HA 阶段 1：worktree_host + 跨主机 /pr 队列化 (#50)

* 部署自动化：唯一发布链路 deploy.py + host_deploy.sh，sha/commit 双重验真，失败回滚旧链路三次栽过的坑：通用 tar 路径导致旧包误部署、传输不验 sha、主机脚本多份漂移、health 通过不等于新代码上线。本单把四点变硬门禁： - 产物唯一命名 codex-app-server-<commit>.tar.gz + .sha256，远端唯一路径 - git archive 产物 + DEPLOYED_COMMIT 清单，默认拒绝脏工作区 - 传输链 scp -> scp_run -> chunk 分片，每路传完远端验 sha，不符删掉重来 - 主机侧唯一脚本：先验 sha/清单，staging 解包 + 编译检查，换目录上线， work/ 原样保留，health + 上线 commit 不符即回滚并退出非零 - deploy.py 成功后独立 ssh 再读一次 live 清单二次核对 - CI：host-verify 加 deploy/tests；release.yml 只在手动/tag + production environment 审批时部署，主干推送绝不自动部署生产 - deploy.sh 标记为旧链路弃用 - health 的 commit 字段已在父提交 HA 阶段 0 里随 server.py 落地，本分支整体包含它；commit 为空时只靠文件核对，门禁同样成立测试：host 32、cloud 487（4 跳过）、deploy 9，全部通过； host_deploy.sh 仿真覆盖成功/坏 sha/清单不符/health commit 不符回滚。生产实机部署未做，等确认后再用新链路推。 * HA stage 1: worktree_host + queued cross-host PR jobs --------- Co-authored-by: host <host@test.local>
2026-10-27 00:05:18 +08:00
1 parent 455513dd33
commit fc8e337d0f
@@ -42,6 +42,7 @@ import html
 import json
 import logging
 import os
+import socket
 import sqlite3
 import threading
 import time
@@ -61,8 +62,9 @@ from cloud.db import PostgresIntegrityError as _PgIntegrityError
 from cloud.db import PostgresOperationalError as _PgOperationalError
 from cloud.kb import KBStore
 from cloud.memory import MemoryStore
-from cloud.pr import (PrSkipped, PrStepError, create_task_pr,
-                      parse_git_remote_owner_repo)
+from cloud.pr import PrSkipped, PrStepError
+from cloud.pr_exec import (enqueue_pr_job, execute_task_pr,
+                           find_open_pr_job)
 from cloud.workers import (
    heartbeat_worker as _registry_heartbeat,
    list_workers as _registry_list,
@@ -103,7 +105,6 @@ from cloud.github_app import (
    record_installation_repos,
    remove_installation,
    remove_installation_repos,
-    resolve_app_token,
    save_app_config,
    set_fix_review_task_id,
 )
@@ -322,6 +323,9 @@ def migrate_tasks_table(conn):
        "goal": "TEXT",
        "verify_command": "TEXT",
        "goal_max_rounds": "INTEGER",
+        # HA 阶段 1：认领任务的 worker 所在主机名；/pr 据此判断
+        # worktree 在本机（同步跑）还是别机（排 pr 任务给该主机）。
+        "worktree_host": "TEXT",
    }
    for name, coltype in new_cols.items():
        if name not in cols:
@@ -456,6 +460,7 @@ def _task_to_dict(row):
        "goal": _row_get(row, "goal"),
        "verify_command": _row_get(row, "verify_command"),
        "goal_max_rounds": _row_get(row, "goal_max_rounds"),
+        "worktree_host": _row_get(row, "worktree_host"),
    }


