: framework=pytest testRoot=\"+testRoot+\" targetMode=\"+contract.targetMode);' \"${CONTRACT}\" && { REPORT=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test-initial-junit.xml\"; EXIT_FILE=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test-initial-pytest-exit.txt\"; mkdir -p \"$(dirname \"${REPORT}\")\"; PYTHONUTF8=1 PYTHONIOENCODING=utf-8 PYTHONDONTWRITEBYTECODE=1 python -m pytest testcase/ -v -p no:cacheprovider --junitxml=\"${REPORT}\"; STATUS=$?; printf \"%s\" \"${STATUS}\" > \"${EXIT_FILE}\"; printf \"JUnit report: %s\\n\" \"${REPORT}\"; printf \"pytestExitCode=%s\\n\" \"${STATUS}\"; if { [ \"${STATUS}\" -eq 0 ] || [ \"${STATUS}\" -eq 1 ]; } && [ -s \"${REPORT}\" ]; then exit 0; fi; exit \"${STATUS}\"; }"
         ],
         "envAllowlist": [],
         "verifyEvidence": {
@@ -404,7 +404,7 @@
           "commandSource": "inline",
           "commandCount": 1,
           "commandLabels": [
-            "test -n \"${HARNESS_DAG_RUN_DIR:-}\" || { echo \"missing HARNESS_DAG_RUN_DIR for backend pytest preflight\" >&2; exit 2; }; CONTRACT=\"${HARNESS_DAG_RUN_DIR}/contracts/backend-test-execution.json\"; test -f \"${CONTRACT}\" || { echo \"missing backend-test execution contract: ${CONTRACT}\" >&2; exit 2; }; node -e 'const fs=require(\"fs\");const path=require(\"path\");const contractPath=process.argv[1];const contract=JSON.parse(fs.readFileSync(contractPath,\"utf8\"));const expected=\"testcase\";const errors=[];if(contract.framework!==\"pytest\") errors.push(\"framework must be pytest\");const testRoot=String(contract.testRoot||\"\");if(!testRoot||testRoot.includes(\"..\")||path.isAbsolute(testRoot)) errors.push(\"unsafe testRoot\");if(testRoot.replace(/\\/+$/,\"\")!==expected.replace(/\\/+$/,\"\")) errors.push(\"testRoot mismatch vs frozen command: \"+testRoot+\" !== \"+expected);const rootAbs=path.resolve(process.cwd(),testRoot);if(!fs.existsSync(rootAbs)) errors.push(\"testRoot does not exist: \"+testRoot);if(contract.targetMode===\"in-process\"&&!(Array.isArray(contract.existingFixtures)&&contract.existingFixtures.length)) errors.push(\"in-process requires existingFixtures\");for (const name of (contract.requiredEnvNames||[])) { if(!process.env[name]) errors.push(\"required env missing: \"+name); }if(contract.targetMode===\"external-running-service\"){ const n=contract.baseUrlEnvName; if(!n||!process.env[n]) errors.push(\"external base URL env missing: \"+String(n||\"<empty>\")); }if(contract.targetMode===\"managed-command\" && !(contract.managedCommand&&contract.managedCommand.sourceRef)) errors.push(\"managed-command requires sourceRef evidence\");if(errors.length){ console.error(errors.join(\"; \")); process.exit(2);} console.log(\"backend-test preflight ok: framework=pytest testRoot=\"+testRoot+\" targetMode=\"+contract.targetMode);' \"${CONTRACT}\"; REPORT=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test-initial-junit.xml\"; EXIT_FILE=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test-initial-pytest-exit.txt\"; mkdir -p \"$(dirname \"${REPORT}\")\"; PYTHONUTF8=1 PYTHONIOENCODING=utf-8 PYTHONDONTWRITEBYTECODE=1 python -m pytest testcase/ -v -p no:cacheprovider --junitxml=\"${REPORT}\"; STATUS=$?; printf \"%s\" \"${STATUS}\" > \"${EXIT_FILE}\"; printf \"JUnit report: %s\\n\" \"${REPORT}\"; printf \"pytestExitCode=%s\\n\" \"${STATUS}\"; if { [ \"${STATUS}\" -eq 0 ] || [ \"${STATUS}\" -eq 1 ]; } && [ -s \"${REPORT}\" ]; then exit 0; fi; exit \"${STATUS}\""
+            "test -n \"${HARNESS_DAG_RUN_DIR:-}\" || { echo \"missing HARNESS_DAG_RUN_DIR for backend pytest preflight\" >&2; exit 2; } && CONTRACT=\"${HARNESS_DAG_RUN_DIR}/contracts/backend-test-execution.json\" && test -f \"${CONTRACT}\" || { echo \"missing backend-test execution contract: ${CONTRACT}\" >&2; exit 2; } && node -e 'const fs=require(\"fs\");const path=require(\"path\");const contractPath=process.argv[1];const contract=JSON.parse(fs.readFileSync(contractPath,\"utf8\"));const expected=\"testcase\";const errors=[];if(contract.framework!==\"pytest\") errors.push(\"framework must be pytest\");const testRoot=String(contract.testRoot||\"\");if(!testRoot||testRoot.includes(\"..\")||path.isAbsolute(testRoot)) errors.push(\"unsafe testRoot\");if(testRoot.replace(/\\/+$/,\"\")!==expected.replace(/\\/+$/,\"\")) errors.push(\"testRoot mismatch vs frozen command: \"+testRoot+\" !