Commit fa86f3638388aaad1d4b2a3ff904ff4bc36cbe05
1 parent
043d6536
docs: move A/B/D/E/F/G/H's requirements+design docs into docs/done/
Per CLAUDE.md's docs/ role split (todo = pending, done = shipped into the SDD/code): all seven Graph Engineering series items with a real implementation (B, D, E, F, G, H -- A had no separate doc, resolved directly in graphlemon_architecture.md; C is explicitly won't-do) now have their requirements+design docs moved from docs/todo/ to docs/done/, git mv'd to preserve history. Every cross-reference to the 12 moved files -- across the other moved docs themselves, graph-engineering-open-items.md, 2 Skill files, and 9 src/*.py docstrings/comments -- updated from docs/todo/<file> to docs/done/<file>. Verified no stale docs/todo/ references to any of the 12 filenames remain anywhere in the repo. graph-engineering-open-items.md itself stays in docs/todo/ (not moved) -- it's a living index that keeps gaining new entries from later comparison-note/gap-analysis passes (H itself was added this way, and a new item already appeared while this cleanup was in progress), not a single finished conclusion. Its own header now reflects that all of A/B/D/E/F/G/H are done and explains why it wasn't moved. Also fixed two pre-existing stray path references (missing todo/done/ prefix entirely, predating this cleanup) in its G section. Full src suite (625 tests) passes -- this is a pure documentation/comment change, no behavior touched. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Showing
24 changed files
with
26 additions
and
26 deletions
docs/todo/dynamic-work-graph-design-skill-design.md renamed to docs/done/dynamic-work-graph-design-skill-design.md
| 1 | # 跨 Org Agent 的动态 Work Graph 设计能力——详细设计（SDD） | 1 | # 跨 Org Agent 的动态 Work Graph 设计能力——详细设计（SDD） |
| 2 | 2 | ||
| 3 | **日期**: 2026-08-06 | 3 | **日期**: 2026-08-06 |
| 4 | -**性质**: 详细设计，对应需求文档 `docs/todo/dynamic-work-graph-design-skill-requirements.md`（条目 E，已确认）。回答该需求文档第 8 节的开放问题。 | 4 | +**性质**: 详细设计，对应需求文档 `docs/done/dynamic-work-graph-design-skill-requirements.md`（条目 E，已确认）。回答该需求文档第 8 节的开放问题。 |
| 5 | **依赖**：条目 G（`docs/work-graph-parallel-execution-design.md`）已实现——`topological_layers()`/`run_graph()` 已经在生产代码里。 | 5 | **依赖**：条目 G（`docs/work-graph-parallel-execution-design.md`）已实现——`topological_layers()`/`run_graph()` 已经在生产代码里。 |
| 6 | **状态**: 设计草案，待评审后实施。 | 6 | **状态**: 设计草案，待评审后实施。 |
| 7 | 7 |
docs/todo/dynamic-work-graph-design-skill-requirements.md renamed to docs/done/dynamic-work-graph-design-skill-requirements.md
docs/todo/role-package-abstraction-design.md renamed to docs/done/role-package-abstraction-design.md
| 1 | # 统一 Role Package 抽象层——详细设计（SDD） | 1 | # 统一 Role Package 抽象层——详细设计（SDD） |
| 2 | 2 | ||
| 3 | **日期**: 2026-08-06 | 3 | **日期**: 2026-08-06 |
| 4 | -**性质**: 详细设计，对应需求文档 `docs/todo/role-package-abstraction-requirements.md`（条目 H，需求评审已通过，见 `docs/todo/graph-engineering-open-items.md` H 节的评审记录）。回答该需求文档第 8 节的开放问题。 | 4 | +**性质**: 详细设计，对应需求文档 `docs/done/role-package-abstraction-requirements.md`（条目 H，需求评审已通过，见 `docs/todo/graph-engineering-open-items.md` H 节的评审记录）。回答该需求文档第 8 节的开放问题。 |
| 5 | **范围确认（用户 2026-08-06）**：FR-3 的 4 张 CHECK 约束表一次性全改，不分阶段。 | 5 | **范围确认（用户 2026-08-06）**：FR-3 的 4 张 CHECK 约束表一次性全改，不分阶段。 |
| 6 | **状态**: 设计草案，实施中。 | 6 | **状态**: 设计草案，实施中。 |
| 7 | 7 |
docs/todo/role-package-abstraction-requirements.md renamed to docs/done/role-package-abstraction-requirements.md
