cc-devflow 4.5.10 → 4.5.12

package/.claude/skills/cc-investigate/assets/TASKS_TEMPLATE.md

@@ -1,29 +1,17 @@
-# TASKS
+# task.md
 
-## Investigation Meta
+## Plan Meta
 
-- Requirement version:
-- Analysis version:
-- Investigate skill version:
+- CC-Investigate skill version:
 - Work branch:
 - Output language:
-- Source bug / incident:
-- Roadmap sync status:
-- Change meta: `change-meta.json`
-
-## Progressive Disclosure Index
-
-- Default read: Investigation Meta, Root Cause Contract, Execution Handoff, current task block.
-- Runtime reset: run `cc-devflow query workflow-context --change <changeId> --change-key <changeKey> --cwd <repo-root> --data-only --no-trace --compact` before `cc-do`, `cc-check`, or `cc-act`; use `packetOnly` plus `mustNotForget` first, verify `sourceHashes`, open `defaultOpen` refs only when needed, and reserve `deepOpen` for matching `openWhen.conditions`.
-- Open for root-cause doubt: `planning/tasks.md#Root Cause Contract` Project Postmortem Recall, Feedback Loop, Evidence Chain, Boundary Probe Matrix.
-- Open for scheduling: `planning/task-manifest.json`, dependencies, touched files.
-- Open for audit/recovery: Git state, CLI logs, report-card findings, Workflow Forensics.
 
 ## Root Cause Contract
 
 Change:
 Mode: investigation
-Approval:
+Profile: tiny | standard | deep
+Diagnosis:
 
 Symptom:
 -
@@ -31,98 +19,63 @@ Symptom:
 Reproduction:
 -
 
-Feedback Loop:
+Expected:
 -
 
-Root Cause Proof Ladder:
-- Symptom site:
-- First bad state:
-- Violated contract:
-- Original trigger:
-- Counterfactual proof:
-- Escape reason:
+Actual:
+-
 
-Confirmed Root Cause:
+Root Cause:
 -
 
-Frozen Repair Boundary:
-- Allowed files:
-- Forbidden files:
-- Blast radius:
+Evidence Chain:
+-
+
+Repair Boundary:
+-
 
 Verification:
 -
 
+Prevention:
+-
+
 Risk / Escalate If:
 -
 
-> This is the default human-authored investigation contract. Do not create
-> `planning/analysis.md` for new investigations unless the user explicitly
-> requests a legacy artifact or a migration requires preserving one.
-
-## Execution Handoff
-
-- Canonical contract: `planning/tasks.md#Root Cause Contract`
-- Canonical change meta: `change-meta.json`
-- Execution mode: `single-path` | `parallel-ready`
-- Confirmed root cause:
-- Root-cause hypothesis:
-- Root Cause Proof Ladder:
-- First bad state:
-- Original trigger:
-- Counterfactual proof:
-- Feedback loop:
-- Symptom match evidence:
-- Frozen repair boundary:
-- Boundary probes:
-- Backward trace:
-- Reference comparison:
-- Project postmortem recall:
-- Allowed files:
-- Forbidden files:
-- Blast radius:
-- Capability specs:
-- Read first:
-- Commands to trust:
-- Do not re-decide:
-- Parallel boundaries:
-- Correct test seam:
-- Evidence request if blocked:
-- Do not repair symptom site unless analysis proves it is the original trigger:
-
-## Phase 1: Reproduce And Probe Guard
-
-- [ ] T001 [TEST] Capture the failing behavior as a stable reproduction (dependsOn:none) `path/to/test`
-  Goal: 让 bug 先变成一个快、准、可复跑且匹配用户症状的失败事实。
-  Files: `path/to/test`
-  Read first: `analysis.md`, `tasks.md`
-  Project postmortem search: `rg -n "<symptom|test seam|module|model-risk>" devflow/postmortems` or record `no-project-postmortems-yet`
-  Verification: `npm test -- path/to/test`
-  Evidence: failing output or reproducible log + symptom match evidence
-  Correct seam: test must exercise the real trigger chain through a public interface
-  Root cause proof: must expose or preserve evidence for first bad state and original trigger
-  Ready when: feedback loop 已稳定，analysis 已记录必要的 boundary / trace / comparison / root-cause-ladder evidence
+## Execution Protocol
+
+Codex / ClaudeCode must treat this `task.md` as the only repair contract.
 
