@tea-agent/loop-agent 0.39.0-beta.6 → 0.39.0-beta.8

package/CHANGELOG.md

@@ -2,6 +2,16 @@
 
 ## [Unreleased]
 
+- 前端 design-review 拒绝纳入自动恢复（方向 A 姊妹实现）：`request_design_changes`（definite finding）不再让 writer-admission blocked 变成 terminal failed——runner 终态判定识别 committed design fact 后生成 recovery trigger（new-dag，从 plan 重启）+ 渲染 design findings PRD 草稿 + `deriveDagRerunFeedback` 增加 design typed-fact 通道（findings 注入下一轮 `<rerun_feedback>`），受同一 `frontendRecoveryQuota` 控制；无 design fact 的 blocked admission 仍保持 terminal failed。design-review 发现"AC 未被契约/测试锚定"这类真问题会在写代码前自动进入修正轮，而非一次失败即停。
+- 前端 DAG 两个闭环补齐（P0-1 / P2-4）：
+  - **P0-1 前端 recovery 配额可配置**：`task.json frontendRecovery.maxContinuations`（默认 1，可配 2-5）冻结进 DAG spec（`spec.frontendRecovery`），runner 的 `finalizeTerminalRunStatus` 4 处硬编码 `< 1` 改为按配额判定——verify 偶发失败导致 run 真失败的场景可放宽到 2-3 次自动恢复，不必人工介入。
+  - **P2-4 `dag follow-up` 命令**：`loop-agent dag follow-up <parent-run-id> [--task-id <id>] [--execute] [--profile <p>]`——读取 parent run 的 `contracts/frontend-review-findings-prd.md`，createTask + importPrd（taskKind=frontend-implementation + PRD 内容）生成下游修复任务，`--execute` 直接 advance 走前端 DAG。review findings 从"只落文件的草稿"变成"一步进入下一轮 DAG 的任务"，闭环补齐。
+- frontend-plan-pi 重试上限从 5 收紧到 3（`FRONTEND_PLAN_LADDER_RETRY_POLICY.maxAttempts`）：每次 attempt 都是完整跑一遍 plan（读上下文 + 提交 record_* ledger），5 次在坏情况下等于 5 倍 plan token 成本；3 次仍覆盖常见失败（invalid-output 格式滑动、read-burst、传输类），四档阶梯只部分可遍历即判 non-converging，减少单节点无限烧 token 风险。
+
+- 前端 review `request_review_changes` 不再被静默当作成功（方向 A）：`frontend-review-pi` 提交 typed `request_review_changes` 时，run 终态判定为「未通过」（`partial_failed` + `terminalReason=review-request-changes`，即使全部节点 FINISHED 也不显示成功），committed findings 自动渲染为 run-owned 下游任务 PRD 草稿 `contracts/frontend-review-findings-prd.md`（含 issueCategory/evidenceRefs/findings/restartPhase 指引），并生成 recovery trigger（issueCategory→failureOwner 映射，new-dag）。`deriveDagRerunFeedback` 新增 typed-fact 通道：无文本 verdict、无 convergence 的 frontend 场景也能把 committed `request_review_changes` findings 注入下一轮 `<rerun_feedback>`，问题不再丢失、下一轮从 restartPhase 定点修复而非重复流程。
+- 前端 review findings PRD 草稿携带修复范围路由信号（方向 A 补充）：`deriveFrontendReviewFixScope` 从 committed findings 确定性推导建议 shape（单文件无远程 API→micro、同目录集中多文件→small、跨目录/API 信号→standard）与建议 complexity、目标文件、建议 allowedPaths；PRD 标题改为「修复 review 发现（<shape>）：<目标文件>」，正文新增「修复范围（供下一轮任务生成路由）」段（含 small 信号词，如「单文件局部修复」「无远程接口」），下一轮任务以该 PRD 生成 DAG 时，`resolveFrontendTaskShape` 能把小修复路由到 micro=7/small=10 节点拓扑，而非默认 11 节点 standard 全流程。
+- 前端 shape 分类 API 否定词覆盖中文空格形式（冒烟暴露边界）：`无 API/网络调用`、`无 API` 等表述不再被误判为远程 API 信号（原 `\b(...)\b` 对 CJK 开头无词边界），`resolveFrontendTaskShape` 与 `deriveFrontendReviewFixScope` 的 hasApiSignal 判定同步修正——带「无 API/无接口」声明的单文件小修复正确路由 micro/small，而非误升级 standard。
+- 前端实现契约对 `decision=new` 的退化空 `specReference` 归一化兜底（冒烟暴露 plan invalid-output）：模型偶发把 new 组件输出成 `specReference:{path:"",section:"",line:null}`（空对象而非 prompt 要求的 null），原校验直接判 `invalid-output` 触发完整 plan 重试；`frontendImplementationContractSchema` preprocess 新增 `normalizeNewComponentSpecReference`——new 选择携带空 path 的退化 specReference 时按 null 意图归一化为缺省（非空 path 的 `specified` 命中原样保留，真实 new+specReference 仍拒绝），一次格式滑动不再烧掉整个 plan attempt。
 - 深度合入 origin/main（source e68dfbe1）：以 frontend-node typed-tools 拓扑为基底移植 main 硬化——canonical artifact 消费、fail-closed 无验证 marker、风险分级细化（DEPENDENCY_INSTALL_LANGUAGE）、`HARNESS_DAG_RERUN_PROMPT_OVERRIDE` prompt override、Pi SDK 运行时依赖 0.83.0 与 `engines node>=22.19.0`、next-release scripts 入包；废弃节点（verify-assess/reverify/repair-pi/plan-revision/final-design-review/lint-baseline shell）能力确认被当前流程覆盖后裁剪对应实现（repair-gate 机制、lint-baseline shell 类型），plan retry 文案对齐 committed ledger；affected 392 + M2-M9 303 测试全绿，fast 3909/3910、integration 397/398（各 1 个 fn 既有失败）。
 
