Merge pull request #155 from openqj/feat-chatgpt-codex-align1

ChatGPT Codex 对齐：技能包 + 租户播种 + web_search Docker 联网修法

cloud/skill_seed.py

@@ -0,0 +1,124 @@
+"""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>/skills/<name>/SKILL.md.
+  Why this path: verified live on 2026-10-30 with the real
+  Codex binary (host.py skills-list against a temp codex-home
+  on the production host, production untouched). The first
+  attempt -- <codex-home>/.agents/skills/ -- was NOT discovered
+  (skills/list returned only the 5 system skills). Copying the
+  same SKILL.md files to <codex-home>/skills/ made them appear
+  as scope=user (5 system + 3 ours, count 8). System skills
+  themselves live at <codex-home>/skills/.system/, which is
+  the tell that this is the user-skills directory for a
+  CODEX_HOME. 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 right channel.
+  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): discovery
+itself is now live-verified (skills/list, scope=user, on a temp
+home with the real Codex binary). What is NOT yet verified is
+model invocation inside a real Docker tenant task (an explicit
+$live-info call that actually runs and returns a result, and
+whether the relay model honours it). Until a task-level 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, and that
+skills/list sees them there.
+"""
+
+import os
+import shutil
+from pathlib import Path
+
+# cloud/skills/<name>/SKILL.md, next to this module.
+SKILLS_DIR = Path(__file__).resolve().parent / "skills"
+# User-level skills inside a codex-home (live-verified 2026-10-30:
+# .agents/skills inside a codex-home is NOT discovered).
+DEST_SUBDIR = Path("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/skills/document-tools/SKILL.md

@@ -0,0 +1,55 @@
+---
+name: document-tools
+description: 创建或编译 LaTeX 项目，处理 Word、PDF、表格和演示文稿时使用。先核查本机工具有没有，缺工具就明说，绝不假装产出了文件。
+---
+
+# document-tools：文档处理
+
+## 何时用
+
+用户要做 LaTeX 编译、Word（.docx）读写、PDF 读写、表格
+（.xlsx / .csv）处理、演示文稿（.pptx）制作时用。
+
+## 何时不用
+
+- 只是读一段纯文本、改代码、写 Markdown：不用本技能，
+  直接用文件工具。
+- 用户没说要产出文档，只是问文档里写了什么：先读文件，
+  不用走编译流程。
+
+## 工具前提（先核查，不满足就明说）
+
+在工作区 shell 里先查，缺什么就报什么，不要跳过核查直接写：
+
+- LaTeX：`latexmk` / `pdflatex` / `xelatex` 是否存在。
+- 通用转换：`pandoc` 是否存在。
+- Python 库：`python3 -c "import docx, openpyxl, pptx, fitz"`，
+  哪个 import 失败就说明哪个缺失。
+- PDF 阅读：`pdftotext` 或 Python 的 `fitz` / `pypdf`。
+
+核查命令本身不产出文件，核查失败时回答里写清“缺 XX，
+本环境无法编译 / 无法处理该格式”，并给出可替代的方案
+（例如只产出 Markdown / CSV），不要伪造一个文件路径。
+
+## 步骤
+
+1. 先确认输入和输出：输入文件路径、输出格式、输出路径、
+   语言（中文 LaTeX 优先 xelatex + CJK 字体，缺字体先报）。
+2. 选最小工具链：能用 pandoc 就不用手写 LaTeX 模板；
+   能用 Python 库读写就不用先转格式。
+3. 编译 / 生成后必须验证产出：
+   - 文件确实存在，大小不是 0。
+   - LaTeX：编译日志无致命错误（error / Emergency stop），
+     页数符合预期。
+   - docx / xlsx / pptx：用对应库重新打开一次，能读回
+     刚才写的内容（标题、表头、页数/幻灯片数）。
+   - PDF：能用 `pdftotext` 或 `fitz` 读回文本，确认不是空白页。
+4. 验证失败时不要把半成品当成品交，先贴出报错，再修。
+
+## 输出要求
+
+- 交代产出文件的真实路径、页数 / 幻灯片数 / 表格行数，
+  以及用哪条命令验证过。
+- 不要编造页数、字数、文件大小；写不出的就写“未验证”。
+- 涉及用户数据的文件不要写到工作区以外，不要上传到
+  第三方服务，除非用户明确要求。

