@tea-agent/loop-agent 0.16.1 → 0.16.3

package/docs/templates/backend-test-dag.review-cases.prompt.md

@@ -2,7 +2,7 @@
 
 ## Purpose
 
-Use this prompt for a read-only **backend test case review** node: `executor: "pi"`, `role: "reviewer"`, `writePolicy: "read-only"`. The reviewer audits generated backend functional test cases for completeness, format compliance, and traceability to source requirements. Downstream `generate-backend-pytest-pi` depends on a `VERDICT: pass` to proceed.
+Use this prompt for a read-only **backend test case review** node: `executor: "pi"`, `role: "reviewer"`, `writePolicy: "read-only"`. The reviewer audits generated backend functional test cases for completeness, format compliance, and traceability to source requirements. A first review may return `request-revision` to drive a single `revise-backend-cases-pi` pass; **final** review (`review-backend-cases-final-pi`) must emit `VERDICT: pass` before `generate-backend-pytest-pi`.
 
 Do **not** create `executor: reviewer`. Reviewer is a **role** on `executor: pi`.
 
@@ -56,7 +56,9 @@ Do NOT re-read source documents. Use the validated analysis artifact, case manif
 | **Boundary conditions** | Edge cases (empty input, max length, edge values) | Important |
 | **State transitions** | Illegal state changes covered | Important |
 | **Requirement traceability** | Each acceptance criterion (AC-xxx) maps to at least one test case ID (manifest coverageSummary or evidenceGaps) | Critical |
-| **Manifest consistency** | Markdown cases align with Case Manifest v1 caseId/acIds | Critical |
+| **Manifest consistency** | Markdown case bodies **and** any AC matrix list the **same full** `BE-*` ids as Case Manifest v1 `caseId`→`acIds`. Never claim "all cases" / "全部用例" cover an AC unless every case maps that AC. | Critical |
+| **Planned automation** | Missing `test_*.py` before generate-pytest is **Informational only**, not Critical | Informational |
+| **Out-of-scope ACs** | Flyway / frontend e2e / `mvn test` etc. already in manifest `evidenceGaps` must not be treated as uncovered Critical | Informational |
 | **Case structure** | Each case has: ID, Title, Precondition, Steps, Expected Result | Important |
 | **No duplicate IDs** | All test case IDs are unique across files | Critical |
 
@@ -77,7 +79,11 @@ Do NOT re-read source documents. Use the validated analysis artifact, case manif
 
 ### Output Shape (after verdict line)
 
-1. **Coverage Assessment** — table mapping each AC to covering test case IDs (or "uncovered").
+1. **Coverage Assessment** — table mapping each AC to covering **full** test case IDs (or "uncovered" / gap).
 2. **Findings** — bullet list tagged `Critical`, `Important`, or `Informational`.
 3. **Statistics** — total case count, positive/negative/boundary breakdown, module distribution.
-4. **Required revisions** (only when `request-revision`) — numbered items for the upstream generator to fix.
+4. **Required revisions** (only when `request-revision` on the **first** review) — numbered, concrete MD edits for `revise-backend-cases-pi` (fix matrices, acIds, full BE-* ids).
+
+### Final review note
+
+When this prompt is used for `review-backend-cases-final-pi` after revision, still use the same checklist. Remaining Critical issues must yield `request-revision` (final gate will stop the DAG). Do not pass with unresolved MD↔manifest AC mismatches.

package/docs/templates/backend-test-execution.schema.json

@@ -69,7 +69,12 @@
         "additionalProperties": false,
         "required": ["path", "description"],
         "properties": {
-          "path": { "type": "string", "minLength": 1 },
+          "path": {
+            "type": "string",
+            "minLength": 1,
+            "pattern": "^/(?!/)(?!.*(?:^|/)\\.{1,2}(?:/|$))(?!.*//)(?!.*\\\\)[^?#]*$",
+            "description": "HTTP URL path on the target service for readiness probes (e.g. /api/health). Not a repository file path; must start with one /, use POSIX separators, and must not include duplicate slashes, dot segments, query, fragment, or scheme. Runtime trims surrounding whitespace before validating and materializing the normalized path."
+          },
           "description": { "type": "string", "minLength": 1 }
         }
       }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tea-agent/loop-agent",
-  "version": "0.16.1",
+  "version": "0.16.3",
   "type": "module",
   "bin": {
     "loop-agent": "bin/loop-agent.js",

package/skills/frontend-review/SKILL.md

@@ -12,8 +12,12 @@ references:
 Use for `frontend-review-pi`; read the findings guide first. Required inputs are
 original task/reference material, contract/constraints, Mock assessment, original and
 revised/confirmed plan, final design verdict, implementation summary, actual diff,
-and static/behavior/optional Mock shell evidence. Missing actual diff or required
-evidence forces revision; never infer it from a summary.
+and static/behavior/optional Mock shell evidence. The actual diff is the run-owned
+`frontend-worktree-diff-shell` artifacts: `contracts/frontend-worktree-diff.json` and
+`artifacts/diff_patch.patch` under the current DAG run directory. When those artifacts
+exist, treat them as the authoritative actual diff—do not request revision solely for
+"missing diff". Only force revision for a missing actual diff when both artifacts are
+absent; never invent a diff from an implementation summary alone.
 
