@tea-agent/loop-agent 0.39.0-next.24 → 0.39.0-next.26

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (34) hide show
  1. package/CHANGELOG.md +8 -0
  2. package/README.md +2 -0
  3. package/dist/build-stamp.json +2 -2
  4. package/dist/executors/pi-executor.js +51 -0
  5. package/dist/executors/pi-sdk-executor.js +108 -57
  6. package/dist/executors/shell-executor.js +55 -1
  7. package/dist/worker/console/pi-readiness.js +4 -4
  8. package/dist/worker/observe/static/state.js +2 -2
  9. package/dist/worker/observe/static/views/session-timeline.js +18 -5
  10. package/dist/workflows/dag/backend-test-case-coverage-analysis.js +54 -2
  11. package/dist/workflows/dag/backend-test-scenario-partitions.js +73 -1
  12. package/dist/workflows/dag/frontend-test-case-quality.js +5 -13
  13. package/dist/workflows/dag/frontend-test-environment-probe.js +227 -0
  14. package/dist/workflows/dag/frontend-test-markdown.js +61 -0
  15. package/dist/workflows/dag/frontend-test-result-contract.js +10 -18
  16. package/dist/workflows/dag/frontend-test-standard-scenarios.js +68 -0
  17. package/dist/workflows/dag/init-hybrid.js +10 -18
  18. package/dist/workflows/dag/rerun-plan.js +22 -3
  19. package/dist/workflows/dag/types.js +4 -0
  20. package/dist/workflows/dag/validate.js +2 -0
  21. package/docs/operations/local-development-environment.md +1 -5
  22. package/docs/skills/vetted-skill-registry.md +14 -0
  23. package/docs/templates/README.md +1 -1
  24. package/docs/templates/agent-dag.schema.json +31 -0
  25. package/docs/templates/backend-test-dag.json +2 -2
  26. package/docs/templates/frontend-test-dag.json +8 -10
  27. package/docs/templates/frontend-test-dag.retrieve-context.prompt.md +1 -1
  28. package/package.json +8 -4
  29. package/skills/codebase-scout/SKILL.md +1 -1
  30. package/skills/improve-codebase-architecture/SKILL.md +81 -0
  31. package/skills/improve-codebase-architecture/deepening.md +37 -0
  32. package/skills/improve-codebase-architecture/html-report.md +123 -0
  33. package/skills/improve-codebase-architecture/interface-design.md +44 -0
  34. package/skills/improve-codebase-architecture/language.md +53 -0
@@ -306,6 +306,9 @@ export function computeResetClosure(spec, effectiveFromNodeId) {
306
306
  ...collectReachableDescendants(spec, effectiveFromNodeId),
307
307
  ].sort();
308
308
  }
309
+ function isNeverStartedNodeStatus(status) {
310
+ return status === undefined || status === "SKIPPED" || status === "PENDING";
311
+ }
309
312
  export function assessResetClosureSafety(spec, resetNodeIds, options = {}) {
310
313
  const tasks = taskById(spec);
311
314
  const blockingNodes = [];
@@ -314,9 +317,17 @@ export function assessResetClosureSafety(spec, resetNodeIds, options = {}) {
314
317
  const task = tasks.get(nodeId);
315
318
  if (!task)
316
319
  continue;
320
+ if (options.parentNodes !== undefined &&
321
+ isNeverStartedNodeStatus(options.parentNodes[nodeId]?.status)) {
322
+ continue;
323
+ }
317
324
  if (isWriterTask(task, spec)) {
318
325
  if (nodeId === options.allowedTransportWriterNodeId)
319
326
  continue;
327
+ if (nodeId === options.allowedExclusiveShellFromNodeId &&
328
+ task.executor === "shell") {
329
+ continue;
330
+ }
320
331
  blockingNodes.push({
321
332
  nodeId,
322
333
  reasonCode: "restart-subgraph-contains-writer",
@@ -594,9 +605,17 @@ export async function evaluateDagRerunPlan(input) {
594
605
  blockedReasons.push("ambiguous-skipped-rewrite");
595
606
  }
596
607
  }
597
- const closureSafety = assessResetClosureSafety(input.parentSpec, resetNodeIds, transportWriterRestart && effectiveFromNodeId
598
- ? { allowedTransportWriterNodeId: effectiveFromNodeId }
599
- : {});
608
+ const closureSafety = assessResetClosureSafety(input.parentSpec, resetNodeIds, {
609
+ ...(transportWriterRestart && effectiveFromNodeId
610
+ ? { allowedTransportWriterNodeId: effectiveFromNodeId }
611
+ : {}),
612
+ parentNodes: input.parentState.nodes,
613
+ ...(effectiveFromNodeId &&
614
+ effectiveTask?.executor === "shell" &&
615
+ effectiveRecord?.status === "ERROR"
616
+ ? { allowedExclusiveShellFromNodeId: effectiveFromNodeId }
617
+ : {}),
618
+ });
600
619
  blockingNodes.push(...closureSafety.blockingNodes);
601
620
  for (const code of closureSafety.reasonCodes) {
602
621
  reasonCodes.push(code);
@@ -427,6 +427,8 @@ export const dagBackendTestPipelineSchema = z.enum([
427
427
  "ingest-backend-test-gap",
428
428
  ]);
429
429
  export const dagFrontendBrowserToolPreflightSchema = z.object({}).strict();
430
+ export const dagFrontendTestStandardScenariosSchema = z.object({}).strict();
431
+ export const dagFrontendTestEnvironmentProbeSchema = z.object({}).strict();
430
432
  export const dagFrontendTestEvidenceValidationSchema = z.object({}).strict();
431
433
  export const dagFrontendTestCaseChecklistSchema = z.object({}).strict();
432
434
  export const dagFrontendTestHtmlReportSchema = z.object({}).strict();
@@ -517,6 +519,8 @@ export const dagShellConfigSchema = z.object({
517
519
  frontendReviewContext: dagFrontendReviewContextSchema.optional(),
518
520
  frontendTestCaseChecklist: dagFrontendTestCaseChecklistSchema.optional(),
519
521
  frontendBrowserToolPreflight: dagFrontendBrowserToolPreflightSchema.optional(),
522
+ frontendTestStandardScenarios: dagFrontendTestStandardScenariosSchema.optional(),
523
+ frontendTestEnvironmentProbe: dagFrontendTestEnvironmentProbeSchema.optional(),
520
524
  frontendTestEvidenceValidation: dagFrontendTestEvidenceValidationSchema.optional(),
521
525
  finalWriteSetApprovalGate: dagFinalWriteSetApprovalGateSchema.optional(),
522
526
  frontendTestL5Report: z.object({}).strict().optional(),
@@ -465,6 +465,8 @@ function validateShellTaskConfig(task, spec, issues) {
465
465
  !shell.backendTestPipeline &&
466
466
  !shell.frontendPrewriteGate &&
467
467
  !shell.frontendBrowserToolPreflight &&
468
+ !shell.frontendTestStandardScenarios &&
469
+ !shell.frontendTestEnvironmentProbe &&
468
470
  !shell.frontendVerificationBundle &&
469
471
  !shell.frontendReviewContext &&
470
472
  !shell.frontendTestCaseChecklist &&
@@ -29,11 +29,7 @@ Cursor Cloud VM 当前有两个需要特别注意的环境问题。
29
29
 
30
30
  ### Node.js 版本
31
31
 
32
- VM 默认 `node`(`/exec-daemon/node`)可能是 v22.14.0,但可选依赖 `@earendil-works/pi-ai` / `@earendil-works/pi-coding-agent` 要求 Node.js `>=22.19.0`。版本过低时,`npm install` / `npm ci` 可能跳过这些依赖,随后 `npm run typecheck``npm run build` 会报告:
33
-
34
- ```text
35
- Cannot find module '@earendil-works/...'
