@tea-agent/loop-agent 0.40.0-next.10 → 0.40.0-next.12

package/CHANGELOG.md

@@ -2,12 +2,18 @@
 
 ## [Unreleased]
 
+- 修复 Console 轨迹视图引用未声明 CSS 自定义属性导致仓库发布门禁失败的问题，补齐品牌色、警告色与字体别名并保持现有视觉回退值。
+
 ### 重点更新
 
+- Console 对话页「轨迹」视图响应式优化：轨迹列宽跟随面板实际宽度收缩（`.oc-trajectory` 加 `width:100%`、`.oc-trajectory-turn/.step` 加 `min-width:0` 修 flex 收缩链），窄窗口（≤720px）自动隐藏耗时列，避免工具行被固定项挤爆。
+- Console 对话页新增「轨迹」视图（详情侧栏 tab）：仿 DSH ui-trajectory，用本仓库 turnGroups 数据把对话按「用户 → 过程 → AI 回复」渲染成统一单元格列表，每行带 kind 标签 + 图标（用户/ AI / 思考 / 工具 / 活动 / 错误 / 压缩）；用户与 AI 用标签颜色 + 图标区分，AI 中间文本也标注；思考、工具、以及超长用户/AI 消息默认单行截断、可展开/收起看全文（含工具参数与结果、状态与耗时）。支持一键「导出 HTML」自包含文件（长内容用 `<details>` 折叠，短内容内联）。主会话思考块标签由英文 Think 改为「思考」。
+- DAG 检查器节点「执行过程」的「导出 HTML」改为复用页面真实渲染与样式，导出的独立 HTML 排版与页面一致；Pi 会话节点导出会带上原始协议事件，左上角提供「展开/隐藏原始协议事件」按钮（默认隐藏，每项仍可单独展开），shell/静态节点导出同样与页面一致。
 - backend-test 的 pytest repair 现在继续使用 run-owned plan，不再搜索测试目录 README；correspondence finding 会直接指向 docstring、参数 ID、符号、脚本或 payload 的修复位置，collection/scenario repair 与 generated-local Python 写边界保持一致，并在单次 Pi 会话达到 24 轮或 80K 最大 usage snapshot 前受控返回 partial failure。
 - Operator Chat 现在可以在同一个页面管理多个工作区；每个会话始终使用创建它的工作区，切换对话时地址栏保持简洁稳定。
 - 对话消息流整体调整为更紧凑、清晰的布局，思考过程、工具执行、阶段性结果和最终回答会按真实发生顺序展示。
 - 上下文过大时会自动压缩并继续原请求，消息流会依次展示触发原因、压缩进度和压缩结果；手动压缩也使用同一套展示方式。
+- Operator Chat 与 DAG Pi 节点默认开启上下文压力处理：发送前接近窗口时压缩一次、识别网关「请求上下文过大」后压缩续跑，并对 OpenAI 格式的大工具输出做线路压缩；可用环境变量关闭，不必改会话记录。
 - 对话进行中可以连续提交多条消息，并支持编辑、删除或立即插入当前回复；刷新页面或重启 Console 后，未发送内容仍会保留。
 
 ### 新增
@@ -18,6 +24,9 @@
 
 ### 改进
 
+- Operator Chat 发送前会在接近模型窗口时主动压缩，压缩失败仍发送当前输入，不会把消息丢掉。DAG 节点同步启用 overflow 识别与线路压缩，但不在 streaming 中主动 compact。
+- 网关「请求上下文过大」及常见包装/嵌套 JSON 由共享分类器识别；目标项目 `loop-agent init` 生成的 Pi overflow extension 与控制器使用同一套短语表。
+- `@agent-context/sift@0.0.1-alpha.6` 作为可选依赖接入 Console 与 DAG：默认开启，`HARNESS_CONSOLE_SIFT` / `HARNESS_DAG_SIFT` 设为 `0`、`false` 或 `off` 即可关闭。Anthropic 缺省 prompt cache 形态保持 no-op，避免破坏缓存。
 - 后端测试的计划与生成阶段只读取任务明确绑定的需求、环境报告和本轮产物，减少无关仓库内容干扰结果，并让后续步骤继续使用同一份已确认计划。
 - Operator Chat 的任务清单工具描述补齐多步骤与 DAG 使用纪律：开始前按具体步骤规划、保持进行中约束、完成后立即更新完整列表，并用面向用户的阶段呈现 DAG 进度，简单任务自动跳过。
 - 正式发布会自动同步更新版本日志和文档站摘要；发布说明优先生成简洁自然的中文，生成服务不可用时也能安全完成发布。
@@ -28,6 +37,15 @@
 