cloud/skills/image-workflow/SKILL.md

@@ -0,0 +1,52 @@
+---
+name: image-workflow
+description: 查看、裁剪、缩放、格式转换已有图片，或在图片生成工具已配置时按描述生成/编辑图片时使用。未配置生成工具时必须明说无法生成，绝不把已有图片或占位图当成生成结果。
+---
+
+# image-workflow：图片查看与处理
+
+## 何时用
+
+- 查看已有图片、裁剪、缩放、转格式、读图片尺寸和格式。
+- 用户明确要求“按描述生成一张图”或“按描述改这张图”，
+  且本环境已配置图片生成工具 / API 时。
+
+## 何时不用
+
+- 只是写代码、改文本、查文档：不用本技能。
+- 用户要生成图片，但本环境没有生成工具：不要硬做，
+  走下面的“未配置”分支。
+
+## 工具前提（先核查，不满足就明说）
+
+1. 查看和处理已有图片：查 `python3 -c "import PIL"`，
+   以及 `convert` / `magick`（ImageMagick）是否存在。
+   有其一即可做裁剪、缩放、转格式；都没有就明说。
+2. 生成 / 编辑图片：先查任务环境里是否已配置图片生成
+   工具或 MCP / API（包括需要什么 key、走哪个 endpoint）。
+   没有配置时，回答必须是“本环境未配置图片生成工具，
+   无法按描述生成”，并给出替代方案（例如用 shell 画示意图、
+   或用户提供已有图片后做裁剪/缩放），绝不能：
+   - 把网上找来的图、占位图、已有图片说成是刚生成的；
+   - 编造一个图片路径或图片内容描述。
+
+## 步骤（已有图片处理）
+
+1. 先读原图信息：格式、尺寸、文件大小，确认输入路径存在。
+2. 按用户要求做裁剪 / 缩放 / 转格式，产出到用户指定的
+   路径（未指定时用工作区内的新文件名，不覆盖原图）。
+3. 验证产出：重新打开产出图，确认格式、尺寸符合要求，
+   文件大小不是 0。
+
+## 步骤（生成 / 编辑，仅当工具已配置时）
+
+1. 把用户描述原样记下来，不要自己加没说的元素。
+2. 调已配置的生成工具，记录工具名、提示词、产出路径。
+3. 验证产出图存在且能打开，再交给用户；失败时贴出
+   工具报错，不要换一张别的图顶替。
+
+## 输出要求
+
+- 每个产出图都要给真实路径和尺寸，生成类还要给提示词。
+- 未配置时不要绕弯子说“已生成”，直接说缺什么、
+  用户补什么才能生成。