36
- ```
32
+ VM 默认 `node`(`/exec-daemon/node`)可能是 v22.14.0,但根包与运行时依赖 `@earendil-works/pi-ai` / `@earendil-works/pi-coding-agent` 都要求 Node.js `>=22.19.0`。版本过低时,npm 默认模式会报告 `EBADENGINE` 警告;启用 `engine-strict` 时,`npm install` / `npm ci` 会直接失败。即使默认模式完成安装,也不应在不受支持的 Node.js 版本上继续执行 typecheck、buildruntime 命令。
37
33
 
38
34
  在 Cursor Cloud 中执行安装或验证前,先切换到已配置的 Node.js 22:
39
35
 
@@ -16,10 +16,22 @@ The entries below are local wrappers or existing local skills. They are not whol
16
16
  | `code-review-core` | local wrapper inspired by code review practice | `skills/code-review-core/SKILL.md` | reviewer | reviewer | No external tools or network by default. |
17
17
  | `codebase-scout` | local wrapper | `skills/codebase-scout/SKILL.md` | scout | scout | Read-only reconnaissance guidance. |
18
18
  | `init-capability-evolution` | local wrapper | `skills/init-capability-evolution/SKILL.md` | supervisor, maintenance | optional | Used only when changes may affect target-project initialization, package surface, or init projection rules. |
19
+ | `frontend-implementation` | local existing (frontend hybrid DAG) | `skills/frontend-implementation/SKILL.md` | frontend plan / contract / scout / mock nodes (spec-level `skillsByRole`) | frontend-implementation DAG only | Required refs node-contracts / design-spec / code-standards; injected by `init-hybrid.ts` spec generation and `src/adapters/loop-agent.ts`; projected via init-surface manifest. Not in `DEFAULT_SKILLS_BY_ROLE`. |
20
+ | `frontend-review` | local existing (frontend hybrid DAG) | `skills/frontend-review/SKILL.md` | reviewer (frontend review nodes, spec-level) | frontend-implementation / repair DAGs | Consumed by `init-hybrid.ts` / `frontend-repair.ts` / `shell-executor.ts`; required ref review-findings (maxChars 2800). |
21
+ | `frontend-verification` | local existing (frontend hybrid DAG) | `skills/frontend-verification/SKILL.md` | verifier / closeout (frontend evidence, spec-level) | frontend DAG closeout | Consumed by `shell-executor.ts` / `frontend-repair.ts` / `frontend-review-context.ts`; required ref verification-checklist. |
22
+ | `frontend-design-review` | local existing (frontend hybrid DAG) | `skills/frontend-design-review/SKILL.md` | design-gate reviewer (before any writer) | frontend-implementation DAG design gate | Injected by `init-hybrid.ts`; runs before the prewrite gate authorizes writers; required ref review-checklist. |
23
+ | `frontend-bounded-implement` | local existing (frontend hybrid DAG) | `skills/frontend-bounded-implement/SKILL.md` | implementer (writer nodes, spec-level) | frontend writers after canonical contract gate | Injected by `init-hybrid.ts`; writers run only after the canonical contract gate accepts and only inside the frozen writeSet (ADR 0015/0016 discipline). |
19
24
  | `grill-with-docs` | local operator skill adapted from domain grilling + ADR/glossary discipline | `skills/grill-with-docs/SKILL.md` | explicit interactive operator only | never a default DAG role | Resolves decisions via `harness.json.governanceRoot`; required refs `context-format.md` / `adr-format.md`; respects writeSet; not in `DEFAULT_SKILLS_BY_ROLE`. |
25
+ | `grill-me` | local interview question engine wrapper | `skills/grill-me/SKILL.md` | interview runtime dependency (not a DAG role) | never a default DAG role | Question engine lives in `src/worker/console/interview/grill-me.ts` (Console interview / operator-actions); intentionally NOT projected by init-surface manifest — runs in this repo's Console only. |
26
+ | `analyze-product-requirements` | local org-internal Product Analysis V4 skill | `skills/analyze-product-requirements/SKILL.md` | source-prepare dependency (not a DAG role) | never a default DAG role | Loaded by `src/task/source-prepare/prepare.ts` during 任务源 preparation; IRON-LAW freeze semantics on `product-analysis.md`; intentionally NOT projected by init-surface manifest. |
20
27
  | `webapp-testing` | local wrapper inspired by frontend/browser testing practice | `skills/webapp-testing/SKILL.md` | verifier, reviewer | optional | Only applies when task explicitly involves browser-rendered behavior; no default Playwright/Semgrep execution. |
21
28
  | `playwright-cli` | repo-local Playwright CLI instructions | `skills/playwright-cli/SKILL.md` | FE-test case executor | FE-test only | Direct browser commands require isolated test environments, per-case evidence paths, and explicit credential/data handling. |
22
29
  | `playwright-cli-case-generator` | adapted from the repo-local playwright CLI case-generator contract | `skills/playwright-cli-case-generator/SKILL.md` | FE-test case generator | FE-test only | Generates Markdown cases and a compact manifest from RAG facts; does not execute browsers, create test code, or invent API/data constraints. |
30
+ | `analyze-product-dependencies` | local org-internal product dependency analysis | `skills/analyze-product-dependencies/SKILL.md` | explicit interactive operator only | never a default DAG role | PRD → code/API mapping analysis; read-only; no runtime references; not projected. |
31
+ | `browser-tools` | local operator skill (CDP automation) | `skills/browser-tools/SKILL.md` | explicit interactive operator only | never a default DAG role | Requires user-visible Chrome with remote debugging (:9222); credential/data handling reviewed per use; not projected. |
32
+ | `local-jacoco-coverage` | local operator orchestration skill | `skills/local-jacoco-coverage/SKILL.md` | explicit interactive operator only | never a default DAG role | Orchestrates backend-test DAGs with a JaCoCo agent — it drives DAGs, so it must never be loaded by one (no recursion); not projected. |
33
+ | `using-git-worktrees` | local wrapper | `skills/using-git-worktrees/SKILL.md` | explicit interactive operator only | never a default DAG role | Workspace isolation guidance only; no runtime references; not projected. |
34
+ | `improve-codebase-architecture` | local operator skill (copied from shared agent platform 2026-08-21) | `skills/improve-codebase-architecture/SKILL.md` | explicit interactive operator only | never a default DAG role | Interactive architecture review producing a temp HTML report; reads CONTEXT.md glossary + `docs/decisions/` ADRs; cross-directory refs `../grill-with-docs/{context,adr}-format.md` are exempt (see Vetting Rules); not projected. |
23
35
 
24
36
  ## Verification placement taxonomy
25
37
 
@@ -42,6 +54,8 @@ Authoring vocabulary for where a check or verification skill should live. Prefer
42
54
  - Default role mappings may reference only repo-local skills that resolve cleanly under `dag validate --strict-skills`.
43
55
  - `agent-worker` is explicitly outside default role mappings. Its trigger description must cover `agent-worker`, Feature Packet, TaskSpec, Task Pool, self-host/candidate and the `loop-agent` routing boundary; `scripts/check-skill-entry.sh` enforces this public entry contract.
44
56
  - `grill-with-docs` is an explicit interactive operator skill only; it must stay outside `DEFAULT_SKILLS_BY_ROLE`.
57
+ - Registry ↔ disk sync: every `skills/*/SKILL.md` in the repo must have a row above. Operator-local skills are recorded with `never a default DAG role` instead of being omitted, so an audit cannot mistake them for drift.
58
+ - `improve-codebase-architecture` is exempt from the "references stay within the skill directory" rule: it is operator-only, never resolved by DAG skill snapshots, and reuses `grill-with-docs` context/ADR formats by relative path.
45
59
  - Optional/security/web skills remain task- or profile-specific until their tool, network, credential, and write behavior is reviewed.
46
60
  - This registry records source inspiration, not license clearance for vendored third-party content. Vendoring requires a separate license/security review.
47
61
  - `SKILL.md` is the entry point. References must be declared in frontmatter and stay within the skill directory.
