Files
LangBot/skills/scripts/e2e/langrag-kb-retrieve.mjs
T
Junyan Chin e9dd584792 feat: MCP server + in-repo skills (agent-friendly platform) (#2269)
* feat(api): support global API key from config.yaml (api.global_api_key)

Accept a config-defined global API key anywhere a web-UI key is accepted
(X-API-Key / Bearer), with no login session and no DB record. Useful for
automated deployments and AI agents (HTTP API + MCP). Defaults to empty
(disabled); does not require the lbk_ prefix.

- templates/config.yaml: add api.global_api_key with security notes
- service/apikey.py: verify_api_key checks global key first (constant-time)
- docs/API_KEY_AUTH.md: document the global key + security guidance
- tests: cover global-key match, prefix-free, fallback-to-db, disabled

* feat(mcp): expose LangBot management as an MCP server at /mcp

Add an MCP (Model Context Protocol) server so external AI agents can manage a
LangBot instance. Reuses the same API-key auth as the HTTP API (including the
config.yaml global API key).

- pkg/api/mcp/server.py: FastMCP server wrapping the service layer; 21 curated
  tools across system/bots/pipelines/models/knowledge/mcp-servers/skills
- pkg/api/mcp/mount.py: ASGI dispatcher fronting Quart; authenticates /mcp
  requests with an API key, runs the streamable-HTTP session manager lifespan
- controller/main.py: serve the wrapped ASGI app via hypercorn (was run_task)
- web: new 'MCP' tab in the API integration dialog showing endpoint, auth, and
  client config; i18n for 8 locales
- tests/manual/mcp_smoke.py: e2e check (401 unauth, list tools, call tools)

Tool surface is intentionally curated (not all ~25 route groups) to keep the
agent surface small, safe, and maintainable. Extend deliberately.

* feat(skills): add in-repo skills/ as the single source of truth

Migrate the agent skills + QA/e2e test harness from the (now archived)
langbot-app/langbot-skills repo into LangBot/skills/, and add four new skills.

Migrated:
- langbot-plugin-dev, langbot-testing (e2e), langbot-env-setup,
  langbot-skills-maintenance, langbot-eba-adapter-dev
- the bin/lbs CLI (src/, test/, scripts/, schemas/, qa-agent-docs/)

New:
- langbot-dev      core backend + web development
- langbot-deploy   Docker/K8s deployment + config.yaml + global API key
- langbot-mcp-ops  operating the LangBot MCP server (/mcp)
- langbot-space-ops operating the Space marketplace MCP server

- src/cli.ts repoRoot(): recognize the skills assets root (skills.index.json +
  bin/lbs) so the CLI works when nested inside the LangBot repo
- README.md: unified skill catalog; skills.index.json regenerated

Parity with source verified: bin/lbs validate + node test suite match the
source repo (only the uncommitted .lbpkg build-artifact fixture differs).

* docs(agents): document agent-facing surfaces + API/MCP/skills sync rule

* docs(readme): add 'Built for AI Agents' section across all locales

Highlight MCP server, in-repo skills (single source of truth), AGENTS.md
sync rule, and llms.txt. Cross-link LangBot Space MCP marketplace.

* style(mcp): fix ruff format + prettier lint in MCP server and API panel

* style(web): prettier format MCP i18n locale entries

* docs(skills): note MCP instance control in dev/testing skills

All development-guidance skills now point to the LangBot instance MCP
server (/mcp) and the Space marketplace MCP server, reusing API keys.
2026-06-20 15:14:47 +08:00

