cc-devflow 4.5.10 → 4.5.12

package/.claude/skills/cc-act/scripts/verify-act-gate.sh

@@ -2,10 +2,6 @@
 
 set -euo pipefail
 
-# ------------------------------------------------------------
-# cc-act: 校验 Check 阶段是否真的闭合
-# ------------------------------------------------------------
-
 usage() {
   cat <<'EOF'
 Usage: verify-act-gate.sh --dir path/to/change
@@ -28,58 +24,22 @@ fi
 
 script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$script_dir/cc-act-common.sh"
-CHANGE_DIR="$(req_act_change_dir "$REQ_DIR")"
-report_card="$(req_act_report_path "$CHANGE_DIR")"
-tasks_file="$(req_act_tasks_path "$CHANGE_DIR")"
-
-[[ -f "$report_card" ]] || { echo "Gate open: missing report-card.json" >&2; exit 1; }
 
-verdict="$(jq -r '.verdict // "unknown"' "$report_card" 2>/dev/null || echo unknown)"
-reroute="$(jq -r '.reroute // "unknown"' "$report_card" 2>/dev/null || echo unknown)"
-spec_sync_ready="$(jq -r '.specSyncReady // false' "$report_card" 2>/dev/null || echo false)"
-evidence_count="$(jq -r '((.evidence // []) + (.claimEvidence // []) + (.quickGates // []) + (.strictGates // [])) | length' "$report_card" 2>/dev/null || echo 0)"
-gap_count="$(jq -r '(.gaps // []) | length' "$report_card" 2>/dev/null || echo 0)"
-review_freshness="$(jq -r '.review.freshness.status // "unknown"' "$report_card" 2>/dev/null || echo unknown)"
-failure_ownership_open="$(jq -r '
-  (.runtime.failureOwnership? // [])
-  | map(select(((.classification? // "") | IN("in-branch", "ambiguous")) and ((.status? // "open") | IN("open", "pending"))))
-  | length
-' "$report_card" 2>/dev/null || echo 0)"
-coverage_status="$(jq -r '.qa.coverageAudit.status // "unknown"' "$report_card" 2>/dev/null || echo unknown)"
-browser_status="$(jq -r '.qa.browserEvidence.status // "unknown"' "$report_card" 2>/dev/null || echo unknown)"
-feedback_loop_status="$(jq -r '.qa.feedbackLoop.status // "skipped"' "$report_card" 2>/dev/null || echo skipped)"
-behavior_evidence_status="$(jq -r '.qa.behaviorEvidence.status // "skipped"' "$report_card" 2>/dev/null || echo skipped)"
+change_dir="$(req_act_change_dir "$REQ_DIR")"
+task_file="$(req_act_tasks_path "$change_dir")"
 
-remaining_tasks="0"
-if [[ -f "$tasks_file" ]]; then
-  remaining_tasks="$(awk '/^- \[ \]/{c++} END{print c+0}' "$tasks_file" 2>/dev/null || echo 0)"
-fi
+[[ -f "$task_file" ]] || { echo "Gate open: missing task.md" >&2; exit 1; }
 
-[[ "$verdict" == "pass" ]] || { echo "Gate open: verdict=$verdict" >&2; exit 1; }
-[[ "$reroute" == "none" ]] || { echo "Gate open: reroute=$reroute" >&2; exit 1; }
-[[ "$spec_sync_ready" == "true" ]] || { echo "Gate open: spec_sync_ready=$spec_sync_ready" >&2; exit 1; }
-[[ "$evidence_count" -gt 0 ]] || { echo "Gate open: evidence is empty" >&2; exit 1; }
-[[ "$gap_count" -eq 0 ]] || { echo "Gate open: gaps=$gap_count" >&2; exit 1; }
-[[ "$review_freshness" == "fresh" || "$review_freshness" == "not-applicable" ]] || { echo "Gate open: review_freshness=$review_freshness" >&2; exit 1; }
-[[ "$failure_ownership_open" -eq 0 ]] || { echo "Gate open: failure_ownership_open=$failure_ownership_open" >&2; exit 1; }
-[[ "$coverage_status" != "blocked" && "$coverage_status" != "fail" && "$coverage_status" != "pending" ]] || { echo "Gate open: coverage_status=$coverage_status" >&2; exit 1; }
-[[ "$browser_status" != "blocked" && "$browser_status" != "fail" && "$browser_status" != "pending" ]] || { echo "Gate open: browser_status=$browser_status" >&2; exit 1; }
-[[ "$feedback_loop_status" != "blocked" && "$feedback_loop_status" != "fail" && "$feedback_loop_status" != "pending" ]] || { echo "Gate open: feedback_loop_status=$feedback_loop_status" >&2; exit 1; }
-[[ "$behavior_evidence_status" != "blocked" && "$behavior_evidence_status" != "fail" && "$behavior_evidence_status" != "pending" ]] || { echo "Gate open: behavior_evidence_status=$behavior_evidence_status" >&2; exit 1; }
+remaining_tasks="$(awk '/^- \[ \]/{c++} END{print c+0}' "$task_file" 2>/dev/null || echo 0)"
 [[ "$remaining_tasks" -eq 0 ]] || { echo "Gate open: remaining_tasks=$remaining_tasks" >&2; exit 1; }
 