 ### 修复
 
+- 修复 backend-test 的 Scenario Partition 计划表只提示 `each-value`/`omitted`、却由下游确定性门禁强制要求 `not-in-set` 的合同漂移；计划、Markdown Case 与 pytest 现在统一明确唯一补集槽位，避免 PI 因表格指令遗漏 `TP-<Partition ID>-NOT-IN-SET` 后触发 `MISSING_COMPLEMENT_SLOT`。
+- 修复文档审计扫描本地 `.scratch/` 临时证据与打包目录、导致仓库 preflight 和发布前验证被非治理文件阻断的问题。
+- 修复 backend-test 把 Markdown 明确声明的 enum-invalid、wrong-type、null、empty 和精确非法 custom literal 当作 payload enum 契约漂移、错误消耗唯一一次 pytest repair 的问题；豁免现在按 pytest parameter ID、目标字段和值逐 TP 绑定，positive/nominal drift 与 path 缺陷仍严格阻断。
+- 修复 backend-test 无法从同一生成模块的安全 payload helper 中绑定 field-target positional/keyword/default 参数，以及无法识别精确 `_without(payload, field)` 删除语义的问题；computed、动态、二层、跨模块和危险 helper 仍保持 `UNDETERMINED`。
+- 修复 backend-test 无法静态证明同一生成模块内安全 payload helper、导致 request-level nominal 场景长期停留在 `UNDETERMINED` 的问题；超长边界 observed 现在持久化为有界摘要并保留真实长度，空白修复建议也明确使用真实空格而非字面 escape 文本。
+- 修复 backend-test 把 Markdown 中 `\\u0020`/`\\x20` 空白表示与 pytest 真实空白字符串误判为 scenario-param 不一致的问题；readiness 的逐项排除现在携带有界的 TP、字段、expected/observed raw/normalized 和源码位置诊断，同时不对普通业务字符做 trim、大小写折叠或宽松解码。
+- 修复 Console 把 backend-test writer 的局部保护文件误判为整个 writeSet 越界的问题；任务级禁止路径仍保持硬阻断，合法 DAG 可继续取得 autonomous execution receipt。
+- 修复 backend-test 对 `resource_client.call(..., payload=...)` 一类本地 transport 的 payload AST 假阴性；readiness 新增固定分类/Case 排除汇总和 pytest 启动事实，payload repair finding 同时携带 expected/observed/missing path 清单。
+- 修复后端测试在 payload、fixture 与 Markdown→pytest 对应关系同时异常时只修复其中一类问题的问题；pytest 侧缺陷现在通过结构化 `repairFindings` 合并进入唯一一次有界 repair，Markdown Test Point 未分类或重复分类则在生成阶段定向重试并禁止下游猜修。
 - 修复重命名会话时输入框没有回显当前标题的问题。
 - 修复停止回复后输入区恢复迟缓、排队消息偶发丢失，以及切换会话后旧状态残留的问题。
 - 修复宽表格、文件预览、滚动条和窄屏布局中的多处显示异常。

package/dist/application/dag/generate-task-dag.js

@@ -109,8 +109,12 @@ function findForbiddenOverlapsForPacket(task) {
     const overlaps = [];
     for (const writeSetEntry of task.writeSet ?? []) {
         for (const forbiddenPath of task.forbiddenPaths ?? []) {
-            if (pathMatchesPattern(writeSetEntry, forbiddenPath) ||
-                pathMatchesPattern(forbiddenPath, writeSetEntry)) {
+            // A narrower forbidden child may intentionally carve a protected
+            // file out of a broader node writeSet. The runtime write guard gives
+            // forbiddenPaths precedence; report a packet conflict only when the
+            // writeSet entry itself is inside the forbidden boundary. Console G2
+            // separately rechecks task-global forbidden paths with live scope.
+            if (pathMatchesPattern(writeSetEntry, forbiddenPath)) {
                 overlaps.push({ writeSetEntry, forbiddenPath });
             }
         }