@@ -30,7 +30,7 @@
30
30
 
31
31
  ## Backend-test
32
32
 
33
- - `backend-test-dag.json` — backend-test DAG 模板;其中 `generate-backend-md-cases-pi` 是唯一允许 `writer-empty-diff` 重试的 writer(总共两次,仅限 post-write-guard attribution 确认的空 diff)。
33
+ - `backend-test-dag.json` — backend-test DAG 模板;其中 `generate-backend-md-cases-pi` 是唯一允许 `writer-empty-diff` 重试的 writer(总共两次,仅限 post-write-guard attribution 确认的空 diff);N2/N5 合同限定 Scenario Partition 必须有源有限域。
34
34
  - `backend-test-dag.classify.prompt.md`、`backend-test-dag.generate-pytest.prompt.md`、`backend-test-dag.review-cases.prompt.md`、`backend-test-dag.retrospect.prompt.md` — 分类、生成、审查和复盘提示。
35
35
  - `backend-test-analysis.schema.json`、`backend-test-execution.schema.json`、`backend-test-result.schema.json`、`backend-test-case-manifest.schema.json` — 分析、执行、结果与用例清单 schema。
36
36
 
@@ -356,6 +356,31 @@
356
356
  "properties": { "schemaVersion": { "const": 1 }, "requireBaseline": { "const": true } }
357
357
  },
358
358
  "frontendTestCaseChecklist": { "type": "object", "additionalProperties": false },
359
+ "frontendBrowserToolPreflight": { "type": "object", "additionalProperties": false },
360
+ "frontendTestStandardScenarios": { "type": "object", "additionalProperties": false },
361
+ "frontendTestEnvironmentProbe": { "type": "object", "additionalProperties": false },
362
+ "frontendTestCaseManifest": {
363
+ "type": "object",
364
+ "additionalProperties": false,
365
+ "properties": {
366
+ "maxCases": { "type": "integer", "minimum": 1 },
367
+ "declaredAcIds": { "type": "array", "items": { "type": "string" } }
368
+ }
369
+ },
370
+ "frontendTestResultFinalize": {
371
+ "type": "object",
372
+ "additionalProperties": false,
373
+ "properties": {
374
+ "declaredAcIds": { "type": "array", "items": { "type": "string" } }
375
+ }
376
+ },
377
+ "frontendTestReports": {
378
+ "type": "object",
379
+ "additionalProperties": false,
380
+ "properties": {
381
+ "l5": { "type": "boolean" }
382
+ }
383
+ },
359
384
  "frontendTestEvidenceValidation": { "type": "object", "additionalProperties": false },
360
385
  "frontendTestHtmlReport": { "type": "object", "additionalProperties": false },
361
386
  "backendTestPipeline": {
@@ -383,6 +408,12 @@
383
408
  { "required": ["frontendVerificationBundle"] },
384
409
  { "required": ["frontendReviewContext"] },
385
410
  { "required": ["frontendTestCaseChecklist"] },
411
+ { "required": ["frontendBrowserToolPreflight"] },
412
+ { "required": ["frontendTestStandardScenarios"] },
413
+ { "required": ["frontendTestEnvironmentProbe"] },
414
+ { "required": ["frontendTestCaseManifest"] },
415
+ { "required": ["frontendTestResultFinalize"] },
416
+ { "required": ["frontendTestReports"] },
386
417
  { "required": ["frontendTestEvidenceValidation"] },
387
418
  { "required": ["frontendTestHtmlReport"] },
388
419
  { "required": ["backendTestPipeline"] }
@@ -145,7 +145,7 @@
145
145
  ]
146
146
  },
147
147
  "outputContract": "Write a Chinese, human-readable testcase/md/README.md as the single Markdown-first entry page with Coverage Scope, Coverage Matrix and a machine-parseable module index. Do not write module case cards here; do not execute pytest or modify production code/config.",
148
- "subtask_prompt": "This is a required file-generation node. After reading the bounded inputs, immediately use write tools to create testcase/md/README.md. Do not end after analysis or planning, and do not return before a non-empty bounded diff exists. Write ONLY testcase/md/README.md in this node; module case cards are written by downstream sharded nodes.\n\nOutput budget protocol (hard, max output <=16K per turn): Never paste full Matrix, case bodies, or source text into assistant chat. README holds only Scope+Matrix+module index; never inline full case bodies. If a Completeness Gate / OUTPUT_LIMIT_RECOVERY retry is injected, continue only listed target paths.\n\nThe first non-empty response line must be exactly IMPLEMENTATION_OUTCOME: changed after the README has been written, or IMPLEMENTATION_OUTCOME: blocked when precise missing evidence prevents safe generation. already-satisfied is not valid for this node.\n\nRead the upstream environment report. Generate the Markdown-first backend test README under testcase/md/README.md.\n\nWrite human-readable content in Simplified Chinese by default. Keep English only for machine-readable IDs and technical literals such as Case/AC/REQ/BR IDs, HTTP methods, paths, field names, enum values, commands, filenames, code symbols and exact source citations.\n\nCreate testcase/md/README.md as the concise entry page: test objective, target/environment, isolation/cleanup, module summary and a linked case index table with Case ID, Chinese case name, scenario type, endpoint and expected status/result. Avoid repeating every case body in README.\n\nBefore the Coverage Matrix, write a mandatory machine-readable `## Coverage Scope` section in README using exactly `| Field | Value |`, immediately followed by the separator row `|---|---|`, and these six unique rows: `Change Classification`, `Coverage Policy`, `Affected Operations`, `Affected Rule Keys`, `Regression Floor`, `Scope Evidence`. Always set `Change Classification` to `new-operation` and `Coverage Policy` to `full-contract`; do NOT reason about whether operations are new or existing. Cover all in-scope rules from the requirement document at full depth; treat the product requirement as the coverage baseline and use API contract evidence (fields/status/enum/boundary/format) to supplement scenario dimensions. Scope is limited to operations/rules the requirement document (or its referenced API contract) explicitly describes; do not expand to unrelated operations that the requirement does not mention. List affected operations exactly as `METHOD /path`, stable rule keys separated by semicolons, and precise source pointers as Scope Evidence.\n\nCoverage depth is full over the in-scope rules: fully cover every documented status, request/response field rule, requiredness, enum, boundary, format, auth and business state of each affected operation the requirement describes, but do not re-test unrelated operations the requirement does not mention. Inspect shared validator/helper/DTO/query builder evidence and expand Affected Operations when the same affected path can affect them; unresolved impact stays visible as GAP/CONFLICT.\n\nBefore writing cases, build the mandatory machine-readable Coverage Matrix inside `testcase/md/README.md` itself. Its section heading line must be exactly `## Coverage Matrix` with no numeric prefix/suffix; never place the canonical Matrix only in a module file. Use this exact header: `| Rule Key | Priority | Source | Endpoint/Field | Dimension | Rule | Required Test Points | Case IDs | Status |`. Every data row must contain exactly 9 pipe-delimited cells and must never omit `Dimension`; use concise dimensions such as requirement, operation, response-status, requiredness, enum, boundary, format, business-state or error. Use only P0/P1/P2 and COVERED/PARTIAL/GAP/CONFLICT. Use stable `TP-<UPPERCASE-HYPHENATED-ID>` test points separated by semicolons.\n\nEach Rule Key must appear in exactly one Matrix row. Preserve each AC/REQ/BR Rule Key as one row; if one product rule spans multiple dimensions, use a concise composite Dimension in that single row instead of duplicating the key. Derive OpenAPI Rule Keys exactly as the deterministic analyzer does: operation token is `<HTTP-METHOD>-<PATH>` with braces removed and every non-alphanumeric run replaced by a hyphen, uppercase (for example POST `/api/resource-notes` → `POST-API-RESOURCE-NOTES`); response statuses use `API-<OPERATION>-RESPONSE-STATUS`; body/parameter fields use `API-<OPERATION>-<FIELD>-REQUIRED|ENUM|MIN-LENGTH|MAX-LENGTH|MINIMUM|MAXIMUM|PATTERN|FORMAT`. Do not invent aliases such as API-CREATE-FIELDS when a deterministic key applies.\n\nCoverage priority is strict inside the declared scope: P0 product requirements/task hard constraints always remain in scope; P1 exhaustively supplements documented operations, fields, business rules, statuses and errors only for Affected Operations; P2 adds bounded protocol robustness only when it is relevant to the change and does not invent product behavior. Coverage percentages describe the declared affected scope, never whole-API completeness unless every operation is explicitly listed. Conflicts or undefined expectations must stay visible as GAP/CONFLICT with precise source pointers, never guessed.\n\nFor uniqueness/lifecycle rules cover absent, active-existing, deleted-existing, create-delete-recreate, restore-then-recreate and documented scope/case-normalization states. For every enum cover every valid value plus bounded invalid equivalence classes (unknown, case variant, whitespace, empty, null/missing and wrong types as applicable). For every length/number rule cover min-1, min, nominal, max and max+1. For format rules cover each allowed class separately plus a valid mixed value, and representative forbidden classes including uppercase, internal/leading/trailing whitespace, tab/newline, unsupported punctuation, slash, emoji or control characters when the source contract supports that expectation.\n\nMandatory module index: include a `## Module Index` table in README that lists every planned module as a canonical relative link of the exact form `[label](./<stem>.md)` plus a `testcase/md/<stem>.md` path cell, so a downstream deterministic manifest can parse the module list. Group by stable business resource/domain, not by CRUD operation: one resource's list/detail/create/update/delete cases belong in one module such as `resource_notes`; split only when a single module would exceed the per-child 16K output protocol, keep the total module count at the smallest safe value, and never exceed 8 modules. Name each module file with a stable lowercase business stem such as `health` or `resource_notes`. Pure hexadecimal/hash-like opaque stems such as `a401606` or `deadbeef` are forbidden. Do not use priority-only stems `p0`, `p1` or `p2`; Priority belongs only in the Coverage Matrix and never defines module files. Do not use Case-ID-like module filenames such as `BE-HEALTH.md` or `BE-NOTES.md`. The relative link target MUST equal the on-disk filename stem the sharded writer will create. For every automatable case, `自动化映射` must name exactly `testcase/test_<module>.py`, where <module> is that Markdown filename without `.md`, lowercased, with non-alphanumeric characters replaced by underscores. Example: `testcase/md/health.md` → `testcase/test_health.py`; `testcase/md/resource_notes.md` → `testcase/test_resource_notes.py`. Never invent a different pytest path in Markdown than the module stem implies.\n\nScenario Partitions (query/filter axes): for every affected GET/list operation, declare one row per enum or classification axis used for filtering (query/path parameters such as type/status/category). Add a mandatory machine-readable `## Scenario Partitions` section after the Coverage Matrix using exactly `| Partition ID | Operation | Axis | Domain | Required Slots | Expected by Slot | Bind Rule |` with the separator row. Partition ID is a stable `SP-<OPERATION>-<AXIS>` token; Domain must copy the legal values verbatim from the bound OpenAPI enum or requirement sentence (never guess); Required Slots writes `each-value` plus `omitted` only when the parameter is optional; Expected by Slot states the documented expectation per slot kind (`domain-value`, `default-behavior`, `empty-result`/`excluded-result` when documented, or `GAP` when the source does not document the complement expectation — never invent 空列表/400). POST/PUT body field-validation enums stay in the Coverage Matrix as `TP-<FIELD>-ENUM-*` and MUST NOT get a Scenario Partition row. Do not create partitions for axes without a documented legal-value domain. Cross-axis combinations stay as ONE nominal Case; never declare a cross-axis cartesian partition.\n\nBefore finalizing README, calculate the predicted collected-item count as `sum(max(1, number of variant Test Points in each Case))`. If the task declares an item budget, the prediction must not exceed it. Reduce excess only by removing duplicate execution and converting same-request checkpoints to assertions; never drop required rules, boundaries, enums, operation-specific inputs, or business states. Record the prediction in README. Use only environment-supported fixtures/targets/isolation, record evidence gaps in Chinese, and do not emit JSON, pytest, or execute commands.\n\n## Derived task contract: 需求.md\n\n# Backend test\n- AC-001 proof\n\n## Authoritative reference index\n\n[]\n\nFor each index entry, use `readPath` for Pi read-tool calls and copy `path` exactly into Markdown Source References. Bound files under .harness/tasks/<taskId>/source/** are read-only inputs: reading them is allowed even though writing .harness/** is forbidden. Never resolve `path` relative to the repository root, search for substitutes, or fall back to docs/** when a bound read fails.\n\nRead only precise indexed references needed for AC/API/field/rule evidence; references remain authoritative over derived text."
