cc-devflow 4.5.6 → 4.5.8

package/docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md

@@ -4,7 +4,7 @@
 
 - Requirement version: `REQ-002.v2`
 - Design version: `design.v2`
-- CC-Plan skill version: `3.7.7`
+- CC-Plan skill version: `3.8.2`
 - Source roadmap item: `RM-010`
 - Source roadmap version: `roadmap.v2`
 
@@ -22,6 +22,7 @@
   - Implementation decisions: reuse invite engine, billing checks, and audit contract after the row-outcome matrix is approved
   - Testing decisions: test bulk-import rules, admin upload flow, and audit mapping
   - Out of scope: SCIM provisioning, background jobs, rollback wizard
+- AI Leverage Decision Lens: sharp-wedge; AI can implement this bounded import path fast, but cc-check may still block final proof if row semantics drift
 - Read first:
   - `design.md`
   - `src/admin/BulkInvitePanel.tsx`
@@ -36,50 +37,94 @@
   - audit row-result contract
 - Parallel boundaries: no parallel execution until row-outcome semantics are frozen
 
+## Execution Protocol
+
+ClaudeCode / Codex 执行本计划时，必须把本文件当成任务模板合同，而不是普通 TODO 列表。
+
+- Template source: `assets/TASKS_TEMPLATE.md`
+- Task selection: read `planning/task-manifest.json.currentTaskId`; if empty, run the ready-task selector before choosing work.
+- Task block rule: read the full task block before coding; title-only execution is invalid.
+- Completion rule: after verification and review gates pass, run the completion script; do not manually edit checkbox, status, or `currentTaskId`.
+- Completion failure: if the script fails, fix the missing checkpoint / review / dependency evidence and rerun it. Do not bypass it by editing JSON or Markdown.
+
+```bash
+SCRIPT_ROOT=".claude/skills/cc-do/scripts"
+if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then
+  SCRIPT_ROOT=".codex/skills/cc-do/scripts"
+fi
+bash "$SCRIPT_ROOT/select-ready-tasks.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json
+bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task <task-id>
+```
+
 ## Phase 1: Rule Matrix
 
 - [x] T001 [TEST] Add failing tests for duplicate and over-limit row outcomes (dependsOn:none) `src/invite/bulk-import.test.ts`
   Goal: 先把最危险的 bulk invite 行为变成红灯。
+  TDD phase: red
   Files: `src/invite/bulk-import.test.ts`
   Read first: `design.md`, `src/invite/bulk-import.ts`
   Verification: `npm test -- src/invite/bulk-import.test.ts`
   Evidence: failing output
+  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T001`; do not hand-edit status.
+  Test seam: bulk invite rules and admin upload UI behavior
+  Public verification path: Run the bulk invite rule and admin panel tests through their public flows
+  Allowed mocks: file upload boundary / billing / seat limit boundary
   Ready when: 当前规则文件已经可定位
 
 - [x] T002 [IMPL] Implement the initial bulk invite row classification (dependsOn:T001) `src/invite/bulk-import.ts`
   Goal: 给 duplicate / over-limit 行为一个最小实现。
+  TDD phase: green
   Files: `src/invite/bulk-import.ts`
   Read first: `design.md`, `src/invite/bulk-import.test.ts`
   Verification: `npm test -- src/invite/bulk-import.test.ts`
   Evidence: passing output + checkpoint
+  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T002`; do not hand-edit status.
+  Test seam: bulk invite rules and admin upload UI behavior
+  Public verification path: Run the bulk invite rule and admin panel tests through their public flows
+  Allowed mocks: file upload boundary / billing / seat limit boundary
   Ready when: T001 已见红
 
 ## Phase 2: Surface Integration
 
 - [x] T003 [TEST] Add failing admin panel tests for mixed CSV results (dependsOn:T002) `src/admin/BulkInvitePanel.test.tsx`
   Goal: 在 UI 层看到 mixed row outcomes 的真实表现。
+  TDD phase: red
   Files: `src/admin/BulkInvitePanel.test.tsx`
   Read first: `design.md`, `src/admin/BulkInvitePanel.tsx`
   Verification: `npm test -- src/admin/BulkInvitePanel.test.tsx`
   Evidence: failing output
+  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T003`; do not hand-edit status.
+  Test seam: bulk invite rules and admin upload UI behavior
+  Public verification path: Run the bulk invite rule and admin panel tests through their public flows
+  Allowed mocks: file upload boundary / billing / seat limit boundary
   Ready when: T002 已完成
 
