Merge pull request #122 from pikasTech/fix/code-queue-health-remote-compact
fix: compact remote code queue health
This commit is contained in:
Lyon
@@ -150,7 +150,7 @@ bun scripts/cli.ts ssh D601 glob --root /home/ubuntu/pikapython --pattern '**/*-
|
||||
|
||||
`--main-server-ip` 是一个全局前缀，必须放在需要透传的命令同一次调用中，例如 `bun scripts/cli.ts --main-server-ip 74.48.78.17 debug health`。默认传输是公网 frontend：本地 CLI 读取本仓库 `config.json` 中的 frontend 登录账号密码，登录 `http://<ip>:<frontendPort>/` 获取 HttpOnly session cookie，然后通过 frontend 的 `/api/*` 同源代理访问 backend-core 内网 API；因此计算节点只需要能访问公网 frontend，不需要主 server SSH key，也不需要打开 backend-core REST API 或 PostgreSQL 端口。
|
||||
|
||||
默认 frontend 传输支持 `debug health`、`debug dispatch`、`debug task`、`artifact-registry status|health`、`ci publish-user-service --dry-run`、`microservice list/status/health/diagnostics/tunnel-self-test/proxy`、`decision upload/list/show/health`、`decision requirement list/upsert`、`decision diary import/list/history/months/show/edit/upsert`、`codex task <taskId>`、`codex tasks`、`codex output <taskId>`、`codex judge <taskId> --attempt N` 和 `ssh <PROVIDER_ID> <remote-command>`。运行中纠偏 `codex steer` 属于 active run write control，应在主 server 本机 CLI 或显式 SSH 传输上执行，避免公网 frontend 透传限制 stdin/body 审计语义。其中 `ssh` 的 remote frontend 传输使用 `host.ssh` dispatch 执行有界远端命令，适合 `ssh D601 hostname` 和 `ssh D601 skills` 这类自测；交互式登录 shell 仍应在主 server 本机 CLI 使用，或显式切换到旧 SSH 传输后在主 server 上执行。frontend 远程透传不会流式转发本地 stdin，因此 `ssh py < script.py`、`ssh apply-patch < patch.diff` 这类 stdin-backed helper 必须在主 server 本机运行，或显式切换到 `--main-server-transport ssh`。当 backend-core、database、provider-dispatch 或 provider-host-ssh 缺失时，这些 read-only 预检必须返回结构化 `runnerDisposition=infra-blocked` 和缺失通道列表，而不是裸 `No such container`。若确实需要旧行为，可使用 `--main-server-key <key>` 或 `--main-server-transport ssh`，这时 CLI 会通过 SSH 登录主 server 的 `--main-server-root` 目录执行同一个 `bun scripts/cli.ts <command>`。
|
||||
默认 frontend 传输支持 `debug health`、`debug dispatch`、`debug task`、`artifact-registry status|health`、`ci publish-user-service --dry-run`、`microservice list/status/health/diagnostics/tunnel-self-test/proxy`、`decision upload/list/show/health`、`decision requirement list/upsert`、`decision diary import/list/history/months/show/edit/upsert`、`codex task <taskId>`、`codex tasks`、`codex output <taskId>`、`codex judge <taskId> --attempt N` 和 `ssh <PROVIDER_ID> <remote-command>`。`microservice status/health/diagnostics` 经 frontend 远程传输时也复用本地 CLI 的默认 compact summary，`microservice health code-queue` 只有显式 `--raw` 或 `--full` 才返回完整健康 body。运行中纠偏 `codex steer` 属于 active run write control，应在主 server 本机 CLI 或显式 SSH 传输上执行，避免公网 frontend 透传限制 stdin/body 审计语义。其中 `ssh` 的 remote frontend 传输使用 `host.ssh` dispatch 执行有界远端命令，适合 `ssh D601 hostname` 和 `ssh D601 skills` 这类自测；交互式登录 shell 仍应在主 server 本机 CLI 使用，或显式切换到旧 SSH 传输后在主 server 上执行。frontend 远程透传不会流式转发本地 stdin，因此 `ssh py < script.py`、`ssh apply-patch < patch.diff` 这类 stdin-backed helper 必须在主 server 本机运行，或显式切换到 `--main-server-transport ssh`。当 backend-core、database、provider-dispatch 或 provider-host-ssh 缺失时，这些 read-only 预检必须返回结构化 `runnerDisposition=infra-blocked` 和缺失通道列表，而不是裸 `No such container`。若确实需要旧行为，可使用 `--main-server-key <key>` 或 `--main-server-transport ssh`，这时 CLI 会通过 SSH 登录主 server 的 `--main-server-root` 目录执行同一个 `bun scripts/cli.ts <command>`。