 ### 重点更新
@@ -10,7 +20,10 @@
 - Operator Chat 输入框两项交互增强：① **↑/↓ 历史输入召回**——每次发送的文本进入输入历史（连续重复折叠、上限 100 条），光标在首行按 ↑ 逐条向旧回溯、按 ↓ 向新前进，越过最新一条时恢复回溯前**未发送的草稿**（草稿不会被历史浏览冲掉）；多行文本中部的方向键仍是普通光标移动，IME 组词与 @文件/命令面板打开时不抢占。② **运行中排队下一轮指令**——当前回合运行中 Enter 不再被吞掉，消息作为「排队消息」绑定当前 Turn（服务端 `PUT deferred-turn` 从仅限 stopping 放开为 running/stopping，错误码 `TURN_NOT_STOPPING`→`TURN_NOT_ACTIVE`），当前回合结束（正常完成或停止）后自动发送；排队条提供「立即发送」（停止当前回复并立即发出）、「编辑」（移回输入框改写后再排）、「删除」三种操作，运行中输入框右侧提供排队发送按钮（与停止按钮并列）；排队条单行展示（状态 + 省略号预览 + 操作按钮一行），输入框默认一行高（自动增高上限 280px 不变）。
 - 向导「运行」面板结构化与预期管理（A2/C9）：新增实时运行进度块——节点完成计数与百分比进度条（含 progressbar 无障碍语义）、当前运行节点名称与已运行时长、失败节点与错误摘要，数据来自 `/api/dag-runs/:id` 每 5 秒轮询并在终态自动停止；`effectiveStatus=running-suspected-stall` 时显示橙色「疑似停滞」提示条（建议打开检视查看节点活动或到恢复页协作中止/诊断），把 20–40 分钟长跑的「日志噪音等待」变为有阶段感、可判断的等待。原始 SSE 事件日志默认折叠为「原始事件日志（最近 80 条）」，需要排查时再展开。
 - Console 前端三项体验优化（P0/P2）：① Recovery 页 DAG 紧凑检视侧栏（InspectSplitPanel）从一次性快照改为实时刷新——运行中每 5 秒自动拉取节点/事件并新增「进行中/已结束」刷新状态行，到达终态（finished/failed/partial_failed/superseded/abandoned）自动停止轮询，刷新轮不清空既有内容避免闪烁；② Chat 任务旅程卡失败态新增按归一化 failureCategory 的可操作「建议」行（validation/executor/write-guard/timeout/auth/human-required/human-rejected/shell-command/static-error/decision-envelope/unknown 各映射到具体下一步：从失败节点重跑、修正契约后重新生成、跳「模型与认证」页等），不再只报「原因分类为 X」；③ Recovery 页 interrupt 资格轮询退避：选中 run 已终态（含 interrupted）时从 4 秒降到 30 秒，运行中保持 4 秒。
-- Console「设置」页新增「模型配置（models.json）」区块：以弹框形式增/改/删 Pi 的模型条目，支持 6 个定义字段（id、name、contextWindow、maxTokens、input、reasoning）。新增时 Provider 用下拉选择、其余字段自动补默认值；编辑时 Provider 只读且仅在原位置就地替换，只改表单内字段、不覆盖配置里页面未展示的其它字段（如 cost/compat）；不读写 API key（凭据走 Pi CLI）。编辑已存在的模型不再被移到最后。
+- Console 对话页 Models 面板的模型管理增强：以弹框形式增/改/删 Pi 的模型条目，支持 6 个定义字段（id、name、contextWindow、maxTokens、input、reasoning）。新增时 Provider 用下拉选择、其余字段自动补默认值；编辑时 Provider 只读且仅在原位置就地替换，只改表单内字段、不覆盖配置里页面未展示的其它字段（如 cost/compat）；不读写 API key（凭据走 Pi CLI）。编辑已存在的模型不再被移到最后。（该能力仅在对话页提供，设置页不再重复入口。）
+- 修复 `markdown-traceability` pipeline 未将冻结 `backendLayout` 传给 `validateBackendMarkdownTraceability`，自定义 layout 下不再回落默认 `testcase/md` ENOENT；新增回归用例以非默认 nested layout（`testRoot=testcase/elb/remote`、`markdownRel=md`）执行真实 shell pipeline，traceability 从自定义 Markdown 目录读取并 PASS，默认 layout 行为不变。（验证：`npm run typecheck`、`npx vitest run test/backend-test-markdown-workflow.test.ts test/backend-test-layout.test.ts`、`npm run build`、`git diff --check`。）
+- backend-test 快速补强（backend-test-fast-failclosed-attribution）：两处 fail-open 缺口已 fail-closed。① 当前轮次 Markdown 作用域严格依赖唯一有效 `## Module Index`——README 缺失 / 不可读 / `## Module Index` 重复（或缺标题）/ 唯一但空或不可解析任一状态，`markdownFiles` 与 coverage `markdownModuleFiles` 均返回空作用域而非回退全目录扫描，历史 `.md` 不再渗入 Case/coverage/partition facts，`resolveBackendTestManifestModules` 新增可区分 `manifestStatus`（valid/missing/unreadable/duplicate/empty-unparsable）与 `moduleIndexHeadingCount`，`validateBackendMarkdownCases` 与 `analyzeBackendTestCaseCoverage` 为非法状态各推 FAIL finding，默认与自定义 `backendTest` 布局一致。② collection 分类器不再凭 `__NNN_*` 裸 import 名称单独判 REPAIRABLE：inventory 构建时预计算每个 mapped script 的裸本地 helper import 证据（`scriptBareImports`），只有「存在同名 generated-local helper asset 且 mapped script 源码确实 import 该裸模块」才判 REPAIRABLE 并给精确 repairPaths；无 helper asset / mapped script 无对应 import / 无法精确归因一律 `BLOCKED`（`missing-generated-local-helper-without-evidence`。真第三方模块缺失保持 BLOCKED，不通过 PYTHONPATH/sys.path/conftest/ImportError fallback 绕行。（验证：`npm run typecheck`、backend-test 四聚焦 vitest、`npm run build`、`git diff --check`。）
+- backend-test 后续修复（backend-test-fast-manifest-import-fix）：Markdown 用例校验与 coverage 分析改为按 README `## Module Index` 清单限定本轮有效模块资产——未声明旧 `.md`（如 legacy.md）不再进入 Case/coverage/partition 统计，报告改为显式非静默 unmanifested advisory；“清单声明但文件缺失” fail-closed 明确失败，默认与自定义 `backendTest` 布局统一生效。generated pytest 裸本地 helper import（`from __551_manager_helpers import ...`）在 writer completeness gate 判为 recoverable 并给出精确 mapped 脚本 target path；collection 分类器对可归因到 mapped 资产的裸本地 helper `ModuleNotFoundError` 判 REPAIRABLE 并提供精确 repairPaths，真正第三方依赖缺失仍保持 BLOCKED。不放宽 self-contained、writeSet、forbiddenPaths、skip/xfail、断言与单次业务执行约束（验证：`npm run typecheck`、backend-test 聚焦 vitest、`npm run build`、`git diff --check`）。
 - 前端风险分级细分 manifest 触及语义：`allowedPaths` 含 `package.json`/lockfile 或需求文本提到 package.json 不再单独触发 `new-dependency` high-risk（改一行 script、调构建参数的任务不再被顶到强制全门禁并误标高风险），只有任务文本同时出现安装语言（npm install / yarn add / pnpm add / 新增依赖等）才升级；仅路径触及时记 `new-dependency:manifest-path-without-install-language` 拒绝信号，审计可溯。
 - 前端验证 fallback 生成期诚实化：真实项目无可读取的 `package.json` scripts 且未探测到本地 tsc 时，不再注入必然失败的 `npm run typecheck` / `npm run build` / `npm test`（纯静态 / vanilla JS 站点原会在 verify 阶段假失败），改为执行显式 no-op 标记命令（`No frontend verification command configured`，进入冻结命令集可被 contract 引用，trace 如实记录 not-run），并写生成期 advisory 提示用 `--verify` 或执行约束显式声明验证命令后重新生成 DAG。无 repoRoot 的单测 fixture 保留历史 generic fallback。**标记不构成验证证据（fail-closed）**：verification trace 将绑定标记的 target 判为失败、只含标记的 static 证据判为 unavailable，repair 分类归为 non-repairable `contract`，verify 节点以 `frontend verification unavailable` 硬失败阻断 review/closeout——无真实验证命令的 run 无法走完绿灯链。
 - frontend-test `passed` 回执链改按 dispatch 序号判序（B-HASH-01）：`summarizePlaywrightCliReceipts` 先按 `sequence` 排序再判 open→find→cleanup 连续链；并行 `find`/`screenshot` 按完成时间落盘导致的乱序不再误杀执行已通过的 case（Wave 1 实测 4 条 passed 被改判 `browser-command-evidence-missing`）。真 gap / 重复序号仍 fail-closed。