-## Phase 2: Repair
+- CLI resolver: all workflow commands must run through `.claude/skills/cc-dev/scripts/resolve-cc-devflow.sh` or `.codex/skills/cc-dev/scripts/resolve-cc-devflow.sh`; if it cannot prove `query workflow-context` and `next-change-key`, stop blocked.
+- Do not generate process files beyond this `task.md`.
+- Complete tasks with `scripts/mark-task-complete.sh --tasks devflow/changes/<change-key>/task.md --task <task-id>`.
+- Stage commit rule: when PDCA or IDCA finishes in the current environment, commit the completed stage to Git.
 
-- [ ] T002 [IMPL] Apply the minimal root-cause fix (dependsOn:T001) `path/to/file`
-  Goal: 只修已确认根因，不扩成重写。
+## Phase 1: Repair
+
+- [ ] T001 [TEST] Capture the confirmed failure (dependsOn:none) `path/to/test`
+  Goal: 证明 Root Cause Contract 的失败链在当前代码中可复现。
+  Root cause proof: reference the Root Cause Contract fields above.
+  Do not re-decide: first bad state, original trigger, repair boundary.
+  TDD phase: red
+  Files: `path/to/test`
+  Read first: `task.md`
+  Verification: `npm test -- path/to/test`
+  Evidence: failing output
+  Completion: after failing evidence exists, run `bash "$SCRIPT_ROOT/mark-task-complete.sh" --tasks devflow/changes/<change-key>/task.md --task T001`.
+  Public verification path: public interface / caller flow / CLI / API / UI / trace replay / harness.
+  Ready when: reproduction path is available.
+
+- [ ] T002 [IMPL] Repair the first bad state (dependsOn:T001) `path/to/file`
+  Goal: 用最小代码修复已证明的根因。
+  Root cause proof: do not repair symptom site unless Root Cause Contract proves it is the original trigger.
+  Do not re-decide: repair boundary, test seam, forbidden files.
+  TDD phase: green
   Files: `path/to/file`
-  Read first: `analysis.md`, `path/to/test`
-  Project postmortem search: `rg -n "<root cause|module|failure-class|model-risk>" devflow/postmortems` or record `no-project-postmortems-yet`
+  Read first: `task.md`, `path/to/test`
   Verification: `npm test -- path/to/test`
   Evidence: passing output + Git diff
-  Do not re-decide: root cause, first bad state, original trigger, allowed files, forbidden files
-  Ready when: T001 已证明同一个用户症状存在，analysis 已证明根因源头和 counterfactual proof
-
-## Phase 3: Verify
-
-- [ ] T003 Run checks and collect fresh evidence (dependsOn:T002) `command or file`
-  Goal: 为 `cc-check` 准备新鲜证据。
-  Files: `command or file`
-  Read first: `tasks.md`, `task-manifest.json`
-  Project postmortem search: `rg -n "<verification|release|tooling|model-risk>" devflow/postmortems` or record `no-project-postmortems-yet`
-  Verification: `npm test && npm run lint`
-  Evidence: gate output
-  Root cause proof: verification must prove the first bad state no longer forms, not only that the symptom disappeared
-  Ready when: repair task 已收口
+  Completion: after green evidence exists, run `bash "$SCRIPT_ROOT/mark-task-complete.sh" --tasks devflow/changes/<change-key>/task.md --task T002`.
+  Public verification path: same as T001.
+  Ready when: T001 has the expected failing evidence.

package/.claude/skills/cc-investigate/references/investigation-contract.md

@@ -2,235 +2,32 @@
 
 ## Iron Law
 
-- 没有根因，不准修 bug。
-- 没有 frozen root-cause contract，不准生成 repair task。
+- No root cause, no repair.
+- No frozen `task.md#Root Cause Contract`, no repair task.
 
 ## Minimum Evidence
 
-每次调查至少留下这些事实：
-
 - symptom
 - reproduction path
-- feedback loop contract
-- symptom match evidence
 - expected vs actual
 - code path
 - recent change signal
-- prior investigation signal
-- boundary probe matrix, when the failure crosses components
-- backward trace chain, when the error appears below the original trigger
-- root cause proof ladder: symptom site, first bad state, violated contract, original trigger, counterfactual proof, escape reason
-- reference comparison, when a similar working path exists
-- diagnostic instrumentation plan, when probes are needed
-- pattern analysis
-- ranked candidate hypotheses
-- root-cause hypothesis
-- falsification method
-- confirmed root cause
-- correct test seam
-- root cause class
+- prior postmortem signal
+- first bad state
+- violated contract
+- original trigger
+- counterfactual proof
+- escape reason
 - repair boundary
-- blast radius
-- roadmap sync status
+- verification command
 