+if ! git diff --quiet -- "$task_file" 2>/dev/null; then
+  echo "Gate open: task.md has unstaged or uncommitted edits" >&2
+  exit 1
+fi
+
 cat <<EOF
 GATE=closed
-VERDICT=$verdict
-REROUTE=$reroute
-SPEC_SYNC_READY=$spec_sync_ready
-EVIDENCE_COUNT=$evidence_count
-GAP_COUNT=$gap_count
-REVIEW_FRESHNESS=$review_freshness
-FAILURE_OWNERSHIP_OPEN=$failure_ownership_open
-COVERAGE_STATUS=$coverage_status
-BROWSER_STATUS=$browser_status
-FEEDBACK_LOOP_STATUS=$feedback_loop_status
-BEHAVIOR_EVIDENCE_STATUS=$behavior_evidence_status
+TASK_FILE=$task_file
 REMAINING_TASKS=$remaining_tasks
 EOF

package/.claude/skills/cc-check/CHANGELOG.md

@@ -1,5 +1,29 @@
 # CC-Check Skill Changelog
 
+## v1.12.1 - 2026-05-13
+
+- compress the visible output contract to `Verdict / Evidence / Review / Route`
+- explicitly forbid `review/report-card.json`, JSON, Markdown reports, and other process files
+- keep review and reroute conclusions in the current response instead of durable process documents
+
+## v1.11.4 - 2026-05-13
+
+- require the shared `resolve-cc-devflow.sh` CLI resolver before reading workflow context or review truth
+- block verification when the available CLI cannot prove `query workflow-context` and `review` support
+- forbid replacing missing review truth or report-card generation with simulated adapter output or handwritten artifacts
+
+## v1.11.3 - 2026-05-13
+
+- make `review/report-card.json` script-owned: agents must regenerate it through `scripts/render-report-card.js` and validate it with `scripts/verify-gate.sh`
+- forbid direct manual edits to report-card fields such as timestamp, summary, QA/browser evidence, UAT, claim evidence, or reroute
+- route unsupported evidence shapes back into renderer/schema changes instead of allowing one-off JSON patching
+
+## v1.11.2 - 2026-05-13
+
+- internalize verification operating rules so conflicting proof sources must be resolved explicitly instead of averaged
+- block `pass` when gates are skipped, evidence is stale, ownership is ambiguous, or tests prove implementation shape instead of user intent
+- retarget investigated bug verification to `planning/tasks.md#Root Cause Contract`
+
 ## v1.11.1 - 2026-05-13
 
 - treat `passed`, `done`, `completed`, and `verified` task statuses as complete when rendering the `requirements-met` claim evidence

package/.claude/skills/cc-check/PLAYBOOK.md

@@ -1,285 +1,31 @@
 # CC-Check Playbook
 
-## Iron Law
-
-```text
-NO PASS WITHOUT FRESH EVIDENCE
-```
-
-只要 gate、review、spec truth 里任一层没有本轮新鲜证据，`pass` 就不成立。
-
 ## Visible State Machine
 