== \"+expected);const rootAbs=path.resolve(process.cwd(),testRoot);if(!fs.existsSync(rootAbs)) errors.push(\"testRoot does not exist: \"+testRoot);if(contract.targetMode===\"in-process\"&&!(Array.isArray(contract.existingFixtures)&&contract.existingFixtures.length)) errors.push(\"in-process requires existingFixtures\");for (const name of (contract.requiredEnvNames||[])) { if(!process.env[name]) errors.push(\"required env missing: \"+name); }if(contract.targetMode===\"external-running-service\"){ const n=contract.baseUrlEnvName; if(!n||!process.env[n]) errors.push(\"external base URL env missing: \"+String(n||\"<empty>\")); }if(contract.targetMode===\"managed-command\" && !(contract.managedCommand&&contract.managedCommand.sourceRef)) errors.push(\"managed-command requires sourceRef evidence\");if(errors.length){ console.error(errors.join(\"; \")); process.exit(2);} console.log(\"backend-test preflight ok: framework=pytest testRoot=\"+testRoot+\" targetMode=\"+contract.targetMode);' \"${CONTRACT}\" && { REPORT=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test-initial-junit.xml\"; EXIT_FILE=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test-initial-pytest-exit.txt\"; mkdir -p \"$(dirname \"${REPORT}\")\"; PYTHONUTF8=1 PYTHONIOENCODING=utf-8 PYTHONDONTWRITEBYTECODE=1 python -m pytest testcase/ -v -p no:cacheprovider --junitxml=\"${REPORT}\"; STATUS=$?; printf \"%s\" \"${STATUS}\" > \"${EXIT_FILE}\"; printf \"JUnit report: %s\\n\" \"${REPORT}\"; printf \"pytestExitCode=%s\\n\" \"${STATUS}\"; if { [ \"${STATUS}\" -eq 0 ] || [ \"${STATUS}\" -eq 1 ]; } && [ -s \"${REPORT}\" ]; then exit 0; fi; exit \"${STATUS}\"; }"
           ],
           "finalFullRequired": true
         },
@@ -496,13 +496,46 @@
         "artifacts/**"
       ],
       "outputContract": "Maturity rating in assistant output plus a report written under docs/test-reports/**.",
-      "subtask_prompt": "Read the complete JSON from direct upstream materialize-classification-and-result-context-shell and generate a test retrospective report.\n\nThat JSON contains result, manifest (including coverageSummary), and classification. Treat those fields as authoritative; do not rely on pointer/hash summaries.\n\n\n\n## Output Steps (do in order):\n\n1. First, output the maturity rating on the first line: Rating: A/B/C/D\n\n2. Then write the full report under docs/test-reports/\n\n\n\n## Stats authority (deterministic only):\n\n- Pass rate, failed/error/skipped counts, and failure list MUST come from contracts/backend-test-result.json only.\n\n- AC coverage ratio / case counts MUST come from contracts/backend-test-case-manifest.json coverageSummary (or gate-derived fields). Do NOT invent coverage %.\n\n- Use classify-backend-test-result-pi JSON as interpretive evidence only.\n\n- NEVER rewrite a failed result as passed. Outcome gate (not this report) is authoritative for task success.\n\n\n\n## Report Structure:\n\n1. Maturity Rating with rationale\n\n2. Test Coverage Summary (manifest coverageSummary + Result v1 pass rate)\n\n3. Review Findings and resolution status\n\n4. Failed Test Analysis (if any) + classification category\n\n5. Recommendations for improvement\n\n\n\n## Rating Criteria:\n\n- A: coverageSummary.acCoverageRatio=1 + 100% pytest pass + no Critical findings\n\n- B: acCoverageRatio≥0.8 + ≥90% pass + Low findings only\n\n- C: acCoverageRatio≥0.6 + ≥70% pass + no Critical findings\n\n- D: below C thresholds\n\n\n\n## Constraints:\n\n- Stay within writeSet: docs/test-reports/**\n\n- Do NOT re-read source documents — use upstream outputs only\n\n- Do not write root artifacts/**"
+      "subtask_prompt": "Read the complete JSON from direct upstream materialize-classification-and-result-context-shell and generate a test retrospective report.\n\nThat JSON contains result, manifest (including coverageSummary), and classification. Treat those fields as authoritative; do not rely on pointer/hash summaries.\n\n\n\n## Output Steps (do in order):\n\n1. First, output the maturity rating on the first line: Rating: A/B/C/D\n\n2. Then write the full report under docs/test-reports/\n\n\n\n## Stats authority (deterministic only):\n\n- Pass rate, failed/error/skipped counts, and failure list MUST come from contracts/backend-test-result.json only.\n\n- AC coverage ratio / case counts MUST come from contracts/backend-test-case-manifest.json coverageSummary (or gate-derived fields). Do NOT invent coverage %.\n\n- Automation coverage MUST use coverageSummary.generatedCount / coverageSummary.caseCount. If either field is missing, write unavailable; do not estimate.