package/dist/build-stamp.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "version": "0.40.0-next.10",
-  "gitSha": "d108eb1087e69b3b84bc5c81d86e561adb5fb051",
-  "builtAt": "2026-08-28T01:40:07.616Z"
+  "version": "0.40.0-next.12",
+  "gitSha": "41c2688fb25e22404d7dd6f9a7c884a2e638d500",
+  "builtAt": "2026-08-29T08:53:25.216Z"
 }

package/dist/commands/client-recovery.js

@@ -19,36 +19,11 @@ export const MAX_SESSION_RETRIES = 5;
 /** Hard cap for OpenCode overflow compact+resume recoveries (≤ 2). */
 export const MAX_OVERFLOW_RECOVERIES = 1;
 import { PI_RECOMMENDED_COMPACTION, PI_RECOMMENDED_RETRY, } from "../shared/pi-retry-settings.js";
+import { CONTEXT_OVERFLOW_PHRASES, buildGeneratedOverflowClassifierSource, isContextOverflow as classifySharedOverflow, } from "../shared/pi-context-pressure/overflow.js";
 export { PI_RECOMMENDED_COMPACTION, PI_RECOMMENDED_RETRY };
-/**
- * Shared overflow phrase sources used by isContextOverflow and generated plugins.
- * Keep English + Chinese intranet gateway messages in one place to avoid drift.
- */
-export const CONTEXT_OVERFLOW_PHRASES = [
-    "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",
-];
-function escapeRegExpLiteral(value) {
-    return value.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
-}
-const CONTEXT_OVERFLOW_PATTERN = new RegExp(CONTEXT_OVERFLOW_PHRASES.map(escapeRegExpLiteral).join("|"), "i");
+export { CONTEXT_OVERFLOW_PHRASES };
 function buildGeneratedContextOverflowPatternSource() {
-    return `const CONTEXT_OVERFLOW_PHRASES = ${JSON.stringify([
-        ...CONTEXT_OVERFLOW_PHRASES,
-    ])};
-const OVERFLOW_PATTERN = new RegExp(
-  CONTEXT_OVERFLOW_PHRASES.map((phrase) =>
-    phrase.replace(/[.*+?^\${}()|[\\]\\\\]/g, "\\\\$&"),
-  ).join("|"),
-  "i",
-);`;
+    return buildGeneratedOverflowClassifierSource();
 }
 const PERMANENT_MESSAGE_PATTERNS = [
     {
@@ -65,7 +40,7 @@ const PERMANENT_MESSAGE_PATTERNS = [
     },
     {
         reason: "context-overflow",
-        pattern: CONTEXT_OVERFLOW_PATTERN,
+        pattern: /context_length_exceeded|请求上下文过大/i,
     },
     {
         reason: "cancelled",
@@ -180,6 +155,8 @@ function permanentReason(error) {
         return "api-error";
     }
     const text = collectErrorText(error);
+    if (isContextOverflow(error))
+        return "context-overflow";
     for (const entry of PERMANENT_MESSAGE_PATTERNS) {
         if (entry.pattern.test(text))
             return entry.reason;
@@ -192,7 +169,7 @@ function permanentReason(error) {
  * business validation, or standard 502/LLMRequestError as overflow.
  */
 export function isContextOverflow(error) {
-    return CONTEXT_OVERFLOW_PATTERN.test(collectErrorText(error));
+    return classifySharedOverflow(error);
 }
 function looksTransient(error) {
     const text = collectErrorText(error);
@@ -887,7 +864,7 @@ function textOf(error) {
 }
 
 function isContextOverflow(error) {
-  return OVERFLOW_PATTERN.test(textOf(error));
+  return isOverflowMessage(textOf(error));
 }
 
 function buildOverflowResumePrompt(sessionId, error, attempt) {
@@ -1163,11 +1140,6 @@ const EXTENSION_PATH = ${JSON.stringify(PI_CONTEXT_OVERFLOW_EXTENSION_PATH)};
 ${buildGeneratedContextOverflowPatternSource()}
 const NORMALIZED_PREFIX = "context_length_exceeded:";
 
-function isOverflowMessage(text) {
-  if (typeof text !== "string" || !text) return false;
-  return OVERFLOW_PATTERN.test(text);
-}
-
 export default function loopAgentContextOverflowExtension(pi) {
   void EXTENSION_PATH;
   pi.on("message_end", (event) => {