-`cc-do -> cc-check -> cc-act`
-
-- Enter from: closed implementation work with fresh runtime evidence.
-- Stay in: `cc-check` while verdict is being rebuilt from current commands and review proof.
-- Exit to: `cc-act` only when the verdict is `pass` with `reroute=none`.
-- Reroute to: `cc-do` for code fixes, `cc-investigate` for root-cause invalidation, or `cc-plan` for design invalidation.
-
-## First Verdict Test
-
-开始前只问 3 件事：
-
-1. 我手里有没有本次新鲜证据？
-2. 这些证据是在证明失败，还是只是在暴露缺件？
-3. 如果现在不能 `pass`，下一步应该回 `cc-do`、`cc-investigate` 还是 `cc-plan`？
-
-先答完这三题，再跑完整 gate；不要一边验证一边发明 verdict。
-
-## Four Verification Phases
-
-1. **Reset Contract**
-   - 重新读取 `planning/design.md` 或 `planning/analysis.md`
-   - 重新读取 `planning/tasks.md`、`planning/task-manifest.json`
-   - 按 `review-findings.json` -> `review-ledger.jsonl` -> legacy `cc-review-report.md` 的顺序读取 review truth
-   - 明确本轮验收对象和 spec delta
-2. **Re-run Reality**
-   - 重新跑 gate
-   - 读取退出码、关键输出、skip 原因
-3. **Check Every Boundary**
-   - runtime gate
-   - task review proof
-   - requirement diff review
-   - claim evidence matrix
-   - QA feedback loop and behavior evidence
-   - QA regression / test-quality proof
-   - QA coverage and browser evidence
-   - review freshness and finding confidence
-   - failure ownership
-   - spec sync readiness
-4. **Freeze Verdict**
-   - 只允许 `pass` / `fail` / `blocked`
-   - 只允许诚实 reroute
-
-## Gate Function
-
-在宣称任何“完成、通过、ready”之前，必须做 4 件事：
-
-1. 找到证明这个结论的命令
-2. 重新运行完整命令
-3. 读取真实输出和退出码
-4. 把证据写进 `report-card.json`
-5. 把任务级 review 与需求级 diff review 分开写清楚
-6. 把每个成功声明映射到 `claimEvidence[]`
-7. 行为变更必须补 `qa` 证据或例外理由
-8. 失败输出必须写入 `runtime.failureOwnership[]`
-9. failure ownership 必须包含 named error、artifact refs 和 rescue action
-10. human UAT 必须 pass、fail、blocked 或带 skip reason；失败不能被测试绿灯覆盖
-
-## Verification Layers
-
-1. Runtime reality
-2. Task review proof
-3. Requirement diff truth
-4. Claim evidence matrix
-5. QA feedback loop and behavior evidence
-6. QA regression and test quality
-7. QA coverage and browser evidence
-8. Review freshness and confidence calibration
-9. Failure ownership
-10. Spec alignment and sync readiness
-11. Human UAT
-12. Named runtime errors and rescue actions
-
-## Claim Evidence Matrix
-
-每个“通过”声明都要回答：这条声明由哪条命令或 artifact 证明？
-
-- `tests-pass`：本轮 test command、exit 0、0 failures
-- `lint-clean` / `typecheck-clean` / `build-succeeds`：对应 gate 的本轮输出
-- `bug-fixed`：原始症状或回归测试通过
-- `regression-test-works`：red -> green 证据，而不是只绿一次
-- `requirements-met`：逐项 plan / manifest checklist
-- `agent-completed`：VCS diff 或 artifact 证明实际变化
-
-缺少必要 claim 的证据时，verdict 至少是 `blocked`。不要把没有证据的 claim 写进 summary。
-
-## Requirement Diff Review
-
-需求级 review 至少分 5 步：
-
-1. `base truth`：确认 base branch、当前 branch、PR 状态。
-2. `plan completion`：逐项核对 tasks / manifest 是否真的由 diff 或 runtime proof 兑现。
-3. `scope drift`：识别多做、少做、做偏。
-4. `critical pass`：检查数据安全、并发、shell、LLM trust boundary、枚举覆盖、静默失败、文档漂移。
-5. `adversarial synthesis`：合并外部 review / codex / subagent /人工 finding，去重并标置信度。
-6. `specialist facets`：按风险记录 testing / security / performance / api-contract / data-migration / design 等审查面；没有覆盖必须写 skip reason。
-7. `freshness`：确认 review 对应当前 head；review 后新增 commit 时不能继续拿旧审查支撑 `pass`。
-
-这些结论进入 `review.diffReview`，不能只写在口头总结里。
-
-每层 review 都要带 `reviewPacket`：`baseSha`、`headSha`、`requirements`、`implemented`、`reviewerContext`。缺少审查范围时，review 不能支撑 `pass`。
-
-review 还要带 `freshness`：`status`、`reviewedCommit`、`currentCommit`、`commitsSinceReview`、`staleReason`。`status=stale` 或缺失 freshness 时，`pass` 不成立。
-
-每条 finding 都要带 `triageStatus`：
-
-- `accepted-fixed`
-- `rejected-with-evidence`
-- `deferred-minor`
-- `clarification-needed`
-
-`critical` / `important` finding 未闭环或仍是 `clarification-needed`，不能进入 `cc-act`。
-
-每条 finding 还要带 `confidenceScore`、`fingerprint`、`displayTier`、`suppressionReason`。低置信 finding 只能作为 warning 或 gap，不能伪装成 blocking fact。