135 lines
4.8 KiB
JavaScript

#!/usr/bin/env node
import {
bodyText,
createBrowser,
ensureEvidence,
evidencePaths,
exitCode,
isLoginUrl,
localIsoWithOffset,
safeScreenshot,
writeResult,
} from "./lib/langbot-e2e.mjs";
const caseId = process.env.LBS_CASE_ID || "langrag-kb-retrieve";
const paths = evidencePaths(caseId);
await ensureEvidence(paths);
const startedAt = new Date();
const frontendUrl = process.env.LANGBOT_FRONTEND_URL || "";
const backendUrl = process.env.LANGBOT_BACKEND_URL || "";
const kbUuid = process.env.LANGBOT_LOCAL_AGENT_RAG_KB_UUID || process.env.LANGBOT_RAG_KB_UUID || "";
const query = process.env.LANGBOT_E2E_RETRIEVE_QUERY || "What is the local agent runner retrieval sentinel?";
const expectedText = process.env.LANGBOT_E2E_EXPECTED_TEXT || "azalea-cobalt-7421";
let browser;
const result = {
source: "automation",
case_id: caseId,
run_id: paths.runId,
started_at: startedAt.toISOString(),
started_at_local: localIsoWithOffset(startedAt),
finished_at: "",
finished_at_local: "",
status: "fail",
reason: "",
url: "",
kb_uuid: kbUuid,
query,
expected_text: expectedText,
evidence: {
console_log: paths.consoleLog,
network_log: paths.networkLog,
screenshot: paths.screenshot,
automation_result_json: paths.automationResultJson,
result_json: paths.resultJson,
},
evidence_collected: ["ui", "screenshot", "console", "network", "api_diagnostic"],
};
try {
if (!frontendUrl) throw new Error("LANGBOT_FRONTEND_URL is not configured.");
if (!backendUrl) throw new Error("LANGBOT_BACKEND_URL is not configured.");
if (!kbUuid) throw new Error("LANGBOT_LOCAL_AGENT_RAG_KB_UUID or LANGBOT_RAG_KB_UUID is required.");
browser = await createBrowser(paths);
const { page } = browser;
await page.goto(`${frontendUrl.replace(/\/$/, "")}/home/knowledge`, { waitUntil: "domcontentloaded" });
await page.waitForLoadState("networkidle", { timeout: 10_000 }).catch(() => {});
result.url = page.url();
const text = await bodyText(page);
if (isLoginUrl(page.url()) || /登录|Login|Sign in/i.test(text)) {
result.status = "blocked";
result.reason = "Browser profile is not authenticated for LANGBOT_FRONTEND_URL.";
} else if (!/Knowledge|知识库|qa-local-agent-rag/i.test(text)) {
result.status = "fail";
result.reason = "Knowledge page opened, but no Knowledge UI signal or QA KB name was visible.";
} else {
const retrieve = await page.evaluate(async ({ backendUrl, kbUuid, query }) => {
const token = localStorage.getItem("token");
if (!token) {
return { status: "blocked", authenticated: false, reason: "Browser profile has no localStorage token." };
}
const response = await fetch(`${backendUrl}/api/v1/knowledge/bases/${encodeURIComponent(kbUuid)}/retrieve`, {
method: "POST",
headers: {
Authorization: `Bearer ${token}`,
"Content-Type": "application/json",
},
body: JSON.stringify({ query }),
});
const json = await response.json().catch(() => ({}));
return {
status: response.status >= 400 ? "fail" : "ready",
authenticated: true,
http_status: response.status,
code: json.code ?? null,
msg: json.msg || "",
results: json.data?.results || [],
};
}, { backendUrl, kbUuid, query });
result.retrieve = {
...retrieve,
results: Array.isArray(retrieve.results)
? retrieve.results.map((item) => ({
score: item.score ?? item.distance ?? null,
text: String(item.text || item.content || "").slice(0, 500),
metadata: item.metadata || {},
}))
: [],
};
const resultText = JSON.stringify(result.retrieve.results || []);
if (retrieve.status === "blocked") {
result.status = "blocked";
result.reason = retrieve.reason || "Retrieve API blocked.";
} else if (retrieve.status === "fail") {
result.status = "fail";
result.reason = retrieve.msg || "Retrieve API failed.";
} else if (!resultText.includes(expectedText)) {
result.status = "fail";
result.reason = `Retrieve results did not contain expected text: ${expectedText}`;
} else {
result.status = "pass";
result.reason = `Knowledge retrieve returned expected sentinel: ${expectedText}`;
}
}
await safeScreenshot(page, paths.screenshot);
} catch (error) {
result.status = /Playwright is not installed|not configured|required/.test(error.message) ? "env_issue" : "fail";
result.reason = error.message;
} finally {
if (browser) await browser.close().catch(() => {});
const finishedAt = new Date();
result.finished_at = finishedAt.toISOString();
result.finished_at_local = localIsoWithOffset(finishedAt);
await writeResult(paths, result);
console.log(JSON.stringify(result, null, 2));
}
process.exit(exitCode(result.status));