| @@ -16,7 +16,7 @@ | @@ -16,7 +16,7 @@ | ||
| 16 | | **context** | `memory: project` → `.claude/agent-memory/{role}/`，git 版本化；但 Work Node 执行时塞进 prompt 的内容是每个调用点临时拼的（`build_prompt(node, outputs)`），没有独立的"context 组装层"抽象 | 局部实现，无统一抽象 | | 16 | | **context** | `memory: project` → `.claude/agent-memory/{role}/`，git 版本化；但 Work Node 执行时塞进 prompt 的内容是每个调用点临时拼的（`build_prompt(node, outputs)`），没有独立的"context 组装层"抽象 | 局部实现，无统一抽象 | |
| 17 | | **skills** | `skills/<name>/SKILL.md`，按名字挂进角色的 `skills:` frontmatter | 七项里最成熟、最像"可复用打包单元"的一个 | | 17 | | **skills** | `skills/<name>/SKILL.md`，按名字挂进角色的 `skills:` frontmatter | 七项里最成熟、最像"可复用打包单元"的一个 | |
| 18 | | **applications** | 没有对应的一等概念。架构文档 §7.2 提到 `mcpServers` 字段可以挂专属 MCP server，但 `agent_profile.py::FRONTMATTER` 里三个角色**一个都没配** | 基本空白 | | 18 | | **applications** | 没有对应的一等概念。架构文档 §7.2 提到 `mcpServers` 字段可以挂专属 MCP server，但 `agent_profile.py::FRONTMATTER` 里三个角色**一个都没配** | 基本空白 | |
| 19 | -| **workflows** | Claude Code 原生 Dynamic Workflows 机制在，但只有 Planner 真正用——`work_graph_plan.py::plan_work_graph()` 的提示词硬编码永远只生成 brd/prd/sdd/benchmark 四个节点，Coder/Validator 走的是更简化的单次 `trigger_org_node()` 调用，没有"先规划图再执行"这条路径（见 `docs/todo/dynamic-work-graph-design-skill-requirements.md`，即条目 E，已确认待做） | 机制存在，不是每个角色都能复用的打包能力 | | 19 | +| **workflows** | Claude Code 原生 Dynamic Workflows 机制在，但只有 Planner 真正用——`work_graph_plan.py::plan_work_graph()` 的提示词硬编码永远只生成 brd/prd/sdd/benchmark 四个节点，Coder/Validator 走的是更简化的单次 `trigger_org_node()` 调用，没有"先规划图再执行"这条路径（见 `docs/done/dynamic-work-graph-design-skill-requirements.md`，即条目 E，已确认待做） | 机制存在，不是每个角色都能复用的打包能力 | |
| 20 | | **permissions** | `tools`/`disallowedTools` per role（如 Validator `disallowedTools: [Edit, Write]`） | 有格式，但有记录在案的真实漏洞：`agent_profile.py` 注释明确写了"scoped Bash patterns（如 `Bash(git commit:*)`）会把 Bash 整个禁掉"，Validator 的 git-mutation 限制实际上退化成了 SOUL.md 里的文字约定，不是工具层强制 | | 20 | | **permissions** | `tools`/`disallowedTools` per role（如 Validator `disallowedTools: [Edit, Write]`） | 有格式，但有记录在案的真实漏洞：`agent_profile.py` 注释明确写了"scoped Bash patterns（如 `Bash(git commit:*)`）会把 Bash 整个禁掉"，Validator 的 git-mutation 限制实际上退化成了 SOUL.md 里的文字约定，不是工具层强制 | |
| 21 | | **acceptance criteria** | Benchmark、PASS/FAIL/INCONCLUSIVE、SDD REQ-01~15、`root_cause_trace` 根因归属 | 七项里最成熟的一环 | | 21 | | **acceptance criteria** | Benchmark、PASS/FAIL/INCONCLUSIVE、SDD REQ-01~15、`root_cause_trace` 根因归属 | 七项里最成熟的一环 | |
| 22 | 22 | ||
| @@ -32,7 +32,7 @@ | @@ -32,7 +32,7 @@ | ||
| 32 | ## 3. 非目标 | 32 | ## 3. 非目标 |
| 33 | 33 | ||
| 34 | 1. **不要求第一版就实现"运行时自主创建新角色"**。架构文档 §3"关键设计原则 1"明确 Org Graph 结构是人工定义、代码级固定，改动属于架构变更需要人工评审——这条决策不动。本需求要解决的是"人工新增一个角色时，需要改多少处代码/schema"这个摩擦，而不是让系统自己决定要不要新增角色。新增角色依然是人工发起的动作，只是发起方式从"改代码"变成"写一份声明式的 package"。 | 34 | 1. **不要求第一版就实现"运行时自主创建新角色"**。架构文档 §3"关键设计原则 1"明确 Org Graph 结构是人工定义、代码级固定，改动属于架构变更需要人工评审——这条决策不动。本需求要解决的是"人工新增一个角色时，需要改多少处代码/schema"这个摩擦，而不是让系统自己决定要不要新增角色。新增角色依然是人工发起的动作，只是发起方式从"改代码"变成"写一份声明式的 package"。 |
| 35 | -2. **不在本文档里解决 workflows 维度的具体落地**——Coder/Validator 缺少动态 Work Graph 规划能力这件事，已经是条目 E（`docs/todo/dynamic-work-graph-design-skill-requirements.md`）的范围，本文档只要求"Role Package 里要有一个字段/引用指向这个角色的 workflow 规划能力"，不重复设计 E 已经在做的事。 | 35 | +2. **不在本文档里解决 workflows 维度的具体落地**——Coder/Validator 缺少动态 Work Graph 规划能力这件事，已经是条目 E（`docs/done/dynamic-work-graph-design-skill-requirements.md`）的范围，本文档只要求"Role Package 里要有一个字段/引用指向这个角色的 workflow 规划能力"，不重复设计 E 已经在做的事。 |