package/dist/build-stamp.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "version": "0.39.0-beta.6",
-  "gitSha": "740f411873839c25833d8d41d0ee74d0285f7082",
-  "builtAt": "2026-08-23T14:01:39.565Z"
+  "version": "0.39.0-beta.8",
+  "gitSha": "b698721e82e0ff98c85484a5b2864d9b28e968f8",
+  "builtAt": "2026-08-24T06:32:44.509Z"
 }

package/dist/cli/command-definitions.js

@@ -35,6 +35,7 @@ import { runDagReconcileTasks } from "../commands/dag-reconcile-tasks.js";
 import { runDagReconcileRun } from "../commands/dag-reconcile-run.js";
 import { runDagRequestInterrupt } from "../commands/dag-request-interrupt.js";
 import { runDagRerunTask } from "../commands/dag-rerun-task.js";
+import { runDagFollowUp } from "../commands/dag-follow-up.js";
 import { runDagRerun } from "../commands/dag-rerun.js";
 import { runDagResume } from "../commands/dag-resume.js";
 import { runDagDecisionInspect, runDagDecisionValidate, } from "../workflows/dag/decision-envelope.js";
@@ -135,6 +136,7 @@ const DAG_SUBCOMMANDS = [
     "request-interrupt",
     "rerun",
     "rerun-task",
+    "follow-up",
     "reconcile-tasks",
     "final-verification",
     "decision",
@@ -577,6 +579,11 @@ export const COMMAND_DEFINITIONS = [
                 await runDagRerunTask(repoRoot, rerunTaskArgs);
                 return;
             }
+            if (subcommand === "follow-up") {
+                const followUpArgs = rest.filter((arg) => Boolean(arg));
+                await runDagFollowUp(repoRoot, followUpArgs);
+                return;
+            }
             if (subcommand === "reconcile-tasks") {
                 const reconcileArgs = rest.filter((arg) => Boolean(arg));
                 await runDagReconcileTasks(repoRoot, reconcileArgs);

package/dist/cli/program.js

@@ -13,6 +13,7 @@ import { runDagReconcileTasks } from "../commands/dag-reconcile-tasks.js";
 import { runDagReconcileRun } from "../commands/dag-reconcile-run.js";
 import { runDagRequestInterrupt } from "../commands/dag-request-interrupt.js";
 import { runDagRerunTask } from "../commands/dag-rerun-task.js";
+import { runDagFollowUp } from "../commands/dag-follow-up.js";
 import { runDagRerun } from "../commands/dag-rerun.js";
 import { runDagReject } from "../commands/dag-reject.js";
 import { runDagCloseoutDraft, runDagReport } from "../commands/dag-report.js";
@@ -352,6 +353,9 @@ async function runDagAction(repoRoot, subcommand, rest) {
         case "rerun-task":
             await runDagRerunTask(repoRoot, args);
             return;
+        case "follow-up":
+            await runDagFollowUp(repoRoot, args);
+            return;
         case "reconcile-tasks":
             await runDagReconcileTasks(repoRoot, args);
             return;
@@ -511,6 +515,7 @@ function addDagCommand(program, defaultRepoRoot) {
         "request-interrupt",
         "rerun",
         "rerun-task",
+        "follow-up",
         "reconcile-tasks",
         "final-verification",
     ], defaultRepoRoot);

package/dist/commands/client-recovery.js

@@ -1356,12 +1356,15 @@ export async function runClientRecovery(input) {
     }
     const plugin = await installProjectOpenCodePlugin({
         repoRoot: input.repoRoot,
+        onlyIfMissing: true,
     });
     const overflowPlugin = await installProjectOpenCodeOverflowCompactPlugin({
         repoRoot: input.repoRoot,
+        onlyIfMissing: true,
     });
     const piExtension = await installProjectPiContextOverflowExtension({
         repoRoot: input.repoRoot,
+        onlyIfMissing: true,
     });
     const pi = await applyProjectPiSettingsMerge({ repoRoot: input.repoRoot });
     if (mode !== "user") {

