From b6423cff4312f4919b2374aca072b1b9d99197bd Mon Sep 17 00:00:00 2001 From: bboonnee Date: Mon, 3 Aug 2026 12:50:34 +0800 Subject: [PATCH] U-013 fix: auto-commit main-checkout drift too, not just the worktree's own --- .gitignore | 7 +++++++ docs/development-plan.md | 1 + docs/sdd/unit_matrix.json | 2 +- src/e2e_pipeline.py | 5 +++++ src/test_e2e_pipeline.py | 9 ++++++++- src/test_work_node_run.py | 34 ++++++++++++++++++++++++++++++++++ src/work_node_run.py | 43 +++++++++++++++++++++++++++++++++++-------- 7 files changed, 91 insertions(+), 10 deletions(-) diff --git a/.gitignore b/.gitignore index 2b57d43..550bfa8 100644 --- a/.gitignore +++ b/.gitignore @@ -6,3 +6,10 @@ __pycache__/ # source content. Agent memory (.claude/agent-memory/) IS tracked per # architecture doc §8 decision 1 ("Memory...必须通过 Git 提交留痕"). .claude/workflows/ + +# Coder Work Node isolation checkouts (work_node_run.create_worktree). Live +# INSIDE the main repo's own working tree while a node is running -- must +# never be picked up by `git add -A` on repo_path itself (2026-08-03: doing +# so once made a still-present worktree checkout look like a tracked +# gitlink, which then showed as "deleted" the moment remove_worktree() ran). +.graphlemon-worktrees/ diff --git a/docs/development-plan.md b/docs/development-plan.md index 235870d..47500f2 100644 --- a/docs/development-plan.md +++ b/docs/development-plan.md @@ -136,6 +136,7 @@ - **精度提升（2026-07-31，实现后补充）**：03-C §3.6 给出了 `USAGE_LIMIT_REACHED` 的精确探测正则 `/hit your (session|weekly|Opus) limit/i`，比 U-010/U-012 当时用的短语近似匹配更准——U-013 按这条正则实现，且真正写回 `work_node_execution.quota_wait_started_at`/`quota_limit_type`（U-010/U-012 阶段这两张表字段还没有真实归属）。`c_work_node_run` 是内部接口（03-C 原话"不对外暴露 HTTP，供 c_work_graph_execute 调用"），退避重试从 U-012 的整图级别下沉到这里的单节点级别 - 覆盖：01-M `work_node_execution`；03-C `c_work_node_run`；REQ-03（boundary） - **真实 bug（2026-08-02/03，U-042 第一次真实自举压测时发现）**：`RealGitWorktreeIsolationTest` 从 U-013 建成那天起，`run_fn` 一直是测试自己写的、写完文件后主动 `git add` + `git commit` 的假实现——这个盲区从没被真实 Coder 会话踩过，因为 PH1~PH4 所有真实调用都没启用 `needs_worktree=True`（development-plan.md U-031 的实现补充里已经记过这条），直到 U-035 让 self-target 场景无条件强制 worktree，U-042 第一次真实自举跑起来后才第一次真正踩中。真实现象：Coder 在 worktree 里确实编辑了文件，自己也验证过（`git status`/`git diff --stat` 都在它自己的 `test_report` 里回显了），但从未 `git commit`——Coder 人设里没有任何一处要求它提交自己的改动。`merge_worktree()` 只会 `git merge` 已提交的分支，worktree 分支上如果压根没有新提交，merge 就是个真正的空操作（"Already up to date"，不产生新 commit），紧接着 `remove_worktree()` 把这个还带着未提交改动的目录直接删掉——一次真实、已验证过的 Coder 改动就这样被无声吞掉，`implement_code()` 算出来的 `code_diff` 自然是空的。修复：新增 `work_node_run.ensure_worktree_committed()`，在 `merge_worktree()` 之前检查 worktree 是否有未提交改动（`git status --porcelain`），有则自动 `git add -A` + 提交一条 `graphlemon: auto-commit uncommitted worktree changes for `，worktree 本来就干净（比如纯排查、没有真的改代码）时什么也不做。新增两个回归测试：`test_uncommitted_worktree_changes_are_auto_committed_before_merge`（复现"改了但没提交"场景，断言改动最终真的落到主分支）、`test_clean_worktree_with_no_changes_is_still_a_valid_merge`（确认"确实没什么好改"这种合法结果不会被误伤）。这是"判断用 Agent，机制用代码"原则的又一次体现——不指望靠给人设加一条"记得 commit"的提示词来保证正确性，而是在系统层面兜底，人设漂移/遗忘不应该导致真实工作成果被无声丢弃。 + - **真实 bug 的第二层（2026-08-03，U-042 第八/九次真实压测发现，比上面这条更深一层）**：`ensure_worktree_committed()` 只兜住了 worktree 自己的未提交改动，但 git worktree 的设计本身是**和主仓库共享同一个项目身份**（同一个 `.git`，只是另一份检出）——一次真实压测发现，`claude -p` 的 `memory: project` 写入并不总是遵守调用时传入的 `cwd`，而是可能直接落在**主仓库自己的检出目录**上，和当时具体是哪个节点、哪次调用完全无关（不是 `_check_prd_consistency` 一个函数的问题，把它单独包一层 worktree 只是挪动了"这次踩中的是哪次调用"，没有从根上解决）。