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

@@ -1,9 +1,12 @@
 import { appendFile, mkdir } from "node:fs/promises";
+import os from "node:os";
 import path from "node:path";
+import { randomUUID } from "node:crypto";
 import { computeExtensionToolAllowlistExtras } from "./pi-extension-resolver.js";
 import { BoundedTextPreview, classifyPiFailure, createPiJsonlStreamCollector, DEFAULT_ABORT_GRACE_MS, DEFAULT_STALL_TIMEOUT_MS, DEFAULT_TIMEOUT_MS, extractPiEventStopReason, extractAssistantTextFromPiJson, } from "./pi-executor.js";
 import { serializeSessionEvent } from "./pi-event-serializer.js";
 import { PI_RECOMMENDED_COMPACTION, PI_RECOMMENDED_RETRY, } from "../shared/pi-retry-settings.js";
+import { createCompactionController, createContextPressureExtension, createSiftBridgeState, inMemoryCompactionSettings, isDagSiftEnabled, parseCompactionPolicy, parseSiftBridgeConfig, SIFT_RETRIEVE_TOOL_NAME, } from "../shared/pi-context-pressure/index.js";
 /** Same-session recovery after a transport stall. Exactly one continue per SDK attempt. */
 export const PI_SDK_STALL_CONTINUE_MAX = 1;
 /**
@@ -215,15 +218,37 @@ async function createSdkSession(sdk, input, shared) {
     // Inject rate-limit-tolerant auto-retry settings for the session lifecycle.
     // Prefer SettingsManager.inMemory so harness runs do not depend on ~/.pi or
     // project .pi/settings.json being present/trusted.
+    const policy = parseCompactionPolicy();
+    const compaction = {
+        ...PI_RECOMMENDED_COMPACTION,
+        ...inMemoryCompactionSettings(policy),
+    };
     const settingsManager = typeof SettingsManager?.inMemory === "function"
         ? SettingsManager.inMemory({
             retry: {
                 ...PI_RECOMMENDED_RETRY,
                 provider: { ...PI_RECOMMENDED_RETRY.provider },
             },
-            compaction: { ...PI_RECOMMENDED_COMPACTION },
+            compaction,
         }, { projectTrusted: true })
         : undefined;
+    const nodeSessionId = `dag-${randomUUID()}`;
+    const controller = createCompactionController();
+    const siftEnabled = isDagSiftEnabled();
+    const sift = siftEnabled.enabled
+        ? createSiftBridgeState(parseSiftBridgeConfig({
+            sessionId: nodeSessionId,
+            defaultStashRoot: path.join(os.tmpdir(), "loop-agent-dag-sift"),
+        }))
+        : undefined;
+    if (sift)
+        sift.counters = controller.counters;
+    const pressureExtension = createContextPressureExtension({
+        name: "dag-pi-context-pressure",
+        policy,
+        controller,
+        sift,
+    });
     const loader = new DefaultResourceLoader({
         cwd: input.cwd,
         agentDir,
@@ -233,6 +258,7 @@ async function createSdkSession(sdk, input, shared) {
         ...(input.additionalExtensionPaths && input.additionalExtensionPaths.length > 0
             ? { additionalExtensionPaths: input.additionalExtensionPaths }
             : {}),
+        ...(pressureExtension ? { extensionFactories: [pressureExtension] } : {}),
         ...(settingsManager ? { settingsManager } : {}),
         appendSystemPromptOverride: (base) => [
             ...base,
@@ -247,10 +273,12 @@ async function createSdkSession(sdk, input, shared) {
     // extras into the create-time allowlist; protected builtins, the deny
     // surface, and write-capable extension tools never join.
     const extensionToolExtras = [];
-    if (input.additionalExtensionPaths &&
-        input.additionalExtensionPaths.length > 0) {
-        const registered = collectLoaderExtensionToolNames(loader);
-        extensionToolExtras.push(...computeExtensionToolAllowlistExtras(registered.map((name) => ({ name })), input.toolNames));
+    const registered = collectLoaderExtensionToolNames(loader);
+    extensionToolExtras.push(...computeExtensionToolAllowlistExtras(registered.map((name) => ({ name })), input.toolNames));
+    if (siftEnabled.enabled &&
+        !extensionToolExtras.includes(SIFT_RETRIEVE_TOOL_NAME) &&
+        !input.toolNames.includes(SIFT_RETRIEVE_TOOL_NAME)) {
+        extensionToolExtras.push(...computeExtensionToolAllowlistExtras([{ name: SIFT_RETRIEVE_TOOL_NAME }], input.toolNames));
     }
     const sessionToolNames = [...input.toolNames, ...extensionToolExtras];
     if (input.requireWriterCustomTools) {