package/dist/commands/dag-follow-up.js

@@ -0,0 +1,138 @@
+import { mkdir } from "node:fs/promises";
+import path from "node:path";
+import { FRONTEND_REVIEW_FINDINGS_PRD_REL, readFrontendReviewFindingsPrd, } from "../workflows/dag/frontend-review-findings.js";
+import { locateDagRun } from "../workflows/dag/lifecycle.js";
+import { createTask, getTaskPaths } from "../task/runtime.js";
+import { importPrdDocument } from "../task/source-references.js";
+function parseFlagValue(rawArgs, flag) {
+    const index = rawArgs.indexOf(flag);
+    if (index < 0 || index + 1 >= rawArgs.length)
+        return undefined;
+    return rawArgs[index + 1];
+}
+export function parseDagFollowUpArgs(rawArgs) {
+    const positional = rawArgs.filter((arg) => !arg.startsWith("-"));
+    const parentRunId = positional[0];
+    if (!parentRunId) {
+        throw new Error("usage: dag follow-up <parent-run-id> [--task-id <id>] [--execute] [--profile <profile>]");
+    }
+    return {
+        parentRunId,
+        taskId: parseFlagValue(rawArgs, "--task-id"),
+        execute: rawArgs.includes("--execute"),
+        profile: parseFlagValue(rawArgs, "--profile"),
+    };
+}
+export function deriveFollowUpTaskId(parentRunId) {
+    // Deterministic, valid task id derived from the parent run id.
+    return `${parentRunId}-followup`;
+}
+/** CLI entry: parse raw args and run the follow-up flow. */
+export async function runDagFollowUp(repoRoot, rawArgs) {
+    const parsed = parseDagFollowUpArgs(rawArgs);
+    const result = await runDagFollowUpInternal(repoRoot, parsed.parentRunId, {
+        taskId: parsed.taskId,
+        execute: parsed.execute,
+        profile: parsed.profile,
+    });
+    console.log(JSON.stringify(result, null, 2));
+    if (!result.ok) {
+        process.exitCode = result.mode === "blocked" ? 2 : 1;
+    }
+}
+export async function runDagFollowUpInternal(repoRoot, parentRunId, options = {}) {
+    const located = await locateDagRun(repoRoot, parentRunId);
+    if (!located) {
+        return {
+            ok: false,
+            mode: "invalid",
+            reason: `dag run not found: ${parentRunId}`,
+        };
+    }
+    const prd = await readFrontendReviewFindingsPrd(located.runDir);
+    if (!prd) {
+        return {
+            ok: false,
+            mode: "invalid",
+            reason: `no frontend review findings PRD found in run ${parentRunId} (${FRONTEND_REVIEW_FINDINGS_PRD_REL}); the review must have committed request_review_changes`,
+        };
+    }
+    const taskId = options.taskId ?? deriveFollowUpTaskId(parentRunId);
+    try {
+        await createTask(repoRoot, taskId, `修复 review 发现（parent ${parentRunId}）`);
+    }
+    catch (error) {
+        return {
+            ok: false,
+            mode: "blocked",
+            reason: `failed to create task ${taskId}: ${error instanceof Error ? error.message : String(error)}`,
+        };
+    }
+    // Materialize the PRD draft into the task's source directory so the task
+    // lifecycle can import it as its requirement.
+    const prdMaterialized = path.join(getTaskPaths(repoRoot, taskId).sourceDir, "review-findings-prd.md");
+    try {
+        await mkdir(path.dirname(prdMaterialized), { recursive: true });
+        await importPrdDocument({
+            repoRoot,
+            taskId,
+            filePath: path.join(located.runDir, FRONTEND_REVIEW_FINDINGS_PRD_REL),
+            name: "review-findings-prd",
+        });
+    }
+    catch (error) {
+        return {
+            ok: false,
+            mode: "blocked",
+            reason: `failed to import PRD into task ${taskId}: ${error instanceof Error ? error.message : String(error)}`,
+        };
+    }
+    if (!options.execute) {
+        return {
+            ok: true,
+            mode: "created",
+            taskId,
+            prdPath: prdMaterialized,
+            next: {
+                kind: "advance",
+                command: `loop-agent task advance ${taskId} --task-kind frontend-implementation --json`,
+            },
+        };
+    }
+    // Execute: advance through the frontend DAG.
+    const { advanceTaskLifecycle } = await import("../application/task-lifecycle/advance.js");
+    const profile = options.profile === "auto" ||
+        options.profile === "minimal" ||
+        options.profile === "standard" ||
+        options.profile === "reviewed" ||
+        options.profile === "supervised"
+        ? options.profile
+        : undefined;
+    const result = await advanceTaskLifecycle({
+        repoRoot,
+        taskId,
+        taskKind: "frontend-implementation",
+        taskKindExplicit: true,
+        ...(profile ? { profile, profileExplicit: true } : {}),
+        observer: undefined,
+    });
+    const ok = result.lifecycleState === "run-succeeded" ||
+        result.lifecycleState === "awaiting-write-set-approval";
+    return {
+        ok,
+        mode: ok ? "created" : "blocked",
+        taskId,
+        prdPath: prdMaterialized,
+        reason: ok
+            ? undefined
+            : `advance lifecycleState: ${result.lifecycleState}${result.blockers.length > 0
+                ? `; blockers: ${result.blockers.map((b) => b.code).join(", ")}`
+                : ""}`,
+        next: ok
+            ? undefined
+            : {
+                kind: "advance",
+                command: `loop-agent task advance ${taskId} --task-kind frontend-implementation --json`,
+            },
+    };
+}

package/dist/commands/task-advance.js

@@ -355,6 +355,25 @@ export async function runTaskAdvance(repoRoot, args) {
                 intervalMs: options.progressIntervalMs,
             });
         }
+        // Idempotent client-recovery surface install before any DAG run: the Pi
+        // context-overflow extension / OpenCode plugins / project .pi settings
+        // are normally installed by `loop-agent init`, but an upgraded or
+        // non-init-created project may lack them. Installing here (missing-only)
+        // ensures the overflow compact+retry recovery path is always present,
+        // independent of how the project was created. Best-effort: a failure to
+        // install never blocks the run.
+        if (options.approveGate && !options.dryRun) {
+            try {
+                const { runClientRecovery } = await import("./client-recovery.js");
+                // mode "project" installs only project-owned surfaces
+                // (.pi/extensions + .opencode/plugins + .pi/settings.json),
+                // never the user home; installs are missing-only.
+                await runClientRecovery({ repoRoot, mode: "project" });
+            }
+            catch {
+                // best-effort; do not fail the run over a recovery-surface install
+            }
+        }
         const result = await advanceTaskLifecycle(toUseCaseInput(repoRoot, taskId, options, progress?.observer));
         const outcome = mapOutcome(result);
         const gateStop = result.lifecycleState === "awaiting-write-set-approval" &&