cloud/skills/live-info/SKILL.md

@@ -0,0 +1,55 @@
+---
+name: live-info
+description: 查询天气、时区、股票价格、体育赛程等实时公开信息时使用。只用可查证的公开来源，绝不编造数字，回答必须带来源和快照时间。
+---
+
+# live-info：实时公开信息查询
+
+## 何时用
+
+用户问天气、时区换算、某只股票的当前价、某场比赛的赛程或比分等
+“现在是多少”类问题时用。编程任务里需要查官方文档、发布说明、
+最新版本时，同样走本技能的查证流程，不要凭记忆给数字。
+
+## 何时不用
+
+- 用户只问概念、历史、代码怎么写：不用本技能。
+- 已经有任务内文件、数据库、日志能直接回答的：以任务内证据为准，
+  不用再上网。
+
+## 工具前提（先核查，不满足就明说）
+
+1. 先确认本任务里是否有网页搜索工具（codex-app-server 里是
+   websearch MCP 的 `web_search` / `web_fetch`，生产 worker 需
+   带 `--websearch-mcp` 才播种）。没有搜索工具时，直接告诉用户
+   “本环境无联网查询工具，无法核实实时数字”，不要编一个。
+2. 有搜索工具时，优先查官方或一级来源：气象部门、交易所、
+   联赛/球队官网、时区数据库说明。聚合新闻、论坛、二手转载
+   只能当线索，不能当唯一来源。
+
+## 步骤
+
+1. 把问题拆成可查的实体 + 时间 + 地点：例如“北京明天天气”
+   → 城市 = 北京，日期 = 明天（换算成具体日期并写出来），
+   指标 = 气温/降水/风力。
+2. 用 `web_search` 查 1-2 个一级来源，打开来源页核对数字，
+   不要只抄搜索摘要。
+3. 股票：只报快照价 + 涨跌 + 快照时间，并说明“快照价不是
+   投资建议，盘中价格会变”。不要给买入/卖出建议。
+4. 时区：先写出两个时区的 UTC 偏移和夏令时状态，再换算，
+   不要只给换算结果。
+5. 体育赛程：写清联赛、主客队、开赛时间（含时区）、比分
+   是“已结束 / 进行中 / 未开始”哪一种。
+
+## 输出要求
+
+- 数字后面必须跟来源和时间，例如“来源：XX 官网，查询时间
+  2026-10-30 00:00 CST”。
+- 查不到、来源冲突、或时间已过期时，明说查不到 / 冲突，
+  不要选一个看起来顺眼的数字。
+- 不要把预测（天气预报、分析师目标价）写成事实。
+
+## 校验
+
+回答前自查：每个数字都有来源吗？时间写了吗？时区写了吗？
+有一项没有，就补查或删掉该数字。

cloud/tests/test_chatgpt_codex_skills.py

@@ -0,0 +1,52 @@
+"""ChatGPT Codex 对齐第一批：技能包校验。
+
+只校验技能文件本身，不启动 worker、不跑模型、不改生产行为：
+每个 cloud/skills/<名>/SKILL.md 必须有 name + description
+frontmatter、名字与目录一致、正文非空、不含密钥占位。
+"""
+
+import os
+import re
+import unittest
+from pathlib import Path
+
+SKILLS_DIR = Path(__file__).resolve().parents[1] / "skills"
+EXPECTED = {"live-info", "document-tools", "image-workflow"}
+
+
+def _frontmatter(text):
+    m = re.match(r"^---\n(.*?)\n---\n", text, re.DOTALL)
+    if not m:
+        return None
+    out = {}
+    for line in m.group(1).splitlines():
+        if ":" in line:
+            k, v = line.split(":", 1)
+            out[k.strip()] = v.strip()
+    return out
+
+
+class ChatGptCodexSkillsTestCase(unittest.TestCase):
+    def test_expected_skills_exist(self):
+        names = {p.name for p in SKILLS_DIR.iterdir() if p.is_dir()}
+        self.assertEqual(names, EXPECTED)
+
+    def test_skill_frontmatter_and_body(self):
+        for name in sorted(EXPECTED):
+            path = SKILLS_DIR / name / "SKILL.md"
+            self.assertTrue(path.is_file(), str(path))
+            text = path.read_text(encoding="utf-8")
+            fm = _frontmatter(text)
+            self.assertIsNotNone(fm, name)
+            self.assertEqual(fm.get("name"), name)
+            desc = fm.get("description", "")
+            self.assertTrue(desc, name)
+            self.assertLessEqual(len(desc), 200, name)
+            body = text.split("---", 2)[-1].strip()
+            self.assertTrue(len(body) > 200, name)
+            for bad in ("API_KEY", "sk-", "password"):
+                self.assertNotIn(bad, text, name)
+
+
+if __name__ == "__main__":
+    unittest.main()