@@ -1638,6 +1643,10 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
        成功时把 pr_url/pr_number 写回任务并记审计 pr_created。
        推送：成功时发 review-requested，落盘失败时发 merge-failed
        （均为 best-effort，不影响 PR 响应；跳过时不发）。
+        HA 阶段 1：任务的 worktree_host 与本机不同时，不直接跑，
+        而是排 pr 任务给该主机（返回 200 + pr_queued，同一任务
+        未完成的任务去重），由该主机上的 local worker 执行；
+        worktree 在本机（或未记录）时同步跑，与旧行为一致。
        App-token：项目 repo_url 能解析出 github.com 仓库名且
        库里有该仓库的 App 安装记录时，现换 installation token
        走 App 路径（响应里 auth_via=app），否则走原来的 gh +
@@ -1660,51 +1669,36 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
                "status": task["status"],
            })
            return
-        conn = self._db()
-        try:
-            prow = conn.execute(
-                "SELECT auto_pr, repo_url FROM projects WHERE id = ?",
-                (task["project_id"],)).fetchone()
-        finally:
-            conn.close()
-        auto_pr = 0
-        repo_url = None
-        if prow is not None:
-            try:
-                auto_pr = prow["auto_pr"] or 0
-            except (KeyError, IndexError, TypeError):
-                auto_pr = 0
-            try:
-                repo_url = prow["repo_url"]
-            except (KeyError, IndexError, TypeError):
-                repo_url = None
-        app_token = None
-        auth_via = "pat"
-        repo_full_name = None
-        if repo_url:
-            parsed = parse_git_remote_owner_repo(repo_url)
-            if parsed:
-                repo_full_name = "%s/%s" % parsed
-        if repo_full_name:
+        # HA 阶段 1：worktree 在别机时不直接跑，排 pr 任务给该主机；
+        # 本机（或 worktree_host 未记录的老任务）走同步路。
+        worktree_host = task.get("worktree_host")
+        if worktree_host and worktree_host != socket.gethostname():
            conn = self._db()
            try:
-                app_token = resolve_app_token(
-                    conn, repo_full_name,
-                    http_client=getattr(
-                        self.server, "pr_app_token_client", None))
+                existing = find_open_pr_job(conn, task_id)
+                if existing is not None:
+                    job_id = existing["id"]
+                else:
+                    job_id = enqueue_pr_job(
+                        conn, task_id, task["project_id"], worktree_host)
            finally:
                conn.close()
-            if app_token:
-                auth_via = "app"
+            self._send_json(200, {
+                "task_id": task_id, "status": task["status"],
+                "pr_queued": True, "pr_job_id": job_id,
+                "worktree_host": worktree_host,
+            })
+            return
        try:
-            result = create_task_pr(
-                task_id, auto_pr,
+            result = execute_task_pr(
+                self.server.db_path, task_id, user_id,
                worktrees_root=getattr(
                    self.server, "host_worktrees_dir", None),
                git_runner=getattr(self.server, "pr_git_runner", None),
                gh_runner=getattr(self.server, "pr_gh_runner", None),
                gh_which=getattr(self.server, "pr_gh_which", None),
-                app_token=app_token,
+                app_token_client=getattr(
+                    self.server, "pr_app_token_client", None),
                github_api=getattr(self.server, "pr_github_api", None))
        except PrSkipped as exc:
            self._send_json(200, {
@@ -1713,41 +1707,24 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
            })
            return
        except PrStepError as exc:
-            self._notify_pr_event(
-                task["project_id"], "merge-failed",
-                {"task_id": task_id, "step": exc.step,
-                 "error": exc.message})
+            # merge-failed 事件已在 execute_task_pr 内发出，这里只映射响应。
            self._send_json(502, {
                "error": exc.message, "step": exc.step,
                "task_id": task_id, "status": task["status"],
            })
            return
-        now = time.time()
        conn = self._db()
        try:
-            conn.execute(
-                "UPDATE tasks SET pr_url = ?, pr_number = ?,"
-                " updated_at = ? WHERE id = ?",
-                (result["pr_url"], result["pr_number"], now, task_id),
-            )
-            conn.commit()
            task = _task_to_dict(
                conn.execute(
                    "SELECT * FROM tasks WHERE id = ?",
                    (task_id,)).fetchone())
        finally:
            conn.close()
-        with _auth_store(self.server.db_path) as store:
-            store.audit(user_id, task["project_id"], "pr_created",
-                        result["pr_url"])
-        self._notify_pr_event(
-            task["project_id"], "review-requested",
-            {"task_id": task_id, "pr_url": result["pr_url"],
-             "pr_number": result["pr_number"]})
        self._send_json(200, dict(task, pr_url=result["pr_url"],
                                  pr_number=result["pr_number"],
                                  branch=result["branch"],
-                                  auth_via=auth_via))
+                                  auth_via=result["auth_via"]))

    def _heartbeat_task(self, user_id, task_id):
        row = self._fetch_task(task_id)