| 36 | 3. **不在本文档里重新解决 permissions 维度的已知漏洞**（scoped Bash disallowedTools 不生效）——这是 Claude Code 平台本身的行为限制，本文档只要求 Role Package 的 permissions 字段要能诚实反映"这条限制实际上是工具层强制还是仅靠文字约定"，不假装这个漏洞已经修复。 | 36 | 3. **不在本文档里重新解决 permissions 维度的已知漏洞**（scoped Bash disallowedTools 不生效）——这是 Claude Code 平台本身的行为限制，本文档只要求 Role Package 的 permissions 字段要能诚实反映"这条限制实际上是工具层强制还是仅靠文字约定"，不假装这个漏洞已经修复。 |
| 37 | 4. **不要求一次性覆盖全部七个维度到同等成熟度**。applications 维度目前是空白，第一版只需要定义清楚"这个维度存在、字段长什么样、允许为空"，不要求马上有真实的 MCP server 集成可用。 | 37 | 4. **不要求一次性覆盖全部七个维度到同等成熟度**。applications 维度目前是空白，第一版只需要定义清楚"这个维度存在、字段长什么样、允许为空"，不要求马上有真实的 MCP server 集成可用。 |
| 38 | 5. **不做通用的"角色市场/角色商店"之类的产品化能力**。这是纯粹的内部抽象层重构，不涉及把角色包装成可分发、可交易的产品单元。 | 38 | 5. **不做通用的"角色市场/角色商店"之类的产品化能力**。这是纯粹的内部抽象层重构，不涉及把角色包装成可分发、可交易的产品单元。 |
docs/todo/validator-loop-until-dry-skill-design.md renamed to docs/done/validator-loop-until-dry-skill-design.md
| 1 | # Validator "未知规模扫描收敛" Skill——详细设计（SDD） | 1 | # Validator "未知规模扫描收敛" Skill——详细设计（SDD） |
| 2 | 2 | ||
| 3 | **日期**: 2026-08-06 | 3 | **日期**: 2026-08-06 |
| 4 | -**性质**: 详细设计，对应需求文档 `docs/todo/validator-loop-until-dry-skill-requirements.md`（条目 B，已确认）。回答该需求文档第 8 节的开放问题。 | 4 | +**性质**: 详细设计，对应需求文档 `docs/done/validator-loop-until-dry-skill-requirements.md`（条目 B，已确认）。回答该需求文档第 8 节的开放问题。 |
| 5 | **状态**: 设计草案，实施中。 | 5 | **状态**: 设计草案，实施中。 |
| 6 | 6 | ||
| 7 | ## 1. 范围确认：纯 Skill，不动执行引擎 | 7 | ## 1. 范围确认：纯 Skill，不动执行引擎 |
docs/todo/validator-loop-until-dry-skill-requirements.md renamed to docs/done/validator-loop-until-dry-skill-requirements.md
docs/todo/verifier-fan-out-jury-design.md renamed to docs/done/verifier-fan-out-jury-design.md
| 1 | # 三视角评审团——Work Graph Fan-out 实现——详细设计（SDD） | 1 | # 三视角评审团——Work Graph Fan-out 实现——详细设计（SDD） |
| 2 | 2 | ||
| 3 | **日期**: 2026-08-06 | 3 | **日期**: 2026-08-06 |
| 4 | -**性质**: 详细设计，对应需求文档 `docs/todo/verifier-fan-out-jury-requirements.md`（条目 F，已确认）。回答该需求文档第 8 节的开放问题。 | 4 | +**性质**: 详细设计，对应需求文档 `docs/done/verifier-fan-out-jury-requirements.md`（条目 F，已确认）。回答该需求文档第 8 节的开放问题。 |
| 5 | **依赖代码**：`src/root_cause_trace.py`（`judge_root_cause`/`_PERSPECTIVE_FRAMINGS`）、`src/org_level_loop.py`（`run_fix_loop`，唯一真实生产调用方）、`src/work_graph_orchestrate.py`（G 已实现的 `run_graph()`/`topological_layers()`）。 | 5 | **依赖代码**：`src/root_cause_trace.py`（`judge_root_cause`/`_PERSPECTIVE_FRAMINGS`）、`src/org_level_loop.py`（`run_fix_loop`，唯一真实生产调用方）、`src/work_graph_orchestrate.py`（G 已实现的 `run_graph()`/`topological_layers()`）。 |
| 6 | **状态**: 设计草案，待评审后实施。 | 6 | **状态**: 设计草案，待评审后实施。 |
| 7 | 7 |
docs/todo/verifier-fan-out-jury-requirements.md renamed to docs/done/verifier-fan-out-jury-requirements.md
docs/todo/work-graph-parallel-execution-design.md renamed to docs/done/work-graph-parallel-execution-design.md
docs/todo/work-graph-parallel-execution-requirements.md renamed to docs/done/work-graph-parallel-execution-requirements.md
docs/todo/work-graph-time-travel-debugging-design.md renamed to docs/done/work-graph-time-travel-debugging-design.md
| 1 | # Work Graph 执行历史 Time-Travel 调试——详细设计（SDD） | 1 | # Work Graph 执行历史 Time-Travel 调试——详细设计（SDD） |
| 2 | 2 | ||
| 3 | **日期**: 2026-08-06 | 3 | **日期**: 2026-08-06 |
| 4 | -**性质**: 详细设计，对应需求文档 `docs/todo/work-graph-time-travel-debugging-requirements.md`（条目 D，已确认）。回答该需求文档第 8 节的开放问题。 | 4 | +**性质**: 详细设计，对应需求文档 `docs/done/work-graph-time-travel-debugging-requirements.md`（条目 D，已确认）。回答该需求文档第 8 节的开放问题。 |
