align: 第二批：把技能包播种进租户 codex-home

仿 websearch MCP 播种，默认关：
- cloud/skill_seed.py：cloud/skills/ 的 SKILL.md 拷进租户
  codex-home/.agents/skills/（个人级技能路径，见模块
  文档的路径依据与诚实边界）；幂等，租户改过的文件
  绝不覆盖（上报 differs），缺包不阻塞任务。
- cloud/worker.py：新增 --seed-skills，_tenant_dirs 里
  调用播种；老租户下一次任务自动合并；播种失败只记
  日志、不阻塞任务（技能是可选流程说明）。
- cloud/tests/test_skill_seed_worker.py：播种助手 + worker
  开关，仿 test_websearch_worker.py 的结构。
- docs/chatgpt-codex-alignment.md：补第二批说明与实测
  待办（真实 Docker 任务 skills/list + $live-info 调用，
  通过前不宣称生产任务已能用这些技能）。

验证：skill_seed + chatgpt skills + websearch worker
共 14 项全过。本批不改生产配置、不部署，autoscaler
加 --seed-skills 是部署时另行的主机步骤。

cloud/skill_seed.py

@@ -0,0 +1,117 @@
+"""Seed ChatGPT-Codex-alignment skills into a tenant codex-home.
+
+Mirrors the websearch MCP seeding pattern in cloud/websearch.py,
+but for skills, not MCP config:
+
+- Source is cloud/skills/<name>/SKILL.md (the batch-1 skill pack).
+- Destination is <codex-home>/.agents/skills/<name>/SKILL.md.
+  Why this path: Codex documents personal skills at
+  $HOME/.agents/skills and project skills at .agents/skills
+  (scanned from the working directory up to the repo root).
+  A Docker tenant task must not pollute its task repo/worktree
+  (seeding into the worktree would show up in the task diff),
+  so the tenant codex-home -- the per-project persistent home
+  that is mounted into the container at
+  /var/lib/codex-app-server/codex-home -- is the personal-level
+  analogue. This is the same channel websearch MCP seeding uses.
+- Idempotent and non-destructive by design:
+  - a missing destination file is copied;
+  - an identical destination file is left alone;
+  - a differing destination file is NEVER overwritten (that is
+    a tenant-modified skill) -- it is reported in
+    ``skills_skipped_differ`` and left alone;
+  - a skill directory without SKILL.md is skipped, never invented.
+- No config.toml change, no key, no network: skills are plain
+  instruction files, and the helper never writes secrets.
+
+Honest boundary (see docs/chatgpt-codex-alignment.md): the
+destination path follows the documented personal-skills pattern
+mapped onto the tenant home. Whether a given Codex build picks
+these skills up in a Docker tenant task still needs a live
+verification task (skills/list + an explicit $live-info call),
+the same kind of e2e probe websearch MCP got after its seeding
+PR. Until that probe passes, do not claim the skills are live
+in production tasks -- this helper only guarantees the files
+land in the tenant home, idempotently, without clobbering
+tenant edits.
+"""
+
+import os
+import shutil
+from pathlib import Path
+
+# cloud/skills/<name>/SKILL.md, next to this module.
+SKILLS_DIR = Path(__file__).resolve().parent / "skills"
+# Personal-level skills inside a codex-home.