148
+ "subtask_prompt": "This is a required file-generation node. After reading the bounded inputs, immediately use write tools to create testcase/md/README.md. Do not end after analysis or planning, and do not return before a non-empty bounded diff exists. Write ONLY testcase/md/README.md in this node; module case cards are written by downstream sharded nodes.\n\nOutput budget protocol (hard, max output <=16K per turn): Never paste full Matrix, case bodies, or source text into assistant chat. README holds only Scope+Matrix+module index; never inline full case bodies. If a Completeness Gate / OUTPUT_LIMIT_RECOVERY retry is injected, continue only listed target paths.\n\nThe first non-empty response line must be exactly IMPLEMENTATION_OUTCOME: changed after the README has been written, or IMPLEMENTATION_OUTCOME: blocked when precise missing evidence prevents safe generation. already-satisfied is not valid for this node.\n\nRead the upstream environment report. Generate the Markdown-first backend test README under testcase/md/README.md.\n\nWrite human-readable content in Simplified Chinese by default. Keep English only for machine-readable IDs and technical literals such as Case/AC/REQ/BR IDs, HTTP methods, paths, field names, enum values, commands, filenames, code symbols and exact source citations.\n\nCreate testcase/md/README.md as the concise entry page: test objective, target/environment, isolation/cleanup, module summary and a linked case index table with Case ID, Chinese case name, scenario type, endpoint and expected status/result. Avoid repeating every case body in README.\n\nBefore the Coverage Matrix, write a mandatory machine-readable `## Coverage Scope` section in README using exactly `| Field | Value |`, immediately followed by the separator row `|---|---|`, and these six unique rows: `Change Classification`, `Coverage Policy`, `Affected Operations`, `Affected Rule Keys`, `Regression Floor`, `Scope Evidence`. Always set `Change Classification` to `new-operation` and `Coverage Policy` to `full-contract`; do NOT reason about whether operations are new or existing. Cover all in-scope rules from the requirement document at full depth; treat the product requirement as the coverage baseline and use API contract evidence (fields/status/enum/boundary/format) to supplement scenario dimensions. Scope is limited to operations/rules the requirement document (or its referenced API contract) explicitly describes; do not expand to unrelated operations that the requirement does not mention. List affected operations exactly as `METHOD /path`, stable rule keys separated by semicolons, and precise source pointers as Scope Evidence.\n\nCoverage depth is full over the in-scope rules: fully cover every documented status, request/response field rule, requiredness, enum, boundary, format, auth and business state of each affected operation the requirement describes, but do not re-test unrelated operations the requirement does not mention. Inspect shared validator/helper/DTO/query builder evidence and expand Affected Operations when the same affected path can affect them; unresolved impact stays visible as GAP/CONFLICT.\n\nBefore writing cases, build the mandatory machine-readable Coverage Matrix inside `testcase/md/README.md` itself. Its section heading line must be exactly `## Coverage Matrix` with no numeric prefix/suffix; never place the canonical Matrix only in a module file. Use this exact header: `| Rule Key | Priority | Source | Endpoint/Field | Dimension | Rule | Required Test Points | Case IDs | Status |`. Every data row must contain exactly 9 pipe-delimited cells and must never omit `Dimension`; use concise dimensions such as requirement, operation, response-status, requiredness, enum, boundary, format, business-state or error. Use only P0/P1/P2 and COVERED/PARTIAL/GAP/CONFLICT. Use stable `TP-<UPPERCASE-HYPHENATED-ID>` test points separated by semicolons.\n\nEach Rule Key must appear in exactly one Matrix row. Preserve each AC/REQ/BR Rule Key as one row; if one product rule spans multiple dimensions, use a concise composite Dimension in that single row instead of duplicating the key. Derive OpenAPI Rule Keys exactly as the deterministic analyzer does: operation token is `<HTTP-METHOD>-<PATH>` with braces removed and every non-alphanumeric run replaced by a hyphen, uppercase (for example POST `/api/resource-notes` → `POST-API-RESOURCE-NOTES`); response statuses use `API-<OPERATION>-RESPONSE-STATUS`; body/parameter fields use `API-<OPERATION>-<FIELD>-REQUIRED|ENUM|MIN-LENGTH|MAX-LENGTH|MINIMUM|MAXIMUM|PATTERN|FORMAT`. Do not invent aliases such as API-CREATE-FIELDS when a deterministic key applies.\n\nCoverage priority is strict inside the declared scope: P0 product requirements/task hard constraints always remain in scope; P1 exhaustively supplements documented operations, fields, business rules, statuses and errors only for Affected Operations; P2 adds bounded protocol robustness only when it is relevant to the change and does not invent product behavior. Coverage percentages describe the declared affected scope, never whole-API completeness unless every operation is explicitly listed. Conflicts or undefined expectations must stay visible as GAP/CONFLICT with precise source pointers, never guessed.\n\nFor uniqueness/lifecycle rules cover absent, active-existing, deleted-existing, create-delete-recreate, restore-then-recreate and documented scope/case-normalization states. For every enum cover every valid value plus bounded invalid equivalence classes (unknown, case variant, whitespace, empty, null/missing and wrong types as applicable). For every length/number rule cover min-1, min, nominal, max and max+1. For format rules cover each allowed class separately plus a valid mixed value, and representative forbidden classes including uppercase, internal/leading/trailing whitespace, tab/newline, unsupported punctuation, slash, emoji or control characters when the source contract supports that expectation.\n\nMandatory module index: include a `## Module Index` table in README that lists every planned module as a canonical relative link of the exact form `[label](./<stem>.md)` plus a `testcase/md/<stem>.md` path cell, so a downstream deterministic manifest can parse the module list. Group by stable business resource/domain, not by CRUD operation: one resource's list/detail/create/update/delete cases belong in one module such as `resource_notes`; split only when a single module would exceed the per-child 16K output protocol, keep the total module count at the smallest safe value, and never exceed 8 modules. Name each module file with a stable lowercase business stem such as `health` or `resource_notes`. Pure hexadecimal/hash-like opaque stems such as `a401606` or `deadbeef` are forbidden. Do not use priority-only stems `p0`, `p1` or `p2`; Priority belongs only in the Coverage Matrix and never defines module files. Do not use Case-ID-like module filenames such as `BE-HEALTH.md` or `BE-NOTES.md`. The relative link target MUST equal the on-disk filename stem the sharded writer will create. For every automatable case, `自动化映射` must name exactly `testcase/test_<module>.py`, where <module> is that Markdown filename without `.md`, lowercased, with non-alphanumeric characters replaced by underscores. Example: `testcase/md/health.md` → `testcase/test_health.py`; `testcase/md/resource_notes.md` → `testcase/test_resource_notes.py`. Never invent a different pytest path in Markdown than the module stem implies.\n\nScenario Partitions (query/filter axes): for every affected GET/list operation, declare one row per enum or classification axis used for filtering (query/path parameters such as type/status/category). Add a mandatory machine-readable `## Scenario Partitions` section after the Coverage Matrix using exactly `| Partition ID | Operation | Axis | Domain | Required Slots | Expected by Slot | Bind Rule |` with the separator row. Partition ID is a stable `SP-<OPERATION>-<AXIS>` token; Domain must copy the legal values verbatim from the bound OpenAPI enum or requirement sentence (never guess); Required Slots writes `each-value` plus `omitted` only when the parameter is optional; Expected by Slot states the documented expectation per slot kind (`domain-value`, `default-behavior`, `empty-result`/`excluded-result` when documented, or `GAP` when the source does not document the complement expectation — never invent 空列表/400). POST/PUT body field-validation enums stay in the Coverage Matrix as `TP-<FIELD>-ENUM-*` and MUST NOT get a Scenario Partition row. Do not create partitions for axes without a documented legal-value domain. Only GET/list query or path parameters whose bound source documents a finite enum or classification set may become a Scenario Partition. Do not create partitions for free-form strings, primary keys, required-or-optional-only parameters, or boundary/format-only axes. If an axis has no finite legal-value domain, do not declare a Partition row and do not invent NOT-IN-SET cases. Cross-axis combinations stay as ONE nominal Case; never declare a cross-axis cartesian partition.\n\nBefore finalizing README, calculate the predicted collected-item count as `sum(max(1, number of variant Test Points in each Case))`. If the task declares an item budget, the prediction must not exceed it. Reduce excess only by removing duplicate execution and converting same-request checkpoints to assertions; never drop required rules, boundaries, enums, operation-specific inputs, or business states. Record the prediction in README. Use only environment-supported fixtures/targets/isolation, record evidence gaps in Chinese, and do not emit JSON, pytest, or execute commands.\n\n## Derived task contract: 需求.md\n\n# Backend test\n- AC-001 proof\n\n## Authoritative reference index\n\n[]\n\nFor each index entry, use `readPath` for Pi read-tool calls and copy `path` exactly into Markdown Source References. Bound files under .harness/tasks/<taskId>/source/** are read-only inputs: reading them is allowed even though writing .harness/** is forbidden. Never resolve `path` relative to the repository root, search for substitutes, or fall back to docs/** when a bound read fails.\n\nRead only precise indexed references needed for AC/API/field/rule evidence; references remain authoritative over derived text."