package/dist/executors/dag-pi-executor.js

@@ -26,6 +26,15 @@ import { redactSecrets, truncateUtf8Preview } from "../shared/preview.js";
  * recoverable partial-write-set (incomplete-write-set) upgrade.
  */
 export const WRITER_THINKING_EXHAUSTED_CATEGORY = "writer-thinking-exhausted";
+/**
+ * The writer session burned an excessive token budget (a read-edit-test loop
+ * that never converged) and still failed. Distinct from empty-output so the
+ * report shows the real cause and recovery recommends a fresh compacted run.
+ * Not auto-retried by default; operators may rerun after a model switch.
+ */
+export const WRITER_BUDGET_EXHAUSTED_CATEGORY = "writer-budget-exhausted";
+/** Token ceiling for a single writer node before it is judged budget-exhausted. */
+export const WRITER_TOKEN_BUDGET = 2_000_000;
 function readWriterThinkingExhaustionEvidence(result) {
     const wider = result;
     return {
@@ -2681,6 +2690,12 @@ export async function executeDagPiNode(input, meta, piStepFn = executePiStep, wr
         changeManifestChangedFiles !== undefined &&
         changeManifestChangedFiles.length === 0 &&
         writeToolCallCount === 0;
+    // Budget-exhausted: the provider session consumed an extreme amount of
+    // tokens (e.g. an unresolved read-edit-test loop) and still failed. Only
+    // applies on a non-ok writer result; a successful write is never re-labeled.
+    const writerBudgetExhausted = !mapped.ok &&
+        typeof mapped.tokensUsed === "number" &&
+        mapped.tokensUsed > WRITER_TOKEN_BUDGET;
     const targetCleanTransport = !mapped.ok &&
         isTargetTemplateTransientRetryNode(input.task) &&
         rawFailureCategory !== undefined &&
@@ -2724,17 +2739,35 @@ export async function executeDagPiNode(input, meta, piStepFn = executePiStep, wr
                         mapped.failureCategory === "invalid-output" ||
                         mapped.failureCategory === WRITER_EMPTY_DIFF_RETRY_CATEGORY)
                     ? INCOMPLETE_WRITE_SET_RETRY_CATEGORY
-                    : // writer-thinking-exhausted: a length-stopped thinking-only attempt with
-                        // zero write tool calls and zero attributed diff is terminal and
-                        // non-retryable; recommend a model switch + fresh run. Only applies on
-                        // the empty-output base category so provider/transport failures keep
-                        // their original category, and only when the completeness gate did not
-                        // upgrade to incomplete-write-set above.
-                        writerThinkingExhausted
-                            ? WRITER_THINKING_EXHAUSTED_CATEGORY
-                            : writerCleanTimeout
-                                ? WRITER_CLEAN_TIMEOUT_RETRY_CATEGORY
-                                : mapped.failureCategory,
+                    : // partial-success-with-context-overflow: the writer hit a context
+                        // overflow on its final provider call but had already persisted
+                        // real file changes (change-manifest non-empty). Classify it
+                        // distinctly so the report shows "code largely done, verification
+                        // incomplete" instead of a misleading empty-output / spec issue,
+                        // and recovery can rerun from verify/implement with a compacted
+                        // session rather than asking the operator for spec clarification.
+                        rawFailureCategory === "context-overflow" &&
+                            (changeManifestChangedFiles?.length ?? 0) > 0
+                            ? "partial-success-with-context-overflow"
+                            : // writer-thinking-exhausted: a length-stopped thinking-only attempt with
+                                // zero write tool calls and zero attributed diff is terminal and
+                                // non-retryable; recommend a model switch + fresh run. Only applies on
+                                // the empty-output base category so provider/transport failures keep
+                                // their original category, and only when the completeness gate did not
+                                // upgrade to incomplete-write-set above.
+                                writerThinkingExhausted
+                                    ? WRITER_THINKING_EXHAUSTED_CATEGORY
+                                    : writerCleanTimeout
+                                        ? WRITER_CLEAN_TIMEOUT_RETRY_CATEGORY
+                                        : // writer-budget-exhausted: the provider session consumed an
+                                            // excessive amount of tokens (a read-edit-test loop that never
+                                            // converged) and still failed. Classify distinctly so the
+                                            // report says the run burned its budget instead of a generic
+                                            // empty-output, and recovery recommends a fresh compacted
+                                            // run rather than spec-clarification.
+                                            writerBudgetExhausted
+                                                ? WRITER_BUDGET_EXHAUSTED_CATEGORY
+                                                : mapped.failureCategory,
         durationMs: mapped.durationMs || Date.now() - started,
     };
 }

package/dist/executors/pi-executor.js

@@ -1012,6 +1012,13 @@ export function classifyPiFailure(input) {
     if (input.exitCode === 0 && input.assistantText.trim())
         return "success";
     const combined = `${input.stderr}\n${input.stdout}`.toLowerCase();
+    // Context overflow (400 request-too-large / context window exceeded).
+    // Must be detected BEFORE the generic rate-limit/quota phrases: an overflow
+    // error often contains "too many tokens" / "maximum context" which would
+    // otherwise be misread as rate-limit or quota. Kept in sync with
+    // CONTEXT_OVERFLOW_PHRASES in commands/client-recovery.ts.
+    if (/请求上下文过大|context_length_exceeded|context overflow|context length overflow|too many tokens|maximum context|prompt is too long|request_too_large|context window/.test(combined))
+        return "context-overflow";
     // Prefer explicit rate-limit / HTTP 429 before generic "limit" quota phrases.
     // Chinese gateways often say "请求频率已达到限制" without English "rate limit".
     if (/rate.?limit|too many requests|\b429\b|请求频率|频率.*限制|rpm|tpm/.test(combined))

package/dist/executors/shell-executor.js

@@ -1068,7 +1068,7 @@ async function executeBackendTestPipeline(input, meta) {
         else if (pipeline === "markdown-traceability") {
             let report;
             try {
-                report = await validateBackendMarkdownTraceability(input.cwd);
+                report = await validateBackendMarkdownTraceability(input.cwd, backendLayout);
             }
             catch (error) {
                 report = `# Backend Test Traceability\n\n## Status\n\nFAIL\n\n## Findings\n\n- Traceability validation could not complete: ${error instanceof Error ? error.message : String(error)}\n`;

package/dist/shared/dag-failure-category.js

@@ -47,10 +47,22 @@ const RAW_TO_NORMALIZED = {
     "verify-failure": "validation",
     "test-failure": "validation",
     "verification-plan-stale": "validation",
+    "read-burst": "validation",
+    // Writer persisted real file changes but the final provider call hit a
+    // context overflow; verification never ran. Distinct from empty-output so
+    // the report shows partial success instead of a spec issue.
+    "partial-success-with-context-overflow": "validation",
+    // Writer burned an excessive token budget (unconverged read-edit-test loop)
+    // and still failed; distinct from empty-output for accurate reporting.
+    "writer-budget-exhausted": "validation",
     network: "executor",
     quota: "executor",
     "rate-limit": "executor",
     unavailable: "executor",
+    // Context window overflow (400 request-too-large): the session needs
+    // compaction / fresh context before retrying — an executor-side
+    // environment condition, not a plan-quality defect.
+    "context-overflow": "executor",
     // Deterministic capability/policy refusal: missing verified launcher JS
     // entry, capability allowlist rejection, or missing bounded write tool
     // profile. These are environment/config defects the operator repairs