| 5 | **状态**: 设计草案，实施中，后端+控制台一起做（用户 2026-08-06 确认）。 | 5 | **状态**: 设计草案，实施中，后端+控制台一起做（用户 2026-08-06 确认）。 |
| 6 | 6 | ||
| 7 | ## 1. `ux_work_graph_run_active` 比需求文档描述的风险更小 | 7 | ## 1. `ux_work_graph_run_active` 比需求文档描述的风险更小 |
docs/todo/work-graph-time-travel-debugging-requirements.md renamed to docs/done/work-graph-time-travel-debugging-requirements.md
docs/todo/graph-engineering-open-items.md
| 1 | # Graph Engineering 系列对照笔记——待确认事项清单 | 1 | # Graph Engineering 系列对照笔记——待确认事项清单 |
| 2 | 2 | ||
| 3 | -**日期**: 2026-08-04（2026-08-05 更新：A/B/D/E/F/G 已确认方向，C 已确认暂不做） | ||
| 4 | -**性质**: 从三份对照笔记里提取出的全部"待讨论的开放问题"，去重合并后按主题整理，供逐条确认方案。每条确认后会展开成独立的需求文档（参考 `docs/work-graph-parallel-execution-requirements.md` 的产出方式），本文件本身只做索引和现状追踪，不写详细方案。 | 3 | +**日期**: 2026-08-04（2026-08-06 更新：A/B/D/E/F/G/H 全部已实现，C 已确认不做——全部条目均已resolve，本文件继续作为这条主线的活索引保留在 `docs/todo/`，不迁入 `docs/done/`，因为它会随新一批对照笔记/差距检查持续追加条目，见 H 的加入方式） |
| 4 | +**性质**: 从三份对照笔记里提取出的全部"待讨论的开放问题"，去重合并后按主题整理，供逐条确认方案。每条确认后会展开成独立的需求文档（参考 `docs/done/work-graph-parallel-execution-requirements.md` 的产出方式，条目落地后连同设计文档一并移入 `docs/done/`），本文件本身只做索引和现状追踪，不写详细方案。 | ||
| 5 | **来源文档**： | 5 | **来源文档**： |
| 6 | - `docs/reference/graph-engineering-1000-agents-5-steps.diff-with-graphlemon.md`（简称"5 步版对照"） | 6 | - `docs/reference/graph-engineering-1000-agents-5-steps.diff-with-graphlemon.md`（简称"5 步版对照"） |
| 7 | - `docs/reference/graph-engineering-vs-loop-engineering-overview.diff-with-graphlemon.md`（简称"综述版对照"） | 7 | - `docs/reference/graph-engineering-vs-loop-engineering-overview.diff-with-graphlemon.md`（简称"综述版对照"） |
| @@ -36,7 +36,7 @@ | @@ -36,7 +36,7 @@ | ||
| 36 | 36 | ||
| 37 | ## B. loop-until-dry 要不要在 Validator 落地 | 37 | ## B. loop-until-dry 要不要在 Validator 落地 |
| 38 | 38 | ||
| 39 | -**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/validator-loop-until-dry-skill-requirements.md` + 设计文档 `docs/todo/validator-loop-until-dry-skill-design.md` | 39 | +**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/validator-loop-until-dry-skill-requirements.md` + 设计文档 `docs/done/validator-loop-until-dry-skill-design.md` |
| 40 | 40 | ||
| 41 | **来源**：5 步版对照 §4 开放问题 1 | 41 | **来源**：5 步版对照 §4 开放问题 1 |
| 42 | 42 | ||
| @@ -62,7 +62,7 @@ | @@ -62,7 +62,7 @@ | ||
| 62 | 62 | ||
| 63 | ## D. Time-travel 调试要不要立项 | 63 | ## D. Time-travel 调试要不要立项 |
| 64 | 64 | ||
| 65 | -**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/work-graph-time-travel-debugging-requirements.md` + 设计文档 `docs/todo/work-graph-time-travel-debugging-design.md` | 65 | +**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/work-graph-time-travel-debugging-requirements.md` + 设计文档 `docs/done/work-graph-time-travel-debugging-design.md` |
| 66 | 66 | ||
| 67 | **来源**：综述版对照 §6 | 67 | **来源**：综述版对照 §6 |
| 68 | 68 | ||
| @@ -78,7 +78,7 @@ | @@ -78,7 +78,7 @@ | ||
| 78 | 78 | ||
| 79 | ## E. Planning Skill 提示词强化——识别可并行节点 + 通用 Work Graph 设计能力 | 79 | ## E. Planning Skill 提示词强化——识别可并行节点 + 通用 Work Graph 设计能力 |
| 80 | 80 | ||
| 81 | -**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/dynamic-work-graph-design-skill-requirements.md` + 设计文档 `docs/todo/dynamic-work-graph-design-skill-design.md` | 81 | +**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/dynamic-work-graph-design-skill-requirements.md` + 设计文档 `docs/done/dynamic-work-graph-design-skill-design.md` |
| 82 | 82 | ||
| 83 | **来源**：综述版对照 §7 开放问题 3 + 14 步版对照 §3 开放问题 2（同一主题：让 Planning 阶段更早识别并行机会） | 83 | **来源**：综述版对照 §7 开放问题 3 + 14 步版对照 §3 开放问题 2（同一主题：让 Planning 阶段更早识别并行机会） |