149
149
  },
150
150
  {
151
151
  "id": "materialize-backend-md-module-manifest-shell",
@@ -274,7 +274,7 @@
274
274
  "type": "implementation-outcome-v1"
275
275
  },
276
276
  "outputContract": "First non-empty line is IMPLEMENTATION_OUTCOME: changed|already-satisfied|blocked. Perform exactly one bounded incremental synchronization of testcase/md/** against all bound source references; preserve valid Cases and report a concise summary.",
277
- "subtask_prompt": "Perform one gap-targeted synchronization, not a full-suite rewrite or stylistic review. Start from explicit bound source IDs/error codes/DTO fields/normative quoted rules and the README Matrix; open and edit only modules that own a missing or conflicting rule. Preserve unrelated valid modules byte-for-byte and avoid optional wording cleanup.\n\nOutput budget protocol: never dump full Matrix/case bodies into assistant chat. Inspect README first, build a concise target list, then read/write only target modules one file per tool call. Do not traverse every module when the Matrix and source token inventory show no gap; return `already-satisfied`. When adding omitted in-scope cases, keep every required section. Do not bulk-delete in-scope cases to save tokens.\n\nFor every variant Test Point, ensure the Markdown scenario intent is machine-checkable and located inside that same Case body/自动化映射, never in a file-level appendix, implementation-details block, or another Case. Use an exact transport target: `场景意图: <TP-ID>; operation=<METHOD /path>; target=<body.field|query.field|path.field|header.field|request>; intent=<empty|missing|null|min-1|min|max|max+1|pattern-invalid|enum-invalid|wrong-type|nominal-operation|custom-literal:V>; bound=<n optional>; example=<optional>; expectedCode=<optional>`. Never use vague targets such as field=resource/health. Keep pytest params aligned to the exact target. For intent=missing/empty/default-omit, pytest may use `_OMIT` or delete the key; for intent=enum-invalid use a concrete invalid enum literal (for example `UNKNOWN_STATUS`), never `_OMIT`/missing-key; for trim/padded samples use `custom-literal:trim` or a real padded string, not a bare token like `filter-active` when the intent is `custom-literal:ACTIVE`.\n\nTreat the requirement document as the coverage baseline; scope is limited to operations/rules it (or its referenced API contract) describes, and API contract evidence supplements scenario dimensions. For every in-scope operation, check applicable lifecycle/uniqueness states (including deleted-existing when in scope), valid enum values, bounded invalid classes, min-1/min/nominal/max/max+1, allowed/forbidden format classes, required/null/missing/wrong-type semantics, status/error codes, auth and state transitions. Inspect shared validator/helper/DTO/query builder evidence and expand Affected Operations when the same affected path can affect them; unresolved impact stays visible as GAP/CONFLICT. Directly add in-scope omissions; reject scope expansion to operations absent from the requirement document; undefined impact remains GAP/CONFLICT rather than invented behavior.\n\nCheck AC completeness/meaning, endpoint, fields/shape, status/error codes, rules, states, documented boundaries/auth, positive/negative coverage, executable steps and assertable results. Require the exact `## Coverage Scope` Field/Value table with the `|---|---|` separator row, a valid classification-policy pair, non-empty Affected Operations/Rule Keys/Scope Evidence, and the classification-specific Regression Floor. Require the exact unnumbered `## Coverage Matrix` heading in `testcase/md/README.md`, exact headers, exactly 9 cells in every data row (including a non-empty Dimension), deterministic OpenAPI Rule Keys for every in-scope affected operation, exactly one Matrix row per Rule Key (merge multi-dimension product rows), and bidirectional Matrix Rule/Test Point ↔ Case bindings. Never describe affected-scope coverage as whole-API completeness. Every explicit AC ID must appear in at least one Case `验收标准`; every explicit in-scope AC/REQ/BR Rule Key cited by a Case must have exactly one Coverage Matrix row, and no Case may cite a source Rule Key omitted from the Matrix. Every Matrix Case ID must share at least one of that row's Required Test Points and the Case must cite that Rule Key. Perform an explicit execution-redundancy review: merge checkpoint-only parameter rows, repeated default/read-back assertions, DELETE status/body/follow-up-read checks, response schema/Content-Type checks, PUT full-update/timestamp checks, repeated list setup and identical null/empty inputs when endpoint, input partition, precondition state and expected outcome are the same. Preserve separate POST/PUT, boundary, enum, wrong-type, role/tenant and distinct business-state variants. Directly repair malformed headings/rows/keys and binding modes rather than merely commenting on them. Reject avoidable English prose, duplicated bilingual wording, repeated boilerplate, oversized unstructured sections, a `### 操作步骤` section that contains only a table without any numbered executable line, vague results such as ‘符合预期’, Case-ID-like module filenames (for example `BE-HEALTH.md`), dropped exact `### 操作步骤`/`### 预期结果` headings, and missing or drifted script/function mapping where it can be derived.\n\nCorrect testcase/md/** directly: add documented omissions, remove unsupported cases, rename module files to stable lowercase stems when needed, normalize every Case ID to hyphen-separated module segments plus exactly three zero-padded digits (`BE-RESOURCE_NOTES-01` → `BE-RESOURCE-NOTES-001`; `BE-RN-011A` must be renumbered or merged) consistently across headings/index/mappings, fix automation mappings so each automatable case points at `testcase/test_<module>.py` derived from that module filename and declares exactly one primary symbol (evidence-only meta cases may keep `脚本/primary symbol=无` with empty variants), assign every Test Point exactly one of `变体测试点`/`场景断言测试点`/`横切证据测试点`, then perform an exact-set check: each Case's `### 测试点` set must equal (not merely contain) the union of those three binding lists; delete stale/legacy aliases and ensure every binding-list Test Point is present, expand every variant parameter row into its own atomic TP ID, make every non-cross-cutting TP Case-specific and owned by exactly one Case, require every primary symbol to start with the canonical Case prefix, ensure every explicit AC ID appears in an applicable Case `验收标准`, merge execution duplicates, improve navigation/tables/Chinese wording, or record gaps in Chinese. Remove every credential/header value, placeholder, fake token and anti-example from Markdown. Sensitive key names may remain only as a plain list; values must be described as runtime-only and omitted, with no colon/value pair or literal example anywhere, including details blocks and explanatory text. Keep Case IDs, AC/REQ/BR IDs, HTTP methods, paths, fields, enum values, filenames, code symbols and source citations as exact machine-readable identifiers; only normalize Case ID separator/sequence formatting as specified above. Recalculate predicted collected items as `sum(max(1, variant count per Case))`; when the task declares a budget, directly merge redundant journeys/reclassify same-request checkpoints until the prediction is within budget, while preserving all required coverage. The validator accepts Chinese and legacy English section aliases; retain or converge to the Chinese human-readable headings without losing structure.\n\nThis is the single Markdown incremental synchronization round. Read every authoritative reference index entry whose role hints include acceptance-criteria, api-contract, data-contract or business-rule; do not rely on the derived PRD as a complete inventory. Preserve every explicit AC/REQ/BR ID, every documented HTTP/business error code, every DTO/JSON field, enum value, boundary, format, nested shape, transaction/state/idempotency/uniqueness/auth/tenant/cross-field rule. For each natural-language normative business rule preserved as required scope, include its exact source sentence without paraphrase together with source path and line/heading anchor so the deterministic ledger can verify quote/hash provenance. Ensure every Case declares exactly `Payload Contract: none` or the three labels `Payload Required Paths`, `Payload Allowed Paths`, and `Payload Enum`; every label must occupy its own machine-readable list line, and a Case must never concatenate target/setup operations or multiple `Payload Contract` tokens onto one line, and explanatory prose/details must not repeat any `Payload Contract:` token; never infer missing keys or enum values. A target GET/DELETE operation with no request body must remain `Payload Contract: none` even when its setup journey performs POST/PUT with a DTO; setup payloads never redefine the target Case payload contract. Add only missing Matrix rows/Test Points/Cases/assertions or repair exact drift; do not rewrite already-valid unrelated modules. Work gap-targeted: inspect source anchors and affected modules first, leave unrelated valid modules byte-stable, and return `already-satisfied` without restating the full suite when no gap exists.