 ## Output Shape
 
-- `planning/tasks.md#Root Cause Contract` 是人类真相源
-- `planning/tasks.md` 的 task blocks 是修复 handoff
-- `planning/task-manifest.json` 是执行真相源
-- `change-meta.json` 必须记录 roadmap sync status、spec diagnosis 和 no-op reason / updated files
-
-## Root-Cause Hypothesis
-
-每条假设都必须可证伪：
-
-- `candidateRank`：候选假设排序，避免第一直觉锚定
-- `hypothesis`：具体说明什么坏了，为什么会导致症状
-- `evidenceFor`
-- `evidenceAgainst`
-- `falsificationMethod`
-- `expectedObservation`
-- `actualObservation`
-- `status`：`pending` / `confirmed` / `rejected` / `needs-more-evidence`
-
-只有 `confirmed` 假设可以进入 Root Cause。
-
-## Root Cause Proof Ladder
-
-confirmed root cause 必须证明：
-
-- `symptomSite`：用户实际看到的失败点
-- `firstBadState`：状态第一次变坏的位置和证据
-- `violatedContract`：被破坏的契约、invariant、schema、协议或时序条件
-- `originalTrigger`：制造 first bad state 的动作、事件、diff、配置或外部响应
-- `counterfactualProof`：恢复契约、替换输入、回滚 diff 或断言边界后的实际观察
-- `escapeReason`：为什么测试、类型、review、监控或 artifact gate 没挡住
-
-缺 `firstBadState`、`originalTrigger` 或 `counterfactualProof` 时，根因状态只能是 `needs-more-evidence`；不允许生成 repair task。
-
-## Feedback Loop Contract
-
-调查必须先构造一个可信 pass/fail loop：
-
-- `loopType`: failing-test / http-script / cli-fixture / browser-script / trace-replay / throwaway-harness / property-fuzz / bisect / differential / hitl
-- `commandOrDriver`
-- `expectedFailingSignal`
-- `actualFailingSignal`
-- `symptomMatchEvidence`
-- `runtime`
-- `determinism`
-- `failureRate`
-- `sharpeningPlan`
-
-loop 必须复现用户报告的同一失败。无法构造 loop 时，只能进入 `Evidence Request`，不能冻结根因。
-
-## Pattern Analysis
-
-调查必须显式选择或排除常见模式：
-
-- race condition
-- null propagation
-- state corruption
-- integration failure
-- configuration drift
-- stale cache
-- resource leak
-- performance regression
-- trust boundary drift
-- timing guess / flaky wait
-
-模式分析只是检索索引，不是 root cause。
-
-## Boundary Probe Matrix
-
-多组件链路必须记录每个边界的事实：
-
-- `componentBoundary`
-- `inputObserved`
-- `outputObserved`
-- `configEnvObserved`
-- `stateObserved`
-- `verdict`: `pass` / `fail` / `unknown`
-
-第一个失败边界决定下一轮调查收缩点；多个边界同时失败时，优先追共同上游。
-
-## Backward Trace Chain
-
-深层堆栈或坏值来源不明时，必须追到源头：
-
-- immediate failure site
-- direct caller
-- caller chain
-- bad value origin
-- original trigger
-- why symptom-site fix is rejected
-
-找不到 original trigger 时，不能冻结根因。
-
-## Reference Comparison
-
-有相似可用实现时，必须记录：
-
-- similar working example
-- broken path
-- differences found
-- differences accepted as hypothesis
-- differences ruled out
-
-不能用“差不多”跳过差异。
-
-## Diagnostic Instrumentation
-
-临时探针必须回答一个明确问题：
-
-- probe tag
-- probe location
-- question answered
-- command to run
-- expected signal
-- actual signal
-- cleanup requirement
-
-探针不是修复。handoff 必须说明删除、保留为正式日志，或转成测试断言。
-
-debug 日志必须带唯一前缀，例如 `[DEBUG-FIX123-a4f2]`，确保 cleanup 可以用 grep 验证。
-
-## Correct Test Seam
-
-修复 handoff 必须记录回归测试是否覆盖真实触发链：
-
-- `testSeam`
-- `publicInterfaceExercised`
-- `realTriggerChainCoverage`
-- `whyShallowTestRejected`
-- `ifNoCorrectSeam`
-
-没有正确 seam 时，必须把它记录为架构事实，并保留原始 feedback loop 作为修复验证。
-
-## Domain And Decision Context
-
-调查前先读 cc-devflow 原生上下文：`devflow/specs/INDEX.md`、相关 capability specs、roadmap/backlog handoff、历史 `planning/design.md` / `planning/analysis.md`、`change-meta.json`。
-
-- 输出中的领域概念、假设名、测试名使用项目既有词汇
-- 如果根因或修复方向违反 capability spec、roadmap decision 或历史 design decision，必须显式记录冲突和理由
-- 缺失领域词汇是调查信号，不要临时发明同义词掩盖契约缺口
-
-## Prior History
-
-调查必须记录是否检查了：
-
-- `git log --oneline -20 -- <affected-files>`
-- historical `planning/analysis.md`
-- `TODOS.md` / backlog / roadmap
-- previous `report-card.json` findings
-
-如果同一区域重复出现 bug，必须标记为 architectural smell candidate。
-
-## External Research
-
-外部调研必须脱敏：
-
-- 不搜索 host、IP、token、customer id、内部路径、SQL、私有 repo 名
-- 只搜索通用错误类别、框架 / 库名、版本、组件名
-- research finding 只能作为候选假设，必须回到本仓库验证
-
-## No Code Root Cause
-
-如果结论不是代码根因，必须写清：
-
-- `rootCauseClass`: `code` / `config` / `environment` / `external` / `timing`
-- why not code root cause
-- monitoring or future evidence needed
-- operator handling after fix
-
-环境、外部服务、时序窗口仍然需要证据；不能把调查不足写成外因。
-
-## Repair Boundary
-
-修复边界至少记录：
-
-- affected module
-- allowed files
-- forbidden files
-- expected spec delta
-- verification after fix
-- blast radius file count
-- blast radius risk
-
-预计触碰超过 5 个文件时，必须 split / justify / reroute。
-
-## Escalation
-
-三次假设失败后，不再继续猜。必须记录：
-
-- failed hypothesis count
-- attempted evidence
-- why current entry is suspect
-- recommended next option：continue / instrument-and-wait / human-review / reroute-cc-plan
-- evidence request：repro env / HAR / log dump / core dump / timestamped recording / temporary production instrumentation
+- `task.md#Root Cause Contract` is the human truth.
+- `task.md` task blocks are the repair handoff.
+- Git commit records Investigate completion.
+- No process file beyond `task.md`.
 