 - [x] T004 [IMPL] Render bulk invite results in the admin panel (dependsOn:T003) `src/admin/BulkInvitePanel.tsx`
   Goal: 把 row outcomes 接进管理界面。
+  TDD phase: green
   Files: `src/admin/BulkInvitePanel.tsx`
   Read first: `design.md`, `src/admin/BulkInvitePanel.test.tsx`
   Verification: `npm test -- src/admin/BulkInvitePanel.test.tsx`
   Evidence: passing output + review notes
+  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T004`; do not hand-edit status.
+  Test seam: bulk invite rules and admin upload UI behavior
+  Public verification path: Run the bulk invite rule and admin panel tests through their public flows
+  Allowed mocks: file upload boundary / billing / seat limit boundary
   Ready when: T003 已见红
 
 ## Phase 3: Verification
 
 - [x] T005 Run mixed-surface checks and gather review evidence (dependsOn:T004) `bulk invite quality gates`
   Goal: 为 `cc-check` 准备 bulk invite 的新鲜证据。
+  TDD phase: evidence
   Files: `src/admin/BulkInvitePanel.tsx`, `src/invite/bulk-import.ts`
   Read first: `tasks.md`, `task-manifest.json`
   Verification:
   - `npm test -- src/invite/bulk-import.test.ts`
   - `npm test -- src/admin/BulkInvitePanel.test.tsx`
   Evidence: passing output + review notes
+  Completion: after verification evidence and required checkpoint/review records exist, run `SCRIPT_ROOT=".claude/skills/cc-do/scripts"; if [[ ! -d "$SCRIPT_ROOT" && -d ".codex/skills/cc-do/scripts" ]]; then SCRIPT_ROOT=".codex/skills/cc-do/scripts"; fi; bash "$SCRIPT_ROOT/mark-task-complete.sh" --manifest docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/task-manifest.json --tasks docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/tasks.md --task T005`; do not hand-edit status.
+  Test seam: bulk invite rules and admin upload UI behavior
+  Public verification path: Run the bulk invite rule and admin panel tests through their public flows
+  Allowed mocks: file upload boundary / billing / seat limit boundary
   Ready when: T004 已完成

package/docs/examples/full-design-blocked/roadmap.json

@@ -5,7 +5,7 @@
   },
   "meta": {
     "roadmapVersion": "roadmap.v2",
-    "skillVersion": "5.0.0",
+    "skillVersion": "5.2.0",
     "status": "active",
     "lastUpdated": "2026-04-19",
     "currentFocusStage": "Stage 2"
@@ -14,7 +14,23 @@
     "planningPosture": "",
     "evidenceMaturity": "",
     "canonicalTerms": [],
-    "durableDecisionSources": []
+    "durableDecisionSources": [],
+    "aiLeverageRouteLens": {
+      "realUserOrOperator": "workspace admin onboarding 20-200 collaborators",
+      "statusQuoWorkaround": "paste individual invite emails or coordinate in spreadsheets",
+      "humanTeamEffortForFullScope": "multiple weeks across product, engineering, billing, and support review",
+      "ccAgentEffortForFullScope": "several hours once row semantics are approved, but unbounded before that",
+      "aiCompressionRatio": "high after semantics freeze, low while the product contract is ambiguous",
+      "completeLakeBoundary": "row classification, admin upload flow, billing-seat checks, and audit mapping after rule approval",
+      "oceanBoundary": "SCIM, background retries, rollback wizard, and unspecified billing semantics",
+      "scopeRecommendation": "sharp-wedge",
+      "firstSuccessSignal": "admins can predict duplicate, invalid, and over-limit outcomes",
+      "killSignal": "duplicate and seat-limit semantics remain unresolved",
+      "verdict": "sharp-wedge",
+      "missingEvidence": [
+        "none recorded at route handoff; cc-check later reopened duplicate, invalid-row, partial-success, and seat-limit semantics"
+      ]
+    }
   },
   "evidence": [],
   "route": {

package/docs/examples/local-handoff/BACKLOG.md

@@ -5,7 +5,7 @@
 ## Backlog Meta
 
 - Roadmap version: `roadmap.v2`
-- Skill version: `5.0.0`
+- Skill version: `5.2.0`
 - Last synced: `2026-04-19`
 - Current focus stage: `Stage 2`
 - Roadmap state source: `roadmap.json`

package/docs/examples/local-handoff/README.md

@@ -4,7 +4,7 @@
 
 - Example version: `1.0.0`
 - Last reviewed: `2026-04-17`
-- Bound skills: `cc-roadmap@5.0.0`, `cc-plan@3.7.7`, `cc-do@1.6.2`, `cc-check@1.10.1`, `cc-act@1.8.2`
+- Bound skills: `cc-roadmap@5.2.0`, `cc-plan@3.8.2`, `cc-do@1.6.3`, `cc-check@1.10.1`, `cc-act@1.8.3`
 