package/dist/executors/shell-executor.js

@@ -32,11 +32,11 @@ import { materializeBackendTestExecutionContract } from "../workflows/dag/backen
 import { resolveBackendTestLayout } from "../workflows/dag/backend-test-layout.js";
 import { frontendTestLayoutFromSpec, } from "../workflows/dag/frontend-test-layout.js";
 import { backendTestGapDocSchema, ingestBackendTestGap, } from "../workflows/dag/backend-test-gap-fill.js";
-import { analyzeBackendTestCaseCoverage, analyzeBackendTestMarkdownPytestCorrespondence, materializeBackendTestCaseManifestFromFacts, } from "../workflows/dag/backend-test-case-coverage-analysis.js";
+import { analyzeBackendTestCaseCoverage, analyzeBackendTestMarkdownPytestCorrespondence, classifyBackendTestCorrespondenceRepair, materializeBackendTestCaseManifestFromFacts, } from "../workflows/dag/backend-test-case-coverage-analysis.js";
 import { materializeBackendTestResultFromPytestHtml, materializeBackendTestResultFromRunDir, parsePytestHtmlReport, } from "../workflows/dag/backend-test-result-contract.js";
 import { collectBackendTestHumanCaseCatalog, collectBackendTestMappedPytestScripts, resolveBackendTestMappedPytestScripts, collectJacocoCoverage, hasBlockingBackendMarkdownSafetyFindings, hasBlockingBackendMarkdownModuleStemFindings, inspectBackendTestEnvironment, markdownFiles, requiredBackendMarkdownCaseAcIds, renderBackendTestFacts, renderBackendTestHtml, renderBackendTestL5Dashboard, redactBackendTestOutput, validateBackendMarkdownCases, validateBackendMarkdownTraceability, writeRunReport, } from "../workflows/dag/backend-test-markdown-workflow.js";
 import { applyDeterministicScenarioParamRepairs, assessBackendScenarioParamConsistency, classifyBackendTestFailureWithScenarioParam, readBackendScenarioParamFacts, renderBackendTestFailureAnalysis, writeBackendScenarioParamArtifacts, writeScenarioParamRepairAudit, } from "../workflows/dag/backend-test-scenario-param.js";
-import { assessBackendPytestCollection, assessMissingBackendPytestScripts, assessPriorityOnlyBackendPytestModules, assertBackendTestExecutionReadinessFresh, buildBackendPytestAssetInventory, buildBackendTestItemEligibility, materializeBackendTestExecutionReadiness, materializeEffectiveBackendPytestCollection, readBackendPytestCollectionFacts, readBackendTestExecutionReadiness, writeBackendPytestCollectionArtifacts, } from "../workflows/dag/backend-test-pytest-collection.js";
+import { assessBackendPytestCollection, assessMissingBackendPytestScripts, assessPriorityOnlyBackendPytestModules, assertBackendTestExecutionReadinessFresh, buildBackendPytestAssetInventory, buildBackendTestItemEligibility, materializeBackendTestExecutionReadiness, materializeEffectiveBackendPytestCollection, readBackendPytestCollectionFacts, readBackendTestExecutionReadiness, summarizeBackendTestExclusions, writeBackendPytestCollectionArtifacts, } from "../workflows/dag/backend-test-pytest-collection.js";
 import { computeL5ReportMetrics } from "../workflows/dag/l5-report-metrics.js";
 import { buildBackendTestCanonicalResultFromInitialShellSnippet, materializeBackendTestClassification, } from "../workflows/dag/backend-test-classification-contract.js";
 import { backendTestSemanticReviewSchema, materializeBackendTestSemanticReview, } from "../workflows/dag/backend-test-semantic-review-contract.js";
@@ -870,26 +870,49 @@ async function executeBackendTestPipeline(input, meta) {
                 const correspondenceFactsPath = path.join(contractsDir, "backend-test-markdown-pytest-correspondence-initial.json");
                 await writeFile(correspondenceFactsPath, JSON.stringify(correspondence.facts, null, 2), "utf8");
                 outputs.push(`initialCorrespondence=${correspondenceReportPath}`, `initialCorrespondenceFacts=${correspondenceFactsPath}`);
-                if (correspondence.facts.status === "FAIL" && facts.status === "PASS") {
-                    const correspondenceRepairPaths = Array.from(new Set(correspondence.facts.entries
-                        .filter((entry) => entry.status !== "EXACT_1_TO_1")
-                        .flatMap((entry) => [entry.expectedScript, ...entry.actualScripts])