后果：主仓库工作区多出一处未提交的 memory 文件改动，下一个节点自己的、原本完全正常的 worktree merge 会因为"主分支有本地改动会被覆盖"直接报错退出（`git merge` exit 2）。修复：`ensure_worktree_committed()` 从只处理 worktree 自身，扩展成同时也对 `repo_path`（主仓库检出目录）本身跑一遍同样的"有脏改动就自动提交"逻辑，在每次 `merge_worktree()` 之前调用两次——不管是哪次真实调用造成的漂移、原因是什么，统一兜底，而不是针对某一个特定调用点单独打补丁。修复过程中顺带发现并解决了这条兜底自己引入的一个新问题：对主仓库跑 `git add -A` 时，如果某个节点的 worktree 检出目录（`.graphlemon-worktrees//`）当时还没被 `remove_worktree()` 清理，会被当成一个类似 git link 的条目一并加进去，紧接着目录被删掉后 `git status` 就会显示成一条诡异的"D"（删除）——两处修复：`.graphlemon-worktrees/` 加进 `.gitignore`（这是长期正确性），`ensure_worktree_committed()` 自己的 `git add -A`/`git status --porcelain` 也显式排除这个路径（`-- . ':!.graphlemon-worktrees'`），不依赖调用方仓库一定配置了对的 `.gitignore`。新增回归测试 `test_drift_on_main_checkout_is_auto_committed_before_merge`，模拟"改动落在主仓库而不是 worktree"这个具体场景，并验证接下来一个节点的合并不受影响。 ### PH1-S3 端到端验收（收口） diff --git a/docs/sdd/unit_matrix.json b/docs/sdd/unit_matrix.json index dce7fb8..d72105c 100644 --- a/docs/sdd/unit_matrix.json +++ b/docs/sdd/unit_matrix.json @@ -25,7 +25,7 @@ {"id": "U-010", "phase": "PH1", "sub_phase": "PH1-S1", "name": "c_org_node_trigger 完整实现（三段前向状态迁移，见 development-plan.md 2026-07-31 范围说明）", "classification": "Value Path", "depends_on": ["U-005", "U-009"], "coverage": {"model": [], "view": [], "controller": ["c_org_node_trigger"], "process": [], "requirement": []}, "done": "三个 Org Agent 分别可被触发（真实 claude --agent 调用），task.status 按 queued→planning_brd_prd_sdd→coding→validating 正确流转；重试/路由/blocked_pending_human 不在本 Unit 范围"}, {"id": "U-011", "phase": "PH1", "sub_phase": "PH1-S2", "name": "c_work_graph_plan 实现（只规划不执行，见 development-plan.md 2026-07-31/2026-08-03 订正）", "classification": "Value Path", "depends_on": ["U-004", "U-010"], "coverage": {"model": ["artifact", "work_graph_run"], "view": [], "controller": ["c_work_graph_plan"], "process": [], "requirement": ["REQ-02"]}, "done": "graph_manifest 通过结构校验（brd/prd/sdd/benchmark 四节点+依赖链），work_graph_run(status=planning) 落地；REQ-02 happy 用例整体随 U-012/U-013 累计满足。c_artifact_write（03-C §3.7）目前没有任何 Unit 认领，是已知缺口。2026-08-03：U-042 第六次真实自举压测发现真实 LLM 输出可能完全不给 depends_on/edges（比此前已知的\"字段名不对\"更彻底），_normalize_graph_manifest 现在对 brd/prd/sdd/benchmark 四个规范 artifact_type 齐全时强制按已知的固定线性链补 depends_on，不再完全依赖 LLM 自己给对"}, {"id": "U-012", "phase": "PH1", "sub_phase": "PH1-S2", "name": "c_work_graph_execute 完整实现（见 development-plan.md 2026-07-31 范围说明）", "classification": "Value Path", "depends_on": ["U-006", "U-011"], "coverage": {"model": [], "view": [], "controller": ["c_work_graph_execute"], "process": ["p_work_graph_execution", "p_usage_limit_wait"], "requirement": ["REQ-07", "REQ-14"]}, "done": "REQ-07 boundary/failure 通过（happy 需 PH2 REQ-04/05/06 就绪后累计满足）；REQ-14 happy 通过。退避重试是整图级别，非逐节点；CLASSIFIER_BLOCKED 用单次调用 permission_denials≥3 近似判定"}, - {"id": "U-013", "phase": "PH1", "sub_phase": "PH1-S2", "name": "c_work_node_run + git worktree 隔离（见 development-plan.md 2026-07-31 订正、2026-08-02/03 真实 bug 修复）", "classification": "Value Path", "depends_on": ["U-012"], "coverage": {"model": ["work_node_execution"], "view": [], "controller": ["c_work_node_run"], "process": [], "requirement": ["REQ-03"]}, "done": "REQ-03 boundary 通过（真实 git worktree 隔离+merge，无冲突）；happy 需 c_artifact_write 落地后累计满足。