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, "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"], "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"], "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/tests/test_websearch_mcp_env.py

@@ -0,0 +1,71 @@
+"""ensure_websearch_mcp_env: MCP env lives in config.toml, because
+Codex's MCP subprocess does not inherit the Codex process env
+(2026-10-30: Codex bash had SEARXNG_URL + proxy, MCP chain was
+still ["duckduckgo"] only; adding the config env section made
+the same task return real SearXNG results)."""
+
+import os
+import sys
+import tempfile
+import unittest
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
+from cloud.websearch import ensure_websearch_mcp_env  # noqa: E402
+
+
+BASE = ("model = \"gpt-6.1-sol\"\n\n"
+        "[mcp_servers.websearch]\n"
+        "command = \"python3\"\n"
+        "args = [\"/var/lib/codex-app-server/codex-home/"
+        "websearch_mcp.py\"]\n")
+
+
+class TestMcpEnv(unittest.TestCase):
+    def _home(self, text):
+        tmp = tempfile.mkdtemp()
+        with open(os.path.join(tmp, "config.toml"), "w") as fh:
+            fh.write(text)
+        return tmp
+
+    def _read(self, home):
+        with open(os.path.join(home, "config.toml")) as fh:
+            return fh.read()
+
+    def test_insert_env_after_websearch_section(self):
+        home = self._home(BASE)
+        self.assertTrue(ensure_websearch_mcp_env(
+            home, {"SEARXNG_URL": "http://searx.test",
+                   "http_proxy": "http://10.0.0.1:8888"}))
+        text = self._read(home)
+        self.assertIn("[mcp_servers.websearch.env]", text)
+        self.assertIn('SEARXNG_URL = "http://searx.test"', text)
+        self.assertIn('http_proxy = "http://10.0.0.1:8888"', text)
+        self.assertIn('command = "python3"', text)
+
+    def test_replace_existing_env_preserves_other_sections(self):
+        home = self._home(BASE + "[mcp_servers.websearch.env]\n"
+                          "SEARXNG_URL = \"http://old.test\"\n\n"
+                          "[other]\nfoo = 1\n")
+        self.assertTrue(ensure_websearch_mcp_env(
+            home, {"SEARXNG_URL": "http://new.test"}))
+        text = self._read(home)
+        self.assertIn('SEARXNG_URL = "http://new.test"', text)
+        self.assertNotIn("old.test", text)
+        self.assertIn("[other]\nfoo = 1", text)
+
+    def test_empty_env_writes_nothing(self):
+        home = self._home(BASE)
+        self.assertFalse(ensure_websearch_mcp_env(home, {}))
+        self.assertEqual(self._read(home), BASE)
+
+    def test_idempotent_second_write(self):
+        home = self._home(BASE)
+        env = {"SEARXNG_URL": "http://searx.test"}
+        self.assertTrue(ensure_websearch_mcp_env(home, env))
+        self.assertFalse(ensure_websearch_mcp_env(home, env))
+        self.assertEqual(self._read(home).count(
+            "[mcp_servers.websearch.env]"), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