 ## Reroute
 
-- 根因明确，修复边界清楚 -> `cc-do`
-- 发现这不是 bug，而是范围/设计问题 -> `cc-plan`
-- 发现这其实是项目优先级问题 -> `roadmap`
+If the issue is missing product scope, go to `cc-plan`. If it is roadmap priority, go to `cc-roadmap`. If evidence is unavailable, return an Evidence Request.

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

@@ -1,5 +1,11 @@
 # Changelog
 
+## 1.1.1
+
+- replace manifest and verification-report wording with `task.md`, fresh evidence, and response-only routing
+- compress required output to queue truth, selected goal, reason, goal packet, and route
+- forbid JSON/status/resume/report process files during next-work selection
+
 ## 1.0.1
 
 - Include unarchived `devflow/changes/<REQ|FIX>-*` directories as next-work candidates before fresh issue selection.

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

@@ -33,22 +33,26 @@ find devflow/changes -maxdepth 1 -type d \
 
 分类规则：
 
-- `resume-planning`: planning / analysis 还没冻结。
-- `resume-execution`: manifest 还有 pending ready task。
-- `resume-check`: tasks 完成但没有 passing report-card。
-- `resume-act`: report-card pass，但交付材料、roadmap/spec sync 或 PR/handoff 未闭合。
+- `resume-planning`: `task.md` 还没冻结。
+- `resume-execution`: `task.md` 还有未完成任务。
+- `resume-check`: tasks 完成但缺少当前新鲜验证结论。
+- `resume-act`: 当前验证已过，但 PR / handoff / closeout 未闭合。
 - `archive-closeout`: 已 merged/done，但仍在 active changes 根目录。
 - `archive-blocked`: handoff 写了 `ArchiveSkip`、archive target 冲突或用户要求暂不归档。
 
 同一 roadmap 优先级下，优先继续已有 active change，再选择新的 issue。已经在 `devflow/changes/archive/YYYY-MM/` 下的目录不进入普通候选。
 
-## Required Outputs
+## Required Output
+
+Short response only:
 
 - Queue truth
-- Selected goal or no-ready-goal
-- Selection reason
+- Selected goal or `no-ready-goal`
+- Reason
 - Goal Packet when selected
-- Next gate
+- Route: `cc-dev` / `cc-roadmap` / `stop`
+
+Do not create process files.
 
 ## No-Ready Reasons