2026-08-02/03：U-042 第一次真实自举压测发现 Coder 编辑 worktree 后从不 commit、merge_worktree 空操作、真实改动被 remove_worktree 静默吞掉的真实 bug，新增 ensure_worktree_committed() 兜底自动提交，已修复并补测试"}, + {"id": "U-013", "phase": "PH1", "sub_phase": "PH1-S2", "name": "c_work_node_run + git worktree 隔离（见 development-plan.md 2026-07-31 订正、2026-08-02/03 真实 bug 修复）", "classification": "Value Path", "depends_on": ["U-012"], "coverage": {"model": ["work_node_execution"], "view": [], "controller": ["c_work_node_run"], "process": [], "requirement": ["REQ-03"]}, "done": "REQ-03 boundary 通过（真实 git worktree 隔离+merge，无冲突）；happy 需 c_artifact_write 落地后累计满足。2026-08-02/03：U-042 第一次真实自举压测发现 Coder 编辑 worktree 后从不 commit、merge_worktree 空操作、真实改动被 remove_worktree 静默吞掉的真实 bug，新增 ensure_worktree_committed() 兜底自动提交；第八/九次压测又发现更深一层——worktree 和主仓库共享项目身份，memory:project 写入可能直接落在主仓库检出目录而非 worktree，导致下一个节点 merge 失败，已扩展 ensure_worktree_committed() 同时兜底主仓库自身、并把 .graphlemon-worktrees/ 加入 .gitignore，全部补了真实回归测试"}, {"id": "U-014", "phase": "PH1", "sub_phase": "PH1-S3", "name": "贪吃蛇场景端到端验收（含补建 c_artifact_write，见 development-plan.md 2026-07-31 实现补充）", "classification": "Value Path", "depends_on": ["U-011", "U-012", "U-013"], "coverage": {"model": ["artifact"], "view": [], "controller": ["c_artifact_write"], "process": [], "requirement": []}, "done": "架构文档 §11 验收标准第 1-3 条全部达成；plan_documents（Planner 四件套+血缘）真实验证过，Coder/Validator 全流程真实跑通待用户确认后执行"}, {"id": "U-015", "phase": "PH2", "sub_phase": "PH2-S1", "name": "p_validator_root_cause_trace 实现", "classification": "Risk Gate", "depends_on": ["U-013"], "coverage": {"model": ["bug_record"], "view": [], "controller": ["c_bug_record_create"], "process": ["p_validator_root_cause_trace"], "requirement": ["REQ-04"]}, "done": "REQ-04 happy/boundary/failure 通过"}, diff --git a/src/e2e_pipeline.py b/src/e2e_pipeline.py index 6f403f2..0b60067 100644 --- a/src/e2e_pipeline.py +++ b/src/e2e_pipeline.py @@ -187,6 +187,11 @@ def _check_prd_consistency(target_folder_path, prd_content, timeout=180): ) if worktree_path: work_node_run.ensure_worktree_committed(worktree_path, node_exec_id) + # also catch drift on the MAIN checkout (worktrees share project + # identity, so a real `memory: project` write can land there + # regardless of `cwd` -- see work_node_run.ensure_worktree_ + # committed's own docstring) before the merge below. + work_node_run.ensure_worktree_committed(target_folder_path, node_exec_id + "-main-checkout-drift") work_node_run.merge_worktree(target_folder_path, node_exec_id) return _coerce_bool(result["consistent"]), result.get("issues", []) finally: diff --git a/src/test_e2e_pipeline.py b/src/test_e2e_pipeline.py index 9a94931..77195ed 100644 --- a/src/test_e2e_pipeline.py +++ b/src/test_e2e_pipeline.py @@ -235,7 +235,14 @@ class PrdConsistencySelfTargetWorktreeTest(unittest.TestCase): # WORKTREE path as cwd, never the main checkout, when self-targeting self.assertEqual(mock_write.call_args[0][0], "/repo/.graphlemon-worktrees/x") self.assertEqual(mock_execute.call_args[0][0], "/repo/.graphlemon-worktrees/x") - mock_ensure.assert_called_once() + # called twice: once for the worktree itself, once for the main + # checkout (worktrees share project identity, so a real memory + # write can land on the main checkout regardless of cwd -- see + # work_node_run.ensure_worktree_committed's own docstring) + self.assertEqual(mock_ensure.call_count, 2) + ensure_paths = [call.args[0] for call in mock_ensure.call_args_list] + self.assertIn("/repo/.graphlemon-worktrees/x", ensure_paths) + self.assertIn("/repo", ensure_paths) mock_merge.assert_called_once() mock_remove.assert_called_once() diff --git a/src/test_work_node_run.py b/src/test_work_node_run.py index 5cd3c33..040fc73 100644 --- a/src/test_work_node_run.py +++ b/src/test_work_node_run.py @@ -425,6 +425,40 @@ class RealGitWorktreeIsolationTest(WorkNodeRunTestBase): ).stdout self.assertEqual(status.strip(), "") + def test_drift_on_main_checkout_is_auto_committed_before_merge(self): + # 2026-08-03 regression: git worktrees deliberately share project + # identity with their main checkout -- a real self-hosting run + # showed `claude`'s own memory writes can land on the MAIN + # checkout (repo_path) instead of the worktree, regardless of + # cwd. If left uncommitted, the NEXT node's own worktree merge + # fails with "local changes would be overwritten by merge". This + # run_fn simulates that: it writes a file directly into repo_path + # (not cwd, i.e. not the worktree) to reproduce main-checkout + # drift caused by something outside the node's own isolated work. + def run_fn(cwd, model=None): + with open(os.path.join(self.tmp.name, "main-checkout-drift.txt"), "w") as f: + f.write("landed on the main checkout, not the worktree") + return {"value": "done"} + + work_node_run.run_work_node( + self.conn, "node-1", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, + run_fn=run_fn, needs_worktree=True, repo_path=self.tmp.name, + ) + + status = subprocess.run( + ["git", "status", "--porcelain"], cwd=self.tmp.name, check=True, capture_output=True, text=True + ).stdout + self.assertEqual(status.strip(), "", "main checkout drift must be auto-committed, not left dirty") + self.assertTrue(os.path.isfile(os.path.join(self.tmp.name, "main-checkout-drift.txt"))) + + # a SECOND node's own worktree merge must not fail because of it + work_node_run.run_work_node( + self.conn, "node-2", {"goal": "x"}, _IN_SCHEMA, _OUT_SCHEMA, + run_fn=self._write_file_run_fn("module_b.txt", "module b content"), + needs_worktree=True, repo_path=self.tmp.name, + ) + self.assertTrue(os.path.isfile(os.path.join(self.tmp.name, "module_b.txt"))) + class BreakpointRecoveryTest(WorkNodeRunTestBase): """U-021 / REQ-06: run_work_node called again for a node_exec_id that was diff --git a/src/work_node_run.py b/src/work_node_run.py index bafefb4..9183d6c 100644 --- a/src/work_node_run.py +++ b/src/work_node_run.py @@ -117,7 +117,7 @@ def create_worktree(repo_path, node_exec_id): return worktree_path -def ensure_worktree_committed(worktree_path, node_exec_id): +def ensure_worktree_committed(path, node_exec_id): """A Coder Work Node is never actually required to `git commit` its own edits before finishing -- nothing in its persona instructs it to, and every prior test's `run_fn` happened to commit its own changes, so this @@ -126,19 +126,40 @@ def ensure_worktree_committed(worktree_path, node_exec_id): merge_worktree() found nothing to merge (a no-op "Already up to date" merge) -- remove_worktree() then silently discarded the dirty working tree along with the real