\n\n- Code coverage MUST come only from the validated contracts/code-coverage-v1.json artifact generated by coverage.py/pytest-cov or JaCoCo. Show line, branch, function/method, covered, total, ratio, threshold, status, source scope, requirement IDs, tool, commit, and artifact hash.\n\n- Stability MUST come from independent Stability Evidence: use successfulRuns / recordedRuns, same suite/version, and require n≥5; a single run is unavailable.\n\n- Use classify-backend-test-result-pi JSON as interpretive evidence only.\n\n- NEVER rewrite a failed result as passed. Outcome gate (not this report) is authoritative for task success.\n\n\n\n## Report Structure:\n\n1. Maturity Rating with rationale\n\n2. Test Coverage Summary (Result v1 pass rate, AC coverage, automation coverage, code coverage, and stability evidence)\n\n3. Failed Test Analysis (failure/error details, category, confidence, evidence, and owner direction)\n\n4. Defects (local Bug ledger in the same report directory; unavailable when absent)\n\n5. Risks (Critical/High/Medium/Low, impact, controls, residual risk, treatment; Critical risks block L-5, High risks do not automatically block)\n\n6. Regression Recommendations (immediate, related, periodic, deferred; every item links to failure/risk/AC/case IDs)\n\n7. L-5 conclusion with blocking items\n\n\n\n## Rating Criteria:\n\n- L-5 ready requires pass rate=100%, AC coverage=100%, automation coverage≥90%, stability≥95% with n≥5, line coverage≥80%, branch coverage≥70%, skipped=0, and no blocking Critical risk.\n\n- Any required metric fail or unavailable means L-5 not-ready. Function/method coverage is displayed but not a gate. Preserve the existing A/B/C/D single-run rating separately.\n\n\n\n## Constraints:\n\n- Stay within writeSet: docs/test-reports/**\n\n- Do NOT re-read source documents — use upstream outputs only\n\n- Do not write root artifacts/**"
     },
     {
-      "id": "backend-test-outcome-gate-shell",
+      "id": "l5-metrics-pi",
       "depends_on": [
         "test-retrospect-pi"
       ],
+      "role": "reviewer",
+      "executor": "pi",
+      "complexity": "MED",
+      "writePolicy": "read-only",
+      "allowedPaths": [
+        "testcase/**",
+        "docs/test-reports/**"
+      ],
+      "forbiddenPaths": [
+        ".harness/**",
+        ".harness/dag-runs/**",
+        "artifacts/**"
+      ],
+      "outputContract": "Exactly one JSON object with status=ready|not-ready, metrics, and blockingItems; no file writes.",
+      "subtask_prompt": "You are the independent L-5 metrics node at the end of the existing backend-test DAG.\n\nThe direct upstream test-retrospect-pi output is the primary report to assess. Read it together with the run-owned Result v1, Case Manifest v1, Code Coverage v1, and Stability Evidence artifacts when present.\n\nDo not create a new DAG, rewrite the retrospective report, change test outcome, or modify any repository file.\n\nReturn exactly one JSON object and no surrounding prose.\n\nRequired shape: {\"status\":\"ready\"|\"not-ready\",\"metrics\":{\"passRate\":metric,\"acCoverage\":metric,\"automationCoverage\":metric,\"stability\":metric,\"lineCoverage\":metric,\"branchCoverage\":metric,\"skipped\":metric,\"criticalRisks\":metric},\"blockingItems\":[string]}.\n\nEach metric must contain numerator, denominator, ratio, threshold, status=pass|fail|unavailable, and reason (null only when passed).\n\nUse only explicit evidence. Missing or invalid required evidence is unavailable, never zero or an estimate.\n\nL-5 ready requires pass rate=100%, AC coverage=100%, automation coverage>=90%, stability>=95% with n>=5, line coverage>=80%, branch coverage>=70%, skipped=0, and zero blocking Critical risks.\n\nFunction/method coverage is display-only and does not gate L-5. Preserve the distinction between L-5 maturity and the Result v1 outcome gate.",
+      "retryPolicy": {
+        "maxAttempts": 3,
+        "backoff": "exponential",
+        "initialDelayMs": 2000,
+        "maxDelayMs": 30000,
+        "retryCategories": [
+          "timeout",
+          "network",
+          "rate-limit",
+          "unavailable"
+        ]
+      }
+    },
+    {
+      "id": "backend-test-outcome-gate-shell",
+      "depends_on": [
+        "l5-metrics-pi"
+      ],
       "role": "verifier",
       "executor": "shell",
       "complexity": "LOW",