|
||||
|
||||
计算节点可以用该入口测试自身的远程升级闭环，而不需要在计算节点公开 core REST API 或 database。标准顺序是：先运行 `bun scripts/cli.ts --main-server-ip 74.48.78.17 debug health` 确认主 server 看到当前 Provider 在线，且该 Provider labels 中 `unideskCapabilities` 包含 `host.ssh`、`hostSshConfigured=true`、`hostSshKeyPresent=true`；再运行 `bun scripts/cli.ts --main-server-ip 74.48.78.17 debug dispatch <PROVIDER_ID> provider.upgrade --mode schedule --wait-ms 15000` 触发真实 `provider.upgrade`；随后再次运行 `debug health` 确认节点重新上线；最后运行 `bun scripts/cli.ts --main-server-ip 74.48.78.17 debug dispatch <PROVIDER_ID> host.ssh --wait-ms 15000` 和 `bun scripts/cli.ts --main-server-ip 74.48.78.17 ssh <PROVIDER_ID> hostname` 验证 SSH 透传能力。provider-gateway 新部署或升级后没有完成这组 remote CLI 自测，不能视为交付完成。
|
||||
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { summarizeMicroserviceHealthResponse } from "./src/microservices";
|
||||
import { summarizeRemoteMicroserviceResponse } from "./src/remote";
|
||||
|
||||
type JsonRecord = Record<string, unknown>;
|
||||
|
||||
@@ -102,6 +103,8 @@ const fixture = largeCodeQueueHealth();
|
||||
const compact = asRecord(summarizeMicroserviceHealthResponse(fixture, ["health", "code-queue"], "code-queue"));
|
||||
const raw = summarizeMicroserviceHealthResponse(fixture, ["health", "code-queue", "--raw"], "code-queue");
|
||||
const full = summarizeMicroserviceHealthResponse(fixture, ["health", "code-queue", "--full"], "code-queue");
|
||||
const remoteCompact = asRecord(summarizeRemoteMicroserviceResponse("health", "code-queue", fixture, ["microservice", "health", "code-queue"]));
|
||||
const remoteRaw = summarizeRemoteMicroserviceResponse("health", "code-queue", fixture, ["microservice", "health", "code-queue", "--raw"]);
|
||||
const unhealthyWrapper = asRecord(summarizeMicroserviceHealthResponse({
|
||||
ok: false,
|
||||
status: 503,
|
||||
@@ -137,6 +140,8 @@ assertCondition(liveness.effectiveLiveness === "live" && liveness.splitBrainLive
|
||||
assertCondition(String(liveness.interpretation).includes("continue supervision"), "compact liveness includes commander interpretation", liveness);
|
||||
assertCondition(typeof outputPolicy.rawCommand === "string" && String(outputPolicy.rawCommand).includes("--raw"), "compact output exposes raw drill-down command", outputPolicy);
|
||||
assertCondition(raw === fixture && full === fixture, "--raw/--full must preserve full health access", { rawSame: raw === fixture, fullSame: full === fixture });
|
||||
assertCondition(!("body" in remoteCompact) && asRecord(remoteCompact.queue).runningCount === 5, "remote frontend health must reuse compact code-queue summary by default", remoteCompact);
|
||||
assertCondition(remoteRaw === fixture, "remote frontend health --raw must preserve full diagnostics", { remoteRawSame: remoteRaw === fixture });
|
||||
assertCondition(unhealthyWrapper.ok === false && unhealthyWrapper.reason === "health body ok=false", "unhealthy wrapper keeps probe failure", unhealthyWrapper);
|
||||