-                        .filter((candidate) => candidate.startsWith("testcase/") && candidate.endsWith(".py")))).sort();
-                    if (correspondenceRepairPaths.length > 0) {
-                        facts.status = "REPAIRABLE";
-                        facts.repairEligible = true;
-                        facts.repairPaths = Array.from(new Set([...facts.repairPaths, ...correspondenceRepairPaths])).sort();
+                if (correspondence.facts.status === "FAIL") {
+                    const repair = classifyBackendTestCorrespondenceRepair(correspondence.facts, backendLayout);
+                    if (repair.markdownBlockingEntries.length > 0) {
+                        facts.status = "BLOCKED";
+                        facts.repairEligible = false;
+                        facts.repairPaths = [];
                         facts.findings.push({
-                            kind: "markdown-pytest-correspondence",
+                            kind: "markdown-correspondence-contract",
                             classification: "test-asset-defect",
-                            repairability: "repairable",
-                            detail: correspondence.facts.entries
-                                .filter((entry) => entry.status !== "EXACT_1_TO_1")
-                                .flatMap((entry) => entry.findings)
+                            repairability: "blocked",
+                            detail: repair.markdownBlockingEntries
+                                .map((entry) => `${entry.caseId ?? "unknown Case"}: ${entry.reasonCodes.join(", ")}`)
                                 .join("; ")
-                                .slice(0, 12_000) || "Markdown-to-pytest correspondence is incomplete",
+                                .slice(0, 12_000),
                         });
                     }
+                    else if (repair.pytestRepairPaths.length > 0 &&
+                        (facts.status === "PASS" || facts.status === "REPAIRABLE")) {
+                        facts.status = "REPAIRABLE";
+                        facts.repairEligible = true;
+                        facts.repairPaths = Array.from(new Set([...facts.repairPaths, ...repair.pytestRepairPaths])).sort();
+                        const repairEntries = correspondence.facts.entries.filter((entry) => repair.pytestRepairEntries.some((candidate) => candidate.caseId === entry.caseId));
+                        for (const entry of repairEntries.slice(0, 40)) {
+                            const classified = repair.pytestRepairEntries.find((candidate) => candidate.caseId === entry.caseId);
+                            facts.findings.push({
+                                kind: "markdown-pytest-correspondence",
+                                classification: "test-asset-defect",
+                                repairability: "repairable",
+                                detail: entry.findings.join("; ").slice(0, 2_000) || "Markdown-to-pytest correspondence is incomplete",
+                                ...(entry.caseId ? { caseId: entry.caseId } : {}),
+                                reasonCodes: classified?.reasonCodes ?? [],
+                                repairPaths: classified?.paths ?? [],
+                                payloadExpectedPaths: Array.from(new Set([
+                                    ...entry.payloadAssessment.requiredPaths,
+                                    ...entry.payloadAssessment.allowedPaths,
+                                ])).sort(),
+                                payloadObservedPaths: entry.payloadAssessment.observedPaths,
+                                payloadMissingPaths: entry.payloadAssessment.missingPaths,
+                                payloadUnexpectedPaths: entry.payloadAssessment.unexpectedPaths,
+                                payloadEnumMismatches: entry.payloadAssessment.enumMismatches,
+                            });
+                        }
+                    }
                 }
             }
             catch (error) {
@@ -912,6 +935,19 @@ async function executeBackendTestPipeline(input, meta) {
                     collectedItemCount: facts.collectedItemCount,