 This example shows verified work that is **ready to move forward**, but `cc-act` still chooses `local-handoff`.
 

package/docs/examples/local-handoff/ROADMAP.md

@@ -3,7 +3,7 @@
 ## Roadmap Meta
 
 - Roadmap version: `roadmap.v3`
-- Skill version: `5.0.0`
+- Skill version: `5.2.0`
 - Status: `active`
 - Last updated: `2026-04-16`
 - Owner / decider: `product-owner`
@@ -27,6 +27,21 @@
 - Adoption / trust bottleneck: admins want proof they can take activity history out of the UI cleanly
 - Known unknowns: whether CSV alone is enough or if JSON export will be needed later
 
+## AI Leverage Route Lens
+
+- Real user / operator: workspace admin preparing weekly activity review notes
+- Status quo workaround: manually copy visible audit rows into an internal note
+- Human-team effort for full scope: about one day for an engineer to implement, test, and document the local export
+- CC / agent effort for full scope: about 30 minutes for visible-row CSV export plus targeted test and lint
+- AI compression ratio: roughly 10x for the bounded local export path
+- Complete-lake boundary: visible-row CSV export, panel action, current data source, targeted panel test, and lint
+- Ocean boundary: JSON export, scheduled reporting, shared reporting backend, and cross-panel reporting platform
+- Scope recommendation: `boil-lake`
+- First success signal: admins finish weekly review without manual row copying
+- Kill signal: implementation requires shared reporting pipeline redesign
+- Verdict: `boil-lake`
+- Missing evidence before ready-for-cc-plan: none
+
 ## Recommended Route
 
 - Recommendation: `wedge-first`

package/docs/examples/local-handoff/changes/REQ-003-audit-log-export/planning/design.md

@@ -4,7 +4,7 @@
 
 - Requirement version: `REQ-003.v1`
 - Design version: `design.v1`
-- CC-Plan skill version: `3.7.7`
+- CC-Plan skill version: `3.8.2`
 - Requirement ID: `REQ-003`
 - Design mode: `tiny-design`
 - Why this stays `tiny-design`: the patch adds one export action inside the existing admin audit UI without changing data contracts
@@ -66,6 +66,30 @@
 - Risk: admins may soon ask for more export formats
 - Mitigation: treat JSON or scheduled exports as later roadmap items
 
+## AI Leverage Decision Lens
+
+- Real user / operator: workspace admin preparing weekly review notes
+- Status quo workaround: manually copy visible audit rows
+- Human-team effort for full scope: about one day for an engineer to implement, test, and document the local export
+- CC / agent effort for full scope: about 30 minutes for visible-row CSV export plus targeted test and lint
+- AI compression ratio: roughly 10x for the bounded local export path
+- Complete-lake boundary: visible-row CSV export, panel action, current data source, targeted panel test, and lint
+- Ocean boundary: JSON export, scheduled reporting, shared reporting backend, and cross-panel reporting platform
+- Scope recommendation: `boil-lake`
+- Cost model: low agent time, low human review time, targeted panel test plus lint, low maintenance cost while scoped to visible rows, reversible UI action
+- Verdict: `boil-lake`
+- Missing evidence or pivot reason: none
+
+## External Best-Practice Validation
+
+- Needed: No
+- Decision status: not-needed
+- Generalized search terms:
+- Sources checked:
+- Repo-fit verdict: skipped
+- Changes to frozen design:
+- Skipped reason: the local handoff exports existing visible rows and does not introduce a new reporting standard
+
 ## Review Gate
 
 - Placeholder scan: pass
@@ -74,6 +98,8 @@
 - Ambiguity scan: pass
 - Feasibility scan: pass
 - PRD brief scan: pass; the export story and scope boundaries are explicit
+- AI Leverage Decision Lens scan: pass; visible-row export lake is bounded enough to complete while reporting platform work stays out
+- External best-practice scan: pass; not needed for a repo-local visible-row export
 - Decision question scan: pass; `D1` approved the tiny-design CSV-export boundary
 - Final recommendation: approved as `tiny-design`