assertCondition(unhealthyQueue.runningCount === 5 && unhealthyLiveness.effectiveLiveness === "live", "unhealthy wrapper still surfaces upstream queue liveness", { unhealthyQueue, unhealthyLiveness });
|
||||
|
||||
@@ -146,6 +151,7 @@ console.log(JSON.stringify({
|
||||
"default code-queue health output is compact and omits raw body/queue dumps",
|
||||
"critical ok/status/service/running/heartbeat/liveness fields remain visible",
|
||||
"unhealthy backend health wrapper still surfaces upstream code-queue liveness",
|
||||
"remote frontend microservice health uses the same compact/raw policy",
|
||||
"--raw and --full return the original health response for diagnostics",
|
||||
],
|
||||
compactChars: compactBody.length,
|
||||
|
||||
+10
-2
@@ -1,7 +1,7 @@
|
||||
import { spawn } from "node:child_process";
|
||||
import { type UniDeskConfig } from "./config";
|
||||
import { type DebugDispatchCommand, isDebugDispatchCommand } from "./debug";
|
||||
import { summarizeMicroserviceProxyResponse } from "./microservices";
|
||||
import { summarizeMicroserviceHealthResponse, summarizeMicroserviceObservation, summarizeMicroserviceProxyResponse } from "./microservices";
|
||||
import { parseNetworkPerfOptions, runNetworkPerf } from "./network-perf";
|
||||
import { isSshSkillDiscoveryArgs, parseSshArgs } from "./ssh";
|
||||
import { codexJudgeQueryAsync, codexOutputQueryAsync, codexPrPreflightQueryAsync, codexTaskQueryAsync, codexTasksQueryAsync } from "./code-queue";
|
||||
@@ -618,6 +618,13 @@ async function remoteDebugTask(session: FrontendSession, args: string[]): Promis
|
||||
return { transport: "frontend", tasksResponse, taskId, task: task ?? null };
|
||||
}
|
||||
|
||||
export function summarizeRemoteMicroserviceResponse(action: string, id: string, response: unknown, args: string[]): unknown {
|
||||
const optionArgs = args.slice(3);
|
||||
if (action === "health") return summarizeMicroserviceHealthResponse(response, optionArgs, id);
|
||||
if (action === "status" || action === "diagnostics") return summarizeMicroserviceObservation(action, id, response, optionArgs);
|
||||
return response;
|
||||
}
|
||||
|
||||
async function remoteMicroservice(session: FrontendSession, args: string[]): Promise<unknown> {
|
||||
const action = args[1] ?? "list";
|
||||
const id = args[2];
|
||||
@@ -626,9 +633,10 @@ async function remoteMicroservice(session: FrontendSession, args: string[]): Pro
|
||||
return { transport: "frontend", response: await frontendJson(session, "/api/microservices", undefined, 12_000) };
|
||||
}
|
||||
if ((action === "status" || action === "health" || action === "diagnostics" || action === "tunnel-self-test") && id !== undefined) {
|
||||
const response = await frontendJson(session, `/api/microservices/${encodeURIComponent(id)}/${action}`, undefined, 18_000);
|
||||
return {
|
||||
transport: "frontend",
|
||||
response: await frontendJson(session, `/api/microservices/${encodeURIComponent(id)}/${action}`, undefined, 18_000),
|
||||
response: summarizeRemoteMicroserviceResponse(action, id, response, args),
|
||||
};
|
||||
}
|
||||
if (action === "proxy" && id !== undefined && path !== undefined && path.startsWith("/")) {
|
||||
|
||||
Reference in New Issue
Block a user