cloud/tests/test_websearch_searxng.py

@@ -0,0 +1,52 @@
+"""SearXNG provider: engines are pinned, not left to the default
+general category (2026-10-30: default took 20s in a Docker task,
+pinned bing,360search took 0.47s via the same egress proxy)."""
+
+import json
+import os
+import sys
+import unittest
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
+from cloud.websearch import _provider_searxng  # noqa: E402
+
+
+class _FakeHttp:
+    def __init__(self):
+        self.urls = []
+
+    def get(self, url, headers=None):
+        self.urls.append(url)
+        body = json.dumps({"results": [
+            {"title": "Beijing weather", "url": "https://example.test/w",
+             "content": "sunny"}]}).encode("utf-8")
+        return 200, body, "application/json"
+
+
+class TestSearXNGEngines(unittest.TestCase):
+    def test_default_pins_bing_360search(self):
+        http = _FakeHttp()
+        results, _ = _provider_searxng(
+            "Beijing weather", 3, {"SEARXNG_URL": "http://searx.test"},
+            http)
+        self.assertEqual(len(results), 1)
+        self.assertIn("engines=bing%2C360search", http.urls[0])
+
+    def test_env_overrides_pin(self):
+        http = _FakeHttp()
+        _provider_searxng(
+            "q", 3, {"SEARXNG_URL": "http://searx.test",
+                     "SEARXNG_ENGINES": "bing"}, http)
+        self.assertIn("engines=bing", http.urls[0])
+        self.assertNotIn("360search", http.urls[0])
+
+    def test_empty_env_restores_unpinned(self):
+        http = _FakeHttp()
+        _provider_searxng(
+            "q", 3, {"SEARXNG_URL": "http://searx.test",
+                     "SEARXNG_ENGINES": ""}, http)
+        self.assertNotIn("engines=", http.urls[0])
+
+
+if __name__ == "__main__":
+    unittest.main()

cloud/websearch.py

@@ -267,8 +267,22 @@ def _provider_searxng(query, limit, env, http):
     base = (env.get("SEARXNG_URL") or "").rstrip("/")
     if not base:
         raise WebSearchError("searxng not configured (SEARXNG_URL unset)")
-    url = (base + "/search?"
-           + urllib.parse.urlencode({"q": query, "format": "json"}))
+    # Engines are pinned, not left to SearXNG's default "general"
+    # category. Measured 2026-10-30 on the production host:
+    # default general search took 20.0s in a Docker task container
+    # (wikipedia / wikidata / brave / duckduckgo / google engines
+    # all timing out, only bing + 360search returning), which hits
+    # the MCP's 20s timeout and then falls through to DuckDuckGo,
+    # which itself times out via the egress proxy -- so the whole
+    # chain fails even though SearXNG can answer. Pinning to the
+    # two proven-fast engines cuts the same query to 0.47s via
+    # the same proxy. SEARXNG_ENGINES overrides the pin; an empty
+    # value restores the old unpinned behaviour.
+    params = {"q": query, "format": "json"}
+    engines = env.get("SEARXNG_ENGINES", "bing,360search")
+    if engines:
+        params["engines"] = engines
+    url = base + "/search?" + urllib.parse.urlencode(params)
     _status, body, _ctype = http.get(url, _default_headers(env, "searxng"))
     data = json.loads(body.decode("utf-8", errors="replace"))
     results = []
@@ -633,3 +647,79 @@ def ensure_codex_home_websearch(codex_home_dir, command_args=None,
             "config_changed": config_changed,
             "script_changed": script_changed,
             "script_differs": script_differs}
+
+
+def ensure_websearch_mcp_env(codex_home_dir, env):
+    """Write [mcp_servers.websearch.env] into a tenant config.toml.
+
+    Why this exists (measured 2026-10-30, not guessed): Codex's
+    MCP server subprocess does NOT inherit the Codex process env.
+    A Docker task whose Codex bash env contained SEARXNG_URL and
+    http_proxy still ran web_search with chain ["duckduckgo"]
+    only, failing instantly with "Temporary failure in name
+    resolution" -- SEARXNG_URL never reached the MCP process, and
+    without a proxy the container has no direct DNS. Adding an
+    explicit ``env`` table to the MCP config made the same task
+    return real SearXNG results. Container env (docker -e) is
+    therefore NOT sufficient for MCP tools; the env must live in
+    config.toml, where Codex actually reads it for MCP servers.
+
+    Idempotent: an existing env subsection is replaced in place,
+    other sections are left untouched, and a missing websearch
+    section is created first (command/args only, no env values
+    invented). Values are written as TOML basic strings via
+    json.dumps (safe for URLs and proxy URLs). Returns True when
+    the file was written, False when env is empty or the file
+    could not be written (caller logs, never crashes the task).
+    """
+    if not env:
+        return False
+    home = os.path.abspath(codex_home_dir)
+    config_path = os.path.join(home, "config.toml")
+    try:
+        existing = ""
+        if os.path.exists(config_path):
+            with open(config_path, encoding="utf-8") as fh:
+                existing = fh.read()
+        if "[mcp_servers.websearch]" not in existing:
+            existing += ("\n[mcp_servers.websearch]\n"
+                         "command = \"python3\"\n"
+                         "args = [\"/var/lib/codex-app-server/"
+                         "codex-home/websearch_mcp.py\"]\n")
+        env_lines = ["[mcp_servers.websearch.env]"]
+        for key in sorted(env):
+            env_lines.append("%s = %s" % (key, json.dumps(env[key])))
+        env_block = "\n".join(env_lines) + "\n"
+        lines = existing.splitlines(keepends=True)
+        start = end = None
+        for i, line in enumerate(lines):
+            if line.strip() == "[mcp_servers.websearch.env]":
+                start = i
+            elif start is not None and line.startswith("["):
+                end = i
+                break
+        if start is not None:
+            if end is None:
+                end = len(lines)
+            lines[start:end] = [env_block]
+            new_text = "".join(lines)
+        else:
+            insert_at = None
+            in_section = False
+            for i, line in enumerate(lines):
+                if line.strip() == "[mcp_servers.websearch]":
+                    in_section = True
+                elif in_section and line.startswith("["):
+                    insert_at = i
+                    break
+            if insert_at is None:
+                insert_at = len(lines)
+            lines.insert(insert_at, env_block)
+            new_text = "".join(lines)
+        if new_text == existing:
+            return False
+        with open(config_path, "w", encoding="utf-8") as fh:
+            fh.write(new_text)
+        return True
+    except Exception:
+        return False