work. Auto-commits any uncommitted state left - in the worktree before it gets merged, so "the Coder said it edited a + at `path` before a merge is attempted, so "the Coder said it edited a file" and "the change actually lands" can't diverge silently. No-op - when the worktree is already clean (a node that legitimately made no - changes, e.g. a pure investigation).""" + when `path` is already clean (a node that legitimately made no + changes, e.g. a pure investigation). + + **Also called on `repo_path` itself, not just the worktree (2026-08-03, + real self-hosting run)**: git worktrees deliberately SHARE project + identity with their main checkout -- a real run showed that `claude + -p`'s own `memory: project` writes land on the main checkout's + `.claude/agent-memory/` regardless of which worktree `cwd` the call + actually ran in (worktree-wrapping one specific call, as first tried + for `_check_prd_consistency`, only moves around which call happens to + trigger this, it doesn't prevent it). Calling this same, already-tested + committer on `repo_path` right before every `merge_worktree()` closes + that gap generically, regardless of which real call caused the drift or + why -- `path` being a worktree or the main checkout doesn't change what + "auto-commit any dirty state here" means.""" + # `.graphlemon-worktrees/` (create_worktree's own checkout location) + # lives INSIDE repo_path while a node is running -- excluded from both + # the dirty-check and the add, not just relying on the caller repo + # having a matching .gitignore (2026-08-03: without this, `git add -A` + # on repo_path picked up the still-present worktree checkout itself as + # a tracked gitlink-like entry, which then showed as "deleted" the + # moment remove_worktree() ran right after). + exclude_worktrees = ["--", ".", ":!.graphlemon-worktrees"] status = subprocess.run( - ["git", "status", "--porcelain"], cwd=worktree_path, check=True, capture_output=True, text=True, + ["git", "status", "--porcelain"] + exclude_worktrees, cwd=path, check=True, capture_output=True, text=True, ).stdout if not status.strip(): return - subprocess.run(["git", "add", "-A"], cwd=worktree_path, check=True, capture_output=True) + subprocess.run(["git", "add", "-A"] + exclude_worktrees, cwd=path, check=True, capture_output=True) subprocess.run( - _prefix_git(["commit", "-m", "graphlemon: auto-commit uncommitted worktree changes for " + node_exec_id]), - cwd=worktree_path, check=True, capture_output=True, text=True, + _prefix_git(["commit", "-m", "graphlemon: auto-commit uncommitted changes for " + node_exec_id]), + cwd=path, check=True, capture_output=True, text=True, ) @@ -342,6 +363,12 @@ def run_work_node( conn.commit() if worktree_path: ensure_worktree_committed(worktree_path, node_exec_id) + # also catch drift on the MAIN checkout itself (e.g. a + # real `memory: project` write that landed there instead + # of the worktree, see this function's own docstring) -- + # otherwise the merge below can fail with "local changes + # would be overwritten by merge". + ensure_worktree_committed(repo_path, node_exec_id + "-main-checkout-drift") merge_worktree(repo_path, node_exec_id) remove_worktree(repo_path, worktree_path) # 03-C §3.6: "执行完成后清理 worktree" return output_payload -- libgit2 0.21.4