                     missingMappedScripts: facts.missingMappedScripts,
                     repairPaths: facts.repairPaths,
+                    repairFindings: facts.findings.map((finding) => ({
+                        kind: finding.kind,
+                        repairability: finding.repairability,
+                        detail: finding.detail,
+                        ...(finding.caseId ? { caseId: finding.caseId } : {}),
+                        ...(finding.reasonCodes ? { reasonCodes: finding.reasonCodes } : {}),
+                        ...(finding.repairPaths ? { repairPaths: finding.repairPaths } : {}),
+                        ...(finding.payloadExpectedPaths ? { payloadExpectedPaths: finding.payloadExpectedPaths } : {}),
+                        ...(finding.payloadObservedPaths ? { payloadObservedPaths: finding.payloadObservedPaths } : {}),
+                        ...(finding.payloadMissingPaths ? { payloadMissingPaths: finding.payloadMissingPaths } : {}),
+                        ...(finding.payloadUnexpectedPaths ? { payloadUnexpectedPaths: finding.payloadUnexpectedPaths } : {}),
+                        ...(finding.payloadEnumMismatches ? { payloadEnumMismatches: finding.payloadEnumMismatches } : {}),
+                    })),
                     factsPath: "contracts/backend-test-pytest-collection-initial.json",
                 }),
                 stderr: "",
@@ -1011,6 +1047,7 @@ async function executeBackendTestPipeline(input, meta) {
                 })
                 : { eligibleItemIds: effective.collectedItemIds, excludedItems: [] };
             const eligibilityInputHashes = Object.fromEntries((correspondence?.facts.inputFiles ?? []).map((item) => [item.path, item.sha256]));
+            const exclusionSummary = summarizeBackendTestExclusions(eligibility.excludedItems);
             const eligibilityFactsPath = path.join(meta.runDir, "contracts", "backend-test-execution-eligibility.json");
             await mkdir(path.dirname(eligibilityFactsPath), { recursive: true });
             await writeFile(eligibilityFactsPath, `${JSON.stringify({
@@ -1021,6 +1058,9 @@ async function executeBackendTestPipeline(input, meta) {
                 excludedItemCount: eligibility.excludedItems.length,
                 eligibleItemIds: eligibility.eligibleItemIds,
                 excludedItems: eligibility.excludedItems,
+                exclusionSummary,
+                pytestSpawned: false,
+                businessTestBodyExecutedCount: 0,
                 inputHashes: eligibilityInputHashes,
             }, null, 2)}\n`, "utf8");
             const eligibilityReportPath = await writeRunReport(meta.runDir, "backend-test-execution-eligibility.md", [
@@ -1033,6 +1073,10 @@ async function executeBackendTestPipeline(input, meta) {
                 `- Collected items: ${effective.collectedItemIds.length}`,
                 `- Eligible items: ${eligibility.eligibleItemIds.length}`,
                 `- Excluded items: ${eligibility.excludedItems.length}`,
+                `- Excluded Cases: ${exclusionSummary.excludedCaseCount}`,
+                `- Exclusion categories: ${Object.entries(exclusionSummary.excludedByReason).map(([category, count]) => `${category}=${count}`).join("; ") || "none"}`,
+                "- pytest spawned: false",
+                "- Business test bodies executed: 0",
                 "",
                 "## Excluded Items",
                 "",
@@ -1061,6 +1105,9 @@ async function executeBackendTestPipeline(input, meta) {
                     executionReadinessStatus: readiness.status,
                     eligibleItemCount: readiness.eligibleItemIds.length,
                     excludedItemCount: readiness.excludedItems.length,
+                    exclusionSummary: readiness.exclusionSummary,
+                    pytestSpawned: readiness.pytestSpawned,
+                    businessTestBodyExecutedCount: readiness.businessTestBodyExecutedCount,
                     factsPath: "contracts/backend-test-pytest-collection-effective.json",
                     readinessPath: "contracts/backend-test-execution-readiness.json",
                     reportPath: artifacts.reportPath,