package/dist/task/config-types.js

@@ -219,6 +219,21 @@ const taskConfigObjectSchema = z.object({
     maxFixLoops: z.number().int().min(0).optional().default(2),
     /** Supervised DAG convergence is opt-in until runtime smoke evidence is stronger. */
     convergence: convergenceConfigSchema.optional().default({ enabled: false }),
+    /** Frontend recovery continuation quota. Bounds how many times a failed
+     * frontend run may auto-recover via M6 recovery operations (1 = current
+     * default; raise to 2-3 for more tolerance of transient verify failures). */
+    frontendRecovery: z
+        .object({
+        maxContinuations: z
+            .number()
+            .int()
+            .min(1)
+            .max(5)
+            .optional()
+            .default(1),
+    })
+        .strict()
+        .optional(),
     /** Outer loop auto mode never writes by default; DAG execute requires this policy plus path/writeSet gates. */
     loopAutoExecutionPolicy: loopAutoExecutionPolicySchema
         .optional()

package/dist/task/frontend-project-capability.js

@@ -133,9 +133,28 @@ export async function listOpenspecDiscovery(repoRoot, options = {}) {
         .filter(Boolean);
     const collected = [];
     let excludedGovernanceCount = 0;
+    // Metadata / bookkeeping directories that are not normative design specs:
+    // changelogs, ADR/history archives, proposals under review, and scratch
+    // state. Reading them inflates the candidate list (and the plan prompt)
+    // with files no component selection should cite. A task that genuinely
+    // needs one can still reference it explicitly — the prewrite gate
+    // candidates come from this discovery, but explicit task-source citations
+    // flow through openspecMandatoryPaths independently.
+    const DEFAULT_EXCLUDED_SPEC_PREFIXES = [
+        "openspec/changes",
+        "openspec/project-specs/changes",
+        "openspec/project-specs/changelog",
+        "openspec/project-specs/history",
+        "openspec/project-specs/archive",
+        "openspec/project-specs/decisions",
+        "openspec/project-specs/proposals",
+    ];
     const isExcluded = (rel) => {
         if (isGovernanceSubtreePath(rel, governanceRoot))
             return true;
+        if (DEFAULT_EXCLUDED_SPEC_PREFIXES.some((prefix) => rel === prefix || rel.startsWith(prefix + "/"))) {
+            return true;
+        }
         return extraExcludedPrefixes.some((prefix) => rel === prefix || rel.startsWith(prefix + "/"));
     };
     for (const specDir of options.specRoots ?? [...OPENSPEC_SPEC_DIRS]) {

package/dist/worker/console/static/assets/{abnfDiagram-N423BO3Z-CfDSkLtp.js → abnfDiagram-N423BO3Z-bPer1waP.js}

@@ -1 +1 @@
-import{g as p,r as u,d as a}from"./chunk-6Q2QTUOP-BtTDauXA.js";import{p as f}from"./chunk-JWPE2WC7-B_f-emL4.js";import{_ as n,l as o}from"./mermaid.core-TPPHfQbe.js";import{M as c,b as d}from"./cynefin-VYW2F7L2-DbMU2PZ2.js";import"./index-DPbsruV5.js";var v=d().RailroadAbnf.parser.LangiumParser,i=n(e=>{const r=e.alternatives.map(g);return r.length===1?r[0]:{type:"choice",alternatives:r}},"transformAlternation"),g=n(e=>{const r=e.elements.map(y);return r.length===1?r[0]:{type:"sequence",elements:r}},"transformConcatenation"),b=n(e=>{if(e.includes("*")){const[t,s]=e.split("*"),l=t?parseInt(t,10):0,m=s?parseInt(s,10):1/0;return{min:l,max:m}}const r=parseInt(e,10);return{min:r,max:r}},"parseRepeat"),y=n(e=>{const r=A(e.primary);if(!e.repeat)return r;const{min:t,max:s}=b(e.repeat);return t===0&&s===1?{type:"optional",element:r}:{type:"repetition",element:r,min:t,max:s}},"transformElement"),A=n(e=>{switch(e.$type){case"AbnfStringLiteral":return{type:"terminal",value:e.value};case"AbnfNumVal":return{type:"terminal",value:e.value};case"AbnfRuleName":return{type:"nonterminal",name:e.name};case"AbnfGroup":return i(e.element);case"AbnfOptionalGroup":return{type:"optional",element:i(e.element)};default:throw new Error(`Unsupported ABNF primary node: ${e.$type}`)}},"transformPrimary"),P=n(e=>({name:e.name,definition:i(e.definition)}),"transformRule"),h=n(e=>{f(e,a),e.title&&a.setTitle(e.title),e.rules.map(r=>a.addRule(P(r)))},"populateDb"),R={parse:n(e=>{a.clear(),o.debug("[ABNF Parser] Starting Langium parse");const r=v.parse(e);if(r.lexerErrors.length>0||r.parserErrors.length>0)throw new c(r);const t=r.value;o.debug("[ABNF Parser] Parsed rules:",t.rules.length),h(t),o.debug("[ABNF Parser] Parse complete")},"parse"),parser:{yy:a}},B={parser:R,db:a,renderer:u,styles:p};export{B as diagram};
+import{g as p,r as u,d as a}from"./chunk-6Q2QTUOP-Bw9nFjCJ.js";import{p as f}from"./chunk-JWPE2WC7-Dt75ZdBD.js";import{_ as n,l as o}from"./mermaid.core-BlvpGVG8.js";import{M as c,b as d}from"./cynefin-VYW2F7L2-eTOts9L1.js";import"./index-DBh_x_Ek.js";var v=d().RailroadAbnf.parser.LangiumParser,i=n(e=>{const r=e.alternatives.map(g);return r.length===1?r[0]:{type:"choice",alternatives:r}},"transformAlternation"),g=n(e=>{const r=e.elements.map(y);return r.length===1?r[0]:{type:"sequence",elements:r}},"transformConcatenation"),b=n(e=>{if(e.includes("*")){const[t,s]=e.split("*"),l=t?parseInt(t,10):0,m=s?parseInt(s,10):1/0;return{min:l,max:m}}const r=parseInt(e,10);return{min:r,max:r}},"parseRepeat"),y=n(e=>{const r=A(e.primary);if(!e.repeat)return r;const{min:t,max:s}=b(e.repeat);return t===0&&s===1?{type:"optional",element:r}:{type:"repetition",element:r,min:t,max:s}},"transformElement"),A=n(e=>{switch(e.$type){case"AbnfStringLiteral":return{type:"terminal",value:e.value};case"AbnfNumVal":return{type:"terminal",value:e.value};case"AbnfRuleName":return{type:"nonterminal",name:e.name};case"AbnfGroup":return i(e.element);case"AbnfOptionalGroup":return{type:"optional",element:i(e.element)};default:throw new Error(`Unsupported ABNF primary node: ${e.$type}`)}},"transformPrimary"),P=n(e=>({name:e.name,definition:i(e.definition)}),"transformRule"),h=n(e=>{f(e,a),e.title&&a.setTitle(e.title),e.rules.map(r=>a.addRule(P(r)))},"populateDb"),R={parse:n(e=>{a.clear(),o.debug("[ABNF Parser] Starting Langium parse");const r=v.parse(e);if(r.lexerErrors.length>0||r.parserErrors.length>0)throw new c(r);const t=r.value;o.debug("[ABNF Parser] Parsed rules:",t.rules.length),h(t),o.debug("[ABNF Parser] Parse complete")},"parse"),parser:{yy:a}},B={parser:R,db:a,renderer:u,styles:p};export{B as diagram};