| 84 | 84 | ||
| @@ -92,7 +92,7 @@ | @@ -92,7 +92,7 @@ | ||
| 92 | 92 | ||
| 93 | ## F. 三视角评审团机制要不要推广到其他验证点 | 93 | ## F. 三视角评审团机制要不要推广到其他验证点 |
| 94 | 94 | ||
| 95 | -**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/verifier-fan-out-jury-requirements.md` + 设计文档 `docs/todo/verifier-fan-out-jury-design.md` | 95 | +**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/verifier-fan-out-jury-requirements.md` + 设计文档 `docs/done/verifier-fan-out-jury-design.md` |
| 96 | 96 | ||
| 97 | **来源**：综述版对照 §7 开放问题 4 + 14 步版对照 §3 开放问题 4（同一主题） | 97 | **来源**：综述版对照 §7 开放问题 4 + 14 步版对照 §3 开放问题 4（同一主题） |
| 98 | 98 | ||
| @@ -106,7 +106,7 @@ | @@ -106,7 +106,7 @@ | ||
| 106 | 106 | ||
| 107 | ## G. Work Graph 节点并行执行（Python 线程池方案） | 107 | ## G. Work Graph 节点并行执行（Python 线程池方案） |
| 108 | 108 | ||
| 109 | -**状态**：✅ 已实现（2026-08-06）→ 需求文档见 `docs/work-graph-parallel-execution-requirements.md` | 109 | +**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/work-graph-parallel-execution-requirements.md` + 设计文档 `docs/done/work-graph-parallel-execution-design.md` |
| 110 | 110 | ||
| 111 | **来源**：14 步版对照 §3 开放问题 1 | 111 | **来源**：14 步版对照 §3 开放问题 1 |
| 112 | 112 | ||
| @@ -120,7 +120,7 @@ | @@ -120,7 +120,7 @@ | ||
| 120 | 120 | ||
| 121 | ## H. 统一 Role Package 抽象层 | 121 | ## H. 统一 Role Package 抽象层 |
| 122 | 122 | ||
| 123 | -**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/todo/role-package-abstraction-requirements.md` + 设计文档 `docs/todo/role-package-abstraction-design.md` | 123 | +**状态**：✅ 已实现（2026-08-06）→ 需求文档 `docs/done/role-package-abstraction-requirements.md` + 设计文档 `docs/done/role-package-abstraction-design.md` |
| 124 | 124 | ||
| 125 | **来源**：不属于三份 Graph Engineering 对照笔记，是用户对照 Agentic Enterprise 产品目标（"role + context + skills + applications + workflows + permissions + acceptance criteria；all essentially are context for intelligent computing"）单独提出的差距检查，2026-08-06。 | 125 | **来源**：不属于三份 Graph Engineering 对照笔记，是用户对照 Agentic Enterprise 产品目标（"role + context + skills + applications + workflows + permissions + acceptance criteria；all essentially are context for intelligent computing"）单独提出的差距检查，2026-08-06。 |
| 126 | 126 |
skills/design-dynamic-work-graph/SKILL.md
| @@ -11,7 +11,7 @@ tags: | @@ -11,7 +11,7 @@ tags: | ||
| 11 | - orchestration | 11 | - orchestration |
| 12 | metadata: | 12 | metadata: |
| 13 | origin: graphlemon-native | 13 | origin: graphlemon-native |
| 14 | - related: [G（并行执行）docs/work-graph-parallel-execution-design.md, E docs/todo/dynamic-work-graph-design-skill-design.md] | 14 | + related: [G（并行执行）docs/work-graph-parallel-execution-design.md, E docs/done/dynamic-work-graph-design-skill-design.md] |
| 15 | platforms: [linux, macos, windows] | 15 | platforms: [linux, macos, windows] |
| 16 | --- | 16 | --- |
| 17 | 17 |
skills/unknown-scope-defect-sweep/SKILL.md
| @@ -11,7 +11,7 @@ tags: | @@ -11,7 +11,7 @@ tags: | ||
| 11 | - sweep | 11 | - sweep |
| 12 | metadata: | 12 | metadata: |
| 13 | origin: graphlemon-native | 13 | origin: graphlemon-native |
| 14 | - related: [qa-task-validation, docs/todo/validator-loop-until-dry-skill-design.md] | 14 | + related: [qa-task-validation, docs/done/validator-loop-until-dry-skill-design.md] |
| 15 | platforms: [linux, macos, windows] | 15 | platforms: [linux, macos, windows] |
| 16 | --- | 16 | --- |