cloud/worker.py

@@ -166,6 +166,8 @@ 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.websearch import ensure_websearch_mcp_env as _ensure_websearch_mcp_env
+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 +414,7 @@ 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 +567,14 @@ 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/skills/（用户级技能路径，实测见
+        # 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 +2413,24 @@ 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
@@ -2789,12 +2817,29 @@ class Worker:
         # 走 extra_env（容器内进程本就需要它调 API）。
         search_env = {
             k: os.environ[k]
-            for k in ("SEARXNG_URL", "PERPLEXITY_API_KEY", "EXA_API_KEY",
+            for k in ("SEARXNG_URL", "SEARXNG_ENGINES",
+                      "PERPLEXITY_API_KEY", "EXA_API_KEY",
                       "TAVILY_API_KEY", "BRAVE_API_KEY")
             if os.environ.get(k)
         }
         if search_env:
             proxy_env = _merge_env(proxy_env, search_env)
+        # MCP env must live in config.toml, not just docker -e:
+        # Codex's MCP subprocess does not inherit the Codex
+        # process env (2026-10-30实测：Codex bash 里有
+        # SEARXNG_URL + proxy，MCP 链却只有 duckduckgo，
+        # DNS 瞬间失败；给 config 加 [mcp_servers.websearch.env]
+        # 后同一任务立刻返回真实 SearXNG 结果）。网关在此时
+        # 才已知，所以这里、容器启动前写租户 config，绝不
+        # 在播种时写死一个网关。写失败只记日志，不阻塞任务。
+        if self.tenant_isolation and proxy_env:
+            try:
+                home = self._tenant_dirs(
+                    task.get("project_id"))["codex_home"]
+                _ensure_websearch_mcp_env(home, proxy_env)
+            except Exception as exc:
+                self.logger.warning(
+                    "websearch MCP env write failed: %s" % exc)
         return (True, tenant_mounts, tenant_network, proxy_env, None)
 
     def _run_fork(self, task, quota_check=None):
@@ -5672,6 +5717,12 @@ 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/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 +5784,8 @@ 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。