package/dist/governance/checks.js

@@ -8,6 +8,7 @@ import { buildTaskReadModel } from '../task/read-model.js';
 const SKIP_DIRS = new Set([
     '.git',
     '.harness',
+    '.scratch',
     'node_modules',
     'dist',
     'coverage',

package/dist/shared/pi-context-pressure/checkpoint.js

@@ -0,0 +1,116 @@
+const CHECKPOINT_MAX_BYTES = 12 * 1024;
+function boundText(value, maxChars) {
+    if (typeof value !== "string" || !value.trim())
+        return "";
+    return value.length <= maxChars ? value : `${value.slice(0, maxChars - 1)}…`;
+}
+function asRecord(value) {
+    return value !== null && typeof value === "object" && !Array.isArray(value)
+        ? value
+        : undefined;
+}
+function extractLastUserGoal(messages) {
+    if (!Array.isArray(messages))
+        return "";
+    for (let index = messages.length - 1; index >= 0; index -= 1) {
+        const message = asRecord(messages[index]);
+        if (!message || message.role !== "user")
+            continue;
+        const content = message.content;
+        if (typeof content === "string")
+            return boundText(content, 800);
+        if (Array.isArray(content)) {
+            const texts = content
+                .map((block) => {
+                const rec = asRecord(block);
+                return typeof rec?.text === "string" ? rec.text : "";
+            })
+                .filter(Boolean);
+            if (texts.length > 0)
+                return boundText(texts.join("\n"), 800);
+        }
+    }
+    return "";
+}
+function extractTodos(details) {
+    const record = asRecord(details);
+    const todos = record?.todos ?? record?.items;
+    if (!Array.isArray(todos))
+        return "";
+    const lines = todos
+        .slice(0, 24)
+        .map((item) => {
+        const rec = asRecord(item);
+        const status = typeof rec?.status === "string" ? rec.status : "pending";
+        const content = typeof rec?.content === "string"
+            ? rec.content
+            : typeof rec?.title === "string"
+                ? rec.title
+                : "";
+        return content ? `- [${status}] ${content}` : "";
+    })
+        .filter(Boolean);
+    return boundText(lines.join("\n"), 1200);
+}
+function extractFileOps(fileOps) {
+    const record = asRecord(fileOps);
+    if (!record)
+        return "";
+    const parts = [];
+    for (const key of ["edited", "written", "read", "deleted", "ops"]) {
+        const value = record[key];
+        if (Array.isArray(value)) {
+            parts.push(`${key}: ${value
+                .slice(0, 20)
+                .map((item) => (typeof item === "string" ? item : JSON.stringify(item)))
+                .join(", ")}`);
+        }
+        else if (typeof value === "string" && value) {
+            parts.push(`${key}: ${value}`);
+        }
+    }
+    if (parts.length === 0) {
+        try {
+            return boundText(JSON.stringify(fileOps), 800);
+        }
+        catch {
+            return "";
+        }
+    }
+    return boundText(parts.join("\n"), 800);
+}
+export function buildOverflowCheckpoint(input) {
+    const preparation = input.preparation;
+    const firstKeptEntryId = typeof preparation?.firstKeptEntryId === "string" &&
+        preparation.firstKeptEntryId
+        ? preparation.firstKeptEntryId
+        : undefined;
+    const tokensBefore = typeof preparation?.tokensBefore === "number" &&
+        Number.isFinite(preparation.tokensBefore)
+        ? preparation.tokensBefore
+        : undefined;
+    if (!firstKeptEntryId || tokensBefore === undefined)
+        return undefined;
+    const sections = [
+        "Deterministic overflow checkpoint (no extra summary request).",
+        boundText(preparation?.previousSummary, 2000)
+            ? `Previous summary:\n${boundText(preparation?.previousSummary, 2000)}`
+            : "",
+        extractLastUserGoal(preparation?.messagesToSummarize)
+            ? `Latest user goal:\n${extractLastUserGoal(preparation?.messagesToSummarize)}`
+            : "",
+        extractTodos(input.todos) ? `Open todos:\n${extractTodos(input.todos)}` : "",
+        extractFileOps(preparation?.fileOps)
+            ? `File ops:\n${extractFileOps(preparation?.fileOps)}`
+            : "",
+        typeof input.lastError === "string" && input.lastError
+            ? `Latest error:\n${boundText(input.lastError, 400)}`
+            : "",
+        "Next step: continue the interrupted turn from the kept recent messages. Do not repeat completed file writes.",
+    ].filter(Boolean);
+    let summary = sections.join("\n\n");
+    if (Buffer.byteLength(summary, "utf8") > CHECKPOINT_MAX_BYTES) {
+        summary = `${summary.slice(0, CHECKPOINT_MAX_BYTES - 1)}…`;
+    }
+    return { summary, firstKeptEntryId, tokensBefore };
+}