 ## Verdict Contract
 

package/skills/loop-agent/references/hybrid-dag.md

@@ -18,7 +18,10 @@
 
 前端专用链在 `frontend-scout-pi` 后加入只读 `frontend-mock-assess-pi` 和确定性 contract gate，根据接口契约、后端就绪度、生成期能力 seed 与固化验证入口选择 `native|browser-intercept|request-adapter|not-needed|blocked`。策略直接传给 plan、两阶段 design review、唯一 writer、实现 review 和 closeout；真实请求保持默认，缺少契约、生产隔离、注释真实请求或显式 required 合同不完整时 gate 阻塞。可选 `frontendMock` 配置声明 `auto|required|disabled`、既有服务目录与专项命令；默认 `auto` 下没有已确认 Mock 能力时跳过 Mock 继续实现并保留真实联调缺口，不安全或不完整的显式 required 合同只生成无 writer 的评估链，有可信命令时才增加 `frontend-mock-verify-shell`。Mock-backed 证据只证明前端状态；跳过 Mock 且未调用后端时 closeout 报告 `Frontend status: locally-validated` 与 `Real integration: pending`。
 
-显式专用 `taskKind` 保持兼容并优先于任务源分类，也不扩充 governance profile：`frontend-implementation` 显式选择前端实现 DAG，`frontend-test` 选择 FE-test RAG DAG，`backend-test` 选择后端测试 DAG，`knowledge-sync` 选择 Feature 测试知识回写 DAG，`knowledge-graph-bootstrap` 选择业务知识图谱开荒/增量 DAG。后端测试链为 `analyze-inputs-pi → backend-test-analysis-contract-shell → backend-test-environment-scout-pi → backend-test-execution-contract-shell → generate-backend-functional-cases-pi → emit-backend-case-manifest-pi → backend-test-case-manifest-shell → review-backend-cases-pi → review-backend-cases-gate-shell → generate-backend-pytest-pi → backend-test-traceability-gate-shell → execute-backend-pytest-shell → parse-backend-test-result-shell → classify-backend-test-result-pi → test-retrospect-pi → backend-test-outcome-gate-shell`。analysis/execution/case-manifest gate 写入 run-owned contracts；parse materialize Backend Test Result v1（`contracts/backend-test-result.json`）。Case Manifest 确定性校验 AC→case 覆盖；traceability gate 校验 generated file/symbol。execute 在非空 JUnit 下将 pytest exit 0/1 视为节点成功以便 always-run retrospect；`backend-test-outcome-gate-shell` 以 result.outcome 收口；retrospect 使用 manifest coverageSummary + Result v1，不得自造 coverage%。`evidenceGaps`、未知 framework、secret 值、路径穿越或 preflight 失败时后续 writer/execute 不启动。`knowledge-sync` 链必须绑定 `featureId`；图谱运维公共入口是 `loop-agent knowledge query|graph-init|graph-materialize|graph-promote|graph-incremental-prepare`。治理等级仍由既有 `minimal|standard|reviewed|supervised` 规则推断。
+
+> Backend-test vNext：Analysis v2 明确 responseBody shape、ordering、field comparison/precision 与 sourceRefs，并兼容归一化 v1；pytest 生成后 traceability 会按真实 symbol 更新 generated Manifest 和 global/in-scope/cross-domain coverage，随后执行结构化语义 review，最多一次 testcase-only revision，final pass 后才运行 initial pytest。Observe snapshot 投影 initial/classification/repair/final/effective facts。
+
+显式专用 `taskKind` 保持兼容并优先于任务源分类。`backend-test` 选择固定 **24 个真实顶层节点**的后端测试 DAG：intake 双合同、cases+manifest、单次 case revision、pytest 生成与 semantic review、单次 semantic revision、initial execute+parse、classification+eligibility、单次 TestBug repair、final/effective Result、retrospective 和 outcome gate。三条可选分支由 fail-closed `runIf` 控制，不通过动态子节点隐藏数量；所有原有 contracts/JUnit/Result/traceability/repair safety artifacts 继续保留。`knowledge-sync` 与 `knowledge-graph-bootstrap` 继续通过各自显式 taskKind 选择知识回写/图谱开荒 DAG。治理等级仍由 `minimal|standard|reviewed|supervised` 推断。
 
 ### DAG workflow 层级