\n\nFor affected API fields, use one valid nominal payload plus atomic required/missing/null/empty/wrong-type, every documented enum value plus bounded invalid classes, documented min-1/min/nominal/max/max+1, formats and nested object/array constraints. Do not generate a Cartesian product or invent undocumented constraints. Do not invent a concrete identifier type when the source only requires presence; for a missing-resource 404 path with unspecified identifier syntax/type, synchronize the Case to a create-delete-derived valid identifier journey rather than an arbitrary UUID/text placeholder.\n\nScenario Partitions synchronization: when README declares `## Scenario Partitions`, verify each declared partition's slots are fully materialized as variant Test Points with exact `TP-<Partition ID>-...` IDs (each-value per Domain value, OMITTED only for optional axes, exactly one NOT-IN-SET with intent=enum-invalid). Directly add missing slot rows/Cases; never delete a declared partition or drop its complement slot to force coverage green. When the bound source does not document the complement expectation, keep the slot with GAP expected instead of guessing. Body-field validation enums (`TP-<FIELD>-ENUM-*`) are NOT partitions — do not add partition rows for them.\n\nBefore returning, verify that every explicit source AC/REQ/BR, error code and strong DTO field token appears in README or an applicable module Case. If a fact cannot be safely automated, retain it as GAP/CONFLICT with its exact source pointer instead of dropping it. Return already-satisfied only when no target file needs an incremental edit.\n\nRead only indexed source paths. Do not scan the repository, modify source/**, generate pytest, execute tests, or emit JSON.\n\n## Derived task contract: 需求.md\n\n# Backend test\n- AC-001 proof\n\n## Authoritative reference index\n\n[]\n\nFor each index entry, use `readPath` for Pi read-tool calls and keep `path` as the exact Markdown Source References citation. Bound files under .harness/tasks/<taskId>/source/** are read-only inputs: reading them is allowed even though writing .harness/** is forbidden. Never resolve `path` relative to the repository root, search for substitutes, or fall back to docs/** when a bound read fails.",
277
+ "subtask_prompt": "Perform one gap-targeted synchronization, not a full-suite rewrite or stylistic review. Start from explicit bound source IDs/error codes/DTO fields/normative quoted rules and the README Matrix; open and edit only modules that own a missing or conflicting rule. Preserve unrelated valid modules byte-for-byte and avoid optional wording cleanup.\n\nOutput budget protocol: never dump full Matrix/case bodies into assistant chat. Inspect README first, build a concise target list, then read/write only target modules one file per tool call. Do not traverse every module when the Matrix and source token inventory show no gap; return `already-satisfied`. When adding omitted in-scope cases, keep every required section. Do not bulk-delete in-scope cases to save tokens.\n\nFor every variant Test Point, ensure the Markdown scenario intent is machine-checkable and located inside that same Case body/自动化映射, never in a file-level appendix, implementation-details block, or another Case. Use an exact transport target: `场景意图: <TP-ID>; operation=<METHOD /path>; target=<body.field|query.field|path.field|header.field|request>; intent=<empty|missing|null|min-1|min|max|max+1|pattern-invalid|enum-invalid|wrong-type|nominal-operation|custom-literal:V>; bound=<n optional>; example=<optional>; expectedCode=<optional>`. Never use vague targets such as field=resource/health. Keep pytest params aligned to the exact target. For intent=missing/empty/default-omit, pytest may use `_OMIT` or delete the key; for intent=enum-invalid use a concrete invalid enum literal (for example `UNKNOWN_STATUS`), never `_OMIT`/missing-key; for trim/padded samples use `custom-literal:trim` or a real padded string, not a bare token like `filter-active` when the intent is `custom-literal:ACTIVE`.\n\nTreat the requirement document as the coverage baseline; scope is limited to operations/rules it (or its referenced API contract) describes, and API contract evidence supplements scenario dimensions. For every in-scope operation, check applicable lifecycle/uniqueness states (including deleted-existing when in scope), valid enum values, bounded invalid classes, min-1/min/nominal/max/max+1, allowed/forbidden format classes, required/null/missing/wrong-type semantics, status/error codes, auth and state transitions. Inspect shared validator/helper/DTO/query builder evidence and expand Affected Operations when the same affected path can affect them; unresolved impact stays visible as GAP/CONFLICT. Directly add in-scope omissions; reject scope expansion to operations absent from the requirement document; undefined impact remains GAP/CONFLICT rather than invented behavior.\n\nCheck AC completeness/meaning, endpoint, fields/shape, status/error codes, rules, states, documented boundaries/auth, positive/negative coverage, executable steps and assertable results. Require the exact `## Coverage Scope` Field/Value table with the `|---|---|` separator row, a valid classification-policy pair, non-empty Affected Operations/Rule Keys/Scope Evidence, and the classification-specific Regression Floor. Require the exact unnumbered `## Coverage Matrix` heading in `testcase/md/README.md`, exact headers, exactly 9 cells in every data row (including a non-empty Dimension), deterministic OpenAPI Rule Keys for every in-scope affected operation, exactly one Matrix row per Rule Key (merge multi-dimension product rows), and bidirectional Matrix Rule/Test Point ↔ Case bindings. Never describe affected-scope coverage as whole-API completeness. Every explicit AC ID must appear in at least one Case `验收标准`; every explicit in-scope AC/REQ/BR Rule Key cited by a Case must have exactly one Coverage Matrix row, and no Case may cite a source Rule Key omitted from the Matrix. Every Matrix Case ID must share at least one of that row's Required Test Points and the Case must cite that Rule Key. Perform an explicit execution-redundancy review: merge checkpoint-only parameter rows, repeated default/read-back assertions, DELETE status/body/follow-up-read checks, response schema/Content-Type checks, PUT full-update/timestamp checks, repeated list setup and identical null/empty inputs when endpoint, input partition, precondition state and expected outcome are the same. Preserve separate POST/PUT, boundary, enum, wrong-type, role/tenant and distinct business-state variants. Directly repair malformed headings/rows/keys and binding modes rather than merely commenting on them. Reject avoidable English prose, duplicated bilingual wording, repeated boilerplate, oversized unstructured sections, a `### 操作步骤` section that contains only a table without any numbered executable line, vague results such as ‘符合预期’, Case-ID-like module filenames (for example `BE-HEALTH.md`), dropped exact `### 操作步骤`/`### 预期结果` headings, and missing or drifted script/function mapping where it can be derived.\n\nCorrect testcase/md/** directly: add documented omissions, remove unsupported cases, rename module files to stable lowercase stems when needed, normalize every Case ID to hyphen-separated module segments plus exactly three zero-padded digits (`BE-RESOURCE_NOTES-01` → `BE-RESOURCE-NOTES-001`; `BE-RN-011A` must be renumbered or merged) consistently across headings/index/mappings, fix automation mappings so each automatable case points at `testcase/test_<module>.py` derived from that module filename and declares exactly one primary symbol (evidence-only meta cases may keep `脚本/primary symbol=无` with empty variants), assign every Test Point exactly one of `变体测试点`/`场景断言测试点`/`横切证据测试点`, then perform an exact-set check: each Case's `### 测试点` set must equal (not merely contain) the union of those three binding lists; delete stale/legacy aliases and ensure every binding-list Test Point is present, expand every variant parameter row into its own atomic TP ID, make every non-cross-cutting TP Case-specific and owned by exactly one Case, require every primary symbol to start with the canonical Case prefix, ensure every explicit AC ID appears in an applicable Case `验收标准`, merge execution duplicates, improve navigation/tables/Chinese wording, or record gaps in Chinese. Remove every credential/header value, placeholder, fake token and anti-example from Markdown. Sensitive key names may remain only as a plain list; values must be described as runtime-only and omitted, with no colon/value pair or literal example anywhere, including details blocks and explanatory text. Keep Case IDs, AC/REQ/BR IDs, HTTP methods, paths, fields, enum values, filenames, code symbols and source citations as exact machine-readable identifiers; only normalize Case ID separator/sequence formatting as specified above. Recalculate predicted collected items as `sum(max(1, variant count per Case))`; when the task declares a budget, directly merge redundant journeys/reclassify same-request checkpoints until the prediction is within budget, while preserving all required coverage. The validator accepts Chinese and legacy English section aliases; retain or converge to the Chinese human-readable headings without losing structure.