package/docs/templates/backend-test-dag.retrospect.prompt.md

@@ -46,7 +46,9 @@ This node runs on **both pass and assertion-fail** paths (after parse + classify
    Use `coverageSummary.acCoverageRatio`, `coveredAcCount`, `explicitAcCount`, case counts only from this artifact.
 3. **Classification** — `classify-backend-test-result-pi` JSON (`category`, `confidence`, `evidence`). Interpretive only; does not override outcome.
 4. **Review report** — `review-backend-cases-pi` output (VERDICT, findings, coverage assessment).
-5. Optional secondary: execute stdout markers / JUnit path (do not re-parse logs for counts when Result v1 exists).
+5. **Code Coverage v1** — optional validated `contracts/code-coverage-v1.json`, generated by coverage.py/pytest-cov or JaCoCo. Never infer it from Result v1.
+6. **Stability Evidence** — optional independent contract for repeated runs of the same suite and version.
+7. Optional secondary: execute stdout markers / JUnit path (do not re-parse logs for counts when Result v1 exists).
 
 Do NOT re-read source documents. Use upstream outputs only.
 
@@ -54,6 +56,9 @@ Do NOT re-read source documents. Use upstream outputs only.
 
 - Pass rate = `passed / (passed + failed + error)` when denominator > 0 (skipped excluded from denominator unless Result documents otherwise) — **Result v1 only**.
 - AC coverage = `coverageSummary.acCoverageRatio` from Case Manifest v1 only (do **not** recompute or invent percentages).
+- Automation coverage = `coverageSummary.generatedCount / coverageSummary.caseCount`; if either field is missing, output `unavailable`.
+- Code coverage = Code Coverage v1 only. Display line (gate ≥80%), branch (gate ≥70%), and function/method (display only), each with covered, total, ratio, status, reason, source scope, requirement IDs, tool/version, commit and artifact SHA-256. Missing artifacts or line/branch metrics are `unavailable` and block L-5.
+- Stability = Stability Evidence `successfulRuns / recordedRuns`, same suite and version, minimum `n≥5`; one run is `unavailable` and cannot prove `FlakyTest`.
 - Failed case table rows must match `failures[]` from Result v1.
 - If Result v1 `outcome` is not `passed`, the retrospective **must not** claim overall success.
 