package/dist/worker/console/static/assets/{arc-BlefM6I5.js → arc-BLdkwucW.js}

@@ -1 +1 @@
-import{Y as ln,$ as an,a0 as F,a1 as q,a2 as j,a3 as un,a4 as y,a5 as tn,a6 as J,a7 as _,a8 as rn,a9 as o,aa as on,ab as sn,ac as fn}from"./mermaid.core-TPPHfQbe.js";function cn(l){return l.innerRadius}function yn(l){return l.outerRadius}function gn(l){return l.startAngle}function dn(l){return l.endAngle}function mn(l){return l&&l.padAngle}function pn(l,h,I,D,v,A,z,a){var O=I-l,i=D-h,n=z-v,d=a-A,u=d*O-n*i;if(!(u*u<y))return u=(n*(h-A)-d*(l-v))/u,[l+u*O,h+u*i]}function U(l,h,I,D,v,A,z){var a=l-I,O=h-D,i=(z?A:-A)/J(a*a+O*O),n=i*O,d=-i*a,u=l+n,s=h+d,f=I+n,c=D+d,B=(u+f)/2,t=(s+c)/2,m=f-u,g=c-s,R=m*m+g*g,T=v-A,P=u*c-f*s,S=(g<0?-1:1)*J(on(0,T*T*R-P*P)),Y=(P*g-m*S)/R,$=(-P*m-g*S)/R,w=(P*g+m*S)/R,p=(-P*m+g*S)/R,x=Y-B,e=$-t,r=w-B,C=p-t;return x*x+e*e>r*r+C*C&&(Y=w,$=p),{cx:Y,cy:$,x01:-n,y01:-d,x11:Y*(v/T-1),y11:$*(v/T-1)}}function hn(){var l=cn,h=yn,I=j(0),D=null,v=gn,A=dn,z=mn,a=null,O=ln(i);function i(){var n,d,u=+l.apply(this,arguments),s=+h.apply(this,arguments),f=v.apply(this,arguments)-un,c=A.apply(this,arguments)-un,B=rn(c-f),t=c>f;if(a||(a=n=O()),s<u&&(d=s,s=u,u=d),!(s>y))a.moveTo(0,0);else if(B>tn-y)a.moveTo(s*F(f),s*q(f)),a.arc(0,0,s,f,c,!t),u>y&&(a.moveTo(u*F(c),u*q(c)),a.arc(0,0,u,c,f,t));else{var m=f,g=c,R=f,T=c,P=B,S=B,Y=z.apply(this,arguments)/2,$=Y>y&&(D?+D.apply(this,arguments):J(u*u+s*s)),w=_(rn(s-u)/2,+I.apply(this,arguments)),p=w,x=w,e,r;if($>y){var C=sn($/u*q(Y)),K=sn($/s*q(Y));(P-=C*2)>y?(C*=t?1:-1,R+=C,T-=C):(P=0,R=T=(f+c)/2),(S-=K*2)>y?(K*=t?1:-1,m+=K,g-=K):(S=0,m=g=(f+c)/2)}var G=s*F(m),H=s*q(m),L=u*F(T),M=u*q(T);if(w>y){var N=s*F(g),Q=s*q(g),V=u*F(R),W=u*q(R),E;if(B<an)if(E=pn(G,H,V,W,N,Q,L,M)){var X=G-E[0],Z=H-E[1],b=N-E[0],k=Q-E[1],nn=1/q(fn((X*b+Z*k)/(J(X*X+Z*Z)*J(b*b+k*k)))/2),en=J(E[0]*E[0]+E[1]*E[1]);p=_(w,(u-en)/(nn-1)),x=_(w,(s-en)/(nn+1))}else p=x=0}S>y?x>y?(e=U(V,W,G,H,s,x,t),r=U(N,Q,L,M,s,x,t),a.moveTo(e.cx+e.x01,e.cy+e.y01),x<w?a.arc(e.cx,e.cy,x,o(e.y01,e.x01),o(r.y01,r.x01),!t):(a.arc(e.cx,e.cy,x,o(e.y01,e.x01),o(e.y11,e.x11),!t),a.arc(0,0,s,o(e.cy+e.y11,e.cx+e.x11),o(r.cy+r.y11,r.cx+r.x11),!t),a.arc(r.cx,r.cy,x,o(r.y11,r.x11),o(r.y01,r.x01),!t))):(a.moveTo(G,H),a.arc(0,0,s,m,g,!t)):a.moveTo(G,H),!(u>y)||!(P>y)?a.lineTo(L,M):p>y?(e=U(L,M,N,Q,u,-p,t),r=U(G,H,V,W,u,-p,t),a.lineTo(e.cx+e.x01,e.cy+e.y01),p<w?a.arc(e.cx,e.cy,p,o(e.y01,e.x01),o(r.y01,r.x01),!t):(a.arc(e.cx,e.cy,p,o(e.y01,e.x01),o(e.y11,e.x11),!t),a.arc(0,0,u,o(e.cy+e.y11,e.cx+e.x11),o(r.cy+r.y11,r.cx+r.x11),t),a.arc(r.cx,r.cy,p,o(r.y11,r.x11),o(r.y01,r.x01),!t))):a.arc(0,0,u,T,R,t)}if(a.closePath(),n)return a=null,n+""||null}return i.centroid=function(){var n=(+l.apply(this,arguments)+ +h.apply(this,arguments))/2,d=(+v.apply(this,arguments)+ +A.apply(this,arguments))/2-an/2;return[F(d)*n,q(d)*n]},i.innerRadius=function(n){return arguments.length?(l=typeof n=="function"?n:j(+n),i):l},i.outerRadius=function(n){return arguments.length?(h=typeof n=="function"?n:j(+n),i):h},i.cornerRadius=function(n){return arguments.length?(I=typeof n=="function"?n:j(+n),i):I},i.padRadius=function(n){return arguments.length?(D=n==null?null:typeof n=="function"?n:j(+n),i):D},i.startAngle=function(n){return arguments.length?(v=typeof n=="function"?n:j(+n),i):v},i.endAngle=function(n){return arguments.length?(A=typeof n=="function"?n:j(+n),i):A},i.padAngle=function(n){return arguments.length?(z=typeof n=="function"?n:j(+n),i):z},i.context=function(n){return arguments.length?(a=n??null,i):a},i}export{hn as d};