-
-## QA Test Quality
-
-行为变化、bugfix、边界条件、用户可见流程必须补 `qa`：
-
-- `feedbackLoop`：用什么 loop 证明现实，速度、确定性、信号锋利度、复现率如何
-- `behaviorEvidence`：用户边界、expected / actual、复现步骤、稳定性、领域语言
-- `regressionProof`：red command、red failure reason、green command、是否恢复最终状态
-- `testQuality`：是否经公共接口验证真实行为、mock 是否只停在系统边界、是否存在 test-only production API
-- `architectureFollowUps`：没有正确 test seam 时记录 seam / hidden coupling / shallow module 的后续改造
-- `tddException`：纯配置、生成文件、throwaway prototype 等例外和替代验证
-- `coverageAudit`：覆盖率、codepath / user-flow map、缺口、是否需要 e2e / eval、测试质量星级
-- `browserEvidence`：UI / 用户路径变更的 affected routes、截图、console、health score、issues，或明确 skip reason
-
-测试只绿过一次，不能证明 regression test 有效；断言 mock 本身，不能证明真实行为。没有可信反馈环时，`pass` 不成立。
-
-## Failure Ownership
-
-失败要先归属，再下结论：
-
-- `in-branch`：当前分支引入，默认回 `cc-do`
-- `pre-existing`：base branch 也存在，必须有复验证据
-- `environment`：依赖、权限、服务、密钥、平台缺失，通常是 `blocked`
-- `ambiguous`：无法证明归属，默认不能 `pass`
-
-不要把环境红灯、基线红灯、本分支红灯混成一句“测试失败”。
-
-## Verdict
-
-只允许 3 种结论：
-
-- `pass`
-- `fail`
-- `blocked`
-
-速判规则：
-
-1. 命令或 review 明确失败 => `fail`
-2. 条件缺失、证据不足、review 缺件 => `blocked`
-3. 只有当 gate 和 review 都过，才是 `pass`
-
-如果已经证明根因故事失效，别用 `blocked` 糊过去，直接 reroute 到 `cc-investigate`。
-
-## Minimum `report-card.json`
-
-```json
-{
-  "changeId": "REQ-123",
-  "verdict": "pass",
-  "overall": "pass",
-  "summary": "one-line reality",
-  "claimEvidence": [],
-  "runtime": {
-    "status": "pass",
-    "failureOwnership": []
-  },
-  "qa": {
-    "status": "pass",
-    "feedbackLoop": {
-      "status": "pass",
-      "mode": "targeted-test",
-      "commandOrArtifact": "npm test -- src/feature/feature.test.ts",
-      "speed": "fast",
-      "determinism": "high",
-      "signalSharpness": "fails only when the target behavior is absent",
-      "reproductionRate": "1/1",
-      "attempts": [],
-      "blockedReason": ""
-    },
-    "behaviorEvidence": {
-      "status": "pass",
-      "userFacingBoundary": "feature action",
-      "expectedBehavior": "the user-visible behavior succeeds",
-      "actualBehavior": "verified by targeted test",
-      "reproductionSteps": [],
-      "consistency": "deterministic",
-      "domainLanguage": []
-    },
-    "regressionProof": [],
-    "testQuality": [],
-    "coverageAudit": {
-      "status": "pass",
-      "coveragePct": 80,
-      "pathMap": [],
-      "gaps": [],
-      "testsAdded": [],
-      "e2eRequired": false,
-      "evalRequired": false,
-      "qualityStars": "★★"
-    },
-    "browserEvidence": {
-      "status": "skipped",
-      "mode": "not-applicable",
-      "affectedRoutes": [],
-      "screenshots": [],
-      "consoleErrors": [],
-      "healthScore": null,
-      "issues": [],
-      "skipReason": "not a UI or user-path change"
-    },
-    "architectureFollowUps": [],
-    "tddException": null
-  },
-  "quickGates": [],
-  "strictGates": [],
-  "review": {
-    "status": "pass",
-    "summary": "",
-    "details": "",
-    "freshness": { "status": "fresh", "reviewedCommit": "example-head", "currentCommit": "example-head", "commitsSinceReview": 0, "staleReason": "" },
-    "qualityScore": 9,
-    "specialistReviews": [],
-    "taskReviews": { "status": "pass", "required": true, "summary": "", "reviewers": [], "findings": [] },
-    "diffReview": { "status": "skipped", "required": false, "summary": "", "reviewers": [], "findings": [] },
-    "findings": []
-  },
-  "blockingFindings": [],
-  "reroute": "none",
-  "timestamp": "2026-04-15T12:00:00.000Z"
-}
-```
-
-`reroute` 只能是 `none`、`cc-do`、`cc-investigate`、`cc-plan`。
-
-## Reroute Rules
-
-- 实现没做完、测试没过、review 提出明确修复项 => `cc-do`
-- 根因站不住、复现链断了、当前修复只是症状补丁 => `cc-investigate`
-- 范围错了、设计前提失效、当前计划已经不可信 => `cc-plan`
-- 只有 `pass` 才能写 `none`
+`cc-do -> cc-check -> cc-act | cc-do | cc-investigate | cc-plan`
 