\n\nThis is the single Markdown incremental synchronization round. Read every authoritative reference index entry whose role hints include acceptance-criteria, api-contract, data-contract or business-rule; do not rely on the derived PRD as a complete inventory. Preserve every explicit AC/REQ/BR ID, every documented HTTP/business error code, every DTO/JSON field, enum value, boundary, format, nested shape, transaction/state/idempotency/uniqueness/auth/tenant/cross-field rule. For each natural-language normative business rule preserved as required scope, include its exact source sentence without paraphrase together with source path and line/heading anchor so the deterministic ledger can verify quote/hash provenance. Ensure every Case declares exactly `Payload Contract: none` or the three labels `Payload Required Paths`, `Payload Allowed Paths`, and `Payload Enum`; every label must occupy its own machine-readable list line, and a Case must never concatenate target/setup operations or multiple `Payload Contract` tokens onto one line, and explanatory prose/details must not repeat any `Payload Contract:` token; never infer missing keys or enum values. A target GET/DELETE operation with no request body must remain `Payload Contract: none` even when its setup journey performs POST/PUT with a DTO; setup payloads never redefine the target Case payload contract. Add only missing Matrix rows/Test Points/Cases/assertions or repair exact drift; do not rewrite already-valid unrelated modules. Work gap-targeted: inspect source anchors and affected modules first, leave unrelated valid modules byte-stable, and return `already-satisfied` without restating the full suite when no gap exists.\n\nFor affected API fields, use one valid nominal payload plus atomic required/missing/null/empty/wrong-type, every documented enum value plus bounded invalid classes, documented min-1/min/nominal/max/max+1, formats and nested object/array constraints. Do not generate a Cartesian product or invent undocumented constraints. Do not invent a concrete identifier type when the source only requires presence; for a missing-resource 404 path with unspecified identifier syntax/type, synchronize the Case to a create-delete-derived valid identifier journey rather than an arbitrary UUID/text placeholder.\n\nScenario Partitions synchronization: when README declares `## Scenario Partitions`, verify each declared partition's slots are fully materialized as variant Test Points with exact `TP-<Partition ID>-...` IDs (each-value per Domain value, OMITTED only for optional axes, exactly one NOT-IN-SET with intent=enum-invalid). Directly add missing slot rows/Cases. You may delete an illegal Partition row that has no source-backed finite domain, together with its derived `TP-SP-*` slots/Cases. Never delete a legal source-backed partition or drop its complement slot to force coverage green. When the bound source does not document the complement expectation, keep the slot with GAP expected instead of guessing. Body-field validation enums (`TP-<FIELD>-ENUM-*`) are NOT partitions — do not add partition rows for them.\n\nBefore returning, verify that every explicit source AC/REQ/BR, error code and strong DTO field token appears in README or an applicable module Case. If a fact cannot be safely automated, retain it as GAP/CONFLICT with its exact source pointer instead of dropping it. Return already-satisfied only when no target file needs an incremental edit.\n\nRead only indexed source paths. Do not scan the repository, modify source/**, generate pytest, execute tests, or emit JSON.\n\n## Derived task contract: 需求.md\n\n# Backend test\n- AC-001 proof\n\n## Authoritative reference index\n\n[]\n\nFor each index entry, use `readPath` for Pi read-tool calls and keep `path` as the exact Markdown Source References citation. Bound files under .harness/tasks/<taskId>/source/** are read-only inputs: reading them is allowed even though writing .harness/** is forbidden. Never resolve `path` relative to the repository root, search for substitutes, or fall back to docs/** when a bound read fails.",
278
278
  "retryPolicy": {
279
279
  "maxAttempts": 2,
280
280
  "backoff": "exponential",
@@ -66,12 +66,11 @@
66
66
  ".harness/**",
67
67
  "artifacts/**"
68
68
  ],
69
- "outputContract": "Write testcase/frontend/rag/standard-scenarios.v1.json for generate-time standard scenario coverage.",
70
- "subtask_prompt": "Materialize frontend-test standard scenarios v1 into the RAG package.",
69
+ "outputContract": "Write testcase/frontend/rag/standard-scenarios.v1.json for generate-time standard scenario coverage. Copy docs/templates or harness.json governanceRoot templates (including ai_workspace/loop-agent/templates) when present; otherwise write the minimal STD-FE-SMOKE-ENTRY fallback.",
70
+ "subtask_prompt": "Prepare frontend-test package: materialize standard-scenarios.v1.json into the RAG package from docs/templates, governanceRoot/templates, or the init-projected ai_workspace/loop-agent/templates path.",
71
71
  "shell": {
72
- "commands": [
73
- "node -e \"const fs=require('fs'),path=require('path');const dest='testcase/frontend/rag/standard-scenarios.v1.json';const candidates=[path.join('docs','templates','frontend-test-standard-scenarios.v1.json')];let src=null;for(const c of candidates){if(fs.existsSync(c)){src=c;break;}}fs.mkdirSync(path.dirname(dest),{recursive:true});if(src){fs.copyFileSync(src,dest);process.stdout.write(JSON.stringify({status:'copied',from:src,to:dest}));}else{const minimal={schemaVersion:1,id:'frontend-test-standard-scenarios-v1',scenarios:[{id:'STD-FE-SMOKE-ENTRY',title:'入口可打开',category:'smoke',priority:'must',testPoints:['open'],minCases:1}]};fs.writeFileSync(dest,JSON.stringify(minimal,null,2)+'\\n');process.stdout.write(JSON.stringify({status:'fallback',to:dest}));}"
74
- ],
72
+ "commands": [],
73
+ "frontendTestStandardScenarios": {},
75
74
  "cwd": ".",
76
75
  "timeoutMs": 60000
77
76
  }
@@ -120,12 +119,11 @@
120
119
  ".harness/**",
121
120
  "artifacts/**"
122
121
  ],
123
- "outputContract": "Fail-closed environment preflight: absolute non-production baseUrl + curl HTTP reachability; writes environmentProbe facts; unreachable => blockedReason frontend-base-url-unreachable (node ERROR so generate/map do not run).",
124
- "subtask_prompt": "Parse the concrete baseUrl selected by retrieve-frontend-test-context-pi from testcase/frontend/rag/context.md. Reject production, non-http(s), credentials, query and fragment. Probe with curl (HEAD then GET fallback; connect/max-time; no auth/cookie). 2xx/3xx => reachable and continue. 4xx/5xx/DNS/timeout/connection refused/TLS => blockedReason frontend-base-url-unreachable. Missing curl => blockedReason curl-unavailable. Do not start the app. Runtime hybrid generator embeds the authoritative probe script.",
122
+ "outputContract": "Fail-closed environment preflight: absolute non-production baseUrl + curl HTTP reachability; writes environmentProbe facts; unreachable => blockedReason frontend-base-url-unreachable with errorClass (connection-refused / dns-unresolved / connect-timeout / http-N). Node ERROR so generate/map do not run. Does not start the app.",
123
+ "subtask_prompt": "Parse the concrete baseUrl selected by retrieve-frontend-test-context-pi from testcase/frontend/rag/context.md. Reject production, non-http(s), credentials, query and fragment. Probe with curl (HEAD then GET fallback; connect/max-time; no auth/cookie). 2xx/3xx => reachable and continue. Connection refused records errorClass=connection-refused and tells the operator to start the local app then rerun from this node. 4xx/5xx/DNS/timeout/TLS => blockedReason frontend-base-url-unreachable. Missing curl => blockedReason curl-unavailable. Do not start the app.",
125
124
  "shell": {
126
- "commands": [
127
- "node -e \"console.log('template placeholder: runtime hybrid DAG embeds curl preflight; do not use this static command as source of truth')\""
128
- ],
125
+ "commands": [],
126
+ "frontendTestEnvironmentProbe": {},
129
127
  "cwd": ".",
130
128
  "timeoutMs": 60000
131
129
  }
@@ -17,5 +17,5 @@ Do not claim the environment is reachable until preflight completes. Preflight d
17
17
 
18
18
  ## Standard scenario coverage
19
19
 
20
- - Copy or reference `docs/templates/frontend-test-standard-scenarios.v1.json` into `testcase/frontend/rag/standard-scenarios.v1.json` when available.
20
+ - Copy or reference `docs/templates/frontend-test-standard-scenarios.v1.json`, `harness.json` `governanceRoot`/templates, or the init-projected `ai_workspace/loop-agent/templates/frontend-test-standard-scenarios.v1.json` into `testcase/frontend/rag/standard-scenarios.v1.json` when available.