| 17 | 17 |
src/agent_profile.py
| @@ -33,7 +33,7 @@ read by this module's own Python code; `json.load` is the zero-risk choice, | @@ -33,7 +33,7 @@ read by this module's own Python code; `json.load` is the zero-risk choice, | ||
| 33 | no hand-rolled parser. role.json content is deliberately a REFERENCE | 33 | no hand-rolled parser. role.json content is deliberately a REFERENCE |
| 34 | manifest, not a content copy: `identity.soul_md_path`/`agents_md_path` still | 34 | manifest, not a content copy: `identity.soul_md_path`/`agents_md_path` still |
| 35 | point at the same `agents/<org_node>/SOUL.md`/`AGENTS.md` files, unmoved -- | 35 | point at the same `agents/<org_node>/SOUL.md`/`AGENTS.md` files, unmoved -- |
| 36 | -see docs/todo/role-package-abstraction-design.md §2 for why keeping the | 36 | +see docs/done/role-package-abstraction-design.md §2 for why keeping the |
| 37 | existing identity files as the single source of prose content makes the | 37 | existing identity files as the single source of prose content makes the |
| 38 | migration's "deployed output must stay byte-identical" requirement close to | 38 | migration's "deployed output must stay byte-identical" requirement close to |
| 39 | automatic (only the frontmatter's data SOURCE changed, not the body-assembly | 39 | automatic (only the frontmatter's data SOURCE changed, not the body-assembly |
src/org_level_loop.py
| @@ -17,7 +17,7 @@ def run_fix_loop(conn, task_id, target_folder_path, bug_description, context, fi | @@ -17,7 +17,7 @@ def run_fix_loop(conn, task_id, target_folder_path, bug_description, context, fi | ||
| 17 | function doesn't add its own fallback for that, matching 04-P's own | 17 | function doesn't add its own fallback for that, matching 04-P's own |
| 18 | "升级人工" answer to disagreement). | 18 | "升级人工" answer to disagreement). |
| 19 | 19 | ||
| 20 | - **F (2026-08-06, docs/todo/verifier-fan-out-jury-design.md)**: root | 20 | + **F (2026-08-06, docs/done/verifier-fan-out-jury-design.md)**: root |
| 21 | cause judgment now runs as a real Work Graph fan-out (each perspective | 21 | cause judgment now runs as a real Work Graph fan-out (each perspective |
| 22 | is its own Work Node with its own clean context) instead of three | 22 | is its own Work Node with its own clean context) instead of three |
| 23 | sequential Python closures calling org_node_trigger.trigger_org_node -- | 23 | sequential Python closures calling org_node_trigger.trigger_org_node -- |
src/root_cause_trace.py
| @@ -15,7 +15,7 @@ concrete question each perspective asks is a prompt-engineering concern for | @@ -15,7 +15,7 @@ concrete question each perspective asks is a prompt-engineering concern for | ||
| 15 | the caller (see real_validator_perspective below for the real-call version), | 15 | the caller (see real_validator_perspective below for the real-call version), |
| 16 | not this module's. | 16 | not this module's. |
| 17 | 17 | ||
| 18 | -**F (2026-08-06, docs/todo/verifier-fan-out-jury-design.md)**: judge_root_cause | 18 | +**F (2026-08-06, docs/done/verifier-fan-out-jury-design.md)**: judge_root_cause |
| 19 | above is the closure-based implementation -- each perspective is a Python | 19 | above is the closure-based implementation -- each perspective is a Python |
