Skip to content

code-yeongyu/oh-my-openagent / .agents/skills/codex-qa

codex-qa

Verified

QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex. The first-party method drives the real `codex app-server` against an isolated CODEX_HOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by asserting hook/started + hook/completed notifications. Also: isolated install verification, per-component hook probes, a tmux TUI smoke, and runtime log observation (RUST_LOG / logs SQLite / /debug-config). Ships tested helper scripts each with a --self-test. Use whenever someone changes anything under packages/omo-codex or wants to QA, smoke-test, verify, or debug the Codex plugin, its hooks/components, the installer/config.toml, the app-server flow, or the Codex TUI. Triggers: codex qa, qa codex, codex-qa, test codex plugin, verify codex hook, codex app-server, lazycodex qa, isolated CODEX_HOME, prove codex hook fired, codex tui test.

FileKindSize
SKILL.mdskill md7.6 KB
references/app-server.mdmarkdown3.0 KB
references/components-hooks.mdmarkdown2.7 KB
references/docker-qa.mdmarkdown2.6 KB
references/install-verify.mdmarkdown2.6 KB
references/isolation.mdmarkdown2.5 KB
references/logging-debug.mdmarkdown2.6 KB
scripts/app-server-drive.shexecutablescript3.1 KB
scripts/hook-unit-probe.shexecutablescript3.0 KB
scripts/install-verify.shexecutablescript2.5 KB
scripts/lib/app-server-client.mjsscript6.3 KB
scripts/lib/app-server-client.test.jsscript1.9 KB
scripts/lib/common.shexecutablescript7.1 KB
scripts/lib/mock-model.mjsscript2.1 KB
scripts/lsp-e2e.shexecutablescript150.9 KB
scripts/tui-smoke.shexecutablescript2.9 KB

scripts/lib/mock-model.mjs

View on GitHub
// mock-model.mjs - a local OpenAI Responses-API SSE server for codex-qa.
//
// WHY: codex talks to a model over HTTP. Pointing a custom model_provider at
// this server lets QA drive a REAL codex turn end-to-end with NO real API
// call, no key, and no network egress - so we test OUR plugin, never OpenAI.
//
// It answers POST .../responses with the 3-event Responses stream codex needs
// for one assistant message (response.created -> output_item.done ->
// response.completed). Each POST gets a fresh response, so a turn that makes
// several model requests (session-start probe + the turn itself) is covered.
//
// Env:
//   MOCK_PORT  TCP port to bind (default 0 = OS-assigned; the chosen port is
//              printed as "MOCK_LISTENING <port>" on stdout so the caller can
//              read it back).
//   MOCK_TEXT  assistant message text (default below).
import { createServer } from "node:http"

const TEXT = process.env.MOCK_TEXT || "Hello from the codex-qa mock model."

const server = createServer((req, res) => {
  if (req.method === "POST" && req.url && req.url.endsWith("/responses")) {
    let body = ""
    req.on("data", (c) => (body += c))
    req.on("end", () => {
      res.writeHead(200, {
        "Content-Type": "text/event-stream",
        "Cache-Control": "no-cache",
        Connection: "keep-alive",
      })
      const sse = (obj) => res.write(`event: ${obj.type}\ndata: ${JSON.stringify(obj)}\n\n`)
      sse({ type: "response.created", response: { id: "resp-1" } })
      sse({
        type: "response.output_item.done",
        item: {
          type: "message",
          role: "assistant",
          id: "msg-1",
          content: [{ type: "output_text", text: TEXT }],
        },
      })
      sse({
        type: "response.completed",
        response: { id: "resp-1", usage: { input_tokens: 0, output_tokens: 0, total_tokens: 0 } },
      })
      res.end()
    })
    return
  }
  res.writeHead(404).end()
})

const port = Number(process.env.MOCK_PORT || 0)
server.listen(port, "127.0.0.1", () => {
  process.stdout.write(`MOCK_LISTENING ${server.address().port}\n`)
})
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 321kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 321kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 321kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 197kUpdated Claude CodeCodexVerifiedInstall