+DEST_SUBDIR = Path(".agents") / "skills"
+
+
+def skill_source_dir(skills_dir=None):
+    """Skill pack directory: explicit override or cloud/skills/."""
+    if skills_dir is not None:
+        return Path(skills_dir)
+    return SKILLS_DIR
+
+
+def list_skills(skills_dir=None):
+    """[(name, SKILL.md path)] for every skill in the pack."""
+    src = skill_source_dir(skills_dir)
+    out = []
+    if not src.is_dir():
+        return out
+    for entry in sorted(src.iterdir()):
+        if not entry.is_dir():
+            continue
+        skill_file = entry / "SKILL.md"
+        if skill_file.is_file():
+            out.append((entry.name, skill_file))
+    return out
+
+
+def ensure_codex_home_skills(codex_home_dir, skills_dir=None):
+    """Copy the skill pack into a tenant codex-home.
+
+    Returns {"dest_dir", "skills_copied", "skills_skipped_differ",
+    "skills_skipped_missing"}: copied = names newly written,
+    skipped_differ = names whose destination SKILL.md differs
+    from the pack (tenant-modified, left alone), skipped_missing
+    = skill directories in the pack without a SKILL.md file
+    (should not happen; the batch-1 test guards it).
+    A missing source directory yields all-empty lists, never
+    an exception: skills are optional, a missing pack must not
+    block a task the way a missing websearch config would.
+    """
+    home = Path(codex_home_dir)
+    dest_root = home / DEST_SUBDIR
+    dest_root.mkdir(parents=True, exist_ok=True)
+    copied = []
+    skipped_differ = []
+    skipped_missing = []
+    src = skill_source_dir(skills_dir)
+    if not src.is_dir():
+        return {"dest_dir": str(dest_root), "skills_copied": copied,
+                "skills_skipped_differ": skipped_differ,
+                "skills_skipped_missing": skipped_missing}
+    # Directories in the pack, including ones without SKILL.md,
+    # so a broken pack is reported instead of silently dropped.
+    for entry in sorted(src.iterdir()):
+        if not entry.is_dir():
+            continue
+        skill_file = entry / "SKILL.md"
+        if not skill_file.is_file():
+            skipped_missing.append(entry.name)
+            continue
+        dest_dir = dest_root / entry.name
+        dest_file = dest_dir / "SKILL.md"
+        src_bytes = skill_file.read_bytes()
+        if dest_file.is_file():
+            if dest_file.read_bytes() == src_bytes:
+                continue
+            skipped_differ.append(entry.name)
+            continue
+        dest_dir.mkdir(parents=True, exist_ok=True)
+        shutil.copyfile(skill_file, dest_file)
+        copied.append(entry.name)
+    return {"dest_dir": str(dest_root), "skills_copied": copied,
+            "skills_skipped_differ": skipped_differ,
+            "skills_skipped_missing": skipped_missing}