-## Red Flags
+## Core Rules
 
-看到下面这些念头就停下 reset：
+1. Fresh evidence or no pass.
+2. Read `task.md`, current diff, and the smallest relevant source files.
+3. Re-run commands; do not inherit green claims from chat.
+4. Do not generate process files.
+5. Separate missing evidence from proven failure.
+6. Commit the completed Check stage when the environment finishes.
 
-- “上次跑过，沿用就行”
-- “测试绿了，review 应该也没问题”
-- “先给 blocked，省得解释 reroute”
-- “manifest proof 以后再补”
-- “spec truth 应该没漂”
+## Verdict Shape
 
-## Local Kit
+- `pass`: all required behavior and quality claims have fresh evidence.
+- `fail`: a command, review, or behavior check proves a defect.
+- `blocked`: required evidence, dependency, auth, input, or environment is unavailable.
 
-- `assets/REPORT_CARD_TEMPLATE.json` 提供最小输出形状
-- `scripts/run-quality-gates.sh` 跑真实命令
-- `scripts/render-report-card.js` 根据 gate 结果、review 结果和 manifest 生成 `report-card.json`
-- `scripts/verify-gate.sh` 检查证据和文件是否齐全
-- `references/review-contract.md` 说明任务级 / 需求级审查责任边界
+## Required Output
 
-## Dry-Run Checklist
+Short response only:
 
-真正落盘前，快速过这 5 问：
+- Verdict: `pass` / `fail` / `blocked`
+- Evidence: commands, exit status, and proven claims
+- Review: clean, findings remain, or not reviewed
+- Route: `cc-act` / `cc-do` / `cc-investigate` / `cc-plan` / `stop`
 
-1. 我写下的 summary 能不能让 reviewer 一眼看懂现在卡在哪？
-2. `blockingFindings` 是不是具体到可行动？
-3. `reroute` 是不是和失败类型一致？
-4. `review.status` 是真实现实，还是我脑补的绿色？
-5. 如果把这份 `report-card.json` 给下一位接手者，他知道接下来去哪吗？
-6. diff review 是否同时覆盖了 plan completion、scope drift、critical pass、doc staleness？
-7. feedback loop 是否真的证明了用户描述的行为，而不是只证明附近代码能跑？
+Do not write process files.