@@ -74,6 +79,7 @@ Do NOT re-read source documents. Use upstream outputs only.
 - If Result v1 shows >30% failed+error among executed tests, cap at **D** regardless of coverage.
 - Skipped tests count as "not covered" for pass rate but not as failures.
 - Collection/command/report errors → cap at **D** and record classification (not ProductBug by default).
+- The downstream `l5-metrics-pi` node owns the separate L-5 conclusion. This retrospective must provide the authoritative evidence and risks, but must not replace the downstream L-5 JSON conclusion.
 
 ### Report Structure
 
@@ -95,6 +101,15 @@ Write the report as a Markdown file named `backend-test-retrospect-<date>.md` un
 | Total acceptance criteria | N |
 | Covered by test cases | N (X%) |
 | Total functional test cases | N |
+| Automated cases / total cases | N / N (X%) or unavailable |
+| Code line coverage | N / N (X%), threshold ≥80%, status |
+| Code branch coverage | N / N (X%), threshold ≥70%, status |
+| Code function/method coverage | N / N (X%) or unavailable |
+| Stability | successfulRuns / recordedRuns (X%), n, or unavailable |
+
+Code coverage must include language, tool/version, requirement IDs, source scope, commit and artifact SHA-256.
+
+The downstream `l5-metrics-pi` node consumes this report and the run-owned contracts to calculate the independent L-5 conclusion.
 
 ## 2. Automation Results (from Result v1)
 
@@ -112,21 +127,35 @@ Write the report as a Markdown file named `backend-test-retrospect-<date>.md` un
 
 ### Failed Test Analysis
 
-| Test Case / Function | Message (truncated) | Classification |
-|----------------------|-------------------|----------------|
-| ... | ... | ... |
+| Test Case / Function | Kind | Classification | Confidence | Evidence | Owner direction |
+|----------------------|------|----------------|------------|----------|----------------|
+| ... | ... | ... | ... | ... | ... |
+
+## 3. Defects
+
+Use the local Bug ledger in the same directory as the report. Include defect ID, title, AC/case, severity, priority, status, reproduction, evidence, category, owner, fix version and regression status. If absent, write `缺陷登记：unavailable`.
+
+## 4. Risks
+
+| Risk ID | Level | Impact | Likelihood | Current control | Residual risk | Treatment |
+|---------|-------|--------|------------|-----------------|---------------|-----------|
+| ... | Critical/High/Medium/Low | ... | ... | ... | ... | ... |
+
+## 5. Regression Recommendations
+
+Every recommendation must reference a failure/risk/AC/case ID and include target suite, priority and verification command.
 
-## 3. Review Findings
+## 6. Review Findings
 
 | Severity | Finding | Status |
 |----------|---------|--------|
 | … | … | … |
 
-## 4. Maturity Rating Rationale
+## 7. Maturity Rating Rationale
 
 Explain which threshold was met or missed.
 
-## 5. Recommendations
+## 8. Recommendations
 
 - Actionable items for the next iteration.
 - Do not propose changing production code solely to greenwash tests.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tea-agent/loop-agent",
-  "version": "0.16.24",
+  "version": "0.16.25",
   "type": "module",
   "bin": {
     "loop-agent": "bin/loop-agent.js",

package/skills/loop-agent/references/command-reference.md

@@ -374,6 +374,7 @@ loop-agent plan complete <plan-id> --summary "<summary>"
 loop-agent plan check
 loop-agent handoff check [task-id]
 loop-agent handoff coverage <task-id> [--json|--markdown]
+loop-agent coverage report --language python|java --input <coverage.json|jacoco.xml> --requirement-id <AC-id> --source-scope <path[,path]> [--output <path>] [--json|--markdown]
 ```
 
 - `docs audit`：扫描文档腐化风险，如 active/completed 漂移、失效链接、host-gap closeout