21
21
  - Add `## Standard scenario coverage` to coverage-map.md with planned/n/a for each must scenario.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@tea-agent/loop-agent",
3
- "version": "0.39.0-next.24",
3
+ "version": "0.39.0-next.26",
4
4
  "type": "module",
5
5
  "bin": {
6
6
  "loop-agent": "bin/loop-agent.js",
@@ -39,6 +39,9 @@
39
39
  "publishConfig": {
40
40
  "access": "public"
41
41
  },
42
+ "engines": {
43
+ "node": ">=22.19.0"
44
+ },
42
45
  "scripts": {
43
46
  "dev": "node --import tsx/esm src/cli.ts",
44
47
  "cursor": "node --import tsx/esm src/cli.ts cursor-prompt",
@@ -64,6 +67,8 @@
64
67
  "verify:tree": "node scripts/pre-push-verify.mjs --verify-current-tree"
65
68
  },
66
69
  "dependencies": {
70
+ "@earendil-works/pi-ai": "0.83.0",
71
+ "@earendil-works/pi-coding-agent": "0.83.0",
67
72
  "commander": "^12.1.0",
68
73
  "katex": "^0.16.47",
69
74
  "mermaid": "^11.16.1",
@@ -71,13 +76,12 @@
71
76
  "rehype-katex": "^7.0.1",
72
77
  "remark-math": "^6.0.0",
73
78
  "semver": "^7.8.5",
79
+ "typebox": "1.3.7",
74
80
  "yaml": "^2.9.0",
75
81
  "zod": "^3.25.76"
76
82
  },
77
83
  "optionalDependencies": {
78
- "@cursor/sdk": "^1.0.7",
79
- "@earendil-works/pi-ai": "0.80.10",
80
- "@earendil-works/pi-coding-agent": "0.80.10"
84
+ "@cursor/sdk": "^1.0.7"
81
85
  },
82
86
  "devDependencies": {
83
87
  "@remixicon/react": "^4.9.0",
@@ -10,7 +10,7 @@ description: 用于只读 scout 节点,在实现前定位现有代码、测试
10
10
  ## 规则
11
11
 
12
12
  - 从 repo 指令、task source 与邻近测试入手。
13
- - 可用时优先 CodeGraph;否则用 `rg` 与聚焦文件阅读。
13
+ - 可用时优先 CodeGraph;否则 Shell 搜索优先 `rg`,按名找文件优先 `fd`,再聚焦阅读文件。
14
14
  - 在提议新抽象前,识别现有 helper 与 ownership 边界。
15
15
  - 只返回事实,不做编辑。
16
16
 
@@ -0,0 +1,81 @@
1
+ ---
2
+ name: improve-codebase-architecture
3
+ description: Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
4
+ ---
5
+
6
+ # Improve Codebase Architecture
7
+
8
+ Surface architectural friction and propose **deepening opportunities** — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
9
+
10
+ ## Glossary
11
+
12
+ Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in [language.md](language.md).
13
+
14
+ - **Module** — anything with an interface and an implementation (function, class, package, slice).
15
+ - **Interface** — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.
16
+ - **Implementation** — the code inside.
17
+ - **Depth** — leverage at the interface: a lot of behaviour behind a small interface. **Deep** = high leverage. **Shallow** = interface nearly as complex as the implementation.
18
+ - **Seam** — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not "boundary.")
19
+ - **Adapter** — a concrete thing satisfying an interface at a seam.
20
+ - **Leverage** — what callers get from depth.
21
+ - **Locality** — what maintainers get from depth: change, bugs, knowledge concentrated in one place.
22
+
23
+ Key principles (see [language.md](language.md) for the full list):
24
+
25
+ - **Deletion test**: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
26
+ - **The interface is the test surface.**
27
+ - **One adapter = hypothetical seam. Two adapters = real seam.**
28
+
29
+ This skill is _informed_ by the project's domain model. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate.
30
+
31
+ ## Process
32
+
33
+ ### 1. Explore
34
+
35
+ Read the project's domain glossary and any ADRs in the area you're touching first.
36
+
37
+ Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
38
+
39
+ - Where does understanding one concept require bouncing between many small modules?
40
+ - Where are modules **shallow** — interface nearly as complex as the implementation?
41
+ - Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)?
42
+ - Where do tightly-coupled modules leak across their seams?
43
+ - Which parts of the codebase are untested, or hard to test through their current interface?
44
+
45
+ Apply the **deletion test** to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
46
+
47
+ ### 2. Present candidates as an HTML report
48
+
49
+ Write a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from `$TMPDIR`, falling back to `/tmp` (or `%TEMP%` on Windows), and write to `<tmpdir>/architecture-review-<timestamp>.html` so each run gets a fresh file. Open it for the user — `xdg-open <path>` on Linux, `open <path>` on macOS, `start <path>` on Windows — and tell them the absolute path.
50
+
51
+ The report uses **Tailwind via CDN** for layout and styling, and **Mermaid via CDN** for diagrams where a graph/flow/sequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS/SVG visuals — use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs/SVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a **before/after visualisation**. Be visual.
52
+
53
+ For each candidate, the same template as before, but rendered as a card:
54
+
55
+ - **Files** — which files/modules are involved
56
+ - **Problem** — why the current architecture is causing friction
57
+ - **Solution** — plain English description of what would change
58
+ - **Benefits** — explained in terms of locality and leverage, and how tests would improve
59
+ - **Before / After diagram** — side-by-side, custom-drawn, illustrating the shallowness and the deepening
60
+ - **Recommendation strength** — one of `Strong`, `Worth exploring`, `Speculative`, rendered as a badge
61
+
62
+ End the report with a **Top recommendation** section: which candidate you'd tackle first and why.
63
+
64
+ **Use CONTEXT.md vocabulary for the domain, and [language.md](language.md) vocabulary for the architecture.** If `CONTEXT.md` defines "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service."
65
+
66
+ **ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: _"contradicts ADR-0007 — but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids.
67
+
68
+ See [html-report.md](html-report.md) for the full HTML scaffold, diagram patterns, and styling guidance.
69
+
70
+ Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"
71
+
72
+ ### 3. Grilling loop
73
+
74
+ Once the user picks a candidate, drop into a grilling conversation. Walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
75
+
76
+ Side effects happen inline as decisions crystallize:
77
+
78
+ - **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md` — same discipline as `/grill-with-docs` (see [context-format.md](../grill-with-docs/context-format.md)). Create the file lazily if it doesn't exist.
79
+ - **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there.
80
+ - **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons ("not worth it right now") and self-evident ones. See [adr-format.md](../grill-with-docs/adr-format.md).
81
+ - **Want to explore alternative interfaces for the deepened module?** See [interface-design.md](interface-design.md).
@@ -0,0 +1,37 @@
1
+ # Deepening
2
+
3
+ How to deepen a cluster of shallow modules safely, given its dependencies. Assumes the vocabulary in [language.md](language.md) — **module**, **interface**, **seam**, **adapter**.
4
+
5
+ ## Dependency categories
6
+
7
+ When assessing a candidate for deepening, classify its dependencies. The category determines how the deepened module is tested across its seam.
8
+
9
+ ### 1. In-process
10
+
11
+ Pure computation, in-memory state, no I/O. Always deepenable — merge the modules and test through the new interface directly. No adapter needed.
12
+
13
+ ### 2. Local-substitutable
14
+
15
+ Dependencies that have local test stand-ins (PGLite for Postgres, in-memory filesystem). Deepenable if the stand-in exists. The deepened module is tested with the stand-in running in the test suite. The seam is internal; no port at the module's external interface.
16
+
17
+ ### 3. Remote but owned (Ports & Adapters)
18
+
19
+ Your own services across a network boundary (microservices, internal APIs). Define a **port** (interface) at the seam. The deep module owns the logic; the transport is injected as an **adapter**. Tests use an in-memory adapter. Production uses an HTTP/gRPC/queue adapter.
20
+
21
+ Recommendation shape: *"Define a port at the seam, implement an HTTP adapter for production and an in-memory adapter for testing, so the logic sits in one deep module even though it's deployed across a network."*
22
+
23
+ ### 4. True external (Mock)
24
+
25
+ Third-party services (Stripe, Twilio, etc.) you don't control. The deepened module takes the external dependency as an injected port; tests provide a mock adapter.
26
+
27
+ ## Seam discipline
28
+
29
+ - **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a port unless at least two adapters are justified (typically production + test). A single-adapter seam is just indirection.
30
+ - **Internal seams vs external seams.** A deep module can have internal seams (private to its implementation, used by its own tests) as well as the external seam at its interface. Don't expose internal seams through the interface just because tests use them.
31
+
32
+ ## Testing strategy: replace, don't layer
33
+
34
+ - Old unit tests on shallow modules become waste once tests at the deepened module's interface exist — delete them.
35
+ - Write new tests at the deepened module's interface. The **interface is the test surface**.
36
+ - Tests assert on observable outcomes through the interface, not internal state.
37
+ - Tests should survive internal refactors — they describe behaviour, not implementation. If a test has to change when the implementation changes, it's testing past the interface.