+import{Y as ln,$ as an,a0 as F,a1 as q,a2 as j,a3 as un,a4 as y,a5 as tn,a6 as J,a7 as _,a8 as rn,a9 as o,aa as on,ab as sn,ac as fn}from"./mermaid.core-BlvpGVG8.js";function cn(l){return l.innerRadius}function yn(l){return l.outerRadius}function gn(l){return l.startAngle}function dn(l){return l.endAngle}function mn(l){return l&&l.padAngle}function pn(l,h,I,D,v,A,z,a){var O=I-l,i=D-h,n=z-v,d=a-A,u=d*O-n*i;if(!(u*u<y))return u=(n*(h-A)-d*(l-v))/u,[l+u*O,h+u*i]}function U(l,h,I,D,v,A,z){var a=l-I,O=h-D,i=(z?A:-A)/J(a*a+O*O),n=i*O,d=-i*a,u=l+n,s=h+d,f=I+n,c=D+d,B=(u+f)/2,t=(s+c)/2,m=f-u,g=c-s,R=m*m+g*g,T=v-A,P=u*c-f*s,S=(g<0?-1:1)*J(on(0,T*T*R-P*P)),Y=(P*g-m*S)/R,$=(-P*m-g*S)/R,w=(P*g+m*S)/R,p=(-P*m+g*S)/R,x=Y-B,e=$-t,r=w-B,C=p-t;return x*x+e*e>r*r+C*C&&(Y=w,$=p),{cx:Y,cy:$,x01:-n,y01:-d,x11:Y*(v/T-1),y11:$*(v/T-1)}}function hn(){var l=cn,h=yn,I=j(0),D=null,v=gn,A=dn,z=mn,a=null,O=ln(i);function i(){var n,d,u=+l.apply(this,arguments),s=+h.apply(this,arguments),f=v.apply(this,arguments)-un,c=A.apply(this,arguments)-un,B=rn(c-f),t=c>f;if(a||(a=n=O()),s<u&&(d=s,s=u,u=d),!(s>y))a.moveTo(0,0);else if(B>tn-y)a.moveTo(s*F(f),s*q(f)),a.arc(0,0,s,f,c,!t),u>y&&(a.moveTo(u*F(c),u*q(c)),a.arc(0,0,u,c,f,t));else{var m=f,g=c,R=f,T=c,P=B,S=B,Y=z.apply(this,arguments)/2,$=Y>y&&(D?+D.apply(this,arguments):J(u*u+s*s)),w=_(rn(s-u)/2,+I.apply(this,arguments)),p=w,x=w,e,r;if($>y){var C=sn($/u*q(Y)),K=sn($/s*q(Y));(P-=C*2)>y?(C*=t?1:-1,R+=C,T-=C):(P=0,R=T=(f+c)/2),(S-=K*2)>y?(K*=t?1:-1,m+=K,g-=K):(S=0,m=g=(f+c)/2)}var G=s*F(m),H=s*q(m),L=u*F(T),M=u*q(T);if(w>y){var N=s*F(g),Q=s*q(g),V=u*F(R),W=u*q(R),E;if(B<an)if(E=pn(G,H,V,W,N,Q,L,M)){var X=G-E[0],Z=H-E[1],b=N-E[0],k=Q-E[1],nn=1/q(fn((X*b+Z*k)/(J(X*X+Z*Z)*J(b*b+k*k)))/2),en=J(E[0]*E[0]+E[1]*E[1]);p=_(w,(u-en)/(nn-1)),x=_(w,(s-en)/(nn+1))}else p=x=0}S>y?x>y?(e=U(V,W,G,H,s,x,t),r=U(N,Q,L,M,s,x,t),a.moveTo(e.cx+e.x01,e.cy+e.y01),x<w?a.arc(e.cx,e.cy,x,o(e.y01,e.x01),o(r.y01,r.x01),!t):(a.arc(e.cx,e.cy,x,o(e.y01,e.x01),o(e.y11,e.x11),!t),a.arc(0,0,s,o(e.cy+e.y11,e.cx+e.x11),o(r.cy+r.y11,r.cx+r.x11),!t),a.arc(r.cx,r.cy,x,o(r.y11,r.x11),o(r.y01,r.x01),!t))):(a.moveTo(G,H),a.arc(0,0,s,m,g,!t)):a.moveTo(G,H),!(u>y)||!(P>y)?a.lineTo(L,M):p>y?(e=U(L,M,N,Q,u,-p,t),r=U(G,H,V,W,u,-p,t),a.lineTo(e.cx+e.x01,e.cy+e.y01),p<w?a.arc(e.cx,e.cy,p,o(e.y01,e.x01),o(r.y01,r.x01),!t):(a.arc(e.cx,e.cy,p,o(e.y01,e.x01),o(e.y11,e.x11),!t),a.arc(0,0,u,o(e.cy+e.y11,e.cx+e.x11),o(r.cy+r.y11,r.cx+r.x11),t),a.arc(r.cx,r.cy,p,o(r.y11,r.x11),o(r.y01,r.x01),!t))):a.arc(0,0,u,T,R,t)}if(a.closePath(),n)return a=null,n+""||null}return i.centroid=function(){var n=(+l.apply(this,arguments)+ +h.apply(this,arguments))/2,d=(+v.apply(this,arguments)+ +A.apply(this,arguments))/2-an/2;return[F(d)*n,q(d)*n]},i.innerRadius=function(n){return arguments.length?(l=typeof n=="function"?n:j(+n),i):l},i.outerRadius=function(n){return arguments.length?(h=typeof n=="function"?n:j(+n),i):h},i.cornerRadius=function(n){return arguments.length?(I=typeof n=="function"?n:j(+n),i):I},i.padRadius=function(n){return arguments.length?(D=n==null?null:typeof n=="function"?n:j(+n),i):D},i.startAngle=function(n){return arguments.length?(v=typeof n=="function"?n:j(+n),i):v},i.endAngle=function(n){return arguments.length?(A=typeof n=="function"?n:j(+n),i):A},i.padAngle=function(n){return arguments.length?(z=typeof n=="function"?n:j(+n),i):z},i.context=function(n){return arguments.length?(a=n??null,i):a},i}export{hn as d};