| 20 | function call, sequentially, in the SAME process/context. Kept as-is (not | 20 | function call, sequentially, in the SAME process/context. Kept as-is (not |
| 21 | replaced): it's the cheap path for scenarios that don't need worktree/Work | 21 | replaced): it's the cheap path for scenarios that don't need worktree/Work |
src/schema.py
| @@ -84,7 +84,7 @@ CREATE TABLE skill ( | @@ -84,7 +84,7 @@ CREATE TABLE skill ( | ||
| 84 | -- ('planner','coder','validator')) -- relaxed to a plain non-empty-string | 84 | -- ('planner','coder','validator')) -- relaxed to a plain non-empty-string |
| 85 | -- check so a new role, added purely via roles/<role_id>/role.json (no | 85 | -- check so a new role, added purely via roles/<role_id>/role.json (no |
| 86 | -- schema.py/agent_profile.py code change), isn't rejected by a stale | 86 | -- schema.py/agent_profile.py code change), isn't rejected by a stale |
| 87 | - -- hardcoded enum. See docs/todo/role-package-abstraction-design.md §4. | 87 | + -- hardcoded enum. See docs/done/role-package-abstraction-design.md §4. |
| 88 | owner_org_node TEXT NOT NULL CHECK (owner_org_node != ''), | 88 | owner_org_node TEXT NOT NULL CHECK (owner_org_node != ''), |
| 89 | file_path TEXT NOT NULL, | 89 | file_path TEXT NOT NULL, |
| 90 | current_git_commit_sha TEXT NOT NULL, | 90 | current_git_commit_sha TEXT NOT NULL, |
src/test_org_level_loop.py
| @@ -5,7 +5,7 @@ Testing constraint). Real coverage is in src/test_org_level_loop_e2e.py | @@ -5,7 +5,7 @@ Testing constraint). Real coverage is in src/test_org_level_loop_e2e.py | ||
| 5 | 5 | ||
| 6 | **F (2026-08-06)**: root-cause judgment now runs through | 6 | **F (2026-08-06)**: root-cause judgment now runs through |
| 7 | root_cause_trace.judge_root_cause_via_work_graph (a real Work Graph fan-out, | 7 | root_cause_trace.judge_root_cause_via_work_graph (a real Work Graph fan-out, |
| 8 | -see docs/todo/verifier-fan-out-jury-design.md), so the 3 perspective calls | 8 | +see docs/done/verifier-fan-out-jury-design.md), so the 3 perspective calls |
| 9 | are mocked at work_graph_execute.write_workflow_script/execute_work_graph | 9 | are mocked at work_graph_execute.write_workflow_script/execute_work_graph |
| 10 | (same boundary as test_work_graph_orchestrate.py), not at | 10 | (same boundary as test_work_graph_orchestrate.py), not at |
| 11 | org_node_trigger.trigger_org_node -- that mock is now only used for the | 11 | org_node_trigger.trigger_org_node -- that mock is now only used for the |
src/test_work_graph_fork.py
| 1 | """D (2026-08-06) tests: work_graph_fork.py, mocked at the claude | 1 | """D (2026-08-06) tests: work_graph_fork.py, mocked at the claude |
| 2 | subprocess boundary (CLAUDE.md Testing constraint) -- same pattern as | 2 | subprocess boundary (CLAUDE.md Testing constraint) -- same pattern as |
| 3 | test_work_graph_orchestrate.py. Covers the requirements doc's acceptance | 3 | test_work_graph_orchestrate.py. Covers the requirements doc's acceptance |
| 4 | -standards 1-3 (docs/todo/work-graph-time-travel-debugging-requirements.md). | 4 | +standards 1-3 (docs/done/work-graph-time-travel-debugging-requirements.md). |
| 5 | 5 | ||
| 6 | Run: python3 -m unittest src.test_work_graph_fork -v | 6 | Run: python3 -m unittest src.test_work_graph_fork -v |
| 7 | """ | 7 | """ |
src/work_graph_fork.py
| @@ -3,7 +3,7 @@ work_graph_run from an already-'done' work_node_execution, substituting a | @@ -3,7 +3,7 @@ work_graph_run from an already-'done' work_node_execution, substituting a | ||