cloud/tests/test_skill_seed_worker.py

@@ -0,0 +1,132 @@
+"""Worker wiring for ChatGPT-Codex-alignment skills: tenant seeding.
+
+Mirrors test_websearch_worker.py: no Docker, no network, no real
+model. _tenant_dirs runs against temp dirs; the skill pack used
+here is the real cloud/skills/ pack, so a broken pack fails here
+before it ever reaches a tenant.
+"""
+
+import os
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+try:
+    from cloud.server import init_db
+    from cloud.worker import Worker
+    from cloud.skill_seed import ensure_codex_home_skills, list_skills
+except ImportError:
+    sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
+    from cloud.server import init_db
+    from cloud.worker import Worker
+    from cloud.skill_seed import ensure_codex_home_skills, list_skills
+
+
+class SkillSeedHelperTestCase(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+
+    def tearDown(self):
+        self.tmp.cleanup()
+
+    def _src(self):
+        src = os.path.join(self.tmp.name, "pack")
+        for name in ("live-info", "document-tools"):
+            d = os.path.join(src, name)
+            os.makedirs(d, exist_ok=True)
+            open(os.path.join(d, "SKILL.md"), "w").write(
+                "---\nname: %s\ndescription: test\n---\nbody\n" % name)
+        return src
+
+    def test_copy_idempotent_and_missing_source(self):
+        home = os.path.join(self.tmp.name, "home")
+        out = ensure_codex_home_skills(home, self._src())
+        self.assertEqual(sorted(out["skills_copied"]),
+                         ["document-tools", "live-info"])
+        self.assertEqual(out["skills_skipped_differ"], [])
+        out2 = ensure_codex_home_skills(home, self._src())
+        self.assertEqual(out2["skills_copied"], [])
+        out3 = ensure_codex_home_skills(
+            os.path.join(self.tmp.name, "home2"),
+            os.path.join(self.tmp.name, "no-such-pack"))
+        self.assertEqual(out3["skills_copied"], [])
+
+    def test_tenant_modified_skill_is_never_overwritten(self):
+        home = os.path.join(self.tmp.name, "home")
+        src = self._src()
+        ensure_codex_home_skills(home, src)
+        dest = os.path.join(home, ".agents", "skills",
+                            "live-info", "SKILL.md")
+        open(dest, "w").write("tenant edited version\n")
+        out = ensure_codex_home_skills(home, src)
+        self.assertEqual(out["skills_skipped_differ"], ["live-info"])
+        self.assertEqual(open(dest).read(), "tenant edited version\n")
+
+    def test_real_pack_lists_three_skills(self):
+        names = [n for n, _p in list_skills()]
+        self.assertEqual(names,
+                         ["document-tools", "image-workflow",
+                          "live-info"])
+
+
+class WorkerSkillSeedTestCase(unittest.TestCase):
+    def setUp(self):
+        self.tmp = tempfile.TemporaryDirectory()
+        self.db_path = os.path.join(self.tmp.name, "control.db")
+        init_db(self.db_path)
+        self.template_home = os.path.join(self.tmp.name, "tpl-home")
+        os.makedirs(self.template_home)
+        open(os.path.join(self.template_home, "config.toml"),
+             "w").write('[model_provider.xcmapi]\n'
+                         'base_url="https://xcmapi.org/v1"\n')
+        self.template_repo = os.path.join(self.tmp.name, "tpl-repo")
+        os.makedirs(os.path.join(self.template_repo, ".git"))
+        open(os.path.join(self.template_repo, "sample.py"),
+             "w").write("def add(a, b):\n    return a + b\n")
+
+    def tearDown(self):
+        self.tmp.cleanup()
+
+    def _worker(self, **kwargs):
+        kwargs.setdefault("env", {"XCM_API_KEY": "test-placeholder"})
+        kwargs.setdefault("tenants_root",
+                          os.path.join(self.tmp.name, "tenants"))
+        kwargs.setdefault("tenant_template_home", self.template_home)
+        kwargs.setdefault("tenant_template_repo", self.template_repo)
+        kwargs.setdefault("tenant_isolation", True)
+        return Worker(self.db_path, "/fake/host.py", **kwargs)
+
+    def _skill_path(self, dirs, name):
+        return os.path.join(dirs["codex_home"], ".agents", "skills",
+                            name, "SKILL.md")
+
+    def test_flag_off_is_old_behaviour(self):
+        worker = self._worker()
+        self.assertFalse(worker.seed_skills)
+        dirs = worker._tenant_dirs("projA")
+        self.assertFalse(os.path.exists(
+            os.path.join(dirs["codex_home"], ".agents", "skills")))
+
+    def test_flag_on_seeds_real_pack(self):
+        worker = self._worker(seed_skills=True)
+        dirs = worker._tenant_dirs("projA")
+        for name in ("live-info", "document-tools", "image-workflow"):
+            path = self._skill_path(dirs, name)
+            self.assertTrue(os.path.exists(path), path)
+            self.assertIn("name: %s" % name, open(path).read())
+
+    def test_old_tenant_merges_and_user_edit_survives(self):
+        worker = self._worker()
+        dirs = worker._tenant_dirs("projA")
+        worker2 = self._worker(seed_skills=True)
+        worker2._tenant_dirs("projA")
+        path = self._skill_path(dirs, "live-info")
+        self.assertTrue(os.path.exists(path))
+        open(path, "w").write("tenant edited version\n")
+        worker2._tenant_dirs("projA")
+        self.assertEqual(open(path).read(), "tenant edited version\n")
+
+
+if __name__ == "__main__":
+    unittest.main()