| 3 | human-provided output for that node and re-executing everything strictly | 3 | human-provided output for that node and re-executing everything strictly |
| 4 | downstream of it for real, while every other node reuses the original | 4 | downstream of it for real, while every other node reuses the original |
| 5 | run's persisted output_payload untouched. See | 5 | run's persisted output_payload untouched. See |
| 6 | -docs/todo/work-graph-time-travel-debugging-design.md for the full design. | 6 | +docs/done/work-graph-time-travel-debugging-design.md for the full design. |
| 7 | 7 | ||
| 8 | **Output substitution, not re-prompting** (design doc §2, resolving the | 8 | **Output substitution, not re-prompting** (design doc §2, resolving the |
| 9 | requirements doc's FR-1 ambiguity): the fork point's own output_payload is | 9 | requirements doc's FR-1 ambiguity): the fork point's own output_payload is |
src/work_graph_orchestrate.py
| @@ -352,7 +352,7 @@ def run_graph( | @@ -352,7 +352,7 @@ def run_graph( | ||
| 352 | independent work, no reason to throw away completed work), then raised | 352 | independent work, no reason to throw away completed work), then raised |
| 353 | together as `WorkGraphLayerError` once the whole layer has settled. | 353 | together as `WorkGraphLayerError` once the whole layer has settled. |
| 354 | One real limitation, accepted deliberately (see | 354 | One real limitation, accepted deliberately (see |
| 355 | - `docs/todo/work-graph-parallel-execution-design.md` §6): a node | 355 | + `docs/done/work-graph-parallel-execution-design.md` §6): a node |
| 356 | waiting on a quota-backoff sleep inside `run_work_node` blocks the | 356 | waiting on a quota-backoff sleep inside `run_work_node` blocks the |
| 357 | thread pool worker running it, which in turn blocks the layer barrier | 357 | thread pool worker running it, which in turn blocks the layer barrier |
| 358 | even after every sibling has finished -- Python threads have no clean | 358 | even after every sibling has finished -- Python threads have no clean |
src/work_graph_plan.py
| @@ -80,7 +80,7 @@ _PROMPT_TEMPLATE = ( | @@ -80,7 +80,7 @@ _PROMPT_TEMPLATE = ( | ||
| 80 | # E (2026-08-06): the generic, cross-Org-Agent path -- used for every | 80 | # E (2026-08-06): the generic, cross-Org-Agent path -- used for every |
| 81 | # org_node OTHER than 'planner'. Planner's own doc-writing chain stays on | 81 | # org_node OTHER than 'planner'. Planner's own doc-writing chain stays on |
| 82 | # _PROMPT_TEMPLATE above unchanged (zero regression risk, see | 82 | # _PROMPT_TEMPLATE above unchanged (zero regression risk, see |
| 83 | -# docs/todo/dynamic-work-graph-design-skill-design.md §3): that chain is a | 83 | +# docs/done/dynamic-work-graph-design-skill-design.md §3): that chain is a |
| 84 | # fixed architectural constant (brd->prd->sdd->benchmark->...), not | 84 | # fixed architectural constant (brd->prd->sdd->benchmark->...), not |
| 85 | # something that should vary call to call, whereas Coder/Validator's | 85 | # something that should vary call to call, whereas Coder/Validator's |
| 86 | # sub-tasks have no such fixed small vocabulary of node types. Each node | 86 | # sub-tasks have no such fixed small vocabulary of node types. Each node |