cloud/worker.py

@@ -166,6 +166,7 @@ from cloud.peer_messages import peer_message_prefix as _peer_prefix
 from cloud.peer_messages import row_get as _row_get
 from cloud.sub2api import ensure_user_gateway_key as _ensure_sub2api_key
 from cloud.websearch import ensure_codex_home_websearch as _ensure_websearch_mcp
+from cloud.skill_seed import ensure_codex_home_skills as _ensure_skills
 from cloud.sub2api import gateway_name as _gateway_name
 from cloud.sub2api import gateway_origin as _gateway_origin
 from cloud.sub2api import list_gateway_models as _list_gateway_models
@@ -412,7 +413,7 @@ class Worker:
                  tenant_isolation=False, tenants_root=None,
                  tenant_template_home=None, tenant_template_repo=None,
                  egress_proxy_port=0, claim_executor_only=False,
-                 websearch_mcp=False,
+                 websearch_mcp=False, seed_skills=False,
                  host_name=None, pr_jobs_only=False,
                  upload_dir=None,
                  digest_interval_seconds=3600,
@@ -565,6 +566,14 @@ class Worker:
         # [mcp_servers.websearch]（容器内路径，见 _tenant_dirs）。
         # 老租户下一次任务自动合并，已有 section 不重写。
         self.websearch_mcp = bool(websearch_mcp)
+        # 技能播种：默认关（老行为：租户 codex-home 只有模板
+        # config.toml + 可选的 websearch MCP）。开启后
+        # _tenant_dirs 在 websearch 播种之后调用 skill_seed
+        # 的播种助手，把 cloud/skills/ 的 SKILL.md 拷进租户
+        # codex-home/.agents/skills/（个人级技能路径，见
+        # skill_seed.py 的路径说明）。老租户下一次任务自动
+        # 合并；租户改过的技能文件绝不覆盖，只上报 differs。
+        self.seed_skills = bool(seed_skills)
         # HA 阶段 1：本 worker 所在主机名。认领任务时写进
         # tasks.worktree_host，/pr 据此判断 worktree 在哪台主机。
         # 容器内 worker 的 socket.gethostname() 是容器名、不是宿主名，
@@ -2403,6 +2412,24 @@ class Worker:
                     "python3",
                     "/var/lib/codex-app-server/codex-home/"
                     "websearch_mcp.py"])
+        if self.seed_skills:
+            # 技能播种失败绝不阻塞任务：技能是可选的流程
+            # 说明，不是 websearch 那种“已宣传就必须有”的
+            # 工具；播种助手本身对缺包、已存在、租户改动
+            # 都是静默处理，只在文件系统本身出错时才抛，
+            # 那种情况下任务仍应派发（技能缺失只影响流程，
+            # 不影响 agent 本身跑起来）。
+            try:
+                _ensure_skills(dirs["codex_home"])
+            except Exception as exc:
+                # 只记日志不阻塞：技能缺失只影响流程说明，
+                # 不应把一次可选播种失败变成任务派发失败。
+                # 但绝不静默吞掉——日志里要留下来供排查。
+                try:
+                    self.logger.warning(
+                        "skill seeding failed: %s", exc)
+                except Exception:
+                    pass
         if not os.path.exists(os.path.join(dirs["test_repo"], ".git")) \
                 and not os.path.exists(dirs["test_repo"] + "/sample.py"):
             # 目标为空目录（刚 mkdir 出来的）才播种；已有内容
@@ -5672,6 +5699,12 @@ def main(argv=None):
                              " [mcp_servers.websearch] 并拷入"
                              " websearch.py / websearch_mcp.py；"
                              "默认关，老租户不受影响")
+    parser.add_argument("--seed-skills", action="store_true",
+                        help="租户 codex-home 自动播种对齐技能包："
+                             "_tenant_dirs 把 cloud/skills/ 的 SKILL.md"
+                             " 拷进租户 codex-home/.agents/skills/；"
+                             "默认关，老租户不受影响；租户改过的"
+                             "技能文件绝不覆盖")
     parser.add_argument("--task-timeout", type=float, default=1800,
                         help="每任务截止时间（秒，默认 1800）；0 表示不限时"
                              "（与 host --turn-timeout 0 同约定，worker 级"
@@ -5733,7 +5766,8 @@ def main(argv=None):
                     tenant_template_repo=args.tenant_template_repo,
                     egress_proxy_port=args.egress_proxy_port,
                     claim_executor_only=args.claim_executor_only,
-                    websearch_mcp=args.websearch_mcp)
+                    websearch_mcp=args.websearch_mcp,
+                    seed_skills=args.seed_skills)
     # CLI 启动清理兜底（常驻与单次都做）：清掉上一轮残留容器。
     worker.cleanup_stale_containers()
     # CLI 起 worker 前先建表/迁移：全新库直接起循环不应因缺表而炸。